diff --git "a/train.log" "b/train.log"
--- "a/train.log"
+++ "b/train.log"
@@ -49466,3 +49466,4240 @@ Eval results for step (55000 / 100000 | Eval Loss: 1.0243054628372192 | Eval wer
 
 60%|██████    | 3/5 [02:23<01:11, 35.62s/it]
 
 80%|████████  | 4/5 [02:24<00:21, 21.81s/it]
 
100%|██████████| 5/5 [02:24<00:00, 14.15s/it]
100%|██████████| 5/5 [02:24<00:00, 29.00s/it]
+
+
+
Evaluating eval...:   0%|          | 0/1900 [00:00<?, ?it/s]
+
+
Evaluating eval...:   0%|          | 1/1900 [00:03<1:47:45,  3.40s/it]
+
+
Evaluating eval...:   0%|          | 2/1900 [00:04<1:07:14,  2.13s/it]
+
+
Evaluating eval...:   0%|          | 3/1900 [00:05<54:53,  1.74s/it]  
+
+
Evaluating eval...:   0%|          | 4/1900 [00:07<48:37,  1.54s/it]
+
+
Evaluating eval...:   0%|          | 5/1900 [00:08<44:54,  1.42s/it]
+
+
Evaluating eval...:   0%|          | 6/1900 [00:09<42:09,  1.34s/it]
+
+
Evaluating eval...:   0%|          | 7/1900 [00:10<40:53,  1.30s/it]
+
+
Evaluating eval...:   0%|          | 8/1900 [00:11<39:57,  1.27s/it]
+
+
Evaluating eval...:   0%|          | 9/1900 [00:13<38:54,  1.23s/it]
+
+
Evaluating eval...:   1%|          | 10/1900 [00:14<38:38,  1.23s/it]
+
+
Evaluating eval...:   1%|          | 11/1900 [00:15<38:33,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 12/1900 [00:16<38:09,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 13/1900 [00:17<38:01,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 14/1900 [00:19<37:45,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 15/1900 [00:20<37:52,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 16/1900 [00:21<37:44,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 17/1900 [00:22<37:37,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 18/1900 [00:23<37:44,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 19/1900 [00:25<37:07,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 20/1900 [00:26<37:09,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 21/1900 [00:27<37:27,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 22/1900 [00:28<37:17,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 23/1900 [00:29<36:54,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 24/1900 [00:31<37:26,  1.20s/it]
+
+
Evaluating eval...:   1%|▏         | 25/1900 [00:32<37:06,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 26/1900 [00:33<36:46,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 27/1900 [00:34<37:17,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 28/1900 [00:35<36:58,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 29/1900 [00:36<36:52,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 30/1900 [00:38<36:54,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 31/1900 [00:39<36:52,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 32/1900 [00:40<37:27,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 33/1900 [00:41<37:40,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 34/1900 [00:43<38:04,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 35/1900 [00:44<38:17,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 36/1900 [00:45<38:13,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 37/1900 [00:46<38:03,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 38/1900 [00:47<37:31,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 39/1900 [00:49<37:29,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 40/1900 [00:50<37:15,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 41/1900 [00:51<36:52,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 42/1900 [00:52<37:21,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 43/1900 [00:53<37:11,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 44/1900 [00:55<37:13,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 45/1900 [00:56<36:39,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 46/1900 [00:57<36:27,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 47/1900 [00:58<36:07,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 48/1900 [00:59<36:00,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 49/1900 [01:00<36:01,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 50/1900 [01:02<36:37,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 51/1900 [01:03<36:38,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 52/1900 [01:04<36:24,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 53/1900 [01:05<36:11,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 54/1900 [01:06<36:28,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 55/1900 [01:08<37:06,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 56/1900 [01:09<37:07,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 57/1900 [01:10<37:04,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 58/1900 [01:11<37:12,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 59/1900 [01:12<36:54,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 60/1900 [01:14<36:20,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 61/1900 [01:15<37:25,  1.22s/it]
+
+
Evaluating eval...:   3%|▎         | 62/1900 [01:16<36:57,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 63/1900 [01:17<36:39,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 64/1900 [01:18<36:28,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 65/1900 [01:20<36:01,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 66/1900 [01:21<35:48,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 67/1900 [01:22<35:42,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 68/1900 [01:23<36:29,  1.20s/it]
+
+
Evaluating eval...:   4%|▎         | 69/1900 [01:24<35:59,  1.18s/it]
+
+
Evaluating eval...:   4%|▎         | 70/1900 [01:26<36:31,  1.20s/it]
+
+
Evaluating eval...:   4%|▎         | 71/1900 [01:27<36:30,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 72/1900 [01:28<36:42,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 73/1900 [01:29<36:33,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 74/1900 [01:30<36:45,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 75/1900 [01:32<36:32,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 76/1900 [01:33<36:29,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 77/1900 [01:34<36:36,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 78/1900 [01:35<36:36,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 79/1900 [01:36<36:31,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 80/1900 [01:38<36:22,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 81/1900 [01:39<36:13,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 82/1900 [01:40<37:19,  1.23s/it]
+
+
Evaluating eval...:   4%|▍         | 83/1900 [01:41<38:21,  1.27s/it]
+
+
Evaluating eval...:   4%|▍         | 84/1900 [01:43<37:47,  1.25s/it]
+
+
Evaluating eval...:   4%|▍         | 85/1900 [01:44<37:14,  1.23s/it]
+
+
Evaluating eval...:   5%|▍         | 86/1900 [01:45<36:17,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 87/1900 [01:46<36:25,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 88/1900 [01:47<36:04,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 89/1900 [01:49<37:22,  1.24s/it]
+
+
Evaluating eval...:   5%|▍         | 90/1900 [01:50<36:54,  1.22s/it]
+
+
Evaluating eval...:   5%|▍         | 91/1900 [01:51<37:01,  1.23s/it]
+
+
Evaluating eval...:   5%|▍         | 92/1900 [01:52<36:30,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 93/1900 [01:53<36:25,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 94/1900 [01:55<35:49,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 95/1900 [01:56<35:32,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 96/1900 [01:57<36:23,  1.21s/it]
+
+
Evaluating eval...:   5%|▌         | 97/1900 [01:58<36:00,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 98/1900 [01:59<36:21,  1.21s/it]
+
+
Evaluating eval...:   5%|▌         | 99/1900 [02:01<36:03,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 100/1900 [02:02<36:07,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 101/1900 [02:03<36:56,  1.23s/it]
+
+
Evaluating eval...:   5%|▌         | 102/1900 [02:04<37:17,  1.24s/it]
+
+
Evaluating eval...:   5%|▌         | 103/1900 [02:06<36:43,  1.23s/it]
+
+
Evaluating eval...:   5%|▌         | 104/1900 [02:07<36:16,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 105/1900 [02:08<35:57,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 106/1900 [02:09<35:20,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 107/1900 [02:10<35:43,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 108/1900 [02:11<35:16,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 109/1900 [02:13<35:32,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 110/1900 [02:14<35:11,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 111/1900 [02:15<35:27,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 112/1900 [02:16<36:14,  1.22s/it]
+
+
Evaluating eval...:   6%|▌         | 113/1900 [02:17<35:52,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 114/1900 [02:19<35:17,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 115/1900 [02:20<35:10,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 116/1900 [02:21<34:47,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 117/1900 [02:22<34:54,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 118/1900 [02:23<35:29,  1.19s/it]
+
+
Evaluating eval...:   6%|▋         | 119/1900 [02:25<35:32,  1.20s/it]
+
+
Evaluating eval...:   6%|▋         | 120/1900 [02:26<35:50,  1.21s/it]
+
+
Evaluating eval...:   6%|▋         | 121/1900 [02:27<35:17,  1.19s/it]
+
+
Evaluating eval...:   6%|▋         | 122/1900 [02:28<35:14,  1.19s/it]
+
+
Evaluating eval...:   6%|▋         | 123/1900 [02:29<35:09,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 124/1900 [02:31<35:27,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 125/1900 [02:32<35:29,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 126/1900 [02:33<35:48,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 127/1900 [02:34<35:52,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 128/1900 [02:35<35:27,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 129/1900 [02:37<35:03,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 130/1900 [02:38<34:52,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 131/1900 [02:39<34:57,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 132/1900 [02:40<35:28,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 133/1900 [02:41<34:52,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 134/1900 [02:42<35:07,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 135/1900 [02:44<35:17,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 136/1900 [02:45<35:44,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 137/1900 [02:46<36:27,  1.24s/it]
+
+
Evaluating eval...:   7%|▋         | 138/1900 [02:47<36:14,  1.23s/it]
+
+
Evaluating eval...:   7%|▋         | 139/1900 [02:49<35:49,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 140/1900 [02:50<35:37,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 141/1900 [02:51<35:24,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 142/1900 [02:52<36:13,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 143/1900 [02:54<35:50,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 144/1900 [02:55<35:04,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 145/1900 [02:56<35:03,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 146/1900 [02:57<34:45,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 147/1900 [02:58<35:10,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 148/1900 [02:59<34:40,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 149/1900 [03:01<34:46,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 150/1900 [03:02<35:55,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 151/1900 [03:03<35:54,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 152/1900 [03:04<35:40,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 153/1900 [03:06<35:51,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 154/1900 [03:07<35:40,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 155/1900 [03:08<35:16,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 156/1900 [03:09<35:14,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 157/1900 [03:11<36:19,  1.25s/it]
+
+
Evaluating eval...:   8%|▊         | 158/1900 [03:12<35:56,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 159/1900 [03:13<35:05,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 160/1900 [03:14<34:56,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 161/1900 [03:15<35:32,  1.23s/it]
+
+
Evaluating eval...:   9%|▊         | 162/1900 [03:17<34:55,  1.21s/it]
+
+
Evaluating eval...:   9%|▊         | 163/1900 [03:18<34:20,  1.19s/it]
+
+
Evaluating eval...:   9%|▊         | 164/1900 [03:19<34:30,  1.19s/it]
+
+
Evaluating eval...:   9%|▊         | 165/1900 [03:20<34:30,  1.19s/it]
+
+
Evaluating eval...:   9%|▊         | 166/1900 [03:21<34:20,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 167/1900 [03:23<35:11,  1.22s/it]
+
+
Evaluating eval...:   9%|▉         | 168/1900 [03:24<34:34,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 169/1900 [03:25<34:13,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 170/1900 [03:26<34:08,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 171/1900 [03:27<34:07,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 172/1900 [03:29<34:30,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 173/1900 [03:30<34:29,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 174/1900 [03:31<34:49,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 175/1900 [03:32<34:14,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 176/1900 [03:33<33:46,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 177/1900 [03:35<35:26,  1.23s/it]
+
+
Evaluating eval...:   9%|▉         | 178/1900 [03:36<35:22,  1.23s/it]
+
+
Evaluating eval...:   9%|▉         | 179/1900 [03:37<34:52,  1.22s/it]
+
+
Evaluating eval...:   9%|▉         | 180/1900 [03:38<34:38,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 181/1900 [03:39<34:16,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 182/1900 [03:41<34:56,  1.22s/it]
+
+
Evaluating eval...:  10%|▉         | 183/1900 [03:42<34:48,  1.22s/it]
+
+
Evaluating eval...:  10%|▉         | 184/1900 [03:43<34:21,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 185/1900 [03:44<34:14,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 186/1900 [03:45<33:50,  1.18s/it]
+
+
Evaluating eval...:  10%|▉         | 187/1900 [03:47<33:29,  1.17s/it]
+
+
Evaluating eval...:  10%|▉         | 188/1900 [03:48<33:45,  1.18s/it]
+
+
Evaluating eval...:  10%|▉         | 189/1900 [03:49<33:31,  1.18s/it]
+
+
Evaluating eval...:  10%|█         | 190/1900 [03:50<33:31,  1.18s/it]
+
+
Evaluating eval...:  10%|█         | 191/1900 [03:51<33:22,  1.17s/it]
+
+
Evaluating eval...:  10%|█         | 192/1900 [03:53<34:21,  1.21s/it]
+
+
Evaluating eval...:  10%|█         | 193/1900 [03:54<35:39,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 194/1900 [03:55<35:19,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 195/1900 [03:56<35:13,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 196/1900 [03:58<34:49,  1.23s/it]
+
+
Evaluating eval...:  10%|█         | 197/1900 [03:59<35:30,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 198/1900 [04:00<35:25,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 199/1900 [04:01<34:43,  1.23s/it]
+
+
Evaluating eval...:  11%|█         | 200/1900 [04:02<34:07,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 201/1900 [04:04<33:38,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 202/1900 [04:05<33:14,  1.17s/it]
+
+
Evaluating eval...:  11%|█         | 203/1900 [04:06<33:38,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 204/1900 [04:07<33:32,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 205/1900 [04:08<33:30,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 206/1900 [04:09<33:30,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 207/1900 [04:11<34:03,  1.21s/it]
+
+
Evaluating eval...:  11%|█         | 208/1900 [04:12<33:35,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 209/1900 [04:13<33:26,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 210/1900 [04:14<33:11,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 211/1900 [04:15<33:18,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 212/1900 [04:17<33:15,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 213/1900 [04:18<33:59,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 214/1900 [04:19<34:04,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 215/1900 [04:20<33:52,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 216/1900 [04:21<33:47,  1.20s/it]
+
+
Evaluating eval...:  11%|█▏        | 217/1900 [04:23<33:47,  1.20s/it]
+
+
Evaluating eval...:  11%|█▏        | 218/1900 [04:24<34:04,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 219/1900 [04:25<33:53,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 220/1900 [04:26<34:10,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 221/1900 [04:28<33:57,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 222/1900 [04:29<33:38,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 223/1900 [04:30<33:06,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 224/1900 [04:31<32:47,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 225/1900 [04:32<32:41,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 226/1900 [04:33<32:55,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 227/1900 [04:35<32:46,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 228/1900 [04:36<33:22,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 229/1900 [04:37<32:51,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 230/1900 [04:38<32:55,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 231/1900 [04:39<33:00,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 232/1900 [04:40<32:41,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 233/1900 [04:42<32:40,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 234/1900 [04:43<32:43,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 235/1900 [04:44<32:45,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 236/1900 [04:45<33:15,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 237/1900 [04:46<33:35,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 238/1900 [04:48<33:43,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 239/1900 [04:49<34:50,  1.26s/it]
+
+
Evaluating eval...:  13%|█▎        | 240/1900 [04:50<34:00,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 241/1900 [04:51<33:30,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 242/1900 [04:53<33:25,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 243/1900 [04:54<32:57,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 244/1900 [04:55<32:49,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 245/1900 [04:56<33:15,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 246/1900 [04:57<33:15,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 247/1900 [04:59<33:03,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 248/1900 [05:00<33:06,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 249/1900 [05:01<32:41,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 250/1900 [05:02<33:13,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 251/1900 [05:03<33:14,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 252/1900 [05:05<32:49,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 253/1900 [05:06<33:24,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 254/1900 [05:07<33:12,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 255/1900 [05:08<33:03,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 256/1900 [05:09<32:44,  1.20s/it]
+
+
Evaluating eval...:  14%|█▎        | 257/1900 [05:11<32:18,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 258/1900 [05:12<31:58,  1.17s/it]
+
+
Evaluating eval...:  14%|█▎        | 259/1900 [05:13<32:02,  1.17s/it]
+
+
Evaluating eval...:  14%|█▎        | 260/1900 [05:14<32:11,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 261/1900 [05:15<32:13,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 262/1900 [05:16<32:00,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 263/1900 [05:18<32:12,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 264/1900 [05:19<32:01,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 265/1900 [05:20<32:21,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 266/1900 [05:21<32:15,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 267/1900 [05:22<32:39,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 268/1900 [05:24<32:28,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 269/1900 [05:25<32:22,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 270/1900 [05:26<32:06,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 271/1900 [05:27<31:43,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 272/1900 [05:28<32:06,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 273/1900 [05:29<32:22,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 274/1900 [05:31<32:24,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 275/1900 [05:32<32:26,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 276/1900 [05:33<32:49,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 277/1900 [05:34<32:34,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 278/1900 [05:36<32:18,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 279/1900 [05:37<32:47,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 280/1900 [05:38<32:47,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 281/1900 [05:39<32:45,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 282/1900 [05:40<32:47,  1.22s/it]
+
+
Evaluating eval...:  15%|█▍        | 283/1900 [05:42<32:20,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 284/1900 [05:43<32:20,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 285/1900 [05:44<31:57,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 286/1900 [05:45<32:28,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 287/1900 [05:46<32:17,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 288/1900 [05:48<33:50,  1.26s/it]
+
+
Evaluating eval...:  15%|█▌        | 289/1900 [05:49<33:13,  1.24s/it]
+
+
Evaluating eval...:  15%|█▌        | 290/1900 [05:50<32:41,  1.22s/it]
+
+
Evaluating eval...:  15%|█▌        | 291/1900 [05:51<32:18,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 292/1900 [05:53<32:21,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 293/1900 [05:54<31:54,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 294/1900 [05:55<31:38,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 295/1900 [05:56<31:44,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 296/1900 [05:57<32:05,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 297/1900 [05:58<32:19,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 298/1900 [06:00<32:33,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 299/1900 [06:01<32:00,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 300/1900 [06:02<32:10,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 301/1900 [06:03<32:28,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 302/1900 [06:05<32:05,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 303/1900 [06:06<31:46,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 304/1900 [06:07<31:22,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 305/1900 [06:08<31:27,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 306/1900 [06:09<31:23,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 307/1900 [06:10<31:18,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 308/1900 [06:12<31:17,  1.18s/it]
+
+
Evaluating eval...:  16%|█▋        | 309/1900 [06:13<31:18,  1.18s/it]
+
+
Evaluating eval...:  16%|█▋        | 310/1900 [06:14<31:36,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 311/1900 [06:15<31:46,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 312/1900 [06:16<31:44,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 313/1900 [06:18<31:30,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 314/1900 [06:19<31:22,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 315/1900 [06:20<31:34,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 316/1900 [06:21<31:18,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 317/1900 [06:22<31:42,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 318/1900 [06:24<31:23,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 319/1900 [06:25<31:39,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 320/1900 [06:26<31:36,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 321/1900 [06:27<31:07,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 322/1900 [06:28<31:09,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 323/1900 [06:29<31:13,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 324/1900 [06:31<30:45,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 325/1900 [06:32<30:44,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 326/1900 [06:33<30:40,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 327/1900 [06:34<30:37,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 328/1900 [06:35<31:01,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 329/1900 [06:36<30:38,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 330/1900 [06:38<31:07,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 331/1900 [06:39<32:02,  1.23s/it]
+
+
Evaluating eval...:  17%|█▋        | 332/1900 [06:40<31:57,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 333/1900 [06:41<31:54,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 334/1900 [06:43<31:33,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 335/1900 [06:44<31:03,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 336/1900 [06:45<31:08,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 337/1900 [06:46<31:12,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 338/1900 [06:47<31:37,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 339/1900 [06:49<31:45,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 340/1900 [06:50<31:24,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 341/1900 [06:51<31:29,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 342/1900 [06:52<31:03,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 343/1900 [06:53<30:47,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 344/1900 [06:55<30:59,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 345/1900 [06:56<31:02,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 346/1900 [06:57<30:54,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 347/1900 [06:58<30:56,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 348/1900 [06:59<30:30,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 349/1900 [07:00<30:18,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 350/1900 [07:02<30:30,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 351/1900 [07:03<31:06,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 352/1900 [07:04<31:11,  1.21s/it]
+
+
Evaluating eval...:  19%|█▊        | 353/1900 [07:05<31:46,  1.23s/it]
+
+
Evaluating eval...:  19%|█▊        | 354/1900 [07:07<31:28,  1.22s/it]
+
+
Evaluating eval...:  19%|█▊        | 355/1900 [07:08<31:55,  1.24s/it]
+
+
Evaluating eval...:  19%|█▊        | 356/1900 [07:09<31:56,  1.24s/it]
+
+
Evaluating eval...:  19%|█▉        | 357/1900 [07:10<31:21,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 358/1900 [07:12<31:42,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 359/1900 [07:13<31:15,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 360/1900 [07:14<31:12,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 361/1900 [07:15<30:41,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 362/1900 [07:16<31:28,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 363/1900 [07:18<31:06,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 364/1900 [07:19<30:41,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 365/1900 [07:20<30:29,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 366/1900 [07:21<30:10,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 367/1900 [07:22<30:29,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 368/1900 [07:24<31:29,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 369/1900 [07:25<31:16,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 370/1900 [07:26<30:53,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 371/1900 [07:27<30:47,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 372/1900 [07:28<30:24,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 373/1900 [07:30<30:13,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 374/1900 [07:31<29:54,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 375/1900 [07:32<29:41,  1.17s/it]
+
+
Evaluating eval...:  20%|█▉        | 376/1900 [07:33<29:55,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 377/1900 [07:34<30:31,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 378/1900 [07:36<30:39,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 379/1900 [07:37<30:22,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 380/1900 [07:38<30:25,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 381/1900 [07:39<30:25,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 382/1900 [07:40<30:42,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 383/1900 [07:42<30:14,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 384/1900 [07:43<30:02,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 385/1900 [07:44<29:55,  1.18s/it]
+
+
Evaluating eval...:  20%|██        | 386/1900 [07:45<30:06,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 387/1900 [07:46<30:08,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 388/1900 [07:48<30:03,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 389/1900 [07:49<30:05,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 390/1900 [07:50<29:57,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 391/1900 [07:51<30:04,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 392/1900 [07:52<29:46,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 393/1900 [07:53<29:31,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 394/1900 [07:55<29:36,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 395/1900 [07:56<29:22,  1.17s/it]
+
+
Evaluating eval...:  21%|██        | 396/1900 [07:57<30:02,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 397/1900 [07:58<30:08,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 398/1900 [07:59<29:45,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 399/1900 [08:01<30:04,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 400/1900 [08:02<30:08,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 401/1900 [08:03<30:03,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 402/1900 [08:04<29:44,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 403/1900 [08:05<30:09,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 404/1900 [08:07<30:11,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 405/1900 [08:08<30:12,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 406/1900 [08:09<29:58,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 407/1900 [08:10<29:48,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 408/1900 [08:11<30:09,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 409/1900 [08:13<30:08,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 410/1900 [08:14<30:11,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 411/1900 [08:15<30:11,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 412/1900 [08:16<29:40,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 413/1900 [08:18<29:59,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 414/1900 [08:19<29:45,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 415/1900 [08:20<29:14,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 416/1900 [08:21<28:52,  1.17s/it]
+
+
Evaluating eval...:  22%|██▏       | 417/1900 [08:22<29:28,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 418/1900 [08:23<29:14,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 419/1900 [08:25<28:59,  1.17s/it]
+
+
Evaluating eval...:  22%|██▏       | 420/1900 [08:26<29:41,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 421/1900 [08:27<29:41,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 422/1900 [08:28<29:26,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 423/1900 [08:29<30:01,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 424/1900 [08:31<30:05,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 425/1900 [08:32<29:49,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 426/1900 [08:33<30:05,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 427/1900 [08:34<29:49,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 428/1900 [08:35<29:15,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 429/1900 [08:37<29:28,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 430/1900 [08:38<28:58,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 431/1900 [08:39<29:06,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 432/1900 [08:40<29:57,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 433/1900 [08:42<29:42,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 434/1900 [08:43<30:24,  1.24s/it]
+
+
Evaluating eval...:  23%|██▎       | 435/1900 [08:44<29:42,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 436/1900 [08:45<29:40,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 437/1900 [08:46<29:02,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 438/1900 [08:48<28:48,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 439/1900 [08:49<29:03,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 440/1900 [08:50<28:55,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 441/1900 [08:51<28:47,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 442/1900 [08:52<28:30,  1.17s/it]
+
+
Evaluating eval...:  23%|██▎       | 443/1900 [08:53<28:45,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 444/1900 [08:55<28:48,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 445/1900 [08:56<29:01,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 446/1900 [08:57<29:02,  1.20s/it]
+
+
Evaluating eval...:  24%|██▎       | 447/1900 [08:58<28:39,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 448/1900 [08:59<28:26,  1.17s/it]
+
+
Evaluating eval...:  24%|██▎       | 449/1900 [09:01<28:23,  1.17s/it]
+
+
Evaluating eval...:  24%|██▎       | 450/1900 [09:02<28:25,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 451/1900 [09:03<28:46,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 452/1900 [09:04<28:28,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 453/1900 [09:05<29:03,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 454/1900 [09:07<29:30,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 455/1900 [09:08<29:31,  1.23s/it]
+
+
Evaluating eval...:  24%|██▍       | 456/1900 [09:09<29:26,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 457/1900 [09:10<29:21,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 458/1900 [09:12<29:06,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 459/1900 [09:13<28:32,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 460/1900 [09:14<28:22,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 461/1900 [09:15<28:41,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 462/1900 [09:16<28:28,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 463/1900 [09:17<28:28,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 464/1900 [09:19<28:40,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 465/1900 [09:20<28:37,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 466/1900 [09:21<28:11,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 467/1900 [09:22<28:12,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 468/1900 [09:23<28:17,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 469/1900 [09:25<28:17,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 470/1900 [09:26<28:15,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 471/1900 [09:27<28:14,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 472/1900 [09:28<28:53,  1.21s/it]
+
+
Evaluating eval...:  25%|██▍       | 473/1900 [09:29<28:31,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 474/1900 [09:31<28:22,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 475/1900 [09:32<28:15,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 476/1900 [09:33<28:02,  1.18s/it]
+
+
Evaluating eval...:  25%|██▌       | 477/1900 [09:34<28:30,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 478/1900 [09:35<28:30,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 479/1900 [09:37<28:48,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 480/1900 [09:38<28:33,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 481/1900 [09:39<29:20,  1.24s/it]
+
+
Evaluating eval...:  25%|██▌       | 482/1900 [09:40<28:42,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 483/1900 [09:41<28:28,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 484/1900 [09:43<28:51,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 485/1900 [09:44<28:28,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 486/1900 [09:45<28:02,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 487/1900 [09:46<27:52,  1.18s/it]
+
+
Evaluating eval...:  26%|██▌       | 488/1900 [09:47<28:15,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 489/1900 [09:49<28:10,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 490/1900 [09:50<27:58,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 491/1900 [09:51<28:02,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 492/1900 [09:52<28:27,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 493/1900 [09:54<28:58,  1.24s/it]
+
+
Evaluating eval...:  26%|██▌       | 494/1900 [09:55<28:33,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 495/1900 [09:56<28:17,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 496/1900 [09:57<28:23,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 497/1900 [09:58<28:39,  1.23s/it]
+
+
Evaluating eval...:  26%|██▌       | 498/1900 [10:00<28:45,  1.23s/it]
+
+
Evaluating eval...:  26%|██▋       | 499/1900 [10:01<28:30,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 500/1900 [10:02<28:20,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 501/1900 [10:03<28:27,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 502/1900 [10:04<28:29,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 503/1900 [10:06<28:49,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 504/1900 [10:07<29:25,  1.26s/it]
+
+
Evaluating eval...:  27%|██▋       | 505/1900 [10:08<29:29,  1.27s/it]
+
+
Evaluating eval...:  27%|██▋       | 506/1900 [10:10<28:49,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 507/1900 [10:11<28:20,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 508/1900 [10:12<28:31,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 509/1900 [10:13<28:45,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 510/1900 [10:14<28:24,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 511/1900 [10:16<27:56,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 512/1900 [10:17<27:40,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 513/1900 [10:18<27:20,  1.18s/it]
+
+
Evaluating eval...:  27%|██▋       | 514/1900 [10:19<27:15,  1.18s/it]
+
+
Evaluating eval...:  27%|██▋       | 515/1900 [10:20<27:55,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 516/1900 [10:22<27:55,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 517/1900 [10:23<27:33,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 518/1900 [10:24<28:05,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 519/1900 [10:25<28:13,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 520/1900 [10:26<27:43,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 521/1900 [10:28<27:57,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 522/1900 [10:29<27:51,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 523/1900 [10:30<27:55,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 524/1900 [10:31<27:55,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 525/1900 [10:32<27:44,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 526/1900 [10:34<27:34,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 527/1900 [10:35<27:57,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 528/1900 [10:36<27:52,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 529/1900 [10:37<27:58,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 530/1900 [10:39<27:40,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 531/1900 [10:40<27:28,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 532/1900 [10:41<27:58,  1.23s/it]
+
+
Evaluating eval...:  28%|██▊       | 533/1900 [10:42<27:35,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 534/1900 [10:43<27:42,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 535/1900 [10:45<27:19,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 536/1900 [10:46<27:10,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 537/1900 [10:47<27:10,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 538/1900 [10:48<27:16,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 539/1900 [10:49<27:19,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 540/1900 [10:51<27:21,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 541/1900 [10:52<26:58,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 542/1900 [10:53<27:22,  1.21s/it]
+
+
Evaluating eval...:  29%|██▊       | 543/1900 [10:54<26:54,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 544/1900 [10:55<26:47,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 545/1900 [10:57<27:37,  1.22s/it]
+
+
Evaluating eval...:  29%|██▊       | 546/1900 [10:58<27:22,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 547/1900 [10:59<27:21,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 548/1900 [11:00<27:40,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 549/1900 [11:02<27:36,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 550/1900 [11:03<27:46,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 551/1900 [11:04<27:32,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 552/1900 [11:05<27:49,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 553/1900 [11:06<27:35,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 554/1900 [11:08<27:04,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 555/1900 [11:09<26:52,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 556/1900 [11:10<26:48,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 557/1900 [11:11<26:29,  1.18s/it]
+
+
Evaluating eval...:  29%|██▉       | 558/1900 [11:12<26:41,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 559/1900 [11:14<26:27,  1.18s/it]
+
+
Evaluating eval...:  29%|██▉       | 560/1900 [11:15<26:55,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 561/1900 [11:16<26:40,  1.19s/it]
+
+
Evaluating eval...:  30%|██▉       | 562/1900 [11:17<26:50,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 563/1900 [11:18<27:12,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 564/1900 [11:20<27:46,  1.25s/it]
+
+
Evaluating eval...:  30%|██▉       | 565/1900 [11:21<27:37,  1.24s/it]
+
+
Evaluating eval...:  30%|██▉       | 566/1900 [11:22<27:40,  1.24s/it]
+
+
Evaluating eval...:  30%|██▉       | 567/1900 [11:23<27:31,  1.24s/it]
+
+
Evaluating eval...:  30%|██▉       | 568/1900 [11:25<27:44,  1.25s/it]
+
+
Evaluating eval...:  30%|██▉       | 569/1900 [11:26<27:50,  1.25s/it]
+
+
Evaluating eval...:  30%|███       | 570/1900 [11:27<28:38,  1.29s/it]
+
+
Evaluating eval...:  30%|███       | 571/1900 [11:29<27:38,  1.25s/it]
+
+
Evaluating eval...:  30%|███       | 572/1900 [11:30<27:14,  1.23s/it]
+
+
Evaluating eval...:  30%|███       | 573/1900 [11:31<26:51,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 574/1900 [11:32<26:41,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 575/1900 [11:33<26:29,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 576/1900 [11:34<26:27,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 577/1900 [11:36<26:23,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 578/1900 [11:37<26:27,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 579/1900 [11:38<26:32,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 580/1900 [11:39<26:22,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 581/1900 [11:40<26:06,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 582/1900 [11:43<33:21,  1.52s/it]
+
+
Evaluating eval...:  31%|███       | 583/1900 [11:44<30:58,  1.41s/it]
+
+
Evaluating eval...:  31%|███       | 584/1900 [11:45<29:17,  1.34s/it]
+
+
Evaluating eval...:  31%|███       | 585/1900 [11:46<28:16,  1.29s/it]
+
+
Evaluating eval...:  31%|███       | 586/1900 [11:47<28:15,  1.29s/it]
+
+
Evaluating eval...:  31%|███       | 587/1900 [11:49<27:26,  1.25s/it]
+
+
Evaluating eval...:  31%|███       | 588/1900 [11:50<26:39,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 589/1900 [11:51<26:36,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 590/1900 [11:52<26:31,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 591/1900 [11:53<26:16,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 592/1900 [11:55<26:22,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 593/1900 [11:56<26:12,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 594/1900 [11:57<26:22,  1.21s/it]
+
+
Evaluating eval...:  31%|███▏      | 595/1900 [11:58<25:59,  1.19s/it]
+
+
Evaluating eval...:  31%|███▏      | 596/1900 [11:59<26:16,  1.21s/it]
+
+
Evaluating eval...:  31%|███▏      | 597/1900 [12:01<26:25,  1.22s/it]
+
+
Evaluating eval...:  31%|███▏      | 598/1900 [12:02<26:15,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 599/1900 [12:03<26:16,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 600/1900 [12:04<26:24,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 601/1900 [12:06<26:09,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 602/1900 [12:07<25:45,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 603/1900 [12:08<25:54,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 604/1900 [12:09<25:50,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 605/1900 [12:10<25:53,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 606/1900 [12:11<26:00,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 607/1900 [12:13<25:35,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 608/1900 [12:14<26:09,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 609/1900 [12:15<26:21,  1.23s/it]
+
+
Evaluating eval...:  32%|███▏      | 610/1900 [12:16<25:58,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 611/1900 [12:17<25:38,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 612/1900 [12:19<26:00,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 613/1900 [12:20<25:46,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 614/1900 [12:21<26:26,  1.23s/it]
+
+
Evaluating eval...:  32%|███▏      | 615/1900 [12:22<26:02,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 616/1900 [12:24<25:44,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 617/1900 [12:25<25:26,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 618/1900 [12:26<25:14,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 619/1900 [12:27<25:38,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 620/1900 [12:28<25:20,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 621/1900 [12:30<25:26,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 622/1900 [12:31<25:34,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 623/1900 [12:32<25:50,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 624/1900 [12:33<26:04,  1.23s/it]
+
+
Evaluating eval...:  33%|███▎      | 625/1900 [12:34<26:06,  1.23s/it]
+
+
Evaluating eval...:  33%|███▎      | 626/1900 [12:36<25:35,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 627/1900 [12:37<25:14,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 628/1900 [12:38<25:04,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 629/1900 [12:39<25:26,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 630/1900 [12:40<25:22,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 631/1900 [12:42<25:48,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 632/1900 [12:43<25:27,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 633/1900 [12:44<25:05,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 634/1900 [12:45<24:41,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 635/1900 [12:46<24:40,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 636/1900 [12:47<25:02,  1.19s/it]
+
+
Evaluating eval...:  34%|███▎      | 637/1900 [12:49<25:11,  1.20s/it]
+
+
Evaluating eval...:  34%|███▎      | 638/1900 [12:50<25:32,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 639/1900 [12:51<25:52,  1.23s/it]
+
+
Evaluating eval...:  34%|███▎      | 640/1900 [12:52<25:46,  1.23s/it]
+
+
Evaluating eval...:  34%|███▎      | 641/1900 [12:54<25:36,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 642/1900 [12:55<25:22,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 643/1900 [12:56<25:40,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 644/1900 [12:57<25:37,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 645/1900 [12:59<25:29,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 646/1900 [13:00<25:55,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 647/1900 [13:01<25:28,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 648/1900 [13:02<25:09,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 649/1900 [13:03<25:13,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 650/1900 [13:05<25:17,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 651/1900 [13:06<25:17,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 652/1900 [13:07<24:59,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 653/1900 [13:08<24:39,  1.19s/it]
+
+
Evaluating eval...:  34%|███▍      | 654/1900 [13:09<24:55,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 655/1900 [13:11<24:49,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 656/1900 [13:12<24:46,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 657/1900 [13:13<24:36,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 658/1900 [13:14<25:00,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 659/1900 [13:15<24:56,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 660/1900 [13:17<24:36,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 661/1900 [13:18<24:37,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 662/1900 [13:19<24:58,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 663/1900 [13:20<24:51,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 664/1900 [13:21<24:51,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 665/1900 [13:23<24:44,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 666/1900 [13:24<24:41,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 667/1900 [13:25<25:41,  1.25s/it]
+
+
Evaluating eval...:  35%|███▌      | 668/1900 [13:26<25:08,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 669/1900 [13:27<24:52,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 670/1900 [13:29<24:57,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 671/1900 [13:30<24:57,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 672/1900 [13:31<24:48,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 673/1900 [13:32<24:34,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 674/1900 [13:34<24:37,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 675/1900 [13:35<24:24,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 676/1900 [13:36<24:14,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 677/1900 [13:37<24:16,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 678/1900 [13:38<24:25,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 679/1900 [13:39<24:01,  1.18s/it]
+
+
Evaluating eval...:  36%|███▌      | 680/1900 [13:41<24:13,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 681/1900 [13:42<24:51,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 682/1900 [13:43<24:46,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 683/1900 [13:44<24:38,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 684/1900 [13:46<24:14,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 685/1900 [13:47<23:56,  1.18s/it]
+
+
Evaluating eval...:  36%|███▌      | 686/1900 [13:48<24:22,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 687/1900 [13:49<24:03,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 688/1900 [13:50<23:45,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 689/1900 [13:51<23:47,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 690/1900 [13:53<23:53,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 691/1900 [13:54<23:56,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 692/1900 [13:55<23:37,  1.17s/it]
+
+
Evaluating eval...:  36%|███▋      | 693/1900 [13:56<23:40,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 694/1900 [13:57<23:42,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 695/1900 [13:59<24:00,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 696/1900 [14:00<24:03,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 697/1900 [14:01<23:57,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 698/1900 [14:02<24:04,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 699/1900 [14:03<24:27,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 700/1900 [14:05<24:07,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 701/1900 [14:06<24:10,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 702/1900 [14:07<24:13,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 703/1900 [14:08<23:50,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 704/1900 [14:10<24:44,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 705/1900 [14:11<24:49,  1.25s/it]
+
+
Evaluating eval...:  37%|███▋      | 706/1900 [14:12<24:33,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 707/1900 [14:13<24:05,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 708/1900 [14:14<24:21,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 709/1900 [14:16<24:07,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 710/1900 [14:17<23:55,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 711/1900 [14:18<24:38,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 712/1900 [14:19<24:35,  1.24s/it]
+
+
Evaluating eval...:  38%|███▊      | 713/1900 [14:21<24:48,  1.25s/it]
+
+
Evaluating eval...:  38%|███▊      | 714/1900 [14:22<24:16,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 715/1900 [14:23<24:03,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 716/1900 [14:24<23:39,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 717/1900 [14:25<23:26,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 718/1900 [14:27<23:32,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 719/1900 [14:28<23:28,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 720/1900 [14:29<23:19,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 721/1900 [14:30<23:46,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 722/1900 [14:31<23:39,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 723/1900 [14:33<23:35,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 724/1900 [14:34<23:35,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 725/1900 [14:35<23:13,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 726/1900 [14:36<23:14,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 727/1900 [14:37<23:02,  1.18s/it]
+
+
Evaluating eval...:  38%|███▊      | 728/1900 [14:39<23:33,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 729/1900 [14:40<23:10,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 730/1900 [14:41<23:55,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 731/1900 [14:42<23:45,  1.22s/it]
+
+
Evaluating eval...:  39%|███▊      | 732/1900 [14:43<23:27,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 733/1900 [14:45<23:25,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 734/1900 [14:46<23:22,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 735/1900 [14:47<23:08,  1.19s/it]
+
+
Evaluating eval...:  39%|███▊      | 736/1900 [14:48<23:03,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 737/1900 [14:49<22:57,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 738/1900 [14:51<23:16,  1.20s/it]
+
+
Evaluating eval...:  39%|███▉      | 739/1900 [14:52<23:04,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 740/1900 [14:53<23:04,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 741/1900 [14:54<23:45,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 742/1900 [14:55<23:45,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 743/1900 [14:57<23:50,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 744/1900 [14:58<23:22,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 745/1900 [14:59<23:45,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 746/1900 [15:00<23:48,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 747/1900 [15:02<24:19,  1.27s/it]
+
+
Evaluating eval...:  39%|███▉      | 748/1900 [15:03<23:44,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 749/1900 [15:04<23:50,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 750/1900 [15:05<23:34,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 751/1900 [15:07<23:25,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 752/1900 [15:08<23:32,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 753/1900 [15:09<23:38,  1.24s/it]
+
+
Evaluating eval...:  40%|███▉      | 754/1900 [15:10<23:12,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 755/1900 [15:11<22:55,  1.20s/it]
+
+
Evaluating eval...:  40%|███▉      | 756/1900 [15:13<23:14,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 757/1900 [15:14<23:14,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 758/1900 [15:15<23:20,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 759/1900 [15:16<23:14,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 760/1900 [15:18<23:18,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 761/1900 [15:19<23:00,  1.21s/it]
+
+
Evaluating eval...:  40%|████      | 762/1900 [15:20<22:33,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 763/1900 [15:21<22:26,  1.18s/it]
+
+
Evaluating eval...:  40%|████      | 764/1900 [15:22<22:21,  1.18s/it]
+
+
Evaluating eval...:  40%|████      | 765/1900 [15:23<22:46,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 766/1900 [15:25<22:43,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 767/1900 [15:26<23:06,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 768/1900 [15:27<23:56,  1.27s/it]
+
+
Evaluating eval...:  40%|████      | 769/1900 [15:29<23:35,  1.25s/it]
+
+
Evaluating eval...:  41%|████      | 770/1900 [15:30<23:07,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 771/1900 [15:31<22:52,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 772/1900 [15:32<23:09,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 773/1900 [15:33<22:54,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 774/1900 [15:34<22:29,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 775/1900 [15:36<22:53,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 776/1900 [15:37<22:48,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 777/1900 [15:38<23:02,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 778/1900 [15:39<22:47,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 779/1900 [15:41<22:36,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 780/1900 [15:42<24:00,  1.29s/it]
+
+
Evaluating eval...:  41%|████      | 781/1900 [15:43<23:45,  1.27s/it]
+
+
Evaluating eval...:  41%|████      | 782/1900 [15:45<24:14,  1.30s/it]
+
+
Evaluating eval...:  41%|████      | 783/1900 [15:46<23:44,  1.27s/it]
+
+
Evaluating eval...:  41%|████▏     | 784/1900 [15:47<23:15,  1.25s/it]
+
+
Evaluating eval...:  41%|████▏     | 785/1900 [15:48<22:53,  1.23s/it]
+
+
Evaluating eval...:  41%|████▏     | 786/1900 [15:49<22:37,  1.22s/it]
+
+
Evaluating eval...:  41%|████▏     | 787/1900 [15:51<22:37,  1.22s/it]
+
+
Evaluating eval...:  41%|████▏     | 788/1900 [15:52<22:34,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 789/1900 [15:53<22:39,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 790/1900 [15:54<22:26,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 791/1900 [15:56<22:31,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 792/1900 [15:57<22:44,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 793/1900 [15:58<22:24,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 794/1900 [15:59<22:12,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 795/1900 [16:00<22:10,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 796/1900 [16:02<21:56,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 797/1900 [16:03<21:54,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 798/1900 [16:04<21:55,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 799/1900 [16:05<21:46,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 800/1900 [16:06<22:04,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 801/1900 [16:08<21:59,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 802/1900 [16:09<21:39,  1.18s/it]
+
+
Evaluating eval...:  42%|████▏     | 803/1900 [16:10<22:04,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 804/1900 [16:11<21:52,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 805/1900 [16:12<22:26,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 806/1900 [16:14<22:02,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 807/1900 [16:15<21:48,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 808/1900 [16:16<22:22,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 809/1900 [16:17<22:31,  1.24s/it]
+
+
Evaluating eval...:  43%|████▎     | 810/1900 [16:19<22:22,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 811/1900 [16:20<22:10,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 812/1900 [16:21<22:23,  1.24s/it]
+
+
Evaluating eval...:  43%|████▎     | 813/1900 [16:22<21:56,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 814/1900 [16:23<21:54,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 815/1900 [16:25<21:45,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 816/1900 [16:26<21:52,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 817/1900 [16:27<21:45,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 818/1900 [16:28<21:52,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 819/1900 [16:29<21:45,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 820/1900 [16:31<21:46,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 821/1900 [16:32<21:36,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 822/1900 [16:33<21:41,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 823/1900 [16:34<21:49,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 824/1900 [16:35<21:41,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 825/1900 [16:37<21:30,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 826/1900 [16:38<21:52,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 827/1900 [16:39<21:52,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 828/1900 [16:40<22:04,  1.24s/it]
+
+
Evaluating eval...:  44%|████▎     | 829/1900 [16:42<21:42,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 830/1900 [16:43<21:48,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 831/1900 [16:44<21:35,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 832/1900 [16:45<21:33,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 833/1900 [16:46<21:37,  1.22s/it]
+
+
Evaluating eval...:  44%|████▍     | 834/1900 [16:48<21:16,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 835/1900 [16:49<21:36,  1.22s/it]
+
+
Evaluating eval...:  44%|████▍     | 836/1900 [16:50<21:37,  1.22s/it]
+
+
Evaluating eval...:  44%|████▍     | 837/1900 [16:51<21:17,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 838/1900 [16:52<20:55,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 839/1900 [16:54<20:48,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 840/1900 [16:55<20:50,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 841/1900 [16:56<21:26,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 842/1900 [16:57<21:17,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 843/1900 [16:58<21:04,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 844/1900 [17:00<20:48,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 845/1900 [17:01<20:48,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 846/1900 [17:02<21:11,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 847/1900 [17:03<20:57,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 848/1900 [17:04<20:57,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 849/1900 [17:06<20:53,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 850/1900 [17:07<21:24,  1.22s/it]
+
+
Evaluating eval...:  45%|████▍     | 851/1900 [17:08<21:20,  1.22s/it]
+
+
Evaluating eval...:  45%|████▍     | 852/1900 [17:09<22:00,  1.26s/it]
+
+
Evaluating eval...:  45%|████▍     | 853/1900 [17:11<21:51,  1.25s/it]
+
+
Evaluating eval...:  45%|████▍     | 854/1900 [17:12<21:46,  1.25s/it]
+
+
Evaluating eval...:  45%|████▌     | 855/1900 [17:13<21:37,  1.24s/it]
+
+
Evaluating eval...:  45%|████▌     | 856/1900 [17:14<21:15,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 857/1900 [17:15<20:58,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 858/1900 [17:17<21:07,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 859/1900 [17:18<20:58,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 860/1900 [17:19<20:53,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 861/1900 [17:20<21:17,  1.23s/it]
+
+
Evaluating eval...:  45%|████▌     | 862/1900 [17:22<21:10,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 863/1900 [17:23<20:43,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 864/1900 [17:24<20:35,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 865/1900 [17:25<20:25,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 866/1900 [17:26<20:26,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 867/1900 [17:27<20:45,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 868/1900 [17:29<21:15,  1.24s/it]
+
+
Evaluating eval...:  46%|████▌     | 869/1900 [17:30<20:52,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 870/1900 [17:31<20:46,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 871/1900 [17:32<20:54,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 872/1900 [17:34<20:48,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 873/1900 [17:35<20:34,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 874/1900 [17:36<20:45,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 875/1900 [17:37<20:40,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 876/1900 [17:38<20:27,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 877/1900 [17:40<20:10,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 878/1900 [17:41<20:25,  1.20s/it]
+
+
Evaluating eval...:  46%|████▋     | 879/1900 [17:42<20:18,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 880/1900 [17:43<20:10,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 881/1900 [17:44<19:59,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 882/1900 [17:45<20:07,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 883/1900 [17:47<20:30,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 884/1900 [17:48<20:41,  1.22s/it]
+
+
Evaluating eval...:  47%|███��▋     | 885/1900 [17:49<20:22,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 886/1900 [17:50<20:14,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 887/1900 [17:52<20:20,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 888/1900 [17:53<20:22,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 889/1900 [17:54<20:18,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 890/1900 [17:55<20:10,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 891/1900 [17:56<20:41,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 892/1900 [17:58<20:39,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 893/1900 [17:59<20:36,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 894/1900 [18:00<20:11,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 895/1900 [18:01<20:29,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 896/1900 [18:03<20:20,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 897/1900 [18:04<20:04,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 898/1900 [18:05<20:25,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 899/1900 [18:06<19:59,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 900/1900 [18:07<19:56,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 901/1900 [18:08<19:39,  1.18s/it]
+
+
Evaluating eval...:  47%|████▋     | 902/1900 [18:10<19:52,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 903/1900 [18:11<20:04,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 904/1900 [18:12<20:00,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 905/1900 [18:13<19:46,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 906/1900 [18:14<19:40,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 907/1900 [18:16<19:51,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 908/1900 [18:17<19:38,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 909/1900 [18:18<19:38,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 910/1900 [18:19<19:28,  1.18s/it]
+
+
Evaluating eval...:  48%|████▊     | 911/1900 [18:20<19:47,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 912/1900 [18:22<19:43,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 913/1900 [18:23<19:48,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 914/1900 [18:24<19:50,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 915/1900 [18:25<20:23,  1.24s/it]
+
+
Evaluating eval...:  48%|████▊     | 916/1900 [18:27<20:04,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 917/1900 [18:28<19:43,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 918/1900 [18:29<19:51,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 919/1900 [18:30<19:47,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 920/1900 [18:31<19:39,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 921/1900 [18:33<19:31,  1.20s/it]
+
+
Evaluating eval...:  49%|████▊     | 922/1900 [18:34<19:20,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 923/1900 [18:35<19:54,  1.22s/it]
+
+
Evaluating eval...:  49%|████▊     | 924/1900 [18:36<19:31,  1.20s/it]
+
+
Evaluating eval...:  49%|████▊     | 925/1900 [18:37<19:46,  1.22s/it]
+
+
Evaluating eval...:  49%|████▊     | 926/1900 [18:39<19:34,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 927/1900 [18:40<19:20,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 928/1900 [18:41<19:47,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 929/1900 [18:42<19:28,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 930/1900 [18:43<19:11,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 931/1900 [18:45<19:26,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 932/1900 [18:46<19:37,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 933/1900 [18:47<19:38,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 934/1900 [18:48<19:22,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 935/1900 [18:49<19:33,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 936/1900 [18:51<20:29,  1.28s/it]
+
+
Evaluating eval...:  49%|████▉     | 937/1900 [18:52<20:12,  1.26s/it]
+
+
Evaluating eval...:  49%|████▉     | 938/1900 [18:53<19:57,  1.24s/it]
+
+
Evaluating eval...:  49%|████▉     | 939/1900 [18:55<19:44,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 940/1900 [18:56<19:32,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 941/1900 [18:57<19:28,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 942/1900 [18:58<19:26,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 943/1900 [18:59<19:11,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 944/1900 [19:01<19:08,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 945/1900 [19:02<18:56,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 946/1900 [19:03<18:57,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 947/1900 [19:04<19:17,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 948/1900 [19:05<19:00,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 949/1900 [19:07<19:01,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 950/1900 [19:08<18:59,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 951/1900 [19:09<19:15,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 952/1900 [19:10<19:30,  1.23s/it]
+
+
Evaluating eval...:  50%|█████     | 953/1900 [19:11<19:01,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 954/1900 [19:13<18:46,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 955/1900 [19:14<18:54,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 956/1900 [19:15<18:40,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 957/1900 [19:16<18:32,  1.18s/it]
+
+
Evaluating eval...:  50%|█████     | 958/1900 [19:17<18:34,  1.18s/it]
+
+
Evaluating eval...:  50%|█████     | 959/1900 [19:18<18:36,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 960/1900 [19:20<18:45,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 961/1900 [19:21<19:05,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 962/1900 [19:22<18:55,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 963/1900 [19:23<19:09,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 964/1900 [19:25<19:17,  1.24s/it]
+
+
Evaluating eval...:  51%|█████     | 965/1900 [19:26<19:11,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 966/1900 [19:27<18:48,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 967/1900 [19:28<18:33,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 968/1900 [19:29<18:26,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 969/1900 [19:31<18:34,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 970/1900 [19:32<18:52,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 971/1900 [19:33<18:43,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 972/1900 [19:34<18:57,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 973/1900 [19:36<18:57,  1.23s/it]
+
+
Evaluating eval...:  51%|█████▏    | 974/1900 [19:37<18:36,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 975/1900 [19:38<18:59,  1.23s/it]
+
+
Evaluating eval...:  51%|█████▏    | 976/1900 [19:39<18:56,  1.23s/it]
+
+
Evaluating eval...:  51%|█████▏    | 977/1900 [19:40<18:35,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 978/1900 [19:42<18:45,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 979/1900 [19:43<18:33,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 980/1900 [19:44<18:28,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 981/1900 [19:45<18:11,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 982/1900 [19:46<18:00,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 983/1900 [19:48<18:08,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 984/1900 [19:49<18:08,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 985/1900 [19:50<18:06,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 986/1900 [19:51<18:03,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 987/1900 [19:52<18:09,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 988/1900 [19:53<17:59,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 989/1900 [19:55<18:05,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 990/1900 [19:56<18:35,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 991/1900 [19:57<18:19,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 992/1900 [19:58<18:03,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 993/1900 [20:00<18:12,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 994/1900 [20:01<17:59,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 995/1900 [20:02<18:34,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 996/1900 [20:03<18:17,  1.21s/it]
+
+
Evaluating eval...:  52%|████���▏    | 997/1900 [20:04<18:11,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 998/1900 [20:06<18:10,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 999/1900 [20:07<18:12,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1000/1900 [20:08<17:55,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1001/1900 [20:09<17:53,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1002/1900 [20:10<17:55,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1003/1900 [20:12<18:12,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1004/1900 [20:13<18:12,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1005/1900 [20:14<17:56,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1006/1900 [20:15<17:56,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1007/1900 [20:16<17:50,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1008/1900 [20:18<17:43,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1009/1900 [20:19<17:37,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1010/1900 [20:20<17:36,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1011/1900 [20:21<17:35,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1012/1900 [20:22<18:10,  1.23s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1013/1900 [20:24<17:52,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1014/1900 [20:25<18:04,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1015/1900 [20:26<17:49,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1016/1900 [20:27<18:26,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1017/1900 [20:29<18:23,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1018/1900 [20:30<18:15,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1019/1900 [20:31<18:35,  1.27s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1020/1900 [20:32<18:27,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1021/1900 [20:34<18:12,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1022/1900 [20:35<18:13,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1023/1900 [20:36<18:14,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1024/1900 [20:37<18:10,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1025/1900 [20:39<17:47,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1026/1900 [20:40<17:48,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1027/1900 [20:41<17:44,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1028/1900 [20:42<17:32,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1029/1900 [20:43<17:27,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1030/1900 [20:45<17:18,  1.19s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1031/1900 [20:46<17:37,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1032/1900 [20:47<18:11,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1033/1900 [20:48<17:46,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1034/1900 [20:50<18:14,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1035/1900 [20:51<17:53,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1036/1900 [20:52<17:48,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1037/1900 [20:53<17:47,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1038/1900 [20:55<17:38,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1039/1900 [20:56<17:41,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1040/1900 [20:57<17:31,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1041/1900 [20:58<17:36,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1042/1900 [20:59<17:40,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1043/1900 [21:01<17:30,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1044/1900 [21:02<17:28,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1045/1900 [21:03<17:11,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1046/1900 [21:04<17:04,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1047/1900 [21:05<16:56,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1048/1900 [21:07<16:57,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1049/1900 [21:08<17:11,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1050/1900 [21:09<17:27,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1051/1900 [21:10<17:09,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1052/1900 [21:12<17:16,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1053/1900 [21:13<17:11,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1054/1900 [21:14<16:59,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1055/1900 [21:15<16:46,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1056/1900 [21:16<17:20,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1057/1900 [21:18<17:27,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1058/1900 [21:19<17:14,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1059/1900 [21:20<16:50,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1060/1900 [21:21<16:36,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1061/1900 [21:22<16:32,  1.18s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1062/1900 [21:24<16:29,  1.18s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1063/1900 [21:25<16:43,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1064/1900 [21:26<16:59,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1065/1900 [21:27<16:57,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1066/1900 [21:28<16:47,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1067/1900 [21:30<16:55,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1068/1900 [21:31<16:43,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1069/1900 [21:32<16:50,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1070/1900 [21:33<16:48,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1071/1900 [21:35<16:57,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1072/1900 [21:36<17:00,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1073/1900 [21:37<16:43,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1074/1900 [21:38<16:43,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1075/1900 [21:39<16:46,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1076/1900 [21:41<16:55,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1077/1900 [21:42<16:51,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1078/1900 [21:43<16:29,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1079/1900 [21:44<16:42,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1080/1900 [21:46<17:19,  1.27s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1081/1900 [21:47<17:06,  1.25s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1082/1900 [21:48<16:46,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1083/1900 [21:49<16:53,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1084/1900 [21:51<16:43,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1085/1900 [21:52<16:44,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1086/1900 [21:53<16:53,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1087/1900 [21:54<16:41,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1088/1900 [21:55<16:31,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1089/1900 [21:57<16:53,  1.25s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1090/1900 [21:58<16:39,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1091/1900 [21:59<16:21,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1092/1900 [22:01<16:57,  1.26s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1093/1900 [22:02<16:40,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1094/1900 [22:03<16:26,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1095/1900 [22:04<16:14,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1096/1900 [22:05<15:59,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1097/1900 [22:06<15:51,  1.18s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1098/1900 [22:08<16:09,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1099/1900 [22:09<16:12,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1100/1900 [22:10<16:10,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1101/1900 [22:11<15:59,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1102/1900 [22:12<15:57,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1103/1900 [22:14<16:20,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1104/1900 [22:15<16:06,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1105/1900 [22:16<17:03,  1.29s/it]
+
+
Evaluating eval...:  58%|███���█▊    | 1106/1900 [22:18<16:50,  1.27s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1107/1900 [22:19<16:39,  1.26s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1108/1900 [22:20<16:25,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1109/1900 [22:21<16:18,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1110/1900 [22:22<16:00,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1111/1900 [22:24<16:31,  1.26s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1112/1900 [22:25<16:14,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1113/1900 [22:26<16:10,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1114/1900 [22:27<16:03,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1115/1900 [22:29<16:03,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1116/1900 [22:30<16:05,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1117/1900 [22:31<15:58,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1118/1900 [22:32<15:48,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1119/1900 [22:34<16:03,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1120/1900 [22:35<16:01,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1121/1900 [22:36<15:50,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1122/1900 [22:37<15:36,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1123/1900 [22:38<15:48,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1124/1900 [22:40<15:46,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1125/1900 [22:41<15:40,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1126/1900 [22:42<15:35,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1127/1900 [22:43<15:30,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1128/1900 [22:45<15:45,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1129/1900 [22:46<15:30,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1130/1900 [22:47<15:18,  1.19s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1131/1900 [22:48<15:23,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1132/1900 [22:49<15:26,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1133/1900 [22:51<15:34,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1134/1900 [22:52<15:30,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1135/1900 [22:53<16:04,  1.26s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1136/1900 [22:54<15:40,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1137/1900 [22:55<15:24,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1138/1900 [22:57<15:39,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1139/1900 [22:58<15:35,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1140/1900 [22:59<15:38,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1141/1900 [23:00<15:37,  1.24s/it]
+
+
Evaluating eval...:  60%|██████    | 1142/1900 [23:02<15:19,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1143/1900 [23:03<15:09,  1.20s/it]
+
+
Evaluating eval...:  60%|██████    | 1144/1900 [23:04<15:13,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1145/1900 [23:05<15:19,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1146/1900 [23:06<15:25,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1147/1900 [23:08<15:24,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1148/1900 [23:09<15:18,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1149/1900 [23:10<15:03,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1150/1900 [23:11<15:13,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1151/1900 [23:12<15:00,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1152/1900 [23:14<14:58,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1153/1900 [23:15<15:07,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1154/1900 [23:16<15:02,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1155/1900 [23:17<15:02,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1156/1900 [23:19<14:58,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1157/1900 [23:20<14:57,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1158/1900 [23:21<15:14,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1159/1900 [23:22<15:04,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1160/1900 [23:23<15:00,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1161/1900 [23:25<15:00,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1162/1900 [23:26<14:48,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1163/1900 [23:27<14:53,  1.21s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1164/1900 [23:28<14:38,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1165/1900 [23:29<14:40,  1.20s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1166/1900 [23:31<14:57,  1.22s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1167/1900 [23:32<14:55,  1.22s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1168/1900 [23:33<14:49,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1169/1900 [23:34<14:46,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1170/1900 [23:36<14:57,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1171/1900 [23:37<15:03,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1172/1900 [23:38<14:54,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1173/1900 [23:39<14:43,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1174/1900 [23:40<14:34,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1175/1900 [23:42<14:48,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1176/1900 [23:43<14:53,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1177/1900 [23:44<14:36,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1178/1900 [23:45<14:22,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1179/1900 [23:46<14:23,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1180/1900 [23:48<14:31,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1181/1900 [23:49<14:17,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1182/1900 [23:50<14:23,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1183/1900 [23:51<14:36,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1184/1900 [23:53<14:41,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1185/1900 [23:54<14:37,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1186/1900 [23:55<14:47,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1187/1900 [23:56<14:34,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1188/1900 [23:57<14:24,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1189/1900 [23:59<14:16,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1190/1900 [24:00<14:07,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1191/1900 [24:01<14:10,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1192/1900 [24:02<14:24,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1193/1900 [24:03<14:16,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1194/1900 [24:05<14:20,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1195/1900 [24:06<14:13,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1196/1900 [24:07<14:05,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1197/1900 [24:08<14:21,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1198/1900 [24:10<14:14,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1199/1900 [24:11<14:24,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1200/1900 [24:12<14:13,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1201/1900 [24:13<14:04,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1202/1900 [24:14<13:52,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1203/1900 [24:16<14:02,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1204/1900 [24:17<14:08,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1205/1900 [24:18<14:11,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1206/1900 [24:19<14:16,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1207/1900 [24:21<14:02,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1208/1900 [24:22<14:00,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1209/1900 [24:23<13:55,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1210/1900 [24:24<14:05,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1211/1900 [24:25<14:05,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1212/1900 [24:27<14:06,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1213/1900 [24:28<13:56,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1214/1900 [24:29<13:49,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1215/1900 [24:30<13:44,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1216/1900 [24:31<13:49,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1217/1900 [24:33<13:55,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1218/1900 [24:34<14:06,  1.24s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1219/1900 [24:35<13:59,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1220/1900 [24:37<14:08,  1.25s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1221/1900 [24:38<13:54,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1222/1900 [24:39<13:39,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1223/1900 [24:40<13:39,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1224/1900 [24:41<13:32,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1225/1900 [24:42<13:31,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1226/1900 [24:44<13:29,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1227/1900 [24:45<13:23,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1228/1900 [24:46<13:20,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1229/1900 [24:47<13:18,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1230/1900 [24:48<13:20,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1231/1900 [24:50<13:18,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1232/1900 [24:51<13:18,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1233/1900 [24:52<13:13,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1234/1900 [24:53<13:13,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1235/1900 [24:54<13:27,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1236/1900 [24:56<13:15,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1237/1900 [24:57<13:11,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1238/1900 [24:58<13:02,  1.18s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1239/1900 [24:59<13:07,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1240/1900 [25:00<13:21,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1241/1900 [25:02<13:10,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1242/1900 [25:03<13:08,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1243/1900 [25:04<13:21,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1244/1900 [25:05<13:03,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1245/1900 [25:06<12:53,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1246/1900 [25:08<12:59,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1247/1900 [25:09<12:56,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1248/1900 [25:10<12:49,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1249/1900 [25:11<12:56,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1250/1900 [25:12<12:55,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1251/1900 [25:13<12:47,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1252/1900 [25:15<12:45,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1253/1900 [25:16<12:47,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1254/1900 [25:17<12:54,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1255/1900 [25:18<13:00,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1256/1900 [25:20<12:57,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1257/1900 [25:21<12:48,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1258/1900 [25:22<12:51,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1259/1900 [25:23<12:40,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1260/1900 [25:24<12:40,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1261/1900 [25:25<12:40,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1262/1900 [25:27<12:32,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1263/1900 [25:28<12:32,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1264/1900 [25:29<12:33,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1265/1900 [25:30<12:32,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1266/1900 [25:31<12:51,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1267/1900 [25:33<12:42,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1268/1900 [25:34<12:38,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1269/1900 [25:35<12:42,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1270/1900 [25:36<12:32,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1271/1900 [25:37<12:34,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1272/1900 [25:39<12:24,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1273/1900 [25:40<12:20,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1274/1900 [25:41<12:19,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1275/1900 [25:42<12:14,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1276/1900 [25:43<12:13,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1277/1900 [25:44<12:12,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1278/1900 [25:46<12:07,  1.17s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1279/1900 [25:47<12:07,  1.17s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1280/1900 [25:48<12:06,  1.17s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1281/1900 [25:49<12:01,  1.17s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1282/1900 [25:50<11:58,  1.16s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1283/1900 [25:51<11:59,  1.17s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1284/1900 [25:53<11:59,  1.17s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1285/1900 [25:54<12:05,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1286/1900 [25:55<12:08,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1287/1900 [25:56<12:33,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1288/1900 [25:58<12:31,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1289/1900 [25:59<12:29,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1290/1900 [26:00<12:21,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1291/1900 [26:01<12:12,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1292/1900 [26:02<12:18,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1293/1900 [26:04<12:16,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1294/1900 [26:05<12:20,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1295/1900 [26:06<12:10,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1296/1900 [26:07<12:11,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1297/1900 [26:08<12:00,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1298/1900 [26:10<12:02,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1299/1900 [26:11<12:01,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1300/1900 [26:12<12:07,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1301/1900 [26:13<12:06,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1302/1900 [26:14<11:58,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1303/1900 [26:16<12:02,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1304/1900 [26:17<12:01,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1305/1900 [26:18<11:52,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1306/1900 [26:19<11:51,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1307/1900 [26:20<11:42,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1308/1900 [26:22<11:44,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1309/1900 [26:23<11:44,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1310/1900 [26:24<11:38,  1.18s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1311/1900 [26:25<11:40,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1312/1900 [26:26<11:38,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1313/1900 [26:28<11:46,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1314/1900 [26:29<11:34,  1.18s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1315/1900 [26:30<11:33,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1316/1900 [26:31<11:40,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1317/1900 [26:32<11:38,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1318/1900 [26:34<11:43,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1319/1900 [26:35<11:41,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1320/1900 [26:36<11:31,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1321/1900 [26:37<11:40,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1322/1900 [26:38<11:39,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1323/1900 [26:40<11:33,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1324/1900 [26:41<11:23,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1325/1900 [26:42<11:14,  1.17s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1326/1900 [26:43<11:14,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1327/1900 [26:44<11:12,  1.17s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1328/1900 [26:45<11:26,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1329/1900 [26:47<11:19,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1330/1900 [26:48<11:25,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1331/1900 [26:49<11:20,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1332/1900 [26:50<11:19,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1333/1900 [26:51<11:18,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1334/1900 [26:53<11:15,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1335/1900 [26:54<11:13,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1336/1900 [26:55<11:11,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1337/1900 [26:56<11:15,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1338/1900 [26:57<11:09,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1339/1900 [26:59<11:10,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1340/1900 [27:00<11:07,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1341/1900 [27:01<11:02,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1342/1900 [27:02<11:06,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1343/1900 [27:03<10:57,  1.18s/it]
+
+
Evaluating eval...:  71%|███████   | 1344/1900 [27:05<11:43,  1.26s/it]
+
+
Evaluating eval...:  71%|███████   | 1345/1900 [27:06<11:34,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1346/1900 [27:07<11:45,  1.27s/it]
+
+
Evaluating eval...:  71%|███████   | 1347/1900 [27:09<11:28,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1348/1900 [27:10<11:12,  1.22s/it]
+
+
Evaluating eval...:  71%|███████   | 1349/1900 [27:11<11:32,  1.26s/it]
+
+
Evaluating eval...:  71%|███████   | 1350/1900 [27:12<11:19,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1351/1900 [27:13<11:21,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1352/1900 [27:15<11:17,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1353/1900 [27:16<11:17,  1.24s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1354/1900 [27:17<11:11,  1.23s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1355/1900 [27:18<10:59,  1.21s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1356/1900 [27:20<11:07,  1.23s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1357/1900 [27:21<10:59,  1.21s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1358/1900 [27:22<10:54,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1359/1900 [27:23<10:52,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1360/1900 [27:24<10:49,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1361/1900 [27:26<10:52,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1362/1900 [27:27<10:40,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1363/1900 [27:28<10:42,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1364/1900 [27:29<10:37,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1365/1900 [27:30<10:34,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1366/1900 [27:31<10:32,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1367/1900 [27:33<10:33,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1368/1900 [27:34<10:38,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1369/1900 [27:35<10:42,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1370/1900 [27:36<10:39,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1371/1900 [27:37<10:36,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1372/1900 [27:39<10:26,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1373/1900 [27:40<10:20,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1374/1900 [27:41<10:18,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1375/1900 [27:42<10:23,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1376/1900 [27:43<10:23,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1377/1900 [27:45<10:20,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1378/1900 [27:46<10:13,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1379/1900 [27:47<10:13,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1380/1900 [27:48<10:18,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1381/1900 [27:49<10:26,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1382/1900 [27:51<10:21,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1383/1900 [27:52<10:18,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1384/1900 [27:53<10:14,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1385/1900 [27:54<10:11,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1386/1900 [27:55<10:16,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1387/1900 [27:56<10:08,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1388/1900 [27:58<10:05,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1389/1900 [27:59<10:01,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1390/1900 [28:00<10:15,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1391/1900 [28:01<10:14,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1392/1900 [28:02<10:11,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1393/1900 [28:04<10:10,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1394/1900 [28:05<10:25,  1.24s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1395/1900 [28:06<10:17,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1396/1900 [28:07<10:08,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1397/1900 [28:09<10:01,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1398/1900 [28:10<10:06,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1399/1900 [28:11<10:03,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1400/1900 [28:12<09:56,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1401/1900 [28:13<10:10,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1402/1900 [28:15<09:56,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1403/1900 [28:16<09:50,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1404/1900 [28:17<09:45,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1405/1900 [28:18<09:40,  1.17s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1406/1900 [28:19<09:42,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1407/1900 [28:20<09:48,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1408/1900 [28:22<09:58,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1409/1900 [28:23<09:51,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1410/1900 [28:24<09:45,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1411/1900 [28:25<09:45,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1412/1900 [28:26<09:42,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1413/1900 [28:28<09:40,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1414/1900 [28:29<09:37,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1415/1900 [28:30<09:35,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1416/1900 [28:31<09:29,  1.18s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1417/1900 [28:32<09:30,  1.18s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1418/1900 [28:34<09:24,  1.17s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1419/1900 [28:35<09:41,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1420/1900 [28:36<09:39,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1421/1900 [28:37<09:35,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1422/1900 [28:38<09:42,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1423/1900 [28:40<09:34,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1424/1900 [28:41<09:35,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1425/1900 [28:42<09:32,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1426/1900 [28:43<09:31,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1427/1900 [28:44<09:31,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1428/1900 [28:46<09:37,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1429/1900 [28:47<09:38,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1430/1900 [28:48<09:29,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1431/1900 [28:49<09:37,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1432/1900 [28:51<09:54,  1.27s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1433/1900 [28:52<09:45,  1.25s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1434/1900 [28:53<09:35,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1435/1900 [28:54<09:28,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1436/1900 [28:56<09:27,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1437/1900 [28:57<09:22,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1438/1900 [28:58<09:14,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1439/1900 [28:59<09:10,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1440/1900 [29:00<09:12,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1441/1900 [29:02<09:07,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1442/1900 [29:03<09:07,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1443/1900 [29:04<09:12,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1444/1900 [29:05<09:08,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1445/1900 [29:06<09:00,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1446/1900 [29:08<09:04,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1447/1900 [29:09<09:01,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1448/1900 [29:10<08:59,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1449/1900 [29:11<08:59,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1450/1900 [29:12<09:07,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1451/1900 [29:14<09:07,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1452/1900 [29:15<08:58,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1453/1900 [29:16<08:52,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1454/1900 [29:17<09:07,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1455/1900 [29:18<09:03,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1456/1900 [29:20<09:06,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1457/1900 [29:21<09:03,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1458/1900 [29:22<09:04,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1459/1900 [29:23<08:55,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1460/1900 [29:25<08:48,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1461/1900 [29:26<08:45,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1462/1900 [29:27<08:45,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1463/1900 [29:28<08:44,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1464/1900 [29:29<08:48,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1465/1900 [29:31<08:44,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1466/1900 [29:32<08:54,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1467/1900 [29:33<08:45,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1468/1900 [29:34<08:59,  1.25s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1469/1900 [29:36<08:54,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1470/1900 [29:37<08:42,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1471/1900 [29:38<08:42,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1472/1900 [29:39<08:34,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1473/1900 [29:40<08:33,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1474/1900 [29:42<08:31,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1475/1900 [29:43<08:33,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1476/1900 [29:44<08:34,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1477/1900 [29:45<08:33,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1478/1900 [29:46<08:30,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1479/1900 [29:48<08:39,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1480/1900 [29:49<08:31,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1481/1900 [29:50<08:27,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1482/1900 [29:51<08:24,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1483/1900 [29:52<08:15,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1484/1900 [29:54<08:10,  1.18s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1485/1900 [29:55<08:21,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1486/1900 [29:56<08:16,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1487/1900 [29:57<08:17,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1488/1900 [29:58<08:08,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1489/1900 [30:00<08:06,  1.18s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1490/1900 [30:01<08:08,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1491/1900 [30:02<08:02,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1492/1900 [30:03<08:07,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1493/1900 [30:04<08:11,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1494/1900 [30:06<08:04,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1495/1900 [30:07<07:59,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1496/1900 [30:08<07:54,  1.17s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1497/1900 [30:09<07:50,  1.17s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1498/1900 [30:10<07:54,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1499/1900 [30:11<07:59,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1500/1900 [30:13<08:03,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1501/1900 [30:14<07:56,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1502/1900 [30:15<07:55,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1503/1900 [30:16<07:54,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1504/1900 [30:17<07:51,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1505/1900 [30:19<07:51,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1506/1900 [30:20<07:53,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1507/1900 [30:21<07:50,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1508/1900 [30:22<07:56,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1509/1900 [30:23<07:55,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1510/1900 [30:25<07:48,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1511/1900 [30:26<07:49,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1512/1900 [30:27<07:53,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1513/1900 [30:28<07:55,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1514/1900 [30:30<07:50,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1515/1900 [30:31<07:59,  1.25s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1516/1900 [30:32<07:54,  1.24s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1517/1900 [30:33<07:43,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1518/1900 [30:34<07:34,  1.19s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1519/1900 [30:36<07:27,  1.18s/it]
+
+
Evaluating eval...:  80%|████████  | 1520/1900 [30:37<07:31,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1521/1900 [30:38<07:32,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1522/1900 [30:39<07:26,  1.18s/it]
+
+
Evaluating eval...:  80%|████████  | 1523/1900 [30:40<07:30,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1524/1900 [30:42<07:32,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1525/1900 [30:43<07:30,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1526/1900 [30:44<07:26,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1527/1900 [30:45<07:25,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1528/1900 [30:46<07:26,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1529/1900 [30:48<07:23,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1530/1900 [30:49<07:28,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1531/1900 [30:50<07:28,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1532/1900 [30:51<07:33,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1533/1900 [30:52<07:27,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1534/1900 [30:54<07:24,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1535/1900 [30:55<07:17,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1536/1900 [30:56<07:12,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1537/1900 [30:57<07:17,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1538/1900 [30:58<07:12,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1539/1900 [31:00<07:21,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1540/1900 [31:01<07:16,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1541/1900 [31:02<07:27,  1.25s/it]
+
+
Evaluating eval...:  81%|████████  | 1542/1900 [31:03<07:17,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1543/1900 [31:05<07:15,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1544/1900 [31:06<07:13,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1545/1900 [31:07<07:08,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1546/1900 [31:08<07:12,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1547/1900 [31:09<07:13,  1.23s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1548/1900 [31:11<07:06,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1549/1900 [31:12<06:59,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1550/1900 [31:13<07:06,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1551/1900 [31:14<07:05,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1552/1900 [31:15<06:57,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1553/1900 [31:17<06:54,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1554/1900 [31:18<06:51,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1555/1900 [31:19<06:48,  1.18s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1556/1900 [31:20<06:59,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1557/1900 [31:21<06:56,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1558/1900 [31:23<07:03,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1559/1900 [31:24<07:01,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1560/1900 [31:25<06:51,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1561/1900 [31:26<06:53,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1562/1900 [31:28<06:55,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1563/1900 [31:29<06:54,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1564/1900 [31:30<06:46,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1565/1900 [31:31<06:45,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1566/1900 [31:32<06:44,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1567/1900 [31:34<06:43,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1568/1900 [31:35<07:15,  1.31s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1569/1900 [31:37<07:08,  1.30s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1570/1900 [31:38<06:59,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1571/1900 [31:39<06:49,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1572/1900 [31:40<06:50,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1573/1900 [31:41<06:41,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1574/1900 [31:43<06:35,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1575/1900 [31:44<06:38,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1576/1900 [31:45<06:33,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1577/1900 [31:46<06:35,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1578/1900 [31:47<06:31,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1579/1900 [31:49<06:31,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1580/1900 [31:50<06:37,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1581/1900 [31:51<06:48,  1.28s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1582/1900 [31:53<06:45,  1.28s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1583/1900 [31:54<06:41,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1584/1900 [31:55<06:45,  1.28s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1585/1900 [31:56<06:41,  1.28s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1586/1900 [31:58<06:36,  1.26s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1587/1900 [31:59<06:24,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1588/1900 [32:00<06:16,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1589/1900 [32:01<06:16,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1590/1900 [32:02<06:16,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1591/1900 [32:04<06:21,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1592/1900 [32:05<06:12,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1593/1900 [32:06<06:12,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1594/1900 [32:07<06:12,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1595/1900 [32:08<06:10,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1596/1900 [32:10<06:08,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1597/1900 [32:11<06:06,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1598/1900 [32:12<06:00,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1599/1900 [32:13<05:55,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1600/1900 [32:14<05:53,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1601/1900 [32:16<05:51,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1602/1900 [32:17<05:50,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1603/1900 [32:18<05:51,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1604/1900 [32:19<05:54,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1605/1900 [32:20<05:48,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1606/1900 [32:21<05:49,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1607/1900 [32:23<05:47,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1608/1900 [32:24<05:49,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1609/1900 [32:25<05:59,  1.23s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1610/1900 [32:26<05:52,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1611/1900 [32:28<05:45,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1612/1900 [32:29<05:41,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1613/1900 [32:30<05:36,  1.17s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1614/1900 [32:31<05:41,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1615/1900 [32:32<05:39,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1616/1900 [32:33<05:36,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1617/1900 [32:35<05:38,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1618/1900 [32:36<05:42,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1619/1900 [32:37<05:41,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1620/1900 [32:38<05:37,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1621/1900 [32:40<05:36,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1622/1900 [32:41<05:30,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1623/1900 [32:42<05:30,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1624/1900 [32:43<05:25,  1.18s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1625/1900 [32:44<05:34,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1626/1900 [32:46<05:36,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1627/1900 [32:47<05:38,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1628/1900 [32:48<05:34,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1629/1900 [32:49<05:31,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1630/1900 [32:50<05:28,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1631/1900 [32:52<05:37,  1.25s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1632/1900 [32:53<05:30,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1633/1900 [32:54<05:27,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1634/1900 [32:55<05:22,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1635/1900 [32:57<05:18,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1636/1900 [32:58<05:17,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1637/1900 [32:59<05:23,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1638/1900 [33:00<05:16,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1639/1900 [33:01<05:18,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1640/1900 [33:03<05:15,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1641/1900 [33:04<05:12,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1642/1900 [33:05<05:16,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1643/1900 [33:06<05:15,  1.23s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1644/1900 [33:08<05:09,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1645/1900 [33:09<05:04,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1646/1900 [33:10<05:08,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1647/1900 [33:11<05:07,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1648/1900 [33:12<05:08,  1.23s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1649/1900 [33:14<05:04,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1650/1900 [33:15<05:03,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1651/1900 [33:16<04:59,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1652/1900 [33:17<04:56,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1653/1900 [33:18<04:53,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1654/1900 [33:20<04:53,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1655/1900 [33:21<04:57,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1656/1900 [33:22<04:56,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1657/1900 [33:23<04:56,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1658/1900 [33:24<04:54,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1659/1900 [33:26<05:02,  1.25s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1660/1900 [33:27<04:57,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1661/1900 [33:28<04:58,  1.25s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1662/1900 [33:29<04:51,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1663/1900 [33:31<04:44,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1664/1900 [33:32<04:47,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1665/1900 [33:33<04:45,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1666/1900 [33:34<04:53,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1667/1900 [33:36<04:50,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1668/1900 [33:37<04:44,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1669/1900 [33:38<04:42,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1670/1900 [33:39<04:43,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1671/1900 [33:41<04:42,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1672/1900 [33:42<04:41,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1673/1900 [33:43<04:44,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1674/1900 [33:44<04:48,  1.27s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1675/1900 [33:46<04:43,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1676/1900 [33:47<04:38,  1.24s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1677/1900 [33:48<04:32,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1678/1900 [33:49<04:27,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1679/1900 [33:50<04:28,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1680/1900 [33:52<04:25,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1681/1900 [33:53<04:26,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1682/1900 [33:54<04:22,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1683/1900 [33:55<04:23,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1684/1900 [33:56<04:20,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1685/1900 [33:58<04:17,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1686/1900 [33:59<04:17,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1687/1900 [34:00<04:18,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1688/1900 [34:01<04:18,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1689/1900 [34:02<04:15,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1690/1900 [34:04<04:13,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1691/1900 [34:05<04:16,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1692/1900 [34:06<04:12,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1693/1900 [34:07<04:15,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1694/1900 [34:09<04:14,  1.24s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1695/1900 [34:10<04:10,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1696/1900 [34:11<04:06,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1697/1900 [34:12<04:07,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1698/1900 [34:13<04:06,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1699/1900 [34:15<04:02,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1700/1900 [34:16<04:03,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1701/1900 [34:17<04:04,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1702/1900 [34:18<04:02,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1703/1900 [34:20<03:59,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1704/1900 [34:21<03:58,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1705/1900 [34:22<03:54,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1706/1900 [34:23<03:55,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1707/1900 [34:24<03:53,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1708/1900 [34:26<03:54,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1709/1900 [34:27<03:52,  1.22s/it]
+
+
Evaluating eval...:  90%|█████████ | 1710/1900 [34:28<03:51,  1.22s/it]
+
+
Evaluating eval...:  90%|█████████ | 1711/1900 [34:29<03:47,  1.21s/it]
+
+
Evaluating eval...:  90%|█████████ | 1712/1900 [34:30<03:45,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1713/1900 [34:32<03:41,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1714/1900 [34:33<03:37,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1715/1900 [34:34<03:39,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1716/1900 [34:35<03:39,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1717/1900 [34:36<03:46,  1.24s/it]
+
+
Evaluating eval...:  90%|█████████ | 1718/1900 [34:38<03:46,  1.25s/it]
+
+
Evaluating eval...:  90%|█████████ | 1719/1900 [34:39<03:42,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1720/1900 [34:40<03:42,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1721/1900 [34:41<03:39,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1722/1900 [34:43<03:39,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1723/1900 [34:44<03:34,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1724/1900 [34:45<03:37,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1725/1900 [34:46<03:35,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1726/1900 [34:48<03:35,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1727/1900 [34:49<03:34,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1728/1900 [34:50<03:28,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1729/1900 [34:51<03:24,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1730/1900 [34:52<03:25,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1731/1900 [34:54<03:22,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1732/1900 [34:55<03:21,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1733/1900 [34:56<03:21,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1734/1900 [34:57<03:18,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1735/1900 [34:58<03:17,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1736/1900 [35:00<03:19,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1737/1900 [35:01<03:17,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1738/1900 [35:02<03:15,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1739/1900 [35:03<03:16,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1740/1900 [35:04<03:13,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1741/1900 [35:06<03:12,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1742/1900 [35:07<03:09,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1743/1900 [35:08<03:07,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1744/1900 [35:09<03:05,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1745/1900 [35:10<03:03,  1.18s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1746/1900 [35:12<03:09,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1747/1900 [35:13<03:06,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1748/1900 [35:14<03:05,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1749/1900 [35:15<03:04,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1750/1900 [35:17<03:04,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1751/1900 [35:18<03:02,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1752/1900 [35:19<02:59,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1753/1900 [35:20<02:56,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1754/1900 [35:21<02:54,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1755/1900 [35:23<02:56,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1756/1900 [35:24<02:56,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1757/1900 [35:25<02:59,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1758/1900 [35:26<02:54,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1759/1900 [35:27<02:50,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1760/1900 [35:29<02:47,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1761/1900 [35:30<02:45,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1762/1900 [35:31<02:46,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1763/1900 [35:32<02:43,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1764/1900 [35:34<02:49,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1765/1900 [35:35<02:48,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1766/1900 [35:36<02:44,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1767/1900 [35:37<02:42,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1768/1900 [35:39<02:42,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1769/1900 [35:40<02:41,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1770/1900 [35:41<02:44,  1.27s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1771/1900 [35:42<02:42,  1.26s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1772/1900 [35:44<02:37,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1773/1900 [35:45<02:35,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1774/1900 [35:46<02:33,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1775/1900 [35:47<02:33,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1776/1900 [35:48<02:30,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1777/1900 [35:50<02:27,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1778/1900 [35:51<02:26,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1779/1900 [35:52<02:22,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1780/1900 [35:53<02:21,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1781/1900 [35:54<02:19,  1.17s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1782/1900 [35:55<02:20,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1783/1900 [35:57<02:22,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1784/1900 [35:58<02:19,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1785/1900 [35:59<02:17,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1786/1900 [36:00<02:16,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1787/1900 [36:01<02:14,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1788/1900 [36:03<02:13,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1789/1900 [36:04<02:10,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1790/1900 [36:05<02:10,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1791/1900 [36:06<02:10,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1792/1900 [36:07<02:08,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1793/1900 [36:09<02:08,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1794/1900 [36:10<02:05,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1795/1900 [36:11<02:04,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1796/1900 [36:12<02:02,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1797/1900 [36:13<02:02,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1798/1900 [36:15<02:03,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1799/1900 [36:16<02:01,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1800/1900 [36:17<01:59,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1801/1900 [36:18<01:57,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1802/1900 [36:19<01:56,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1803/1900 [36:21<01:57,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1804/1900 [36:22<01:54,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1805/1900 [36:23<01:52,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1806/1900 [36:24<01:52,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1807/1900 [36:25<01:50,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1808/1900 [36:26<01:48,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1809/1900 [36:28<01:46,  1.17s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1810/1900 [36:29<01:46,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1811/1900 [36:30<01:46,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1812/1900 [36:31<01:44,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1813/1900 [36:32<01:43,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1814/1900 [36:34<01:43,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1815/1900 [36:35<01:40,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1816/1900 [36:36<01:41,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1817/1900 [36:37<01:43,  1.24s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1818/1900 [36:39<01:40,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1819/1900 [36:40<01:37,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1820/1900 [36:41<01:36,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1821/1900 [36:42<01:36,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1822/1900 [36:43<01:34,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1823/1900 [36:44<01:31,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1824/1900 [36:46<01:32,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1825/1900 [36:47<01:31,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1826/1900 [36:48<01:30,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1827/1900 [36:49<01:29,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1828/1900 [36:51<01:29,  1.24s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1829/1900 [36:52<01:30,  1.27s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1830/1900 [36:53<01:27,  1.25s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1831/1900 [36:54<01:24,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1832/1900 [36:56<01:21,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1833/1900 [36:57<01:20,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1834/1900 [36:58<01:19,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1835/1900 [36:59<01:17,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1836/1900 [37:00<01:16,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1837/1900 [37:02<01:17,  1.24s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1838/1900 [37:03<01:15,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1839/1900 [37:04<01:14,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1840/1900 [37:05<01:13,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1841/1900 [37:07<01:11,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1842/1900 [37:08<01:10,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1843/1900 [37:09<01:08,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1844/1900 [37:10<01:07,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1845/1900 [37:11<01:05,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1846/1900 [37:13<01:05,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1847/1900 [37:14<01:03,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1848/1900 [37:15<01:03,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1849/1900 [37:16<01:02,  1.23s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1850/1900 [37:17<01:00,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1851/1900 [37:19<00:59,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1852/1900 [37:20<00:57,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1853/1900 [37:21<00:57,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1854/1900 [37:22<00:55,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1855/1900 [37:24<00:55,  1.23s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1856/1900 [37:25<00:53,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1857/1900 [37:26<00:51,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1858/1900 [37:27<00:50,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1859/1900 [37:28<00:49,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1860/1900 [37:29<00:48,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1861/1900 [37:31<00:46,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1862/1900 [37:32<00:45,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1863/1900 [37:33<00:43,  1.18s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1864/1900 [37:34<00:42,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1865/1900 [37:35<00:41,  1.18s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1866/1900 [37:37<00:40,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1867/1900 [37:38<00:40,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1868/1900 [37:39<00:38,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1869/1900 [37:40<00:38,  1.24s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1870/1900 [37:42<00:36,  1.23s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1871/1900 [37:43<00:36,  1.25s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1872/1900 [37:44<00:34,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1873/1900 [37:45<00:32,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1874/1900 [37:46<00:31,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1875/1900 [37:48<00:30,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1876/1900 [37:49<00:29,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1877/1900 [37:50<00:28,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1878/1900 [37:51<00:26,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1879/1900 [37:53<00:25,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1880/1900 [37:54<00:23,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1881/1900 [37:55<00:22,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1882/1900 [37:56<00:21,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1883/1900 [37:57<00:21,  1.25s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1884/1900 [37:59<00:20,  1.27s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1885/1900 [38:00<00:18,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1886/1900 [38:01<00:17,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1887/1900 [38:02<00:15,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1888/1900 [38:03<00:14,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1889/1900 [38:05<00:13,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1890/1900 [38:06<00:11,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1891/1900 [38:07<00:10,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1892/1900 [38:08<00:09,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1893/1900 [38:09<00:08,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1894/1900 [38:11<00:07,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1895/1900 [38:12<00:06,  1.21s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1896/1900 [38:13<00:04,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1897/1900 [38:14<00:03,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1898/1900 [38:15<00:02,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1899/1900 [38:17<00:01,  1.20s/it]
+
+
Evaluating eval...: 100%|██████████| 1900/1900 [38:18<00:00,  1.32s/it]
Evaluating eval...: 100%|██████████| 1900/1900 [38:18<00:00,  1.21s/it]
+Eval results for step (60000 / 100000 | Eval Loss: 1.017992377281189 | Eval wer: 25.980787307946727 | Eval wer_ortho: 29.260534672159288 |)
+
                                                                             
Eval results for step (60000 / 100000 | Eval Loss: 1.017992377281189 | Eval wer: 25.980787307946727 | Eval wer_ortho: 29.260534672159288 |)
+
Train steps ... :  60%|██████    | 60000/100000 [18:18:33<6:30:04,  1.71it/s]
Train steps ... :  60%|██████    | 60001/100000 [18:18:33<8469:33:20, 762.28s/it]
Train steps ... :  60%|██████    | 60002/100000 [18:18:34<5930:29:21, 533.77s/it]
Train steps ... :  60%|██████    | 60003/100000 [18:18:34<4153:10:44, 373.81s/it]
Train steps ... :  60%|██████    | 60004/100000 [18:18:35<2909:06:46, 261.85s/it]
Train steps ... :  60%|██████    | 60005/100000 [18:18:35<2038:16:17, 183.47s/it]
Train steps ... :  60%|██████    | 60006/100000 [18:18:36<1428:42:02, 128.60s/it]
Train steps ... :  60%|██████    | 60007/100000 [18:18:37<1002:00:53, 90.20s/it] 
Train steps ... :  60%|██████    | 60008/100000 [18:18:37<703:20:52, 63.31s/it] 
Train steps ... :  60%|██████    | 60009/100000 [18:18:38<494:17:01, 44.50s/it]
Train steps ... :  60%|██████    | 60010/100000 [18:18:38<347:56:08, 31.32s/it]
Train steps ... :  60%|██████    | 60011/100000 [18:18:39<245:29:33, 22.10s/it]
Train steps ... :  60%|██████    | 60012/100000 [18:18:39<173:46:40, 15.64s/it]
Train steps ... :  60%|██████    | 60013/100000 [18:18:40<123:35:02, 11.13s/it]
Train steps ... :  60%|██████    | 60014/100000 [18:18:41<88:27:11,  7.96s/it] 
Train steps ... :  60%|██████    | 60015/100000 [18:18:41<63:51:45,  5.75s/it]
Train steps ... :  60%|██████    | 60016/100000 [18:18:42<46:38:46,  4.20s/it]
Train steps ... :  60%|██████    | 60017/100000 [18:18:42<34:35:39,  3.11s/it]
Train steps ... :  60%|██████    | 60018/100000 [18:18:43<26:09:20,  2.36s/it]
Train steps ... :  60%|██████    | 60019/100000 [18:18:44<20:16:08,  1.83s/it]
Train steps ... :  60%|██████    | 60020/100000 [18:18:44<16:08:38,  1.45s/it]
Train steps ... :  60%|██████    | 60021/100000 [18:18:45<13:14:58,  1.19s/it]
Train steps ... :  60%|██████    | 60022/100000 [18:18:45<11:13:28,  1.01s/it]
Train steps ... :  60%|██████    | 60023/100000 [18:18:46<9:48:19,  1.13it/s] 
Train steps ... :  60%|██████    | 60024/100000 [18:18:46<8:48:29,  1.26it/s]
Train steps ... :  60%|██████    | 60025/100000 [18:18:47<8:06:34,  1.37it/s]Step... (60025 / 100000 | Loss: 0.6611750721931458, Learning Rate: 4.017587939698493e-05)
+
                                                                             
Step... (60025 / 100000 | Loss: 0.7510958909988403, Learning Rate: 4.017587939698493e-05)
+
Train steps ... :  60%|██████    | 60025/100000 [18:18:47<8:06:34,  1.37it/s]
Train steps ... :  60%|██████    | 60026/100000 [18:18:48<7:37:07,  1.46it/s]
Train steps ... :  60%|██████    | 60027/100000 [18:18:48<7:16:37,  1.53it/s]
Train steps ... :  60%|██████    | 60028/100000 [18:18:49<7:02:19,  1.58it/s]
Train steps ... :  60%|██████    | 60029/100000 [18:18:49<6:52:16,  1.62it/s]
Train steps ... :  60%|██████    | 60030/100000 [18:18:50<6:45:21,  1.64it/s]
Train steps ... :  60%|██████    | 60031/100000 [18:18:51<6:41:12,  1.66it/s]
Train steps ... :  60%|██████    | 60032/100000 [18:18:51<6:37:15,  1.68it/s]
Train steps ... :  60%|██████    | 60033/100000 [18:18:52<6:34:40,  1.69it/s]
Train steps ... :  60%|██████    | 60034/100000 [18:18:52<6:32:55,  1.70it/s]
Train steps ... :  60%|██████    | 60035/100000 [18:18:53<6:31:47,  1.70it/s]
Train steps ... :  60%|██████    | 60036/100000 [18:18:53<6:30:59,  1.70it/s]
Train steps ... :  60%|██████    | 60037/100000 [18:18:54<6:30:38,  1.70it/s]
Train steps ... :  60%|██████    | 60038/100000 [18:18:55<6:29:54,  1.71it/s]
Train steps ... :  60%|██████    | 60039/100000 [18:18:55<6:29:38,  1.71it/s]
Train steps ... :  60%|██████    | 60040/100000 [18:18:56<6:29:20,  1.71it/s]
Train steps ... :  60%|██████    | 60041/100000 [18:18:56<6:29:47,  1.71it/s]
Train steps ... :  60%|██████    | 60042/100000 [18:18:57<6:30:39,  1.70it/s]
Train steps ... :  60%|██████    | 60043/100000 [18:18:58<6:28:56,  1.71it/s]
Train steps ... :  60%|██████    | 60044/100000 [18:18:58<6:29:54,  1.71it/s]
Train steps ... :  60%|██████    | 60045/100000 [18:18:59<6:29:03,  1.71it/s]
Train steps ... :  60%|██████    | 60046/100000 [18:18:59<6:30:07,  1.71it/s]
Train steps ... :  60%|██████    | 60047/100000 [18:19:00<6:30:48,  1.70it/s]
Train steps ... :  60%|██████    | 60048/100000 [18:19:00<6:30:28,  1.71it/s]
Train steps ... :  60%|██████    | 60049/100000 [18:19:01<6:29:38,  1.71it/s]
Train steps ... :  60%|██████    | 60050/100000 [18:19:02<6:29:41,  1.71it/s]Step... (60050 / 100000 | Loss: 0.8174548745155334, Learning Rate: 4.0150753768844224e-05)
+
                                                                             
Step... (60050 / 100000 | Loss: 0.7333468794822693, Learning Rate: 4.0150753768844224e-05)
+
Train steps ... :  60%|██████    | 60050/100000 [18:19:02<6:29:41,  1.71it/s]
Train steps ... :  60%|██████    | 60051/100000 [18:19:02<6:29:21,  1.71it/s]
Train steps ... :  60%|██████    | 60052/100000 [18:19:03<6:28:56,  1.71it/s]
Train steps ... :  60%|██████    | 60053/100000 [18:19:03<6:29:45,  1.71it/s]
Train steps ... :  60%|██████    | 60054/100000 [18:19:04<6:29:29,  1.71it/s]
Train steps ... :  60%|██████    | 60055/100000 [18:19:05<6:29:04,  1.71it/s]
Train steps ... :  60%|██████    | 60056/100000 [18:19:05<6:29:30,  1.71it/s]
Train steps ... :  60%|██████    | 60057/100000 [18:19:06<6:29:24,  1.71it/s]
Train steps ... :  60%|██████    | 60058/100000 [18:19:06<6:29:23,  1.71it/s]
Train steps ... :  60%|██████    | 60059/100000 [18:19:07<6:29:19,  1.71it/s]
Train steps ... :  60%|██████    | 60060/100000 [18:19:07<6:29:14,  1.71it/s]
Train steps ... :  60%|██████    | 60061/100000 [18:19:08<6:28:55,  1.71it/s]
Train steps ... :  60%|██████    | 60062/100000 [18:19:09<6:28:39,  1.71it/s]
Train steps ... :  60%|██████    | 60063/100000 [18:19:09<6:28:59,  1.71it/s]
Train steps ... :  60%|██████    | 60064/100000 [18:19:10<6:28:38,  1.71it/s]
Train steps ... :  60%|██████    | 60065/100000 [18:19:10<6:28:32,  1.71it/s]
Train steps ... :  60%|██████    | 60066/100000 [18:19:11<6:28:36,  1.71it/s]
Train steps ... :  60%|██████    | 60067/100000 [18:19:12<6:28:31,  1.71it/s]
Train steps ... :  60%|██████    | 60068/100000 [18:19:12<6:28:27,  1.71it/s]
Train steps ... :  60%|██████    | 60069/100000 [18:19:13<6:28:13,  1.71it/s]
Train steps ... :  60%|██████    | 60070/100000 [18:19:13<6:28:03,  1.71it/s]
Train steps ... :  60%|██████    | 60071/100000 [18:19:14<6:27:55,  1.72it/s]
Train steps ... :  60%|██████    | 60072/100000 [18:19:14<6:27:58,  1.72it/s]
Train steps ... :  60%|██████    | 60073/100000 [18:19:15<6:28:57,  1.71it/s]
Train steps ... :  60%|██████    | 60074/100000 [18:19:16<6:29:21,  1.71it/s]
Train steps ... :  60%|██████    | 60075/100000 [18:19:16<6:28:51,  1.71it/s]Step... (60075 / 100000 | Loss: 0.5022232532501221, Learning Rate: 4.012562814070352e-05)
+
                                                                             
Step... (60075 / 100000 | Loss: 1.0095033645629883, Learning Rate: 4.012562814070352e-05)
+
Train steps ... :  60%|██████    | 60075/100000 [18:19:17<6:28:51,  1.71it/s]
Train steps ... :  60%|██████    | 60076/100000 [18:19:17<6:29:01,  1.71it/s]
Train steps ... :  60%|██████    | 60077/100000 [18:19:17<6:28:39,  1.71it/s]
Train steps ... :  60%|██████    | 60078/100000 [18:19:18<6:28:23,  1.71it/s]
Train steps ... :  60%|██████    | 60079/100000 [18:19:19<6:28:43,  1.71it/s]
Train steps ... :  60%|██████    | 60080/100000 [18:19:19<6:28:49,  1.71it/s]
Train steps ... :  60%|██████    | 60081/100000 [18:19:20<6:28:37,  1.71it/s]
Train steps ... :  60%|██████    | 60082/100000 [18:19:20<6:28:37,  1.71it/s]
Train steps ... :  60%|██████    | 60083/100000 [18:19:21<6:28:30,  1.71it/s]
Train steps ... :  60%|██████    | 60084/100000 [18:19:22<6:28:33,  1.71it/s]
Train steps ... :  60%|██████    | 60085/100000 [18:19:22<6:28:21,  1.71it/s]
Train steps ... :  60%|██████    | 60086/100000 [18:19:23<6:28:34,  1.71it/s]
Train steps ... :  60%|██████    | 60087/100000 [18:19:23<6:29:15,  1.71it/s]
Train steps ... :  60%|██████    | 60088/100000 [18:19:24<6:29:10,  1.71it/s]
Train steps ... :  60%|██████    | 60089/100000 [18:19:24<6:28:51,  1.71it/s]
Train steps ... :  60%|██████    | 60090/100000 [18:19:25<6:29:00,  1.71it/s]
Train steps ... :  60%|██████    | 60091/100000 [18:19:26<6:28:32,  1.71it/s]
Train steps ... :  60%|██████    | 60092/100000 [18:19:26<6:28:40,  1.71it/s]
Train steps ... :  60%|██████    | 60093/100000 [18:19:27<6:28:39,  1.71it/s]
Train steps ... :  60%|██████    | 60094/100000 [18:19:27<6:28:15,  1.71it/s]
Train steps ... :  60%|██████    | 60095/100000 [18:19:28<6:28:02,  1.71it/s]
Train steps ... :  60%|██████    | 60096/100000 [18:19:29<6:28:25,  1.71it/s]
Train steps ... :  60%|██████    | 60097/100000 [18:19:29<6:28:14,  1.71it/s]
Train steps ... :  60%|██████    | 60098/100000 [18:19:30<6:28:52,  1.71it/s]
Train steps ... :  60%|██████    | 60099/100000 [18:19:30<6:28:39,  1.71it/s]
Train steps ... :  60%|██████    | 60100/100000 [18:19:31<6:28:34,  1.71it/s]Step... (60100 / 100000 | Loss: 0.6236955523490906, Learning Rate: 4.010050251256282e-05)
+
                                                                             
Step... (60100 / 100000 | Loss: 0.5744083523750305, Learning Rate: 4.010050251256282e-05)
+
Train steps ... :  60%|██████    | 60100/100000 [18:19:31<6:28:34,  1.71it/s]
Train steps ... :  60%|██████    | 60101/100000 [18:19:31<6:28:36,  1.71it/s]
Train steps ... :  60%|██████    | 60102/100000 [18:19:32<6:28:37,  1.71it/s]
Train steps ... :  60%|██████    | 60103/100000 [18:19:33<6:29:06,  1.71it/s]
Train steps ... :  60%|██████    | 60104/100000 [18:19:33<6:29:09,  1.71it/s]
Train steps ... :  60%|██████    | 60105/100000 [18:19:34<6:28:53,  1.71it/s]
Train steps ... :  60%|██████    | 60106/100000 [18:19:34<6:29:55,  1.71it/s]
Train steps ... :  60%|██████    | 60107/100000 [18:19:35<6:28:41,  1.71it/s]
Train steps ... :  60%|██████    | 60108/100000 [18:19:36<6:29:24,  1.71it/s]
Train steps ... :  60%|██████    | 60109/100000 [18:19:36<6:29:13,  1.71it/s]
Train steps ... :  60%|██████    | 60110/100000 [18:19:37<6:29:00,  1.71it/s]
Train steps ... :  60%|██████    | 60111/100000 [18:19:37<6:29:18,  1.71it/s]
Train steps ... :  60%|██████    | 60112/100000 [18:19:38<6:29:00,  1.71it/s]
Train steps ... :  60%|██████    | 60113/100000 [18:19:38<6:28:35,  1.71it/s]
Train steps ... :  60%|██████    | 60114/100000 [18:19:39<6:28:22,  1.71it/s]
Train steps ... :  60%|██████    | 60115/100000 [18:19:40<6:28:28,  1.71it/s]
Train steps ... :  60%|██████    | 60116/100000 [18:19:40<6:28:11,  1.71it/s]
Train steps ... :  60%|██████    | 60117/100000 [18:19:41<6:28:09,  1.71it/s]
Train steps ... :  60%|██████    | 60118/100000 [18:19:41<6:27:44,  1.71it/s]
Train steps ... :  60%|██████    | 60119/100000 [18:19:42<6:27:33,  1.72it/s]
Train steps ... :  60%|██████    | 60120/100000 [18:19:43<6:27:46,  1.71it/s]
Train steps ... :  60%|██████    | 60121/100000 [18:19:43<6:27:53,  1.71it/s]
Train steps ... :  60%|██████    | 60122/100000 [18:19:44<6:27:26,  1.72it/s]
Train steps ... :  60%|██████    | 60123/100000 [18:19:44<6:27:32,  1.71it/s]
Train steps ... :  60%|██████    | 60124/100000 [18:19:45<6:27:26,  1.72it/s]
Train steps ... :  60%|██████    | 60125/100000 [18:19:45<6:27:35,  1.71it/s]Step... (60125 / 100000 | Loss: 0.9190086126327515, Learning Rate: 4.0075376884422113e-05)
+
                                                                             
Step... (60125 / 100000 | Loss: 0.7438170909881592, Learning Rate: 4.0075376884422113e-05)
+
Train steps ... :  60%|██████    | 60125/100000 [18:19:46<6:27:35,  1.71it/s]
Train steps ... :  60%|██████    | 60126/100000 [18:19:46<6:28:00,  1.71it/s]
Train steps ... :  60%|██████    | 60127/100000 [18:19:47<6:27:49,  1.71it/s]
Train steps ... :  60%|██████    | 60128/100000 [18:19:47<6:28:05,  1.71it/s]
Train steps ... :  60%|██████    | 60129/100000 [18:19:48<6:27:50,  1.71it/s]
Train steps ... :  60%|██████    | 60130/100000 [18:19:48<6:27:46,  1.71it/s]
Train steps ... :  60%|██████    | 60131/100000 [18:19:49<6:28:21,  1.71it/s]
Train steps ... :  60%|██████    | 60132/100000 [18:19:50<6:28:52,  1.71it/s]
Train steps ... :  60%|██████    | 60133/100000 [18:19:50<6:28:42,  1.71it/s]
Train steps ... :  60%|██████    | 60134/100000 [18:19:51<6:28:27,  1.71it/s]
Train steps ... :  60%|██████    | 60135/100000 [18:19:51<6:28:19,  1.71it/s]
Train steps ... :  60%|██████    | 60136/100000 [18:19:52<6:28:05,  1.71it/s]
Train steps ... :  60%|██████    | 60137/100000 [18:19:52<6:27:45,  1.71it/s]
Train steps ... :  60%|██████    | 60138/100000 [18:19:53<6:28:13,  1.71it/s]
Train steps ... :  60%|██████    | 60139/100000 [18:19:54<6:28:35,  1.71it/s]
Train steps ... :  60%|██████    | 60140/100000 [18:19:54<6:28:43,  1.71it/s]
Train steps ... :  60%|██████    | 60141/100000 [18:19:55<6:28:48,  1.71it/s]
Train steps ... :  60%|██████    | 60142/100000 [18:19:55<6:28:16,  1.71it/s]
Train steps ... :  60%|██████    | 60143/100000 [18:19:56<6:29:06,  1.71it/s]
Train steps ... :  60%|██████    | 60144/100000 [18:19:57<6:28:28,  1.71it/s]
Train steps ... :  60%|██████    | 60145/100000 [18:19:57<6:28:22,  1.71it/s]
Train steps ... :  60%|██████    | 60146/100000 [18:19:58<6:28:09,  1.71it/s]
Train steps ... :  60%|██████    | 60147/100000 [18:19:58<6:28:07,  1.71it/s]
Train steps ... :  60%|██████    | 60148/100000 [18:19:59<6:28:24,  1.71it/s]
Train steps ... :  60%|██████    | 60149/100000 [18:19:59<6:28:11,  1.71it/s]
Train steps ... :  60%|██████    | 60150/100000 [18:20:00<6:28:17,  1.71it/s]Step... (60150 / 100000 | Loss: 0.784695029258728, Learning Rate: 4.005025125628141e-05)
+
                                                                             
Step... (60150 / 100000 | Loss: 0.9955648183822632, Learning Rate: 4.005025125628141e-05)
+
Train steps ... :  60%|██████    | 60150/100000 [18:20:00<6:28:17,  1.71it/s]
Train steps ... :  60%|██████    | 60151/100000 [18:20:01<6:27:54,  1.71it/s]
Train steps ... :  60%|██████    | 60152/100000 [18:20:01<6:27:44,  1.71it/s]
Train steps ... :  60%|██████    | 60153/100000 [18:20:02<6:27:47,  1.71it/s]
Train steps ... :  60%|██████    | 60154/100000 [18:20:02<6:28:02,  1.71it/s]
Train steps ... :  60%|██████    | 60155/100000 [18:20:03<6:27:49,  1.71it/s]
Train steps ... :  60%|██████    | 60156/100000 [18:20:04<6:28:16,  1.71it/s]
Train steps ... :  60%|██████    | 60157/100000 [18:20:04<6:28:27,  1.71it/s]
Train steps ... :  60%|██████    | 60158/100000 [18:20:05<6:27:59,  1.71it/s]
Train steps ... :  60%|██████    | 60159/100000 [18:20:05<6:27:45,  1.71it/s]
Train steps ... :  60%|██████    | 60160/100000 [18:20:06<6:27:40,  1.71it/s]
Train steps ... :  60%|██████    | 60161/100000 [18:20:07<6:28:00,  1.71it/s]
Train steps ... :  60%|██████    | 60162/100000 [18:20:07<6:28:22,  1.71it/s]
Train steps ... :  60%|██████    | 60163/100000 [18:20:08<6:27:57,  1.71it/s]
Train steps ... :  60%|██████    | 60164/100000 [18:20:08<6:28:16,  1.71it/s]
Train steps ... :  60%|██████    | 60165/100000 [18:20:09<6:27:58,  1.71it/s]
Train steps ... :  60%|██████    | 60166/100000 [18:20:09<6:28:07,  1.71it/s]
Train steps ... :  60%|██████    | 60167/100000 [18:20:10<6:27:44,  1.71it/s]
Train steps ... :  60%|██████    | 60168/100000 [18:20:11<6:27:24,  1.71it/s]
Train steps ... :  60%|██████    | 60169/100000 [18:20:11<6:27:44,  1.71it/s]
Train steps ... :  60%|██████    | 60170/100000 [18:20:12<6:27:44,  1.71it/s]
Train steps ... :  60%|██████    | 60171/100000 [18:20:12<6:27:18,  1.71it/s]
Train steps ... :  60%|██████    | 60172/100000 [18:20:13<6:27:35,  1.71it/s]
Train steps ... :  60%|██████    | 60173/100000 [18:20:14<6:27:36,  1.71it/s]
Train steps ... :  60%|██████    | 60174/100000 [18:20:14<6:27:41,  1.71it/s]
Train steps ... :  60%|██████    | 60175/100000 [18:20:15<6:27:40,  1.71it/s]Step... (60175 / 100000 | Loss: 0.9200769662857056, Learning Rate: 4.00251256281407e-05)
+
                                                                             
Step... (60175 / 100000 | Loss: 0.562822699546814, Learning Rate: 4.00251256281407e-05)
+
Train steps ... :  60%|██████    | 60175/100000 [18:20:15<6:27:40,  1.71it/s]
Train steps ... :  60%|██████    | 60176/100000 [18:20:15<6:28:00,  1.71it/s]
Train steps ... :  60%|██████    | 60177/100000 [18:20:16<6:27:53,  1.71it/s]
Train steps ... :  60%|██████    | 60178/100000 [18:20:16<6:28:33,  1.71it/s]
Train steps ... :  60%|██████    | 60179/100000 [18:20:17<6:28:23,  1.71it/s]
Train steps ... :  60%|██████    | 60180/100000 [18:20:18<6:28:07,  1.71it/s]
Train steps ... :  60%|██████    | 60181/100000 [18:20:18<6:28:07,  1.71it/s]
Train steps ... :  60%|██████    | 60182/100000 [18:20:19<6:27:47,  1.71it/s]
Train steps ... :  60%|██████    | 60183/100000 [18:20:19<6:27:36,  1.71it/s]
Train steps ... :  60%|██████    | 60184/100000 [18:20:20<6:27:38,  1.71it/s]
Train steps ... :  60%|██████    | 60185/100000 [18:20:21<6:28:03,  1.71it/s]
Train steps ... :  60%|██████    | 60186/100000 [18:20:21<6:27:45,  1.71it/s]
Train steps ... :  60%|██████    | 60187/100000 [18:20:22<6:27:51,  1.71it/s]
Train steps ... :  60%|██████    | 60188/100000 [18:20:22<6:27:52,  1.71it/s]
Train steps ... :  60%|██████    | 60189/100000 [18:20:23<6:27:31,  1.71it/s]
Train steps ... :  60%|██████    | 60190/100000 [18:20:23<6:27:26,  1.71it/s]
Train steps ... :  60%|██████    | 60191/100000 [18:20:24<6:28:17,  1.71it/s]
Train steps ... :  60%|██████    | 60192/100000 [18:20:25<6:28:41,  1.71it/s]
Train steps ... :  60%|██████    | 60193/100000 [18:20:25<6:28:07,  1.71it/s]
Train steps ... :  60%|██████    | 60194/100000 [18:20:26<6:27:59,  1.71it/s]
Train steps ... :  60%|██████    | 60195/100000 [18:20:26<6:28:19,  1.71it/s]
Train steps ... :  60%|██████    | 60196/100000 [18:20:27<6:28:00,  1.71it/s]
Train steps ... :  60%|██████    | 60197/100000 [18:20:28<6:27:46,  1.71it/s]
Train steps ... :  60%|██████    | 60198/100000 [18:20:28<6:27:35,  1.71it/s]
Train steps ... :  60%|██████    | 60199/100000 [18:20:29<6:27:31,  1.71it/s]
Train steps ... :  60%|██████    | 60200/100000 [18:20:29<6:27:04,  1.71it/s]Step... (60200 / 100000 | Loss: 0.6694826483726501, Learning Rate: 4e-05)
+
                                                                             
Step... (60200 / 100000 | Loss: 0.7641364336013794, Learning Rate: 4e-05)
+
Train steps ... :  60%|██████    | 60200/100000 [18:20:30<6:27:04,  1.71it/s]
Train steps ... :  60%|██████    | 60201/100000 [18:20:30<6:27:10,  1.71it/s]
Train steps ... :  60%|██████    | 60202/100000 [18:20:30<6:27:00,  1.71it/s]
Train steps ... :  60%|██████    | 60203/100000 [18:20:31<6:27:15,  1.71it/s]
Train steps ... :  60%|██████    | 60204/100000 [18:20:32<6:27:05,  1.71it/s]
Train steps ... :  60%|██████    | 60205/100000 [18:20:32<6:27:08,  1.71it/s]
Train steps ... :  60%|██████    | 60206/100000 [18:20:33<6:27:52,  1.71it/s]
Train steps ... :  60%|██████    | 60207/100000 [18:20:33<6:27:55,  1.71it/s]
Train steps ... :  60%|██████    | 60208/100000 [18:20:34<6:27:53,  1.71it/s]
Train steps ... :  60%|██████    | 60209/100000 [18:20:35<6:27:38,  1.71it/s]
Train steps ... :  60%|██████    | 60210/100000 [18:20:35<6:27:49,  1.71it/s]
Train steps ... :  60%|██████    | 60211/100000 [18:20:36<6:28:20,  1.71it/s]
Train steps ... :  60%|██████    | 60212/100000 [18:20:36<6:27:25,  1.71it/s]
Train steps ... :  60%|██████    | 60213/100000 [18:20:37<6:27:47,  1.71it/s]
Train steps ... :  60%|██████    | 60214/100000 [18:20:37<6:27:34,  1.71it/s]
Train steps ... :  60%|██████    | 60215/100000 [18:20:38<6:28:05,  1.71it/s]
Train steps ... :  60%|██████    | 60216/100000 [18:20:39<6:27:38,  1.71it/s]
Train steps ... :  60%|██████    | 60217/100000 [18:20:39<6:27:27,  1.71it/s]
Train steps ... :  60%|██████    | 60218/100000 [18:20:40<6:27:26,  1.71it/s]
Train steps ... :  60%|██████    | 60219/100000 [18:20:40<6:27:31,  1.71it/s]
Train steps ... :  60%|██████    | 60220/100000 [18:20:41<6:27:27,  1.71it/s]
Train steps ... :  60%|██████    | 60221/100000 [18:20:42<6:27:45,  1.71it/s]
Train steps ... :  60%|██████    | 60222/100000 [18:20:42<6:27:19,  1.71it/s]
Train steps ... :  60%|██████    | 60223/100000 [18:20:43<6:27:01,  1.71it/s]
Train steps ... :  60%|██████    | 60224/100000 [18:20:43<6:27:30,  1.71it/s]
Train steps ... :  60%|██████    | 60225/100000 [18:20:44<6:27:47,  1.71it/s]Step... (60225 / 100000 | Loss: 0.642896294593811, Learning Rate: 3.99748743718593e-05)
+
                                                                             
Step... (60225 / 100000 | Loss: 0.81590336561203, Learning Rate: 3.99748743718593e-05)
+
Train steps ... :  60%|██████    | 60225/100000 [18:20:44<6:27:47,  1.71it/s]
Train steps ... :  60%|██████    | 60226/100000 [18:20:44<6:27:52,  1.71it/s]
Train steps ... :  60%|███��██    | 60227/100000 [18:20:45<6:28:02,  1.71it/s]
Train steps ... :  60%|██████    | 60228/100000 [18:20:46<6:27:58,  1.71it/s]
Train steps ... :  60%|██████    | 60229/100000 [18:20:46<6:27:35,  1.71it/s]
Train steps ... :  60%|██████    | 60230/100000 [18:20:47<6:27:47,  1.71it/s]
Train steps ... :  60%|██████    | 60231/100000 [18:20:47<6:27:20,  1.71it/s]
Train steps ... :  60%|██████    | 60232/100000 [18:20:48<6:27:02,  1.71it/s]
Train steps ... :  60%|██████    | 60233/100000 [18:20:49<6:26:58,  1.71it/s]
Train steps ... :  60%|██████    | 60234/100000 [18:20:49<6:26:45,  1.71it/s]
Train steps ... :  60%|██████    | 60235/100000 [18:20:50<6:27:08,  1.71it/s]
Train steps ... :  60%|██████    | 60236/100000 [18:20:50<6:26:53,  1.71it/s]
Train steps ... :  60%|██████    | 60237/100000 [18:20:51<6:27:14,  1.71it/s]
Train steps ... :  60%|██████    | 60238/100000 [18:20:52<6:27:10,  1.71it/s]
Train steps ... :  60%|██████    | 60239/100000 [18:20:52<6:27:17,  1.71it/s]
Train steps ... :  60%|██████    | 60240/100000 [18:20:53<6:27:36,  1.71it/s]
Train steps ... :  60%|██████    | 60241/100000 [18:20:53<6:27:51,  1.71it/s]
Train steps ... :  60%|██████    | 60242/100000 [18:20:54<6:27:29,  1.71it/s]
Train steps ... :  60%|██████    | 60243/100000 [18:20:54<6:27:17,  1.71it/s]
Train steps ... :  60%|██████    | 60244/100000 [18:20:55<6:27:28,  1.71it/s]
Train steps ... :  60%|██████    | 60245/100000 [18:20:56<6:27:25,  1.71it/s]
Train steps ... :  60%|██████    | 60246/100000 [18:20:56<6:27:19,  1.71it/s]
Train steps ... :  60%|██████    | 60247/100000 [18:20:57<6:27:31,  1.71it/s]
Train steps ... :  60%|██████    | 60248/100000 [18:20:57<6:27:42,  1.71it/s]
Train steps ... :  60%|██████    | 60249/100000 [18:20:58<6:28:43,  1.70it/s]
Train steps ... :  60%|██████    | 60250/100000 [18:20:59<6:28:00,  1.71it/s]Step... (60250 / 100000 | Loss: 0.6613524556159973, Learning Rate: 3.9949748743718597e-05)
+
                                                                             
Step... (60250 / 100000 | Loss: 0.6212773323059082, Learning Rate: 3.9949748743718597e-05)
+
Train steps ... :  60%|██████    | 60250/100000 [18:20:59<6:28:00,  1.71it/s]
Train steps ... :  60%|██████    | 60251/100000 [18:20:59<6:28:19,  1.71it/s]
Train steps ... :  60%|██████    | 60252/100000 [18:21:00<6:28:43,  1.70it/s]
Train steps ... :  60%|██████    | 60253/100000 [18:21:00<6:28:05,  1.71it/s]
Train steps ... :  60%|██████    | 60254/100000 [18:21:01<6:27:42,  1.71it/s]
Train steps ... :  60%|██████    | 60255/100000 [18:21:01<6:27:05,  1.71it/s]
Train steps ... :  60%|██████    | 60256/100000 [18:21:02<6:27:46,  1.71it/s]
Train steps ... :  60%|██████    | 60257/100000 [18:21:03<6:27:21,  1.71it/s]
Train steps ... :  60%|██████    | 60258/100000 [18:21:03<6:27:49,  1.71it/s]
Train steps ... :  60%|██████    | 60259/100000 [18:21:04<6:27:26,  1.71it/s]
Train steps ... :  60%|██████    | 60260/100000 [18:21:04<6:27:20,  1.71it/s]
Train steps ... :  60%|██████    | 60261/100000 [18:21:05<6:27:08,  1.71it/s]
Train steps ... :  60%|██████    | 60262/100000 [18:21:06<6:27:09,  1.71it/s]
Train steps ... :  60%|██████    | 60263/100000 [18:21:06<6:27:30,  1.71it/s]
Train steps ... :  60%|██████    | 60264/100000 [18:21:07<6:27:41,  1.71it/s]
Train steps ... :  60%|██████    | 60265/100000 [18:21:07<6:28:26,  1.70it/s]
Train steps ... :  60%|██████    | 60266/100000 [18:21:08<6:27:24,  1.71it/s]
Train steps ... :  60%|██████    | 60267/100000 [18:21:08<6:27:47,  1.71it/s]
Train steps ... :  60%|██████    | 60268/100000 [18:21:09<6:28:01,  1.71it/s]
Train steps ... :  60%|██████    | 60269/100000 [18:21:10<6:27:25,  1.71it/s]
Train steps ... :  60%|██████    | 60270/100000 [18:21:10<6:27:16,  1.71it/s]
Train steps ... :  60%|██████    | 60271/100000 [18:21:11<6:26:50,  1.71it/s]
Train steps ... :  60%|██████    | 60272/100000 [18:21:11<6:26:52,  1.71it/s]
Train steps ... :  60%|██████    | 60273/100000 [18:21:12<6:27:16,  1.71it/s]
Train steps ... :  60%|██████    | 60274/100000 [18:21:13<6:26:49,  1.71it/s]
Train steps ... :  60%|██████    | 60275/100000 [18:21:13<6:27:09,  1.71it/s]Step... (60275 / 100000 | Loss: 1.0877643823623657, Learning Rate: 3.992462311557789e-05)
+
                                                                             
Step... (60275 / 100000 | Loss: 0.733521044254303, Learning Rate: 3.992462311557789e-05)
+
Train steps ... :  60%|██████    | 60275/100000 [18:21:13<6:27:09,  1.71it/s]
Train steps ... :  60%|██████    | 60276/100000 [18:21:14<6:27:21,  1.71it/s]
Train steps ... :  60%|██████    | 60277/100000 [18:21:14<6:27:18,  1.71it/s]
Train steps ... :  60%|██████    | 60278/100000 [18:21:15<6:27:27,  1.71it/s]
Train steps ... :  60%|██████    | 60279/100000 [18:21:16<6:27:45,  1.71it/s]
Train steps ... :  60%|██████    | 60280/100000 [18:21:16<6:27:30,  1.71it/s]
Train steps ... :  60%|██████    | 60281/100000 [18:21:17<6:27:18,  1.71it/s]
Train steps ... :  60%|██████    | 60282/100000 [18:21:17<6:27:20,  1.71it/s]
Train steps ... :  60%|██████    | 60283/100000 [18:21:18<6:27:19,  1.71it/s]
Train steps ... :  60%|██████    | 60284/100000 [18:21:18<6:26:53,  1.71it/s]
Train steps ... :  60%|██████    | 60285/100000 [18:21:19<6:26:29,  1.71it/s]
Train steps ... :  60%|██████    | 60286/100000 [18:21:20<6:26:26,  1.71it/s]
Train steps ... :  60%|██████    | 60287/100000 [18:21:20<6:26:24,  1.71it/s]
Train steps ... :  60%|██████    | 60288/100000 [18:21:21<6:26:58,  1.71it/s]
Train steps ... :  60%|██████    | 60289/100000 [18:21:21<6:27:08,  1.71it/s]
Train steps ... :  60%|██████    | 60290/100000 [18:21:22<6:26:57,  1.71it/s]
Train steps ... :  60%|██████    | 60291/100000 [18:21:23<6:26:33,  1.71it/s]
Train steps ... :  60%|██████    | 60292/100000 [18:21:23<6:26:33,  1.71it/s]
Train steps ... :  60%|██████    | 60293/100000 [18:21:24<6:26:39,  1.71it/s]
Train steps ... :  60%|██████    | 60294/100000 [18:21:24<6:26:34,  1.71it/s]
Train steps ... :  60%|██████    | 60295/100000 [18:21:25<6:26:12,  1.71it/s]
Train steps ... :  60%|██████    | 60296/100000 [18:21:25<6:26:57,  1.71it/s]
Train steps ... :  60%|██████    | 60297/100000 [18:21:26<6:26:42,  1.71it/s]
Train steps ... :  60%|██████    | 60298/100000 [18:21:27<6:27:00,  1.71it/s]
Train steps ... :  60%|██████    | 60299/100000 [18:21:27<6:26:55,  1.71it/s]
Train steps ... :  60%|██████    | 60300/100000 [18:21:28<6:26:37,  1.71it/s]Step... (60300 / 100000 | Loss: 0.5376139879226685, Learning Rate: 3.989949748743719e-05)
+
                                                                             
Step... (60300 / 100000 | Loss: 0.6398978233337402, Learning Rate: 3.989949748743719e-05)
+
Train steps ... :  60%|██████    | 60300/100000 [18:21:28<6:26:37,  1.71it/s]
Train steps ... :  60%|██████    | 60301/100000 [18:21:28<6:26:57,  1.71it/s]
Train steps ... :  60%|██████    | 60302/100000 [18:21:29<6:26:53,  1.71it/s]
Train steps ... :  60%|██████    | 60303/100000 [18:21:30<6:26:33,  1.71it/s]
Train steps ... :  60%|██████    | 60304/100000 [18:21:30<6:26:35,  1.71it/s]
Train steps ... :  60%|██████    | 60305/100000 [18:21:31<6:26:35,  1.71it/s]
Train steps ... :  60%|██████    | 60306/100000 [18:21:31<6:26:09,  1.71it/s]
Train steps ... :  60%|██████    | 60307/100000 [18:21:32<6:26:10,  1.71it/s]
Train steps ... :  60%|██████    | 60308/100000 [18:21:32<6:26:16,  1.71it/s]
Train steps ... :  60%|██████    | 60309/100000 [18:21:33<6:26:31,  1.71it/s]
Train steps ... :  60%|██████    | 60310/100000 [18:21:34<6:26:25,  1.71it/s]
Train steps ... :  60%|██████    | 60311/100000 [18:21:34<6:26:47,  1.71it/s]
Train steps ... :  60%|██████    | 60312/100000 [18:21:35<6:26:24,  1.71it/s]
Train steps ... :  60%|██████    | 60313/100000 [18:21:35<6:26:14,  1.71it/s]
Train steps ... :  60%|██████    | 60314/100000 [18:21:36<6:26:27,  1.71it/s]
Train steps ... :  60%|██████    | 60315/100000 [18:21:37<6:26:08,  1.71it/s]
Train steps ... :  60%|██████    | 60316/100000 [18:21:37<6:26:35,  1.71it/s]
Train steps ... :  60%|██████    | 60317/100000 [18:21:38<6:26:36,  1.71it/s]
Train steps ... :  60%|██████    | 60318/100000 [18:21:38<6:26:12,  1.71it/s]
Train steps ... :  60%|██████    | 60319/100000 [18:21:39<6:26:34,  1.71it/s]
Train steps ... :  60%|██████    | 60320/100000 [18:21:39<6:26:10,  1.71it/s]
Train steps ... :  60%|██████    | 60321/100000 [18:21:40<6:25:44,  1.71it/s]
Train steps ... :  60%|██████    | 60322/100000 [18:21:41<6:26:05,  1.71it/s]
Train steps ... :  60%|██████    | 60323/100000 [18:21:41<6:25:59,  1.71it/s]
Train steps ... :  60%|██████    | 60324/100000 [18:21:42<6:26:19,  1.71it/s]
Train steps ... :  60%|██████    | 60325/100000 [18:21:42<6:26:22,  1.71it/s]Step... (60325 / 100000 | Loss: 0.8311471939086914, Learning Rate: 3.9874371859296486e-05)
+
                                                                             
Step... (60325 / 100000 | Loss: 0.6541004180908203, Learning Rate: 3.9874371859296486e-05)
+
Train steps ... :  60%|██████    | 60325/100000 [18:21:43<6:26:22,  1.71it/s]
Train steps ... :  60%|██████    | 60326/100000 [18:21:43<6:26:47,  1.71it/s]
Train steps ... :  60%|██████    | 60327/100000 [18:21:44<6:26:36,  1.71it/s]
Train steps ... :  60%|██████    | 60328/100000 [18:21:44<6:26:39,  1.71it/s]
Train steps ... :  60%|██████    | 60329/100000 [18:21:45<6:26:57,  1.71it/s]
Train steps ... :  60%|██████    | 60330/100000 [18:21:45<6:26:24,  1.71it/s]
Train steps ... :  60%|██████    | 60331/100000 [18:21:46<6:26:11,  1.71it/s]
Train steps ... :  60%|██████    | 60332/100000 [18:21:46<6:25:53,  1.71it/s]
Train steps ... :  60%|██████    | 60333/100000 [18:21:47<6:25:39,  1.71it/s]
Train steps ... :  60%|██████    | 60334/100000 [18:21:48<6:26:26,  1.71it/s]
Train steps ... :  60%|██████    | 60335/100000 [18:21:48<6:26:44,  1.71it/s]
Train steps ... :  60%|██████    | 60336/100000 [18:21:49<6:26:59,  1.71it/s]
Train steps ... :  60%|██████    | 60337/100000 [18:21:49<6:26:51,  1.71it/s]
Train steps ... :  60%|██████    | 60338/100000 [18:21:50<6:26:30,  1.71it/s]
Train steps ... :  60%|██████    | 60339/100000 [18:21:51<6:26:54,  1.71it/s]
Train steps ... :  60%|██████    | 60340/100000 [18:21:51<6:26:25,  1.71it/s]
Train steps ... :  60%|██████    | 60341/100000 [18:21:52<6:26:07,  1.71it/s]
Train steps ... :  60%|██████    | 60342/100000 [18:21:52<6:26:22,  1.71it/s]
Train steps ... :  60%|██████    | 60343/100000 [18:21:53<6:26:25,  1.71it/s]
Train steps ... :  60%|██████    | 60344/100000 [18:21:53<6:26:44,  1.71it/s]
Train steps ... :  60%|██████    | 60345/100000 [18:21:54<6:27:02,  1.71it/s]
Train steps ... :  60%|██████    | 60346/100000 [18:21:55<6:26:18,  1.71it/s]
Train steps ... :  60%|██████    | 60347/100000 [18:21:55<6:25:58,  1.71it/s]
Train steps ... :  60%|██████    | 60348/100000 [18:21:56<6:26:02,  1.71it/s]
Train steps ... :  60%|██████    | 60349/100000 [18:21:56<6:25:58,  1.71it/s]
Train steps ... :  60%|██████    | 60350/100000 [18:21:57<6:25:59,  1.71it/s]Step... (60350 / 100000 | Loss: 0.5322315692901611, Learning Rate: 3.9849246231155776e-05)
+
                                                                             
Step... (60350 / 100000 | Loss: 0.5992520451545715, Learning Rate: 3.9849246231155776e-05)
+
Train steps ... :  60%|██████    | 60350/100000 [18:21:57<6:25:59,  1.71it/s]
Train steps ... :  60%|██████    | 60351/100000 [18:21:58<6:25:57,  1.71it/s]
Train steps ... :  60%|██████    | 60352/100000 [18:21:58<6:26:02,  1.71it/s]
Train steps ... :  60%|██████    | 60353/100000 [18:21:59<6:26:30,  1.71it/s]
Train steps ... :  60%|██████    | 60354/100000 [18:21:59<6:26:37,  1.71it/s]
Train steps ... :  60%|██████    | 60355/100000 [18:22:00<6:26:10,  1.71it/s]
Train steps ... :  60%|██████    | 60356/100000 [18:22:00<6:26:06,  1.71it/s]
Train steps ... :  60%|██████    | 60357/100000 [18:22:01<6:26:09,  1.71it/s]
Train steps ... :  60%|██████    | 60358/100000 [18:22:02<6:25:53,  1.71it/s]
Train steps ... :  60%|██████    | 60359/100000 [18:22:02<6:25:49,  1.71it/s]
Train steps ... :  60%|██████    | 60360/100000 [18:22:03<6:25:45,  1.71it/s]
Train steps ... :  60%|██████    | 60361/100000 [18:22:03<6:25:56,  1.71it/s]
Train steps ... :  60%|██████    | 60362/100000 [18:22:04<6:25:41,  1.71it/s]
Train steps ... :  60%|██████    | 60363/100000 [18:22:05<6:25:22,  1.71it/s]
Train steps ... :  60%|██████    | 60364/100000 [18:22:05<6:25:31,  1.71it/s]
Train steps ... :  60%|██████    | 60365/100000 [18:22:06<6:25:50,  1.71it/s]
Train steps ... :  60%|██████    | 60366/100000 [18:22:06<6:25:38,  1.71it/s]
Train steps ... :  60%|██████    | 60367/100000 [18:22:07<6:25:58,  1.71it/s]
Train steps ... :  60%|██████    | 60368/100000 [18:22:08<6:25:46,  1.71it/s]
Train steps ... :  60%|██████    | 60369/100000 [18:22:08<6:25:45,  1.71it/s]
Train steps ... :  60%|██████    | 60370/100000 [18:22:09<6:25:47,  1.71it/s]
Train steps ... :  60%|██████    | 60371/100000 [18:22:09<6:25:46,  1.71it/s]
Train steps ... :  60%|██████    | 60372/100000 [18:22:10<6:25:47,  1.71it/s]
Train steps ... :  60%|██████    | 60373/100000 [18:22:10<6:25:43,  1.71it/s]
Train steps ... :  60%|██████    | 60374/100000 [18:22:11<6:25:28,  1.71it/s]
Train steps ... :  60%|██████    | 60375/100000 [18:22:12<6:25:52,  1.71it/s]Step... (60375 / 100000 | Loss: 0.654417872428894, Learning Rate: 3.982412060301507e-05)
+
                                                                             
Step... (60375 / 100000 | Loss: 0.9006190299987793, Learning Rate: 3.982412060301507e-05)
+
Train steps ... :  60%|██████    | 60375/100000 [18:22:12<6:25:52,  1.71it/s]
Train steps ... :  60%|██████    | 60376/100000 [18:22:12<6:25:53,  1.71it/s]
Train steps ... :  60%|██████    | 60377/100000 [18:22:13<6:25:58,  1.71it/s]
Train steps ... :  60%|██████    | 60378/100000 [18:22:13<6:25:55,  1.71it/s]
Train steps ... :  60%|██████    | 60379/100000 [18:22:14<6:25:48,  1.71it/s]
Train steps ... :  60%|██████    | 60380/100000 [18:22:15<6:26:20,  1.71it/s]
Train steps ... :  60%|██████    | 60381/100000 [18:22:15<6:26:08,  1.71it/s]
Train steps ... :  60%|██████    | 60382/100000 [18:22:16<6:25:54,  1.71it/s]
Train steps ... :  60%|██████    | 60383/100000 [18:22:16<6:25:35,  1.71it/s]
Train steps ... :  60%|██████    | 60384/100000 [18:22:17<6:25:37,  1.71it/s]
Train steps ... :  60%|██████    | 60385/100000 [18:22:17<6:25:43,  1.71it/s]
Train steps ... :  60%|██████    | 60386/100000 [18:22:18<6:25:18,  1.71it/s]
Train steps ... :  60%|██████    | 60387/100000 [18:22:19<6:25:17,  1.71it/s]
Train steps ... :  60%|██████    | 60388/100000 [18:22:19<6:25:51,  1.71it/s]
Train steps ... :  60%|██████    | 60389/100000 [18:22:20<6:25:37,  1.71it/s]
Train steps ... :  60%|██████    | 60390/100000 [18:22:20<6:26:06,  1.71it/s]
Train steps ... :  60%|██████    | 60391/100000 [18:22:21<6:25:55,  1.71it/s]
Train steps ... :  60%|██████    | 60392/100000 [18:22:22<6:25:57,  1.71it/s]
Train steps ... :  60%|██████    | 60393/100000 [18:22:22<6:25:38,  1.71it/s]
Train steps ... :  60%|██████    | 60394/100000 [18:22:23<6:25:31,  1.71it/s]
Train steps ... :  60%|██████    | 60395/100000 [18:22:23<6:25:24,  1.71it/s]
Train steps ... :  60%|██████    | 60396/100000 [18:22:24<6:25:56,  1.71it/s]
Train steps ... :  60%|██████    | 60397/100000 [18:22:24<6:25:21,  1.71it/s]
Train steps ... :  60%|██████    | 60398/100000 [18:22:25<6:25:22,  1.71it/s]
Train steps ... :  60%|██████    | 60399/100000 [18:22:26<6:25:10,  1.71it/s]
Train steps ... :  60%|██████    | 60400/100000 [18:22:26<6:25:36,  1.71it/s]Step... (60400 / 100000 | Loss: 0.646799623966217, Learning Rate: 3.9798994974874376e-05)
+
                                                                             
Step... (60400 / 100000 | Loss: 0.8288842439651489, Learning Rate: 3.9798994974874376e-05)
+
Train steps ... :  60%|██████    | 60400/100000 [18:22:27<6:25:36,  1.71it/s]
Train steps ... :  60%|██████    | 60401/100000 [18:22:27<6:25:52,  1.71it/s]
Train steps ... :  60%|██████    | 60402/100000 [18:22:27<6:25:19,  1.71it/s]
Train steps ... :  60%|██████    | 60403/100000 [18:22:28<6:25:34,  1.71it/s]
Train steps ... :  60%|██████    | 60404/100000 [18:22:29<6:25:39,  1.71it/s]
Train steps ... :  60%|██████    | 60405/100000 [18:22:29<6:25:23,  1.71it/s]
Train steps ... :  60%|██████    | 60406/100000 [18:22:30<6:25:57,  1.71it/s]
Train steps ... :  60%|██████    | 60407/100000 [18:22:30<6:25:58,  1.71it/s]
Train steps ... :  60%|██████    | 60408/100000 [18:22:31<6:25:45,  1.71it/s]
Train steps ... :  60%|██████    | 60409/100000 [18:22:31<6:25:50,  1.71it/s]
Train steps ... :  60%|██████    | 60410/100000 [18:22:32<6:25:35,  1.71it/s]
Train steps ... :  60%|██████    | 60411/100000 [18:22:33<6:25:27,  1.71it/s]
Train steps ... :  60%|██████    | 60412/100000 [18:22:33<6:25:48,  1.71it/s]
Train steps ... :  60%|██████    | 60413/100000 [18:22:34<6:25:28,  1.71it/s]
Train steps ... :  60%|██████    | 60414/100000 [18:22:34<6:25:19,  1.71it/s]
Train steps ... :  60%|██████    | 60415/100000 [18:22:35<6:25:34,  1.71it/s]
Train steps ... :  60%|██████    | 60416/100000 [18:22:36<6:25:47,  1.71it/s]
Train steps ... :  60%|██████    | 60417/100000 [18:22:36<6:25:38,  1.71it/s]
Train steps ... :  60%|██████    | 60418/100000 [18:22:37<6:25:24,  1.71it/s]
Train steps ... :  60%|██████    | 60419/100000 [18:22:37<6:25:20,  1.71it/s]
Train steps ... :  60%|██████    | 60420/100000 [18:22:38<6:25:32,  1.71it/s]
Train steps ... :  60%|██████    | 60421/100000 [18:22:38<6:25:14,  1.71it/s]
Train steps ... :  60%|██████    | 60422/100000 [18:22:39<6:25:26,  1.71it/s]
Train steps ... :  60%|██████    | 60423/100000 [18:22:40<6:25:46,  1.71it/s]
Train steps ... :  60%|██████    | 60424/100000 [18:22:40<6:25:29,  1.71it/s]
Train steps ... :  60%|██████    | 60425/100000 [18:22:41<6:25:25,  1.71it/s]Step... (60425 / 100000 | Loss: 0.6488335132598877, Learning Rate: 3.977386934673367e-05)
+
                                                                             
Step... (60425 / 100000 | Loss: 0.8858366012573242, Learning Rate: 3.977386934673367e-05)
+
Train steps ... :  60%|██████    | 60425/100000 [18:22:41<6:25:25,  1.71it/s]
Train steps ... :  60%|██████    | 60426/100000 [18:22:41<6:25:20,  1.71it/s]
Train steps ... :  60%|██████    | 60427/100000 [18:22:42<6:25:28,  1.71it/s]
Train steps ... :  60%|██████    | 60428/100000 [18:22:43<6:25:23,  1.71it/s]
Train steps ... :  60%|██████    | 60429/100000 [18:22:43<6:25:15,  1.71it/s]
Train steps ... :  60%|██████    | 60430/100000 [18:22:44<6:25:19,  1.71it/s]
Train steps ... :  60%|██████    | 60431/100000 [18:22:44<6:25:44,  1.71it/s]
Train steps ... :  60%|██████    | 60432/100000 [18:22:45<6:26:00,  1.71it/s]
Train steps ... :  60%|██████    | 60433/100000 [18:22:45<6:25:48,  1.71it/s]
Train steps ... :  60%|██████    | 60434/100000 [18:22:46<6:25:36,  1.71it/s]
Train steps ... :  60%|██████    | 60435/100000 [18:22:47<6:25:42,  1.71it/s]
Train steps ... :  60%|██████    | 60436/100000 [18:22:47<6:25:31,  1.71it/s]
Train steps ... :  60%|██████    | 60437/100000 [18:22:48<6:25:37,  1.71it/s]
Train steps ... :  60%|██████    | 60438/100000 [18:22:48<6:25:41,  1.71it/s]
Train steps ... :  60%|██████    | 60439/100000 [18:22:49<6:25:13,  1.71it/s]
Train steps ... :  60%|██████    | 60440/100000 [18:22:50<6:25:51,  1.71it/s]
Train steps ... :  60%|██████    | 60441/100000 [18:22:50<6:25:24,  1.71it/s]
Train steps ... :  60%|██████    | 60442/100000 [18:22:51<6:25:10,  1.71it/s]
Train steps ... :  60%|██████    | 60443/100000 [18:22:51<6:25:33,  1.71it/s]
Train steps ... :  60%|██████    | 60444/100000 [18:22:52<6:25:42,  1.71it/s]
Train steps ... :  60%|██████    | 60445/100000 [18:22:53<6:25:52,  1.71it/s]
Train steps ... :  60%|██████    | 60446/100000 [18:22:53<6:25:56,  1.71it/s]
Train steps ... :  60%|██████    | 60447/100000 [18:22:54<6:25:28,  1.71it/s]
Train steps ... :  60%|██████    | 60448/100000 [18:22:54<6:25:25,  1.71it/s]
Train steps ... :  60%|██████    | 60449/100000 [18:22:55<6:25:36,  1.71it/s]
Train steps ... :  60%|██████    | 60450/100000 [18:22:55<6:25:39,  1.71it/s]Step... (60450 / 100000 | Loss: 0.9721323251724243, Learning Rate: 3.974874371859297e-05)
+
                                                                             
Step... (60450 / 100000 | Loss: 0.6566224098205566, Learning Rate: 3.974874371859297e-05)
+
Train steps ... :  60%|██████    | 60450/100000 [18:22:56<6:25:39,  1.71it/s]
Train steps ... :  60%|██████    | 60451/100000 [18:22:56<6:25:18,  1.71it/s]
Train steps ... :  60%|██████    | 60452/100000 [18:22:57<6:25:01,  1.71it/s]
Train steps ... :  60%|██████    | 60453/100000 [18:22:57<6:24:55,  1.71it/s]
Train steps ... :  60%|██████    | 60454/100000 [18:22:58<6:25:21,  1.71it/s]
Train steps ... :  60%|██████    | 60455/100000 [18:22:58<6:25:20,  1.71it/s]
Train steps ... :  60%|██████    | 60456/100000 [18:22:59<6:25:16,  1.71it/s]
Train steps ... :  60%|██████    | 60457/100000 [18:23:00<6:25:30,  1.71it/s]
Train steps ... :  60%|██████    | 60458/100000 [18:23:00<6:25:08,  1.71it/s]
Train steps ... :  60%|██████    | 60459/100000 [18:23:01<6:24:56,  1.71it/s]
Train steps ... :  60%|██████    | 60460/100000 [18:23:01<6:25:12,  1.71it/s]
Train steps ... :  60%|██████    | 60461/100000 [18:23:02<6:25:37,  1.71it/s]
Train steps ... :  60%|██████    | 60462/100000 [18:23:02<6:25:19,  1.71it/s]
Train steps ... :  60%|██████    | 60463/100000 [18:23:03<6:25:06,  1.71it/s]
Train steps ... :  60%|██████    | 60464/100000 [18:23:04<6:25:08,  1.71it/s]
Train steps ... :  60%|██████    | 60465/100000 [18:23:04<6:25:04,  1.71it/s]
Train steps ... :  60%|██████    | 60466/100000 [18:23:05<6:25:09,  1.71it/s]
Train steps ... :  60%|██████    | 60467/100000 [18:23:05<6:24:51,  1.71it/s]
Train steps ... :  60%|██████    | 60468/100000 [18:23:06<6:24:42,  1.71it/s]
Train steps ... :  60%|██████    | 60469/100000 [18:23:07<6:25:04,  1.71it/s]
Train steps ... :  60%|██████    | 60470/100000 [18:23:07<6:24:59,  1.71it/s]
Train steps ... :  60%|██████    | 60471/100000 [18:23:08<6:24:59,  1.71it/s]
Train steps ... :  60%|██████    | 60472/100000 [18:23:08<6:25:06,  1.71it/s]
Train steps ... :  60%|██████    | 60473/100000 [18:23:09<6:25:19,  1.71it/s]
Train steps ... :  60%|██████    | 60474/100000 [18:23:09<6:24:57,  1.71it/s]
Train steps ... :  60%|██████    | 60475/100000 [18:23:10<6:24:51,  1.71it/s]Step... (60475 / 100000 | Loss: 0.6957526206970215, Learning Rate: 3.9723618090452266e-05)
+
                                                                             
Step... (60475 / 100000 | Loss: 0.6502178907394409, Learning Rate: 3.9723618090452266e-05)
+
Train steps ... :  60%|██████    | 60475/100000 [18:23:10<6:24:51,  1.71it/s]
Train steps ... :  60%|██████    | 60476/100000 [18:23:11<6:24:43,  1.71it/s]
Train steps ... :  60%|██████    | 60477/100000 [18:23:11<6:24:56,  1.71it/s]
Train steps ... :  60%|██████    | 60478/100000 [18:23:12<6:25:13,  1.71it/s]
Train steps ... :  60%|██████    | 60479/100000 [18:23:12<6:25:09,  1.71it/s]
Train steps ... :  60%|██████    | 60480/100000 [18:23:13<6:25:28,  1.71it/s]
Train steps ... :  60%|██████    | 60481/100000 [18:23:14<6:25:42,  1.71it/s]
Train steps ... :  60%|██████    | 60482/100000 [18:23:14<6:25:37,  1.71it/s]
Train steps ... :  60%|██████    | 60483/100000 [18:23:15<6:25:17,  1.71it/s]
Train steps ... :  60%|██████    | 60484/100000 [18:23:15<6:24:51,  1.71it/s]
Train steps ... :  60%|██████    | 60485/100000 [18:23:16<6:24:59,  1.71it/s]
Train steps ... :  60%|██████    | 60486/100000 [18:23:16<6:24:47,  1.71it/s]
Train steps ... :  60%|██████    | 60487/100000 [18:23:17<6:24:57,  1.71it/s]
Train steps ... :  60%|██████    | 60488/100000 [18:23:18<6:24:38,  1.71it/s]
Train steps ... :  60%|██████    | 60489/100000 [18:23:18<6:25:14,  1.71it/s]
Train steps ... :  60%|██████    | 60490/100000 [18:23:19<6:25:17,  1.71it/s]
Train steps ... :  60%|██████    | 60491/100000 [18:23:19<6:25:06,  1.71it/s]
Train steps ... :  60%|██████    | 60492/100000 [18:23:20<6:25:01,  1.71it/s]
Train steps ... :  60%|██████    | 60493/100000 [18:23:21<6:24:51,  1.71it/s]
Train steps ... :  60%|██████    | 60494/100000 [18:23:21<6:24:24,  1.71it/s]
Train steps ... :  60%|██████    | 60495/100000 [18:23:22<6:24:21,  1.71it/s]
Train steps ... :  60%|██████    | 60496/100000 [18:23:22<6:24:25,  1.71it/s]
Train steps ... :  60%|██████    | 60497/100000 [18:23:23<6:25:02,  1.71it/s]
Train steps ... :  60%|██████    | 60498/100000 [18:23:23<6:25:16,  1.71it/s]
Train steps ... :  60%|██████    | 60499/100000 [18:23:24<6:25:16,  1.71it/s]
Train steps ... :  60%|██████    | 60500/100000 [18:23:25<6:24:53,  1.71it/s]Step... (60500 / 100000 | Loss: 0.9695751667022705, Learning Rate: 3.969849246231156e-05)
+
                                                                             
Step... (60500 / 100000 | Loss: 0.8334026336669922, Learning Rate: 3.969849246231156e-05)
+
Train steps ... :  60%|██████    | 60500/100000 [18:23:25<6:24:53,  1.71it/s]
Train steps ... :  61%|██████    | 60501/100000 [18:23:25<6:24:40,  1.71it/s]
Train steps ... :  61%|██████    | 60502/100000 [18:23:26<6:24:24,  1.71it/s]
Train steps ... :  61%|██████    | 60503/100000 [18:23:26<6:24:24,  1.71it/s]
Train steps ... :  61%|██████    | 60504/100000 [18:23:27<6:24:51,  1.71it/s]
Train steps ... :  61%|██████    | 60505/100000 [18:23:28<6:25:08,  1.71it/s]
Train steps ... :  61%|██████    | 60506/100000 [18:23:28<6:25:06,  1.71it/s]
Train steps ... :  61%|██████    | 60507/100000 [18:23:29<6:25:01,  1.71it/s]
Train steps ... :  61%|██████    | 60508/100000 [18:23:29<6:24:51,  1.71it/s]
Train steps ... :  61%|██████    | 60509/100000 [18:23:30<6:24:28,  1.71it/s]
Train steps ... :  61%|██████    | 60510/100000 [18:23:31<6:24:29,  1.71it/s]
Train steps ... :  61%|██████    | 60511/100000 [18:23:31<6:24:13,  1.71it/s]
Train steps ... :  61%|██████    | 60512/100000 [18:23:32<6:24:59,  1.71it/s]
Train steps ... :  61%|██████    | 60513/100000 [18:23:32<6:25:00,  1.71it/s]
Train steps ... :  61%|██████    | 60514/100000 [18:23:33<6:25:11,  1.71it/s]
Train steps ... :  61%|██████    | 60515/100000 [18:23:33<6:25:08,  1.71it/s]
Train steps ... :  61%|██████    | 60516/100000 [18:23:34<6:24:45,  1.71it/s]
Train steps ... :  61%|██████    | 60517/100000 [18:23:35<6:24:57,  1.71it/s]
Train steps ... :  61%|██████    | 60518/100000 [18:23:35<6:25:05,  1.71it/s]
Train steps ... :  61%|██████    | 60519/100000 [18:23:36<6:25:12,  1.71it/s]
Train steps ... :  61%|██████    | 60520/100000 [18:23:36<6:25:03,  1.71it/s]
Train steps ... :  61%|██████    | 60521/100000 [18:23:37<6:26:13,  1.70it/s]
Train steps ... :  61%|██████    | 60522/100000 [18:23:38<6:25:49,  1.71it/s]
Train steps ... :  61%|██████    | 60523/100000 [18:23:38<6:25:34,  1.71it/s]
Train steps ... :  61%|██████    | 60524/100000 [18:23:39<6:25:24,  1.71it/s]
Train steps ... :  61%|██████    | 60525/100000 [18:23:39<6:25:13,  1.71it/s]Step... (60525 / 100000 | Loss: 0.6178513169288635, Learning Rate: 3.967336683417085e-05)
+
                                                                             
Step... (60525 / 100000 | Loss: 0.5069817900657654, Learning Rate: 3.967336683417085e-05)
+
Train steps ... :  61%|██████    | 60525/100000 [18:23:40<6:25:13,  1.71it/s]
Train steps ... :  61%|██████    | 60526/100000 [18:23:40<6:24:55,  1.71it/s]
Train steps ... :  61%|██████    | 60527/100000 [18:23:40<6:24:26,  1.71it/s]
Train steps ... :  61%|██████    | 60528/100000 [18:23:41<6:24:22,  1.71it/s]
Train steps ... :  61%|██████    | 60529/100000 [18:23:42<6:24:18,  1.71it/s]
Train steps ... :  61%|██████    | 60530/100000 [18:23:42<6:25:23,  1.71it/s]
Train steps ... :  61%|██████    | 60531/100000 [18:23:43<6:25:25,  1.71it/s]
Train steps ... :  61%|██████    | 60532/100000 [18:23:43<6:24:52,  1.71it/s]
Train steps ... :  61%|██████    | 60533/100000 [18:23:44<6:24:53,  1.71it/s]
Train steps ... :  61%|██████    | 60534/100000 [18:23:45<6:24:54,  1.71it/s]
Train steps ... :  61%|██████    | 60535/100000 [18:23:45<6:24:41,  1.71it/s]
Train steps ... :  61%|██████    | 60536/100000 [18:23:46<6:24:14,  1.71it/s]
Train steps ... :  61%|██████    | 60537/100000 [18:23:46<6:24:20,  1.71it/s]
Train steps ... :  61%|██████    | 60538/100000 [18:23:47<6:24:07,  1.71it/s]
Train steps ... :  61%|██████    | 60539/100000 [18:23:47<6:24:21,  1.71it/s]
Train steps ... :  61%|██████    | 60540/100000 [18:23:48<6:24:27,  1.71it/s]
Train steps ... :  61%|██████    | 60541/100000 [18:23:49<6:24:35,  1.71it/s]
Train steps ... :  61%|██████    | 60542/100000 [18:23:49<6:24:25,  1.71it/s]
Train steps ... :  61%|██████    | 60543/100000 [18:23:50<6:24:38,  1.71it/s]
Train steps ... :  61%|██████    | 60544/100000 [18:23:50<6:24:16,  1.71it/s]
Train steps ... :  61%|██████    | 60545/100000 [18:23:51<6:24:12,  1.71it/s]
Train steps ... :  61%|██████    | 60546/100000 [18:23:52<6:24:11,  1.71it/s]
Train steps ... :  61%|██████    | 60547/100000 [18:23:52<6:24:11,  1.71it/s]
Train steps ... :  61%|██████    | 60548/100000 [18:23:53<6:24:25,  1.71it/s]
Train steps ... :  61%|██████    | 60549/100000 [18:23:53<6:24:47,  1.71it/s]
Train steps ... :  61%|██████    | 60550/100000 [18:23:54<6:24:39,  1.71it/s]Step... (60550 / 100000 | Loss: 0.6689404249191284, Learning Rate: 3.964824120603015e-05)
+
                                                                             
Step... (60550 / 100000 | Loss: 0.8414467573165894, Learning Rate: 3.964824120603015e-05)
+
Train steps ... :  61%|██████    | 60550/100000 [18:23:54<6:24:39,  1.71it/s]
Train steps ... :  61%|██████    | 60551/100000 [18:23:54<6:24:50,  1.71it/s]
Train steps ... :  61%|██████    | 60552/100000 [18:23:55<6:24:48,  1.71it/s]
Train steps ... :  61%|██████    | 60553/100000 [18:23:56<6:24:30,  1.71it/s]
Train steps ... :  61%|██████    | 60554/100000 [18:23:56<6:24:26,  1.71it/s]
Train steps ... :  61%|██████    | 60555/100000 [18:23:57<6:24:15,  1.71it/s]
Train steps ... :  61%|██████    | 60556/100000 [18:23:57<6:24:09,  1.71it/s]
Train steps ... :  61%|██████    | 60557/100000 [18:23:58<6:24:18,  1.71it/s]
Train steps ... :  61%|██████    | 60558/100000 [18:23:59<6:24:12,  1.71it/s]
Train steps ... :  61%|██████    | 60559/100000 [18:23:59<6:24:18,  1.71it/s]
Train steps ... :  61%|██████    | 60560/100000 [18:24:00<6:24:16,  1.71it/s]
Train steps ... :  61%|██████    | 60561/100000 [18:24:00<6:24:29,  1.71it/s]
Train steps ... :  61%|██████    | 60562/100000 [18:24:01<6:24:11,  1.71it/s]
Train steps ... :  61%|██████    | 60563/100000 [18:24:02<6:23:43,  1.71it/s]
Train steps ... :  61%|██████    | 60564/100000 [18:24:02<6:23:44,  1.71it/s]
Train steps ... :  61%|██████    | 60565/100000 [18:24:03<6:23:27,  1.71it/s]
Train steps ... :  61%|██████    | 60566/100000 [18:24:03<6:23:51,  1.71it/s]
Train steps ... :  61%|██████    | 60567/100000 [18:24:04<6:24:10,  1.71it/s]
Train steps ... :  61%|██████    | 60568/100000 [18:24:04<6:24:04,  1.71it/s]
Train steps ... :  61%|██████    | 60569/100000 [18:24:05<6:23:46,  1.71it/s]
Train steps ... :  61%|██████    | 60570/100000 [18:24:06<6:23:47,  1.71it/s]
Train steps ... :  61%|██████    | 60571/100000 [18:24:06<6:23:49,  1.71it/s]
Train steps ... :  61%|██████    | 60572/100000 [18:24:07<6:23:42,  1.71it/s]
Train steps ... :  61%|██████    | 60573/100000 [18:24:07<6:23:46,  1.71it/s]
Train steps ... :  61%|██████    | 60574/100000 [18:24:08<6:23:29,  1.71it/s]
Train steps ... :  61%|██████    | 60575/100000 [18:24:09<6:23:34,  1.71it/s]Step... (60575 / 100000 | Loss: 0.6578206419944763, Learning Rate: 3.9623115577889446e-05)
+
                                                                             
Step... (60575 / 100000 | Loss: 0.7384178638458252, Learning Rate: 3.9623115577889446e-05)
+
Train steps ... :  61%|██████    | 60575/100000 [18:24:09<6:23:34,  1.71it/s]
Train steps ... :  61%|██████    | 60576/100000 [18:24:09<6:23:33,  1.71it/s]
Train steps ... :  61%|██████    | 60577/100000 [18:24:10<6:23:53,  1.71it/s]
Train steps ... :  61%|██████    | 60578/100000 [18:24:10<6:23:52,  1.71it/s]
Train steps ... :  61%|██████    | 60579/100000 [18:24:11<6:24:09,  1.71it/s]
Train steps ... :  61%|██████    | 60580/100000 [18:24:11<6:24:17,  1.71it/s]
Train steps ... :  61%|██████    | 60581/100000 [18:24:12<6:24:13,  1.71it/s]
Train steps ... :  61%|██████    | 60582/100000 [18:24:13<6:23:58,  1.71it/s]
Train steps ... :  61%|██████    | 60583/100000 [18:24:13<6:23:48,  1.71it/s]
Train steps ... :  61%|██████    | 60584/100000 [18:24:14<6:24:04,  1.71it/s]
Train steps ... :  61%|██████    | 60585/100000 [18:24:14<6:23:55,  1.71it/s]
Train steps ... :  61%|██████    | 60586/100000 [18:24:15<6:24:21,  1.71it/s]
Train steps ... :  61%|██████    | 60587/100000 [18:24:16<6:24:19,  1.71it/s]
Train steps ... :  61%|██████    | 60588/100000 [18:24:16<6:25:01,  1.71it/s]
Train steps ... :  61%|██████    | 60589/100000 [18:24:17<6:24:26,  1.71it/s]
Train steps ... :  61%|██████    | 60590/100000 [18:24:17<6:24:09,  1.71it/s]
Train steps ... :  61%|██████    | 60591/100000 [18:24:18<6:24:16,  1.71it/s]
Train steps ... :  61%|██████    | 60592/100000 [18:24:18<6:23:42,  1.71it/s]
Train steps ... :  61%|██████    | 60593/100000 [18:24:19<6:23:24,  1.71it/s]
Train steps ... :  61%|██████    | 60594/100000 [18:24:20<6:25:40,  1.70it/s]
Train steps ... :  61%|██████    | 60595/100000 [18:24:20<6:24:39,  1.71it/s]
Train steps ... :  61%|██████    | 60596/100000 [18:24:21<6:24:42,  1.71it/s]
Train steps ... :  61%|██████    | 60597/100000 [18:24:21<6:24:37,  1.71it/s]
Train steps ... :  61%|██████    | 60598/100000 [18:24:22<6:24:55,  1.71it/s]
Train steps ... :  61%|██████    | 60599/100000 [18:24:23<6:24:10,  1.71it/s]
Train steps ... :  61%|██████    | 60600/100000 [18:24:23<6:24:21,  1.71it/s]Step... (60600 / 100000 | Loss: 0.6276651620864868, Learning Rate: 3.959798994974875e-05)
+
                                                                             
Step... (60600 / 100000 | Loss: 1.1629213094711304, Learning Rate: 3.959798994974875e-05)
+
Train steps ... :  61%|██████    | 60600/100000 [18:24:23<6:24:21,  1.71it/s]
Train steps ... :  61%|██████    | 60601/100000 [18:24:24<6:24:29,  1.71it/s]
Train steps ... :  61%|██████    | 60602/100000 [18:24:24<6:24:16,  1.71it/s]
Train steps ... :  61%|██████    | 60603/100000 [18:24:25<6:24:00,  1.71it/s]
Train steps ... :  61%|██████    | 60604/100000 [18:24:25<6:23:43,  1.71it/s]
Train steps ... :  61%|██████    | 60605/100000 [18:24:26<6:24:32,  1.71it/s]
Train steps ... :  61%|██████    | 60606/100000 [18:24:27<6:24:59,  1.71it/s]
Train steps ... :  61%|██████    | 60607/100000 [18:24:27<6:24:20,  1.71it/s]
Train steps ... :  61%|██████    | 60608/100000 [18:24:28<6:25:39,  1.70it/s]
Train steps ... :  61%|██████    | 60609/100000 [18:24:28<6:24:07,  1.71it/s]
Train steps ... :  61%|██████    | 60610/100000 [18:24:29<6:25:20,  1.70it/s]
Train steps ... :  61%|██████    | 60611/100000 [18:24:30<6:24:34,  1.71it/s]
Train steps ... :  61%|██████    | 60612/100000 [18:24:30<6:24:16,  1.71it/s]
Train steps ... :  61%|██████    | 60613/100000 [18:24:31<6:24:10,  1.71it/s]
Train steps ... :  61%|██████    | 60614/100000 [18:24:31<6:24:21,  1.71it/s]
Train steps ... :  61%|██████    | 60615/100000 [18:24:32<6:24:49,  1.71it/s]
Train steps ... :  61%|██████    | 60616/100000 [18:24:33<6:24:34,  1.71it/s]
Train steps ... :  61%|██████    | 60617/100000 [18:24:33<6:24:20,  1.71it/s]
Train steps ... :  61%|██████    | 60618/100000 [18:24:34<6:24:19,  1.71it/s]
Train steps ... :  61%|██████    | 60619/100000 [18:24:34<6:24:00,  1.71it/s]
Train steps ... :  61%|██████    | 60620/100000 [18:24:35<6:23:23,  1.71it/s]
Train steps ... :  61%|██████    | 60621/100000 [18:24:35<6:24:17,  1.71it/s]
Train steps ... :  61%|██████    | 60622/100000 [18:24:36<6:24:37,  1.71it/s]
Train steps ... :  61%|██████    | 60623/100000 [18:24:37<6:24:04,  1.71it/s]
Train steps ... :  61%|██████    | 60624/100000 [18:24:37<6:24:31,  1.71it/s]
Train steps ... :  61%|██████    | 60625/100000 [18:24:38<6:25:47,  1.70it/s]Step... (60625 / 100000 | Loss: 0.5718581080436707, Learning Rate: 3.9572864321608046e-05)
+
                                                                             
Step... (60625 / 100000 | Loss: 0.6236929893493652, Learning Rate: 3.9572864321608046e-05)
+
Train steps ... :  61%|██████    | 60625/100000 [18:24:38<6:25:47,  1.70it/s]
Train steps ... :  61%|██████    | 60626/100000 [18:24:38<6:25:38,  1.70it/s]
Train steps ... :  61%|██████    | 60627/100000 [18:24:39<6:24:40,  1.71it/s]
Train steps ... :  61%|██████    | 60628/100000 [18:24:40<6:24:34,  1.71it/s]
Train steps ... :  61%|██████    | 60629/100000 [18:24:40<6:24:32,  1.71it/s]
Train steps ... :  61%|██████    | 60630/100000 [18:24:41<6:23:53,  1.71it/s]
Train steps ... :  61%|██████    | 60631/100000 [18:24:41<6:24:19,  1.71it/s]
Train steps ... :  61%|██████    | 60632/100000 [18:24:42<6:23:42,  1.71it/s]
Train steps ... :  61%|██████    | 60633/100000 [18:24:42<6:23:35,  1.71it/s]
Train steps ... :  61%|██████    | 60634/100000 [18:24:43<6:23:13,  1.71it/s]
Train steps ... :  61%|██████    | 60635/100000 [18:24:44<6:23:20,  1.71it/s]
Train steps ... :  61%|██████    | 60636/100000 [18:24:44<6:23:01,  1.71it/s]
Train steps ... :  61%|██████    | 60637/100000 [18:24:45<6:22:48,  1.71it/s]
Train steps ... :  61%|██████    | 60638/100000 [18:24:45<6:23:17,  1.71it/s]
Train steps ... :  61%|██████    | 60639/100000 [18:24:46<6:22:37,  1.71it/s]
Train steps ... :  61%|██████    | 60640/100000 [18:24:47<6:23:21,  1.71it/s]
Train steps ... :  61%|██████    | 60641/100000 [18:24:47<6:23:20,  1.71it/s]
Train steps ... :  61%|██████    | 60642/100000 [18:24:48<6:24:08,  1.71it/s]
Train steps ... :  61%|██████    | 60643/100000 [18:24:48<6:24:14,  1.71it/s]
Train steps ... :  61%|██████    | 60644/100000 [18:24:49<6:23:33,  1.71it/s]
Train steps ... :  61%|██████    | 60645/100000 [18:24:49<6:23:50,  1.71it/s]
Train steps ... :  61%|██████    | 60646/100000 [18:24:50<6:24:22,  1.71it/s]
Train steps ... :  61%|██████    | 60647/100000 [18:24:51<6:23:46,  1.71it/s]
Train steps ... :  61%|██████    | 60648/100000 [18:24:51<6:23:49,  1.71it/s]
Train steps ... :  61%|██████    | 60649/100000 [18:24:52<6:23:46,  1.71it/s]
Train steps ... :  61%|██████    | 60650/100000 [18:24:52<6:23:44,  1.71it/s]Step... (60650 / 100000 | Loss: 0.6178568601608276, Learning Rate: 3.954773869346734e-05)
+
                                                                             
Step... (60650 / 100000 | Loss: 0.7166794538497925, Learning Rate: 3.954773869346734e-05)
+
Train steps ... :  61%|██████    | 60650/100000 [18:24:53<6:23:44,  1.71it/s]
Train steps ... :  61%|██████    | 60651/100000 [18:24:53<6:24:00,  1.71it/s]
Train steps ... :  61%|██████    | 60652/100000 [18:24:54<6:23:26,  1.71it/s]
Train steps ... :  61%|██████    | 60653/100000 [18:24:54<6:23:07,  1.71it/s]
Train steps ... :  61%|██████    | 60654/100000 [18:24:55<6:23:08,  1.71it/s]
Train steps ... :  61%|██████    | 60655/100000 [18:24:55<6:23:18,  1.71it/s]
Train steps ... :  61%|██████    | 60656/100000 [18:24:56<6:22:38,  1.71it/s]
Train steps ... :  61%|██████    | 60657/100000 [18:24:56<6:23:25,  1.71it/s]
Train steps ... :  61%|██████    | 60658/100000 [18:24:57<6:23:04,  1.71it/s]
Train steps ... :  61%|██████    | 60659/100000 [18:24:58<6:23:08,  1.71it/s]
Train steps ... :  61%|██████    | 60660/100000 [18:24:58<6:23:03,  1.71it/s]
Train steps ... :  61%|██████    | 60661/100000 [18:24:59<6:23:02,  1.71it/s]
Train steps ... :  61%|██████    | 60662/100000 [18:24:59<6:23:13,  1.71it/s]
Train steps ... :  61%|██████    | 60663/100000 [18:25:00<6:23:29,  1.71it/s]
Train steps ... :  61%|██████    | 60664/100000 [18:25:01<6:23:16,  1.71it/s]
Train steps ... :  61%|██████    | 60665/100000 [18:25:01<6:24:21,  1.71it/s]
Train steps ... :  61%|██████    | 60666/100000 [18:25:02<6:24:00,  1.71it/s]
Train steps ... :  61%|██████    | 60667/100000 [18:25:02<6:24:03,  1.71it/s]
Train steps ... :  61%|██████    | 60668/100000 [18:25:03<6:24:00,  1.71it/s]
Train steps ... :  61%|██████    | 60669/100000 [18:25:04<6:24:06,  1.71it/s]
Train steps ... :  61%|██████    | 60670/100000 [18:25:04<6:23:44,  1.71it/s]
Train steps ... :  61%|██████    | 60671/100000 [18:25:05<6:23:40,  1.71it/s]
Train steps ... :  61%|██████    | 60672/100000 [18:25:05<6:23:50,  1.71it/s]
Train steps ... :  61%|██████    | 60673/100000 [18:25:06<6:23:21,  1.71it/s]
Train steps ... :  61%|██████    | 60674/100000 [18:25:06<6:23:49,  1.71it/s]
Train steps ... :  61%|██████    | 60675/100000 [18:25:07<6:24:31,  1.70it/s]Step... (60675 / 100000 | Loss: 0.9544286727905273, Learning Rate: 3.952261306532664e-05)
+
                                                                             
Step... (60675 / 100000 | Loss: 0.6147554516792297, Learning Rate: 3.952261306532664e-05)
+
Train steps ... :  61%|██████    | 60675/100000 [18:25:07<6:24:31,  1.70it/s]
Train steps ... :  61%|██████    | 60676/100000 [18:25:08<6:23:53,  1.71it/s]
Train steps ... :  61%|██████    | 60677/100000 [18:25:08<6:24:30,  1.70it/s]
Train steps ... :  61%|██████    | 60678/100000 [18:25:09<6:23:30,  1.71it/s]
Train steps ... :  61%|██████    | 60679/100000 [18:25:09<6:22:42,  1.71it/s]
Train steps ... :  61%|██████    | 60680/100000 [18:25:10<6:23:11,  1.71it/s]
Train steps ... :  61%|██████    | 60681/100000 [18:25:11<6:23:10,  1.71it/s]
Train steps ... :  61%|██████    | 60682/100000 [18:25:11<6:23:03,  1.71it/s]
Train steps ... :  61%|██████    | 60683/100000 [18:25:12<6:23:07,  1.71it/s]
Train steps ... :  61%|██████    | 60684/100000 [18:25:12<6:23:14,  1.71it/s]
Train steps ... :  61%|██████    | 60685/100000 [18:25:13<6:23:33,  1.71it/s]
Train steps ... :  61%|██████    | 60686/100000 [18:25:13<6:24:02,  1.71it/s]
Train steps ... :  61%|██████    | 60687/100000 [18:25:14<6:24:23,  1.70it/s]
Train steps ... :  61%|██████    | 60688/100000 [18:25:15<6:23:48,  1.71it/s]
Train steps ... :  61%|██████    | 60689/100000 [18:25:15<6:23:14,  1.71it/s]
Train steps ... :  61%|██████    | 60690/100000 [18:25:16<6:22:52,  1.71it/s]
Train steps ... :  61%|██████    | 60691/100000 [18:25:16<6:23:22,  1.71it/s]
Train steps ... :  61%|██████    | 60692/100000 [18:25:17<6:24:14,  1.70it/s]
Train steps ... :  61%|██████    | 60693/100000 [18:25:18<6:24:15,  1.70it/s]
Train steps ... :  61%|██████    | 60694/100000 [18:25:18<6:23:50,  1.71it/s]
Train steps ... :  61%|██████    | 60695/100000 [18:25:19<6:24:03,  1.71it/s]
Train steps ... :  61%|██████    | 60696/100000 [18:25:19<6:23:44,  1.71it/s]
Train steps ... :  61%|██████    | 60697/100000 [18:25:20<6:23:35,  1.71it/s]
Train steps ... :  61%|██████    | 60698/100000 [18:25:20<6:23:27,  1.71it/s]
Train steps ... :  61%|██████    | 60699/100000 [18:25:21<6:23:14,  1.71it/s]
Train steps ... :  61%|██████    | 60700/100000 [18:25:22<6:24:06,  1.71it/s]Step... (60700 / 100000 | Loss: 0.9032889604568481, Learning Rate: 3.949748743718593e-05)
+
                                                                             
Step... (60700 / 100000 | Loss: 0.831689178943634, Learning Rate: 3.949748743718593e-05)
+
Train steps ... :  61%|██████    | 60700/100000 [18:25:22<6:24:06,  1.71it/s]
Train steps ... :  61%|██████    | 60701/100000 [18:25:22<6:24:04,  1.71it/s]
Train steps ... :  61%|██████    | 60702/100000 [18:25:23<6:24:05,  1.71it/s]
Train steps ... :  61%|██████    | 60703/100000 [18:25:23<6:23:26,  1.71it/s]
Train steps ... :  61%|██████    | 60704/100000 [18:25:24<6:22:53,  1.71it/s]
Train steps ... :  61%|██████    | 60705/100000 [18:25:25<6:23:07,  1.71it/s]
Train steps ... :  61%|██████    | 60706/100000 [18:25:25<6:22:49,  1.71it/s]
Train steps ... :  61%|██████    | 60707/100000 [18:25:26<6:22:53,  1.71it/s]
Train steps ... :  61%|██████    | 60708/100000 [18:25:26<6:22:46,  1.71it/s]
Train steps ... :  61%|██████    | 60709/100000 [18:25:27<6:22:42,  1.71it/s]
Train steps ... :  61%|██████    | 60710/100000 [18:25:28<6:22:38,  1.71it/s]
Train steps ... :  61%|██████    | 60711/100000 [18:25:28<6:22:32,  1.71it/s]
Train steps ... :  61%|██████    | 60712/100000 [18:25:29<6:22:08,  1.71it/s]
Train steps ... :  61%|██████    | 60713/100000 [18:25:29<6:22:32,  1.71it/s]
Train steps ... :  61%|██████    | 60714/100000 [18:25:30<6:22:51,  1.71it/s]
Train steps ... :  61%|██████    | 60715/100000 [18:25:30<6:23:07,  1.71it/s]
Train steps ... :  61%|██████    | 60716/100000 [18:25:31<6:23:23,  1.71it/s]
Train steps ... :  61%|██████    | 60717/100000 [18:25:32<6:23:03,  1.71it/s]
Train steps ... :  61%|██████    | 60718/100000 [18:25:32<6:23:50,  1.71it/s]
Train steps ... :  61%|██████    | 60719/100000 [18:25:33<6:24:19,  1.70it/s]
Train steps ... :  61%|██████    | 60720/100000 [18:25:33<6:23:00,  1.71it/s]
Train steps ... :  61%|██████    | 60721/100000 [18:25:34<6:22:32,  1.71it/s]
Train steps ... :  61%|██████    | 60722/100000 [18:25:35<6:22:50,  1.71it/s]
Train steps ... :  61%|██████    | 60723/100000 [18:25:35<6:22:22,  1.71it/s]
Train steps ... :  61%|██████    | 60724/100000 [18:25:36<6:22:29,  1.71it/s]
Train steps ... :  61%|██████    | 60725/100000 [18:25:36<6:22:31,  1.71it/s]Step... (60725 / 100000 | Loss: 0.7533864378929138, Learning Rate: 3.9472361809045226e-05)
+
                                                                             
Step... (60725 / 100000 | Loss: 0.7903097867965698, Learning Rate: 3.9472361809045226e-05)
+
Train steps ... :  61%|██████    | 60725/100000 [18:25:37<6:22:31,  1.71it/s]
Train steps ... :  61%|██████    | 60726/100000 [18:25:37<6:23:08,  1.71it/s]
Train steps ... :  61%|██████    | 60727/100000 [18:25:37<6:22:56,  1.71it/s]
Train steps ... :  61%|██████    | 60728/100000 [18:25:38<6:23:19,  1.71it/s]
Train steps ... :  61%|██████    | 60729/100000 [18:25:39<6:23:04,  1.71it/s]
Train steps ... :  61%|██████    | 60730/100000 [18:25:39<6:22:21,  1.71it/s]
Train steps ... :  61%|██████    | 60731/100000 [18:25:40<6:22:19,  1.71it/s]
Train steps ... :  61%|██████    | 60732/100000 [18:25:40<6:22:13,  1.71it/s]
Train steps ... :  61%|██████    | 60733/100000 [18:25:41<6:22:09,  1.71it/s]
Train steps ... :  61%|██████    | 60734/100000 [18:25:42<6:22:33,  1.71it/s]
Train steps ... :  61%|██████    | 60735/100000 [18:25:42<6:22:50,  1.71it/s]
Train steps ... :  61%|██████    | 60736/100000 [18:25:43<6:22:45,  1.71it/s]
Train steps ... :  61%|██████    | 60737/100000 [18:25:43<6:22:38,  1.71it/s]
Train steps ... :  61%|██████    | 60738/100000 [18:25:44<6:23:50,  1.70it/s]
Train steps ... :  61%|██████    | 60739/100000 [18:25:44<6:22:52,  1.71it/s]
Train steps ... :  61%|██████    | 60740/100000 [18:25:45<6:22:36,  1.71it/s]
Train steps ... :  61%|██████    | 60741/100000 [18:25:46<6:22:34,  1.71it/s]
Train steps ... :  61%|██████    | 60742/100000 [18:25:46<6:23:09,  1.71it/s]
Train steps ... :  61%|██████    | 60743/100000 [18:25:47<6:23:00,  1.71it/s]
Train steps ... :  61%|██████    | 60744/100000 [18:25:47<6:23:04,  1.71it/s]
Train steps ... :  61%|██████    | 60745/100000 [18:25:48<6:23:21,  1.71it/s]
Train steps ... :  61%|██████    | 60746/100000 [18:25:49<6:23:26,  1.71it/s]
Train steps ... :  61%|██████    | 60747/100000 [18:25:49<6:22:43,  1.71it/s]
Train steps ... :  61%|██████    | 60748/100000 [18:25:50<6:22:57,  1.71it/s]
Train steps ... :  61%|██████    | 60749/100000 [18:25:50<6:22:37,  1.71it/s]
Train steps ... :  61%|██████    | 60750/100000 [18:25:51<6:22:24,  1.71it/s]Step... (60750 / 100000 | Loss: 0.7753386497497559, Learning Rate: 3.944723618090452e-05)
+
                                                                             
Step... (60750 / 100000 | Loss: 0.5746611952781677, Learning Rate: 3.944723618090452e-05)
+
Train steps ... :  61%|██████    | 60750/100000 [18:25:51<6:22:24,  1.71it/s]
Train steps ... :  61%|██████    | 60751/100000 [18:25:52<6:22:47,  1.71it/s]
Train steps ... :  61%|██████    | 60752/100000 [18:25:52<6:22:40,  1.71it/s]
Train steps ... :  61%|██████    | 60753/100000 [18:25:53<6:22:33,  1.71it/s]
Train steps ... :  61%|██████    | 60754/100000 [18:25:53<6:22:08,  1.71it/s]
Train steps ... :  61%|██████    | 60755/100000 [18:25:54<6:22:37,  1.71it/s]
Train steps ... :  61%|██████    | 60756/100000 [18:25:54<6:22:11,  1.71it/s]
Train steps ... :  61%|██████    | 60757/100000 [18:25:55<6:21:57,  1.71it/s]
Train steps ... :  61%|██████    | 60758/100000 [18:25:56<6:21:52,  1.71it/s]
Train steps ... :  61%|██████    | 60759/100000 [18:25:56<6:21:41,  1.71it/s]
Train steps ... :  61%|██████    | 60760/100000 [18:25:57<6:21:41,  1.71it/s]
Train steps ... :  61%|██████    | 60761/100000 [18:25:57<6:22:14,  1.71it/s]
Train steps ... :  61%|██████    | 60762/100000 [18:25:58<6:22:35,  1.71it/s]
Train steps ... :  61%|██████    | 60763/100000 [18:25:59<6:22:15,  1.71it/s]
Train steps ... :  61%|██████    | 60764/100000 [18:25:59<6:22:15,  1.71it/s]
Train steps ... :  61%|██████    | 60765/100000 [18:26:00<6:22:46,  1.71it/s]
Train steps ... :  61%|██████    | 60766/100000 [18:26:00<6:22:29,  1.71it/s]
Train steps ... :  61%|██████    | 60767/100000 [18:26:01<6:22:02,  1.71it/s]
Train steps ... :  61%|██████    | 60768/100000 [18:26:01<6:22:19,  1.71it/s]
Train steps ... :  61%|██████    | 60769/100000 [18:26:02<6:22:11,  1.71it/s]
Train steps ... :  61%|██████    | 60770/100000 [18:26:03<6:21:59,  1.71it/s]
Train steps ... :  61%|██████    | 60771/100000 [18:26:03<6:21:39,  1.71it/s]
Train steps ... :  61%|██████    | 60772/100000 [18:26:04<6:22:41,  1.71it/s]
Train steps ... :  61%|██████    | 60773/100000 [18:26:04<6:22:18,  1.71it/s]
Train steps ... :  61%|██████    | 60774/100000 [18:26:05<6:22:40,  1.71it/s]
Train steps ... :  61%|██████    | 60775/100000 [18:26:06<6:22:24,  1.71it/s]Step... (60775 / 100000 | Loss: 0.826643705368042, Learning Rate: 3.942211055276382e-05)
+
                                                                             
Step... (60775 / 100000 | Loss: 0.965018630027771, Learning Rate: 3.942211055276382e-05)
+
Train steps ... :  61%|██████    | 60775/100000 [18:26:06<6:22:24,  1.71it/s]
Train steps ... :  61%|██████    | 60776/100000 [18:26:06<6:22:18,  1.71it/s]
Train steps ... :  61%|██████    | 60777/100000 [18:26:07<6:22:05,  1.71it/s]
Train steps ... :  61%|██████    | 60778/100000 [18:26:07<6:21:56,  1.71it/s]
Train steps ... :  61%|██████    | 60779/100000 [18:26:08<6:21:52,  1.71it/s]
Train steps ... :  61%|██████    | 60780/100000 [18:26:08<6:22:11,  1.71it/s]
Train steps ... :  61%|██████    | 60781/100000 [18:26:09<6:22:55,  1.71it/s]
Train steps ... :  61%|██████    | 60782/100000 [18:26:10<6:23:14,  1.71it/s]
Train steps ... :  61%|██████    | 60783/100000 [18:26:10<6:23:05,  1.71it/s]
Train steps ... :  61%|██████    | 60784/100000 [18:26:11<6:22:51,  1.71it/s]
Train steps ... :  61%|██████    | 60785/100000 [18:26:11<6:22:37,  1.71it/s]
Train steps ... :  61%|██████    | 60786/100000 [18:26:12<6:22:09,  1.71it/s]
Train steps ... :  61%|██████    | 60787/100000 [18:26:13<6:22:29,  1.71it/s]
Train steps ... :  61%|██████    | 60788/100000 [18:26:13<6:22:32,  1.71it/s]
Train steps ... :  61%|██████    | 60789/100000 [18:26:14<6:22:04,  1.71it/s]
Train steps ... :  61%|██████    | 60790/100000 [18:26:14<6:22:16,  1.71it/s]
Train steps ... :  61%|██████    | 60791/100000 [18:26:15<6:22:18,  1.71it/s]
Train steps ... :  61%|██████    | 60792/100000 [18:26:15<6:22:46,  1.71it/s]
Train steps ... :  61%|██████    | 60793/100000 [18:26:16<6:22:25,  1.71it/s]
Train steps ... :  61%|██████    | 60794/100000 [18:26:17<6:22:25,  1.71it/s]
Train steps ... :  61%|██████    | 60795/100000 [18:26:17<6:23:09,  1.71it/s]
Train steps ... :  61%|██████    | 60796/100000 [18:26:18<6:22:10,  1.71it/s]
Train steps ... :  61%|██████    | 60797/100000 [18:26:18<6:22:55,  1.71it/s]
Train steps ... :  61%|██████    | 60798/100000 [18:26:19<6:22:07,  1.71it/s]
Train steps ... :  61%|██████    | 60799/100000 [18:26:20<6:23:01,  1.71it/s]
Train steps ... :  61%|██████    | 60800/100000 [18:26:20<6:22:47,  1.71it/s]Step... (60800 / 100000 | Loss: 0.9218964576721191, Learning Rate: 3.9396984924623115e-05)
+
                                                                             
Step... (60800 / 100000 | Loss: 0.5938840508460999, Learning Rate: 3.9396984924623115e-05)
+
Train steps ... :  61%|██████    | 60800/100000 [18:26:20<6:22:47,  1.71it/s]
Train steps ... :  61%|██████    | 60801/100000 [18:26:21<6:22:32,  1.71it/s]
Train steps ... :  61%|██████    | 60802/100000 [18:26:21<6:23:00,  1.71it/s]
Train steps ... :  61%|██████    | 60803/100000 [18:26:22<6:22:30,  1.71it/s]
Train steps ... :  61%|██████    | 60804/100000 [18:26:23<6:22:32,  1.71it/s]
Train steps ... :  61%|██████    | 60805/100000 [18:26:23<6:22:06,  1.71it/s]
Train steps ... :  61%|██████    | 60806/100000 [18:26:24<6:23:07,  1.71it/s]
Train steps ... :  61%|██████    | 60807/100000 [18:26:24<6:22:22,  1.71it/s]
Train steps ... :  61%|██████    | 60808/100000 [18:26:25<6:22:56,  1.71it/s]
Train steps ... :  61%|██████    | 60809/100000 [18:26:25<6:22:41,  1.71it/s]
Train steps ... :  61%|██████    | 60810/100000 [18:26:26<6:23:19,  1.70it/s]
Train steps ... :  61%|██████    | 60811/100000 [18:26:27<6:23:23,  1.70it/s]
Train steps ... :  61%|██████    | 60812/100000 [18:26:27<6:23:05,  1.70it/s]
Train steps ... :  61%|██████    | 60813/100000 [18:26:28<6:23:23,  1.70it/s]
Train steps ... :  61%|██████    | 60814/100000 [18:26:28<6:23:38,  1.70it/s]
Train steps ... :  61%|██████    | 60815/100000 [18:26:29<6:22:52,  1.71it/s]
Train steps ... :  61%|██████    | 60816/100000 [18:26:30<6:22:59,  1.71it/s]
Train steps ... :  61%|██████    | 60817/100000 [18:26:30<6:22:27,  1.71it/s]
Train steps ... :  61%|██████    | 60818/100000 [18:26:31<6:22:43,  1.71it/s]
Train steps ... :  61%|██████    | 60819/100000 [18:26:31<6:22:51,  1.71it/s]
Train steps ... :  61%|██████    | 60820/100000 [18:26:32<6:22:37,  1.71it/s]
Train steps ... :  61%|██████    | 60821/100000 [18:26:32<6:22:32,  1.71it/s]
Train steps ... :  61%|██████    | 60822/100000 [18:26:33<6:22:29,  1.71it/s]
Train steps ... :  61%|██████    | 60823/100000 [18:26:34<6:22:26,  1.71it/s]
Train steps ... :  61%|██████    | 60824/100000 [18:26:34<6:22:33,  1.71it/s]
Train steps ... :  61%|██████    | 60825/100000 [18:26:35<6:22:30,  1.71it/s]Step... (60825 / 100000 | Loss: 0.9604109525680542, Learning Rate: 3.937185929648242e-05)
+
                                                                             
Step... (60825 / 100000 | Loss: 0.8039932250976562, Learning Rate: 3.937185929648242e-05)
+
Train steps ... :  61%|██████    | 60825/100000 [18:26:35<6:22:30,  1.71it/s]
Train steps ... :  61%|██████    | 60826/100000 [18:26:35<6:23:03,  1.70it/s]
Train steps ... :  61%|██████    | 60827/100000 [18:26:36<6:22:40,  1.71it/s]
Train steps ... :  61%|██████    | 60828/100000 [18:26:37<6:22:03,  1.71it/s]
Train steps ... :  61%|██████    | 60829/100000 [18:26:37<6:22:03,  1.71it/s]
Train steps ... :  61%|██████    | 60830/100000 [18:26:38<6:22:23,  1.71it/s]
Train steps ... :  61%|██████    | 60831/100000 [18:26:38<6:22:34,  1.71it/s]
Train steps ... :  61%|██████    | 60832/100000 [18:26:39<6:22:21,  1.71it/s]
Train steps ... :  61%|██████    | 60833/100000 [18:26:40<6:22:02,  1.71it/s]
Train steps ... :  61%|██████    | 60834/100000 [18:26:40<6:21:33,  1.71it/s]
Train steps ... :  61%|██████    | 60835/100000 [18:26:41<6:22:36,  1.71it/s]
Train steps ... :  61%|██████    | 60836/100000 [18:26:41<6:22:33,  1.71it/s]
Train steps ... :  61%|██████    | 60837/100000 [18:26:42<6:22:03,  1.71it/s]
Train steps ... :  61%|██████    | 60838/100000 [18:26:42<6:22:02,  1.71it/s]
Train steps ... :  61%|██████    | 60839/100000 [18:26:43<6:21:36,  1.71it/s]
Train steps ... :  61%|██████    | 60840/100000 [18:26:44<6:21:26,  1.71it/s]
Train steps ... :  61%|██████    | 60841/100000 [18:26:44<6:21:26,  1.71it/s]
Train steps ... :  61%|██████    | 60842/100000 [18:26:45<6:22:09,  1.71it/s]
Train steps ... :  61%|██████    | 60843/100000 [18:26:45<6:22:03,  1.71it/s]
Train steps ... :  61%|██████    | 60844/100000 [18:26:46<6:21:13,  1.71it/s]
Train steps ... :  61%|██████    | 60845/100000 [18:26:47<6:21:16,  1.71it/s]
Train steps ... :  61%|██████    | 60846/100000 [18:26:47<6:21:17,  1.71it/s]
Train steps ... :  61%|██████    | 60847/100000 [18:26:48<6:21:19,  1.71it/s]
Train steps ... :  61%|██████    | 60848/100000 [18:26:48<6:21:59,  1.71it/s]
Train steps ... :  61%|██████    | 60849/100000 [18:26:49<6:21:51,  1.71it/s]
Train steps ... :  61%|██████    | 60850/100000 [18:26:49<6:21:01,  1.71it/s]Step... (60850 / 100000 | Loss: 0.7803702354431152, Learning Rate: 3.9346733668341715e-05)
+
                                                                             
Step... (60850 / 100000 | Loss: 0.9416118860244751, Learning Rate: 3.9346733668341715e-05)
+
Train steps ... :  61%|██████    | 60850/100000 [18:26:50<6:21:01,  1.71it/s]
Train steps ... :  61%|██████    | 60851/100000 [18:26:50<6:21:34,  1.71it/s]
Train steps ... :  61%|██████    | 60852/100000 [18:26:51<6:21:30,  1.71it/s]
Train steps ... :  61%|██████    | 60853/100000 [18:26:51<6:21:32,  1.71it/s]
Train steps ... :  61%|██████    | 60854/100000 [18:26:52<6:21:16,  1.71it/s]
Train steps ... :  61%|██████    | 60855/100000 [18:26:52<6:21:35,  1.71it/s]
Train steps ... :  61%|██████    | 60856/100000 [18:26:53<6:21:24,  1.71it/s]
Train steps ... :  61%|██████    | 60857/100000 [18:26:54<6:21:52,  1.71it/s]
Train steps ... :  61%|██████    | 60858/100000 [18:26:54<6:21:48,  1.71it/s]
Train steps ... :  61%|██████    | 60859/100000 [18:26:55<6:22:34,  1.71it/s]
Train steps ... :  61%|██████    | 60860/100000 [18:26:55<6:21:30,  1.71it/s]
Train steps ... :  61%|██████    | 60861/100000 [18:26:56<6:22:03,  1.71it/s]
Train steps ... :  61%|██████    | 60862/100000 [18:26:56<6:21:38,  1.71it/s]
Train steps ... :  61%|██████    | 60863/100000 [18:26:57<6:22:30,  1.71it/s]
Train steps ... :  61%|██████    | 60864/100000 [18:26:58<6:22:11,  1.71it/s]
Train steps ... :  61%|██████    | 60865/100000 [18:26:58<6:22:46,  1.70it/s]
Train steps ... :  61%|██████    | 60866/100000 [18:26:59<6:23:12,  1.70it/s]
Train steps ... :  61%|██████    | 60867/100000 [18:26:59<6:22:35,  1.70it/s]
Train steps ... :  61%|██████    | 60868/100000 [18:27:00<6:22:26,  1.71it/s]
Train steps ... :  61%|��█████    | 60869/100000 [18:27:01<6:21:43,  1.71it/s]
Train steps ... :  61%|██████    | 60870/100000 [18:27:01<6:22:09,  1.71it/s]
Train steps ... :  61%|██████    | 60871/100000 [18:27:02<6:21:18,  1.71it/s]
Train steps ... :  61%|██████    | 60872/100000 [18:27:02<6:21:15,  1.71it/s]
Train steps ... :  61%|██████    | 60873/100000 [18:27:03<6:21:31,  1.71it/s]
Train steps ... :  61%|██████    | 60874/100000 [18:27:03<6:21:22,  1.71it/s]
Train steps ... :  61%|██████    | 60875/100000 [18:27:04<6:20:48,  1.71it/s]Step... (60875 / 100000 | Loss: 0.633600115776062, Learning Rate: 3.9321608040201005e-05)
+
                                                                             
Step... (60875 / 100000 | Loss: 0.6069002151489258, Learning Rate: 3.9321608040201005e-05)
+
Train steps ... :  61%|██████    | 60875/100000 [18:27:04<6:20:48,  1.71it/s]
Train steps ... :  61%|██████    | 60876/100000 [18:27:05<6:21:15,  1.71it/s]
Train steps ... :  61%|██████    | 60877/100000 [18:27:05<6:21:54,  1.71it/s]
Train steps ... :  61%|██████    | 60878/100000 [18:27:06<6:21:21,  1.71it/s]
Train steps ... :  61%|██████    | 60879/100000 [18:27:06<6:21:24,  1.71it/s]
Train steps ... :  61%|██████    | 60880/100000 [18:27:07<6:21:10,  1.71it/s]
Train steps ... :  61%|██████    | 60881/100000 [18:27:08<6:21:30,  1.71it/s]
Train steps ... :  61%|██████    | 60882/100000 [18:27:08<6:21:18,  1.71it/s]
Train steps ... :  61%|██████    | 60883/100000 [18:27:09<6:21:44,  1.71it/s]
Train steps ... :  61%|██████    | 60884/100000 [18:27:09<6:20:54,  1.71it/s]
Train steps ... :  61%|██████    | 60885/100000 [18:27:10<6:21:32,  1.71it/s]
Train steps ... :  61%|██████    | 60886/100000 [18:27:11<6:21:00,  1.71it/s]
Train steps ... :  61%|██████    | 60887/100000 [18:27:11<6:21:54,  1.71it/s]
Train steps ... :  61%|██████    | 60888/100000 [18:27:12<6:21:42,  1.71it/s]
Train steps ... :  61%|██████    | 60889/100000 [18:27:12<6:21:40,  1.71it/s]
Train steps ... :  61%|██████    | 60890/100000 [18:27:13<6:21:34,  1.71it/s]
Train steps ... :  61%|██████    | 60891/100000 [18:27:13<6:21:07,  1.71it/s]
Train steps ... :  61%|██████    | 60892/100000 [18:27:14<6:20:45,  1.71it/s]
Train steps ... :  61%|██████    | 60893/100000 [18:27:15<6:21:07,  1.71it/s]
Train steps ... :  61%|██████    | 60894/100000 [18:27:15<6:20:58,  1.71it/s]
Train steps ... :  61%|██████    | 60895/100000 [18:27:16<6:21:12,  1.71it/s]
Train steps ... :  61%|██████    | 60896/100000 [18:27:16<6:21:39,  1.71it/s]
Train steps ... :  61%|██████    | 60897/100000 [18:27:17<6:21:29,  1.71it/s]
Train steps ... :  61%|██████    | 60898/100000 [18:27:18<6:21:12,  1.71it/s]
Train steps ... :  61%|██████    | 60899/100000 [18:27:18<6:20:44,  1.71it/s]
Train steps ... :  61%|██████    | 60900/100000 [18:27:19<6:21:13,  1.71it/s]Step... (60900 / 100000 | Loss: 0.6149848699569702, Learning Rate: 3.92964824120603e-05)
+
                                                                             
Step... (60900 / 100000 | Loss: 0.7915512919425964, Learning Rate: 3.92964824120603e-05)
+
Train steps ... :  61%|██████    | 60900/100000 [18:27:19<6:21:13,  1.71it/s]
Train steps ... :  61%|██████    | 60901/100000 [18:27:19<6:20:54,  1.71it/s]
Train steps ... :  61%|██████    | 60902/100000 [18:27:20<6:20:53,  1.71it/s]
Train steps ... :  61%|██████    | 60903/100000 [18:27:20<6:20:35,  1.71it/s]
Train steps ... :  61%|██████    | 60904/100000 [18:27:21<6:20:15,  1.71it/s]
Train steps ... :  61%|██████    | 60905/100000 [18:27:22<6:20:52,  1.71it/s]
Train steps ... :  61%|██████    | 60906/100000 [18:27:22<6:20:44,  1.71it/s]
Train steps ... :  61%|██████    | 60907/100000 [18:27:23<6:20:43,  1.71it/s]
Train steps ... :  61%|██████    | 60908/100000 [18:27:23<6:21:01,  1.71it/s]
Train steps ... :  61%|██████    | 60909/100000 [18:27:24<6:21:07,  1.71it/s]
Train steps ... :  61%|██████    | 60910/100000 [18:27:25<6:20:56,  1.71it/s]
Train steps ... :  61%|██████    | 60911/100000 [18:27:25<6:20:51,  1.71it/s]
Train steps ... :  61%|██████    | 60912/100000 [18:27:26<6:20:39,  1.71it/s]
Train steps ... :  61%|██████    | 60913/100000 [18:27:26<6:20:47,  1.71it/s]
Train steps ... :  61%|██████    | 60914/100000 [18:27:27<6:20:37,  1.71it/s]
Train steps ... :  61%|██████    | 60915/100000 [18:27:27<6:20:44,  1.71it/s]
Train steps ... :  61%|██████    | 60916/100000 [18:27:28<6:21:00,  1.71it/s]
Train steps ... :  61%|██████    | 60917/100000 [18:27:29<6:20:23,  1.71it/s]
Train steps ... :  61%|███��██    | 60918/100000 [18:27:29<6:20:47,  1.71it/s]
Train steps ... :  61%|██████    | 60919/100000 [18:27:30<6:21:08,  1.71it/s]
Train steps ... :  61%|██████    | 60920/100000 [18:27:30<6:20:55,  1.71it/s]
Train steps ... :  61%|██████    | 60921/100000 [18:27:31<6:21:32,  1.71it/s]
Train steps ... :  61%|██████    | 60922/100000 [18:27:32<6:21:54,  1.71it/s]
Train steps ... :  61%|██████    | 60923/100000 [18:27:32<6:22:06,  1.70it/s]
Train steps ... :  61%|██████    | 60924/100000 [18:27:33<6:21:54,  1.71it/s]
Train steps ... :  61%|██████    | 60925/100000 [18:27:33<6:21:19,  1.71it/s]Step... (60925 / 100000 | Loss: 0.710504412651062, Learning Rate: 3.92713567839196e-05)
+
                                                                             
Step... (60925 / 100000 | Loss: 0.6186422109603882, Learning Rate: 3.92713567839196e-05)
+
Train steps ... :  61%|██████    | 60925/100000 [18:27:34<6:21:19,  1.71it/s]
Train steps ... :  61%|██████    | 60926/100000 [18:27:34<6:21:25,  1.71it/s]
Train steps ... :  61%|██████    | 60927/100000 [18:27:34<6:20:52,  1.71it/s]
Train steps ... :  61%|██████    | 60928/100000 [18:27:35<6:21:05,  1.71it/s]
Train steps ... :  61%|██████    | 60929/100000 [18:27:36<6:20:49,  1.71it/s]
Train steps ... :  61%|██████    | 60930/100000 [18:27:36<6:21:12,  1.71it/s]
Train steps ... :  61%|██████    | 60931/100000 [18:27:37<6:20:40,  1.71it/s]
Train steps ... :  61%|██████    | 60932/100000 [18:27:37<6:20:47,  1.71it/s]
Train steps ... :  61%|██████    | 60933/100000 [18:27:38<6:20:51,  1.71it/s]
Train steps ... :  61%|██████    | 60934/100000 [18:27:39<6:20:38,  1.71it/s]
Train steps ... :  61%|██████    | 60935/100000 [18:27:39<6:20:17,  1.71it/s]
Train steps ... :  61%|██████    | 60936/100000 [18:27:40<6:20:34,  1.71it/s]
Train steps ... :  61%|██████    | 60937/100000 [18:27:40<6:20:12,  1.71it/s]
Train steps ... :  61%|██████    | 60938/100000 [18:27:41<6:20:13,  1.71it/s]
Train steps ... :  61%|██████    | 60939/100000 [18:27:42<6:20:28,  1.71it/s]
Train steps ... :  61%|██████    | 60940/100000 [18:27:42<6:20:24,  1.71it/s]
Train steps ... :  61%|██████    | 60941/100000 [18:27:43<6:20:05,  1.71it/s]
Train steps ... :  61%|██████    | 60942/100000 [18:27:43<6:19:54,  1.71it/s]
Train steps ... :  61%|██████    | 60943/100000 [18:27:44<6:20:20,  1.71it/s]
Train steps ... :  61%|██████    | 60944/100000 [18:27:44<6:20:15,  1.71it/s]
Train steps ... :  61%|██████    | 60945/100000 [18:27:45<6:20:22,  1.71it/s]
Train steps ... :  61%|██████    | 60946/100000 [18:27:46<6:20:33,  1.71it/s]
Train steps ... :  61%|██████    | 60947/100000 [18:27:46<6:20:30,  1.71it/s]
Train steps ... :  61%|██████    | 60948/100000 [18:27:47<6:20:45,  1.71it/s]
Train steps ... :  61%|██████    | 60949/100000 [18:27:47<6:20:16,  1.71it/s]
Train steps ... :  61%|██████    | 60950/100000 [18:27:48<6:20:41,  1.71it/s]Step... (60950 / 100000 | Loss: 0.8446182012557983, Learning Rate: 3.9246231155778895e-05)
+
                                                                             
Step... (60950 / 100000 | Loss: 0.7355121374130249, Learning Rate: 3.9246231155778895e-05)
+
Train steps ... :  61%|██████    | 60950/100000 [18:27:48<6:20:41,  1.71it/s]
Train steps ... :  61%|██████    | 60951/100000 [18:27:49<6:20:48,  1.71it/s]
Train steps ... :  61%|██████    | 60952/100000 [18:27:49<6:21:08,  1.71it/s]
Train steps ... :  61%|██████    | 60953/100000 [18:27:50<6:20:45,  1.71it/s]
Train steps ... :  61%|██████    | 60954/100000 [18:27:50<6:20:42,  1.71it/s]
Train steps ... :  61%|██████    | 60955/100000 [18:27:51<6:20:54,  1.71it/s]
Train steps ... :  61%|██████    | 60956/100000 [18:27:51<6:20:44,  1.71it/s]
Train steps ... :  61%|██████    | 60957/100000 [18:27:52<6:20:55,  1.71it/s]
Train steps ... :  61%|██████    | 60958/100000 [18:27:53<6:20:30,  1.71it/s]
Train steps ... :  61%|██████    | 60959/100000 [18:27:53<6:20:31,  1.71it/s]
Train steps ... :  61%|██████    | 60960/100000 [18:27:54<6:20:57,  1.71it/s]
Train steps ... :  61%|██████    | 60961/100000 [18:27:54<6:20:27,  1.71it/s]
Train steps ... :  61%|██████    | 60962/100000 [18:27:55<6:20:25,  1.71it/s]
Train steps ... :  61%|██████    | 60963/100000 [18:27:56<6:20:15,  1.71it/s]
Train steps ... :  61%|██████    | 60964/100000 [18:27:56<6:20:02,  1.71it/s]
Train steps ... :  61%|██████    | 60965/100000 [18:27:57<6:19:54,  1.71it/s]
Train steps ... :  61%|██████    | 60966/100000 [18:27:57<6:20:17,  1.71it/s]
Train steps ... :  61%|██████    | 60967/100000 [18:27:58<6:20:03,  1.71it/s]
Train steps ... :  61%|██████    | 60968/100000 [18:27:58<6:21:22,  1.71it/s]
Train steps ... :  61%|██████    | 60969/100000 [18:27:59<6:20:53,  1.71it/s]
Train steps ... :  61%|██████    | 60970/100000 [18:28:00<6:20:28,  1.71it/s]
Train steps ... :  61%|██████    | 60971/100000 [18:28:00<6:20:05,  1.71it/s]
Train steps ... :  61%|██████    | 60972/100000 [18:28:01<6:19:55,  1.71it/s]
Train steps ... :  61%|██████    | 60973/100000 [18:28:01<6:19:58,  1.71it/s]
Train steps ... :  61%|██████    | 60974/100000 [18:28:02<6:20:21,  1.71it/s]
Train steps ... :  61%|██████    | 60975/100000 [18:28:03<6:20:43,  1.71it/s]Step... (60975 / 100000 | Loss: 0.8574938178062439, Learning Rate: 3.922110552763819e-05)
+
                                                                             
Step... (60975 / 100000 | Loss: 0.7008132934570312, Learning Rate: 3.922110552763819e-05)
+
Train steps ... :  61%|██████    | 60975/100000 [18:28:03<6:20:43,  1.71it/s]
Train steps ... :  61%|██████    | 60976/100000 [18:28:03<6:20:28,  1.71it/s]
Train steps ... :  61%|██████    | 60977/100000 [18:28:04<6:20:43,  1.71it/s]
Train steps ... :  61%|██████    | 60978/100000 [18:28:04<6:20:15,  1.71it/s]
Train steps ... :  61%|██████    | 60979/100000 [18:28:05<6:20:06,  1.71it/s]
Train steps ... :  61%|██████    | 60980/100000 [18:28:05<6:20:18,  1.71it/s]
Train steps ... :  61%|██████    | 60981/100000 [18:28:06<6:19:51,  1.71it/s]
Train steps ... :  61%|██████    | 60982/100000 [18:28:07<6:19:43,  1.71it/s]
Train steps ... :  61%|██████    | 60983/100000 [18:28:07<6:19:33,  1.71it/s]
Train steps ... :  61%|██████    | 60984/100000 [18:28:08<6:20:03,  1.71it/s]
Train steps ... :  61%|██████    | 60985/100000 [18:28:08<6:20:16,  1.71it/s]
Train steps ... :  61%|██████    | 60986/100000 [18:28:09<6:20:26,  1.71it/s]
Train steps ... :  61%|██████    | 60987/100000 [18:28:10<6:20:13,  1.71it/s]
Train steps ... :  61%|██████    | 60988/100000 [18:28:10<6:19:52,  1.71it/s]
Train steps ... :  61%|██████    | 60989/100000 [18:28:11<6:19:43,  1.71it/s]
Train steps ... :  61%|██████    | 60990/100000 [18:28:11<6:19:40,  1.71it/s]
Train steps ... :  61%|██████    | 60991/100000 [18:28:12<6:19:40,  1.71it/s]
Train steps ... :  61%|██████    | 60992/100000 [18:28:13<6:20:03,  1.71it/s]
Train steps ... :  61%|██████    | 60993/100000 [18:28:13<6:20:22,  1.71it/s]
Train steps ... :  61%|██████    | 60994/100000 [18:28:14<6:20:05,  1.71it/s]
Train steps ... :  61%|██████    | 60995/100000 [18:28:14<6:19:58,  1.71it/s]
Train steps ... :  61%|██████    | 60996/100000 [18:28:15<6:20:12,  1.71it/s]
Train steps ... :  61%|██████    | 60997/100000 [18:28:15<6:20:08,  1.71it/s]
Train steps ... :  61%|██████    | 60998/100000 [18:28:16<6:20:33,  1.71it/s]
Train steps ... :  61%|██████    | 60999/100000 [18:28:17<6:20:18,  1.71it/s]
Train steps ... :  61%|██████    | 61000/100000 [18:28:17<6:20:22,  1.71it/s]Step... (61000 / 100000 | Loss: 0.6051367521286011, Learning Rate: 3.919597989949749e-05)
+
                                                                             
Step... (61000 / 100000 | Loss: 0.6851568818092346, Learning Rate: 3.919597989949749e-05)
+
Train steps ... :  61%|██████    | 61000/100000 [18:28:18<6:20:22,  1.71it/s]
Train steps ... :  61%|██████    | 61001/100000 [18:28:18<6:20:52,  1.71it/s]
Train steps ... :  61%|██████    | 61002/100000 [18:28:18<6:19:53,  1.71it/s]
Train steps ... :  61%|██████    | 61003/100000 [18:28:19<6:19:54,  1.71it/s]
Train steps ... :  61%|██████    | 61004/100000 [18:28:20<6:19:42,  1.71it/s]
Train steps ... :  61%|██████    | 61005/100000 [18:28:20<6:19:47,  1.71it/s]
Train steps ... :  61%|██████    | 61006/100000 [18:28:21<6:20:27,  1.71it/s]
Train steps ... :  61%|██████    | 61007/100000 [18:28:21<6:20:04,  1.71it/s]
Train steps ... :  61%|██████    | 61008/100000 [18:28:22<6:20:15,  1.71it/s]
Train steps ... :  61%|██████    | 61009/100000 [18:28:22<6:19:38,  1.71it/s]
Train steps ... :  61%|██████    | 61010/100000 [18:28:23<6:19:58,  1.71it/s]
Train steps ... :  61%|██████    | 61011/100000 [18:28:24<6:20:15,  1.71it/s]
Train steps ... :  61%|██████    | 61012/100000 [18:28:24<6:20:02,  1.71it/s]
Train steps ... :  61%|██████    | 61013/100000 [18:28:25<6:20:14,  1.71it/s]
Train steps ... :  61%|██████    | 61014/100000 [18:28:25<6:20:17,  1.71it/s]
Train steps ... :  61%|██████    | 61015/100000 [18:28:26<6:19:28,  1.71it/s]
Train steps ... :  61%|██████    | 61016/100000 [18:28:27<6:19:29,  1.71it/s]
Train steps ... :  61%|██████    | 61017/100000 [18:28:27<6:19:27,  1.71it/s]
Train steps ... :  61%|██████    | 61018/100000 [18:28:28<6:19:35,  1.71it/s]
Train steps ... :  61%|██████    | 61019/100000 [18:28:28<6:19:52,  1.71it/s]
Train steps ... :  61%|██████    | 61020/100000 [18:28:29<6:20:00,  1.71it/s]
Train steps ... :  61%|██████    | 61021/100000 [18:28:29<6:20:14,  1.71it/s]
Train steps ... :  61%|██████    | 61022/100000 [18:28:30<6:20:05,  1.71it/s]
Train steps ... :  61%|██████    | 61023/100000 [18:28:31<6:19:40,  1.71it/s]
Train steps ... :  61%|██████    | 61024/100000 [18:28:31<6:19:45,  1.71it/s]
Train steps ... :  61%|██████    | 61025/100000 [18:28:32<6:19:35,  1.71it/s]Step... (61025 / 100000 | Loss: 0.7777224779129028, Learning Rate: 3.9170854271356785e-05)
+
                                                                             
Step... (61025 / 100000 | Loss: 0.9035530090332031, Learning Rate: 3.9170854271356785e-05)
+
Train steps ... :  61%|██████    | 61025/100000 [18:28:32<6:19:35,  1.71it/s]
Train steps ... :  61%|██████    | 61026/100000 [18:28:32<6:19:30,  1.71it/s]
Train steps ... :  61%|██████    | 61027/100000 [18:28:33<6:20:21,  1.71it/s]
Train steps ... :  61%|██████    | 61028/100000 [18:28:34<6:19:53,  1.71it/s]
Train steps ... :  61%|██████    | 61029/100000 [18:28:34<6:20:02,  1.71it/s]
Train steps ... :  61%|██████    | 61030/100000 [18:28:35<6:20:34,  1.71it/s]
Train steps ... :  61%|██████    | 61031/100000 [18:28:35<6:20:33,  1.71it/s]
Train steps ... :  61%|██████    | 61032/100000 [18:28:36<6:20:17,  1.71it/s]
Train steps ... :  61%|██████    | 61033/100000 [18:28:36<6:20:18,  1.71it/s]
Train steps ... :  61%|██████    | 61034/100000 [18:28:37<6:20:28,  1.71it/s]
Train steps ... :  61%|██████    | 61035/100000 [18:28:38<6:20:08,  1.71it/s]
Train steps ... :  61%|██████    | 61036/100000 [18:28:38<6:19:56,  1.71it/s]
Train steps ... :  61%|██████    | 61037/100000 [18:28:39<6:20:27,  1.71it/s]
Train steps ... :  61%|██████    | 61038/100000 [18:28:39<6:20:09,  1.71it/s]
Train steps ... :  61%|██████    | 61039/100000 [18:28:40<6:20:12,  1.71it/s]
Train steps ... :  61%|██████    | 61040/100000 [18:28:41<6:19:40,  1.71it/s]
Train steps ... :  61%|██████    | 61041/100000 [18:28:41<6:19:59,  1.71it/s]
Train steps ... :  61%|██████    | 61042/100000 [18:28:42<6:19:49,  1.71it/s]
Train steps ... :  61%|██████    | 61043/100000 [18:28:42<6:19:36,  1.71it/s]
Train steps ... :  61%|██████    | 61044/100000 [18:28:43<6:19:37,  1.71it/s]
Train steps ... :  61%|██████    | 61045/100000 [18:28:44<6:19:16,  1.71it/s]
Train steps ... :  61%|██████    | 61046/100000 [18:28:44<6:19:28,  1.71it/s]
Train steps ... :  61%|██████    | 61047/100000 [18:28:45<6:19:04,  1.71it/s]
Train steps ... :  61%|██████    | 61048/100000 [18:28:45<6:18:53,  1.71it/s]
Train steps ... :  61%|██████    | 61049/100000 [18:28:46<6:19:12,  1.71it/s]
Train steps ... :  61%|██████    | 61050/100000 [18:28:46<6:19:37,  1.71it/s]Step... (61050 / 100000 | Loss: 0.6212084293365479, Learning Rate: 3.914572864321608e-05)
+
                                                                             
Step... (61050 / 100000 | Loss: 0.7061513662338257, Learning Rate: 3.914572864321608e-05)
+
Train steps ... :  61%|██████    | 61050/100000 [18:28:47<6:19:37,  1.71it/s]
Train steps ... :  61%|██████    | 61051/100000 [18:28:47<6:19:15,  1.71it/s]
Train steps ... :  61%|██████    | 61052/100000 [18:28:48<6:19:25,  1.71it/s]
Train steps ... :  61%|██████    | 61053/100000 [18:28:48<6:19:33,  1.71it/s]
Train steps ... :  61%|██████    | 61054/100000 [18:28:49<6:19:18,  1.71it/s]
Train steps ... :  61%|██████    | 61055/100000 [18:28:49<6:19:38,  1.71it/s]
Train steps ... :  61%|██████    | 61056/100000 [18:28:50<6:19:22,  1.71it/s]
Train steps ... :  61%|██████    | 61057/100000 [18:28:51<6:20:09,  1.71it/s]
Train steps ... :  61%|██████    | 61058/100000 [18:28:51<6:19:49,  1.71it/s]
Train steps ... :  61%|██████    | 61059/100000 [18:28:52<6:20:26,  1.71it/s]
Train steps ... :  61%|██████    | 61060/100000 [18:28:52<6:20:10,  1.71it/s]
Train steps ... :  61%|██████    | 61061/100000 [18:28:53<6:20:48,  1.70it/s]
Train steps ... :  61%|██████    | 61062/100000 [18:28:53<6:20:11,  1.71it/s]
Train steps ... :  61%|██████    | 61063/100000 [18:28:54<6:19:49,  1.71it/s]
Train steps ... :  61%|██████    | 61064/100000 [18:28:55<6:19:48,  1.71it/s]
Train steps ... :  61%|██████    | 61065/100000 [18:28:55<6:19:29,  1.71it/s]
Train steps ... :  61%|██████    | 61066/100000 [18:28:56<6:19:51,  1.71it/s]
Train steps ... :  61%|██████    | 61067/100000 [18:28:56<6:19:37,  1.71it/s]
Train steps ... :  61%|██████    | 61068/100000 [18:28:57<6:19:16,  1.71it/s]
Train steps ... :  61%|██████    | 61069/100000 [18:28:58<6:19:40,  1.71it/s]
Train steps ... :  61%|██████    | 61070/100000 [18:28:58<6:19:29,  1.71it/s]
Train steps ... :  61%|██████    | 61071/100000 [18:28:59<6:19:16,  1.71it/s]
Train steps ... :  61%|██████    | 61072/100000 [18:28:59<6:19:27,  1.71it/s]
Train steps ... :  61%|██████    | 61073/100000 [18:29:00<6:19:26,  1.71it/s]
Train steps ... :  61%|██████    | 61074/100000 [18:29:00<6:18:53,  1.71it/s]
Train steps ... :  61%|██████    | 61075/100000 [18:29:01<6:19:00,  1.71it/s]Step... (61075 / 100000 | Loss: 0.788214921951294, Learning Rate: 3.912060301507538e-05)
+
                                                                             
Step... (61075 / 100000 | Loss: 0.7546067237854004, Learning Rate: 3.912060301507538e-05)
+
Train steps ... :  61%|██████    | 61075/100000 [18:29:01<6:19:00,  1.71it/s]
Train steps ... :  61%|██████    | 61076/100000 [18:29:02<6:19:17,  1.71it/s]
Train steps ... :  61%|██████    | 61077/100000 [18:29:02<6:19:12,  1.71it/s]
Train steps ... :  61%|██████    | 61078/100000 [18:29:03<6:19:16,  1.71it/s]
Train steps ... :  61%|██████    | 61079/100000 [18:29:03<6:19:20,  1.71it/s]
Train steps ... :  61%|██████    | 61080/100000 [18:29:04<6:19:11,  1.71it/s]
Train steps ... :  61%|██████    | 61081/100000 [18:29:05<6:19:32,  1.71it/s]
Train steps ... :  61%|██████    | 61082/100000 [18:29:05<6:19:35,  1.71it/s]
Train steps ... :  61%|██████    | 61083/100000 [18:29:06<6:19:13,  1.71it/s]
Train steps ... :  61%|██████    | 61084/100000 [18:29:06<6:19:21,  1.71it/s]
Train steps ... :  61%|██████    | 61085/100000 [18:29:07<6:19:40,  1.71it/s]
Train steps ... :  61%|██████    | 61086/100000 [18:29:07<6:19:15,  1.71it/s]
Train steps ... :  61%|██████    | 61087/100000 [18:29:08<6:19:43,  1.71it/s]
Train steps ... :  61%|██████    | 61088/100000 [18:29:09<6:19:44,  1.71it/s]
Train steps ... :  61%|██████    | 61089/100000 [18:29:09<6:19:23,  1.71it/s]
Train steps ... :  61%|██████    | 61090/100000 [18:29:10<6:18:59,  1.71it/s]
Train steps ... :  61%|██████    | 61091/100000 [18:29:10<6:19:11,  1.71it/s]
Train steps ... :  61%|██████    | 61092/100000 [18:29:11<6:19:09,  1.71it/s]
Train steps ... :  61%|██████    | 61093/100000 [18:29:12<6:19:06,  1.71it/s]
Train steps ... :  61%|██████    | 61094/100000 [18:29:12<6:19:15,  1.71it/s]
Train steps ... :  61%|██████    | 61095/100000 [18:29:13<6:18:47,  1.71it/s]
Train steps ... :  61%|██████    | 61096/100000 [18:29:13<6:18:52,  1.71it/s]
Train steps ... :  61%|██████    | 61097/100000 [18:29:14<6:18:40,  1.71it/s]
Train steps ... :  61%|██████    | 61098/100000 [18:29:14<6:19:09,  1.71it/s]
Train steps ... :  61%|██████    | 61099/100000 [18:29:15<6:18:44,  1.71it/s]
Train steps ... :  61%|██████    | 61100/100000 [18:29:16<6:18:59,  1.71it/s]Step... (61100 / 100000 | Loss: 0.9717268943786621, Learning Rate: 3.9095477386934675e-05)
+
                                                                             
Step... (61100 / 100000 | Loss: 0.7799345254898071, Learning Rate: 3.9095477386934675e-05)
+
Train steps ... :  61%|██████    | 61100/100000 [18:29:16<6:18:59,  1.71it/s]
Train steps ... :  61%|██████    | 61101/100000 [18:29:16<6:19:04,  1.71it/s]
Train steps ... :  61%|██████    | 61102/100000 [18:29:17<6:18:44,  1.71it/s]
Train steps ... :  61%|██████    | 61103/100000 [18:29:17<6:18:47,  1.71it/s]
Train steps ... :  61%|██████    | 61104/100000 [18:29:18<6:18:30,  1.71it/s]
Train steps ... :  61%|██████    | 61105/100000 [18:29:19<6:19:07,  1.71it/s]
Train steps ... :  61%|██████    | 61106/100000 [18:29:19<6:18:52,  1.71it/s]
Train steps ... :  61%|██████    | 61107/100000 [18:29:20<6:18:56,  1.71it/s]
Train steps ... :  61%|██████    | 61108/100000 [18:29:20<6:19:26,  1.71it/s]
Train steps ... :  61%|██████    | 61109/100000 [18:29:21<6:18:51,  1.71it/s]
Train steps ... :  61%|██████    | 61110/100000 [18:29:22<6:19:21,  1.71it/s]
Train steps ... :  61%|██████    | 61111/100000 [18:29:22<6:19:09,  1.71it/s]
Train steps ... :  61%|██████    | 61112/100000 [18:29:23<6:19:27,  1.71it/s]
Train steps ... :  61%|██████    | 61113/100000 [18:29:23<6:19:01,  1.71it/s]
Train steps ... :  61%|██████    | 61114/100000 [18:29:24<6:19:19,  1.71it/s]
Train steps ... :  61%|██████    | 61115/100000 [18:29:24<6:19:24,  1.71it/s]
Train steps ... :  61%|██████    | 61116/100000 [18:29:25<6:19:10,  1.71it/s]
Train steps ... :  61%|██████    | 61117/100000 [18:29:26<6:19:11,  1.71it/s]
Train steps ... :  61%|██████    | 61118/100000 [18:29:26<6:18:43,  1.71it/s]
Train steps ... :  61%|██████    | 61119/100000 [18:29:27<6:19:06,  1.71it/s]
Train steps ... :  61%|██████    | 61120/100000 [18:29:27<6:18:45,  1.71it/s]
Train steps ... :  61%|██████    | 61121/100000 [18:29:28<6:18:47,  1.71it/s]
Train steps ... :  61%|██████    | 61122/100000 [18:29:29<6:18:37,  1.71it/s]
Train steps ... :  61%|██████    | 61123/100000 [18:29:29<6:18:50,  1.71it/s]
Train steps ... :  61%|██████    | 61124/100000 [18:29:30<6:18:32,  1.71it/s]
Train steps ... :  61%|██████    | 61125/100000 [18:29:30<6:18:28,  1.71it/s]Step... (61125 / 100000 | Loss: 0.6513015627861023, Learning Rate: 3.907035175879397e-05)
+
                                                                             
Step... (61125 / 100000 | Loss: 0.7298558354377747, Learning Rate: 3.907035175879397e-05)
+
Train steps ... :  61%|██████    | 61125/100000 [18:29:31<6:18:28,  1.71it/s]
Train steps ... :  61%|██████    | 61126/100000 [18:29:31<6:18:42,  1.71it/s]
Train steps ... :  61%|██████    | 61127/100000 [18:29:31<6:18:29,  1.71it/s]
Train steps ... :  61%|██████    | 61128/100000 [18:29:32<6:18:14,  1.71it/s]
Train steps ... :  61%|██████    | 61129/100000 [18:29:33<6:18:51,  1.71it/s]
Train steps ... :  61%|██████    | 61130/100000 [18:29:33<6:18:32,  1.71it/s]
Train steps ... :  61%|██████    | 61131/100000 [18:29:34<6:18:47,  1.71it/s]
Train steps ... :  61%|██████    | 61132/100000 [18:29:34<6:18:38,  1.71it/s]
Train steps ... :  61%|██████    | 61133/100000 [18:29:35<6:18:39,  1.71it/s]
Train steps ... :  61%|██████    | 61134/100000 [18:29:36<6:18:42,  1.71it/s]
Train steps ... :  61%|██████    | 61135/100000 [18:29:36<6:18:32,  1.71it/s]
Train steps ... :  61%|██████    | 61136/100000 [18:29:37<6:19:00,  1.71it/s]
Train steps ... :  61%|██████    | 61137/100000 [18:29:37<6:19:22,  1.71it/s]
Train steps ... :  61%|██████    | 61138/100000 [18:29:38<6:19:04,  1.71it/s]
Train steps ... :  61%|██████    | 61139/100000 [18:29:38<6:18:42,  1.71it/s]
Train steps ... :  61%|██████    | 61140/100000 [18:29:39<6:18:27,  1.71it/s]
Train steps ... :  61%|██████    | 61141/100000 [18:29:40<6:18:17,  1.71it/s]
Train steps ... :  61%|██████    | 61142/100000 [18:29:40<6:18:30,  1.71it/s]
Train steps ... :  61%|██████    | 61143/100000 [18:29:41<6:18:24,  1.71it/s]
Train steps ... :  61%|██████    | 61144/100000 [18:29:41<6:18:46,  1.71it/s]
Train steps ... :  61%|██████    | 61145/100000 [18:29:42<6:19:00,  1.71it/s]
Train steps ... :  61%|██████    | 61146/100000 [18:29:43<6:19:05,  1.71it/s]
Train steps ... :  61%|██████    | 61147/100000 [18:29:43<6:18:53,  1.71it/s]
Train steps ... :  61%|██████    | 61148/100000 [18:29:44<6:18:53,  1.71it/s]
Train steps ... :  61%|██████    | 61149/100000 [18:29:44<6:18:40,  1.71it/s]
Train steps ... :  61%|██████    | 61150/100000 [18:29:45<6:18:26,  1.71it/s]Step... (61150 / 100000 | Loss: 0.7225563526153564, Learning Rate: 3.904522613065327e-05)
+
                                                                             
Step... (61150 / 100000 | Loss: 0.6165098547935486, Learning Rate: 3.904522613065327e-05)
+
Train steps ... :  61%|██████    | 61150/100000 [18:29:45<6:18:26,  1.71it/s]
Train steps ... :  61%|██████    | 61151/100000 [18:29:45<6:18:54,  1.71it/s]
Train steps ... :  61%|██████    | 61152/100000 [18:29:46<6:19:08,  1.71it/s]
Train steps ... :  61%|██████    | 61153/100000 [18:29:47<6:18:41,  1.71it/s]
Train steps ... :  61%|██████    | 61154/100000 [18:29:47<6:18:14,  1.71it/s]
Train steps ... :  61%|██████    | 61155/100000 [18:29:48<6:18:09,  1.71it/s]
Train steps ... :  61%|██████    | 61156/100000 [18:29:48<6:18:13,  1.71it/s]
Train steps ... :  61%|██████    | 61157/100000 [18:29:49<6:18:30,  1.71it/s]
Train steps ... :  61%|██████    | 61158/100000 [18:29:50<6:18:07,  1.71it/s]
Train steps ... :  61%|██████    | 61159/100000 [18:29:50<6:18:43,  1.71it/s]
Train steps ... :  61%|██████    | 61160/100000 [18:29:51<6:18:43,  1.71it/s]
Train steps ... :  61%|██████    | 61161/100000 [18:29:51<6:19:47,  1.70it/s]
Train steps ... :  61%|██████    | 61162/100000 [18:29:52<6:19:19,  1.71it/s]
Train steps ... :  61%|██████    | 61163/100000 [18:29:53<6:18:46,  1.71it/s]
Train steps ... :  61%|██████    | 61164/100000 [18:29:53<6:18:42,  1.71it/s]
Train steps ... :  61%|██████    | 61165/100000 [18:29:54<6:18:49,  1.71it/s]
Train steps ... :  61%|██████    | 61166/100000 [18:29:54<6:18:29,  1.71it/s]
Train steps ... :  61%|██████    | 61167/100000 [18:29:55<6:18:15,  1.71it/s]
Train steps ... :  61%|██████    | 61168/100000 [18:29:55<6:19:03,  1.71it/s]
Train steps ... :  61%|██████    | 61169/100000 [18:29:56<6:18:11,  1.71it/s]
Train steps ... :  61%|██████    | 61170/100000 [18:29:57<6:18:23,  1.71it/s]
Train steps ... :  61%|██████    | 61171/100000 [18:29:57<6:18:21,  1.71it/s]
Train steps ... :  61%|██████    | 61172/100000 [18:29:58<6:18:00,  1.71it/s]
Train steps ... :  61%|██████    | 61173/100000 [18:29:58<6:18:06,  1.71it/s]
Train steps ... :  61%|██████    | 61174/100000 [18:29:59<6:18:03,  1.71it/s]
Train steps ... :  61%|██████    | 61175/100000 [18:30:00<6:18:06,  1.71it/s]Step... (61175 / 100000 | Loss: 0.6569720506668091, Learning Rate: 3.9020100502512565e-05)
+
                                                                             
Step... (61175 / 100000 | Loss: 0.6655794382095337, Learning Rate: 3.9020100502512565e-05)
+
Train steps ... :  61%|██████    | 61175/100000 [18:30:00<6:18:06,  1.71it/s]
Train steps ... :  61%|██████    | 61176/100000 [18:30:00<6:18:30,  1.71it/s]
Train steps ... :  61%|██████    | 61177/100000 [18:30:01<6:18:43,  1.71it/s]
Train steps ... :  61%|██████    | 61178/100000 [18:30:01<6:18:30,  1.71it/s]
Train steps ... :  61%|██████    | 61179/100000 [18:30:02<6:18:04,  1.71it/s]
Train steps ... :  61%|██████    | 61180/100000 [18:30:02<6:18:00,  1.71it/s]
Train steps ... :  61%|██████    | 61181/100000 [18:30:03<6:17:59,  1.71it/s]
Train steps ... :  61%|██████    | 61182/100000 [18:30:04<6:18:01,  1.71it/s]
Train steps ... :  61%|██████    | 61183/100000 [18:30:04<6:18:18,  1.71it/s]
Train steps ... :  61%|██████    | 61184/100000 [18:30:05<6:18:43,  1.71it/s]
Train steps ... :  61%|██████    | 61185/100000 [18:30:05<6:18:18,  1.71it/s]
Train steps ... :  61%|██████    | 61186/100000 [18:30:06<6:18:15,  1.71it/s]
Train steps ... :  61%|██████    | 61187/100000 [18:30:07<6:18:06,  1.71it/s]
Train steps ... :  61%|██████    | 61188/100000 [18:30:07<6:17:53,  1.71it/s]
Train steps ... :  61%|██████    | 61189/100000 [18:30:08<6:18:24,  1.71it/s]
Train steps ... :  61%|██████    | 61190/100000 [18:30:08<6:18:02,  1.71it/s]
Train steps ... :  61%|██████    | 61191/100000 [18:30:09<6:18:13,  1.71it/s]
Train steps ... :  61%|██████    | 61192/100000 [18:30:09<6:18:00,  1.71it/s]
Train steps ... :  61%|██████    | 61193/100000 [18:30:10<6:18:26,  1.71it/s]
Train steps ... :  61%|██████    | 61194/100000 [18:30:11<6:18:34,  1.71it/s]
Train steps ... :  61%|██████    | 61195/100000 [18:30:11<6:18:12,  1.71it/s]
Train steps ... :  61%|██████    | 61196/100000 [18:30:12<6:17:48,  1.71it/s]
Train steps ... :  61%|██████    | 61197/100000 [18:30:12<6:17:50,  1.71it/s]
Train steps ... :  61%|██████    | 61198/100000 [18:30:13<6:17:58,  1.71it/s]
Train steps ... :  61%|██████    | 61199/100000 [18:30:14<6:17:51,  1.71it/s]
Train steps ... :  61%|██████    | 61200/100000 [18:30:14<6:17:52,  1.71it/s]Step... (61200 / 100000 | Loss: 0.6398637294769287, Learning Rate: 3.899497487437186e-05)
+
                                                                             
Step... (61200 / 100000 | Loss: 0.6514412760734558, Learning Rate: 3.899497487437186e-05)
+
Train steps ... :  61%|██████    | 61200/100000 [18:30:14<6:17:52,  1.71it/s]
Train steps ... :  61%|██████    | 61201/100000 [18:30:15<6:18:02,  1.71it/s]
Train steps ... :  61%|██████    | 61202/100000 [18:30:15<6:17:50,  1.71it/s]
Train steps ... :  61%|██████    | 61203/100000 [18:30:16<6:18:22,  1.71it/s]
Train steps ... :  61%|██████    | 61204/100000 [18:30:16<6:18:03,  1.71it/s]
Train steps ... :  61%|██████    | 61205/100000 [18:30:17<6:18:20,  1.71it/s]
Train steps ... :  61%|██████    | 61206/100000 [18:30:18<6:18:18,  1.71it/s]
Train steps ... :  61%|██████    | 61207/100000 [18:30:18<6:18:20,  1.71it/s]
Train steps ... :  61%|██████    | 61208/100000 [18:30:19<6:17:52,  1.71it/s]
Train steps ... :  61%|██████    | 61209/100000 [18:30:19<6:18:13,  1.71it/s]
Train steps ... :  61%|██████    | 61210/100000 [18:30:20<6:17:53,  1.71it/s]
Train steps ... :  61%|██████    | 61211/100000 [18:30:21<6:17:46,  1.71it/s]
Train steps ... :  61%|██████    | 61212/100000 [18:30:21<6:18:03,  1.71it/s]
Train steps ... :  61%|██████    | 61213/100000 [18:30:22<6:17:45,  1.71it/s]
Train steps ... :  61%|██████    | 61214/100000 [18:30:22<6:17:53,  1.71it/s]
Train steps ... :  61%|██████    | 61215/100000 [18:30:23<6:18:19,  1.71it/s]
Train steps ... :  61%|██████    | 61216/100000 [18:30:23<6:17:55,  1.71it/s]
Train steps ... :  61%|██████    | 61217/100000 [18:30:24<6:17:49,  1.71it/s]
Train steps ... :  61%|██████    | 61218/100000 [18:30:25<6:18:14,  1.71it/s]
Train steps ... :  61%|██████    | 61219/100000 [18:30:25<6:18:04,  1.71it/s]
Train steps ... :  61%|██████    | 61220/100000 [18:30:26<6:17:42,  1.71it/s]
Train steps ... :  61%|██████    | 61221/100000 [18:30:26<6:17:35,  1.71it/s]
Train steps ... :  61%|██████    | 61222/100000 [18:30:27<6:17:32,  1.71it/s]
Train steps ... :  61%|██████    | 61223/100000 [18:30:28<6:17:56,  1.71it/s]
Train steps ... :  61%|██████    | 61224/100000 [18:30:28<6:17:56,  1.71it/s]
Train steps ... :  61%|██████    | 61225/100000 [18:30:29<6:18:04,  1.71it/s]Step... (61225 / 100000 | Loss: 0.7080504894256592, Learning Rate: 3.896984924623116e-05)
+
                                                                             
Step... (61225 / 100000 | Loss: 0.6909832954406738, Learning Rate: 3.896984924623116e-05)
+
Train steps ... :  61%|██████    | 61225/100000 [18:30:29<6:18:04,  1.71it/s]
Train steps ... :  61%|██████    | 61226/100000 [18:30:29<6:17:39,  1.71it/s]
Train steps ... :  61%|██████    | 61227/100000 [18:30:30<6:17:45,  1.71it/s]
Train steps ... :  61%|██████    | 61228/100000 [18:30:31<6:17:56,  1.71it/s]
Train steps ... :  61%|██████    | 61229/100000 [18:30:31<6:17:40,  1.71it/s]
Train steps ... :  61%|██████    | 61230/100000 [18:30:32<6:17:37,  1.71it/s]
Train steps ... :  61%|██████    | 61231/100000 [18:30:32<6:17:28,  1.71it/s]
Train steps ... :  61%|██████    | 61232/100000 [18:30:33<6:17:41,  1.71it/s]
Train steps ... :  61%|██████    | 61233/100000 [18:30:33<6:18:09,  1.71it/s]
Train steps ... :  61%|██████    | 61234/100000 [18:30:34<6:18:28,  1.71it/s]
Train steps ... :  61%|██████    | 61235/100000 [18:30:35<6:17:51,  1.71it/s]
Train steps ... :  61%|██████    | 61236/100000 [18:30:35<6:17:46,  1.71it/s]
Train steps ... :  61%|██████    | 61237/100000 [18:30:36<6:17:51,  1.71it/s]
Train steps ... :  61%|██████    | 61238/100000 [18:30:36<6:18:25,  1.71it/s]
Train steps ... :  61%|██████    | 61239/100000 [18:30:37<6:18:00,  1.71it/s]
Train steps ... :  61%|██████    | 61240/100000 [18:30:38<6:18:14,  1.71it/s]
Train steps ... :  61%|██████    | 61241/100000 [18:30:38<6:18:12,  1.71it/s]
Train steps ... :  61%|██████    | 61242/100000 [18:30:39<6:18:28,  1.71it/s]
Train steps ... :  61%|██████    | 61243/100000 [18:30:39<6:18:33,  1.71it/s]
Train steps ... :  61%|██████    | 61244/100000 [18:30:40<6:18:03,  1.71it/s]
Train steps ... :  61%|██████    | 61245/100000 [18:30:40<6:18:21,  1.71it/s]
Train steps ... :  61%|██████    | 61246/100000 [18:30:41<6:17:52,  1.71it/s]
Train steps ... :  61%|██████    | 61247/100000 [18:30:42<6:17:38,  1.71it/s]
Train steps ... :  61%|██████    | 61248/100000 [18:30:42<6:17:47,  1.71it/s]
Train steps ... :  61%|██████    | 61249/100000 [18:30:43<6:18:38,  1.71it/s]
Train steps ... :  61%|██████▏   | 61250/100000 [18:30:43<6:18:37,  1.71it/s]Step... (61250 / 100000 | Loss: 0.6431137323379517, Learning Rate: 3.8944723618090455e-05)
+
                                                                             
Step... (61250 / 100000 | Loss: 0.916359543800354, Learning Rate: 3.8944723618090455e-05)
+
Train steps ... :  61%|██████▏   | 61250/100000 [18:30:44<6:18:37,  1.71it/s]
Train steps ... :  61%|██████▏   | 61251/100000 [18:30:44<6:18:21,  1.71it/s]
Train steps ... :  61%|██████▏   | 61252/100000 [18:30:45<6:18:14,  1.71it/s]
Train steps ... :  61%|██████▏   | 61253/100000 [18:30:45<6:18:19,  1.71it/s]
Train steps ... :  61%|██████▏   | 61254/100000 [18:30:46<6:17:53,  1.71it/s]
Train steps ... :  61%|██████▏   | 61255/100000 [18:30:46<6:17:57,  1.71it/s]
Train steps ... :  61%|██████▏   | 61256/100000 [18:30:47<6:17:33,  1.71it/s]
Train steps ... :  61%|██████▏   | 61257/100000 [18:30:47<6:17:11,  1.71it/s]
Train steps ... :  61%|██████▏   | 61258/100000 [18:30:48<6:17:43,  1.71it/s]
Train steps ... :  61%|██████▏   | 61259/100000 [18:30:49<6:17:54,  1.71it/s]
Train steps ... :  61%|██████▏   | 61260/100000 [18:30:49<6:18:00,  1.71it/s]
Train steps ... :  61%|██████▏   | 61261/100000 [18:30:50<6:17:37,  1.71it/s]
Train steps ... :  61%|██████▏   | 61262/100000 [18:30:50<6:17:33,  1.71it/s]
Train steps ... :  61%|██████▏   | 61263/100000 [18:30:51<6:18:17,  1.71it/s]
Train steps ... :  61%|██████▏   | 61264/100000 [18:30:52<6:18:09,  1.71it/s]
Train steps ... :  61%|██████▏   | 61265/100000 [18:30:52<6:18:04,  1.71it/s]
Train steps ... :  61%|██████▏   | 61266/100000 [18:30:53<6:18:00,  1.71it/s]
Train steps ... :  61%|██████▏   | 61267/100000 [18:30:53<6:18:11,  1.71it/s]
Train steps ... :  61%|██████▏   | 61268/100000 [18:30:54<6:17:40,  1.71it/s]
Train steps ... :  61%|██████▏   | 61269/100000 [18:30:55<6:17:36,  1.71it/s]
Train steps ... :  61%|██████▏   | 61270/100000 [18:30:55<6:17:39,  1.71it/s]
Train steps ... :  61%|██████▏   | 61271/100000 [18:30:56<6:17:37,  1.71it/s]
Train steps ... :  61%|██████▏   | 61272/100000 [18:30:56<6:17:14,  1.71it/s]
Train steps ... :  61%|██████▏   | 61273/100000 [18:30:57<6:17:28,  1.71it/s]
Train steps ... :  61%|██████▏   | 61274/100000 [18:30:57<6:17:25,  1.71it/s]
Train steps ... :  61%|██████▏   | 61275/100000 [18:30:58<6:17:35,  1.71it/s]Step... (61275 / 100000 | Loss: 0.7057346105575562, Learning Rate: 3.891959798994975e-05)
+
                                                                             
Step... (61275 / 100000 | Loss: 0.8112835884094238, Learning Rate: 3.891959798994975e-05)
+
Train steps ... :  61%|██████▏   | 61275/100000 [18:30:58<6:17:35,  1.71it/s]
Train steps ... :  61%|██████▏   | 61276/100000 [18:30:59<6:17:45,  1.71it/s]
Train steps ... :  61%|██████▏   | 61277/100000 [18:30:59<6:17:20,  1.71it/s]
Train steps ... :  61%|██████▏   | 61278/100000 [18:31:00<6:17:11,  1.71it/s]
Train steps ... :  61%|██████▏   | 61279/100000 [18:31:00<6:17:09,  1.71it/s]
Train steps ... :  61%|██████▏   | 61280/100000 [18:31:01<6:16:53,  1.71it/s]
Train steps ... :  61%|██████▏   | 61281/100000 [18:31:02<6:17:23,  1.71it/s]
Train steps ... :  61%|██████▏   | 61282/100000 [18:31:02<6:17:01,  1.71it/s]
Train steps ... :  61%|██████▏   | 61283/100000 [18:31:03<6:17:20,  1.71it/s]
Train steps ... :  61%|██████▏   | 61284/100000 [18:31:03<6:17:18,  1.71it/s]
Train steps ... :  61%|██████▏   | 61285/100000 [18:31:04<6:17:55,  1.71it/s]
Train steps ... :  61%|██████▏   | 61286/100000 [18:31:04<6:17:36,  1.71it/s]
Train steps ... :  61%|██████▏   | 61287/100000 [18:31:05<6:17:31,  1.71it/s]
Train steps ... :  61%|██████▏   | 61288/100000 [18:31:06<6:17:49,  1.71it/s]
Train steps ... :  61%|██████▏   | 61289/100000 [18:31:06<6:17:29,  1.71it/s]
Train steps ... :  61%|██████▏   | 61290/100000 [18:31:07<6:18:08,  1.71it/s]
Train steps ... :  61%|██████▏   | 61291/100000 [18:31:07<6:18:08,  1.71it/s]
Train steps ... :  61%|██████▏   | 61292/100000 [18:31:08<6:17:46,  1.71it/s]
Train steps ... :  61%|██████▏   | 61293/100000 [18:31:09<6:17:35,  1.71it/s]
Train steps ... :  61%|██████▏   | 61294/100000 [18:31:09<6:17:13,  1.71it/s]
Train steps ... :  61%|██████▏   | 61295/100000 [18:31:10<6:17:33,  1.71it/s]
Train steps ... :  61%|██████▏   | 61296/100000 [18:31:10<6:17:32,  1.71it/s]
Train steps ... :  61%|██████▏   | 61297/100000 [18:31:11<6:17:06,  1.71it/s]
Train steps ... :  61%|██████▏   | 61298/100000 [18:31:11<6:17:18,  1.71it/s]
Train steps ... :  61%|██████▏   | 61299/100000 [18:31:12<6:17:14,  1.71it/s]
Train steps ... :  61%|██████▏   | 61300/100000 [18:31:13<6:17:15,  1.71it/s]Step... (61300 / 100000 | Loss: 0.8191108703613281, Learning Rate: 3.889447236180905e-05)
+
                                                                             
Step... (61300 / 100000 | Loss: 0.9221705198287964, Learning Rate: 3.889447236180905e-05)
+
Train steps ... :  61%|██████▏   | 61300/100000 [18:31:13<6:17:15,  1.71it/s]
Train steps ... :  61%|██████▏   | 61301/100000 [18:31:13<6:17:09,  1.71it/s]
Train steps ... :  61%|██████▏   | 61302/100000 [18:31:14<6:17:20,  1.71it/s]
Train steps ... :  61%|██████▏   | 61303/100000 [18:31:14<6:16:55,  1.71it/s]
Train steps ... :  61%|██████▏   | 61304/100000 [18:31:15<6:17:37,  1.71it/s]
Train steps ... :  61%|██████▏   | 61305/100000 [18:31:16<6:17:22,  1.71it/s]
Train steps ... :  61%|██████▏   | 61306/100000 [18:31:16<6:17:24,  1.71it/s]
Train steps ... :  61%|██████▏   | 61307/100000 [18:31:17<6:17:03,  1.71it/s]
Train steps ... :  61%|██████▏   | 61308/100000 [18:31:17<6:17:09,  1.71it/s]
Train steps ... :  61%|██████▏   | 61309/100000 [18:31:18<6:16:57,  1.71it/s]
Train steps ... :  61%|██████▏   | 61310/100000 [18:31:18<6:17:15,  1.71it/s]
Train steps ... :  61%|██████▏   | 61311/100000 [18:31:19<6:17:08,  1.71it/s]
Train steps ... :  61%|██████▏   | 61312/100000 [18:31:20<6:17:19,  1.71it/s]
Train steps ... :  61%|██████▏   | 61313/100000 [18:31:20<6:16:57,  1.71it/s]
Train steps ... :  61%|██████▏   | 61314/100000 [18:31:21<6:17:15,  1.71it/s]
Train steps ... :  61%|██████▏   | 61315/100000 [18:31:21<6:17:26,  1.71it/s]
Train steps ... :  61%|██████▏   | 61316/100000 [18:31:22<6:17:07,  1.71it/s]
Train steps ... :  61%|██████▏   | 61317/100000 [18:31:23<6:17:19,  1.71it/s]
Train steps ... :  61%|██████▏   | 61318/100000 [18:31:23<6:17:22,  1.71it/s]
Train steps ... :  61%|██████▏   | 61319/100000 [18:31:24<6:17:13,  1.71it/s]
Train steps ... :  61%|██████▏   | 61320/100000 [18:31:24<6:16:59,  1.71it/s]
Train steps ... :  61%|██████▏   | 61321/100000 [18:31:25<6:16:52,  1.71it/s]
Train steps ... :  61%|██████▏   | 61322/100000 [18:31:26<6:16:49,  1.71it/s]
Train steps ... :  61%|██████▏   | 61323/100000 [18:31:26<6:17:19,  1.71it/s]
Train steps ... :  61%|██████▏   | 61324/100000 [18:31:27<6:17:07,  1.71it/s]
Train steps ... :  61%|██████▏   | 61325/100000 [18:31:27<6:16:47,  1.71it/s]Step... (61325 / 100000 | Loss: 0.5646970868110657, Learning Rate: 3.8869346733668344e-05)
+
                                                                             
Step... (61325 / 100000 | Loss: 0.8909058570861816, Learning Rate: 3.8869346733668344e-05)
+
Train steps ... :  61%|██████▏   | 61325/100000 [18:31:28<6:16:47,  1.71it/s]
Train steps ... :  61%|██████▏   | 61326/100000 [18:31:28<6:17:09,  1.71it/s]
Train steps ... :  61%|██████▏   | 61327/100000 [18:31:28<6:16:56,  1.71it/s]
Train steps ... :  61%|██████▏   | 61328/100000 [18:31:29<6:17:01,  1.71it/s]
Train steps ... :  61%|██████▏   | 61329/100000 [18:31:30<6:17:38,  1.71it/s]
Train steps ... :  61%|██████▏   | 61330/100000 [18:31:30<6:17:40,  1.71it/s]
Train steps ... :  61%|██████▏   | 61331/100000 [18:31:31<6:17:23,  1.71it/s]
Train steps ... :  61%|██████▏   | 61332/100000 [18:31:31<6:17:27,  1.71it/s]
Train steps ... :  61%|██████▏   | 61333/100000 [18:31:32<6:17:13,  1.71it/s]
Train steps ... :  61%|██████▏   | 61334/100000 [18:31:33<6:17:15,  1.71it/s]
Train steps ... :  61%|██████▏   | 61335/100000 [18:31:33<6:17:01,  1.71it/s]
Train steps ... :  61%|██████▏   | 61336/100000 [18:31:34<6:16:41,  1.71it/s]
Train steps ... :  61%|██████▏   | 61337/100000 [18:31:34<6:17:12,  1.71it/s]
Train steps ... :  61%|██████▏   | 61338/100000 [18:31:35<6:17:44,  1.71it/s]
Train steps ... :  61%|██████▏   | 61339/100000 [18:31:35<6:17:52,  1.71it/s]
Train steps ... :  61%|██████▏   | 61340/100000 [18:31:36<6:18:28,  1.70it/s]
Train steps ... :  61%|██████▏   | 61341/100000 [18:31:37<6:17:47,  1.71it/s]
Train steps ... :  61%|██████▏   | 61342/100000 [18:31:37<6:17:41,  1.71it/s]
Train steps ... :  61%|██████▏   | 61343/100000 [18:31:38<6:17:38,  1.71it/s]
Train steps ... :  61%|██████▏   | 61344/100000 [18:31:38<6:17:21,  1.71it/s]
Train steps ... :  61%|██████▏   | 61345/100000 [18:31:39<6:17:04,  1.71it/s]
Train steps ... :  61%|██████▏   | 61346/100000 [18:31:40<6:16:53,  1.71it/s]
Train steps ... :  61%|██████▏   | 61347/100000 [18:31:40<6:16:56,  1.71it/s]
Train steps ... :  61%|██████▏   | 61348/100000 [18:31:41<6:16:40,  1.71it/s]
Train steps ... :  61%|██████▏   | 61349/100000 [18:31:41<6:17:06,  1.71it/s]
Train steps ... :  61%|██████▏   | 61350/100000 [18:31:42<6:17:18,  1.71it/s]Step... (61350 / 100000 | Loss: 0.8125243186950684, Learning Rate: 3.884422110552764e-05)
+
                                                                             
Step... (61350 / 100000 | Loss: 0.7950162887573242, Learning Rate: 3.884422110552764e-05)
+
Train steps ... :  61%|██████▏   | 61350/100000 [18:31:42<6:17:18,  1.71it/s]
Train steps ... :  61%|██████▏   | 61351/100000 [18:31:42<6:17:09,  1.71it/s]
Train steps ... :  61%|██████▏   | 61352/100000 [18:31:43<6:16:49,  1.71it/s]
Train steps ... :  61%|██████▏   | 61353/100000 [18:31:44<6:16:36,  1.71it/s]
Train steps ... :  61%|██████▏   | 61354/100000 [18:31:44<6:16:48,  1.71it/s]
Train steps ... :  61%|██████▏   | 61355/100000 [18:31:45<6:16:41,  1.71it/s]
Train steps ... :  61%|██████▏   | 61356/100000 [18:31:45<6:16:49,  1.71it/s]
Train steps ... :  61%|██████▏   | 61357/100000 [18:31:46<6:16:46,  1.71it/s]
Train steps ... :  61%|██████▏   | 61358/100000 [18:31:47<6:16:40,  1.71it/s]
Train steps ... :  61%|██████▏   | 61359/100000 [18:31:47<6:16:57,  1.71it/s]
Train steps ... :  61%|██████▏   | 61360/100000 [18:31:48<6:16:46,  1.71it/s]
Train steps ... :  61%|██████▏   | 61361/100000 [18:31:48<6:17:25,  1.71it/s]
Train steps ... :  61%|██████▏   | 61362/100000 [18:31:49<6:17:08,  1.71it/s]
Train steps ... :  61%|██████▏   | 61363/100000 [18:31:50<6:17:15,  1.71it/s]
Train steps ... :  61%|██████▏   | 61364/100000 [18:31:50<6:17:20,  1.71it/s]
Train steps ... :  61%|██████▏   | 61365/100000 [18:31:51<6:17:02,  1.71it/s]
Train steps ... :  61%|██████▏   | 61366/100000 [18:31:51<6:17:30,  1.71it/s]
Train steps ... :  61%|██████▏   | 61367/100000 [18:31:52<6:17:03,  1.71it/s]
Train steps ... :  61%|██████▏   | 61368/100000 [18:31:52<6:16:53,  1.71it/s]
Train steps ... :  61%|██████▏   | 61369/100000 [18:31:53<6:16:43,  1.71it/s]
Train steps ... :  61%|██████▏   | 61370/100000 [18:31:54<6:16:30,  1.71it/s]
Train steps ... :  61%|██████▏   | 61371/100000 [18:31:54<6:16:34,  1.71it/s]
Train steps ... :  61%|██████▏   | 61372/100000 [18:31:55<6:16:38,  1.71it/s]
Train steps ... :  61%|██████▏   | 61373/100000 [18:31:55<6:16:23,  1.71it/s]
Train steps ... :  61%|██████▏   | 61374/100000 [18:31:56<6:16:12,  1.71it/s]
Train steps ... :  61%|██████▏   | 61375/100000 [18:31:57<6:16:03,  1.71it/s]Step... (61375 / 100000 | Loss: 1.0578721761703491, Learning Rate: 3.881909547738694e-05)
+
                                                                             
Step... (61375 / 100000 | Loss: 0.8262900114059448, Learning Rate: 3.881909547738694e-05)
+
Train steps ... :  61%|██████▏   | 61375/100000 [18:31:57<6:16:03,  1.71it/s]
Train steps ... :  61%|██████▏   | 61376/100000 [18:31:57<6:16:51,  1.71it/s]
Train steps ... :  61%|██████▏   | 61377/100000 [18:31:58<6:16:29,  1.71it/s]
Train steps ... :  61%|██████▏   | 61378/100000 [18:31:58<6:16:40,  1.71it/s]
Train steps ... :  61%|██████▏   | 61379/100000 [18:31:59<6:16:18,  1.71it/s]
Train steps ... :  61%|██████▏   | 61380/100000 [18:31:59<6:16:21,  1.71it/s]
Train steps ... :  61%|██████▏   | 61381/100000 [18:32:00<6:16:06,  1.71it/s]
Train steps ... :  61%|██████▏   | 61382/100000 [18:32:01<6:16:32,  1.71it/s]
Train steps ... :  61%|██████▏   | 61383/100000 [18:32:01<6:16:20,  1.71it/s]
Train steps ... :  61%|██████▏   | 61384/100000 [18:32:02<6:16:25,  1.71it/s]
Train steps ... :  61%|██████▏   | 61385/100000 [18:32:02<6:16:13,  1.71it/s]
Train steps ... :  61%|██████▏   | 61386/100000 [18:32:03<6:16:00,  1.71it/s]
Train steps ... :  61%|██████▏   | 61387/100000 [18:32:04<6:16:23,  1.71it/s]
Train steps ... :  61%|██████▏   | 61388/100000 [18:32:04<6:16:06,  1.71it/s]
Train steps ... :  61%|██████▏   | 61389/100000 [18:32:05<6:15:58,  1.71it/s]
Train steps ... :  61%|██████▏   | 61390/100000 [18:32:05<6:15:35,  1.71it/s]
Train steps ... :  61%|██████▏   | 61391/100000 [18:32:06<6:15:54,  1.71it/s]
Train steps ... :  61%|██████▏   | 61392/100000 [18:32:06<6:16:00,  1.71it/s]
Train steps ... :  61%|██████▏   | 61393/100000 [18:32:07<6:16:34,  1.71it/s]
Train steps ... :  61%|██████▏   | 61394/100000 [18:32:08<6:16:28,  1.71it/s]
Train steps ... :  61%|██████▏   | 61395/100000 [18:32:08<6:16:26,  1.71it/s]
Train steps ... :  61%|██████▏   | 61396/100000 [18:32:09<6:16:11,  1.71it/s]
Train steps ... :  61%|██████▏   | 61397/100000 [18:32:09<6:16:07,  1.71it/s]
Train steps ... :  61%|██████▏   | 61398/100000 [18:32:10<6:16:05,  1.71it/s]
Train steps ... :  61%|██████▏   | 61399/100000 [18:32:11<6:15:48,  1.71it/s]
Train steps ... :  61%|██████▏   | 61400/100000 [18:32:11<6:16:06,  1.71it/s]Step... (61400 / 100000 | Loss: 0.9059278964996338, Learning Rate: 3.8793969849246234e-05)
+
                                                                             
Step... (61400 / 100000 | Loss: 0.6433029770851135, Learning Rate: 3.8793969849246234e-05)
+
Train steps ... :  61%|██████▏   | 61400/100000 [18:32:11<6:16:06,  1.71it/s]
Train steps ... :  61%|██████▏   | 61401/100000 [18:32:12<6:16:53,  1.71it/s]
Train steps ... :  61%|██████▏   | 61402/100000 [18:32:12<6:16:46,  1.71it/s]
Train steps ... :  61%|██████▏   | 61403/100000 [18:32:13<6:16:36,  1.71it/s]
Train steps ... :  61%|██████▏   | 61404/100000 [18:32:13<6:16:29,  1.71it/s]
Train steps ... :  61%|██████▏   | 61405/100000 [18:32:14<6:16:38,  1.71it/s]
Train steps ... :  61%|██████▏   | 61406/100000 [18:32:15<6:16:24,  1.71it/s]
Train steps ... :  61%|██████▏   | 61407/100000 [18:32:15<6:16:37,  1.71it/s]
Train steps ... :  61%|██████▏   | 61408/100000 [18:32:16<6:16:12,  1.71it/s]
Train steps ... :  61%|██████▏   | 61409/100000 [18:32:16<6:16:17,  1.71it/s]
Train steps ... :  61%|██████▏   | 61410/100000 [18:32:17<6:16:42,  1.71it/s]
Train steps ... :  61%|██████▏   | 61411/100000 [18:32:18<6:16:08,  1.71it/s]
Train steps ... :  61%|██████▏   | 61412/100000 [18:32:18<6:15:47,  1.71it/s]
Train steps ... :  61%|██████▏   | 61413/100000 [18:32:19<6:16:09,  1.71it/s]
Train steps ... :  61%|██████▏   | 61414/100000 [18:32:19<6:16:01,  1.71it/s]
Train steps ... :  61%|██████▏   | 61415/100000 [18:32:20<6:15:44,  1.71it/s]
Train steps ... :  61%|██████▏   | 61416/100000 [18:32:21<6:15:46,  1.71it/s]
Train steps ... :  61%|██████▏   | 61417/100000 [18:32:21<6:16:05,  1.71it/s]
Train steps ... :  61%|██████▏   | 61418/100000 [18:32:22<6:15:39,  1.71it/s]
Train steps ... :  61%|██████▏   | 61419/100000 [18:32:22<6:15:46,  1.71it/s]
Train steps ... :  61%|██████▏   | 61420/100000 [18:32:23<6:15:39,  1.71it/s]
Train steps ... :  61%|██████▏   | 61421/100000 [18:32:23<6:15:38,  1.71it/s]
Train steps ... :  61%|██████▏   | 61422/100000 [18:32:24<6:15:45,  1.71it/s]
Train steps ... :  61%|██████▏   | 61423/100000 [18:32:25<6:15:47,  1.71it/s]
Train steps ... :  61%|██████▏   | 61424/100000 [18:32:25<6:15:39,  1.71it/s]
Train steps ... :  61%|██████▏   | 61425/100000 [18:32:26<6:15:38,  1.71it/s]Step... (61425 / 100000 | Loss: 0.7793303728103638, Learning Rate: 3.8768844221105524e-05)
+
                                                                             
Step... (61425 / 100000 | Loss: 0.7361854314804077, Learning Rate: 3.8768844221105524e-05)
+
Train steps ... :  61%|██████▏   | 61425/100000 [18:32:26<6:15:38,  1.71it/s]
Train steps ... :  61%|██████▏   | 61426/100000 [18:32:26<6:15:52,  1.71it/s]
Train steps ... :  61%|██████▏   | 61427/100000 [18:32:27<6:15:38,  1.71it/s]
Train steps ... :  61%|██████▏   | 61428/100000 [18:32:28<6:15:29,  1.71it/s]
Train steps ... :  61%|██████▏   | 61429/100000 [18:32:28<6:16:50,  1.71it/s]
Train steps ... :  61%|██████▏   | 61430/100000 [18:32:29<6:17:01,  1.71it/s]
Train steps ... :  61%|██████▏   | 61431/100000 [18:32:29<6:15:56,  1.71it/s]
Train steps ... :  61%|██████▏   | 61432/100000 [18:32:30<6:15:51,  1.71it/s]
Train steps ... :  61%|██████▏   | 61433/100000 [18:32:30<6:15:39,  1.71it/s]
Train steps ... :  61%|██████▏   | 61434/100000 [18:32:31<6:16:13,  1.71it/s]
Train steps ... :  61%|██████▏   | 61435/100000 [18:32:32<6:15:40,  1.71it/s]
Train steps ... :  61%|██████▏   | 61436/100000 [18:32:32<6:15:54,  1.71it/s]
Train steps ... :  61%|██████▏   | 61437/100000 [18:32:33<6:16:03,  1.71it/s]
Train steps ... :  61%|██████▏   | 61438/100000 [18:32:33<6:15:44,  1.71it/s]
Train steps ... :  61%|██████▏   | 61439/100000 [18:32:34<6:15:27,  1.71it/s]
Train steps ... :  61%|██████▏   | 61440/100000 [18:32:35<6:15:30,  1.71it/s]
Train steps ... :  61%|██████▏   | 61441/100000 [18:32:35<6:15:47,  1.71it/s]
Train steps ... :  61%|██████▏   | 61442/100000 [18:32:36<6:15:26,  1.71it/s]
Train steps ... :  61%|██████▏   | 61443/100000 [18:32:36<6:15:41,  1.71it/s]
Train steps ... :  61%|██████▏   | 61444/100000 [18:32:37<6:15:51,  1.71it/s]
Train steps ... :  61%|██████▏   | 61445/100000 [18:32:37<6:15:57,  1.71it/s]
Train steps ... :  61%|██████▏   | 61446/100000 [18:32:38<6:15:55,  1.71it/s]
Train steps ... :  61%|██████▏   | 61447/100000 [18:32:39<6:16:29,  1.71it/s]
Train steps ... :  61%|██████▏   | 61448/100000 [18:32:39<6:15:58,  1.71it/s]
Train steps ... :  61%|██████▏   | 61449/100000 [18:32:40<6:15:50,  1.71it/s]
Train steps ... :  61%|██████▏   | 61450/100000 [18:32:40<6:16:06,  1.71it/s]Step... (61450 / 100000 | Loss: 0.5799360871315002, Learning Rate: 3.874371859296483e-05)
+
                                                                             
Step... (61450 / 100000 | Loss: 0.7497272491455078, Learning Rate: 3.874371859296483e-05)
+
Train steps ... :  61%|██████▏   | 61450/100000 [18:32:41<6:16:06,  1.71it/s]
Train steps ... :  61%|██████▏   | 61451/100000 [18:32:41<6:15:50,  1.71it/s]
Train steps ... :  61%|██████▏   | 61452/100000 [18:32:42<6:15:48,  1.71it/s]
Train steps ... :  61%|██████▏   | 61453/100000 [18:32:42<6:16:03,  1.71it/s]
Train steps ... :  61%|██████▏   | 61454/100000 [18:32:43<6:16:07,  1.71it/s]
Train steps ... :  61%|██████▏   | 61455/100000 [18:32:43<6:15:53,  1.71it/s]
Train steps ... :  61%|██████▏   | 61456/100000 [18:32:44<6:15:45,  1.71it/s]
Train steps ... :  61%|██████▏   | 61457/100000 [18:32:44<6:15:28,  1.71it/s]
Train steps ... :  61%|██████▏   | 61458/100000 [18:32:45<6:15:55,  1.71it/s]
Train steps ... :  61%|██████▏   | 61459/100000 [18:32:46<6:16:14,  1.71it/s]
Train steps ... :  61%|██████▏   | 61460/100000 [18:32:46<6:15:46,  1.71it/s]
Train steps ... :  61%|██████▏   | 61461/100000 [18:32:47<6:16:06,  1.71it/s]
Train steps ... :  61%|██████▏   | 61462/100000 [18:32:47<6:16:00,  1.71it/s]
Train steps ... :  61%|██████▏   | 61463/100000 [18:32:48<6:16:01,  1.71it/s]
Train steps ... :  61%|██████▏   | 61464/100000 [18:32:49<6:15:50,  1.71it/s]
Train steps ... :  61%|██████▏   | 61465/100000 [18:32:49<6:16:10,  1.71it/s]
Train steps ... :  61%|██████▏   | 61466/100000 [18:32:50<6:15:44,  1.71it/s]
Train steps ... :  61%|██████▏   | 61467/100000 [18:32:50<6:15:41,  1.71it/s]
Train steps ... :  61%|██████▏   | 61468/100000 [18:32:51<6:15:42,  1.71it/s]
Train steps ... :  61%|██████▏   | 61469/100000 [18:32:52<6:15:19,  1.71it/s]
Train steps ... :  61%|██████▏   | 61470/100000 [18:32:52<6:15:42,  1.71it/s]
Train steps ... :  61%|██████▏   | 61471/100000 [18:32:53<6:16:01,  1.71it/s]
Train steps ... :  61%|██████▏   | 61472/100000 [18:32:53<6:16:00,  1.71it/s]
Train steps ... :  61%|██████▏   | 61473/100000 [18:32:54<6:15:33,  1.71it/s]
Train steps ... :  61%|██████▏   | 61474/100000 [18:32:54<6:15:27,  1.71it/s]
Train steps ... :  61%|██████▏   | 61475/100000 [18:32:55<6:15:13,  1.71it/s]Step... (61475 / 100000 | Loss: 0.6085668206214905, Learning Rate: 3.8718592964824124e-05)
+
                                                                             
Step... (61475 / 100000 | Loss: 0.9506573677062988, Learning Rate: 3.8718592964824124e-05)
+
Train steps ... :  61%|██████▏   | 61475/100000 [18:32:55<6:15:13,  1.71it/s]
Train steps ... :  61%|██████▏   | 61476/100000 [18:32:56<6:15:35,  1.71it/s]
Train steps ... :  61%|██████▏   | 61477/100000 [18:32:56<6:15:38,  1.71it/s]
Train steps ... :  61%|██████▏   | 61478/100000 [18:32:57<6:16:09,  1.71it/s]
Train steps ... :  61%|██████▏   | 61479/100000 [18:32:57<6:16:03,  1.71it/s]
Train steps ... :  61%|██████▏   | 61480/100000 [18:32:58<6:16:07,  1.71it/s]
Train steps ... :  61%|██████▏   | 61481/100000 [18:32:59<6:15:32,  1.71it/s]
Train steps ... :  61%|██████▏   | 61482/100000 [18:32:59<6:15:33,  1.71it/s]
Train steps ... :  61%|██████▏   | 61483/100000 [18:33:00<6:15:11,  1.71it/s]
Train steps ... :  61%|██████▏   | 61484/100000 [18:33:00<6:15:17,  1.71it/s]
Train steps ... :  61%|██████▏   | 61485/100000 [18:33:01<6:15:17,  1.71it/s]
Train steps ... :  61%|██████▏   | 61486/100000 [18:33:01<6:15:18,  1.71it/s]
Train steps ... :  61%|██████▏   | 61487/100000 [18:33:02<6:15:05,  1.71it/s]
Train steps ... :  61%|██████▏   | 61488/100000 [18:33:03<6:14:49,  1.71it/s]
Train steps ... :  61%|██████▏   | 61489/100000 [18:33:03<6:15:31,  1.71it/s]
Train steps ... :  61%|██████▏   | 61490/100000 [18:33:04<6:15:44,  1.71it/s]
Train steps ... :  61%|██████▏   | 61491/100000 [18:33:04<6:15:37,  1.71it/s]
Train steps ... :  61%|██████▏   | 61492/100000 [18:33:05<6:15:42,  1.71it/s]
Train steps ... :  61%|██████▏   | 61493/100000 [18:33:06<6:15:27,  1.71it/s]
Train steps ... :  61%|██████▏   | 61494/100000 [18:33:06<6:15:12,  1.71it/s]
Train steps ... :  61%|██████▏   | 61495/100000 [18:33:07<6:15:17,  1.71it/s]
Train steps ... :  61%|██████▏   | 61496/100000 [18:33:07<6:14:54,  1.71it/s]
Train steps ... :  61%|██████▏   | 61497/100000 [18:33:08<6:15:10,  1.71it/s]
Train steps ... :  61%|██████▏   | 61498/100000 [18:33:08<6:15:05,  1.71it/s]
Train steps ... :  61%|██████▏   | 61499/100000 [18:33:09<6:15:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 61500/100000 [18:33:10<6:15:04,  1.71it/s]Step... (61500 / 100000 | Loss: 0.8006843328475952, Learning Rate: 3.869346733668342e-05)
+
                                                                             
Step... (61500 / 100000 | Loss: 0.7746128439903259, Learning Rate: 3.869346733668342e-05)
+
Train steps ... :  62%|██████▏   | 61500/100000 [18:33:10<6:15:04,  1.71it/s]
Train steps ... :  62%|██████��   | 61501/100000 [18:33:10<6:15:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 61502/100000 [18:33:11<6:15:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 61503/100000 [18:33:11<6:15:37,  1.71it/s]
Train steps ... :  62%|██████▏   | 61504/100000 [18:33:12<6:15:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61505/100000 [18:33:13<6:16:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61506/100000 [18:33:13<6:15:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61507/100000 [18:33:14<6:15:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 61508/100000 [18:33:14<6:15:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 61509/100000 [18:33:15<6:15:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61510/100000 [18:33:16<6:15:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 61511/100000 [18:33:16<6:15:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 61512/100000 [18:33:17<6:14:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 61513/100000 [18:33:17<6:15:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61514/100000 [18:33:18<6:15:37,  1.71it/s]
Train steps ... :  62%|██████▏   | 61515/100000 [18:33:18<6:15:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61516/100000 [18:33:19<6:15:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 61517/100000 [18:33:20<6:15:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61518/100000 [18:33:20<6:15:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 61519/100000 [18:33:21<6:14:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 61520/100000 [18:33:21<6:14:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 61521/100000 [18:33:22<6:15:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61522/100000 [18:33:23<6:14:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 61523/100000 [18:33:23<6:14:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 61524/100000 [18:33:24<6:14:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 61525/100000 [18:33:24<6:15:13,  1.71it/s]Step... (61525 / 100000 | Loss: 0.6949108839035034, Learning Rate: 3.866834170854272e-05)
+
                                                                             
Step... (61525 / 100000 | Loss: 0.6643858551979065, Learning Rate: 3.866834170854272e-05)
+
Train steps ... :  62%|██████▏   | 61525/100000 [18:33:25<6:15:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 61526/100000 [18:33:25<6:15:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61527/100000 [18:33:25<6:14:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 61528/100000 [18:33:26<6:15:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 61529/100000 [18:33:27<6:14:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61530/100000 [18:33:27<6:14:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 61531/100000 [18:33:28<6:14:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 61532/100000 [18:33:28<6:14:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61533/100000 [18:33:29<6:15:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 61534/100000 [18:33:30<6:14:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 61535/100000 [18:33:30<6:14:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61536/100000 [18:33:31<6:15:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 61537/100000 [18:33:31<6:14:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61538/100000 [18:33:32<6:14:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 61539/100000 [18:33:32<6:14:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 61540/100000 [18:33:33<6:14:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61541/100000 [18:33:34<6:15:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 61542/100000 [18:33:34<6:14:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61543/100000 [18:33:35<6:14:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61544/100000 [18:33:35<6:14:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61545/100000 [18:33:36<6:14:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61546/100000 [18:33:37<6:14:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61547/100000 [18:33:37<6:14:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 61548/100000 [18:33:38<6:14:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 61549/100000 [18:33:38<6:14:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 61550/100000 [18:33:39<6:14:40,  1.71it/s]Step... (61550 / 100000 | Loss: 0.6356304287910461, Learning Rate: 3.8643216080402014e-05)
+
                                                                             
Step... (61550 / 100000 | Loss: 0.8067874312400818, Learning Rate: 3.8643216080402014e-05)
+
Train steps ... :  62%|██████▏   | 61550/100000 [18:33:39<6:14:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61551/100000 [18:33:39<6:14:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 61552/100000 [18:33:40<6:15:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 61553/100000 [18:33:41<6:15:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 61554/100000 [18:33:41<6:14:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61555/100000 [18:33:42<6:15:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 61556/100000 [18:33:42<6:14:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 61557/100000 [18:33:43<6:15:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 61558/100000 [18:33:44<6:14:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 61559/100000 [18:33:44<6:15:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 61560/100000 [18:33:45<6:15:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61561/100000 [18:33:45<6:14:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 61562/100000 [18:33:46<6:14:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 61563/100000 [18:33:47<6:14:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 61564/100000 [18:33:47<6:15:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 61565/100000 [18:33:48<6:14:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61566/100000 [18:33:48<6:15:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61567/100000 [18:33:49<6:15:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 61568/100000 [18:33:49<6:15:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 61569/100000 [18:33:50<6:14:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 61570/100000 [18:33:51<6:14:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61571/100000 [18:33:51<6:14:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 61572/100000 [18:33:52<6:14:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 61573/100000 [18:33:52<6:14:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 61574/100000 [18:33:53<6:14:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 61575/100000 [18:33:54<6:14:31,  1.71it/s]Step... (61575 / 100000 | Loss: 0.5896997451782227, Learning Rate: 3.861809045226131e-05)
+
                                                                             
Step... (61575 / 100000 | Loss: 0.5038110017776489, Learning Rate: 3.861809045226131e-05)
+
Train steps ... :  62%|██████▏   | 61575/100000 [18:33:54<6:14:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 61576/100000 [18:33:54<6:14:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 61577/100000 [18:33:55<6:14:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 61578/100000 [18:33:55<6:14:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 61579/100000 [18:33:56<6:15:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 61580/100000 [18:33:56<6:14:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61581/100000 [18:33:57<6:14:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 61582/100000 [18:33:58<6:14:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 61583/100000 [18:33:58<6:14:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 61584/100000 [18:33:59<6:14:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 61585/100000 [18:33:59<6:14:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 61586/100000 [18:34:00<6:14:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61587/100000 [18:34:01<6:15:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61588/100000 [18:34:01<6:15:48,  1.70it/s]
Train steps ... :  62%|██████▏   | 61589/100000 [18:34:02<6:15:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 61590/100000 [18:34:02<6:15:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61591/100000 [18:34:03<6:14:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61592/100000 [18:34:03<6:14:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 61593/100000 [18:34:04<6:14:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61594/100000 [18:34:05<6:14:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61595/100000 [18:34:05<6:14:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61596/100000 [18:34:06<6:14:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 61597/100000 [18:34:06<6:14:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61598/100000 [18:34:07<6:15:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 61599/100000 [18:34:08<6:15:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 61600/100000 [18:34:08<6:14:49,  1.71it/s]Step... (61600 / 100000 | Loss: 0.7562344074249268, Learning Rate: 3.85929648241206e-05)
+
                                                                             
Step... (61600 / 100000 | Loss: 0.5721180438995361, Learning Rate: 3.85929648241206e-05)
+
Train steps ... :  62%|██████▏   | 61600/100000 [18:34:08<6:14:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 61601/100000 [18:34:09<6:14:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 61602/100000 [18:34:09<6:14:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61603/100000 [18:34:10<6:14:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 61604/100000 [18:34:11<6:14:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 61605/100000 [18:34:11<6:13:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 61606/100000 [18:34:12<6:13:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 61607/100000 [18:34:12<6:14:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61608/100000 [18:34:13<6:14:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61609/100000 [18:34:13<6:14:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 61610/100000 [18:34:14<6:14:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61611/100000 [18:34:15<6:14:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 61612/100000 [18:34:15<6:14:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61613/100000 [18:34:16<6:14:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61614/100000 [18:34:16<6:14:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 61615/100000 [18:34:17<6:14:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 61616/100000 [18:34:18<6:14:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 61617/100000 [18:34:18<6:14:37,  1.71it/s]
Train steps ... :  62%|██████▏   | 61618/100000 [18:34:19<6:14:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61619/100000 [18:34:19<6:14:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 61620/100000 [18:34:20<6:14:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 61621/100000 [18:34:20<6:14:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 61622/100000 [18:34:21<6:14:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61623/100000 [18:34:22<6:14:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61624/100000 [18:34:22<6:14:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 61625/100000 [18:34:23<6:14:34,  1.71it/s]Step... (61625 / 100000 | Loss: 0.48533695936203003, Learning Rate: 3.85678391959799e-05)
+
                                                                             
Step... (61625 / 100000 | Loss: 0.8141469955444336, Learning Rate: 3.85678391959799e-05)
+
Train steps ... :  62%|██████▏   | 61625/100000 [18:34:23<6:14:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 61626/100000 [18:34:23<6:14:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 61627/100000 [18:34:24<6:14:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 61628/100000 [18:34:25<6:14:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 61629/100000 [18:34:25<6:14:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 61630/100000 [18:34:26<6:14:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61631/100000 [18:34:26<6:14:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61632/100000 [18:34:27<6:14:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 61633/100000 [18:34:27<6:14:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 61634/100000 [18:34:28<6:14:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 61635/100000 [18:34:29<6:14:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 61636/100000 [18:34:29<6:14:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 61637/100000 [18:34:30<6:14:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 61638/100000 [18:34:30<6:14:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 61639/100000 [18:34:31<6:13:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 61640/100000 [18:34:32<6:13:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 61641/100000 [18:34:32<6:14:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 61642/100000 [18:34:33<6:14:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 61643/100000 [18:34:33<6:14:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 61644/100000 [18:34:34<6:14:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 61645/100000 [18:34:35<6:14:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 61646/100000 [18:34:35<6:14:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 61647/100000 [18:34:36<6:14:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 61648/100000 [18:34:36<6:14:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 61649/100000 [18:34:37<6:14:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 61650/100000 [18:34:37<6:14:07,  1.71it/s]Step... (61650 / 100000 | Loss: 0.7477430105209351, Learning Rate: 3.85427135678392e-05)
+
                                                                             
Step... (61650 / 100000 | Loss: 0.8586531281471252, Learning Rate: 3.85427135678392e-05)
+
Train steps ... :  62%|██████▏   | 61650/100000 [18:34:38<6:14:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61651/100000 [18:34:38<6:14:53,  1.70it/s]
Train steps ... :  62%|██████▏   | 61652/100000 [18:34:39<6:14:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 61653/100000 [18:34:39<6:13:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 61654/100000 [18:34:40<6:13:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61655/100000 [18:34:40<6:14:52,  1.70it/s]
Train steps ... :  62%|██████▏   | 61656/100000 [18:34:41<6:14:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61657/100000 [18:34:42<6:14:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 61658/100000 [18:34:42<6:14:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61659/100000 [18:34:43<6:14:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 61660/100000 [18:34:43<6:13:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 61661/100000 [18:34:44<6:13:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 61662/100000 [18:34:44<6:13:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 61663/100000 [18:34:45<6:14:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61664/100000 [18:34:46<6:13:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61665/100000 [18:34:46<6:13:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 61666/100000 [18:34:47<6:13:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 61667/100000 [18:34:47<6:13:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 61668/100000 [18:34:48<6:13:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 61669/100000 [18:34:49<6:13:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61670/100000 [18:34:49<6:13:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61671/100000 [18:34:50<6:13:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61672/100000 [18:34:50<6:13:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61673/100000 [18:34:51<6:13:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 61674/100000 [18:34:51<6:13:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 61675/100000 [18:34:52<6:13:23,  1.71it/s]Step... (61675 / 100000 | Loss: 0.6686772108078003, Learning Rate: 3.85175879396985e-05)
+
                                                                             
Step... (61675 / 100000 | Loss: 0.7227623462677002, Learning Rate: 3.85175879396985e-05)
+
Train steps ... :  62%|██████▏   | 61675/100000 [18:34:52<6:13:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61676/100000 [18:34:53<6:13:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61677/100000 [18:34:53<6:13:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 61678/100000 [18:34:54<6:13:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61679/100000 [18:34:54<6:13:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61680/100000 [18:34:55<6:13:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 61681/100000 [18:34:56<6:13:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 61682/100000 [18:34:56<6:13:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 61683/100000 [18:34:57<6:13:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 61684/100000 [18:34:57<6:13:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 61685/100000 [18:34:58<6:13:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 61686/100000 [18:34:58<6:13:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 61687/100000 [18:34:59<6:13:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 61688/100000 [18:35:00<6:13:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 61689/100000 [18:35:00<6:13:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61690/100000 [18:35:01<6:14:43,  1.70it/s]
Train steps ... :  62%|██████▏   | 61691/100000 [18:35:01<6:14:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61692/100000 [18:35:02<6:13:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 61693/100000 [18:35:03<6:13:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 61694/100000 [18:35:03<6:13:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 61695/100000 [18:35:04<6:13:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 61696/100000 [18:35:04<6:13:13,  1.71it/s]
Train steps ... :  62%|��█████▏   | 61697/100000 [18:35:05<6:12:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 61698/100000 [18:35:06<6:13:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 61699/100000 [18:35:06<6:13:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61700/100000 [18:35:07<6:13:16,  1.71it/s]Step... (61700 / 100000 | Loss: 0.9511032104492188, Learning Rate: 3.8492462311557794e-05)
+
                                                                             
Step... (61700 / 100000 | Loss: 1.051353931427002, Learning Rate: 3.8492462311557794e-05)
+
Train steps ... :  62%|██████▏   | 61700/100000 [18:35:07<6:13:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 61701/100000 [18:35:07<6:13:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 61702/100000 [18:35:08<6:13:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 61703/100000 [18:35:08<6:13:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 61704/100000 [18:35:09<6:13:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 61705/100000 [18:35:10<6:13:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 61706/100000 [18:35:10<6:13:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 61707/100000 [18:35:11<6:13:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 61708/100000 [18:35:11<6:13:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 61709/100000 [18:35:12<6:12:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 61710/100000 [18:35:13<6:12:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 61711/100000 [18:35:13<6:12:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61712/100000 [18:35:14<6:12:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61713/100000 [18:35:14<6:13:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 61714/100000 [18:35:15<6:13:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 61715/100000 [18:35:15<6:13:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 61716/100000 [18:35:16<6:13:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 61717/100000 [18:35:17<6:12:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61718/100000 [18:35:17<6:13:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 61719/100000 [18:35:18<6:13:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 61720/100000 [18:35:18<6:13:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61721/100000 [18:35:19<6:13:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 61722/100000 [18:35:20<6:13:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 61723/100000 [18:35:20<6:13:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 61724/100000 [18:35:21<6:12:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 61725/100000 [18:35:21<6:13:17,  1.71it/s]Step... (61725 / 100000 | Loss: 0.7681013345718384, Learning Rate: 3.846733668341709e-05)
+
                                                                             
Step... (61725 / 100000 | Loss: 0.6749083399772644, Learning Rate: 3.846733668341709e-05)
+
Train steps ... :  62%|██████▏   | 61725/100000 [18:35:22<6:13:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 61726/100000 [18:35:22<6:13:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 61727/100000 [18:35:22<6:13:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 61728/100000 [18:35:23<6:13:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61729/100000 [18:35:24<6:12:58,  1.71it/s]
Train steps ... :  62%|██████▏   | 61730/100000 [18:35:24<6:12:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61731/100000 [18:35:25<6:12:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 61732/100000 [18:35:25<6:13:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 61733/100000 [18:35:26<6:12:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 61734/100000 [18:35:27<6:12:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 61735/100000 [18:35:27<6:13:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 61736/100000 [18:35:28<6:12:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 61737/100000 [18:35:28<6:13:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 61738/100000 [18:35:29<6:12:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 61739/100000 [18:35:29<6:12:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61740/100000 [18:35:30<6:12:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 61741/100000 [18:35:31<6:12:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61742/100000 [18:35:31<6:13:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61743/100000 [18:35:32<6:13:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 61744/100000 [18:35:32<6:13:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 61745/100000 [18:35:33<6:12:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 61746/100000 [18:35:34<6:12:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61747/100000 [18:35:34<6:12:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 61748/100000 [18:35:35<6:12:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61749/100000 [18:35:35<6:12:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61750/100000 [18:35:36<6:12:36,  1.71it/s]Step... (61750 / 100000 | Loss: 0.6452099084854126, Learning Rate: 3.844221105527639e-05)
+
                                                                             
Step... (61750 / 100000 | Loss: 0.6445231437683105, Learning Rate: 3.844221105527639e-05)
+
Train steps ... :  62%|██████▏   | 61750/100000 [18:35:36<6:12:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 61751/100000 [18:35:37<6:12:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61752/100000 [18:35:37<6:12:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 61753/100000 [18:35:38<6:12:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 61754/100000 [18:35:38<6:12:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 61755/100000 [18:35:39<6:12:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61756/100000 [18:35:39<6:12:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 61757/100000 [18:35:40<6:12:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 61758/100000 [18:35:41<6:12:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 61759/100000 [18:35:41<6:12:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 61760/100000 [18:35:42<6:12:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 61761/100000 [18:35:42<6:12:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61762/100000 [18:35:43<6:12:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61763/100000 [18:35:44<6:12:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 61764/100000 [18:35:44<6:12:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61765/100000 [18:35:45<6:12:37,  1.71it/s]
Train steps ... :  62%|██████▏   | 61766/100000 [18:35:45<6:12:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61767/100000 [18:35:46<6:13:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 61768/100000 [18:35:46<6:12:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61769/100000 [18:35:47<6:13:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 61770/100000 [18:35:48<6:12:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 61771/100000 [18:35:48<6:12:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 61772/100000 [18:35:49<6:12:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 61773/100000 [18:35:49<6:12:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 61774/100000 [18:35:50<6:12:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 61775/100000 [18:35:51<6:12:09,  1.71it/s]Step... (61775 / 100000 | Loss: 0.5809466242790222, Learning Rate: 3.841708542713568e-05)
+
                                                                             
Step... (61775 / 100000 | Loss: 0.5836994647979736, Learning Rate: 3.841708542713568e-05)
+
Train steps ... :  62%|██████▏   | 61775/100000 [18:35:51<6:12:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 61776/100000 [18:35:51<6:12:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 61777/100000 [18:35:52<6:13:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61778/100000 [18:35:52<6:13:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 61779/100000 [18:35:53<6:13:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 61780/100000 [18:35:53<6:13:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 61781/100000 [18:35:54<6:12:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 61782/100000 [18:35:55<6:12:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 61783/100000 [18:35:55<6:12:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 61784/100000 [18:35:56<6:12:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 61785/100000 [18:35:56<6:12:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61786/100000 [18:35:57<6:12:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61787/100000 [18:35:58<6:12:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61788/100000 [18:35:58<6:12:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 61789/100000 [18:35:59<6:12:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 61790/100000 [18:35:59<6:12:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 61791/100000 [18:36:00<6:12:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 61792/100000 [18:36:00<6:12:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 61793/100000 [18:36:01<6:12:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61794/100000 [18:36:02<6:12:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 61795/100000 [18:36:02<6:12:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 61796/100000 [18:36:03<6:12:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 61797/100000 [18:36:03<6:12:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 61798/100000 [18:36:04<6:12:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 61799/100000 [18:36:05<6:12:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 61800/100000 [18:36:05<6:12:42,  1.71it/s]Step... (61800 / 100000 | Loss: 0.7793551683425903, Learning Rate: 3.8391959798994973e-05)
+
                                                                             
Step... (61800 / 100000 | Loss: 0.661311149597168, Learning Rate: 3.8391959798994973e-05)
+
Train steps ... :  62%|██████▏   | 61800/100000 [18:36:06<6:12:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 61801/100000 [18:36:06<6:12:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 61802/100000 [18:36:06<6:12:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 61803/100000 [18:36:07<6:12:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 61804/100000 [18:36:08<6:12:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 61805/100000 [18:36:08<6:12:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61806/100000 [18:36:09<6:11:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 61807/100000 [18:36:09<6:12:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 61808/100000 [18:36:10<6:11:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 61809/100000 [18:36:10<6:11:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61810/100000 [18:36:11<6:11:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 61811/100000 [18:36:12<6:11:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 61812/100000 [18:36:12<6:12:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61813/100000 [18:36:13<6:12:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 61814/100000 [18:36:13<6:12:37,  1.71it/s]
Train steps ... :  62%|██████▏   | 61815/100000 [18:36:14<6:13:41,  1.70it/s]
Train steps ... :  62%|██████▏   | 61816/100000 [18:36:15<6:12:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 61817/100000 [18:36:15<6:12:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 61818/100000 [18:36:16<6:12:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 61819/100000 [18:36:16<6:12:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61820/100000 [18:36:17<6:12:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 61821/100000 [18:36:17<6:12:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61822/100000 [18:36:18<6:12:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 61823/100000 [18:36:19<6:12:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 61824/100000 [18:36:19<6:13:12,  1.70it/s]
Train steps ... :  62%|██████▏   | 61825/100000 [18:36:20<6:13:04,  1.71it/s]Step... (61825 / 100000 | Loss: 0.6827601790428162, Learning Rate: 3.836683417085427e-05)
+
                                                                             
Step... (61825 / 100000 | Loss: 0.8864713907241821, Learning Rate: 3.836683417085427e-05)
+
Train steps ... :  62%|██████▏   | 61825/100000 [18:36:20<6:13:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 61826/100000 [18:36:20<6:13:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61827/100000 [18:36:21<6:12:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 61828/100000 [18:36:22<6:12:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 61829/100000 [18:36:22<6:12:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61830/100000 [18:36:23<6:12:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 61831/100000 [18:36:23<6:12:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61832/100000 [18:36:24<6:12:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61833/100000 [18:36:24<6:11:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 61834/100000 [18:36:25<6:12:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61835/100000 [18:36:26<6:12:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 61836/100000 [18:36:26<6:11:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 61837/100000 [18:36:27<6:11:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 61838/100000 [18:36:27<6:12:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61839/100000 [18:36:28<6:12:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61840/100000 [18:36:29<6:11:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61841/100000 [18:36:29<6:11:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 61842/100000 [18:36:30<6:11:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 61843/100000 [18:36:30<6:12:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 61844/100000 [18:36:31<6:11:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 61845/100000 [18:36:31<6:11:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61846/100000 [18:36:32<6:12:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61847/100000 [18:36:33<6:12:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 61848/100000 [18:36:33<6:12:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61849/100000 [18:36:34<6:11:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 61850/100000 [18:36:34<6:12:01,  1.71it/s]Step... (61850 / 100000 | Loss: 0.9178014397621155, Learning Rate: 3.834170854271357e-05)
+
                                                                             
Step... (61850 / 100000 | Loss: 0.5985079407691956, Learning Rate: 3.834170854271357e-05)
+
Train steps ... :  62%|██████▏   | 61850/100000 [18:36:35<6:12:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61851/100000 [18:36:35<6:12:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 61852/100000 [18:36:36<6:12:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 61853/100000 [18:36:36<6:11:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61854/100000 [18:36:37<6:11:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 61855/100000 [18:36:37<6:12:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 61856/100000 [18:36:38<6:11:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 61857/100000 [18:36:39<6:12:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61858/100000 [18:36:39<6:11:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61859/100000 [18:36:40<6:11:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 61860/100000 [18:36:40<6:12:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 61861/100000 [18:36:41<6:12:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61862/100000 [18:36:41<6:12:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 61863/100000 [18:36:42<6:11:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61864/100000 [18:36:43<6:12:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 61865/100000 [18:36:43<6:12:52,  1.70it/s]
Train steps ... :  62%|██████▏   | 61866/100000 [18:36:44<6:12:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 61867/100000 [18:36:44<6:12:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 61868/100000 [18:36:45<6:12:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 61869/100000 [18:36:46<6:12:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61870/100000 [18:36:46<6:11:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61871/100000 [18:36:47<6:11:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 61872/100000 [18:36:47<6:11:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61873/100000 [18:36:48<6:12:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61874/100000 [18:36:48<6:11:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61875/100000 [18:36:49<6:11:56,  1.71it/s]Step... (61875 / 100000 | Loss: 0.9057223796844482, Learning Rate: 3.831658291457287e-05)
+
                                                                             
Step... (61875 / 100000 | Loss: 0.7962354421615601, Learning Rate: 3.831658291457287e-05)
+
Train steps ... :  62%|██████▏   | 61875/100000 [18:36:49<6:11:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 61876/100000 [18:36:50<6:12:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61877/100000 [18:36:50<6:11:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 61878/100000 [18:36:51<6:11:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 61879/100000 [18:36:51<6:12:41,  1.70it/s]
Train steps ... :  62%|██████▏   | 61880/100000 [18:36:52<6:11:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 61881/100000 [18:36:53<6:11:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61882/100000 [18:36:53<6:11:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61883/100000 [18:36:54<6:11:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 61884/100000 [18:36:54<6:11:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61885/100000 [18:36:55<6:11:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 61886/100000 [18:36:55<6:11:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 61887/100000 [18:36:56<6:11:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 61888/100000 [18:36:57<6:11:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 61889/100000 [18:36:57<6:11:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 61890/100000 [18:36:58<6:11:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 61891/100000 [18:36:58<6:11:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 61892/100000 [18:36:59<6:10:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 61893/100000 [18:37:00<6:11:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 61894/100000 [18:37:00<6:11:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61895/100000 [18:37:01<6:11:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 61896/100000 [18:37:01<6:12:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 61897/100000 [18:37:02<6:11:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 61898/100000 [18:37:03<6:12:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 61899/100000 [18:37:03<6:12:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 61900/100000 [18:37:04<6:12:18,  1.71it/s]Step... (61900 / 100000 | Loss: 0.878122091293335, Learning Rate: 3.829145728643217e-05)
+
                                                                             
Step... (61900 / 100000 | Loss: 0.7826052904129028, Learning Rate: 3.829145728643217e-05)
+
Train steps ... :  62%|██████▏   | 61900/100000 [18:37:04<6:12:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 61901/100000 [18:37:04<6:11:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 61902/100000 [18:37:05<6:12:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 61903/100000 [18:37:05<6:11:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61904/100000 [18:37:06<6:12:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 61905/100000 [18:37:07<6:12:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 61906/100000 [18:37:07<6:12:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 61907/100000 [18:37:08<6:11:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61908/100000 [18:37:08<6:12:26,  1.70it/s]
Train steps ... :  62%|██████▏   | 61909/100000 [18:37:09<6:11:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 61910/100000 [18:37:10<6:11:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 61911/100000 [18:37:10<6:11:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 61912/100000 [18:37:11<6:12:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 61913/100000 [18:37:11<6:12:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 61914/100000 [18:37:12<6:11:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 61915/100000 [18:37:12<6:11:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61916/100000 [18:37:13<6:11:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 61917/100000 [18:37:14<6:11:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61918/100000 [18:37:14<6:11:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61919/100000 [18:37:15<6:11:37,  1.71it/s]
Train steps ... :  62%|██████▏   | 61920/100000 [18:37:15<6:11:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61921/100000 [18:37:16<6:11:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 61922/100000 [18:37:17<6:11:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 61923/100000 [18:37:17<6:11:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 61924/100000 [18:37:18<6:11:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 61925/100000 [18:37:18<6:11:17,  1.71it/s]Step... (61925 / 100000 | Loss: 0.6940246820449829, Learning Rate: 3.8266331658291457e-05)
+
                                                                             
Step... (61925 / 100000 | Loss: 0.7306010723114014, Learning Rate: 3.8266331658291457e-05)
+
Train steps ... :  62%|██████▏   | 61925/100000 [18:37:19<6:11:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 61926/100000 [18:37:19<6:11:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 61927/100000 [18:37:19<6:11:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61928/100000 [18:37:20<6:11:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 61929/100000 [18:37:21<6:11:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 61930/100000 [18:37:21<6:11:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 61931/100000 [18:37:22<6:11:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61932/100000 [18:37:22<6:11:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61933/100000 [18:37:23<6:11:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 61934/100000 [18:37:24<6:11:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 61935/100000 [18:37:24<6:11:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61936/100000 [18:37:25<6:10:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61937/100000 [18:37:25<6:10:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 61938/100000 [18:37:26<6:10:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 61939/100000 [18:37:27<6:10:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61940/100000 [18:37:27<6:11:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 61941/100000 [18:37:28<6:10:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 61942/100000 [18:37:28<6:11:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61943/100000 [18:37:29<6:11:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 61944/100000 [18:37:29<6:10:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61945/100000 [18:37:30<6:10:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 61946/100000 [18:37:31<6:11:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61947/100000 [18:37:31<6:11:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61948/100000 [18:37:32<6:11:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 61949/100000 [18:37:32<6:10:58,  1.71it/s]
Train steps ... :  62%|██████▏   | 61950/100000 [18:37:33<6:10:43,  1.71it/s]Step... (61950 / 100000 | Loss: 0.700009822845459, Learning Rate: 3.824120603015075e-05)
+
                                                                             
Step... (61950 / 100000 | Loss: 0.7189621329307556, Learning Rate: 3.824120603015075e-05)
+
Train steps ... :  62%|██████▏   | 61950/100000 [18:37:33<6:10:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 61951/100000 [18:37:34<6:11:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 61952/100000 [18:37:34<6:11:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 61953/100000 [18:37:35<6:11:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 61954/100000 [18:37:35<6:11:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 61955/100000 [18:37:36<6:11:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 61956/100000 [18:37:36<6:10:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61957/100000 [18:37:37<6:10:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61958/100000 [18:37:38<6:10:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 61959/100000 [18:37:38<6:10:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 61960/100000 [18:37:39<6:10:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61961/100000 [18:37:39<6:11:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 61962/100000 [18:37:40<6:10:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61963/100000 [18:37:41<6:10:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 61964/100000 [18:37:41<6:10:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 61965/100000 [18:37:42<6:10:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 61966/100000 [18:37:42<6:10:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 61967/100000 [18:37:43<6:10:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 61968/100000 [18:37:43<6:10:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 61969/100000 [18:37:44<6:10:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61970/100000 [18:37:45<6:11:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 61971/100000 [18:37:45<6:10:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 61972/100000 [18:37:46<6:10:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 61973/100000 [18:37:46<6:10:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 61974/100000 [18:37:47<6:10:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 61975/100000 [18:37:48<6:10:54,  1.71it/s]Step... (61975 / 100000 | Loss: 0.7333328127861023, Learning Rate: 3.821608040201005e-05)
+
                                                                             
Step... (61975 / 100000 | Loss: 0.8390510082244873, Learning Rate: 3.821608040201005e-05)
+
Train steps ... :  62%|██████▏   | 61975/100000 [18:37:48<6:10:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 61976/100000 [18:37:48<6:10:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61977/100000 [18:37:49<6:10:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 61978/100000 [18:37:49<6:10:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 61979/100000 [18:37:50<6:11:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 61980/100000 [18:37:51<6:10:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 61981/100000 [18:37:51<6:10:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 61982/100000 [18:37:52<6:10:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61983/100000 [18:37:52<6:10:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 61984/100000 [18:37:53<6:10:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61985/100000 [18:37:53<6:10:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61986/100000 [18:37:54<6:10:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 61987/100000 [18:37:55<6:10:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 61988/100000 [18:37:55<6:10:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 61989/100000 [18:37:56<6:10:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 61990/100000 [18:37:56<6:10:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 61991/100000 [18:37:57<6:10:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 61992/100000 [18:37:58<6:10:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61993/100000 [18:37:58<6:10:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 61994/100000 [18:37:59<6:10:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 61995/100000 [18:37:59<6:10:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 61996/100000 [18:38:00<6:10:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 61997/100000 [18:38:00<6:10:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 61998/100000 [18:38:01<6:10:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 61999/100000 [18:38:02<6:10:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 62000/100000 [18:38:02<6:10:43,  1.71it/s]Step... (62000 / 100000 | Loss: 0.6638819575309753, Learning Rate: 3.8190954773869346e-05)
+
                                                                             
Step... (62000 / 100000 | Loss: 0.8061769604682922, Learning Rate: 3.8190954773869346e-05)
+
Train steps ... :  62%|██████▏   | 62000/100000 [18:38:03<6:10:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 62001/100000 [18:38:03<6:10:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62002/100000 [18:38:03<6:10:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 62003/100000 [18:38:04<6:10:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 62004/100000 [18:38:05<6:10:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 62005/100000 [18:38:05<6:10:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 62006/100000 [18:38:06<6:09:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 62007/100000 [18:38:06<6:10:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62008/100000 [18:38:07<6:10:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 62009/100000 [18:38:07<6:10:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 62010/100000 [18:38:08<6:10:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 62011/100000 [18:38:09<6:09:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 62012/100000 [18:38:09<6:10:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 62013/100000 [18:38:10<6:10:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 62014/100000 [18:38:10<6:09:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 62015/100000 [18:38:11<6:10:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 62016/100000 [18:38:12<6:10:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62017/100000 [18:38:12<6:10:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 62018/100000 [18:38:13<6:11:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 62019/100000 [18:38:13<6:10:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 62020/100000 [18:38:14<6:10:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62021/100000 [18:38:14<6:10:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 62022/100000 [18:38:15<6:09:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62023/100000 [18:38:16<6:10:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 62024/100000 [18:38:16<6:10:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 62025/100000 [18:38:17<6:10:12,  1.71it/s]Step... (62025 / 100000 | Loss: 0.718839168548584, Learning Rate: 3.816582914572864e-05)
+
                                                                             
Step... (62025 / 100000 | Loss: 0.8113996982574463, Learning Rate: 3.816582914572864e-05)
+
Train steps ... :  62%|██████▏   | 62025/100000 [18:38:17<6:10:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 62026/100000 [18:38:17<6:10:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 62027/100000 [18:38:18<6:09:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62028/100000 [18:38:19<6:09:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 62029/100000 [18:38:19<6:09:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 62030/100000 [18:38:20<6:09:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 62031/100000 [18:38:20<6:09:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 62032/100000 [18:38:21<6:09:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 62033/100000 [18:38:21<6:10:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 62034/100000 [18:38:22<6:09:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62035/100000 [18:38:23<6:09:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62036/100000 [18:38:23<6:09:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62037/100000 [18:38:24<6:09:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62038/100000 [18:38:24<6:09:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 62039/100000 [18:38:25<6:09:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 62040/100000 [18:38:26<6:09:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 62041/100000 [18:38:26<6:09:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 62042/100000 [18:38:27<6:09:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62043/100000 [18:38:27<6:10:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 62044/100000 [18:38:28<6:10:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 62045/100000 [18:38:29<6:10:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 62046/100000 [18:38:29<6:10:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62047/100000 [18:38:30<6:10:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 62048/100000 [18:38:30<6:09:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62049/100000 [18:38:31<6:10:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 62050/100000 [18:38:31<6:09:58,  1.71it/s]Step... (62050 / 100000 | Loss: 1.0878031253814697, Learning Rate: 3.814070351758794e-05)
+
                                                                             
Step... (62050 / 100000 | Loss: 0.6123453974723816, Learning Rate: 3.814070351758794e-05)
+
Train steps ... :  62%|██████▏   | 62050/100000 [18:38:32<6:09:58,  1.71it/s]
Train steps ... :  62%|██████▏   | 62051/100000 [18:38:32<6:10:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 62052/100000 [18:38:33<6:09:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 62053/100000 [18:38:33<6:10:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 62054/100000 [18:38:34<6:09:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 62055/100000 [18:38:34<6:09:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 62056/100000 [18:38:35<6:09:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 62057/100000 [18:38:36<6:09:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62058/100000 [18:38:36<6:09:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 62059/100000 [18:38:37<6:10:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 62060/100000 [18:38:37<6:09:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 62061/100000 [18:38:38<6:10:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 62062/100000 [18:38:38<6:09:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 62063/100000 [18:38:39<6:09:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 62064/100000 [18:38:40<6:09:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 62065/100000 [18:38:40<6:09:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62066/100000 [18:38:41<6:09:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62067/100000 [18:38:41<6:09:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 62068/100000 [18:38:42<6:09:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62069/100000 [18:38:43<6:10:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 62070/100000 [18:38:43<6:09:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 62071/100000 [18:38:44<6:09:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 62072/100000 [18:38:44<6:09:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 62073/100000 [18:38:45<6:09:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 62074/100000 [18:38:45<6:10:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 62075/100000 [18:38:46<6:10:13,  1.71it/s]Step... (62075 / 100000 | Loss: 1.0096226930618286, Learning Rate: 3.811557788944724e-05)
+
                                                                             
Step... (62075 / 100000 | Loss: 0.763506293296814, Learning Rate: 3.811557788944724e-05)
+
Train steps ... :  62%|██████▏   | 62075/100000 [18:38:46<6:10:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 62076/100000 [18:38:47<6:10:49,  1.70it/s]
Train steps ... :  62%|██████▏   | 62077/100000 [18:38:47<6:11:29,  1.70it/s]
Train steps ... :  62%|██████▏   | 62078/100000 [18:38:48<6:10:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 62079/100000 [18:38:48<6:09:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 62080/100000 [18:38:49<6:10:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 62081/100000 [18:38:50<6:09:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 62082/100000 [18:38:50<6:09:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62083/100000 [18:38:51<6:09:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 62084/100000 [18:38:51<6:09:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 62085/100000 [18:38:52<6:09:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 62086/100000 [18:38:53<6:09:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 62087/100000 [18:38:53<6:09:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 62088/100000 [18:38:54<6:09:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62089/100000 [18:38:54<6:08:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 62090/100000 [18:38:55<6:08:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62091/100000 [18:38:55<6:09:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62092/100000 [18:38:56<6:09:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 62093/100000 [18:38:57<6:09:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 62094/100000 [18:38:57<6:09:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 62095/100000 [18:38:58<6:09:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 62096/100000 [18:38:58<6:09:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 62097/100000 [18:38:59<6:10:34,  1.70it/s]
Train steps ... :  62%|██████▏   | 62098/100000 [18:39:00<6:10:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62099/100000 [18:39:00<6:10:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 62100/100000 [18:39:01<6:09:52,  1.71it/s]Step... (62100 / 100000 | Loss: 0.981731653213501, Learning Rate: 3.809045226130653e-05)
+
                                                                             
Step... (62100 / 100000 | Loss: 0.5597721338272095, Learning Rate: 3.809045226130653e-05)
+
Train steps ... :  62%|██████▏   | 62100/100000 [18:39:01<6:09:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 62101/100000 [18:39:01<6:09:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 62102/100000 [18:39:02<6:09:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 62103/100000 [18:39:02<6:09:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62104/100000 [18:39:03<6:09:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62105/100000 [18:39:04<6:09:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 62106/100000 [18:39:04<6:09:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 62107/100000 [18:39:05<6:09:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 62108/100000 [18:39:05<6:09:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 62109/100000 [18:39:06<6:09:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 62110/100000 [18:39:07<6:09:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 62111/100000 [18:39:07<6:08:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 62112/100000 [18:39:08<6:08:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 62113/100000 [18:39:08<6:08:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 62114/100000 [18:39:09<6:09:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62115/100000 [18:39:09<6:08:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 62116/100000 [18:39:10<6:08:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 62117/100000 [18:39:11<6:08:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 62118/100000 [18:39:11<6:09:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 62119/100000 [18:39:12<6:09:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 62120/100000 [18:39:12<6:08:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 62121/100000 [18:39:13<6:08:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62122/100000 [18:39:14<6:08:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62123/100000 [18:39:14<6:08:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62124/100000 [18:39:15<6:09:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 62125/100000 [18:39:15<6:09:18,  1.71it/s]Step... (62125 / 100000 | Loss: 0.6945229768753052, Learning Rate: 3.806532663316583e-05)
+
                                                                             
Step... (62125 / 100000 | Loss: 0.6680824160575867, Learning Rate: 3.806532663316583e-05)
+
Train steps ... :  62%|██████▏   | 62125/100000 [18:39:16<6:09:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 62126/100000 [18:39:16<6:09:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 62127/100000 [18:39:16<6:09:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 62128/100000 [18:39:17<6:09:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62129/100000 [18:39:18<6:09:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 62130/100000 [18:39:18<6:09:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62131/100000 [18:39:19<6:09:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62132/100000 [18:39:19<6:09:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 62133/100000 [18:39:20<6:09:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 62134/100000 [18:39:21<6:09:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 62135/100000 [18:39:21<6:09:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62136/100000 [18:39:22<6:09:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 62137/100000 [18:39:22<6:08:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 62138/100000 [18:39:23<6:08:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62139/100000 [18:39:23<6:08:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62140/100000 [18:39:24<6:09:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 62141/100000 [18:39:25<6:09:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 62142/100000 [18:39:25<6:09:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62143/100000 [18:39:26<6:08:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 62144/100000 [18:39:26<6:08:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 62145/100000 [18:39:27<6:09:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 62146/100000 [18:39:28<6:08:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 62147/100000 [18:39:28<6:08:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 62148/100000 [18:39:29<6:08:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 62149/100000 [18:39:29<6:08:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 62150/100000 [18:39:30<6:08:19,  1.71it/s]Step... (62150 / 100000 | Loss: 0.5937192440032959, Learning Rate: 3.8040201005025126e-05)
+
                                                                             
Step... (62150 / 100000 | Loss: 0.8647724390029907, Learning Rate: 3.8040201005025126e-05)
+
Train steps ... :  62%|██████▏   | 62150/100000 [18:39:30<6:08:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 62151/100000 [18:39:31<6:08:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 62152/100000 [18:39:31<6:08:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62153/100000 [18:39:32<6:09:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 62154/100000 [18:39:32<6:08:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 62155/100000 [18:39:33<6:08:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 62156/100000 [18:39:33<6:08:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62157/100000 [18:39:34<6:08:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 62158/100000 [18:39:35<6:08:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 62159/100000 [18:39:35<6:08:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62160/100000 [18:39:36<6:08:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62161/100000 [18:39:36<6:08:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 62162/100000 [18:39:37<6:08:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 62163/100000 [18:39:38<6:08:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 62164/100000 [18:39:38<6:08:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 62165/100000 [18:39:39<6:09:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 62166/100000 [18:39:39<6:08:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 62167/100000 [18:39:40<6:08:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 62168/100000 [18:39:40<6:08:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62169/100000 [18:39:41<6:08:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 62170/100000 [18:39:42<6:08:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 62171/100000 [18:39:42<6:08:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 62172/100000 [18:39:43<6:08:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 62173/100000 [18:39:43<6:08:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 62174/100000 [18:39:44<6:08:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62175/100000 [18:39:45<6:08:27,  1.71it/s]Step... (62175 / 100000 | Loss: 0.6596256494522095, Learning Rate: 3.801507537688442e-05)
+
                                                                             
Step... (62175 / 100000 | Loss: 0.735100269317627, Learning Rate: 3.801507537688442e-05)
+
Train steps ... :  62%|██████▏   | 62175/100000 [18:39:45<6:08:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 62176/100000 [18:39:45<6:08:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62177/100000 [18:39:46<6:08:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 62178/100000 [18:39:46<6:08:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 62179/100000 [18:39:47<6:08:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 62180/100000 [18:39:47<6:08:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 62181/100000 [18:39:48<6:07:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 62182/100000 [18:39:49<6:08:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 62183/100000 [18:39:49<6:08:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 62184/100000 [18:39:50<6:08:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 62185/100000 [18:39:50<6:08:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62186/100000 [18:39:51<6:08:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62187/100000 [18:39:52<6:08:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62188/100000 [18:39:52<6:08:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 62189/100000 [18:39:53<6:08:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 62190/100000 [18:39:53<6:08:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62191/100000 [18:39:54<6:08:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 62192/100000 [18:39:54<6:08:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62193/100000 [18:39:55<6:08:26,  1.71it/s]
Train steps ... :  62%|██████▏   | 62194/100000 [18:39:56<6:08:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 62195/100000 [18:39:56<6:08:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 62196/100000 [18:39:57<6:08:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 62197/100000 [18:39:57<6:08:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 62198/100000 [18:39:58<6:08:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 62199/100000 [18:39:59<6:08:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 62200/100000 [18:39:59<6:08:07,  1.71it/s]Step... (62200 / 100000 | Loss: 0.6918402910232544, Learning Rate: 3.798994974874372e-05)
+
                                                                             
Step... (62200 / 100000 | Loss: 0.6532549858093262, Learning Rate: 3.798994974874372e-05)
+
Train steps ... :  62%|██████▏   | 62200/100000 [18:39:59<6:08:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 62201/100000 [18:40:00<6:08:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 62202/100000 [18:40:00<6:08:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 62203/100000 [18:40:01<6:08:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62204/100000 [18:40:01<6:08:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 62205/100000 [18:40:02<6:08:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62206/100000 [18:40:03<6:08:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 62207/100000 [18:40:03<6:08:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62208/100000 [18:40:04<6:08:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62209/100000 [18:40:04<6:08:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 62210/100000 [18:40:05<6:08:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 62211/100000 [18:40:06<6:07:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62212/100000 [18:40:06<6:07:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 62213/100000 [18:40:07<6:07:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 62214/100000 [18:40:07<6:07:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62215/100000 [18:40:08<6:08:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 62216/100000 [18:40:09<6:08:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 62217/100000 [18:40:09<6:08:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 62218/100000 [18:40:10<6:08:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 62219/100000 [18:40:10<6:08:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 62220/100000 [18:40:11<6:08:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 62221/100000 [18:40:11<6:08:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62222/100000 [18:40:12<6:08:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62223/100000 [18:40:13<6:08:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 62224/100000 [18:40:13<6:07:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 62225/100000 [18:40:14<6:07:37,  1.71it/s]Step... (62225 / 100000 | Loss: 0.7265968322753906, Learning Rate: 3.7964824120603016e-05)
+
                                                                             
Step... (62225 / 100000 | Loss: 0.7925437688827515, Learning Rate: 3.7964824120603016e-05)
+
Train steps ... :  62%|██████▏   | 62225/100000 [18:40:14<6:07:37,  1.71it/s]
Train steps ... :  62%|██████▏   | 62226/100000 [18:40:14<6:08:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 62227/100000 [18:40:15<6:08:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 62228/100000 [18:40:16<6:08:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 62229/100000 [18:40:16<6:08:15,  1.71it/s]
Train steps ... :  62%|██████▏   | 62230/100000 [18:40:17<6:08:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62231/100000 [18:40:17<6:08:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 62232/100000 [18:40:18<6:08:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 62233/100000 [18:40:18<6:07:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62234/100000 [18:40:19<6:08:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62235/100000 [18:40:20<6:08:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 62236/100000 [18:40:20<6:07:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 62237/100000 [18:40:21<6:08:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 62238/100000 [18:40:21<6:07:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 62239/100000 [18:40:22<6:08:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62240/100000 [18:40:23<6:07:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 62241/100000 [18:40:23<6:07:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62242/100000 [18:40:24<6:07:58,  1.71it/s]
Train steps ... :  62%|██████▏   | 62243/100000 [18:40:24<6:08:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 62244/100000 [18:40:25<6:08:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 62245/100000 [18:40:25<6:07:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 62246/100000 [18:40:26<6:08:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 62247/100000 [18:40:27<6:07:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 62248/100000 [18:40:27<6:07:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62249/100000 [18:40:28<6:07:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 62250/100000 [18:40:28<6:07:18,  1.71it/s]Step... (62250 / 100000 | Loss: 0.8845995664596558, Learning Rate: 3.793969849246231e-05)
+
                                                                             
Step... (62250 / 100000 | Loss: 0.6618866324424744, Learning Rate: 3.793969849246231e-05)
+
Train steps ... :  62%|██████▏   | 62250/100000 [18:40:29<6:07:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 62251/100000 [18:40:29<6:07:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62252/100000 [18:40:30<6:08:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 62253/100000 [18:40:30<6:07:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62254/100000 [18:40:31<6:07:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62255/100000 [18:40:31<6:07:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62256/100000 [18:40:32<6:07:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 62257/100000 [18:40:32<6:07:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 62258/100000 [18:40:33<6:07:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 62259/100000 [18:40:34<6:07:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62260/100000 [18:40:34<6:07:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62261/100000 [18:40:35<6:07:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62262/100000 [18:40:35<6:07:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 62263/100000 [18:40:36<6:07:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 62264/100000 [18:40:37<6:07:37,  1.71it/s]
Train steps ... :  62%|██████▏   | 62265/100000 [18:40:37<6:07:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 62266/100000 [18:40:38<6:07:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62267/100000 [18:40:38<6:08:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 62268/100000 [18:40:39<6:07:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62269/100000 [18:40:39<6:07:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 62270/100000 [18:40:40<6:07:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 62271/100000 [18:40:41<6:07:58,  1.71it/s]
Train steps ... :  62%|██████▏   | 62272/100000 [18:40:41<6:07:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 62273/100000 [18:40:42<6:08:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 62274/100000 [18:40:42<6:07:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62275/100000 [18:40:43<6:07:30,  1.71it/s]Step... (62275 / 100000 | Loss: 0.5654584169387817, Learning Rate: 3.791457286432161e-05)
+
                                                                             
Step... (62275 / 100000 | Loss: 0.7490348815917969, Learning Rate: 3.791457286432161e-05)
+
Train steps ... :  62%|██████▏   | 62275/100000 [18:40:43<6:07:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 62276/100000 [18:40:44<6:07:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62277/100000 [18:40:44<6:07:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 62278/100000 [18:40:45<6:08:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 62279/100000 [18:40:45<6:07:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62280/100000 [18:40:46<6:08:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62281/100000 [18:40:47<6:07:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 62282/100000 [18:40:47<6:07:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 62283/100000 [18:40:48<6:07:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 62284/100000 [18:40:48<6:07:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 62285/100000 [18:40:49<6:07:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 62286/100000 [18:40:49<6:07:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 62287/100000 [18:40:50<6:07:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 62288/100000 [18:40:51<6:06:58,  1.71it/s]
Train steps ... :  62%|██████▏   | 62289/100000 [18:40:51<6:07:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62290/100000 [18:40:52<6:07:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 62291/100000 [18:40:52<6:07:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 62292/100000 [18:40:53<6:06:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 62293/100000 [18:40:54<6:07:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 62294/100000 [18:40:54<6:07:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 62295/100000 [18:40:55<6:07:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 62296/100000 [18:40:55<6:07:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 62297/100000 [18:40:56<6:07:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 62298/100000 [18:40:56<6:07:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62299/100000 [18:40:57<6:07:59,  1.71it/s]
Train steps ... :  62%|██████▏   | 62300/100000 [18:40:58<6:07:36,  1.71it/s]Step... (62300 / 100000 | Loss: 0.6524479389190674, Learning Rate: 3.7889447236180906e-05)
+
                                                                             
Step... (62300 / 100000 | Loss: 0.802565336227417, Learning Rate: 3.7889447236180906e-05)
+
Train steps ... :  62%|██████▏   | 62300/100000 [18:40:58<6:07:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62301/100000 [18:40:58<6:07:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62302/100000 [18:40:59<6:07:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 62303/100000 [18:40:59<6:07:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62304/100000 [18:41:00<6:07:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 62305/100000 [18:41:01<6:07:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62306/100000 [18:41:01<6:07:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 62307/100000 [18:41:02<6:07:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62308/100000 [18:41:02<6:07:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 62309/100000 [18:41:03<6:06:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62310/100000 [18:41:03<6:07:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 62311/100000 [18:41:04<6:07:40,  1.71it/s]
Train steps ... :  62%|██████▏   | 62312/100000 [18:41:05<6:07:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 62313/100000 [18:41:05<6:07:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 62314/100000 [18:41:06<6:07:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62315/100000 [18:41:06<6:06:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 62316/100000 [18:41:07<6:07:41,  1.71it/s]
Train steps ... :  62%|██████▏   | 62317/100000 [18:41:08<6:07:27,  1.71it/s]
Train steps ... :  62%|██████▏   | 62318/100000 [18:41:08<6:07:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 62319/100000 [18:41:09<6:07:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 62320/100000 [18:41:09<6:07:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 62321/100000 [18:41:10<6:07:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 62322/100000 [18:41:10<6:07:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 62323/100000 [18:41:11<6:07:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 62324/100000 [18:41:12<6:07:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 62325/100000 [18:41:12<6:07:51,  1.71it/s]Step... (62325 / 100000 | Loss: 0.601864218711853, Learning Rate: 3.78643216080402e-05)
+
                                                                             
Step... (62325 / 100000 | Loss: 1.1701934337615967, Learning Rate: 3.78643216080402e-05)
+
Train steps ... :  62%|██████▏   | 62325/100000 [18:41:13<6:07:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 62326/100000 [18:41:13<6:07:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62327/100000 [18:41:13<6:07:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 62328/100000 [18:41:14<6:07:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 62329/100000 [18:41:15<6:07:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 62330/100000 [18:41:15<6:07:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 62331/100000 [18:41:16<6:07:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62332/100000 [18:41:16<6:07:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62333/100000 [18:41:17<6:07:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62334/100000 [18:41:18<6:07:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 62335/100000 [18:41:18<6:06:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 62336/100000 [18:41:19<6:06:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62337/100000 [18:41:19<6:06:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 62338/100000 [18:41:20<6:06:37,  1.71it/s]
Train steps ... :  62%|██████▏   | 62339/100000 [18:41:20<6:06:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62340/100000 [18:41:21<6:06:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62341/100000 [18:41:22<6:06:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 62342/100000 [18:41:22<6:06:18,  1.71it/s]
Train steps ... :  62%|██████▏   | 62343/100000 [18:41:23<6:06:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 62344/100000 [18:41:23<6:06:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 62345/100000 [18:41:24<6:06:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 62346/100000 [18:41:25<6:06:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 62347/100000 [18:41:25<6:07:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 62348/100000 [18:41:26<6:07:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62349/100000 [18:41:26<6:07:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 62350/100000 [18:41:27<6:07:07,  1.71it/s]Step... (62350 / 100000 | Loss: 1.095431923866272, Learning Rate: 3.78391959798995e-05)
+
                                                                             
Step... (62350 / 100000 | Loss: 0.6184946298599243, Learning Rate: 3.78391959798995e-05)
+
Train steps ... :  62%|██████▏   | 62350/100000 [18:41:27<6:07:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 62351/100000 [18:41:27<6:07:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 62352/100000 [18:41:28<6:08:03,  1.70it/s]
Train steps ... :  62%|██████▏   | 62353/100000 [18:41:29<6:07:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62354/100000 [18:41:29<6:07:22,  1.71it/s]
Train steps ... :  62%|██████▏   | 62355/100000 [18:41:30<6:07:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 62356/100000 [18:41:30<6:07:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 62357/100000 [18:41:31<6:07:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 62358/100000 [18:41:32<6:06:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62359/100000 [18:41:32<6:06:37,  1.71it/s]
Train steps ... :  62%|██████▏   | 62360/100000 [18:41:33<6:06:51,  1.71it/s]
Train steps ... :  62%|██████▏   | 62361/100000 [18:41:33<6:06:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62362/100000 [18:41:34<6:06:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 62363/100000 [18:41:34<6:06:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62364/100000 [18:41:35<6:06:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 62365/100000 [18:41:36<6:06:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62366/100000 [18:41:36<6:07:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62367/100000 [18:41:37<6:06:57,  1.71it/s]
Train steps ... :  62%|██████▏   | 62368/100000 [18:41:37<6:07:50,  1.71it/s]
Train steps ... :  62%|██████▏   | 62369/100000 [18:41:38<6:06:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 62370/100000 [18:41:39<6:06:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 62371/100000 [18:41:39<6:06:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 62372/100000 [18:41:40<6:06:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 62373/100000 [18:41:40<6:06:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62374/100000 [18:41:41<6:06:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 62375/100000 [18:41:41<6:06:33,  1.71it/s]Step... (62375 / 100000 | Loss: 0.5535345673561096, Learning Rate: 3.7814070351758796e-05)
+
                                                                             
Step... (62375 / 100000 | Loss: 0.968651533126831, Learning Rate: 3.7814070351758796e-05)
+
Train steps ... :  62%|██████▏   | 62375/100000 [18:41:42<6:06:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62376/100000 [18:41:42<6:07:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 62377/100000 [18:41:43<6:07:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 62378/100000 [18:41:43<6:07:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 62379/100000 [18:41:44<6:06:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62380/100000 [18:41:44<6:06:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 62381/100000 [18:41:45<6:06:53,  1.71it/s]
Train steps ... :  62%|██████▏   | 62382/100000 [18:41:46<6:06:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 62383/100000 [18:41:46<6:06:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62384/100000 [18:41:47<6:06:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62385/100000 [18:41:47<6:06:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62386/100000 [18:41:48<6:06:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 62387/100000 [18:41:49<6:06:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 62388/100000 [18:41:49<6:06:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62389/100000 [18:41:50<6:06:42,  1.71it/s]
Train steps ... :  62%|██████▏   | 62390/100000 [18:41:50<6:06:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 62391/100000 [18:41:51<6:07:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 62392/100000 [18:41:51<6:07:40,  1.70it/s]
Train steps ... :  62%|██████▏   | 62393/100000 [18:41:52<6:07:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62394/100000 [18:41:53<6:07:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 62395/100000 [18:41:53<6:06:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 62396/100000 [18:41:54<6:06:36,  1.71it/s]
Train steps ... :  62%|██████▏   | 62397/100000 [18:41:54<6:06:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 62398/100000 [18:41:55<6:06:31,  1.71it/s]
Train steps ... :  62%|██████▏   | 62399/100000 [18:41:56<6:06:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 62400/100000 [18:41:56<6:06:30,  1.71it/s]Step... (62400 / 100000 | Loss: 0.7032040357589722, Learning Rate: 3.778894472361809e-05)
+
                                                                             
Step... (62400 / 100000 | Loss: 0.9243499040603638, Learning Rate: 3.778894472361809e-05)
+
Train steps ... :  62%|██████▏   | 62400/100000 [18:41:56<6:06:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 62401/100000 [18:41:57<6:06:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 62402/100000 [18:41:57<6:06:09,  1.71it/s]
Train steps ... :  62%|██████▏   | 62403/100000 [18:41:58<6:06:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 62404/100000 [18:41:58<6:06:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 62405/100000 [18:41:59<6:06:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 62406/100000 [18:42:00<6:06:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 62407/100000 [18:42:00<6:07:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 62408/100000 [18:42:01<6:06:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 62409/100000 [18:42:01<6:06:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 62410/100000 [18:42:02<6:06:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 62411/100000 [18:42:03<6:05:54,  1.71it/s]
Train steps ... :  62%|██████▏   | 62412/100000 [18:42:03<6:06:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 62413/100000 [18:42:04<6:06:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 62414/100000 [18:42:04<6:06:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 62415/100000 [18:42:05<6:06:07,  1.71it/s]
Train steps ... :  62%|██████▏   | 62416/100000 [18:42:05<6:06:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 62417/100000 [18:42:06<6:05:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62418/100000 [18:42:07<6:06:24,  1.71it/s]
Train steps ... :  62%|██████▏   | 62419/100000 [18:42:07<6:06:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62420/100000 [18:42:08<6:06:17,  1.71it/s]
Train steps ... :  62%|██████▏   | 62421/100000 [18:42:08<6:06:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62422/100000 [18:42:09<6:06:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 62423/100000 [18:42:10<6:06:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 62424/100000 [18:42:10<6:06:13,  1.71it/s]
Train steps ... :  62%|██████▏   | 62425/100000 [18:42:11<6:06:04,  1.71it/s]Step... (62425 / 100000 | Loss: 0.7477860450744629, Learning Rate: 3.776381909547739e-05)
+
                                                                             
Step... (62425 / 100000 | Loss: 0.8617174625396729, Learning Rate: 3.776381909547739e-05)
+
Train steps ... :  62%|██████▏   | 62425/100000 [18:42:11<6:06:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 62426/100000 [18:42:11<6:06:16,  1.71it/s]
Train steps ... :  62%|██████▏   | 62427/100000 [18:42:12<6:06:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 62428/100000 [18:42:12<6:07:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 62429/100000 [18:42:13<6:05:58,  1.71it/s]
Train steps ... :  62%|██████▏   | 62430/100000 [18:42:14<6:05:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 62431/100000 [18:42:14<6:05:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 62432/100000 [18:42:15<6:06:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62433/100000 [18:42:15<6:05:58,  1.71it/s]
Train steps ... :  62%|██████▏   | 62434/100000 [18:42:16<6:06:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62435/100000 [18:42:17<6:07:00,  1.71it/s]
Train steps ... :  62%|██████▏   | 62436/100000 [18:42:17<6:06:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 62437/100000 [18:42:18<6:06:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62438/100000 [18:42:18<6:06:21,  1.71it/s]
Train steps ... :  62%|██████▏   | 62439/100000 [18:42:19<6:06:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62440/100000 [18:42:20<6:06:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62441/100000 [18:42:20<6:06:38,  1.71it/s]
Train steps ... :  62%|██████▏   | 62442/100000 [18:42:21<6:06:30,  1.71it/s]
Train steps ... :  62%|██████▏   | 62443/100000 [18:42:21<6:06:04,  1.71it/s]
Train steps ... :  62%|██████▏   | 62444/100000 [18:42:22<6:05:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 62445/100000 [18:42:22<6:06:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 62446/100000 [18:42:23<6:06:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 62447/100000 [18:42:24<6:06:14,  1.71it/s]
Train steps ... :  62%|██████▏   | 62448/100000 [18:42:24<6:06:06,  1.71it/s]
Train steps ... :  62%|██████▏   | 62449/100000 [18:42:25<6:06:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62450/100000 [18:42:25<6:05:48,  1.71it/s]Step... (62450 / 100000 | Loss: 0.7755798697471619, Learning Rate: 3.7738693467336686e-05)
+
                                                                             
Step... (62450 / 100000 | Loss: 0.8293005228042603, Learning Rate: 3.7738693467336686e-05)
+
Train steps ... :  62%|██████▏   | 62450/100000 [18:42:26<6:05:48,  1.71it/s]
Train steps ... :  62%|██████▏   | 62451/100000 [18:42:26<6:06:05,  1.71it/s]
Train steps ... :  62%|██████▏   | 62452/100000 [18:42:27<6:06:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 62453/100000 [18:42:27<6:06:10,  1.71it/s]
Train steps ... :  62%|██████▏   | 62454/100000 [18:42:28<6:05:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62455/100000 [18:42:28<6:05:46,  1.71it/s]
Train steps ... :  62%|██████▏   | 62456/100000 [18:42:29<6:05:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 62457/100000 [18:42:29<6:05:43,  1.71it/s]
Train steps ... :  62%|██████▏   | 62458/100000 [18:42:30<6:05:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62459/100000 [18:42:31<6:06:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62460/100000 [18:42:31<6:05:32,  1.71it/s]
Train steps ... :  62%|██████▏   | 62461/100000 [18:42:32<6:05:20,  1.71it/s]
Train steps ... :  62%|██████▏   | 62462/100000 [18:42:32<6:05:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 62463/100000 [18:42:33<6:05:35,  1.71it/s]
Train steps ... :  62%|██████▏   | 62464/100000 [18:42:34<6:05:52,  1.71it/s]
Train steps ... :  62%|██████▏   | 62465/100000 [18:42:34<6:05:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62466/100000 [18:42:35<6:06:25,  1.71it/s]
Train steps ... :  62%|██████▏   | 62467/100000 [18:42:35<6:06:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 62468/100000 [18:42:36<6:05:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 62469/100000 [18:42:36<6:05:45,  1.71it/s]
Train steps ... :  62%|██████▏   | 62470/100000 [18:42:37<6:05:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 62471/100000 [18:42:38<6:05:56,  1.71it/s]
Train steps ... :  62%|██████▏   | 62472/100000 [18:42:38<6:06:23,  1.71it/s]
Train steps ... :  62%|██████▏   | 62473/100000 [18:42:39<6:07:31,  1.70it/s]
Train steps ... :  62%|██████▏   | 62474/100000 [18:42:39<6:07:16,  1.70it/s]
Train steps ... :  62%|██████▏   | 62475/100000 [18:42:40<6:06:33,  1.71it/s]Step... (62475 / 100000 | Loss: 0.7467210292816162, Learning Rate: 3.771356783919598e-05)
+
                                                                             
Step... (62475 / 100000 | Loss: 0.9162946939468384, Learning Rate: 3.771356783919598e-05)
+
Train steps ... :  62%|██████▏   | 62475/100000 [18:42:40<6:06:33,  1.71it/s]
Train steps ... :  62%|██████▏   | 62476/100000 [18:42:41<6:06:51,  1.70it/s]
Train steps ... :  62%|██████▏   | 62477/100000 [18:42:41<6:06:08,  1.71it/s]
Train steps ... :  62%|██████▏   | 62478/100000 [18:42:42<6:06:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 62479/100000 [18:42:42<6:06:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62480/100000 [18:42:43<6:06:12,  1.71it/s]
Train steps ... :  62%|██████▏   | 62481/100000 [18:42:44<6:05:55,  1.71it/s]
Train steps ... :  62%|██████▏   | 62482/100000 [18:42:44<6:06:02,  1.71it/s]
Train steps ... :  62%|██████▏   | 62483/100000 [18:42:45<6:05:39,  1.71it/s]
Train steps ... :  62%|██████▏   | 62484/100000 [18:42:45<6:05:28,  1.71it/s]
Train steps ... :  62%|██████▏   | 62485/100000 [18:42:46<6:05:34,  1.71it/s]
Train steps ... :  62%|██████▏   | 62486/100000 [18:42:46<6:05:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62487/100000 [18:42:47<6:05:47,  1.71it/s]
Train steps ... :  62%|██████▏   | 62488/100000 [18:42:48<6:06:43,  1.70it/s]
Train steps ... :  62%|██████▏   | 62489/100000 [18:42:48<6:06:19,  1.71it/s]
Train steps ... :  62%|██████▏   | 62490/100000 [18:42:49<6:07:18,  1.70it/s]
Train steps ... :  62%|██████▏   | 62491/100000 [18:42:49<6:06:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62492/100000 [18:42:50<6:06:01,  1.71it/s]
Train steps ... :  62%|██████▏   | 62493/100000 [18:42:51<6:05:49,  1.71it/s]
Train steps ... :  62%|██████▏   | 62494/100000 [18:42:51<6:05:44,  1.71it/s]
Train steps ... :  62%|██████▏   | 62495/100000 [18:42:52<6:05:29,  1.71it/s]
Train steps ... :  62%|██████▏   | 62496/100000 [18:42:52<6:05:11,  1.71it/s]
Train steps ... :  62%|██████▏   | 62497/100000 [18:42:53<6:05:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 62498/100000 [18:42:53<6:05:03,  1.71it/s]
Train steps ... :  62%|██████▏   | 62499/100000 [18:42:54<6:04:59,  1.71it/s]
Train steps ... :  62%|██████▎   | 62500/100000 [18:42:55<6:05:04,  1.71it/s]Step... (62500 / 100000 | Loss: 0.7062145471572876, Learning Rate: 3.768844221105528e-05)
+
                                                                             
Step... (62500 / 100000 | Loss: 0.7838563919067383, Learning Rate: 3.768844221105528e-05)
+
Train steps ... :  62%|██████▎   | 62500/100000 [18:42:55<6:05:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 62501/100000 [18:42:55<6:05:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 62502/100000 [18:42:56<6:05:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 62503/100000 [18:42:56<6:05:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 62504/100000 [18:42:57<6:05:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 62505/100000 [18:42:58<6:05:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 62506/100000 [18:42:58<6:05:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 62507/100000 [18:42:59<6:05:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 62508/100000 [18:42:59<6:05:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 62509/100000 [18:43:00<6:05:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 62510/100000 [18:43:00<6:05:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62511/100000 [18:43:01<6:05:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62512/100000 [18:43:02<6:05:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 62513/100000 [18:43:02<6:05:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 62514/100000 [18:43:03<6:05:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62515/100000 [18:43:03<6:05:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 62516/100000 [18:43:04<6:04:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 62517/100000 [18:43:05<6:05:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62518/100000 [18:43:05<6:05:07,  1.71it/s]
Train steps ... :  63%|██████▎   | 62519/100000 [18:43:06<6:05:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62520/100000 [18:43:06<6:05:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 62521/100000 [18:43:07<6:05:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62522/100000 [18:43:07<6:04:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 62523/100000 [18:43:08<6:04:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 62524/100000 [18:43:09<6:04:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 62525/100000 [18:43:09<6:04:49,  1.71it/s]Step... (62525 / 100000 | Loss: 0.5668087005615234, Learning Rate: 3.7663316582914575e-05)
+
                                                                             
Step... (62525 / 100000 | Loss: 0.6276386976242065, Learning Rate: 3.7663316582914575e-05)
+
Train steps ... :  63%|██████▎   | 62525/100000 [18:43:10<6:04:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 62526/100000 [18:43:10<6:04:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 62527/100000 [18:43:10<6:04:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 62528/100000 [18:43:11<6:04:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62529/100000 [18:43:12<6:04:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 62530/100000 [18:43:12<6:05:22,  1.71it/s]
Train steps ... :  63%|██████▎   | 62531/100000 [18:43:13<6:05:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 62532/100000 [18:43:13<6:05:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 62533/100000 [18:43:14<6:05:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 62534/100000 [18:43:14<6:04:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 62535/100000 [18:43:15<6:05:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 62536/100000 [18:43:16<6:05:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 62537/100000 [18:43:16<6:05:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 62538/100000 [18:43:17<6:05:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 62539/100000 [18:43:17<6:05:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 62540/100000 [18:43:18<6:05:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 62541/100000 [18:43:19<6:05:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62542/100000 [18:43:19<6:05:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 62543/100000 [18:43:20<6:05:13,  1.71it/s]
Train steps ... :  63%|██████▎   | 62544/100000 [18:43:20<6:05:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 62545/100000 [18:43:21<6:04:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 62546/100000 [18:43:22<6:04:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 62547/100000 [18:43:22<6:04:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62548/100000 [18:43:23<6:05:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62549/100000 [18:43:23<6:05:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 62550/100000 [18:43:24<6:05:19,  1.71it/s]Step... (62550 / 100000 | Loss: 1.0354403257369995, Learning Rate: 3.763819095477387e-05)
+
                                                                             
Step... (62550 / 100000 | Loss: 0.7529463171958923, Learning Rate: 3.763819095477387e-05)
+
Train steps ... :  63%|██████▎   | 62550/100000 [18:43:24<6:05:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62551/100000 [18:43:24<6:05:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62552/100000 [18:43:25<6:04:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 62553/100000 [18:43:26<6:04:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 62554/100000 [18:43:26<6:04:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 62555/100000 [18:43:27<6:04:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 62556/100000 [18:43:27<6:04:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 62557/100000 [18:43:28<6:04:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 62558/100000 [18:43:29<6:04:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62559/100000 [18:43:29<6:04:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 62560/100000 [18:43:30<6:04:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 62561/100000 [18:43:30<6:05:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 62562/100000 [18:43:31<6:05:09,  1.71it/s]
Train steps ... :  63%|██████▎   | 62563/100000 [18:43:31<6:04:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 62564/100000 [18:43:32<6:05:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62565/100000 [18:43:33<6:05:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 62566/100000 [18:43:33<6:05:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 62567/100000 [18:43:34<6:04:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 62568/100000 [18:43:34<6:05:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 62569/100000 [18:43:35<6:04:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62570/100000 [18:43:36<6:05:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 62571/100000 [18:43:36<6:04:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 62572/100000 [18:43:37<6:04:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62573/100000 [18:43:37<6:04:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 62574/100000 [18:43:38<6:04:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 62575/100000 [18:43:38<6:05:46,  1.71it/s]Step... (62575 / 100000 | Loss: 0.7335259914398193, Learning Rate: 3.761306532663317e-05)
+
                                                                             
Step... (62575 / 100000 | Loss: 0.6497368216514587, Learning Rate: 3.761306532663317e-05)
+
Train steps ... :  63%|██████▎   | 62575/100000 [18:43:39<6:05:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 62576/100000 [18:43:39<6:05:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 62577/100000 [18:43:40<6:05:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 62578/100000 [18:43:40<6:04:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 62579/100000 [18:43:41<6:04:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 62580/100000 [18:43:41<6:05:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 62581/100000 [18:43:42<6:04:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62582/100000 [18:43:43<6:05:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 62583/100000 [18:43:43<6:04:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62584/100000 [18:43:44<6:04:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62585/100000 [18:43:44<6:04:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62586/100000 [18:43:45<6:05:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62587/100000 [18:43:45<6:05:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62588/100000 [18:43:46<6:05:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 62589/100000 [18:43:47<6:05:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 62590/100000 [18:43:47<6:04:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62591/100000 [18:43:48<6:04:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 62592/100000 [18:43:48<6:05:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 62593/100000 [18:43:49<6:04:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62594/100000 [18:43:50<6:05:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 62595/100000 [18:43:50<6:05:07,  1.71it/s]
Train steps ... :  63%|██████▎   | 62596/100000 [18:43:51<6:04:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 62597/100000 [18:43:51<6:04:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 62598/100000 [18:43:52<6:04:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 62599/100000 [18:43:53<6:04:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 62600/100000 [18:43:53<6:04:59,  1.71it/s]Step... (62600 / 100000 | Loss: 0.927019476890564, Learning Rate: 3.7587939698492465e-05)
+
                                                                             
Step... (62600 / 100000 | Loss: 0.9863742589950562, Learning Rate: 3.7587939698492465e-05)
+
Train steps ... :  63%|██████▎   | 62600/100000 [18:43:53<6:04:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62601/100000 [18:43:54<6:04:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62602/100000 [18:43:54<6:05:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 62603/100000 [18:43:55<6:04:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62604/100000 [18:43:55<6:04:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 62605/100000 [18:43:56<6:04:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62606/100000 [18:43:57<6:04:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 62607/100000 [18:43:57<6:04:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 62608/100000 [18:43:58<6:04:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62609/100000 [18:43:58<6:04:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 62610/100000 [18:43:59<6:04:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62611/100000 [18:44:00<6:04:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 62612/100000 [18:44:00<6:04:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62613/100000 [18:44:01<6:04:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62614/100000 [18:44:01<6:04:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 62615/100000 [18:44:02<6:04:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 62616/100000 [18:44:02<6:04:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62617/100000 [18:44:03<6:04:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 62618/100000 [18:44:04<6:04:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 62619/100000 [18:44:04<6:04:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62620/100000 [18:44:05<6:04:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 62621/100000 [18:44:05<6:04:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62622/100000 [18:44:06<6:04:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 62623/100000 [18:44:07<6:04:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 62624/100000 [18:44:07<6:04:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62625/100000 [18:44:08<6:04:19,  1.71it/s]Step... (62625 / 100000 | Loss: 0.5379804372787476, Learning Rate: 3.756281407035176e-05)
+
                                                                             
Step... (62625 / 100000 | Loss: 0.878527820110321, Learning Rate: 3.756281407035176e-05)
+
Train steps ... :  63%|██████▎   | 62625/100000 [18:44:08<6:04:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62626/100000 [18:44:08<6:04:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 62627/100000 [18:44:09<6:04:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 62628/100000 [18:44:09<6:04:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 62629/100000 [18:44:10<6:04:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62630/100000 [18:44:11<6:04:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62631/100000 [18:44:11<6:04:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 62632/100000 [18:44:12<6:03:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62633/100000 [18:44:12<6:03:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 62634/100000 [18:44:13<6:04:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 62635/100000 [18:44:14<6:04:07,  1.71it/s]
Train steps ... :  63%|██████▎   | 62636/100000 [18:44:14<6:04:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62637/100000 [18:44:15<6:04:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 62638/100000 [18:44:15<6:04:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 62639/100000 [18:44:16<6:03:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 62640/100000 [18:44:17<6:03:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 62641/100000 [18:44:17<6:03:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 62642/100000 [18:44:18<6:04:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 62643/100000 [18:44:18<6:04:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62644/100000 [18:44:19<6:04:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 62645/100000 [18:44:19<6:04:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 62646/100000 [18:44:20<6:03:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62647/100000 [18:44:21<6:04:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 62648/100000 [18:44:21<6:04:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 62649/100000 [18:44:22<6:04:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 62650/100000 [18:44:22<6:04:00,  1.71it/s]Step... (62650 / 100000 | Loss: 0.72333824634552, Learning Rate: 3.753768844221106e-05)
+
                                                                             
Step... (62650 / 100000 | Loss: 0.6747829914093018, Learning Rate: 3.753768844221106e-05)
+
Train steps ... :  63%|██████▎   | 62650/100000 [18:44:23<6:04:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 62651/100000 [18:44:23<6:04:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 62652/100000 [18:44:24<6:03:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 62653/100000 [18:44:24<6:03:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 62654/100000 [18:44:25<6:03:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 62655/100000 [18:44:25<6:03:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 62656/100000 [18:44:26<6:04:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 62657/100000 [18:44:26<6:04:13,  1.71it/s]
Train steps ... :  63%|██████▎   | 62658/100000 [18:44:27<6:04:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 62659/100000 [18:44:28<6:04:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62660/100000 [18:44:28<6:04:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 62661/100000 [18:44:29<6:03:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 62662/100000 [18:44:29<6:03:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62663/100000 [18:44:30<6:04:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 62664/100000 [18:44:31<6:04:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 62665/100000 [18:44:31<6:04:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 62666/100000 [18:44:32<6:04:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 62667/100000 [18:44:32<6:03:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 62668/100000 [18:44:33<6:03:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 62669/100000 [18:44:33<6:03:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62670/100000 [18:44:34<6:03:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 62671/100000 [18:44:35<6:03:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 62672/100000 [18:44:35<6:03:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 62673/100000 [18:44:36<6:03:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 62674/100000 [18:44:36<6:03:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 62675/100000 [18:44:37<6:04:02,  1.71it/s]Step... (62675 / 100000 | Loss: 0.8269544839859009, Learning Rate: 3.751256281407035e-05)
+
                                                                             
Step... (62675 / 100000 | Loss: 0.6579440832138062, Learning Rate: 3.751256281407035e-05)
+
Train steps ... :  63%|██████▎   | 62675/100000 [18:44:37<6:04:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 62676/100000 [18:44:38<6:03:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 62677/100000 [18:44:38<6:03:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 62678/100000 [18:44:39<6:03:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 62679/100000 [18:44:39<6:03:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62680/100000 [18:44:40<6:03:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 62681/100000 [18:44:40<6:03:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 62682/100000 [18:44:41<6:03:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 62683/100000 [18:44:42<6:03:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 62684/100000 [18:44:42<6:03:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 62685/100000 [18:44:43<6:03:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 62686/100000 [18:44:43<6:04:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62687/100000 [18:44:44<6:04:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 62688/100000 [18:44:45<6:03:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 62689/100000 [18:44:45<6:03:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62690/100000 [18:44:46<6:03:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62691/100000 [18:44:46<6:02:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 62692/100000 [18:44:47<6:02:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62693/100000 [18:44:47<6:03:07,  1.71it/s]
Train steps ... :  63%|██████▎   | 62694/100000 [18:44:48<6:03:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 62695/100000 [18:44:49<6:02:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62696/100000 [18:44:49<6:03:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 62697/100000 [18:44:50<6:03:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 62698/100000 [18:44:50<6:02:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62699/100000 [18:44:51<6:03:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62700/100000 [18:44:52<6:02:59,  1.71it/s]Step... (62700 / 100000 | Loss: 0.7818096280097961, Learning Rate: 3.748743718592965e-05)
+
                                                                             
Step... (62700 / 100000 | Loss: 0.8052334785461426, Learning Rate: 3.748743718592965e-05)
+
Train steps ... :  63%|██████▎   | 62700/100000 [18:44:52<6:02:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62701/100000 [18:44:52<6:03:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62702/100000 [18:44:53<6:03:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 62703/100000 [18:44:53<6:03:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 62704/100000 [18:44:54<6:04:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 62705/100000 [18:44:55<6:03:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 62706/100000 [18:44:55<6:04:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 62707/100000 [18:44:56<6:03:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62708/100000 [18:44:56<6:03:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 62709/100000 [18:44:57<6:03:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62710/100000 [18:44:57<6:03:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 62711/100000 [18:44:58<6:03:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 62712/100000 [18:44:59<6:03:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 62713/100000 [18:44:59<6:03:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 62714/100000 [18:45:00<6:03:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 62715/100000 [18:45:00<6:03:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 62716/100000 [18:45:01<6:03:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 62717/100000 [18:45:02<6:03:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62718/100000 [18:45:02<6:02:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 62719/100000 [18:45:03<6:03:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 62720/100000 [18:45:03<6:03:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 62721/100000 [18:45:04<6:03:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 62722/100000 [18:45:04<6:03:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 62723/100000 [18:45:05<6:02:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62724/100000 [18:45:06<6:03:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62725/100000 [18:45:06<6:03:11,  1.71it/s]Step... (62725 / 100000 | Loss: 0.7891383171081543, Learning Rate: 3.746231155778895e-05)
+
                                                                             
Step... (62725 / 100000 | Loss: 0.6561888456344604, Learning Rate: 3.746231155778895e-05)
+
Train steps ... :  63%|██████▎   | 62725/100000 [18:45:07<6:03:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62726/100000 [18:45:07<6:03:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 62727/100000 [18:45:07<6:03:09,  1.71it/s]
Train steps ... :  63%|██████▎   | 62728/100000 [18:45:08<6:04:27,  1.70it/s]
Train steps ... :  63%|██████▎   | 62729/100000 [18:45:09<6:02:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 62730/100000 [18:45:09<6:03:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62731/100000 [18:45:10<6:02:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 62732/100000 [18:45:10<6:02:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 62733/100000 [18:45:11<6:02:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62734/100000 [18:45:11<6:02:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 62735/100000 [18:45:12<6:02:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 62736/100000 [18:45:13<6:02:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 62737/100000 [18:45:13<6:02:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 62738/100000 [18:45:14<6:02:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 62739/100000 [18:45:14<6:02:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62740/100000 [18:45:15<6:02:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 62741/100000 [18:45:16<6:02:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 62742/100000 [18:45:16<6:02:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 62743/100000 [18:45:17<6:02:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 62744/100000 [18:45:17<6:02:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 62745/100000 [18:45:18<6:02:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 62746/100000 [18:45:18<6:02:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 62747/100000 [18:45:19<6:03:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62748/100000 [18:45:20<6:02:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 62749/100000 [18:45:20<6:02:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 62750/100000 [18:45:21<6:02:37,  1.71it/s]Step... (62750 / 100000 | Loss: 0.8549294471740723, Learning Rate: 3.7437185929648245e-05)
+
                                                                             
Step... (62750 / 100000 | Loss: 0.6371338963508606, Learning Rate: 3.7437185929648245e-05)
+
Train steps ... :  63%|██████▎   | 62750/100000 [18:45:21<6:02:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62751/100000 [18:45:21<6:02:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62752/100000 [18:45:22<6:02:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62753/100000 [18:45:23<6:02:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 62754/100000 [18:45:23<6:03:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 62755/100000 [18:45:24<6:03:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 62756/100000 [18:45:24<6:02:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 62757/100000 [18:45:25<6:02:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62758/100000 [18:45:25<6:02:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 62759/100000 [18:45:26<6:02:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 62760/100000 [18:45:27<6:02:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 62761/100000 [18:45:27<6:02:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 62762/100000 [18:45:28<6:02:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 62763/100000 [18:45:28<6:02:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 62764/100000 [18:45:29<6:02:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 62765/100000 [18:45:30<6:02:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 62766/100000 [18:45:30<6:02:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 62767/100000 [18:45:31<6:02:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 62768/100000 [18:45:31<6:02:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 62769/100000 [18:45:32<6:02:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62770/100000 [18:45:32<6:02:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 62771/100000 [18:45:33<6:02:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 62772/100000 [18:45:34<6:03:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 62773/100000 [18:45:34<6:02:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 62774/100000 [18:45:35<6:02:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 62775/100000 [18:45:35<6:03:35,  1.71it/s]Step... (62775 / 100000 | Loss: 0.6999568939208984, Learning Rate: 3.741206030150754e-05)
+
                                                                             
Step... (62775 / 100000 | Loss: 1.0442203283309937, Learning Rate: 3.741206030150754e-05)
+
Train steps ... :  63%|██████▎   | 62775/100000 [18:45:36<6:03:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 62776/100000 [18:45:36<6:03:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 62777/100000 [18:45:37<6:02:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 62778/100000 [18:45:37<6:02:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 62779/100000 [18:45:38<6:02:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62780/100000 [18:45:38<6:02:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 62781/100000 [18:45:39<6:02:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 62782/100000 [18:45:40<6:02:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 62783/100000 [18:45:40<6:02:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62784/100000 [18:45:41<6:02:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 62785/100000 [18:45:41<6:02:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 62786/100000 [18:45:42<6:02:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 62787/100000 [18:45:42<6:02:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 62788/100000 [18:45:43<6:02:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 62789/100000 [18:45:44<6:02:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 62790/100000 [18:45:44<6:02:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 62791/100000 [18:45:45<6:02:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 62792/100000 [18:45:45<6:02:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62793/100000 [18:45:46<6:02:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62794/100000 [18:45:47<6:02:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 62795/100000 [18:45:47<6:02:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62796/100000 [18:45:48<6:01:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 62797/100000 [18:45:48<6:01:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 62798/100000 [18:45:49<6:01:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62799/100000 [18:45:49<6:02:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 62800/100000 [18:45:50<6:01:44,  1.71it/s]Step... (62800 / 100000 | Loss: 0.6356715559959412, Learning Rate: 3.738693467336684e-05)
+
                                                                             
Step... (62800 / 100000 | Loss: 0.7599334120750427, Learning Rate: 3.738693467336684e-05)
+
Train steps ... :  63%|██████▎   | 62800/100000 [18:45:50<6:01:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 62801/100000 [18:45:51<6:02:22,  1.71it/s]
Train steps ... :  63%|██████▎   | 62802/100000 [18:45:51<6:02:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 62803/100000 [18:45:52<6:02:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62804/100000 [18:45:52<6:02:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 62805/100000 [18:45:53<6:02:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62806/100000 [18:45:54<6:01:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 62807/100000 [18:45:54<6:02:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 62808/100000 [18:45:55<6:02:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62809/100000 [18:45:55<6:02:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 62810/100000 [18:45:56<6:01:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 62811/100000 [18:45:56<6:01:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 62812/100000 [18:45:57<6:02:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62813/100000 [18:45:58<6:02:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 62814/100000 [18:45:58<6:02:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 62815/100000 [18:45:59<6:02:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 62816/100000 [18:45:59<6:02:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62817/100000 [18:46:00<6:02:07,  1.71it/s]
Train steps ... :  63%|██████▎   | 62818/100000 [18:46:01<6:02:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 62819/100000 [18:46:01<6:01:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62820/100000 [18:46:02<6:01:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 62821/100000 [18:46:02<6:02:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 62822/100000 [18:46:03<6:01:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 62823/100000 [18:46:03<6:02:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 62824/100000 [18:46:04<6:02:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 62825/100000 [18:46:05<6:02:09,  1.71it/s]Step... (62825 / 100000 | Loss: 0.6523489952087402, Learning Rate: 3.7361809045226135e-05)
+
                                                                             
Step... (62825 / 100000 | Loss: 0.5951672792434692, Learning Rate: 3.7361809045226135e-05)
+
Train steps ... :  63%|██████▎   | 62825/100000 [18:46:05<6:02:09,  1.71it/s]
Train steps ... :  63%|██████▎   | 62826/100000 [18:46:05<6:02:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 62827/100000 [18:46:06<6:01:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62828/100000 [18:46:06<6:01:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62829/100000 [18:46:07<6:02:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62830/100000 [18:46:08<6:02:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 62831/100000 [18:46:08<6:02:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 62832/100000 [18:46:09<6:02:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62833/100000 [18:46:09<6:02:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 62834/100000 [18:46:10<6:03:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 62835/100000 [18:46:10<6:02:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 62836/100000 [18:46:11<6:03:49,  1.70it/s]
Train steps ... :  63%|██████▎   | 62837/100000 [18:46:12<6:03:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 62838/100000 [18:46:12<6:02:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 62839/100000 [18:46:13<6:02:07,  1.71it/s]
Train steps ... :  63%|██████▎   | 62840/100000 [18:46:13<6:01:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 62841/100000 [18:46:14<6:01:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62842/100000 [18:46:15<6:01:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 62843/100000 [18:46:15<6:01:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62844/100000 [18:46:16<6:01:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 62845/100000 [18:46:16<6:01:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 62846/100000 [18:46:17<6:01:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62847/100000 [18:46:18<6:01:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 62848/100000 [18:46:18<6:01:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 62849/100000 [18:46:19<6:01:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 62850/100000 [18:46:19<6:01:51,  1.71it/s]Step... (62850 / 100000 | Loss: 0.8124890327453613, Learning Rate: 3.7336683417085425e-05)
+
                                                                             
Step... (62850 / 100000 | Loss: 0.6946130394935608, Learning Rate: 3.7336683417085425e-05)
+
Train steps ... :  63%|██████▎   | 62850/100000 [18:46:20<6:01:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 62851/100000 [18:46:20<6:01:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62852/100000 [18:46:20<6:01:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62853/100000 [18:46:21<6:01:22,  1.71it/s]
Train steps ... :  63%|██████▎   | 62854/100000 [18:46:22<6:01:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 62855/100000 [18:46:22<6:01:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 62856/100000 [18:46:23<6:01:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 62857/100000 [18:46:23<6:01:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62858/100000 [18:46:24<6:01:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 62859/100000 [18:46:25<6:01:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 62860/100000 [18:46:25<6:01:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 62861/100000 [18:46:26<6:01:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62862/100000 [18:46:26<6:01:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 62863/100000 [18:46:27<6:01:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 62864/100000 [18:46:27<6:01:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 62865/100000 [18:46:28<6:01:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62866/100000 [18:46:29<6:01:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 62867/100000 [18:46:29<6:01:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 62868/100000 [18:46:30<6:01:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 62869/100000 [18:46:30<6:01:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62870/100000 [18:46:31<6:01:22,  1.71it/s]
Train steps ... :  63%|██████▎   | 62871/100000 [18:46:32<6:01:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 62872/100000 [18:46:32<6:01:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62873/100000 [18:46:33<6:01:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62874/100000 [18:46:33<6:01:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62875/100000 [18:46:34<6:01:40,  1.71it/s]Step... (62875 / 100000 | Loss: 0.913013756275177, Learning Rate: 3.731155778894472e-05)
+
                                                                             
Step... (62875 / 100000 | Loss: 0.9253337383270264, Learning Rate: 3.731155778894472e-05)
+
Train steps ... :  63%|██████▎   | 62875/100000 [18:46:34<6:01:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 62876/100000 [18:46:34<6:01:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 62877/100000 [18:46:35<6:01:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62878/100000 [18:46:36<6:01:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 62879/100000 [18:46:36<6:01:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62880/100000 [18:46:37<6:01:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 62881/100000 [18:46:37<6:01:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 62882/100000 [18:46:38<6:01:22,  1.71it/s]
Train steps ... :  63%|██████▎   | 62883/100000 [18:46:39<6:01:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 62884/100000 [18:46:39<6:01:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 62885/100000 [18:46:40<6:01:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 62886/100000 [18:46:40<6:01:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 62887/100000 [18:46:41<6:01:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 62888/100000 [18:46:41<6:01:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 62889/100000 [18:46:42<6:01:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 62890/100000 [18:46:43<6:00:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 62891/100000 [18:46:43<6:00:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 62892/100000 [18:46:44<6:00:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 62893/100000 [18:46:44<6:01:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 62894/100000 [18:46:45<6:02:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 62895/100000 [18:46:46<6:01:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 62896/100000 [18:46:46<6:01:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62897/100000 [18:46:47<6:01:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 62898/100000 [18:46:47<6:01:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 62899/100000 [18:46:48<6:01:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 62900/100000 [18:46:48<6:02:10,  1.71it/s]Step... (62900 / 100000 | Loss: 0.5298810005187988, Learning Rate: 3.7286432160804025e-05)
+
                                                                             
Step... (62900 / 100000 | Loss: 1.1669337749481201, Learning Rate: 3.7286432160804025e-05)
+
Train steps ... :  63%|██████��   | 62900/100000 [18:46:49<6:02:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 62901/100000 [18:46:49<6:02:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 62902/100000 [18:46:50<6:01:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 62903/100000 [18:46:50<6:02:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62904/100000 [18:46:51<6:02:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 62905/100000 [18:46:51<6:01:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 62906/100000 [18:46:52<6:01:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 62907/100000 [18:46:53<6:01:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 62908/100000 [18:46:53<6:01:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 62909/100000 [18:46:54<6:00:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62910/100000 [18:46:54<6:00:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 62911/100000 [18:46:55<6:00:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 62912/100000 [18:46:55<6:00:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62913/100000 [18:46:56<6:01:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 62914/100000 [18:46:57<6:01:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 62915/100000 [18:46:57<6:01:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62916/100000 [18:46:58<6:01:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 62917/100000 [18:46:58<6:01:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62918/100000 [18:46:59<6:01:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 62919/100000 [18:47:00<6:01:09,  1.71it/s]
Train steps ... :  63%|██████▎   | 62920/100000 [18:47:00<6:01:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 62921/100000 [18:47:01<6:01:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62922/100000 [18:47:01<6:01:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 62923/100000 [18:47:02<6:00:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 62924/100000 [18:47:03<6:01:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 62925/100000 [18:47:03<6:01:19,  1.71it/s]Step... (62925 / 100000 | Loss: 0.5214627981185913, Learning Rate: 3.726130653266332e-05)
+
                                                                             
Step... (62925 / 100000 | Loss: 0.766952633857727, Learning Rate: 3.726130653266332e-05)
+
Train steps ... :  63%|██████▎   | 62925/100000 [18:47:03<6:01:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62926/100000 [18:47:04<6:01:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 62927/100000 [18:47:04<6:01:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 62928/100000 [18:47:05<6:01:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 62929/100000 [18:47:05<6:01:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62930/100000 [18:47:06<6:01:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 62931/100000 [18:47:07<6:00:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62932/100000 [18:47:07<6:00:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 62933/100000 [18:47:08<6:01:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 62934/100000 [18:47:08<6:01:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 62935/100000 [18:47:09<6:01:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 62936/100000 [18:47:10<6:01:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 62937/100000 [18:47:10<6:01:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62938/100000 [18:47:11<6:01:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 62939/100000 [18:47:11<6:01:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 62940/100000 [18:47:12<6:01:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 62941/100000 [18:47:12<6:01:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 62942/100000 [18:47:13<6:01:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62943/100000 [18:47:14<6:01:13,  1.71it/s]
Train steps ... :  63%|██████▎   | 62944/100000 [18:47:14<6:01:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 62945/100000 [18:47:15<6:01:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62946/100000 [18:47:15<6:01:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 62947/100000 [18:47:16<6:00:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 62948/100000 [18:47:17<6:00:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 62949/100000 [18:47:17<6:00:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 62950/100000 [18:47:18<6:01:21,  1.71it/s]Step... (62950 / 100000 | Loss: 0.8572691679000854, Learning Rate: 3.723618090452262e-05)
+
                                                                             
Step... (62950 / 100000 | Loss: 0.7137911915779114, Learning Rate: 3.723618090452262e-05)
+
Train steps ... :  63%|██████▎   | 62950/100000 [18:47:18<6:01:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62951/100000 [18:47:18<6:01:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 62952/100000 [18:47:19<6:01:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 62953/100000 [18:47:19<6:01:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 62954/100000 [18:47:20<6:01:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62955/100000 [18:47:21<6:01:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 62956/100000 [18:47:21<6:00:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 62957/100000 [18:47:22<6:00:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62958/100000 [18:47:22<6:00:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 62959/100000 [18:47:23<6:01:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 62960/100000 [18:47:24<6:00:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 62961/100000 [18:47:24<6:00:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 62962/100000 [18:47:25<6:00:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 62963/100000 [18:47:25<6:00:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 62964/100000 [18:47:26<6:00:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 62965/100000 [18:47:26<6:00:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 62966/100000 [18:47:27<6:00:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62967/100000 [18:47:28<6:01:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 62968/100000 [18:47:28<6:01:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 62969/100000 [18:47:29<6:01:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62970/100000 [18:47:29<6:01:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62971/100000 [18:47:30<6:01:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62972/100000 [18:47:31<6:01:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 62973/100000 [18:47:31<6:01:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 62974/100000 [18:47:32<6:01:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62975/100000 [18:47:32<6:00:48,  1.71it/s]Step... (62975 / 100000 | Loss: 0.8125129342079163, Learning Rate: 3.7211055276381915e-05)
+
                                                                             
Step... (62975 / 100000 | Loss: 0.7460052371025085, Learning Rate: 3.7211055276381915e-05)
+
Train steps ... :  63%|██████▎   | 62975/100000 [18:47:33<6:00:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 62976/100000 [18:47:33<6:00:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62977/100000 [18:47:34<6:00:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62978/100000 [18:47:34<6:00:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 62979/100000 [18:47:35<6:00:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 62980/100000 [18:47:35<6:00:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 62981/100000 [18:47:36<6:00:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 62982/100000 [18:47:36<6:00:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62983/100000 [18:47:37<6:00:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 62984/100000 [18:47:38<6:00:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 62985/100000 [18:47:38<6:00:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 62986/100000 [18:47:39<6:00:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 62987/100000 [18:47:39<6:00:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 62988/100000 [18:47:40<6:00:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 62989/100000 [18:47:41<6:00:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 62990/100000 [18:47:41<6:00:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 62991/100000 [18:47:42<6:00:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 62992/100000 [18:47:42<6:01:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 62993/100000 [18:47:43<6:00:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 62994/100000 [18:47:43<6:00:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 62995/100000 [18:47:44<6:00:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 62996/100000 [18:47:45<6:00:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 62997/100000 [18:47:45<6:00:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 62998/100000 [18:47:46<6:00:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 62999/100000 [18:47:46<6:00:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 63000/100000 [18:47:47<6:00:15,  1.71it/s]Step... (63000 / 100000 | Loss: 0.7475056052207947, Learning Rate: 3.7185929648241204e-05)
+
                                                                             
Step... (63000 / 100000 | Loss: 0.7621027231216431, Learning Rate: 3.7185929648241204e-05)
+
Train steps ... :  63%|██████▎   | 63000/100000 [18:47:47<6:00:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 63001/100000 [18:47:48<6:00:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63002/100000 [18:47:48<6:00:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 63003/100000 [18:47:49<6:00:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 63004/100000 [18:47:49<6:00:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 63005/100000 [18:47:50<6:00:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 63006/100000 [18:47:50<6:00:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 63007/100000 [18:47:51<6:00:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63008/100000 [18:47:52<6:00:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 63009/100000 [18:47:52<6:00:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 63010/100000 [18:47:53<6:00:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 63011/100000 [18:47:53<6:00:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63012/100000 [18:47:54<6:00:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 63013/100000 [18:47:55<6:00:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 63014/100000 [18:47:55<6:00:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 63015/100000 [18:47:56<6:00:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 63016/100000 [18:47:56<6:00:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 63017/100000 [18:47:57<6:00:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63018/100000 [18:47:57<6:00:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 63019/100000 [18:47:58<6:00:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 63020/100000 [18:47:59<6:01:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 63021/100000 [18:47:59<6:00:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 63022/100000 [18:48:00<6:01:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 63023/100000 [18:48:00<6:00:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 63024/100000 [18:48:01<6:00:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 63025/100000 [18:48:02<6:00:02,  1.71it/s]Step... (63025 / 100000 | Loss: 0.8547648787498474, Learning Rate: 3.71608040201005e-05)
+
                                                                             
Step... (63025 / 100000 | Loss: 0.5762260556221008, Learning Rate: 3.71608040201005e-05)
+
Train steps ... :  63%|██████▎   | 63025/100000 [18:48:02<6:00:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63026/100000 [18:48:02<6:00:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 63027/100000 [18:48:03<6:00:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 63028/100000 [18:48:03<6:00:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 63029/100000 [18:48:04<5:59:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 63030/100000 [18:48:04<6:00:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63031/100000 [18:48:05<5:59:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63032/100000 [18:48:06<5:59:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 63033/100000 [18:48:06<6:00:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63034/100000 [18:48:07<6:00:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63035/100000 [18:48:07<6:00:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 63036/100000 [18:48:08<6:00:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 63037/100000 [18:48:09<6:00:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63038/100000 [18:48:09<6:00:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 63039/100000 [18:48:10<6:00:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 63040/100000 [18:48:10<6:00:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 63041/100000 [18:48:11<6:00:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 63042/100000 [18:48:12<6:00:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 63043/100000 [18:48:12<6:00:13,  1.71it/s]
Train steps ... :  63%|██████▎   | 63044/100000 [18:48:13<5:59:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 63045/100000 [18:48:13<6:00:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 63046/100000 [18:48:14<6:00:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 63047/100000 [18:48:14<6:01:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63048/100000 [18:48:15<6:00:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63049/100000 [18:48:16<6:00:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63050/100000 [18:48:16<6:00:22,  1.71it/s]Step... (63050 / 100000 | Loss: 0.7735694050788879, Learning Rate: 3.71356783919598e-05)
+
                                                                             
Step... (63050 / 100000 | Loss: 1.0015792846679688, Learning Rate: 3.71356783919598e-05)
+
Train steps ... :  63%|██████▎   | 63050/100000 [18:48:17<6:00:22,  1.71it/s]
Train steps ... :  63%|██████▎   | 63051/100000 [18:48:17<6:00:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 63052/100000 [18:48:17<6:00:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 63053/100000 [18:48:18<5:59:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 63054/100000 [18:48:19<6:00:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 63055/100000 [18:48:19<6:00:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 63056/100000 [18:48:20<6:00:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63057/100000 [18:48:20<6:00:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 63058/100000 [18:48:21<5:59:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 63059/100000 [18:48:21<5:59:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 63060/100000 [18:48:22<6:00:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63061/100000 [18:48:23<6:00:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 63062/100000 [18:48:23<5:59:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 63063/100000 [18:48:24<6:00:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 63064/100000 [18:48:24<6:00:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 63065/100000 [18:48:25<6:00:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 63066/100000 [18:48:26<6:01:05,  1.70it/s]
Train steps ... :  63%|██████▎   | 63067/100000 [18:48:26<5:59:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 63068/100000 [18:48:27<6:00:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 63069/100000 [18:48:27<6:00:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 63070/100000 [18:48:28<5:59:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 63071/100000 [18:48:28<5:59:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 63072/100000 [18:48:29<5:59:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 63073/100000 [18:48:30<5:59:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 63074/100000 [18:48:30<5:59:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63075/100000 [18:48:31<6:00:14,  1.71it/s]Step... (63075 / 100000 | Loss: 0.696577787399292, Learning Rate: 3.7110552763819094e-05)
+
                                                                             
Step... (63075 / 100000 | Loss: 0.5806185007095337, Learning Rate: 3.7110552763819094e-05)
+
Train steps ... :  63%|██████▎   | 63075/100000 [18:48:31<6:00:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63076/100000 [18:48:31<6:00:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63077/100000 [18:48:32<5:59:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 63078/100000 [18:48:33<5:59:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 63079/100000 [18:48:33<5:59:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 63080/100000 [18:48:34<5:59:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63081/100000 [18:48:34<5:59:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 63082/100000 [18:48:35<5:59:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63083/100000 [18:48:35<5:59:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 63084/100000 [18:48:36<5:59:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 63085/100000 [18:48:37<5:59:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63086/100000 [18:48:37<5:59:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 63087/100000 [18:48:38<5:59:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63088/100000 [18:48:38<5:59:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63089/100000 [18:48:39<5:59:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 63090/100000 [18:48:40<5:59:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63091/100000 [18:48:40<5:59:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 63092/100000 [18:48:41<5:59:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 63093/100000 [18:48:41<5:59:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 63094/100000 [18:48:42<5:59:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63095/100000 [18:48:43<5:58:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 63096/100000 [18:48:43<5:58:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 63097/100000 [18:48:44<5:59:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 63098/100000 [18:48:44<5:59:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 63099/100000 [18:48:45<5:59:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 63100/100000 [18:48:45<5:59:34,  1.71it/s]Step... (63100 / 100000 | Loss: 0.7403457164764404, Learning Rate: 3.708542713567839e-05)
+
                                                                             
Step... (63100 / 100000 | Loss: 0.6165795922279358, Learning Rate: 3.708542713567839e-05)
+
Train steps ... :  63%|██████▎   | 63100/100000 [18:48:46<5:59:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63101/100000 [18:48:46<5:59:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63102/100000 [18:48:47<5:59:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 63103/100000 [18:48:47<5:59:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 63104/100000 [18:48:48<5:59:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 63105/100000 [18:48:48<5:59:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63106/100000 [18:48:49<5:59:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 63107/100000 [18:48:50<5:59:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 63108/100000 [18:48:50<5:59:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63109/100000 [18:48:51<5:59:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63110/100000 [18:48:51<5:59:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 63111/100000 [18:48:52<5:59:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63112/100000 [18:48:52<5:59:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63113/100000 [18:48:53<5:59:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 63114/100000 [18:48:54<5:59:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63115/100000 [18:48:54<5:59:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63116/100000 [18:48:55<5:59:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63117/100000 [18:48:55<5:59:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 63118/100000 [18:48:56<5:59:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 63119/100000 [18:48:57<5:59:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63120/100000 [18:48:57<5:59:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 63121/100000 [18:48:58<6:00:41,  1.70it/s]
Train steps ... :  63%|██████▎   | 63122/100000 [18:48:58<5:59:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 63123/100000 [18:48:59<5:59:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 63124/100000 [18:48:59<5:59:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 63125/100000 [18:49:00<5:59:16,  1.71it/s]Step... (63125 / 100000 | Loss: 0.785744309425354, Learning Rate: 3.7060301507537694e-05)
+
                                                                             
Step... (63125 / 100000 | Loss: 0.6757562160491943, Learning Rate: 3.7060301507537694e-05)
+
Train steps ... :  63%|██████▎   | 63125/100000 [18:49:00<5:59:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 63126/100000 [18:49:01<5:59:13,  1.71it/s]
Train steps ... :  63%|██████▎   | 63127/100000 [18:49:01<5:59:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 63128/100000 [18:49:02<5:59:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 63129/100000 [18:49:02<5:59:13,  1.71it/s]
Train steps ... :  63%|██████▎   | 63130/100000 [18:49:03<5:59:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 63131/100000 [18:49:04<5:58:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 63132/100000 [18:49:04<5:58:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 63133/100000 [18:49:05<5:59:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 63134/100000 [18:49:05<5:59:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63135/100000 [18:49:06<5:58:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 63136/100000 [18:49:06<5:58:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63137/100000 [18:49:07<5:58:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 63138/100000 [18:49:08<5:58:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 63139/100000 [18:49:08<5:59:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63140/100000 [18:49:09<5:59:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 63141/100000 [18:49:09<5:58:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63142/100000 [18:49:10<5:58:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63143/100000 [18:49:11<5:59:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 63144/100000 [18:49:11<5:59:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63145/100000 [18:49:12<5:59:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 63146/100000 [18:49:12<5:59:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 63147/100000 [18:49:13<5:58:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63148/100000 [18:49:13<5:58:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 63149/100000 [18:49:14<5:59:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 63150/100000 [18:49:15<5:59:32,  1.71it/s]Step... (63150 / 100000 | Loss: 1.1205239295959473, Learning Rate: 3.703517587939699e-05)
+
                                                                             
Step... (63150 / 100000 | Loss: 0.835847795009613, Learning Rate: 3.703517587939699e-05)
+
Train steps ... :  63%|██████▎   | 63150/100000 [18:49:15<5:59:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63151/100000 [18:49:15<5:59:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 63152/100000 [18:49:16<5:58:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 63153/100000 [18:49:16<5:59:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 63154/100000 [18:49:17<5:59:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 63155/100000 [18:49:18<5:58:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 63156/100000 [18:49:18<5:58:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 63157/100000 [18:49:19<5:58:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 63158/100000 [18:49:19<5:58:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63159/100000 [18:49:20<5:58:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 63160/100000 [18:49:21<5:59:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 63161/100000 [18:49:21<5:58:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 63162/100000 [18:49:22<5:58:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63163/100000 [18:49:22<5:58:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 63164/100000 [18:49:23<5:58:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 63165/100000 [18:49:23<5:58:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 63166/100000 [18:49:24<5:58:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63167/100000 [18:49:25<5:58:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 63168/100000 [18:49:25<5:58:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63169/100000 [18:49:26<5:58:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 63170/100000 [18:49:26<5:58:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 63171/100000 [18:49:27<5:58:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 63172/100000 [18:49:28<5:58:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 63173/100000 [18:49:28<5:58:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63174/100000 [18:49:29<5:58:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63175/100000 [18:49:29<5:58:52,  1.71it/s]Step... (63175 / 100000 | Loss: 0.8445966243743896, Learning Rate: 3.701005025125628e-05)
+
                                                                             
Step... (63175 / 100000 | Loss: 0.6516454815864563, Learning Rate: 3.701005025125628e-05)
+
Train steps ... :  63%|██████▎   | 63175/100000 [18:49:30<5:58:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 63176/100000 [18:49:30<5:58:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 63177/100000 [18:49:30<5:59:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63178/100000 [18:49:31<5:59:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 63179/100000 [18:49:32<5:59:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63180/100000 [18:49:32<5:58:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 63181/100000 [18:49:33<5:59:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 63182/100000 [18:49:33<5:58:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63183/100000 [18:49:34<5:58:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 63184/100000 [18:49:35<5:58:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 63185/100000 [18:49:35<5:58:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63186/100000 [18:49:36<5:58:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 63187/100000 [18:49:36<5:58:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 63188/100000 [18:49:37<5:58:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63189/100000 [18:49:37<5:58:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63190/100000 [18:49:38<5:58:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 63191/100000 [18:49:39<5:58:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 63192/100000 [18:49:39<5:59:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63193/100000 [18:49:40<5:59:07,  1.71it/s]
Train steps ... :  63%|██████▎   | 63194/100000 [18:49:40<5:58:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 63195/100000 [18:49:41<5:59:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 63196/100000 [18:49:42<5:58:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 63197/100000 [18:49:42<5:58:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 63198/100000 [18:49:43<5:58:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 63199/100000 [18:49:43<5:58:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 63200/100000 [18:49:44<5:58:56,  1.71it/s]Step... (63200 / 100000 | Loss: 1.0108695030212402, Learning Rate: 3.698492462311558e-05)
+
                                                                             
Step... (63200 / 100000 | Loss: 0.7809455394744873, Learning Rate: 3.698492462311558e-05)
+
Train steps ... :  63%|██████▎   | 63200/100000 [18:49:44<5:58:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 63201/100000 [18:49:44<5:58:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 63202/100000 [18:49:45<5:59:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 63203/100000 [18:49:46<5:58:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 63204/100000 [18:49:46<5:58:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 63205/100000 [18:49:47<5:58:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 63206/100000 [18:49:47<5:58:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63207/100000 [18:49:48<5:58:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63208/100000 [18:49:49<5:58:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 63209/100000 [18:49:49<5:58:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 63210/100000 [18:49:50<5:57:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 63211/100000 [18:49:50<5:57:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 63212/100000 [18:49:51<5:58:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 63213/100000 [18:49:51<5:58:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63214/100000 [18:49:52<5:58:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 63215/100000 [18:49:53<5:58:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 63216/100000 [18:49:53<5:57:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 63217/100000 [18:49:54<5:57:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 63218/100000 [18:49:54<5:57:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 63219/100000 [18:49:55<5:58:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 63220/100000 [18:49:56<5:57:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 63221/100000 [18:49:56<5:58:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 63222/100000 [18:49:57<5:58:22,  1.71it/s]
Train steps ... :  63%|██████▎   | 63223/100000 [18:49:57<5:58:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 63224/100000 [18:49:58<5:58:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63225/100000 [18:49:58<5:58:04,  1.71it/s]Step... (63225 / 100000 | Loss: 0.6168116331100464, Learning Rate: 3.6959798994974874e-05)
+
                                                                             
Step... (63225 / 100000 | Loss: 0.7437542676925659, Learning Rate: 3.6959798994974874e-05)
+
Train steps ... :  63%|██████▎   | 63225/100000 [18:49:59<5:58:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63226/100000 [18:49:59<5:58:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 63227/100000 [18:50:00<5:58:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63228/100000 [18:50:00<5:59:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 63229/100000 [18:50:01<5:58:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 63230/100000 [18:50:01<5:58:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63231/100000 [18:50:02<5:58:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63232/100000 [18:50:03<5:58:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 63233/100000 [18:50:03<5:58:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 63234/100000 [18:50:04<5:58:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 63235/100000 [18:50:04<5:58:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 63236/100000 [18:50:05<5:58:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63237/100000 [18:50:06<5:58:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 63238/100000 [18:50:06<5:58:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63239/100000 [18:50:07<5:57:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 63240/100000 [18:50:07<5:58:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63241/100000 [18:50:08<5:57:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 63242/100000 [18:50:08<5:58:09,  1.71it/s]
Train steps ... :  63%|██████▎   | 63243/100000 [18:50:09<5:57:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 63244/100000 [18:50:10<5:58:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 63245/100000 [18:50:10<5:57:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 63246/100000 [18:50:11<5:59:27,  1.70it/s]
Train steps ... :  63%|██████▎   | 63247/100000 [18:50:11<5:58:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 63248/100000 [18:50:12<5:58:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 63249/100000 [18:50:13<5:58:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 63250/100000 [18:50:13<5:58:20,  1.71it/s]Step... (63250 / 100000 | Loss: 0.5752739906311035, Learning Rate: 3.693467336683417e-05)
+
                                                                             
Step... (63250 / 100000 | Loss: 0.9830003976821899, Learning Rate: 3.693467336683417e-05)
+
Train steps ... :  63%|██████▎   | 63250/100000 [18:50:13<5:58:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63251/100000 [18:50:14<5:58:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63252/100000 [18:50:14<5:57:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 63253/100000 [18:50:15<5:57:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 63254/100000 [18:50:15<5:57:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 63255/100000 [18:50:16<5:57:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 63256/100000 [18:50:17<5:57:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63257/100000 [18:50:17<5:57:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 63258/100000 [18:50:18<5:57:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 63259/100000 [18:50:18<5:57:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63260/100000 [18:50:19<5:58:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63261/100000 [18:50:20<5:58:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 63262/100000 [18:50:20<5:58:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 63263/100000 [18:50:21<5:58:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 63264/100000 [18:50:21<5:58:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63265/100000 [18:50:22<5:58:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63266/100000 [18:50:22<5:58:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 63267/100000 [18:50:23<5:58:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 63268/100000 [18:50:24<5:57:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 63269/100000 [18:50:24<5:58:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 63270/100000 [18:50:25<5:58:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63271/100000 [18:50:25<5:57:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 63272/100000 [18:50:26<5:58:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 63273/100000 [18:50:27<5:58:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63274/100000 [18:50:27<5:58:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 63275/100000 [18:50:28<5:58:51,  1.71it/s]Step... (63275 / 100000 | Loss: 0.7640148401260376, Learning Rate: 3.690954773869347e-05)
+
                                                                             
Step... (63275 / 100000 | Loss: 0.5983059406280518, Learning Rate: 3.690954773869347e-05)
+
Train steps ... :  63%|██████▎   | 63275/100000 [18:50:28<5:58:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 63276/100000 [18:50:28<5:57:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 63277/100000 [18:50:29<5:58:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63278/100000 [18:50:29<5:57:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 63279/100000 [18:50:30<5:58:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 63280/100000 [18:50:31<5:59:13,  1.70it/s]
Train steps ... :  63%|██████▎   | 63281/100000 [18:50:31<5:58:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63282/100000 [18:50:32<5:58:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 63283/100000 [18:50:32<5:58:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 63284/100000 [18:50:33<5:58:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63285/100000 [18:50:34<5:58:09,  1.71it/s]
Train steps ... :  63%|██████▎   | 63286/100000 [18:50:34<5:57:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 63287/100000 [18:50:35<5:57:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 63288/100000 [18:50:35<5:57:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63289/100000 [18:50:36<5:57:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 63290/100000 [18:50:37<5:57:59,  1.71it/s]
Train steps ... :  63%|██████▎   | 63291/100000 [18:50:37<5:57:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 63292/100000 [18:50:38<5:58:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63293/100000 [18:50:38<5:57:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63294/100000 [18:50:39<5:57:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63295/100000 [18:50:39<5:57:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 63296/100000 [18:50:40<5:58:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63297/100000 [18:50:41<5:57:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 63298/100000 [18:50:41<5:57:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63299/100000 [18:50:42<5:58:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 63300/100000 [18:50:42<5:57:58,  1.71it/s]Step... (63300 / 100000 | Loss: 0.510360836982727, Learning Rate: 3.6884422110552764e-05)
+
                                                                             
Step... (63300 / 100000 | Loss: 1.1080477237701416, Learning Rate: 3.6884422110552764e-05)
+
Train steps ... :  63%|██████▎   | 63300/100000 [18:50:43<5:57:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 63301/100000 [18:50:43<5:58:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63302/100000 [18:50:44<5:57:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 63303/100000 [18:50:44<5:58:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 63304/100000 [18:50:45<5:57:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63305/100000 [18:50:45<5:58:57,  1.70it/s]
Train steps ... :  63%|██████▎   | 63306/100000 [18:50:46<5:58:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 63307/100000 [18:50:46<5:58:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63308/100000 [18:50:47<5:58:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 63309/100000 [18:50:48<5:57:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 63310/100000 [18:50:48<5:57:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 63311/100000 [18:50:49<5:57:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63312/100000 [18:50:49<5:57:26,  1.71it/s]
Train steps ... :  63%|██████▎   | 63313/100000 [18:50:50<5:57:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 63314/100000 [18:50:51<5:57:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 63315/100000 [18:50:51<5:56:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 63316/100000 [18:50:52<5:57:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 63317/100000 [18:50:52<5:57:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63318/100000 [18:50:53<5:57:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 63319/100000 [18:50:53<5:57:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 63320/100000 [18:50:54<5:57:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 63321/100000 [18:50:55<5:57:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63322/100000 [18:50:55<5:58:00,  1.71it/s]
Train steps ... :  63%|██████▎   | 63323/100000 [18:50:56<5:58:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63324/100000 [18:50:56<5:58:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 63325/100000 [18:50:57<5:58:12,  1.71it/s]Step... (63325 / 100000 | Loss: 0.7360928058624268, Learning Rate: 3.685929648241207e-05)
+
                                                                             
Step... (63325 / 100000 | Loss: 0.6883491277694702, Learning Rate: 3.685929648241207e-05)
+
Train steps ... :  63%|██████▎   | 63325/100000 [18:50:57<5:58:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63326/100000 [18:50:58<5:58:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63327/100000 [18:50:58<5:58:45,  1.70it/s]
Train steps ... :  63%|██████▎   | 63328/100000 [18:50:59<5:58:55,  1.70it/s]
Train steps ... :  63%|██████▎   | 63329/100000 [18:50:59<5:57:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 63330/100000 [18:51:00<5:57:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 63331/100000 [18:51:01<5:58:33,  1.70it/s]
Train steps ... :  63%|██████▎   | 63332/100000 [18:51:01<5:57:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 63333/100000 [18:51:02<5:57:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 63334/100000 [18:51:02<5:57:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 63335/100000 [18:51:03<5:57:09,  1.71it/s]
Train steps ... :  63%|██████▎   | 63336/100000 [18:51:03<5:57:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63337/100000 [18:51:04<5:57:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 63338/100000 [18:51:05<5:57:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63339/100000 [18:51:05<5:57:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 63340/100000 [18:51:06<5:57:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 63341/100000 [18:51:06<5:57:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63342/100000 [18:51:07<5:56:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 63343/100000 [18:51:08<5:56:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63344/100000 [18:51:08<5:56:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 63345/100000 [18:51:09<5:57:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 63346/100000 [18:51:09<5:56:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 63347/100000 [18:51:10<5:56:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 63348/100000 [18:51:10<5:56:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 63349/100000 [18:51:11<5:56:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63350/100000 [18:51:12<5:56:45,  1.71it/s]Step... (63350 / 100000 | Loss: 0.6420831084251404, Learning Rate: 3.683417085427136e-05)
+
                                                                             
Step... (63350 / 100000 | Loss: 0.744920015335083, Learning Rate: 3.683417085427136e-05)
+
Train steps ... :  63%|██████▎   | 63350/100000 [18:51:12<5:56:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 63351/100000 [18:51:12<5:57:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 63352/100000 [18:51:13<5:57:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63353/100000 [18:51:13<5:57:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 63354/100000 [18:51:14<5:56:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 63355/100000 [18:51:15<5:56:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 63356/100000 [18:51:15<5:56:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63357/100000 [18:51:16<5:56:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63358/100000 [18:51:16<5:56:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 63359/100000 [18:51:17<5:56:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 63360/100000 [18:51:17<5:57:13,  1.71it/s]
Train steps ... :  63%|██████▎   | 63361/100000 [18:51:18<5:57:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 63362/100000 [18:51:19<5:57:13,  1.71it/s]
Train steps ... :  63%|██████▎   | 63363/100000 [18:51:19<5:56:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63364/100000 [18:51:20<5:56:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63365/100000 [18:51:20<5:56:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 63366/100000 [18:51:21<5:57:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 63367/100000 [18:51:22<5:56:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 63368/100000 [18:51:22<5:56:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 63369/100000 [18:51:23<5:56:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63370/100000 [18:51:23<5:56:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 63371/100000 [18:51:24<5:57:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63372/100000 [18:51:24<5:56:53,  1.71it/s]
Train steps ... :  63%|██████▎   | 63373/100000 [18:51:25<5:57:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63374/100000 [18:51:26<5:56:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 63375/100000 [18:51:26<5:57:10,  1.71it/s]Step... (63375 / 100000 | Loss: 0.9074205160140991, Learning Rate: 3.6809045226130654e-05)
+
                                                                             
Step... (63375 / 100000 | Loss: 0.5987386703491211, Learning Rate: 3.6809045226130654e-05)
+
Train steps ... :  63%|██████▎   | 63375/100000 [18:51:27<5:57:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 63376/100000 [18:51:27<5:57:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63377/100000 [18:51:27<5:57:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63378/100000 [18:51:28<5:57:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63379/100000 [18:51:29<5:57:01,  1.71it/s]
Train steps ... :  63%|██████▎   | 63380/100000 [18:51:29<5:57:07,  1.71it/s]
Train steps ... :  63%|██████▎   | 63381/100000 [18:51:30<5:57:24,  1.71it/s]
Train steps ... :  63%|██████▎   | 63382/100000 [18:51:30<5:56:45,  1.71it/s]
Train steps ... :  63%|██████▎   | 63383/100000 [18:51:31<5:56:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 63384/100000 [18:51:31<5:56:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63385/100000 [18:51:32<5:56:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 63386/100000 [18:51:33<5:56:29,  1.71it/s]
Train steps ... :  63%|██████▎   | 63387/100000 [18:51:33<5:56:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63388/100000 [18:51:34<5:56:07,  1.71it/s]
Train steps ... :  63%|██████▎   | 63389/100000 [18:51:34<5:56:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 63390/100000 [18:51:35<5:56:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63391/100000 [18:51:36<5:56:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 63392/100000 [18:51:36<5:56:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 63393/100000 [18:51:37<5:56:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63394/100000 [18:51:37<5:56:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 63395/100000 [18:51:38<5:56:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 63396/100000 [18:51:39<5:56:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 63397/100000 [18:51:39<5:56:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 63398/100000 [18:51:40<5:57:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 63399/100000 [18:51:40<5:56:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 63400/100000 [18:51:41<5:56:42,  1.71it/s]Step... (63400 / 100000 | Loss: 0.8170556426048279, Learning Rate: 3.678391959798995e-05)
+
                                                                             
Step... (63400 / 100000 | Loss: 0.652092456817627, Learning Rate: 3.678391959798995e-05)
+
Train steps ... :  63%|██████▎   | 63400/100000 [18:51:41<5:56:42,  1.71it/s]
Train steps ... :  63%|██████▎   | 63401/100000 [18:51:41<5:56:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 63402/100000 [18:51:42<5:56:40,  1.71it/s]
Train steps ... :  63%|██████▎   | 63403/100000 [18:51:43<5:56:22,  1.71it/s]
Train steps ... :  63%|██████▎   | 63404/100000 [18:51:43<5:56:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 63405/100000 [18:51:44<5:56:09,  1.71it/s]
Train steps ... :  63%|██████▎   | 63406/100000 [18:51:44<5:56:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 63407/100000 [18:51:45<5:56:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 63408/100000 [18:51:46<5:56:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 63409/100000 [18:51:46<5:56:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 63410/100000 [18:51:47<5:56:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 63411/100000 [18:51:47<5:56:39,  1.71it/s]
Train steps ... :  63%|██████▎   | 63412/100000 [18:51:48<5:56:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 63413/100000 [18:51:48<5:57:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63414/100000 [18:51:49<5:57:56,  1.70it/s]
Train steps ... :  63%|██████▎   | 63415/100000 [18:51:50<5:57:10,  1.71it/s]
Train steps ... :  63%|██████▎   | 63416/100000 [18:51:50<5:57:42,  1.70it/s]
Train steps ... :  63%|██████▎   | 63417/100000 [18:51:51<5:56:50,  1.71it/s]
Train steps ... :  63%|██████▎   | 63418/100000 [18:51:51<5:56:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63419/100000 [18:51:52<5:56:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 63420/100000 [18:51:53<5:56:19,  1.71it/s]
Train steps ... :  63%|██████▎   | 63421/100000 [18:51:53<5:56:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 63422/100000 [18:51:54<5:56:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63423/100000 [18:51:54<5:56:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 63424/100000 [18:51:55<5:56:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63425/100000 [18:51:55<5:56:34,  1.71it/s]Step... (63425 / 100000 | Loss: 0.6354853510856628, Learning Rate: 3.675879396984925e-05)
+
                                                                             
Step... (63425 / 100000 | Loss: 0.7891998291015625, Learning Rate: 3.675879396984925e-05)
+
Train steps ... :  63%|██████▎   | 63425/100000 [18:51:56<5:56:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63426/100000 [18:51:56<5:56:28,  1.71it/s]
Train steps ... :  63%|██████▎   | 63427/100000 [18:51:57<5:56:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63428/100000 [18:51:57<5:56:31,  1.71it/s]
Train steps ... :  63%|██████▎   | 63429/100000 [18:51:58<5:56:22,  1.71it/s]
Train steps ... :  63%|██████▎   | 63430/100000 [18:51:58<5:56:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63431/100000 [18:51:59<5:56:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 63432/100000 [18:52:00<5:56:36,  1.71it/s]
Train steps ... :  63%|██████▎   | 63433/100000 [18:52:00<5:56:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63434/100000 [18:52:01<5:56:14,  1.71it/s]
Train steps ... :  63%|██████▎   | 63435/100000 [18:52:01<5:56:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 63436/100000 [18:52:02<5:56:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 63437/100000 [18:52:02<5:56:15,  1.71it/s]
Train steps ... :  63%|██████▎   | 63438/100000 [18:52:03<5:56:13,  1.71it/s]
Train steps ... :  63%|██████▎   | 63439/100000 [18:52:04<5:56:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 63440/100000 [18:52:04<5:55:57,  1.71it/s]
Train steps ... :  63%|██████▎   | 63441/100000 [18:52:05<5:56:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 63442/100000 [18:52:05<5:56:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 63443/100000 [18:52:06<5:56:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63444/100000 [18:52:07<5:56:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 63445/100000 [18:52:07<5:56:43,  1.71it/s]
Train steps ... :  63%|██████▎   | 63446/100000 [18:52:08<5:56:38,  1.71it/s]
Train steps ... :  63%|██████▎   | 63447/100000 [18:52:08<5:56:33,  1.71it/s]
Train steps ... :  63%|██████▎   | 63448/100000 [18:52:09<5:56:17,  1.71it/s]
Train steps ... :  63%|██████▎   | 63449/100000 [18:52:10<5:56:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 63450/100000 [18:52:10<5:56:35,  1.71it/s]Step... (63450 / 100000 | Loss: 0.7283979654312134, Learning Rate: 3.6733668341708544e-05)
+
                                                                             
Step... (63450 / 100000 | Loss: 1.1754099130630493, Learning Rate: 3.6733668341708544e-05)
+
Train steps ... :  63%|██████▎   | 63450/100000 [18:52:10<5:56:35,  1.71it/s]
Train steps ... :  63%|██████▎   | 63451/100000 [18:52:11<5:56:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63452/100000 [18:52:11<5:56:11,  1.71it/s]
Train steps ... :  63%|██████▎   | 63453/100000 [18:52:12<5:56:08,  1.71it/s]
Train steps ... :  63%|██████▎   | 63454/100000 [18:52:12<5:55:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 63455/100000 [18:52:13<5:55:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63456/100000 [18:52:14<5:56:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 63457/100000 [18:52:14<5:55:54,  1.71it/s]
Train steps ... :  63%|██████▎   | 63458/100000 [18:52:15<5:55:52,  1.71it/s]
Train steps ... :  63%|██████▎   | 63459/100000 [18:52:15<5:55:46,  1.71it/s]
Train steps ... :  63%|██████▎   | 63460/100000 [18:52:16<5:56:09,  1.71it/s]
Train steps ... :  63%|██████▎   | 63461/100000 [18:52:17<5:56:22,  1.71it/s]
Train steps ... :  63%|██████▎   | 63462/100000 [18:52:17<5:55:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 63463/100000 [18:52:18<5:56:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 63464/100000 [18:52:18<5:56:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63465/100000 [18:52:19<5:55:51,  1.71it/s]
Train steps ... :  63%|██████▎   | 63466/100000 [18:52:19<5:56:18,  1.71it/s]
Train steps ... :  63%|██████▎   | 63467/100000 [18:52:20<5:56:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63468/100000 [18:52:21<5:56:27,  1.71it/s]
Train steps ... :  63%|██████▎   | 63469/100000 [18:52:21<5:56:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 63470/100000 [18:52:22<5:55:55,  1.71it/s]
Train steps ... :  63%|██████▎   | 63471/100000 [18:52:22<5:56:16,  1.71it/s]
Train steps ... :  63%|██████▎   | 63472/100000 [18:52:23<5:56:20,  1.71it/s]
Train steps ... :  63%|██████▎   | 63473/100000 [18:52:24<5:55:58,  1.71it/s]
Train steps ... :  63%|██████▎   | 63474/100000 [18:52:24<5:55:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63475/100000 [18:52:25<5:56:03,  1.71it/s]Step... (63475 / 100000 | Loss: 0.5472143888473511, Learning Rate: 3.670854271356784e-05)
+
                                                                             
Step... (63475 / 100000 | Loss: 0.8236969113349915, Learning Rate: 3.670854271356784e-05)
+
Train steps ... :  63%|██████▎   | 63475/100000 [18:52:25<5:56:03,  1.71it/s]
Train steps ... :  63%|██████▎   | 63476/100000 [18:52:25<5:55:49,  1.71it/s]
Train steps ... :  63%|██████▎   | 63477/100000 [18:52:26<5:55:30,  1.71it/s]
Train steps ... :  63%|██████▎   | 63478/100000 [18:52:26<5:55:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63479/100000 [18:52:27<5:55:05,  1.71it/s]
Train steps ... :  63%|██████▎   | 63480/100000 [18:52:28<5:55:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63481/100000 [18:52:28<5:55:34,  1.71it/s]
Train steps ... :  63%|██████▎   | 63482/100000 [18:52:29<5:55:32,  1.71it/s]
Train steps ... :  63%|██████▎   | 63483/100000 [18:52:29<5:55:56,  1.71it/s]
Train steps ... :  63%|██████▎   | 63484/100000 [18:52:30<5:56:09,  1.71it/s]
Train steps ... :  63%|██████▎   | 63485/100000 [18:52:31<5:56:06,  1.71it/s]
Train steps ... :  63%|██████▎   | 63486/100000 [18:52:31<5:55:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 63487/100000 [18:52:32<5:55:48,  1.71it/s]
Train steps ... :  63%|██████▎   | 63488/100000 [18:52:32<5:55:37,  1.71it/s]
Train steps ... :  63%|██████▎   | 63489/100000 [18:52:33<5:55:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 63490/100000 [18:52:33<5:55:21,  1.71it/s]
Train steps ... :  63%|██████▎   | 63491/100000 [18:52:34<5:55:23,  1.71it/s]
Train steps ... :  63%|██████▎   | 63492/100000 [18:52:35<5:55:12,  1.71it/s]
Train steps ... :  63%|██████▎   | 63493/100000 [18:52:35<5:56:02,  1.71it/s]
Train steps ... :  63%|██████▎   | 63494/100000 [18:52:36<5:55:41,  1.71it/s]
Train steps ... :  63%|██████▎   | 63495/100000 [18:52:36<5:55:47,  1.71it/s]
Train steps ... :  63%|██████▎   | 63496/100000 [18:52:37<5:55:44,  1.71it/s]
Train steps ... :  63%|██████▎   | 63497/100000 [18:52:38<5:55:25,  1.71it/s]
Train steps ... :  63%|██████▎   | 63498/100000 [18:52:38<5:56:04,  1.71it/s]
Train steps ... :  63%|██████▎   | 63499/100000 [18:52:39<5:55:53,  1.71it/s]
Train steps ... :  64%|██████▎   | 63500/100000 [18:52:39<5:55:55,  1.71it/s]Step... (63500 / 100000 | Loss: 0.8299074172973633, Learning Rate: 3.668341708542714e-05)
+
                                                                             
Step... (63500 / 100000 | Loss: 0.7070842981338501, Learning Rate: 3.668341708542714e-05)
+
Train steps ... :  64%|██████▎   | 63500/100000 [18:52:40<5:55:55,  1.71it/s]
Train steps ... :  64%|██████▎   | 63501/100000 [18:52:40<5:56:00,  1.71it/s]
Train steps ... :  64%|██████▎   | 63502/100000 [18:52:40<5:55:24,  1.71it/s]
Train steps ... :  64%|██████▎   | 63503/100000 [18:52:41<5:55:10,  1.71it/s]
Train steps ... :  64%|██████▎   | 63504/100000 [18:52:42<5:55:30,  1.71it/s]
Train steps ... :  64%|██████▎   | 63505/100000 [18:52:42<5:55:42,  1.71it/s]
Train steps ... :  64%|██████▎   | 63506/100000 [18:52:43<5:55:27,  1.71it/s]
Train steps ... :  64%|██████▎   | 63507/100000 [18:52:43<5:55:19,  1.71it/s]
Train steps ... :  64%|██████▎   | 63508/100000 [18:52:44<5:55:23,  1.71it/s]
Train steps ... :  64%|██████▎   | 63509/100000 [18:52:45<5:55:13,  1.71it/s]
Train steps ... :  64%|██████▎   | 63510/100000 [18:52:45<5:55:20,  1.71it/s]
Train steps ... :  64%|██████▎   | 63511/100000 [18:52:46<5:55:14,  1.71it/s]
Train steps ... :  64%|██████▎   | 63512/100000 [18:52:46<5:55:04,  1.71it/s]
Train steps ... :  64%|██████▎   | 63513/100000 [18:52:47<5:55:24,  1.71it/s]
Train steps ... :  64%|██████▎   | 63514/100000 [18:52:48<5:55:07,  1.71it/s]
Train steps ... :  64%|██████▎   | 63515/100000 [18:52:48<5:55:30,  1.71it/s]
Train steps ... :  64%|██████▎   | 63516/100000 [18:52:49<5:56:13,  1.71it/s]
Train steps ... :  64%|██████▎   | 63517/100000 [18:52:49<5:55:37,  1.71it/s]
Train steps ... :  64%|██████▎   | 63518/100000 [18:52:50<5:55:24,  1.71it/s]
Train steps ... :  64%|██████▎   | 63519/100000 [18:52:50<5:55:43,  1.71it/s]
Train steps ... :  64%|██████▎   | 63520/100000 [18:52:51<5:55:30,  1.71it/s]
Train steps ... :  64%|██████▎   | 63521/100000 [18:52:52<5:55:21,  1.71it/s]
Train steps ... :  64%|██████▎   | 63522/100000 [18:52:52<5:55:12,  1.71it/s]
Train steps ... :  64%|██████▎   | 63523/100000 [18:52:53<5:55:05,  1.71it/s]
Train steps ... :  64%|██████▎   | 63524/100000 [18:52:53<5:55:07,  1.71it/s]
Train steps ... :  64%|██████▎   | 63525/100000 [18:52:54<5:55:03,  1.71it/s]Step... (63525 / 100000 | Loss: 0.9065272808074951, Learning Rate: 3.6658291457286434e-05)
+
                                                                             
Step... (63525 / 100000 | Loss: 0.6592003107070923, Learning Rate: 3.6658291457286434e-05)
+
Train steps ... :  64%|██████▎   | 63525/100000 [18:52:54<5:55:03,  1.71it/s]
Train steps ... :  64%|██████▎   | 63526/100000 [18:52:55<5:55:08,  1.71it/s]
Train steps ... :  64%|██████▎   | 63527/100000 [18:52:55<5:55:14,  1.71it/s]
Train steps ... :  64%|██████▎   | 63528/100000 [18:52:56<5:55:10,  1.71it/s]
Train steps ... :  64%|██████▎   | 63529/100000 [18:52:56<5:55:39,  1.71it/s]
Train steps ... :  64%|██████▎   | 63530/100000 [18:52:57<5:55:15,  1.71it/s]
Train steps ... :  64%|██████▎   | 63531/100000 [18:52:57<5:55:54,  1.71it/s]
Train steps ... :  64%|██████▎   | 63532/100000 [18:52:58<5:55:36,  1.71it/s]
Train steps ... :  64%|██████▎   | 63533/100000 [18:52:59<5:55:36,  1.71it/s]
Train steps ... :  64%|██████▎   | 63534/100000 [18:52:59<5:55:44,  1.71it/s]
Train steps ... :  64%|██████▎   | 63535/100000 [18:53:00<5:56:04,  1.71it/s]
Train steps ... :  64%|██████▎   | 63536/100000 [18:53:00<5:56:04,  1.71it/s]
Train steps ... :  64%|██████▎   | 63537/100000 [18:53:01<5:56:06,  1.71it/s]
Train steps ... :  64%|██████▎   | 63538/100000 [18:53:02<5:56:06,  1.71it/s]
Train steps ... :  64%|██████▎   | 63539/100000 [18:53:02<5:56:06,  1.71it/s]
Train steps ... :  64%|██████▎   | 63540/100000 [18:53:03<5:55:45,  1.71it/s]
Train steps ... :  64%|██████▎   | 63541/100000 [18:53:03<5:55:57,  1.71it/s]
Train steps ... :  64%|██████▎   | 63542/100000 [18:53:04<5:55:43,  1.71it/s]
Train steps ... :  64%|██████▎   | 63543/100000 [18:53:04<5:55:57,  1.71it/s]
Train steps ... :  64%|██████▎   | 63544/100000 [18:53:05<5:56:02,  1.71it/s]
Train steps ... :  64%|██████▎   | 63545/100000 [18:53:06<5:55:53,  1.71it/s]
Train steps ... :  64%|██████▎   | 63546/100000 [18:53:06<5:56:49,  1.70it/s]
Train steps ... :  64%|██████▎   | 63547/100000 [18:53:07<5:56:02,  1.71it/s]
Train steps ... :  64%|██████▎   | 63548/100000 [18:53:07<5:56:30,  1.70it/s]
Train steps ... :  64%|██████▎   | 63549/100000 [18:53:08<5:55:32,  1.71it/s]
Train steps ... :  64%|██████▎   | 63550/100000 [18:53:09<5:55:33,  1.71it/s]Step... (63550 / 100000 | Loss: 0.7508991956710815, Learning Rate: 3.663316582914573e-05)
+
                                                                             
Step... (63550 / 100000 | Loss: 0.7484855651855469, Learning Rate: 3.663316582914573e-05)
+
Train steps ... :  64%|██████▎   | 63550/100000 [18:53:09<5:55:33,  1.71it/s]
Train steps ... :  64%|██████▎   | 63551/100000 [18:53:09<5:55:35,  1.71it/s]
Train steps ... :  64%|██████▎   | 63552/100000 [18:53:10<5:55:29,  1.71it/s]
Train steps ... :  64%|██████▎   | 63553/100000 [18:53:10<5:55:03,  1.71it/s]
Train steps ... :  64%|██████▎   | 63554/100000 [18:53:11<5:54:48,  1.71it/s]
Train steps ... :  64%|██████▎   | 63555/100000 [18:53:11<5:55:21,  1.71it/s]
Train steps ... :  64%|██████▎   | 63556/100000 [18:53:12<5:55:02,  1.71it/s]
Train steps ... :  64%|██████▎   | 63557/100000 [18:53:13<5:54:51,  1.71it/s]
Train steps ... :  64%|██████▎   | 63558/100000 [18:53:13<5:55:10,  1.71it/s]
Train steps ... :  64%|██████▎   | 63559/100000 [18:53:14<5:55:17,  1.71it/s]
Train steps ... :  64%|██████▎   | 63560/100000 [18:53:14<5:55:25,  1.71it/s]
Train steps ... :  64%|██████▎   | 63561/100000 [18:53:15<5:55:03,  1.71it/s]
Train steps ... :  64%|██████▎   | 63562/100000 [18:53:16<5:55:00,  1.71it/s]
Train steps ... :  64%|██████▎   | 63563/100000 [18:53:16<5:54:51,  1.71it/s]
Train steps ... :  64%|██████▎   | 63564/100000 [18:53:17<5:54:53,  1.71it/s]
Train steps ... :  64%|██████▎   | 63565/100000 [18:53:17<5:55:22,  1.71it/s]
Train steps ... :  64%|██████▎   | 63566/100000 [18:53:18<5:55:17,  1.71it/s]
Train steps ... :  64%|██████▎   | 63567/100000 [18:53:19<5:55:27,  1.71it/s]
Train steps ... :  64%|██████▎   | 63568/100000 [18:53:19<5:55:38,  1.71it/s]
Train steps ... :  64%|██████▎   | 63569/100000 [18:53:20<5:55:13,  1.71it/s]
Train steps ... :  64%|██████▎   | 63570/100000 [18:53:20<5:55:23,  1.71it/s]
Train steps ... :  64%|██████▎   | 63571/100000 [18:53:21<5:54:51,  1.71it/s]
Train steps ... :  64%|██████▎   | 63572/100000 [18:53:21<5:54:45,  1.71it/s]
Train steps ... :  64%|██████▎   | 63573/100000 [18:53:22<5:54:36,  1.71it/s]
Train steps ... :  64%|██████▎   | 63574/100000 [18:53:23<5:54:56,  1.71it/s]
Train steps ... :  64%|██████▎   | 63575/100000 [18:53:23<5:54:42,  1.71it/s]Step... (63575 / 100000 | Loss: 0.7872081398963928, Learning Rate: 3.660804020100503e-05)
+
                                                                             
Step... (63575 / 100000 | Loss: 0.8553804159164429, Learning Rate: 3.660804020100503e-05)
+
Train steps ... :  64%|██████▎   | 63575/100000 [18:53:24<5:54:42,  1.71it/s]
Train steps ... :  64%|██████▎   | 63576/100000 [18:53:24<5:54:42,  1.71it/s]
Train steps ... :  64%|██████▎   | 63577/100000 [18:53:24<5:54:42,  1.71it/s]
Train steps ... :  64%|██████▎   | 63578/100000 [18:53:25<5:54:28,  1.71it/s]
Train steps ... :  64%|██████▎   | 63579/100000 [18:53:26<5:54:40,  1.71it/s]
Train steps ... :  64%|██████▎   | 63580/100000 [18:53:26<5:54:23,  1.71it/s]
Train steps ... :  64%|██████▎   | 63581/100000 [18:53:27<5:54:47,  1.71it/s]
Train steps ... :  64%|██████▎   | 63582/100000 [18:53:27<5:54:59,  1.71it/s]
Train steps ... :  64%|██████▎   | 63583/100000 [18:53:28<5:55:25,  1.71it/s]
Train steps ... :  64%|██████▎   | 63584/100000 [18:53:28<5:55:44,  1.71it/s]
Train steps ... :  64%|██████▎   | 63585/100000 [18:53:29<5:55:25,  1.71it/s]
Train steps ... :  64%|██████▎   | 63586/100000 [18:53:30<5:54:53,  1.71it/s]
Train steps ... :  64%|██████▎   | 63587/100000 [18:53:30<5:54:52,  1.71it/s]
Train steps ... :  64%|██████▎   | 63588/100000 [18:53:31<5:55:27,  1.71it/s]
Train steps ... :  64%|██████▎   | 63589/100000 [18:53:31<5:55:10,  1.71it/s]
Train steps ... :  64%|██████▎   | 63590/100000 [18:53:32<5:55:26,  1.71it/s]
Train steps ... :  64%|██████▎   | 63591/100000 [18:53:33<5:55:07,  1.71it/s]
Train steps ... :  64%|██████▎   | 63592/100000 [18:53:33<5:55:19,  1.71it/s]
Train steps ... :  64%|██████▎   | 63593/100000 [18:53:34<5:54:58,  1.71it/s]
Train steps ... :  64%|██████▎   | 63594/100000 [18:53:34<5:54:53,  1.71it/s]
Train steps ... :  64%|██████▎   | 63595/100000 [18:53:35<5:54:41,  1.71it/s]
Train steps ... :  64%|██████▎   | 63596/100000 [18:53:35<5:54:44,  1.71it/s]
Train steps ... :  64%|██████▎   | 63597/100000 [18:53:36<5:54:33,  1.71it/s]
Train steps ... :  64%|██████▎   | 63598/100000 [18:53:37<5:55:00,  1.71it/s]
Train steps ... :  64%|██████▎   | 63599/100000 [18:53:37<5:54:26,  1.71it/s]
Train steps ... :  64%|██████▎   | 63600/100000 [18:53:38<5:54:34,  1.71it/s]Step... (63600 / 100000 | Loss: 0.7533707618713379, Learning Rate: 3.658291457286432e-05)
+
                                                                             
Step... (63600 / 100000 | Loss: 1.0083177089691162, Learning Rate: 3.658291457286432e-05)
+
Train steps ... :  64%|██████▎   | 63600/100000 [18:53:38<5:54:34,  1.71it/s]
Train steps ... :  64%|██████▎   | 63601/100000 [18:53:38<5:54:26,  1.71it/s]
Train steps ... :  64%|██████▎   | 63602/100000 [18:53:39<5:54:39,  1.71it/s]
Train steps ... :  64%|██████▎   | 63603/100000 [18:53:40<5:54:19,  1.71it/s]
Train steps ... :  64%|██████▎   | 63604/100000 [18:53:40<5:54:17,  1.71it/s]
Train steps ... :  64%|██████▎   | 63605/100000 [18:53:41<5:54:58,  1.71it/s]
Train steps ... :  64%|██████▎   | 63606/100000 [18:53:41<5:55:16,  1.71it/s]
Train steps ... :  64%|██████▎   | 63607/100000 [18:53:42<5:55:07,  1.71it/s]
Train steps ... :  64%|██████▎   | 63608/100000 [18:53:42<5:54:45,  1.71it/s]
Train steps ... :  64%|██████▎   | 63609/100000 [18:53:43<5:54:31,  1.71it/s]
Train steps ... :  64%|██████▎   | 63610/100000 [18:53:44<5:54:28,  1.71it/s]
Train steps ... :  64%|██████▎   | 63611/100000 [18:53:44<5:54:46,  1.71it/s]
Train steps ... :  64%|██████▎   | 63612/100000 [18:53:45<5:54:42,  1.71it/s]
Train steps ... :  64%|██████▎   | 63613/100000 [18:53:45<5:54:42,  1.71it/s]
Train steps ... :  64%|██████▎   | 63614/100000 [18:53:46<5:54:37,  1.71it/s]
Train steps ... :  64%|██████▎   | 63615/100000 [18:53:47<5:54:50,  1.71it/s]
Train steps ... :  64%|██████▎   | 63616/100000 [18:53:47<5:54:40,  1.71it/s]
Train steps ... :  64%|██████▎   | 63617/100000 [18:53:48<5:55:05,  1.71it/s]
Train steps ... :  64%|██████▎   | 63618/100000 [18:53:48<5:55:20,  1.71it/s]
Train steps ... :  64%|██████▎   | 63619/100000 [18:53:49<5:55:33,  1.71it/s]
Train steps ... :  64%|██████▎   | 63620/100000 [18:53:50<5:55:40,  1.70it/s]
Train steps ... :  64%|██████▎   | 63621/100000 [18:53:50<5:55:16,  1.71it/s]
Train steps ... :  64%|██████▎   | 63622/100000 [18:53:51<5:55:16,  1.71it/s]
Train steps ... :  64%|██████▎   | 63623/100000 [18:53:51<5:54:49,  1.71it/s]
Train steps ... :  64%|██████▎   | 63624/100000 [18:53:52<5:54:35,  1.71it/s]
Train steps ... :  64%|██████▎   | 63625/100000 [18:53:52<5:54:33,  1.71it/s]Step... (63625 / 100000 | Loss: 0.8122715353965759, Learning Rate: 3.655778894472362e-05)
+
                                                                             
Step... (63625 / 100000 | Loss: 0.6018719673156738, Learning Rate: 3.655778894472362e-05)
+
Train steps ... :  64%|██████▎   | 63625/100000 [18:53:53<5:54:33,  1.71it/s]
Train steps ... :  64%|██████▎   | 63626/100000 [18:53:53<5:54:39,  1.71it/s]
Train steps ... :  64%|██████▎   | 63627/100000 [18:53:54<5:54:45,  1.71it/s]
Train steps ... :  64%|██████▎   | 63628/100000 [18:53:54<5:54:29,  1.71it/s]
Train steps ... :  64%|██████▎   | 63629/100000 [18:53:55<5:54:18,  1.71it/s]
Train steps ... :  64%|██████▎   | 63630/100000 [18:53:55<5:54:16,  1.71it/s]
Train steps ... :  64%|██████▎   | 63631/100000 [18:53:56<5:54:24,  1.71it/s]
Train steps ... :  64%|██████▎   | 63632/100000 [18:53:57<5:55:14,  1.71it/s]
Train steps ... :  64%|██████▎   | 63633/100000 [18:53:57<5:54:57,  1.71it/s]
Train steps ... :  64%|██████▎   | 63634/100000 [18:53:58<5:55:31,  1.70it/s]
Train steps ... :  64%|██████▎   | 63635/100000 [18:53:58<5:54:47,  1.71it/s]
Train steps ... :  64%|██████▎   | 63636/100000 [18:53:59<5:54:32,  1.71it/s]
Train steps ... :  64%|██████▎   | 63637/100000 [18:53:59<5:54:12,  1.71it/s]
Train steps ... :  64%|██████▎   | 63638/100000 [18:54:00<5:54:07,  1.71it/s]
Train steps ... :  64%|██████▎   | 63639/100000 [18:54:01<5:55:14,  1.71it/s]
Train steps ... :  64%|██████▎   | 63640/100000 [18:54:01<5:54:50,  1.71it/s]
Train steps ... :  64%|██████▎   | 63641/100000 [18:54:02<5:54:52,  1.71it/s]
Train steps ... :  64%|██████▎   | 63642/100000 [18:54:02<5:55:05,  1.71it/s]
Train steps ... :  64%|██████▎   | 63643/100000 [18:54:03<5:54:29,  1.71it/s]
Train steps ... :  64%|██████▎   | 63644/100000 [18:54:04<5:55:06,  1.71it/s]
Train steps ... :  64%|██████▎   | 63645/100000 [18:54:04<5:54:52,  1.71it/s]
Train steps ... :  64%|██████▎   | 63646/100000 [18:54:05<5:54:26,  1.71it/s]
Train steps ... :  64%|██████▎   | 63647/100000 [18:54:05<5:54:23,  1.71it/s]
Train steps ... :  64%|██████▎   | 63648/100000 [18:54:06<5:54:35,  1.71it/s]
Train steps ... :  64%|██████▎   | 63649/100000 [18:54:06<5:54:25,  1.71it/s]
Train steps ... :  64%|██████▎   | 63650/100000 [18:54:07<5:54:18,  1.71it/s]Step... (63650 / 100000 | Loss: 0.6303397417068481, Learning Rate: 3.653266331658292e-05)
+
                                                                             
Step... (63650 / 100000 | Loss: 0.7107402086257935, Learning Rate: 3.653266331658292e-05)
+
Train steps ... :  64%|██████▎   | 63650/100000 [18:54:07<5:54:18,  1.71it/s]
Train steps ... :  64%|██████▎   | 63651/100000 [18:54:08<5:54:24,  1.71it/s]
Train steps ... :  64%|██████▎   | 63652/100000 [18:54:08<5:54:29,  1.71it/s]
Train steps ... :  64%|██████▎   | 63653/100000 [18:54:09<5:55:30,  1.70it/s]
Train steps ... :  64%|██████▎   | 63654/100000 [18:54:09<5:54:24,  1.71it/s]
Train steps ... :  64%|██████▎   | 63655/100000 [18:54:10<5:56:26,  1.70it/s]
Train steps ... :  64%|██████▎   | 63656/100000 [18:54:11<5:55:51,  1.70it/s]
Train steps ... :  64%|██████▎   | 63657/100000 [18:54:11<5:56:22,  1.70it/s]
Train steps ... :  64%|██████▎   | 63658/100000 [18:54:12<5:55:38,  1.70it/s]
Train steps ... :  64%|██████▎   | 63659/100000 [18:54:12<5:55:56,  1.70it/s]
Train steps ... :  64%|██████▎   | 63660/100000 [18:54:13<5:55:15,  1.70it/s]
Train steps ... :  64%|██████▎   | 63661/100000 [18:54:14<5:55:59,  1.70it/s]
Train steps ... :  64%|██████▎   | 63662/100000 [18:54:14<5:56:04,  1.70it/s]
Train steps ... :  64%|██████▎   | 63663/100000 [18:54:15<5:55:31,  1.70it/s]
Train steps ... :  64%|██████▎   | 63664/100000 [18:54:15<5:55:01,  1.71it/s]
Train steps ... :  64%|██████▎   | 63665/100000 [18:54:16<5:54:35,  1.71it/s]
Train steps ... :  64%|██████▎   | 63666/100000 [18:54:16<5:54:13,  1.71it/s]
Train steps ... :  64%|██████▎   | 63667/100000 [18:54:17<5:54:56,  1.71it/s]
Train steps ... :  64%|██████▎   | 63668/100000 [18:54:18<5:54:14,  1.71it/s]
Train steps ... :  64%|██████▎   | 63669/100000 [18:54:18<5:53:58,  1.71it/s]
Train steps ... :  64%|██████▎   | 63670/100000 [18:54:19<5:54:46,  1.71it/s]
Train steps ... :  64%|██████▎   | 63671/100000 [18:54:19<5:54:19,  1.71it/s]
Train steps ... :  64%|██████▎   | 63672/100000 [18:54:20<5:53:52,  1.71it/s]
Train steps ... :  64%|██████▎   | 63673/100000 [18:54:21<5:53:54,  1.71it/s]
Train steps ... :  64%|██████▎   | 63674/100000 [18:54:21<5:53:50,  1.71it/s]
Train steps ... :  64%|██████▎   | 63675/100000 [18:54:22<5:53:45,  1.71it/s]Step... (63675 / 100000 | Loss: 0.761788547039032, Learning Rate: 3.650753768844221e-05)
+
                                                                             
Step... (63675 / 100000 | Loss: 0.7985420227050781, Learning Rate: 3.650753768844221e-05)
+
Train steps ... :  64%|██████▎   | 63675/100000 [18:54:22<5:53:45,  1.71it/s]
Train steps ... :  64%|██████▎   | 63676/100000 [18:54:22<5:54:05,  1.71it/s]
Train steps ... :  64%|██████▎   | 63677/100000 [18:54:23<5:53:36,  1.71it/s]
Train steps ... :  64%|██████▎   | 63678/100000 [18:54:23<5:53:22,  1.71it/s]
Train steps ... :  64%|██████▎   | 63679/100000 [18:54:24<5:53:45,  1.71it/s]
Train steps ... :  64%|██████▎   | 63680/100000 [18:54:25<5:53:49,  1.71it/s]
Train steps ... :  64%|██████▎   | 63681/100000 [18:54:25<5:53:34,  1.71it/s]
Train steps ... :  64%|██████▎   | 63682/100000 [18:54:26<5:53:34,  1.71it/s]
Train steps ... :  64%|██████▎   | 63683/100000 [18:54:26<5:53:28,  1.71it/s]
Train steps ... :  64%|██████▎   | 63684/100000 [18:54:27<5:53:23,  1.71it/s]
Train steps ... :  64%|██████▎   | 63685/100000 [18:54:28<5:53:23,  1.71it/s]
Train steps ... :  64%|██████▎   | 63686/100000 [18:54:28<5:53:33,  1.71it/s]
Train steps ... :  64%|██████▎   | 63687/100000 [18:54:29<5:53:55,  1.71it/s]
Train steps ... :  64%|██████▎   | 63688/100000 [18:54:29<5:53:56,  1.71it/s]
Train steps ... :  64%|██████▎   | 63689/100000 [18:54:30<5:54:25,  1.71it/s]
Train steps ... :  64%|██████▎   | 63690/100000 [18:54:30<5:53:29,  1.71it/s]
Train steps ... :  64%|██████▎   | 63691/100000 [18:54:31<5:53:41,  1.71it/s]
Train steps ... :  64%|██████▎   | 63692/100000 [18:54:32<5:53:42,  1.71it/s]
Train steps ... :  64%|██████▎   | 63693/100000 [18:54:32<5:53:31,  1.71it/s]
Train steps ... :  64%|██████▎   | 63694/100000 [18:54:33<5:53:20,  1.71it/s]
Train steps ... :  64%|██████▎   | 63695/100000 [18:54:33<5:53:17,  1.71it/s]
Train steps ... :  64%|██████▎   | 63696/100000 [18:54:34<5:54:01,  1.71it/s]
Train steps ... :  64%|██████▎   | 63697/100000 [18:54:35<5:53:47,  1.71it/s]
Train steps ... :  64%|██████▎   | 63698/100000 [18:54:35<5:53:52,  1.71it/s]
Train steps ... :  64%|██████▎   | 63699/100000 [18:54:36<5:53:48,  1.71it/s]
Train steps ... :  64%|██████▎   | 63700/100000 [18:54:36<5:54:03,  1.71it/s]Step... (63700 / 100000 | Loss: 0.538968026638031, Learning Rate: 3.648241206030151e-05)
+
                                                                             
Step... (63700 / 100000 | Loss: 0.8885844349861145, Learning Rate: 3.648241206030151e-05)
+
Train steps ... :  64%|██████▎   | 63700/100000 [18:54:37<5:54:03,  1.71it/s]
Train steps ... :  64%|██████▎   | 63701/100000 [18:54:37<5:54:08,  1.71it/s]
Train steps ... :  64%|██████▎   | 63702/100000 [18:54:38<5:54:09,  1.71it/s]
Train steps ... :  64%|██████▎   | 63703/100000 [18:54:38<5:53:36,  1.71it/s]
Train steps ... :  64%|██████▎   | 63704/100000 [18:54:39<5:54:15,  1.71it/s]
Train steps ... :  64%|██████▎   | 63705/100000 [18:54:39<5:53:58,  1.71it/s]
Train steps ... :  64%|██████▎   | 63706/100000 [18:54:40<5:54:01,  1.71it/s]
Train steps ... :  64%|██████▎   | 63707/100000 [18:54:40<5:54:03,  1.71it/s]
Train steps ... :  64%|██████▎   | 63708/100000 [18:54:41<5:53:40,  1.71it/s]
Train steps ... :  64%|██████▎   | 63709/100000 [18:54:42<5:53:25,  1.71it/s]
Train steps ... :  64%|██████▎   | 63710/100000 [18:54:42<5:53:29,  1.71it/s]
Train steps ... :  64%|██████▎   | 63711/100000 [18:54:43<5:53:38,  1.71it/s]
Train steps ... :  64%|██████▎   | 63712/100000 [18:54:43<5:53:41,  1.71it/s]
Train steps ... :  64%|██████▎   | 63713/100000 [18:54:44<5:53:24,  1.71it/s]
Train steps ... :  64%|██████▎   | 63714/100000 [18:54:45<5:53:26,  1.71it/s]
Train steps ... :  64%|██████▎   | 63715/100000 [18:54:45<5:53:56,  1.71it/s]
Train steps ... :  64%|██████▎   | 63716/100000 [18:54:46<5:54:02,  1.71it/s]
Train steps ... :  64%|██████▎   | 63717/100000 [18:54:46<5:53:42,  1.71it/s]
Train steps ... :  64%|██████▎   | 63718/100000 [18:54:47<5:53:31,  1.71it/s]
Train steps ... :  64%|██████▎   | 63719/100000 [18:54:47<5:53:40,  1.71it/s]
Train steps ... :  64%|██████▎   | 63720/100000 [18:54:48<5:53:23,  1.71it/s]
Train steps ... :  64%|██████▎   | 63721/100000 [18:54:49<5:54:57,  1.70it/s]
Train steps ... :  64%|██████▎   | 63722/100000 [18:54:49<5:54:45,  1.70it/s]
Train steps ... :  64%|██████▎   | 63723/100000 [18:54:50<5:54:18,  1.71it/s]
Train steps ... :  64%|██████▎   | 63724/100000 [18:54:50<5:53:59,  1.71it/s]
Train steps ... :  64%|██████▎   | 63725/100000 [18:54:51<5:53:37,  1.71it/s]Step... (63725 / 100000 | Loss: 0.6761469841003418, Learning Rate: 3.6457286432160806e-05)
+
                                                                             
Step... (63725 / 100000 | Loss: 0.44804880023002625, Learning Rate: 3.6457286432160806e-05)
+
Train steps ... :  64%|██████▎   | 63725/100000 [18:54:51<5:53:37,  1.71it/s]
Train steps ... :  64%|██████▎   | 63726/100000 [18:54:52<5:53:39,  1.71it/s]
Train steps ... :  64%|██████▎   | 63727/100000 [18:54:52<5:53:19,  1.71it/s]
Train steps ... :  64%|██████▎   | 63728/100000 [18:54:53<5:53:17,  1.71it/s]
Train steps ... :  64%|██████▎   | 63729/100000 [18:54:53<5:53:11,  1.71it/s]
Train steps ... :  64%|██████▎   | 63730/100000 [18:54:54<5:53:01,  1.71it/s]
Train steps ... :  64%|██████▎   | 63731/100000 [18:54:54<5:52:54,  1.71it/s]
Train steps ... :  64%|██████▎   | 63732/100000 [18:54:55<5:52:52,  1.71it/s]
Train steps ... :  64%|██████▎   | 63733/100000 [18:54:56<5:52:43,  1.71it/s]
Train steps ... :  64%|██████▎   | 63734/100000 [18:54:56<5:52:54,  1.71it/s]
Train steps ... :  64%|██████▎   | 63735/100000 [18:54:57<5:52:54,  1.71it/s]
Train steps ... :  64%|██████▎   | 63736/100000 [18:54:57<5:52:43,  1.71it/s]
Train steps ... :  64%|██████▎   | 63737/100000 [18:54:58<5:52:51,  1.71it/s]
Train steps ... :  64%|██████▎   | 63738/100000 [18:54:59<5:53:19,  1.71it/s]
Train steps ... :  64%|██████▎   | 63739/100000 [18:54:59<5:53:12,  1.71it/s]
Train steps ... :  64%|██████▎   | 63740/100000 [18:55:00<5:53:39,  1.71it/s]
Train steps ... :  64%|██████▎   | 63741/100000 [18:55:00<5:53:16,  1.71it/s]
Train steps ... :  64%|██████▎   | 63742/100000 [18:55:01<5:53:17,  1.71it/s]
Train steps ... :  64%|██████▎   | 63743/100000 [18:55:01<5:53:13,  1.71it/s]
Train steps ... :  64%|██████▎   | 63744/100000 [18:55:02<5:53:24,  1.71it/s]
Train steps ... :  64%|██████▎   | 63745/100000 [18:55:03<5:53:09,  1.71it/s]
Train steps ... :  64%|██████▎   | 63746/100000 [18:55:03<5:52:58,  1.71it/s]
Train steps ... :  64%|██████▎   | 63747/100000 [18:55:04<5:53:15,  1.71it/s]
Train steps ... :  64%|██████▎   | 63748/100000 [18:55:04<5:53:01,  1.71it/s]
Train steps ... :  64%|██████▎   | 63749/100000 [18:55:05<5:53:22,  1.71it/s]
Train steps ... :  64%|██████▍   | 63750/100000 [18:55:06<5:53:01,  1.71it/s]Step... (63750 / 100000 | Loss: 0.7415693998336792, Learning Rate: 3.64321608040201e-05)
+
                                                                             
Step... (63750 / 100000 | Loss: 0.6799769401550293, Learning Rate: 3.64321608040201e-05)
+
Train steps ... :  64%|██████▍   | 63750/100000 [18:55:06<5:53:01,  1.71it/s]
Train steps ... :  64%|██████▍   | 63751/100000 [18:55:06<5:53:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 63752/100000 [18:55:07<5:53:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 63753/100000 [18:55:07<5:53:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 63754/100000 [18:55:08<5:53:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 63755/100000 [18:55:08<5:53:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 63756/100000 [18:55:09<5:53:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 63757/100000 [18:55:10<5:54:01,  1.71it/s]
Train steps ... :  64%|██████▍   | 63758/100000 [18:55:10<5:54:05,  1.71it/s]
Train steps ... :  64%|██████▍   | 63759/100000 [18:55:11<5:54:07,  1.71it/s]
Train steps ... :  64%|██████▍   | 63760/100000 [18:55:11<5:53:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 63761/100000 [18:55:12<5:53:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 63762/100000 [18:55:13<5:53:35,  1.71it/s]
Train steps ... :  64%|██████▍   | 63763/100000 [18:55:13<5:52:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 63764/100000 [18:55:14<5:52:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 63765/100000 [18:55:14<5:52:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 63766/100000 [18:55:15<5:53:07,  1.71it/s]
Train steps ... :  64%|██████▍   | 63767/100000 [18:55:16<5:52:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 63768/100000 [18:55:16<5:52:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 63769/100000 [18:55:17<5:53:05,  1.71it/s]
Train steps ... :  64%|██████▍   | 63770/100000 [18:55:17<5:53:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 63771/100000 [18:55:18<5:52:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 63772/100000 [18:55:18<5:52:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 63773/100000 [18:55:19<5:52:51,  1.71it/s]
Train steps ... :  64%|██████▍   | 63774/100000 [18:55:20<5:53:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 63775/100000 [18:55:20<5:53:34,  1.71it/s]Step... (63775 / 100000 | Loss: 0.7471785545349121, Learning Rate: 3.64070351758794e-05)
+
                                                                             
Step... (63775 / 100000 | Loss: 0.581433892250061, Learning Rate: 3.64070351758794e-05)
+
Train steps ... :  64%|██████▍   | 63775/100000 [18:55:21<5:53:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 63776/100000 [18:55:21<5:53:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 63777/100000 [18:55:21<5:52:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 63778/100000 [18:55:22<5:52:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 63779/100000 [18:55:23<5:52:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 63780/100000 [18:55:23<5:52:43,  1.71it/s]
Train steps ... :  64%|██████▍   | 63781/100000 [18:55:24<5:52:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 63782/100000 [18:55:24<5:52:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 63783/100000 [18:55:25<5:53:03,  1.71it/s]
Train steps ... :  64%|██████▍   | 63784/100000 [18:55:25<5:53:11,  1.71it/s]
Train steps ... :  64%|██████▍   | 63785/100000 [18:55:26<5:53:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 63786/100000 [18:55:27<5:53:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 63787/100000 [18:55:27<5:52:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 63788/100000 [18:55:28<5:53:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 63789/100000 [18:55:28<5:53:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 63790/100000 [18:55:29<5:53:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 63791/100000 [18:55:30<5:53:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 63792/100000 [18:55:30<5:53:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 63793/100000 [18:55:31<5:53:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 63794/100000 [18:55:31<5:53:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 63795/100000 [18:55:32<5:54:06,  1.70it/s]
Train steps ... :  64%|██████▍   | 63796/100000 [18:55:32<5:53:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 63797/100000 [18:55:33<5:53:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 63798/100000 [18:55:34<5:53:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 63799/100000 [18:55:34<5:53:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 63800/100000 [18:55:35<5:54:19,  1.70it/s]Step... (63800 / 100000 | Loss: 0.7017810344696045, Learning Rate: 3.6381909547738696e-05)
+
                                                                             
Step... (63800 / 100000 | Loss: 0.8094821572303772, Learning Rate: 3.6381909547738696e-05)
+
Train steps ... :  64%|██████▍   | 63800/100000 [18:55:35<5:54:19,  1.70it/s]
Train steps ... :  64%|██████▍   | 63801/100000 [18:55:35<5:55:20,  1.70it/s]
Train steps ... :  64%|██████▍   | 63802/100000 [18:55:36<5:53:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 63803/100000 [18:55:37<5:53:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 63804/100000 [18:55:37<5:52:52,  1.71it/s]
Train steps ... :  64%|██████▍   | 63805/100000 [18:55:38<5:52:36,  1.71it/s]
Train steps ... :  64%|██████▍   | 63806/100000 [18:55:38<5:53:14,  1.71it/s]
Train steps ... :  64%|██████▍   | 63807/100000 [18:55:39<5:53:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 63808/100000 [18:55:40<5:53:27,  1.71it/s]
Train steps ... :  64%|██████▍   | 63809/100000 [18:55:40<5:53:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 63810/100000 [18:55:41<5:52:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 63811/100000 [18:55:41<5:52:18,  1.71it/s]
Train steps ... :  64%|██████▍   | 63812/100000 [18:55:42<5:52:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 63813/100000 [18:55:42<5:52:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 63814/100000 [18:55:43<5:52:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 63815/100000 [18:55:44<5:53:15,  1.71it/s]
Train steps ... :  64%|██████▍   | 63816/100000 [18:55:44<5:52:52,  1.71it/s]
Train steps ... :  64%|██████▍   | 63817/100000 [18:55:45<5:52:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 63818/100000 [18:55:45<5:52:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 63819/100000 [18:55:46<5:53:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 63820/100000 [18:55:47<5:53:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 63821/100000 [18:55:47<5:52:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 63822/100000 [18:55:48<5:52:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 63823/100000 [18:55:48<5:52:52,  1.71it/s]
Train steps ... :  64%|██████▍   | 63824/100000 [18:55:49<5:52:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 63825/100000 [18:55:49<5:53:09,  1.71it/s]Step... (63825 / 100000 | Loss: 0.7423746585845947, Learning Rate: 3.635678391959799e-05)
+
                                                                             
Step... (63825 / 100000 | Loss: 0.5757318735122681, Learning Rate: 3.635678391959799e-05)
+
Train steps ... :  64%|██████▍   | 63825/100000 [18:55:50<5:53:09,  1.71it/s]
Train steps ... :  64%|██████▍   | 63826/100000 [18:55:50<5:53:32,  1.71it/s]
Train steps ... :  64%|██████▍   | 63827/100000 [18:55:51<5:53:08,  1.71it/s]
Train steps ... :  64%|██████▍   | 63828/100000 [18:55:51<5:52:24,  1.71it/s]
Train steps ... :  64%|██████▍   | 63829/100000 [18:55:52<5:52:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 63830/100000 [18:55:52<5:52:52,  1.71it/s]
Train steps ... :  64%|██████▍   | 63831/100000 [18:55:53<5:52:32,  1.71it/s]
Train steps ... :  64%|██████▍   | 63832/100000 [18:55:54<5:52:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 63833/100000 [18:55:54<5:53:17,  1.71it/s]
Train steps ... :  64%|██████▍   | 63834/100000 [18:55:55<5:52:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 63835/100000 [18:55:55<5:52:49,  1.71it/s]
Train steps ... :  64%|██████▍   | 63836/100000 [18:55:56<5:53:00,  1.71it/s]
Train steps ... :  64%|██████▍   | 63837/100000 [18:55:56<5:52:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 63838/100000 [18:55:57<5:53:02,  1.71it/s]
Train steps ... :  64%|██████▍   | 63839/100000 [18:55:58<5:52:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 63840/100000 [18:55:58<5:53:09,  1.71it/s]
Train steps ... :  64%|██████▍   | 63841/100000 [18:55:59<5:52:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 63842/100000 [18:55:59<5:52:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 63843/100000 [18:56:00<5:52:35,  1.71it/s]
Train steps ... :  64%|██████▍   | 63844/100000 [18:56:01<5:52:18,  1.71it/s]
Train steps ... :  64%|██████▍   | 63845/100000 [18:56:01<5:52:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 63846/100000 [18:56:02<5:52:08,  1.71it/s]
Train steps ... :  64%|██████▍   | 63847/100000 [18:56:02<5:53:05,  1.71it/s]
Train steps ... :  64%|██████▍   | 63848/100000 [18:56:03<5:52:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 63849/100000 [18:56:04<5:52:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 63850/100000 [18:56:04<5:52:56,  1.71it/s]Step... (63850 / 100000 | Loss: 0.7522145509719849, Learning Rate: 3.633165829145729e-05)
+
                                                                             
Step... (63850 / 100000 | Loss: 0.6639347076416016, Learning Rate: 3.633165829145729e-05)
+
Train steps ... :  64%|██████▍   | 63850/100000 [18:56:04<5:52:56,  1.71it/s]
Train steps ... :  64%|██████▍   | 63851/100000 [18:56:05<5:53:14,  1.71it/s]
Train steps ... :  64%|██████▍   | 63852/100000 [18:56:05<5:52:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 63853/100000 [18:56:06<5:52:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 63854/100000 [18:56:06<5:52:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 63855/100000 [18:56:07<5:52:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 63856/100000 [18:56:08<5:52:12,  1.71it/s]
Train steps ... :  64%|██████▍   | 63857/100000 [18:56:08<5:52:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 63858/100000 [18:56:09<5:52:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 63859/100000 [18:56:09<5:52:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 63860/100000 [18:56:10<5:52:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 63861/100000 [18:56:11<5:52:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 63862/100000 [18:56:11<5:52:32,  1.71it/s]
Train steps ... :  64%|██████▍   | 63863/100000 [18:56:12<5:52:03,  1.71it/s]
Train steps ... :  64%|██████▍   | 63864/100000 [18:56:12<5:51:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 63865/100000 [18:56:13<5:52:27,  1.71it/s]
Train steps ... :  64%|██████▍   | 63866/100000 [18:56:13<5:52:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 63867/100000 [18:56:14<5:52:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 63868/100000 [18:56:15<5:52:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 63869/100000 [18:56:15<5:52:10,  1.71it/s]
Train steps ... :  64%|██████▍   | 63870/100000 [18:56:16<5:51:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 63871/100000 [18:56:16<5:52:02,  1.71it/s]
Train steps ... :  64%|██████▍   | 63872/100000 [18:56:17<5:52:11,  1.71it/s]
Train steps ... :  64%|██████▍   | 63873/100000 [18:56:18<5:52:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 63874/100000 [18:56:18<5:53:10,  1.70it/s]
Train steps ... :  64%|██████▍   | 63875/100000 [18:56:19<5:52:18,  1.71it/s]Step... (63875 / 100000 | Loss: 0.5464037656784058, Learning Rate: 3.6306532663316586e-05)
+
                                                                             
Step... (63875 / 100000 | Loss: 0.6140586137771606, Learning Rate: 3.6306532663316586e-05)
+
Train steps ... :  64%|██████▍   | 63875/100000 [18:56:19<5:52:18,  1.71it/s]
Train steps ... :  64%|██████▍   | 63876/100000 [18:56:19<5:53:19,  1.70it/s]
Train steps ... :  64%|██████▍   | 63877/100000 [18:56:20<5:52:26,  1.71it/s]
Train steps ... :  64%|██████▍   | 63878/100000 [18:56:20<5:53:00,  1.71it/s]
Train steps ... :  64%|██████▍   | 63879/100000 [18:56:21<5:53:23,  1.70it/s]
Train steps ... :  64%|██████▍   | 63880/100000 [18:56:22<5:52:56,  1.71it/s]
Train steps ... :  64%|██████▍   | 63881/100000 [18:56:22<5:52:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 63882/100000 [18:56:23<5:52:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 63883/100000 [18:56:23<5:52:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 63884/100000 [18:56:24<5:52:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 63885/100000 [18:56:25<5:53:04,  1.70it/s]
Train steps ... :  64%|██████▍   | 63886/100000 [18:56:25<5:51:43,  1.71it/s]
Train steps ... :  64%|██████▍   | 63887/100000 [18:56:26<5:52:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 63888/100000 [18:56:26<5:52:52,  1.71it/s]
Train steps ... :  64%|██████▍   | 63889/100000 [18:56:27<5:52:04,  1.71it/s]
Train steps ... :  64%|██████▍   | 63890/100000 [18:56:28<5:51:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 63891/100000 [18:56:28<5:52:10,  1.71it/s]
Train steps ... :  64%|██████▍   | 63892/100000 [18:56:29<5:52:26,  1.71it/s]
Train steps ... :  64%|██████▍   | 63893/100000 [18:56:29<5:52:48,  1.71it/s]
Train steps ... :  64%|██████▍   | 63894/100000 [18:56:30<5:52:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 63895/100000 [18:56:30<5:52:57,  1.70it/s]
Train steps ... :  64%|██████▍   | 63896/100000 [18:56:31<5:53:16,  1.70it/s]
Train steps ... :  64%|██████▍   | 63897/100000 [18:56:32<5:52:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 63898/100000 [18:56:32<5:52:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 63899/100000 [18:56:33<5:52:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 63900/100000 [18:56:33<5:52:35,  1.71it/s]Step... (63900 / 100000 | Loss: 0.672834575176239, Learning Rate: 3.628140703517588e-05)
+
                                                                             
Step... (63900 / 100000 | Loss: 0.6902541518211365, Learning Rate: 3.628140703517588e-05)
+
Train steps ... :  64%|██████▍   | 63900/100000 [18:56:34<5:52:35,  1.71it/s]
Train steps ... :  64%|██████▍   | 63901/100000 [18:56:34<5:53:35,  1.70it/s]
Train steps ... :  64%|██████▍   | 63902/100000 [18:56:35<5:52:02,  1.71it/s]
Train steps ... :  64%|██████▍   | 63903/100000 [18:56:35<5:52:10,  1.71it/s]
Train steps ... :  64%|██████▍   | 63904/100000 [18:56:36<5:51:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 63905/100000 [18:56:36<5:52:17,  1.71it/s]
Train steps ... :  64%|██████▍   | 63906/100000 [18:56:37<5:52:12,  1.71it/s]
Train steps ... :  64%|██████▍   | 63907/100000 [18:56:37<5:52:26,  1.71it/s]
Train steps ... :  64%|██████▍   | 63908/100000 [18:56:38<5:52:56,  1.70it/s]
Train steps ... :  64%|██████▍   | 63909/100000 [18:56:39<5:52:48,  1.70it/s]
Train steps ... :  64%|██████▍   | 63910/100000 [18:56:39<5:52:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 63911/100000 [18:56:40<5:53:22,  1.70it/s]
Train steps ... :  64%|██████▍   | 63912/100000 [18:56:40<5:53:40,  1.70it/s]
Train steps ... :  64%|██████▍   | 63913/100000 [18:56:41<5:53:33,  1.70it/s]
Train steps ... :  64%|██████▍   | 63914/100000 [18:56:42<5:54:10,  1.70it/s]
Train steps ... :  64%|██████▍   | 63915/100000 [18:56:42<5:53:18,  1.70it/s]
Train steps ... :  64%|██████▍   | 63916/100000 [18:56:43<5:53:28,  1.70it/s]
Train steps ... :  64%|██████▍   | 63917/100000 [18:56:43<5:53:16,  1.70it/s]
Train steps ... :  64%|██████▍   | 63918/100000 [18:56:44<5:52:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 63919/100000 [18:56:45<5:54:00,  1.70it/s]
Train steps ... :  64%|██████▍   | 63920/100000 [18:56:45<5:54:22,  1.70it/s]
Train steps ... :  64%|██████▍   | 63921/100000 [18:56:46<5:52:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 63922/100000 [18:56:46<5:52:58,  1.70it/s]
Train steps ... :  64%|██████▍   | 63923/100000 [18:56:47<5:52:32,  1.71it/s]
Train steps ... :  64%|██████▍   | 63924/100000 [18:56:47<5:52:36,  1.71it/s]
Train steps ... :  64%|██████▍   | 63925/100000 [18:56:48<5:52:10,  1.71it/s]Step... (63925 / 100000 | Loss: 0.7566722631454468, Learning Rate: 3.625628140703517e-05)
+
                                                                             
Step... (63925 / 100000 | Loss: 0.8371306657791138, Learning Rate: 3.625628140703517e-05)
+
Train steps ... :  64%|██████▍   | 63925/100000 [18:56:48<5:52:10,  1.71it/s]
Train steps ... :  64%|██████▍   | 63926/100000 [18:56:49<5:52:07,  1.71it/s]
Train steps ... :  64%|██████▍   | 63927/100000 [18:56:49<5:51:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 63928/100000 [18:56:50<5:51:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 63929/100000 [18:56:50<5:51:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 63930/100000 [18:56:51<5:51:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 63931/100000 [18:56:52<5:51:22,  1.71it/s]
Train steps ... :  64%|██████▍   | 63932/100000 [18:56:52<5:51:14,  1.71it/s]
Train steps ... :  64%|██████▍   | 63933/100000 [18:56:53<5:51:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 63934/100000 [18:56:53<5:51:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 63935/100000 [18:56:54<5:51:24,  1.71it/s]
Train steps ... :  64%|██████▍   | 63936/100000 [18:56:54<5:51:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 63937/100000 [18:56:55<5:51:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 63938/100000 [18:56:56<5:51:03,  1.71it/s]
Train steps ... :  64%|██████▍   | 63939/100000 [18:56:56<5:51:02,  1.71it/s]
Train steps ... :  64%|██████▍   | 63940/100000 [18:56:57<5:51:44,  1.71it/s]
Train steps ... :  64%|██████▍   | 63941/100000 [18:56:57<5:51:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 63942/100000 [18:56:58<5:51:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 63943/100000 [18:56:59<5:52:03,  1.71it/s]
Train steps ... :  64%|██████▍   | 63944/100000 [18:56:59<5:52:35,  1.70it/s]
Train steps ... :  64%|██████▍   | 63945/100000 [18:57:00<5:51:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 63946/100000 [18:57:00<5:51:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 63947/100000 [18:57:01<5:52:18,  1.71it/s]
Train steps ... :  64%|██████▍   | 63948/100000 [18:57:02<5:52:02,  1.71it/s]
Train steps ... :  64%|██████▍   | 63949/100000 [18:57:02<5:51:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 63950/100000 [18:57:03<5:52:13,  1.71it/s]Step... (63950 / 100000 | Loss: 0.8814723491668701, Learning Rate: 3.6231155778894476e-05)
+
                                                                             
Step... (63950 / 100000 | Loss: 0.6244993209838867, Learning Rate: 3.6231155778894476e-05)
+
Train steps ... :  64%|██████▍   | 63950/100000 [18:57:03<5:52:13,  1.71it/s]
Train steps ... :  64%|██████▍   | 63951/100000 [18:57:03<5:52:04,  1.71it/s]
Train steps ... :  64%|██████▍   | 63952/100000 [18:57:04<5:52:02,  1.71it/s]
Train steps ... :  64%|██████▍   | 63953/100000 [18:57:04<5:51:49,  1.71it/s]
Train steps ... :  64%|██████▍   | 63954/100000 [18:57:05<5:51:49,  1.71it/s]
Train steps ... :  64%|██████▍   | 63955/100000 [18:57:06<5:52:26,  1.70it/s]
Train steps ... :  64%|██████▍   | 63956/100000 [18:57:06<5:51:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 63957/100000 [18:57:07<5:52:31,  1.70it/s]
Train steps ... :  64%|██████▍   | 63958/100000 [18:57:07<5:52:08,  1.71it/s]
Train steps ... :  64%|██████▍   | 63959/100000 [18:57:08<5:52:19,  1.70it/s]
Train steps ... :  64%|██████▍   | 63960/100000 [18:57:09<5:51:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 63961/100000 [18:57:09<5:52:04,  1.71it/s]
Train steps ... :  64%|██████▍   | 63962/100000 [18:57:10<5:52:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 63963/100000 [18:57:10<5:51:12,  1.71it/s]
Train steps ... :  64%|██████▍   | 63964/100000 [18:57:11<5:51:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 63965/100000 [18:57:11<5:50:56,  1.71it/s]
Train steps ... :  64%|██████▍   | 63966/100000 [18:57:12<5:51:04,  1.71it/s]
Train steps ... :  64%|██████▍   | 63967/100000 [18:57:13<5:51:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 63968/100000 [18:57:13<5:51:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 63969/100000 [18:57:14<5:51:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 63970/100000 [18:57:14<5:51:30,  1.71it/s]
Train steps ... :  64%|██████▍   | 63971/100000 [18:57:15<5:51:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 63972/100000 [18:57:16<5:50:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 63973/100000 [18:57:16<5:51:08,  1.71it/s]
Train steps ... :  64%|██████▍   | 63974/100000 [18:57:17<5:51:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 63975/100000 [18:57:17<5:51:26,  1.71it/s]Step... (63975 / 100000 | Loss: 0.5464583039283752, Learning Rate: 3.620603015075377e-05)
+
                                                                             
Step... (63975 / 100000 | Loss: 0.6861674189567566, Learning Rate: 3.620603015075377e-05)
+
Train steps ... :  64%|██████▍   | 63975/100000 [18:57:18<5:51:26,  1.71it/s]
Train steps ... :  64%|██████▍   | 63976/100000 [18:57:18<5:52:26,  1.70it/s]
Train steps ... :  64%|██████▍   | 63977/100000 [18:57:18<5:51:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 63978/100000 [18:57:19<5:51:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 63979/100000 [18:57:20<5:51:24,  1.71it/s]
Train steps ... :  64%|██████▍   | 63980/100000 [18:57:20<5:51:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 63981/100000 [18:57:21<5:51:35,  1.71it/s]
Train steps ... :  64%|██████▍   | 63982/100000 [18:57:21<5:51:36,  1.71it/s]
Train steps ... :  64%|██████▍   | 63983/100000 [18:57:22<5:50:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 63984/100000 [18:57:23<5:51:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 63985/100000 [18:57:23<5:51:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 63986/100000 [18:57:24<5:51:14,  1.71it/s]
Train steps ... :  64%|██████▍   | 63987/100000 [18:57:24<5:51:36,  1.71it/s]
Train steps ... :  64%|██████▍   | 63988/100000 [18:57:25<5:50:56,  1.71it/s]
Train steps ... :  64%|██████▍   | 63989/100000 [18:57:26<5:51:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 63990/100000 [18:57:26<5:51:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 63991/100000 [18:57:27<5:52:12,  1.70it/s]
Train steps ... :  64%|██████▍   | 63992/100000 [18:57:27<5:52:08,  1.70it/s]
Train steps ... :  64%|██████▍   | 63993/100000 [18:57:28<5:53:00,  1.70it/s]
Train steps ... :  64%|██████▍   | 63994/100000 [18:57:28<5:51:58,  1.70it/s]
Train steps ... :  64%|██████▍   | 63995/100000 [18:57:29<5:51:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 63996/100000 [18:57:30<5:51:59,  1.70it/s]
Train steps ... :  64%|██████▍   | 63997/100000 [18:57:30<5:51:59,  1.70it/s]
Train steps ... :  64%|██████▍   | 63998/100000 [18:57:31<5:51:26,  1.71it/s]
Train steps ... :  64%|██████▍   | 63999/100000 [18:57:31<5:51:57,  1.70it/s]
Train steps ... :  64%|██████▍   | 64000/100000 [18:57:32<5:51:20,  1.71it/s]Step... (64000 / 100000 | Loss: 0.7696025967597961, Learning Rate: 3.618090452261307e-05)
+
                                                                             
Step... (64000 / 100000 | Loss: 0.8824397921562195, Learning Rate: 3.618090452261307e-05)
+
Train steps ... :  64%|██████▍   | 64000/100000 [18:57:32<5:51:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 64001/100000 [18:57:33<5:51:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 64002/100000 [18:57:33<5:51:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 64003/100000 [18:57:34<5:50:35,  1.71it/s]
Train steps ... :  64%|██████▍   | 64004/100000 [18:57:34<5:50:36,  1.71it/s]
Train steps ... :  64%|██████▍   | 64005/100000 [18:57:35<5:50:13,  1.71it/s]
Train steps ... :  64%|██████▍   | 64006/100000 [18:57:35<5:50:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 64007/100000 [18:57:36<5:50:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 64008/100000 [18:57:37<5:50:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 64009/100000 [18:57:37<5:50:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64010/100000 [18:57:38<5:51:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 64011/100000 [18:57:38<5:51:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 64012/100000 [18:57:39<5:51:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 64013/100000 [18:57:40<5:50:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 64014/100000 [18:57:40<5:50:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 64015/100000 [18:57:41<5:51:03,  1.71it/s]
Train steps ... :  64%|██████▍   | 64016/100000 [18:57:41<5:50:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 64017/100000 [18:57:42<5:50:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 64018/100000 [18:57:43<5:51:26,  1.71it/s]
Train steps ... :  64%|██████▍   | 64019/100000 [18:57:43<5:50:43,  1.71it/s]
Train steps ... :  64%|██████▍   | 64020/100000 [18:57:44<5:51:03,  1.71it/s]
Train steps ... :  64%|██████▍   | 64021/100000 [18:57:44<5:51:53,  1.70it/s]
Train steps ... :  64%|██████▍   | 64022/100000 [18:57:45<5:51:05,  1.71it/s]
Train steps ... :  64%|██████▍   | 64023/100000 [18:57:45<5:51:43,  1.70it/s]
Train steps ... :  64%|██████▍   | 64024/100000 [18:57:46<5:50:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 64025/100000 [18:57:47<5:50:56,  1.71it/s]Step... (64025 / 100000 | Loss: 0.657234787940979, Learning Rate: 3.6155778894472366e-05)
+
                                                                             
Step... (64025 / 100000 | Loss: 0.7619446516036987, Learning Rate: 3.6155778894472366e-05)
+
Train steps ... :  64%|██████▍   | 64025/100000 [18:57:47<5:50:56,  1.71it/s]
Train steps ... :  64%|██████▍   | 64026/100000 [18:57:47<5:50:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 64027/100000 [18:57:48<5:51:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 64028/100000 [18:57:48<5:51:24,  1.71it/s]
Train steps ... :  64%|██████▍   | 64029/100000 [18:57:49<5:51:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 64030/100000 [18:57:50<5:51:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 64031/100000 [18:57:50<5:51:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 64032/100000 [18:57:51<5:50:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 64033/100000 [18:57:51<5:50:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 64034/100000 [18:57:52<5:50:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 64035/100000 [18:57:52<5:50:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 64036/100000 [18:57:53<5:50:32,  1.71it/s]
Train steps ... :  64%|██████▍   | 64037/100000 [18:57:54<5:50:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 64038/100000 [18:57:54<5:51:09,  1.71it/s]
Train steps ... :  64%|██████▍   | 64039/100000 [18:57:55<5:50:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 64040/100000 [18:57:55<5:50:35,  1.71it/s]
Train steps ... :  64%|██████▍   | 64041/100000 [18:57:56<5:50:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 64042/100000 [18:57:57<5:51:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 64043/100000 [18:57:57<5:50:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 64044/100000 [18:57:58<5:51:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 64045/100000 [18:57:58<5:50:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 64046/100000 [18:57:59<5:50:10,  1.71it/s]
Train steps ... :  64%|██████▍   | 64047/100000 [18:57:59<5:50:22,  1.71it/s]
Train steps ... :  64%|██████▍   | 64048/100000 [18:58:00<5:50:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 64049/100000 [18:58:01<5:51:01,  1.71it/s]
Train steps ... :  64%|██████▍   | 64050/100000 [18:58:01<5:51:05,  1.71it/s]Step... (64050 / 100000 | Loss: 0.6730018258094788, Learning Rate: 3.613065326633166e-05)
+
                                                                             
Step... (64050 / 100000 | Loss: 0.7219545841217041, Learning Rate: 3.613065326633166e-05)
+
Train steps ... :  64%|██████▍   | 64050/100000 [18:58:02<5:51:05,  1.71it/s]
Train steps ... :  64%|██████▍   | 64051/100000 [18:58:02<5:50:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 64052/100000 [18:58:02<5:51:13,  1.71it/s]
Train steps ... :  64%|██████▍   | 64053/100000 [18:58:03<5:50:11,  1.71it/s]
Train steps ... :  64%|██████▍   | 64054/100000 [18:58:04<5:50:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 64055/100000 [18:58:04<5:50:52,  1.71it/s]
Train steps ... :  64%|██████▍   | 64056/100000 [18:58:05<5:50:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 64057/100000 [18:58:05<5:50:56,  1.71it/s]
Train steps ... :  64%|██████▍   | 64058/100000 [18:58:06<5:50:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 64059/100000 [18:58:07<5:50:32,  1.71it/s]
Train steps ... :  64%|██████▍   | 64060/100000 [18:58:07<5:51:11,  1.71it/s]
Train steps ... :  64%|██████▍   | 64061/100000 [18:58:08<5:50:35,  1.71it/s]
Train steps ... :  64%|██████▍   | 64062/100000 [18:58:08<5:50:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 64063/100000 [18:58:09<5:50:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 64064/100000 [18:58:09<5:50:00,  1.71it/s]
Train steps ... :  64%|██████▍   | 64065/100000 [18:58:10<5:50:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 64066/100000 [18:58:11<5:50:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 64067/100000 [18:58:11<5:50:15,  1.71it/s]
Train steps ... :  64%|██████▍   | 64068/100000 [18:58:12<5:50:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 64069/100000 [18:58:12<5:50:03,  1.71it/s]
Train steps ... :  64%|██████▍   | 64070/100000 [18:58:13<5:49:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 64071/100000 [18:58:14<5:50:05,  1.71it/s]
Train steps ... :  64%|██████▍   | 64072/100000 [18:58:14<5:50:00,  1.71it/s]
Train steps ... :  64%|██████▍   | 64073/100000 [18:58:15<5:50:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 64074/100000 [18:58:15<5:51:16,  1.70it/s]
Train steps ... :  64%|██████▍   | 64075/100000 [18:58:16<5:51:08,  1.71it/s]Step... (64075 / 100000 | Loss: 0.7916416525840759, Learning Rate: 3.610552763819095e-05)
+
                                                                             
Step... (64075 / 100000 | Loss: 0.6563141345977783, Learning Rate: 3.610552763819095e-05)
+
Train steps ... :  64%|██████▍   | 64075/100000 [18:58:16<5:51:08,  1.71it/s]
Train steps ... :  64%|██████▍   | 64076/100000 [18:58:16<5:51:47,  1.70it/s]
Train steps ... :  64%|██████▍   | 64077/100000 [18:58:17<5:51:18,  1.70it/s]
Train steps ... :  64%|██████▍   | 64078/100000 [18:58:18<5:51:47,  1.70it/s]
Train steps ... :  64%|██████▍   | 64079/100000 [18:58:18<5:50:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 64080/100000 [18:58:19<5:50:44,  1.71it/s]
Train steps ... :  64%|██████▍   | 64081/100000 [18:58:19<5:50:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 64082/100000 [18:58:20<5:51:25,  1.70it/s]
Train steps ... :  64%|██████▍   | 64083/100000 [18:58:21<5:50:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 64084/100000 [18:58:21<5:50:51,  1.71it/s]
Train steps ... :  64%|██████▍   | 64085/100000 [18:58:22<5:51:50,  1.70it/s]
Train steps ... :  64%|██████▍   | 64086/100000 [18:58:22<5:51:24,  1.70it/s]
Train steps ... :  64%|██████▍   | 64087/100000 [18:58:23<5:51:17,  1.70it/s]
Train steps ... :  64%|██████▍   | 64088/100000 [18:58:23<5:50:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 64089/100000 [18:58:24<5:51:22,  1.70it/s]
Train steps ... :  64%|██████▍   | 64090/100000 [18:58:25<5:50:49,  1.71it/s]
Train steps ... :  64%|██████▍   | 64091/100000 [18:58:25<5:49:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64092/100000 [18:58:26<5:50:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 64093/100000 [18:58:26<5:50:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 64094/100000 [18:58:27<5:50:08,  1.71it/s]
Train steps ... :  64%|██████▍   | 64095/100000 [18:58:28<5:50:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 64096/100000 [18:58:28<5:51:25,  1.70it/s]
Train steps ... :  64%|██████▍   | 64097/100000 [18:58:29<5:50:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 64098/100000 [18:58:29<5:50:30,  1.71it/s]
Train steps ... :  64%|██████▍   | 64099/100000 [18:58:30<5:51:04,  1.70it/s]
Train steps ... :  64%|██████▍   | 64100/100000 [18:58:31<5:50:40,  1.71it/s]Step... (64100 / 100000 | Loss: 0.6780037879943848, Learning Rate: 3.608040201005025e-05)
+
                                                                             
Step... (64100 / 100000 | Loss: 0.5229800343513489, Learning Rate: 3.608040201005025e-05)
+
Train steps ... :  64%|██████▍   | 64100/100000 [18:58:31<5:50:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 64101/100000 [18:58:31<5:50:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 64102/100000 [18:58:32<5:50:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 64103/100000 [18:58:32<5:51:00,  1.70it/s]
Train steps ... :  64%|██████▍   | 64104/100000 [18:58:33<5:50:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 64105/100000 [18:58:33<5:50:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 64106/100000 [18:58:34<5:50:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 64107/100000 [18:58:35<5:50:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 64108/100000 [18:58:35<5:50:07,  1.71it/s]
Train steps ... :  64%|██████▍   | 64109/100000 [18:58:36<5:49:43,  1.71it/s]
Train steps ... :  64%|██████▍   | 64110/100000 [18:58:36<5:49:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 64111/100000 [18:58:37<5:50:01,  1.71it/s]
Train steps ... :  64%|██████▍   | 64112/100000 [18:58:38<5:49:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 64113/100000 [18:58:38<5:49:35,  1.71it/s]
Train steps ... :  64%|██████▍   | 64114/100000 [18:58:39<5:49:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 64115/100000 [18:58:39<5:49:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 64116/100000 [18:58:40<5:49:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 64117/100000 [18:58:40<5:49:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64118/100000 [18:58:41<5:50:15,  1.71it/s]
Train steps ... :  64%|██████▍   | 64119/100000 [18:58:42<5:49:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 64120/100000 [18:58:42<5:51:05,  1.70it/s]
Train steps ... :  64%|██████▍   | 64121/100000 [18:58:43<5:50:56,  1.70it/s]
Train steps ... :  64%|██████▍   | 64122/100000 [18:58:43<5:51:05,  1.70it/s]
Train steps ... :  64%|██████▍   | 64123/100000 [18:58:44<5:50:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 64124/100000 [18:58:45<5:49:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 64125/100000 [18:58:45<5:49:45,  1.71it/s]Step... (64125 / 100000 | Loss: 0.7199704051017761, Learning Rate: 3.6055276381909546e-05)
+
                                                                             
Step... (64125 / 100000 | Loss: 0.7857593297958374, Learning Rate: 3.6055276381909546e-05)
+
Train steps ... :  64%|██████▍   | 64125/100000 [18:58:45<5:49:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 64126/100000 [18:58:46<5:49:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 64127/100000 [18:58:46<5:50:11,  1.71it/s]
Train steps ... :  64%|██████▍   | 64128/100000 [18:58:47<5:50:09,  1.71it/s]
Train steps ... :  64%|██████▍   | 64129/100000 [18:58:48<5:50:04,  1.71it/s]
Train steps ... :  64%|██████▍   | 64130/100000 [18:58:48<5:49:35,  1.71it/s]
Train steps ... :  64%|██████▍   | 64131/100000 [18:58:49<5:49:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 64132/100000 [18:58:49<5:50:07,  1.71it/s]
Train steps ... :  64%|██████▍   | 64133/100000 [18:58:50<5:49:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64134/100000 [18:58:50<5:50:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 64135/100000 [18:58:51<5:49:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 64136/100000 [18:58:52<5:49:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 64137/100000 [18:58:52<5:49:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 64138/100000 [18:58:53<5:49:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 64139/100000 [18:58:53<5:49:10,  1.71it/s]
Train steps ... :  64%|██████▍   | 64140/100000 [18:58:54<5:50:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 64141/100000 [18:58:55<5:50:00,  1.71it/s]
Train steps ... :  64%|██████▍   | 64142/100000 [18:58:55<5:51:02,  1.70it/s]
Train steps ... :  64%|██████▍   | 64143/100000 [18:58:56<5:50:09,  1.71it/s]
Train steps ... :  64%|██████▍   | 64144/100000 [18:58:56<5:50:55,  1.70it/s]
Train steps ... :  64%|██████▍   | 64145/100000 [18:58:57<5:50:04,  1.71it/s]
Train steps ... :  64%|██████▍   | 64146/100000 [18:58:57<5:49:48,  1.71it/s]
Train steps ... :  64%|██████▍   | 64147/100000 [18:58:58<5:49:48,  1.71it/s]
Train steps ... :  64%|██████▍   | 64148/100000 [18:58:59<5:49:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 64149/100000 [18:58:59<5:49:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 64150/100000 [18:59:00<5:49:47,  1.71it/s]Step... (64150 / 100000 | Loss: 0.5686546564102173, Learning Rate: 3.603015075376884e-05)
+
                                                                             
Step... (64150 / 100000 | Loss: 0.919134259223938, Learning Rate: 3.603015075376884e-05)
+
Train steps ... :  64%|██████▍   | 64150/100000 [18:59:00<5:49:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 64151/100000 [18:59:00<5:51:24,  1.70it/s]
Train steps ... :  64%|██████▍   | 64152/100000 [18:59:01<5:49:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 64153/100000 [18:59:02<5:49:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64154/100000 [18:59:02<5:50:57,  1.70it/s]
Train steps ... :  64%|██████��   | 64155/100000 [18:59:03<5:50:44,  1.70it/s]
Train steps ... :  64%|██████▍   | 64156/100000 [18:59:03<5:50:48,  1.70it/s]
Train steps ... :  64%|██████▍   | 64157/100000 [18:59:04<5:50:33,  1.70it/s]
Train steps ... :  64%|██████▍   | 64158/100000 [18:59:05<5:51:21,  1.70it/s]
Train steps ... :  64%|██████▍   | 64159/100000 [18:59:05<5:51:06,  1.70it/s]
Train steps ... :  64%|██████▍   | 64160/100000 [18:59:06<5:50:31,  1.70it/s]
Train steps ... :  64%|██████▍   | 64161/100000 [18:59:06<5:49:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 64162/100000 [18:59:07<5:49:51,  1.71it/s]
Train steps ... :  64%|██████▍   | 64163/100000 [18:59:07<5:50:35,  1.70it/s]
Train steps ... :  64%|██████▍   | 64164/100000 [18:59:08<5:50:24,  1.70it/s]
Train steps ... :  64%|██████▍   | 64165/100000 [18:59:09<5:50:32,  1.70it/s]
Train steps ... :  64%|██████▍   | 64166/100000 [18:59:09<5:50:24,  1.70it/s]
Train steps ... :  64%|██████▍   | 64167/100000 [18:59:10<5:50:10,  1.71it/s]
Train steps ... :  64%|██████▍   | 64168/100000 [18:59:10<5:49:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64169/100000 [18:59:11<5:50:09,  1.71it/s]
Train steps ... :  64%|██████▍   | 64170/100000 [18:59:12<5:49:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 64171/100000 [18:59:12<5:50:00,  1.71it/s]
Train steps ... :  64%|██████▍   | 64172/100000 [18:59:13<5:50:23,  1.70it/s]
Train steps ... :  64%|██████▍   | 64173/100000 [18:59:13<5:50:05,  1.71it/s]
Train steps ... :  64%|██████▍   | 64174/100000 [18:59:14<5:49:27,  1.71it/s]
Train steps ... :  64%|██████▍   | 64175/100000 [18:59:14<5:49:40,  1.71it/s]Step... (64175 / 100000 | Loss: 0.5852042436599731, Learning Rate: 3.6005025125628146e-05)
+
                                                                             
Step... (64175 / 100000 | Loss: 0.8464337587356567, Learning Rate: 3.6005025125628146e-05)
+
Train steps ... :  64%|██████▍   | 64175/100000 [18:59:15<5:49:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 64176/100000 [18:59:15<5:50:41,  1.70it/s]
Train steps ... :  64%|██████▍   | 64177/100000 [18:59:16<5:49:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 64178/100000 [18:59:16<5:50:14,  1.70it/s]
Train steps ... :  64%|██████▍   | 64179/100000 [18:59:17<5:49:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64180/100000 [18:59:17<5:50:15,  1.70it/s]
Train steps ... :  64%|██████▍   | 64181/100000 [18:59:18<5:49:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 64182/100000 [18:59:19<5:50:25,  1.70it/s]
Train steps ... :  64%|██████▍   | 64183/100000 [18:59:19<5:50:12,  1.70it/s]
Train steps ... :  64%|██████▍   | 64184/100000 [18:59:20<5:50:27,  1.70it/s]
Train steps ... :  64%|██████▍   | 64185/100000 [18:59:20<5:50:17,  1.70it/s]
Train steps ... :  64%|██████▍   | 64186/100000 [18:59:21<5:50:05,  1.70it/s]
Train steps ... :  64%|██████▍   | 64187/100000 [18:59:22<5:49:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 64188/100000 [18:59:22<5:49:43,  1.71it/s]
Train steps ... :  64%|██████▍   | 64189/100000 [18:59:23<5:49:17,  1.71it/s]
Train steps ... :  64%|██████▍   | 64190/100000 [18:59:23<5:49:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 64191/100000 [18:59:24<5:49:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 64192/100000 [18:59:24<5:49:49,  1.71it/s]
Train steps ... :  64%|██████▍   | 64193/100000 [18:59:25<5:49:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 64194/100000 [18:59:26<5:49:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 64195/100000 [18:59:26<5:49:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 64196/100000 [18:59:27<5:49:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 64197/100000 [18:59:27<5:49:32,  1.71it/s]
Train steps ... :  64%|██████▍   | 64198/100000 [18:59:28<5:49:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 64199/100000 [18:59:29<5:49:48,  1.71it/s]
Train steps ... :  64%|██████▍   | 64200/100000 [18:59:29<5:50:18,  1.70it/s]Step... (64200 / 100000 | Loss: 0.9340240955352783, Learning Rate: 3.597989949748744e-05)
+
                                                                             
Step... (64200 / 100000 | Loss: 0.6904284358024597, Learning Rate: 3.597989949748744e-05)
+
Train steps ... :  64%|██████▍   | 64200/100000 [18:59:29<5:50:18,  1.70it/s]
Train steps ... :  64%|██████▍   | 64201/100000 [18:59:30<5:49:02,  1.71it/s]
Train steps ... :  64%|██████▍   | 64202/100000 [18:59:30<5:49:59,  1.70it/s]
Train steps ... :  64%|█████���▍   | 64203/100000 [18:59:31<5:50:13,  1.70it/s]
Train steps ... :  64%|██████▍   | 64204/100000 [18:59:31<5:49:35,  1.71it/s]
Train steps ... :  64%|██████▍   | 64205/100000 [18:59:32<5:50:05,  1.70it/s]
Train steps ... :  64%|██████▍   | 64206/100000 [18:59:33<5:50:11,  1.70it/s]
Train steps ... :  64%|██████▍   | 64207/100000 [18:59:33<5:49:04,  1.71it/s]
Train steps ... :  64%|██████▍   | 64208/100000 [18:59:34<5:49:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 64209/100000 [18:59:34<5:49:11,  1.71it/s]
Train steps ... :  64%|██████▍   | 64210/100000 [18:59:35<5:49:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 64211/100000 [18:59:36<5:49:24,  1.71it/s]
Train steps ... :  64%|██████▍   | 64212/100000 [18:59:36<5:50:53,  1.70it/s]
Train steps ... :  64%|██████▍   | 64213/100000 [18:59:37<5:50:04,  1.70it/s]
Train steps ... :  64%|██████▍   | 64214/100000 [18:59:37<5:49:54,  1.70it/s]
Train steps ... :  64%|██████▍   | 64215/100000 [18:59:38<5:50:27,  1.70it/s]
Train steps ... :  64%|██████▍   | 64216/100000 [18:59:39<5:49:36,  1.71it/s]
Train steps ... :  64%|██████▍   | 64217/100000 [18:59:39<5:50:08,  1.70it/s]
Train steps ... :  64%|██████▍   | 64218/100000 [18:59:40<5:49:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 64219/100000 [18:59:40<5:49:22,  1.71it/s]
Train steps ... :  64%|██████▍   | 64220/100000 [18:59:41<5:49:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 64221/100000 [18:59:41<5:49:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 64222/100000 [18:59:42<5:49:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 64223/100000 [18:59:43<5:49:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 64224/100000 [18:59:43<5:50:17,  1.70it/s]
Train steps ... :  64%|██████▍   | 64225/100000 [18:59:44<5:49:39,  1.71it/s]Step... (64225 / 100000 | Loss: 0.5175118446350098, Learning Rate: 3.595477386934674e-05)
+
                                                                             
Step... (64225 / 100000 | Loss: 0.8720399141311646, Learning Rate: 3.595477386934674e-05)
+
Train steps ... :  64%|██████▍   | 64225/100000 [18:59:44<5:49:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 64226/100000 [18:59:44<5:49:46,  1.70it/s]
Train steps ... :  64%|██████▍   | 64227/100000 [18:59:45<5:51:03,  1.70it/s]
Train steps ... :  64%|██████▍   | 64228/100000 [18:59:46<5:49:24,  1.71it/s]
Train steps ... :  64%|██████▍   | 64229/100000 [18:59:46<5:49:01,  1.71it/s]
Train steps ... :  64%|██████▍   | 64230/100000 [18:59:47<5:49:40,  1.70it/s]
Train steps ... :  64%|██████▍   | 64231/100000 [18:59:47<5:49:12,  1.71it/s]
Train steps ... :  64%|██████▍   | 64232/100000 [18:59:48<5:49:12,  1.71it/s]
Train steps ... :  64%|██████▍   | 64233/100000 [18:59:48<5:49:15,  1.71it/s]
Train steps ... :  64%|██████▍   | 64234/100000 [18:59:49<5:49:12,  1.71it/s]
Train steps ... :  64%|██████▍   | 64235/100000 [18:59:50<5:48:51,  1.71it/s]
Train steps ... :  64%|██████▍   | 64236/100000 [18:59:50<5:48:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 64237/100000 [18:59:51<5:48:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 64238/100000 [18:59:51<5:48:36,  1.71it/s]
Train steps ... :  64%|██████▍   | 64239/100000 [18:59:52<5:48:49,  1.71it/s]
Train steps ... :  64%|██████▍   | 64240/100000 [18:59:53<5:49:40,  1.70it/s]
Train steps ... :  64%|██████▍   | 64241/100000 [18:59:53<5:49:05,  1.71it/s]
Train steps ... :  64%|██████▍   | 64242/100000 [18:59:54<5:49:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 64243/100000 [18:59:54<5:49:30,  1.71it/s]
Train steps ... :  64%|██████▍   | 64244/100000 [18:59:55<5:48:44,  1.71it/s]
Train steps ... :  64%|██████▍   | 64245/100000 [18:59:56<5:48:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 64246/100000 [18:59:56<5:48:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 64247/100000 [18:59:57<5:48:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 64248/100000 [18:59:57<5:49:46,  1.70it/s]
Train steps ... :  64%|██████▍   | 64249/100000 [18:59:58<5:48:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64250/100000 [18:59:58<5:48:24,  1.71it/s]Step... (64250 / 100000 | Loss: 0.6247943043708801, Learning Rate: 3.592964824120603e-05)
+
                                                                             
Step... (64250 / 100000 | Loss: 0.5939242839813232, Learning Rate: 3.592964824120603e-05)
+
Train steps ... :  64%|██████▍   | 64250/100000 [18:59:59<5:48:24,  1.71it/s]
Train steps ... :  64%|████��█▍   | 64251/100000 [18:59:59<5:48:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 64252/100000 [19:00:00<5:49:08,  1.71it/s]
Train steps ... :  64%|██████▍   | 64253/100000 [19:00:00<5:48:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 64254/100000 [19:00:01<5:48:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 64255/100000 [19:00:01<5:48:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 64256/100000 [19:00:02<5:49:15,  1.71it/s]
Train steps ... :  64%|██████▍   | 64257/100000 [19:00:03<5:48:51,  1.71it/s]
Train steps ... :  64%|██████▍   | 64258/100000 [19:00:03<5:48:26,  1.71it/s]
Train steps ... :  64%|██████▍   | 64259/100000 [19:00:04<5:47:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 64260/100000 [19:00:04<5:47:56,  1.71it/s]
Train steps ... :  64%|██████▍   | 64261/100000 [19:00:05<5:48:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 64262/100000 [19:00:05<5:48:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 64263/100000 [19:00:06<5:48:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 64264/100000 [19:00:07<5:48:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 64265/100000 [19:00:07<5:48:49,  1.71it/s]
Train steps ... :  64%|██████▍   | 64266/100000 [19:00:08<5:48:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 64267/100000 [19:00:08<5:49:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 64268/100000 [19:00:09<5:49:23,  1.70it/s]
Train steps ... :  64%|██████▍   | 64269/100000 [19:00:10<5:48:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 64270/100000 [19:00:10<5:48:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 64271/100000 [19:00:11<5:48:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 64272/100000 [19:00:11<5:48:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64273/100000 [19:00:12<5:48:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 64274/100000 [19:00:12<5:49:02,  1.71it/s]
Train steps ... :  64%|██████▍   | 64275/100000 [19:00:13<5:49:17,  1.70it/s]Step... (64275 / 100000 | Loss: 1.0825644731521606, Learning Rate: 3.5904522613065325e-05)
+
                                                                             
Step... (64275 / 100000 | Loss: 1.24972665309906, Learning Rate: 3.5904522613065325e-05)
+
Train steps ... :  64%|██████▍   | 64275/100000 [19:00:13<5:49:17,  1.70it/s]
Train steps ... :  64%|██████▍   | 64276/100000 [19:00:14<5:48:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64277/100000 [19:00:14<5:49:13,  1.70it/s]
Train steps ... :  64%|██████▍   | 64278/100000 [19:00:15<5:48:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64279/100000 [19:00:15<5:48:15,  1.71it/s]
Train steps ... :  64%|██████▍   | 64280/100000 [19:00:16<5:48:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 64281/100000 [19:00:17<5:48:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 64282/100000 [19:00:17<5:48:48,  1.71it/s]
Train steps ... :  64%|██████▍   | 64283/100000 [19:00:18<5:48:09,  1.71it/s]
Train steps ... :  64%|██████▍   | 64284/100000 [19:00:18<5:49:08,  1.70it/s]
Train steps ... :  64%|██████▍   | 64285/100000 [19:00:19<5:48:52,  1.71it/s]
Train steps ... :  64%|██████▍   | 64286/100000 [19:00:20<5:48:24,  1.71it/s]
Train steps ... :  64%|██████▍   | 64287/100000 [19:00:20<5:48:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 64288/100000 [19:00:21<5:48:01,  1.71it/s]
Train steps ... :  64%|██████▍   | 64289/100000 [19:00:21<5:48:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 64290/100000 [19:00:22<5:48:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 64291/100000 [19:00:22<5:49:22,  1.70it/s]
Train steps ... :  64%|██████▍   | 64292/100000 [19:00:23<5:49:01,  1.71it/s]
Train steps ... :  64%|██████▍   | 64293/100000 [19:00:24<5:48:44,  1.71it/s]
Train steps ... :  64%|██████▍   | 64294/100000 [19:00:24<5:48:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 64295/100000 [19:00:25<5:47:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 64296/100000 [19:00:25<5:48:13,  1.71it/s]
Train steps ... :  64%|██████▍   | 64297/100000 [19:00:26<5:48:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 64298/100000 [19:00:27<5:48:10,  1.71it/s]
Train steps ... :  64%|██████▍   | 64299/100000 [19:00:27<5:48:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 64300/100000 [19:00:28<5:48:16,  1.71it/s]Step... (64300 / 100000 | Loss: 0.6148931980133057, Learning Rate: 3.587939698492462e-05)
+
                                                                             
Step... (64300 / 100000 | Loss: 0.8093926310539246, Learning Rate: 3.587939698492462e-05)
+
Train steps ... :  64%|██████▍   | 64300/100000 [19:00:28<5:48:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 64301/100000 [19:00:28<5:49:22,  1.70it/s]
Train steps ... :  64%|██████▍   | 64302/100000 [19:00:29<5:48:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 64303/100000 [19:00:29<5:48:52,  1.71it/s]
Train steps ... :  64%|██████▍   | 64304/100000 [19:00:30<5:49:19,  1.70it/s]
Train steps ... :  64%|██████▍   | 64305/100000 [19:00:31<5:49:34,  1.70it/s]
Train steps ... :  64%|██████▍   | 64306/100000 [19:00:31<5:49:15,  1.70it/s]
Train steps ... :  64%|██████▍   | 64307/100000 [19:00:32<5:50:35,  1.70it/s]
Train steps ... :  64%|██████▍   | 64308/100000 [19:00:32<5:50:52,  1.70it/s]
Train steps ... :  64%|██████▍   | 64309/100000 [19:00:33<5:48:59,  1.70it/s]
Train steps ... :  64%|██████▍   | 64310/100000 [19:00:34<5:49:23,  1.70it/s]
Train steps ... :  64%|██████▍   | 64311/100000 [19:00:34<5:49:04,  1.70it/s]
Train steps ... :  64%|██████▍   | 64312/100000 [19:00:35<5:49:22,  1.70it/s]
Train steps ... :  64%|██████▍   | 64313/100000 [19:00:35<5:49:22,  1.70it/s]
Train steps ... :  64%|██████▍   | 64314/100000 [19:00:36<5:49:19,  1.70it/s]
Train steps ... :  64%|██████▍   | 64315/100000 [19:00:37<5:50:29,  1.70it/s]
Train steps ... :  64%|██████▍   | 64316/100000 [19:00:37<5:50:02,  1.70it/s]
Train steps ... :  64%|██████▍   | 64317/100000 [19:00:38<5:50:15,  1.70it/s]
Train steps ... :  64%|██████▍   | 64318/100000 [19:00:38<5:49:31,  1.70it/s]
Train steps ... :  64%|██████▍   | 64319/100000 [19:00:39<5:48:59,  1.70it/s]
Train steps ... :  64%|██████▍   | 64320/100000 [19:00:39<5:48:27,  1.71it/s]
Train steps ... :  64%|██████▍   | 64321/100000 [19:00:40<5:49:37,  1.70it/s]
Train steps ... :  64%|██████▍   | 64322/100000 [19:00:41<5:48:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 64323/100000 [19:00:41<5:49:48,  1.70it/s]
Train steps ... :  64%|██████▍   | 64324/100000 [19:00:42<5:48:53,  1.70it/s]
Train steps ... :  64%|██████▍   | 64325/100000 [19:00:42<5:48:41,  1.71it/s]Step... (64325 / 100000 | Loss: 0.7869887351989746, Learning Rate: 3.585427135678392e-05)
+
                                                                             
Step... (64325 / 100000 | Loss: 0.8662832379341125, Learning Rate: 3.585427135678392e-05)
+
Train steps ... :  64%|██████▍   | 64325/100000 [19:00:43<5:48:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 64326/100000 [19:00:43<5:48:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 64327/100000 [19:00:44<5:48:22,  1.71it/s]
Train steps ... :  64%|██████▍   | 64328/100000 [19:00:44<5:48:01,  1.71it/s]
Train steps ... :  64%|██████▍   | 64329/100000 [19:00:45<5:48:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 64330/100000 [19:00:45<5:49:06,  1.70it/s]
Train steps ... :  64%|██████▍   | 64331/100000 [19:00:46<5:47:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64332/100000 [19:00:47<5:47:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 64333/100000 [19:00:47<5:47:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64334/100000 [19:00:48<5:47:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 64335/100000 [19:00:48<5:47:07,  1.71it/s]
Train steps ... :  64%|██████▍   | 64336/100000 [19:00:49<5:48:38,  1.70it/s]
Train steps ... :  64%|██████▍   | 64337/100000 [19:00:49<5:47:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 64338/100000 [19:00:50<5:47:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 64339/100000 [19:00:51<5:47:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 64340/100000 [19:00:51<5:48:17,  1.71it/s]
Train steps ... :  64%|██████▍   | 64341/100000 [19:00:52<5:48:22,  1.71it/s]
Train steps ... :  64%|██████▍   | 64342/100000 [19:00:52<5:48:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 64343/100000 [19:00:53<5:49:01,  1.70it/s]
Train steps ... :  64%|██████▍   | 64344/100000 [19:00:54<5:48:21,  1.71it/s]
Train steps ... :  64%|██████▍   | 64345/100000 [19:00:54<5:47:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 64346/100000 [19:00:55<5:48:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 64347/100000 [19:00:55<5:48:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 64348/100000 [19:00:56<5:48:55,  1.70it/s]
Train steps ... :  64%|██████▍   | 64349/100000 [19:00:56<5:48:51,  1.70it/s]
Train steps ... :  64%|██████▍   | 64350/100000 [19:00:57<5:49:28,  1.70it/s]Step... (64350 / 100000 | Loss: 0.624691367149353, Learning Rate: 3.5829145728643215e-05)
+
                                                                             
Step... (64350 / 100000 | Loss: 0.8609058856964111, Learning Rate: 3.5829145728643215e-05)
+
Train steps ... :  64%|██████▍   | 64350/100000 [19:00:57<5:49:28,  1.70it/s]
Train steps ... :  64%|██████▍   | 64351/100000 [19:00:58<5:48:12,  1.71it/s]
Train steps ... :  64%|██████▍   | 64352/100000 [19:00:58<5:48:03,  1.71it/s]
Train steps ... :  64%|██████▍   | 64353/100000 [19:00:59<5:48:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 64354/100000 [19:00:59<5:47:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 64355/100000 [19:01:00<5:47:26,  1.71it/s]
Train steps ... :  64%|██████▍   | 64356/100000 [19:01:01<5:48:17,  1.71it/s]
Train steps ... :  64%|██████▍   | 64357/100000 [19:01:01<5:47:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 64358/100000 [19:01:02<5:47:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 64359/100000 [19:01:02<5:47:56,  1.71it/s]
Train steps ... :  64%|██████▍   | 64360/100000 [19:01:03<5:47:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 64361/100000 [19:01:03<5:47:03,  1.71it/s]
Train steps ... :  64%|██████▍   | 64362/100000 [19:01:04<5:47:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 64363/100000 [19:01:05<5:47:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 64364/100000 [19:01:05<5:48:22,  1.70it/s]
Train steps ... :  64%|██████▍   | 64365/100000 [19:01:06<5:48:12,  1.71it/s]
Train steps ... :  64%|██████▍   | 64366/100000 [19:01:06<5:48:22,  1.70it/s]
Train steps ... :  64%|██████▍   | 64367/100000 [19:01:07<5:48:01,  1.71it/s]
Train steps ... :  64%|██████▍   | 64368/100000 [19:01:08<5:47:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 64369/100000 [19:01:08<5:48:09,  1.71it/s]
Train steps ... :  64%|██████▍   | 64370/100000 [19:01:09<5:47:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 64371/100000 [19:01:09<5:47:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 64372/100000 [19:01:10<5:47:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 64373/100000 [19:01:11<5:47:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 64374/100000 [19:01:11<5:47:26,  1.71it/s]
Train steps ... :  64%|██████▍   | 64375/100000 [19:01:12<5:47:34,  1.71it/s]Step... (64375 / 100000 | Loss: 0.9935635328292847, Learning Rate: 3.580402010050252e-05)
+
                                                                             
Step... (64375 / 100000 | Loss: 0.9319328665733337, Learning Rate: 3.580402010050252e-05)
+
Train steps ... :  64%|██████▍   | 64375/100000 [19:01:12<5:47:34,  1.71it/s]
Train steps ... :  64%|██████▍   | 64376/100000 [19:01:12<5:47:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 64377/100000 [19:01:13<5:47:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 64378/100000 [19:01:13<5:47:44,  1.71it/s]
Train steps ... :  64%|██████▍   | 64379/100000 [19:01:14<5:48:11,  1.71it/s]
Train steps ... :  64%|██████▍   | 64380/100000 [19:01:15<5:48:28,  1.70it/s]
Train steps ... :  64%|██████▍   | 64381/100000 [19:01:15<5:48:48,  1.70it/s]
Train steps ... :  64%|██████▍   | 64382/100000 [19:01:16<5:47:52,  1.71it/s]
Train steps ... :  64%|██████▍   | 64383/100000 [19:01:16<5:47:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 64384/100000 [19:01:17<5:48:11,  1.70it/s]
Train steps ... :  64%|██████▍   | 64385/100000 [19:01:18<5:49:16,  1.70it/s]
Train steps ... :  64%|██████▍   | 64386/100000 [19:01:18<5:48:02,  1.71it/s]
Train steps ... :  64%|██████▍   | 64387/100000 [19:01:19<5:47:48,  1.71it/s]
Train steps ... :  64%|██████▍   | 64388/100000 [19:01:19<5:47:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 64389/100000 [19:01:20<5:47:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 64390/100000 [19:01:20<5:47:16,  1.71it/s]
Train steps ... :  64%|██████▍   | 64391/100000 [19:01:21<5:47:17,  1.71it/s]
Train steps ... :  64%|██████▍   | 64392/100000 [19:01:22<5:47:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 64393/100000 [19:01:22<5:47:49,  1.71it/s]
Train steps ... :  64%|██████▍   | 64394/100000 [19:01:23<5:47:25,  1.71it/s]
Train steps ... :  64%|██████▍   | 64395/100000 [19:01:23<5:49:31,  1.70it/s]
Train steps ... :  64%|██████▍   | 64396/100000 [19:01:24<5:47:52,  1.71it/s]
Train steps ... :  64%|██████▍   | 64397/100000 [19:01:25<5:48:26,  1.70it/s]
Train steps ... :  64%|██████▍   | 64398/100000 [19:01:25<5:47:19,  1.71it/s]
Train steps ... :  64%|██████▍   | 64399/100000 [19:01:26<5:47:51,  1.71it/s]
Train steps ... :  64%|██████▍   | 64400/100000 [19:01:26<5:47:37,  1.71it/s]Step... (64400 / 100000 | Loss: 0.5528591871261597, Learning Rate: 3.5778894472361815e-05)
+
                                                                             
Step... (64400 / 100000 | Loss: 0.7400866150856018, Learning Rate: 3.5778894472361815e-05)
+
Train steps ... :  64%|██████▍   | 64400/100000 [19:01:27<5:47:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 64401/100000 [19:01:27<5:48:06,  1.70it/s]
Train steps ... :  64%|██████▍   | 64402/100000 [19:01:28<5:47:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 64403/100000 [19:01:28<5:48:29,  1.70it/s]
Train steps ... :  64%|██████▍   | 64404/100000 [19:01:29<5:48:27,  1.70it/s]
Train steps ... :  64%|██████▍   | 64405/100000 [19:01:29<5:48:14,  1.70it/s]
Train steps ... :  64%|██████▍   | 64406/100000 [19:01:30<5:48:05,  1.70it/s]
Train steps ... :  64%|██████▍   | 64407/100000 [19:01:30<5:47:44,  1.71it/s]
Train steps ... :  64%|██████▍   | 64408/100000 [19:01:31<5:47:48,  1.71it/s]
Train steps ... :  64%|██████▍   | 64409/100000 [19:01:32<5:47:08,  1.71it/s]
Train steps ... :  64%|██████▍   | 64410/100000 [19:01:32<5:47:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 64411/100000 [19:01:33<5:47:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 64412/100000 [19:01:33<5:48:24,  1.70it/s]
Train steps ... :  64%|██████▍   | 64413/100000 [19:01:34<5:48:40,  1.70it/s]
Train steps ... :  64%|██████▍   | 64414/100000 [19:01:35<5:48:24,  1.70it/s]
Train steps ... :  64%|██████▍   | 64415/100000 [19:01:35<5:47:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 64416/100000 [19:01:36<5:47:21,  1.71it/s]
Train steps ... :  64%|██████▍   | 64417/100000 [19:01:36<5:46:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 64418/100000 [19:01:37<5:46:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 64419/100000 [19:01:37<5:47:26,  1.71it/s]
Train steps ... :  64%|██████▍   | 64420/100000 [19:01:38<5:46:53,  1.71it/s]
Train steps ... :  64%|██████▍   | 64421/100000 [19:01:39<5:47:06,  1.71it/s]
Train steps ... :  64%|██████▍   | 64422/100000 [19:01:39<5:47:05,  1.71it/s]
Train steps ... :  64%|██████▍   | 64423/100000 [19:01:40<5:47:29,  1.71it/s]
Train steps ... :  64%|██████▍   | 64424/100000 [19:01:40<5:47:13,  1.71it/s]
Train steps ... :  64%|██████▍   | 64425/100000 [19:01:41<5:46:57,  1.71it/s]Step... (64425 / 100000 | Loss: 1.1801155805587769, Learning Rate: 3.5753768844221105e-05)
+
                                                                             
Step... (64425 / 100000 | Loss: 0.5846565365791321, Learning Rate: 3.5753768844221105e-05)
+
Train steps ... :  64%|██████▍   | 64425/100000 [19:01:41<5:46:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 64426/100000 [19:01:42<5:46:57,  1.71it/s]
Train steps ... :  64%|██████▍   | 64427/100000 [19:01:42<5:46:46,  1.71it/s]
Train steps ... :  64%|██████▍   | 64428/100000 [19:01:43<5:47:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 64429/100000 [19:01:43<5:47:33,  1.71it/s]
Train steps ... :  64%|██████▍   | 64430/100000 [19:01:44<5:47:27,  1.71it/s]
Train steps ... :  64%|██████▍   | 64431/100000 [19:01:45<5:48:30,  1.70it/s]
Train steps ... :  64%|██████▍   | 64432/100000 [19:01:45<5:49:40,  1.70it/s]
Train steps ... :  64%|██████▍   | 64433/100000 [19:01:46<5:49:14,  1.70it/s]
Train steps ... :  64%|██████▍   | 64434/100000 [19:01:46<5:48:26,  1.70it/s]
Train steps ... :  64%|██████▍   | 64435/100000 [19:01:47<5:47:51,  1.70it/s]
Train steps ... :  64%|██████▍   | 64436/100000 [19:01:47<5:47:12,  1.71it/s]
Train steps ... :  64%|██████▍   | 64437/100000 [19:01:48<5:47:38,  1.70it/s]
Train steps ... :  64%|██████▍   | 64438/100000 [19:01:49<5:47:30,  1.71it/s]
Train steps ... :  64%|██████▍   | 64439/100000 [19:01:49<5:46:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64440/100000 [19:01:50<5:47:07,  1.71it/s]
Train steps ... :  64%|██████▍   | 64441/100000 [19:01:50<5:46:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 64442/100000 [19:01:51<5:46:30,  1.71it/s]
Train steps ... :  64%|██████▍   | 64443/100000 [19:01:52<5:48:01,  1.70it/s]
Train steps ... :  64%|██████▍   | 64444/100000 [19:01:52<5:47:07,  1.71it/s]
Train steps ... :  64%|██████▍   | 64445/100000 [19:01:53<5:47:09,  1.71it/s]
Train steps ... :  64%|██████▍   | 64446/100000 [19:01:53<5:46:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 64447/100000 [19:01:54<5:47:00,  1.71it/s]
Train steps ... :  64%|██████▍   | 64448/100000 [19:01:54<5:46:54,  1.71it/s]
Train steps ... :  64%|██████▍   | 64449/100000 [19:01:55<5:46:44,  1.71it/s]
Train steps ... :  64%|██████▍   | 64450/100000 [19:01:56<5:47:31,  1.70it/s]Step... (64450 / 100000 | Loss: 0.6273990273475647, Learning Rate: 3.57286432160804e-05)
+
                                                                             
Step... (64450 / 100000 | Loss: 0.8706067800521851, Learning Rate: 3.57286432160804e-05)
+
Train steps ... :  64%|██████▍   | 64450/100000 [19:01:56<5:47:31,  1.70it/s]
Train steps ... :  64%|██████▍   | 64451/100000 [19:01:56<5:46:50,  1.71it/s]
Train steps ... :  64%|██████▍   | 64452/100000 [19:01:57<5:47:31,  1.70it/s]
Train steps ... :  64%|██████▍   | 64453/100000 [19:01:57<5:47:22,  1.71it/s]
Train steps ... :  64%|██████▍   | 64454/100000 [19:01:58<5:47:00,  1.71it/s]
Train steps ... :  64%|██████▍   | 64455/100000 [19:01:59<5:48:00,  1.70it/s]
Train steps ... :  64%|██████▍   | 64456/100000 [19:01:59<5:48:05,  1.70it/s]
Train steps ... :  64%|██████▍   | 64457/100000 [19:02:00<5:48:08,  1.70it/s]
Train steps ... :  64%|██████▍   | 64458/100000 [19:02:00<5:47:17,  1.71it/s]
Train steps ... :  64%|██████▍   | 64459/100000 [19:02:01<5:46:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 64460/100000 [19:02:02<5:47:23,  1.71it/s]
Train steps ... :  64%|██████▍   | 64461/100000 [19:02:02<5:46:56,  1.71it/s]
Train steps ... :  64%|██████▍   | 64462/100000 [19:02:03<5:46:47,  1.71it/s]
Train steps ... :  64%|██████▍   | 64463/100000 [19:02:03<5:47:42,  1.70it/s]
Train steps ... :  64%|██████▍   | 64464/100000 [19:02:04<5:46:58,  1.71it/s]
Train steps ... :  64%|██████▍   | 64465/100000 [19:02:04<5:47:40,  1.70it/s]
Train steps ... :  64%|██████▍   | 64466/100000 [19:02:05<5:46:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 64467/100000 [19:02:06<5:46:51,  1.71it/s]
Train steps ... :  64%|██████▍   | 64468/100000 [19:02:06<5:46:22,  1.71it/s]
Train steps ... :  64%|██████▍   | 64469/100000 [19:02:07<5:46:24,  1.71it/s]
Train steps ... :  64%|██████▍   | 64470/100000 [19:02:07<5:46:17,  1.71it/s]
Train steps ... :  64%|██████▍   | 64471/100000 [19:02:08<5:47:35,  1.70it/s]
Train steps ... :  64%|██████▍   | 64472/100000 [19:02:09<5:46:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 64473/100000 [19:02:09<5:47:21,  1.70it/s]
Train steps ... :  64%|██████▍   | 64474/100000 [19:02:10<5:46:59,  1.71it/s]
Train steps ... :  64%|██████▍   | 64475/100000 [19:02:10<5:46:39,  1.71it/s]Step... (64475 / 100000 | Loss: 0.6995859146118164, Learning Rate: 3.57035175879397e-05)
+
                                                                             
Step... (64475 / 100000 | Loss: 0.5653340816497803, Learning Rate: 3.57035175879397e-05)
+
Train steps ... :  64%|██████▍   | 64475/100000 [19:02:11<5:46:39,  1.71it/s]
Train steps ... :  64%|██████▍   | 64476/100000 [19:02:11<5:47:29,  1.70it/s]
Train steps ... :  64%|██████▍   | 64477/100000 [19:02:11<5:47:15,  1.70it/s]
Train steps ... :  64%|██████▍   | 64478/100000 [19:02:12<5:46:45,  1.71it/s]
Train steps ... :  64%|██████▍   | 64479/100000 [19:02:13<5:47:22,  1.70it/s]
Train steps ... :  64%|██████▍   | 64480/100000 [19:02:13<5:47:03,  1.71it/s]
Train steps ... :  64%|██████▍   | 64481/100000 [19:02:14<5:47:11,  1.71it/s]
Train steps ... :  64%|██████▍   | 64482/100000 [19:02:14<5:46:44,  1.71it/s]
Train steps ... :  64%|██████▍   | 64483/100000 [19:02:15<5:46:42,  1.71it/s]
Train steps ... :  64%|██████▍   | 64484/100000 [19:02:16<5:46:31,  1.71it/s]
Train steps ... :  64%|██████▍   | 64485/100000 [19:02:16<5:46:55,  1.71it/s]
Train steps ... :  64%|██████▍   | 64486/100000 [19:02:17<5:46:38,  1.71it/s]
Train steps ... :  64%|██████▍   | 64487/100000 [19:02:17<5:46:40,  1.71it/s]
Train steps ... :  64%|██████▍   | 64488/100000 [19:02:18<5:46:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 64489/100000 [19:02:19<5:46:04,  1.71it/s]
Train steps ... :  64%|██████▍   | 64490/100000 [19:02:19<5:46:05,  1.71it/s]
Train steps ... :  64%|██████▍   | 64491/100000 [19:02:20<5:45:48,  1.71it/s]
Train steps ... :  64%|██████▍   | 64492/100000 [19:02:20<5:46:28,  1.71it/s]
Train steps ... :  64%|██████▍   | 64493/100000 [19:02:21<5:46:14,  1.71it/s]
Train steps ... :  64%|██████▍   | 64494/100000 [19:02:21<5:46:37,  1.71it/s]
Train steps ... :  64%|██████▍   | 64495/100000 [19:02:22<5:46:41,  1.71it/s]
Train steps ... :  64%|██████▍   | 64496/100000 [19:02:23<5:46:44,  1.71it/s]
Train steps ... :  64%|██████▍   | 64497/100000 [19:02:23<5:46:11,  1.71it/s]
Train steps ... :  64%|██████▍   | 64498/100000 [19:02:24<5:46:24,  1.71it/s]
Train steps ... :  64%|██████▍   | 64499/100000 [19:02:24<5:46:20,  1.71it/s]
Train steps ... :  64%|██████▍   | 64500/100000 [19:02:25<5:46:58,  1.71it/s]Step... (64500 / 100000 | Loss: 0.617401123046875, Learning Rate: 3.5678391959798995e-05)
+
                                                                             
Step... (64500 / 100000 | Loss: 0.6681485176086426, Learning Rate: 3.5678391959798995e-05)
+
Train steps ... :  64%|██████▍   | 64500/100000 [19:02:25<5:46:58,  1.71it/s]
Train steps ... :  65%|██████▍   | 64501/100000 [19:02:26<5:46:07,  1.71it/s]
Train steps ... :  65%|██████▍   | 64502/100000 [19:02:26<5:46:09,  1.71it/s]
Train steps ... :  65%|██████▍   | 64503/100000 [19:02:27<5:45:53,  1.71it/s]
Train steps ... :  65%|██████▍   | 64504/100000 [19:02:27<5:46:56,  1.71it/s]
Train steps ... :  65%|██████▍   | 64505/100000 [19:02:28<5:47:24,  1.70it/s]
Train steps ... :  65%|██████▍   | 64506/100000 [19:02:28<5:46:59,  1.70it/s]
Train steps ... :  65%|██████▍   | 64507/100000 [19:02:29<5:46:52,  1.71it/s]
Train steps ... :  65%|██████▍   | 64508/100000 [19:02:30<5:46:35,  1.71it/s]
Train steps ... :  65%|██████▍   | 64509/100000 [19:02:30<5:46:59,  1.70it/s]
Train steps ... :  65%|██████▍   | 64510/100000 [19:02:31<5:45:49,  1.71it/s]
Train steps ... :  65%|██████▍   | 64511/100000 [19:02:31<5:46:51,  1.71it/s]
Train steps ... :  65%|██████▍   | 64512/100000 [19:02:32<5:46:07,  1.71it/s]
Train steps ... :  65%|██████▍   | 64513/100000 [19:02:33<5:46:24,  1.71it/s]
Train steps ... :  65%|██████▍   | 64514/100000 [19:02:33<5:46:06,  1.71it/s]
Train steps ... :  65%|██████▍   | 64515/100000 [19:02:34<5:45:58,  1.71it/s]
Train steps ... :  65%|██████▍   | 64516/100000 [19:02:34<5:45:46,  1.71it/s]
Train steps ... :  65%|██████▍   | 64517/100000 [19:02:35<5:46:02,  1.71it/s]
Train steps ... :  65%|██████▍   | 64518/100000 [19:02:35<5:46:06,  1.71it/s]
Train steps ... :  65%|██████▍   | 64519/100000 [19:02:36<5:46:20,  1.71it/s]
Train steps ... :  65%|██████▍   | 64520/100000 [19:02:37<5:46:02,  1.71it/s]
Train steps ... :  65%|██████▍   | 64521/100000 [19:02:37<5:46:03,  1.71it/s]
Train steps ... :  65%|██████▍   | 64522/100000 [19:02:38<5:45:50,  1.71it/s]
Train steps ... :  65%|██████▍   | 64523/100000 [19:02:38<5:45:45,  1.71it/s]
Train steps ... :  65%|██████▍   | 64524/100000 [19:02:39<5:45:45,  1.71it/s]
Train steps ... :  65%|██████▍   | 64525/100000 [19:02:40<5:46:28,  1.71it/s]Step... (64525 / 100000 | Loss: 0.6454149484634399, Learning Rate: 3.565326633165829e-05)
+
                                                                             
Step... (64525 / 100000 | Loss: 0.7039873600006104, Learning Rate: 3.565326633165829e-05)
+
Train steps ... :  65%|██████▍   | 64525/100000 [19:02:40<5:46:28,  1.71it/s]
Train steps ... :  65%|██████▍   | 64526/100000 [19:02:40<5:46:26,  1.71it/s]
Train steps ... :  65%|██████▍   | 64527/100000 [19:02:41<5:46:41,  1.71it/s]
Train steps ... :  65%|██████▍   | 64528/100000 [19:02:41<5:47:44,  1.70it/s]
Train steps ... :  65%|██████▍   | 64529/100000 [19:02:42<5:47:32,  1.70it/s]
Train steps ... :  65%|██████▍   | 64530/100000 [19:02:43<5:46:16,  1.71it/s]
Train steps ... :  65%|██████▍   | 64531/100000 [19:02:43<5:47:02,  1.70it/s]
Train steps ... :  65%|██████▍   | 64532/100000 [19:02:44<5:47:14,  1.70it/s]
Train steps ... :  65%|██████▍   | 64533/100000 [19:02:44<5:46:24,  1.71it/s]
Train steps ... :  65%|██████▍   | 64534/100000 [19:02:45<5:47:07,  1.70it/s]
Train steps ... :  65%|██████▍   | 64535/100000 [19:02:45<5:46:52,  1.70it/s]
Train steps ... :  65%|██████▍   | 64536/100000 [19:02:46<5:46:04,  1.71it/s]
Train steps ... :  65%|██████▍   | 64537/100000 [19:02:47<5:47:00,  1.70it/s]
Train steps ... :  65%|██████▍   | 64538/100000 [19:02:47<5:46:58,  1.70it/s]
Train steps ... :  65%|██████▍   | 64539/100000 [19:02:48<5:46:26,  1.71it/s]
Train steps ... :  65%|██████▍   | 64540/100000 [19:02:48<5:46:42,  1.70it/s]
Train steps ... :  65%|██████▍   | 64541/100000 [19:02:49<5:45:31,  1.71it/s]
Train steps ... :  65%|██████▍   | 64542/100000 [19:02:50<5:46:39,  1.70it/s]
Train steps ... :  65%|██████▍   | 64543/100000 [19:02:50<5:46:34,  1.71it/s]
Train steps ... :  65%|██████▍   | 64544/100000 [19:02:51<5:46:03,  1.71it/s]
Train steps ... :  65%|██████▍   | 64545/100000 [19:02:51<5:45:52,  1.71it/s]
Train steps ... :  65%|██████▍   | 64546/100000 [19:02:52<5:46:05,  1.71it/s]
Train steps ... :  65%|██████▍   | 64547/100000 [19:02:52<5:46:10,  1.71it/s]
Train steps ... :  65%|██████▍   | 64548/100000 [19:02:53<5:46:04,  1.71it/s]
Train steps ... :  65%|██████▍   | 64549/100000 [19:02:54<5:46:03,  1.71it/s]
Train steps ... :  65%|██████▍   | 64550/100000 [19:02:54<5:46:16,  1.71it/s]Step... (64550 / 100000 | Loss: 0.6111820340156555, Learning Rate: 3.562814070351759e-05)
+
                                                                             
Step... (64550 / 100000 | Loss: 0.8888300061225891, Learning Rate: 3.562814070351759e-05)
+
Train steps ... :  65%|██████▍   | 64550/100000 [19:02:55<5:46:16,  1.71it/s]
Train steps ... :  65%|██████▍   | 64551/100000 [19:02:55<5:45:55,  1.71it/s]
Train steps ... :  65%|██████▍   | 64552/100000 [19:02:55<5:46:29,  1.71it/s]
Train steps ... :  65%|██████▍   | 64553/100000 [19:02:56<5:46:34,  1.70it/s]
Train steps ... :  65%|██████▍   | 64554/100000 [19:02:57<5:46:06,  1.71it/s]
Train steps ... :  65%|██████▍   | 64555/100000 [19:02:57<5:46:02,  1.71it/s]
Train steps ... :  65%|██████▍   | 64556/100000 [19:02:58<5:46:07,  1.71it/s]
Train steps ... :  65%|██████▍   | 64557/100000 [19:02:58<5:45:46,  1.71it/s]
Train steps ... :  65%|██████▍   | 64558/100000 [19:02:59<5:45:50,  1.71it/s]
Train steps ... :  65%|██████▍   | 64559/100000 [19:03:00<5:45:23,  1.71it/s]
Train steps ... :  65%|██████▍   | 64560/100000 [19:03:00<5:45:16,  1.71it/s]
Train steps ... :  65%|██████▍   | 64561/100000 [19:03:01<5:45:22,  1.71it/s]
Train steps ... :  65%|██████▍   | 64562/100000 [19:03:01<5:45:40,  1.71it/s]
Train steps ... :  65%|██████▍   | 64563/100000 [19:03:02<5:45:45,  1.71it/s]
Train steps ... :  65%|██████▍   | 64564/100000 [19:03:02<5:46:28,  1.70it/s]
Train steps ... :  65%|██████▍   | 64565/100000 [19:03:03<5:47:22,  1.70it/s]
Train steps ... :  65%|██████▍   | 64566/100000 [19:03:04<5:48:39,  1.69it/s]
Train steps ... :  65%|██████▍   | 64567/100000 [19:03:04<5:47:53,  1.70it/s]
Train steps ... :  65%|██████▍   | 64568/100000 [19:03:05<5:47:15,  1.70it/s]
Train steps ... :  65%|██████▍   | 64569/100000 [19:03:05<5:47:46,  1.70it/s]
Train steps ... :  65%|██████▍   | 64570/100000 [19:03:06<5:46:52,  1.70it/s]
Train steps ... :  65%|██████▍   | 64571/100000 [19:03:07<5:49:34,  1.69it/s]
Train steps ... :  65%|██████▍   | 64572/100000 [19:03:07<5:48:40,  1.69it/s]
Train steps ... :  65%|██████▍   | 64573/100000 [19:03:08<5:48:55,  1.69it/s]
Train steps ... :  65%|██████▍   | 64574/100000 [19:03:08<5:47:16,  1.70it/s]
Train steps ... :  65%|██████▍   | 64575/100000 [19:03:09<5:47:18,  1.70it/s]Step... (64575 / 100000 | Loss: 0.5905587077140808, Learning Rate: 3.560301507537689e-05)
+
                                                                             
Step... (64575 / 100000 | Loss: 0.7022945880889893, Learning Rate: 3.560301507537689e-05)
+
Train steps ... :  65%|██████▍   | 64575/100000 [19:03:09<5:47:18,  1.70it/s]
Train steps ... :  65%|██████▍   | 64576/100000 [19:03:10<5:48:49,  1.69it/s]
Train steps ... :  65%|██████▍   | 64577/100000 [19:03:10<5:46:58,  1.70it/s]
Train steps ... :  65%|██████▍   | 64578/100000 [19:03:11<5:46:55,  1.70it/s]
Train steps ... :  65%|██████▍   | 64579/100000 [19:03:11<5:46:31,  1.70it/s]
Train steps ... :  65%|██████▍   | 64580/100000 [19:03:12<5:46:14,  1.70it/s]
Train steps ... :  65%|██████▍   | 64581/100000 [19:03:12<5:46:18,  1.70it/s]
Train steps ... :  65%|██████▍   | 64582/100000 [19:03:13<5:46:05,  1.71it/s]
Train steps ... :  65%|██████▍   | 64583/100000 [19:03:14<5:45:49,  1.71it/s]
Train steps ... :  65%|██████▍   | 64584/100000 [19:03:14<5:45:34,  1.71it/s]
Train steps ... :  65%|██████▍   | 64585/100000 [19:03:15<5:45:34,  1.71it/s]
Train steps ... :  65%|██████▍   | 64586/100000 [19:03:15<5:46:23,  1.70it/s]
Train steps ... :  65%|██████▍   | 64587/100000 [19:03:16<5:45:44,  1.71it/s]
Train steps ... :  65%|██████▍   | 64588/100000 [19:03:17<5:46:11,  1.70it/s]
Train steps ... :  65%|██████▍   | 64589/100000 [19:03:17<5:46:38,  1.70it/s]
Train steps ... :  65%|██████▍   | 64590/100000 [19:03:18<5:45:47,  1.71it/s]
Train steps ... :  65%|██████▍   | 64591/100000 [19:03:18<5:45:43,  1.71it/s]
Train steps ... :  65%|██████▍   | 64592/100000 [19:03:19<5:45:15,  1.71it/s]
Train steps ... :  65%|██████▍   | 64593/100000 [19:03:19<5:45:00,  1.71it/s]
Train steps ... :  65%|██████▍   | 64594/100000 [19:03:20<5:46:07,  1.70it/s]
Train steps ... :  65%|██████▍   | 64595/100000 [19:03:21<5:46:40,  1.70it/s]
Train steps ... :  65%|██████▍   | 64596/100000 [19:03:21<5:46:43,  1.70it/s]
Train steps ... :  65%|██████▍   | 64597/100000 [19:03:22<5:45:54,  1.71it/s]
Train steps ... :  65%|██████▍   | 64598/100000 [19:03:22<5:45:28,  1.71it/s]
Train steps ... :  65%|██████▍   | 64599/100000 [19:03:23<5:47:12,  1.70it/s]
Train steps ... :  65%|██████▍   | 64600/100000 [19:03:24<5:47:35,  1.70it/s]Step... (64600 / 100000 | Loss: 0.5764319896697998, Learning Rate: 3.557788944723618e-05)
+
                                                                             
Step... (64600 / 100000 | Loss: 0.9562422037124634, Learning Rate: 3.557788944723618e-05)
+
Train steps ... :  65%|██████▍   | 64600/100000 [19:03:24<5:47:35,  1.70it/s]
Train steps ... :  65%|██████▍   | 64601/100000 [19:03:24<5:47:05,  1.70it/s]
Train steps ... :  65%|██████▍   | 64602/100000 [19:03:25<5:48:12,  1.69it/s]
Train steps ... :  65%|██████▍   | 64603/100000 [19:03:25<5:46:44,  1.70it/s]
Train steps ... :  65%|██████▍   | 64604/100000 [19:03:26<5:45:59,  1.71it/s]
Train steps ... :  65%|██████▍   | 64605/100000 [19:03:27<5:46:58,  1.70it/s]
Train steps ... :  65%|██████▍   | 64606/100000 [19:03:27<5:47:12,  1.70it/s]
Train steps ... :  65%|██████▍   | 64607/100000 [19:03:28<5:47:30,  1.70it/s]
Train steps ... :  65%|██████▍   | 64608/100000 [19:03:28<5:46:05,  1.70it/s]
Train steps ... :  65%|██████▍   | 64609/100000 [19:03:29<5:46:18,  1.70it/s]
Train steps ... :  65%|██████▍   | 64610/100000 [19:03:29<5:46:21,  1.70it/s]
Train steps ... :  65%|██████▍   | 64611/100000 [19:03:30<5:45:58,  1.70it/s]
Train steps ... :  65%|██████▍   | 64612/100000 [19:03:31<5:48:52,  1.69it/s]
Train steps ... :  65%|██████▍   | 64613/100000 [19:03:31<5:47:36,  1.70it/s]
Train steps ... :  65%|██████▍   | 64614/100000 [19:03:32<5:47:52,  1.70it/s]
Train steps ... :  65%|██████▍   | 64615/100000 [19:03:32<5:46:15,  1.70it/s]
Train steps ... :  65%|██████▍   | 64616/100000 [19:03:33<5:46:48,  1.70it/s]
Train steps ... :  65%|██████▍   | 64617/100000 [19:03:34<5:46:47,  1.70it/s]
Train steps ... :  65%|██████▍   | 64618/100000 [19:03:34<5:45:50,  1.71it/s]
Train steps ... :  65%|██████▍   | 64619/100000 [19:03:35<5:45:58,  1.70it/s]
Train steps ... :  65%|██████▍   | 64620/100000 [19:03:35<5:46:04,  1.70it/s]
Train steps ... :  65%|██████▍   | 64621/100000 [19:03:36<5:45:37,  1.71it/s]
Train steps ... :  65%|██████▍   | 64622/100000 [19:03:37<5:46:02,  1.70it/s]
Train steps ... :  65%|██████▍   | 64623/100000 [19:03:37<5:45:40,  1.71it/s]
Train steps ... :  65%|██████▍   | 64624/100000 [19:03:38<5:44:56,  1.71it/s]
Train steps ... :  65%|██████▍   | 64625/100000 [19:03:38<5:45:03,  1.71it/s]Step... (64625 / 100000 | Loss: 0.6793789863586426, Learning Rate: 3.555276381909548e-05)
+
                                                                             
Step... (64625 / 100000 | Loss: 1.0041658878326416, Learning Rate: 3.555276381909548e-05)
+
Train steps ... :  65%|██████▍   | 64625/100000 [19:03:39<5:45:03,  1.71it/s]
Train steps ... :  65%|██████▍   | 64626/100000 [19:03:39<5:45:22,  1.71it/s]
Train steps ... :  65%|██████▍   | 64627/100000 [19:03:39<5:45:30,  1.71it/s]
Train steps ... :  65%|██████▍   | 64628/100000 [19:03:40<5:45:32,  1.71it/s]
Train steps ... :  65%|██████▍   | 64629/100000 [19:03:41<5:45:22,  1.71it/s]
Train steps ... :  65%|██████▍   | 64630/100000 [19:03:41<5:45:02,  1.71it/s]
Train steps ... :  65%|██████▍   | 64631/100000 [19:03:42<5:44:57,  1.71it/s]
Train steps ... :  65%|██████▍   | 64632/100000 [19:03:42<5:45:37,  1.71it/s]
Train steps ... :  65%|██████▍   | 64633/100000 [19:03:43<5:45:31,  1.71it/s]
Train steps ... :  65%|██████▍   | 64634/100000 [19:03:44<5:45:29,  1.71it/s]
Train steps ... :  65%|██████▍   | 64635/100000 [19:03:44<5:46:41,  1.70it/s]
Train steps ... :  65%|██████▍   | 64636/100000 [19:03:45<5:45:30,  1.71it/s]
Train steps ... :  65%|██████▍   | 64637/100000 [19:03:45<5:46:06,  1.70it/s]
Train steps ... :  65%|██████▍   | 64638/100000 [19:03:46<5:45:44,  1.70it/s]
Train steps ... :  65%|██████▍   | 64639/100000 [19:03:46<5:45:48,  1.70it/s]
Train steps ... :  65%|██████▍   | 64640/100000 [19:03:47<5:45:13,  1.71it/s]
Train steps ... :  65%|██████▍   | 64641/100000 [19:03:48<5:45:36,  1.71it/s]
Train steps ... :  65%|██████▍   | 64642/100000 [19:03:48<5:45:52,  1.70it/s]
Train steps ... :  65%|██████▍   | 64643/100000 [19:03:49<5:46:06,  1.70it/s]
Train steps ... :  65%|██████▍   | 64644/100000 [19:03:49<5:45:45,  1.70it/s]
Train steps ... :  65%|██████▍   | 64645/100000 [19:03:50<5:45:40,  1.70it/s]
Train steps ... :  65%|██████▍   | 64646/100000 [19:03:51<5:44:55,  1.71it/s]
Train steps ... :  65%|██████▍   | 64647/100000 [19:03:51<5:45:01,  1.71it/s]
Train steps ... :  65%|██████▍   | 64648/100000 [19:03:52<5:45:30,  1.71it/s]
Train steps ... :  65%|██████▍   | 64649/100000 [19:03:52<5:45:30,  1.71it/s]
Train steps ... :  65%|██████▍   | 64650/100000 [19:03:53<5:45:38,  1.70it/s]Step... (64650 / 100000 | Loss: 0.7703125476837158, Learning Rate: 3.5527638190954775e-05)
+
                                                                             
Step... (64650 / 100000 | Loss: 0.8693523406982422, Learning Rate: 3.5527638190954775e-05)
+
Train steps ... :  65%|██████▍   | 64650/100000 [19:03:53<5:45:38,  1.70it/s]
Train steps ... :  65%|██████▍   | 64651/100000 [19:03:54<5:44:55,  1.71it/s]
Train steps ... :  65%|██████▍   | 64652/100000 [19:03:54<5:44:31,  1.71it/s]
Train steps ... :  65%|██████▍   | 64653/100000 [19:03:55<5:44:29,  1.71it/s]
Train steps ... :  65%|██████▍   | 64654/100000 [19:03:55<5:44:38,  1.71it/s]
Train steps ... :  65%|██████▍   | 64655/100000 [19:03:56<5:44:57,  1.71it/s]
Train steps ... :  65%|██████▍   | 64656/100000 [19:03:56<5:45:31,  1.70it/s]
Train steps ... :  65%|██████▍   | 64657/100000 [19:03:57<5:45:49,  1.70it/s]
Train steps ... :  65%|██████▍   | 64658/100000 [19:03:58<5:44:30,  1.71it/s]
Train steps ... :  65%|██████▍   | 64659/100000 [19:03:58<5:45:01,  1.71it/s]
Train steps ... :  65%|██████▍   | 64660/100000 [19:03:59<5:44:40,  1.71it/s]
Train steps ... :  65%|██████▍   | 64661/100000 [19:03:59<5:44:59,  1.71it/s]
Train steps ... :  65%|██████▍   | 64662/100000 [19:04:00<5:45:50,  1.70it/s]
Train steps ... :  65%|██████▍   | 64663/100000 [19:04:01<5:45:03,  1.71it/s]
Train steps ... :  65%|██████▍   | 64664/100000 [19:04:01<5:45:11,  1.71it/s]
Train steps ... :  65%|██████▍   | 64665/100000 [19:04:02<5:45:05,  1.71it/s]
Train steps ... :  65%|██████▍   | 64666/100000 [19:04:02<5:43:47,  1.71it/s]
Train steps ... :  65%|██████▍   | 64667/100000 [19:04:03<5:44:06,  1.71it/s]
Train steps ... :  65%|██████▍   | 64668/100000 [19:04:03<5:43:51,  1.71it/s]
Train steps ... :  65%|██████▍   | 64669/100000 [19:04:04<5:43:42,  1.71it/s]
Train steps ... :  65%|██████▍   | 64670/100000 [19:04:05<5:44:07,  1.71it/s]
Train steps ... :  65%|██████▍   | 64671/100000 [19:04:05<5:44:02,  1.71it/s]
Train steps ... :  65%|██████▍   | 64672/100000 [19:04:06<5:43:51,  1.71it/s]
Train steps ... :  65%|██████▍   | 64673/100000 [19:04:06<5:45:03,  1.71it/s]
Train steps ... :  65%|██████▍   | 64674/100000 [19:04:07<5:44:14,  1.71it/s]
Train steps ... :  65%|██████▍   | 64675/100000 [19:04:08<5:44:28,  1.71it/s]Step... (64675 / 100000 | Loss: 0.7444447875022888, Learning Rate: 3.550251256281407e-05)
+
                                                                             
Step... (64675 / 100000 | Loss: 0.8678774237632751, Learning Rate: 3.550251256281407e-05)
+
Train steps ... :  65%|██████▍   | 64675/100000 [19:04:08<5:44:28,  1.71it/s]
Train steps ... :  65%|██████▍   | 64676/100000 [19:04:08<5:45:51,  1.70it/s]
Train steps ... :  65%|██████▍   | 64677/100000 [19:04:09<5:44:52,  1.71it/s]
Train steps ... :  65%|██████▍   | 64678/100000 [19:04:09<5:44:59,  1.71it/s]
Train steps ... :  65%|██████▍   | 64679/100000 [19:04:10<5:44:02,  1.71it/s]
Train steps ... :  65%|██████▍   | 64680/100000 [19:04:11<5:43:54,  1.71it/s]
Train steps ... :  65%|██████▍   | 64681/100000 [19:04:11<5:43:55,  1.71it/s]
Train steps ... :  65%|██████▍   | 64682/100000 [19:04:12<5:44:37,  1.71it/s]
Train steps ... :  65%|██████▍   | 64683/100000 [19:04:12<5:44:46,  1.71it/s]
Train steps ... :  65%|██████▍   | 64684/100000 [19:04:13<5:44:09,  1.71it/s]
Train steps ... :  65%|██████▍   | 64685/100000 [19:04:13<5:44:10,  1.71it/s]
Train steps ... :  65%|██████▍   | 64686/100000 [19:04:14<5:43:50,  1.71it/s]
Train steps ... :  65%|██████▍   | 64687/100000 [19:04:15<5:44:19,  1.71it/s]
Train steps ... :  65%|██████▍   | 64688/100000 [19:04:15<5:45:14,  1.70it/s]
Train steps ... :  65%|██████▍   | 64689/100000 [19:04:16<5:45:09,  1.71it/s]
Train steps ... :  65%|██████▍   | 64690/100000 [19:04:16<5:44:49,  1.71it/s]
Train steps ... :  65%|██████▍   | 64691/100000 [19:04:17<5:44:37,  1.71it/s]
Train steps ... :  65%|██████▍   | 64692/100000 [19:04:18<5:45:26,  1.70it/s]
Train steps ... :  65%|██████▍   | 64693/100000 [19:04:18<5:44:59,  1.71it/s]
Train steps ... :  65%|██████▍   | 64694/100000 [19:04:19<5:45:07,  1.71it/s]
Train steps ... :  65%|██████▍   | 64695/100000 [19:04:19<5:45:14,  1.70it/s]
Train steps ... :  65%|██████▍   | 64696/100000 [19:04:20<5:45:26,  1.70it/s]
Train steps ... :  65%|██████▍   | 64697/100000 [19:04:20<5:45:03,  1.71it/s]
Train steps ... :  65%|██████▍   | 64698/100000 [19:04:21<5:44:39,  1.71it/s]
Train steps ... :  65%|██████▍   | 64699/100000 [19:04:22<5:44:15,  1.71it/s]
Train steps ... :  65%|██████▍   | 64700/100000 [19:04:22<5:44:13,  1.71it/s]Step... (64700 / 100000 | Loss: 0.7393635511398315, Learning Rate: 3.547738693467337e-05)
+
                                                                             
Step... (64700 / 100000 | Loss: 0.6313965320587158, Learning Rate: 3.547738693467337e-05)
+
Train steps ... :  65%|██████▍   | 64700/100000 [19:04:23<5:44:13,  1.71it/s]
Train steps ... :  65%|██████▍   | 64701/100000 [19:04:23<5:44:30,  1.71it/s]
Train steps ... :  65%|██████▍   | 64702/100000 [19:04:23<5:43:58,  1.71it/s]
Train steps ... :  65%|██████▍   | 64703/100000 [19:04:24<5:44:17,  1.71it/s]
Train steps ... :  65%|██████▍   | 64704/100000 [19:04:25<5:44:33,  1.71it/s]
Train steps ... :  65%|██████▍   | 64705/100000 [19:04:25<5:44:31,  1.71it/s]
Train steps ... :  65%|██████▍   | 64706/100000 [19:04:26<5:44:23,  1.71it/s]
Train steps ... :  65%|██████▍   | 64707/100000 [19:04:26<5:44:13,  1.71it/s]
Train steps ... :  65%|██████▍   | 64708/100000 [19:04:27<5:44:33,  1.71it/s]
Train steps ... :  65%|██████▍   | 64709/100000 [19:04:27<5:44:09,  1.71it/s]
Train steps ... :  65%|██████▍   | 64710/100000 [19:04:28<5:44:10,  1.71it/s]
Train steps ... :  65%|██████▍   | 64711/100000 [19:04:29<5:44:37,  1.71it/s]
Train steps ... :  65%|██████▍   | 64712/100000 [19:04:29<5:44:53,  1.71it/s]
Train steps ... :  65%|██████▍   | 64713/100000 [19:04:30<5:44:09,  1.71it/s]
Train steps ... :  65%|██████▍   | 64714/100000 [19:04:30<5:44:14,  1.71it/s]
Train steps ... :  65%|██████▍   | 64715/100000 [19:04:31<5:44:47,  1.71it/s]
Train steps ... :  65%|██████▍   | 64716/100000 [19:04:32<5:44:01,  1.71it/s]
Train steps ... :  65%|██████▍   | 64717/100000 [19:04:32<5:43:50,  1.71it/s]
Train steps ... :  65%|██████▍   | 64718/100000 [19:04:33<5:44:44,  1.71it/s]
Train steps ... :  65%|██████▍   | 64719/100000 [19:04:33<5:44:03,  1.71it/s]
Train steps ... :  65%|██████▍   | 64720/100000 [19:04:34<5:44:16,  1.71it/s]
Train steps ... :  65%|██████▍   | 64721/100000 [19:04:35<5:44:23,  1.71it/s]
Train steps ... :  65%|██████▍   | 64722/100000 [19:04:35<5:43:50,  1.71it/s]
Train steps ... :  65%|██████▍   | 64723/100000 [19:04:36<5:44:01,  1.71it/s]
Train steps ... :  65%|██████▍   | 64724/100000 [19:04:36<5:44:10,  1.71it/s]
Train steps ... :  65%|██████▍   | 64725/100000 [19:04:37<5:43:56,  1.71it/s]Step... (64725 / 100000 | Loss: 0.7208455801010132, Learning Rate: 3.5452261306532665e-05)
+
                                                                             
Step... (64725 / 100000 | Loss: 0.9302248358726501, Learning Rate: 3.5452261306532665e-05)
+
Train steps ... :  65%|██████▍   | 64725/100000 [19:04:37<5:43:56,  1.71it/s]
Train steps ... :  65%|██████▍   | 64726/100000 [19:04:37<5:44:43,  1.71it/s]
Train steps ... :  65%|██████▍   | 64727/100000 [19:04:38<5:44:11,  1.71it/s]
Train steps ... :  65%|██████▍   | 64728/100000 [19:04:39<5:43:59,  1.71it/s]
Train steps ... :  65%|██████▍   | 64729/100000 [19:04:39<5:43:41,  1.71it/s]
Train steps ... :  65%|██████▍   | 64730/100000 [19:04:40<5:43:58,  1.71it/s]
Train steps ... :  65%|██████▍   | 64731/100000 [19:04:40<5:44:00,  1.71it/s]
Train steps ... :  65%|██████▍   | 64732/100000 [19:04:41<5:43:55,  1.71it/s]
Train steps ... :  65%|██████▍   | 64733/100000 [19:04:42<5:43:54,  1.71it/s]
Train steps ... :  65%|██████▍   | 64734/100000 [19:04:42<5:43:26,  1.71it/s]
Train steps ... :  65%|██████▍   | 64735/100000 [19:04:43<5:43:45,  1.71it/s]
Train steps ... :  65%|██████▍   | 64736/100000 [19:04:43<5:43:25,  1.71it/s]
Train steps ... :  65%|██████▍   | 64737/100000 [19:04:44<5:43:23,  1.71it/s]
Train steps ... :  65%|██████▍   | 64738/100000 [19:04:44<5:43:44,  1.71it/s]
Train steps ... :  65%|██████▍   | 64739/100000 [19:04:45<5:43:26,  1.71it/s]
Train steps ... :  65%|██████▍   | 64740/100000 [19:04:46<5:43:46,  1.71it/s]
Train steps ... :  65%|██████▍   | 64741/100000 [19:04:46<5:45:04,  1.70it/s]
Train steps ... :  65%|██████▍   | 64742/100000 [19:04:47<5:45:28,  1.70it/s]
Train steps ... :  65%|██████▍   | 64743/100000 [19:04:47<5:45:23,  1.70it/s]
Train steps ... :  65%|██████▍   | 64744/100000 [19:04:48<5:44:18,  1.71it/s]
Train steps ... :  65%|██████▍   | 64745/100000 [19:04:49<5:45:02,  1.70it/s]
Train steps ... :  65%|██████▍   | 64746/100000 [19:04:49<5:44:40,  1.70it/s]
Train steps ... :  65%|██████▍   | 64747/100000 [19:04:50<5:43:57,  1.71it/s]
Train steps ... :  65%|██████▍   | 64748/100000 [19:04:50<5:43:57,  1.71it/s]
Train steps ... :  65%|██████▍   | 64749/100000 [19:04:51<5:44:26,  1.71it/s]
Train steps ... :  65%|██████▍   | 64750/100000 [19:04:51<5:43:53,  1.71it/s]Step... (64750 / 100000 | Loss: 1.0494794845581055, Learning Rate: 3.542713567839196e-05)
+
                                                                             
Step... (64750 / 100000 | Loss: 0.6784526109695435, Learning Rate: 3.542713567839196e-05)
+
Train steps ... :  65%|██████▍   | 64750/100000 [19:04:52<5:43:53,  1.71it/s]
Train steps ... :  65%|██████▍   | 64751/100000 [19:04:52<5:43:41,  1.71it/s]
Train steps ... :  65%|██████▍   | 64752/100000 [19:04:53<5:44:00,  1.71it/s]
Train steps ... :  65%|██████▍   | 64753/100000 [19:04:53<5:43:56,  1.71it/s]
Train steps ... :  65%|██████▍   | 64754/100000 [19:04:54<5:44:04,  1.71it/s]
Train steps ... :  65%|██████▍   | 64755/100000 [19:04:54<5:43:51,  1.71it/s]
Train steps ... :  65%|██████▍   | 64756/100000 [19:04:55<5:43:47,  1.71it/s]
Train steps ... :  65%|██████▍   | 64757/100000 [19:04:56<5:44:02,  1.71it/s]
Train steps ... :  65%|██████▍   | 64758/100000 [19:04:56<5:43:48,  1.71it/s]
Train steps ... :  65%|██████▍   | 64759/100000 [19:04:57<5:43:30,  1.71it/s]
Train steps ... :  65%|██████▍   | 64760/100000 [19:04:57<5:43:52,  1.71it/s]
Train steps ... :  65%|██████▍   | 64761/100000 [19:04:58<5:44:01,  1.71it/s]
Train steps ... :  65%|██████▍   | 64762/100000 [19:04:59<5:43:34,  1.71it/s]
Train steps ... :  65%|██████▍   | 64763/100000 [19:04:59<5:43:31,  1.71it/s]
Train steps ... :  65%|██████▍   | 64764/100000 [19:05:00<5:43:43,  1.71it/s]
Train steps ... :  65%|██████▍   | 64765/100000 [19:05:00<5:44:14,  1.71it/s]
Train steps ... :  65%|██████▍   | 64766/100000 [19:05:01<5:44:37,  1.70it/s]
Train steps ... :  65%|██████▍   | 64767/100000 [19:05:01<5:43:45,  1.71it/s]
Train steps ... :  65%|██████▍   | 64768/100000 [19:05:02<5:43:45,  1.71it/s]
Train steps ... :  65%|██████▍   | 64769/100000 [19:05:03<5:43:45,  1.71it/s]
Train steps ... :  65%|██████▍   | 64770/100000 [19:05:03<5:43:24,  1.71it/s]
Train steps ... :  65%|██████▍   | 64771/100000 [19:05:04<5:43:52,  1.71it/s]
Train steps ... :  65%|██████▍   | 64772/100000 [19:05:04<5:43:48,  1.71it/s]
Train steps ... :  65%|██████▍   | 64773/100000 [19:05:05<5:44:27,  1.70it/s]
Train steps ... :  65%|██████▍   | 64774/100000 [19:05:06<5:43:39,  1.71it/s]
Train steps ... :  65%|██████▍   | 64775/100000 [19:05:06<5:43:13,  1.71it/s]Step... (64775 / 100000 | Loss: 0.7728266716003418, Learning Rate: 3.540201005025126e-05)
+
                                                                             
Step... (64775 / 100000 | Loss: 0.6630387306213379, Learning Rate: 3.540201005025126e-05)
+
Train steps ... :  65%|██████▍   | 64775/100000 [19:05:06<5:43:13,  1.71it/s]
Train steps ... :  65%|██████▍   | 64776/100000 [19:05:07<5:43:47,  1.71it/s]
Train steps ... :  65%|██████▍   | 64777/100000 [19:05:07<5:44:05,  1.71it/s]
Train steps ... :  65%|██████▍   | 64778/100000 [19:05:08<5:43:45,  1.71it/s]
Train steps ... :  65%|██████▍   | 64779/100000 [19:05:08<5:44:21,  1.70it/s]
Train steps ... :  65%|██████▍   | 64780/100000 [19:05:09<5:43:21,  1.71it/s]
Train steps ... :  65%|██████▍   | 64781/100000 [19:05:10<5:42:59,  1.71it/s]
Train steps ... :  65%|██████▍   | 64782/100000 [19:05:10<5:43:04,  1.71it/s]
Train steps ... :  65%|██████▍   | 64783/100000 [19:05:11<5:43:06,  1.71it/s]
Train steps ... :  65%|██████▍   | 64784/100000 [19:05:11<5:43:17,  1.71it/s]
Train steps ... :  65%|██████▍   | 64785/100000 [19:05:12<5:42:51,  1.71it/s]
Train steps ... :  65%|██████▍   | 64786/100000 [19:05:13<5:42:44,  1.71it/s]
Train steps ... :  65%|██████▍   | 64787/100000 [19:05:13<5:44:18,  1.70it/s]
Train steps ... :  65%|██████▍   | 64788/100000 [19:05:14<5:44:47,  1.70it/s]
Train steps ... :  65%|██████▍   | 64789/100000 [19:05:14<5:43:26,  1.71it/s]
Train steps ... :  65%|██████▍   | 64790/100000 [19:05:15<5:43:14,  1.71it/s]
Train steps ... :  65%|██████▍   | 64791/100000 [19:05:15<5:43:04,  1.71it/s]
Train steps ... :  65%|██████▍   | 64792/100000 [19:05:16<5:43:47,  1.71it/s]
Train steps ... :  65%|██████▍   | 64793/100000 [19:05:17<5:43:09,  1.71it/s]
Train steps ... :  65%|██████▍   | 64794/100000 [19:05:17<5:43:10,  1.71it/s]
Train steps ... :  65%|██████▍   | 64795/100000 [19:05:18<5:43:28,  1.71it/s]
Train steps ... :  65%|██████▍   | 64796/100000 [19:05:18<5:44:12,  1.70it/s]
Train steps ... :  65%|██████▍   | 64797/100000 [19:05:19<5:43:44,  1.71it/s]
Train steps ... :  65%|██████▍   | 64798/100000 [19:05:20<5:43:48,  1.71it/s]
Train steps ... :  65%|██████▍   | 64799/100000 [19:05:20<5:43:33,  1.71it/s]
Train steps ... :  65%|██████▍   | 64800/100000 [19:05:21<5:43:53,  1.71it/s]Step... (64800 / 100000 | Loss: 0.8361327648162842, Learning Rate: 3.5376884422110554e-05)
+
                                                                             
Step... (64800 / 100000 | Loss: 0.6015046834945679, Learning Rate: 3.5376884422110554e-05)
+
Train steps ... :  65%|██████▍   | 64800/100000 [19:05:21<5:43:53,  1.71it/s]
Train steps ... :  65%|██████▍   | 64801/100000 [19:05:21<5:44:00,  1.71it/s]
Train steps ... :  65%|██████▍   | 64802/100000 [19:05:22<5:43:15,  1.71it/s]
Train steps ... :  65%|██████▍   | 64803/100000 [19:05:23<5:43:51,  1.71it/s]
Train steps ... :  65%|██████▍   | 64804/100000 [19:05:23<5:43:56,  1.71it/s]
Train steps ... :  65%|██████▍   | 64805/100000 [19:05:24<5:43:34,  1.71it/s]
Train steps ... :  65%|██████▍   | 64806/100000 [19:05:24<5:43:29,  1.71it/s]
Train steps ... :  65%|██████▍   | 64807/100000 [19:05:25<5:43:20,  1.71it/s]
Train steps ... :  65%|██████▍   | 64808/100000 [19:05:25<5:43:07,  1.71it/s]
Train steps ... :  65%|██████▍   | 64809/100000 [19:05:26<5:43:42,  1.71it/s]
Train steps ... :  65%|██████▍   | 64810/100000 [19:05:27<5:43:25,  1.71it/s]
Train steps ... :  65%|██████▍   | 64811/100000 [19:05:27<5:43:59,  1.70it/s]
Train steps ... :  65%|██████▍   | 64812/100000 [19:05:28<5:43:24,  1.71it/s]
Train steps ... :  65%|██████▍   | 64813/100000 [19:05:28<5:43:21,  1.71it/s]
Train steps ... :  65%|██████▍   | 64814/100000 [19:05:29<5:43:36,  1.71it/s]
Train steps ... :  65%|██████▍   | 64815/100000 [19:05:30<5:43:06,  1.71it/s]
Train steps ... :  65%|██████▍   | 64816/100000 [19:05:30<5:43:10,  1.71it/s]
Train steps ... :  65%|██████▍   | 64817/100000 [19:05:31<5:43:34,  1.71it/s]
Train steps ... :  65%|██████▍   | 64818/100000 [19:05:31<5:43:23,  1.71it/s]
Train steps ... :  65%|██████▍   | 64819/100000 [19:05:32<5:42:59,  1.71it/s]
Train steps ... :  65%|██████▍   | 64820/100000 [19:05:32<5:42:58,  1.71it/s]
Train steps ... :  65%|██████▍   | 64821/100000 [19:05:33<5:42:51,  1.71it/s]
Train steps ... :  65%|██████▍   | 64822/100000 [19:05:34<5:43:16,  1.71it/s]
Train steps ... :  65%|██████▍   | 64823/100000 [19:05:34<5:43:31,  1.71it/s]
Train steps ... :  65%|██████▍   | 64824/100000 [19:05:35<5:43:42,  1.71it/s]
Train steps ... :  65%|██████▍   | 64825/100000 [19:05:35<5:43:05,  1.71it/s]Step... (64825 / 100000 | Loss: 0.7422919869422913, Learning Rate: 3.535175879396985e-05)
+
                                                                             
Step... (64825 / 100000 | Loss: 0.5967822670936584, Learning Rate: 3.535175879396985e-05)
+
Train steps ... :  65%|██████▍   | 64825/100000 [19:05:36<5:43:05,  1.71it/s]
Train steps ... :  65%|██████▍   | 64826/100000 [19:05:36<5:43:54,  1.70it/s]
Train steps ... :  65%|██████▍   | 64827/100000 [19:05:37<5:43:30,  1.71it/s]
Train steps ... :  65%|██████▍   | 64828/100000 [19:05:37<5:43:23,  1.71it/s]
Train steps ... :  65%|██████▍   | 64829/100000 [19:05:38<5:44:09,  1.70it/s]
Train steps ... :  65%|██████▍   | 64830/100000 [19:05:38<5:43:16,  1.71it/s]
Train steps ... :  65%|██████▍   | 64831/100000 [19:05:39<5:43:27,  1.71it/s]
Train steps ... :  65%|██████▍   | 64832/100000 [19:05:40<5:43:56,  1.70it/s]
Train steps ... :  65%|██████▍   | 64833/100000 [19:05:40<5:43:32,  1.71it/s]
Train steps ... :  65%|██████▍   | 64834/100000 [19:05:41<5:43:59,  1.70it/s]
Train steps ... :  65%|██████▍   | 64835/100000 [19:05:41<5:43:18,  1.71it/s]
Train steps ... :  65%|██████▍   | 64836/100000 [19:05:42<5:43:55,  1.70it/s]
Train steps ... :  65%|██████▍   | 64837/100000 [19:05:42<5:43:46,  1.70it/s]
Train steps ... :  65%|██████▍   | 64838/100000 [19:05:43<5:44:03,  1.70it/s]
Train steps ... :  65%|██████▍   | 64839/100000 [19:05:44<5:44:41,  1.70it/s]
Train steps ... :  65%|██████▍   | 64840/100000 [19:05:44<5:44:53,  1.70it/s]
Train steps ... :  65%|██████▍   | 64841/100000 [19:05:45<5:45:39,  1.70it/s]
Train steps ... :  65%|██████▍   | 64842/100000 [19:05:45<5:44:18,  1.70it/s]
Train steps ... :  65%|██████▍   | 64843/100000 [19:05:46<5:44:26,  1.70it/s]
Train steps ... :  65%|██████▍   | 64844/100000 [19:05:47<5:44:13,  1.70it/s]
Train steps ... :  65%|██████▍   | 64845/100000 [19:05:47<5:43:56,  1.70it/s]
Train steps ... :  65%|██████▍   | 64846/100000 [19:05:48<5:44:58,  1.70it/s]
Train steps ... :  65%|██████▍   | 64847/100000 [19:05:48<5:45:11,  1.70it/s]
Train steps ... :  65%|██████▍   | 64848/100000 [19:05:49<5:44:19,  1.70it/s]
Train steps ... :  65%|██████▍   | 64849/100000 [19:05:50<5:44:52,  1.70it/s]
Train steps ... :  65%|██████▍   | 64850/100000 [19:05:50<5:45:47,  1.69it/s]Step... (64850 / 100000 | Loss: 1.0178906917572021, Learning Rate: 3.532663316582915e-05)
+
                                                                             
Step... (64850 / 100000 | Loss: 0.7992084622383118, Learning Rate: 3.532663316582915e-05)
+
Train steps ... :  65%|██████▍   | 64850/100000 [19:05:50<5:45:47,  1.69it/s]
Train steps ... :  65%|██████▍   | 64851/100000 [19:05:51<5:44:12,  1.70it/s]
Train steps ... :  65%|██████▍   | 64852/100000 [19:05:51<5:43:21,  1.71it/s]
Train steps ... :  65%|██████▍   | 64853/100000 [19:05:52<5:44:52,  1.70it/s]
Train steps ... :  65%|██████▍   | 64854/100000 [19:05:52<5:43:23,  1.71it/s]
Train steps ... :  65%|██████▍   | 64855/100000 [19:05:53<5:44:12,  1.70it/s]
Train steps ... :  65%|██████▍   | 64856/100000 [19:05:54<5:43:40,  1.70it/s]
Train steps ... :  65%|██████▍   | 64857/100000 [19:05:54<5:43:36,  1.70it/s]
Train steps ... :  65%|██████▍   | 64858/100000 [19:05:55<5:43:47,  1.70it/s]
Train steps ... :  65%|██████▍   | 64859/100000 [19:05:55<5:44:21,  1.70it/s]
Train steps ... :  65%|██████▍   | 64860/100000 [19:05:56<5:43:40,  1.70it/s]
Train steps ... :  65%|██████▍   | 64861/100000 [19:05:57<5:43:29,  1.71it/s]
Train steps ... :  65%|██████▍   | 64862/100000 [19:05:57<5:44:24,  1.70it/s]
Train steps ... :  65%|██████▍   | 64863/100000 [19:05:58<5:43:32,  1.70it/s]
Train steps ... :  65%|██████▍   | 64864/100000 [19:05:58<5:43:23,  1.71it/s]
Train steps ... :  65%|██████▍   | 64865/100000 [19:05:59<5:42:58,  1.71it/s]
Train steps ... :  65%|██████▍   | 64866/100000 [19:05:59<5:42:41,  1.71it/s]
Train steps ... :  65%|██████▍   | 64867/100000 [19:06:00<5:43:04,  1.71it/s]
Train steps ... :  65%|██████▍   | 64868/100000 [19:06:01<5:43:16,  1.71it/s]
Train steps ... :  65%|██████▍   | 64869/100000 [19:06:01<5:44:19,  1.70it/s]
Train steps ... :  65%|██████▍   | 64870/100000 [19:06:02<5:43:34,  1.70it/s]
Train steps ... :  65%|██████▍   | 64871/100000 [19:06:02<5:43:18,  1.71it/s]
Train steps ... :  65%|██████▍   | 64872/100000 [19:06:03<5:43:41,  1.70it/s]
Train steps ... :  65%|██████▍   | 64873/100000 [19:06:04<5:44:26,  1.70it/s]
Train steps ... :  65%|██████▍   | 64874/100000 [19:06:04<5:43:44,  1.70it/s]
Train steps ... :  65%|██████▍   | 64875/100000 [19:06:05<5:43:30,  1.70it/s]Step... (64875 / 100000 | Loss: 0.8670705556869507, Learning Rate: 3.5301507537688444e-05)
+
                                                                             
Step... (64875 / 100000 | Loss: 0.8115440607070923, Learning Rate: 3.5301507537688444e-05)
+
Train steps ... :  65%|██████▍   | 64875/100000 [19:06:05<5:43:30,  1.70it/s]
Train steps ... :  65%|██████▍   | 64876/100000 [19:06:05<5:45:46,  1.69it/s]
Train steps ... :  65%|██████▍   | 64877/100000 [19:06:06<5:43:43,  1.70it/s]
Train steps ... :  65%|██████▍   | 64878/100000 [19:06:07<5:43:59,  1.70it/s]
Train steps ... :  65%|██████▍   | 64879/100000 [19:06:07<5:43:53,  1.70it/s]
Train steps ... :  65%|██████▍   | 64880/100000 [19:06:08<5:44:04,  1.70it/s]
Train steps ... :  65%|██████▍   | 64881/100000 [19:06:08<5:42:47,  1.71it/s]
Train steps ... :  65%|██████▍   | 64882/100000 [19:06:09<5:43:08,  1.71it/s]
Train steps ... :  65%|██████▍   | 64883/100000 [19:06:09<5:42:46,  1.71it/s]
Train steps ... :  65%|██████▍   | 64884/100000 [19:06:10<5:42:27,  1.71it/s]
Train steps ... :  65%|██████▍   | 64885/100000 [19:06:11<5:42:47,  1.71it/s]
Train steps ... :  65%|██████▍   | 64886/100000 [19:06:11<5:42:44,  1.71it/s]
Train steps ... :  65%|██████▍   | 64887/100000 [19:06:12<5:42:42,  1.71it/s]
Train steps ... :  65%|██████▍   | 64888/100000 [19:06:12<5:42:44,  1.71it/s]
Train steps ... :  65%|██████▍   | 64889/100000 [19:06:13<5:43:18,  1.70it/s]
Train steps ... :  65%|██████▍   | 64890/100000 [19:06:14<5:43:21,  1.70it/s]
Train steps ... :  65%|██████▍   | 64891/100000 [19:06:14<5:42:56,  1.71it/s]
Train steps ... :  65%|██████▍   | 64892/100000 [19:06:15<5:43:36,  1.70it/s]
Train steps ... :  65%|██████▍   | 64893/100000 [19:06:15<5:43:42,  1.70it/s]
Train steps ... :  65%|██████▍   | 64894/100000 [19:06:16<5:43:27,  1.70it/s]
Train steps ... :  65%|██████▍   | 64895/100000 [19:06:17<5:43:47,  1.70it/s]
Train steps ... :  65%|██████▍   | 64896/100000 [19:06:17<5:42:49,  1.71it/s]
Train steps ... :  65%|██████▍   | 64897/100000 [19:06:18<5:42:48,  1.71it/s]
Train steps ... :  65%|██████▍   | 64898/100000 [19:06:18<5:42:20,  1.71it/s]
Train steps ... :  65%|██████▍   | 64899/100000 [19:06:19<5:42:26,  1.71it/s]
Train steps ... :  65%|██████▍   | 64900/100000 [19:06:19<5:42:42,  1.71it/s]Step... (64900 / 100000 | Loss: 0.7161328792572021, Learning Rate: 3.527638190954774e-05)
+
                                                                             
Step... (64900 / 100000 | Loss: 0.6782782077789307, Learning Rate: 3.527638190954774e-05)
+
Train steps ... :  65%|██████▍   | 64900/100000 [19:06:20<5:42:42,  1.71it/s]
Train steps ... :  65%|██████▍   | 64901/100000 [19:06:20<5:42:01,  1.71it/s]
Train steps ... :  65%|██████▍   | 64902/100000 [19:06:21<5:41:58,  1.71it/s]
Train steps ... :  65%|██████▍   | 64903/100000 [19:06:21<5:42:04,  1.71it/s]
Train steps ... :  65%|██████▍   | 64904/100000 [19:06:22<5:43:23,  1.70it/s]
Train steps ... :  65%|██████▍   | 64905/100000 [19:06:22<5:43:24,  1.70it/s]
Train steps ... :  65%|██████▍   | 64906/100000 [19:06:23<5:43:02,  1.71it/s]
Train steps ... :  65%|██████▍   | 64907/100000 [19:06:24<5:43:04,  1.70it/s]
Train steps ... :  65%|██████▍   | 64908/100000 [19:06:24<5:42:51,  1.71it/s]
Train steps ... :  65%|██████▍   | 64909/100000 [19:06:25<5:43:13,  1.70it/s]
Train steps ... :  65%|██████▍   | 64910/100000 [19:06:25<5:42:52,  1.71it/s]
Train steps ... :  65%|██████▍   | 64911/100000 [19:06:26<5:43:43,  1.70it/s]
Train steps ... :  65%|██████▍   | 64912/100000 [19:06:26<5:43:04,  1.70it/s]
Train steps ... :  65%|██████▍   | 64913/100000 [19:06:27<5:42:41,  1.71it/s]
Train steps ... :  65%|██████▍   | 64914/100000 [19:06:28<5:43:00,  1.70it/s]
Train steps ... :  65%|██████▍   | 64915/100000 [19:06:28<5:42:56,  1.71it/s]
Train steps ... :  65%|██████▍   | 64916/100000 [19:06:29<5:42:54,  1.71it/s]
Train steps ... :  65%|██████▍   | 64917/100000 [19:06:29<5:42:52,  1.71it/s]
Train steps ... :  65%|██████▍   | 64918/100000 [19:06:30<5:43:24,  1.70it/s]
Train steps ... :  65%|██████▍   | 64919/100000 [19:06:31<5:43:17,  1.70it/s]
Train steps ... :  65%|██████▍   | 64920/100000 [19:06:31<5:42:43,  1.71it/s]
Train steps ... :  65%|██████▍   | 64921/100000 [19:06:32<5:43:32,  1.70it/s]
Train steps ... :  65%|██████▍   | 64922/100000 [19:06:32<5:44:00,  1.70it/s]
Train steps ... :  65%|██████▍   | 64923/100000 [19:06:33<5:42:57,  1.70it/s]
Train steps ... :  65%|██████▍   | 64924/100000 [19:06:34<5:42:43,  1.71it/s]
Train steps ... :  65%|██████▍   | 64925/100000 [19:06:34<5:43:19,  1.70it/s]Step... (64925 / 100000 | Loss: 0.7943218946456909, Learning Rate: 3.525125628140704e-05)
+
                                                                             
Step... (64925 / 100000 | Loss: 0.7173665761947632, Learning Rate: 3.525125628140704e-05)
+
Train steps ... :  65%|██████▍   | 64925/100000 [19:06:34<5:43:19,  1.70it/s]
Train steps ... :  65%|██████▍   | 64926/100000 [19:06:35<5:43:13,  1.70it/s]
Train steps ... :  65%|██████▍   | 64927/100000 [19:06:35<5:43:08,  1.70it/s]
Train steps ... :  65%|██████▍   | 64928/100000 [19:06:36<5:42:43,  1.71it/s]
Train steps ... :  65%|██████▍   | 64929/100000 [19:06:36<5:43:21,  1.70it/s]
Train steps ... :  65%|██████▍   | 64930/100000 [19:06:37<5:43:12,  1.70it/s]
Train steps ... :  65%|██████▍   | 64931/100000 [19:06:38<5:42:49,  1.70it/s]
Train steps ... :  65%|██████▍   | 64932/100000 [19:06:38<5:42:12,  1.71it/s]
Train steps ... :  65%|██████▍   | 64933/100000 [19:06:39<5:42:40,  1.71it/s]
Train steps ... :  65%|██████▍   | 64934/100000 [19:06:39<5:42:22,  1.71it/s]
Train steps ... :  65%|██████▍   | 64935/100000 [19:06:40<5:42:04,  1.71it/s]
Train steps ... :  65%|██████▍   | 64936/100000 [19:06:41<5:42:58,  1.70it/s]
Train steps ... :  65%|██████▍   | 64937/100000 [19:06:41<5:42:34,  1.71it/s]
Train steps ... :  65%|██████▍   | 64938/100000 [19:06:42<5:41:54,  1.71it/s]
Train steps ... :  65%|██████▍   | 64939/100000 [19:06:42<5:42:05,  1.71it/s]
Train steps ... :  65%|██████▍   | 64940/100000 [19:06:43<5:42:06,  1.71it/s]
Train steps ... :  65%|██████▍   | 64941/100000 [19:06:43<5:42:00,  1.71it/s]
Train steps ... :  65%|██████▍   | 64942/100000 [19:06:44<5:41:27,  1.71it/s]
Train steps ... :  65%|██████▍   | 64943/100000 [19:06:45<5:42:07,  1.71it/s]
Train steps ... :  65%|██████▍   | 64944/100000 [19:06:45<5:42:02,  1.71it/s]
Train steps ... :  65%|██████▍   | 64945/100000 [19:06:46<5:42:39,  1.71it/s]
Train steps ... :  65%|██████▍   | 64946/100000 [19:06:46<5:43:04,  1.70it/s]
Train steps ... :  65%|██████▍   | 64947/100000 [19:06:47<5:42:02,  1.71it/s]
Train steps ... :  65%|██████▍   | 64948/100000 [19:06:48<5:42:09,  1.71it/s]
Train steps ... :  65%|██████▍   | 64949/100000 [19:06:48<5:42:27,  1.71it/s]
Train steps ... :  65%|██████▍   | 64950/100000 [19:06:49<5:42:11,  1.71it/s]Step... (64950 / 100000 | Loss: 0.5650230646133423, Learning Rate: 3.5226130653266334e-05)
+
                                                                             
Step... (64950 / 100000 | Loss: 0.8224467039108276, Learning Rate: 3.5226130653266334e-05)
+
Train steps ... :  65%|██████▍   | 64950/100000 [19:06:49<5:42:11,  1.71it/s]
Train steps ... :  65%|██████▍   | 64951/100000 [19:06:49<5:42:04,  1.71it/s]
Train steps ... :  65%|██████▍   | 64952/100000 [19:06:50<5:42:18,  1.71it/s]
Train steps ... :  65%|██████▍   | 64953/100000 [19:06:51<5:42:14,  1.71it/s]
Train steps ... :  65%|██████▍   | 64954/100000 [19:06:51<5:41:58,  1.71it/s]
Train steps ... :  65%|██████▍   | 64955/100000 [19:06:52<5:41:55,  1.71it/s]
Train steps ... :  65%|██████▍   | 64956/100000 [19:06:52<5:41:53,  1.71it/s]
Train steps ... :  65%|██████▍   | 64957/100000 [19:06:53<5:41:29,  1.71it/s]
Train steps ... :  65%|██████▍   | 64958/100000 [19:06:53<5:42:29,  1.71it/s]
Train steps ... :  65%|██████▍   | 64959/100000 [19:06:54<5:42:26,  1.71it/s]
Train steps ... :  65%|██████▍   | 64960/100000 [19:06:55<5:42:15,  1.71it/s]
Train steps ... :  65%|██████▍   | 64961/100000 [19:06:55<5:42:28,  1.71it/s]
Train steps ... :  65%|██████▍   | 64962/100000 [19:06:56<5:41:53,  1.71it/s]
Train steps ... :  65%|██████▍   | 64963/100000 [19:06:56<5:41:41,  1.71it/s]
Train steps ... :  65%|██████▍   | 64964/100000 [19:06:57<5:41:44,  1.71it/s]
Train steps ... :  65%|██████▍   | 64965/100000 [19:06:58<5:41:22,  1.71it/s]
Train steps ... :  65%|██████▍   | 64966/100000 [19:06:58<5:41:45,  1.71it/s]
Train steps ... :  65%|██████▍   | 64967/100000 [19:06:59<5:41:54,  1.71it/s]
Train steps ... :  65%|██████▍   | 64968/100000 [19:06:59<5:42:43,  1.70it/s]
Train steps ... :  65%|██████▍   | 64969/100000 [19:07:00<5:42:59,  1.70it/s]
Train steps ... :  65%|██████▍   | 64970/100000 [19:07:00<5:43:15,  1.70it/s]
Train steps ... :  65%|██████▍   | 64971/100000 [19:07:01<5:41:32,  1.71it/s]
Train steps ... :  65%|██████▍   | 64972/100000 [19:07:02<5:41:45,  1.71it/s]
Train steps ... :  65%|██████▍   | 64973/100000 [19:07:02<5:41:44,  1.71it/s]
Train steps ... :  65%|██████▍   | 64974/100000 [19:07:03<5:41:46,  1.71it/s]
Train steps ... :  65%|██████▍   | 64975/100000 [19:07:03<5:42:22,  1.71it/s]Step... (64975 / 100000 | Loss: 0.8500574827194214, Learning Rate: 3.520100502512563e-05)
+
                                                                             
Step... (64975 / 100000 | Loss: 0.7256127595901489, Learning Rate: 3.520100502512563e-05)
+
Train steps ... :  65%|██████▍   | 64975/100000 [19:07:04<5:42:22,  1.71it/s]
Train steps ... :  65%|██████▍   | 64976/100000 [19:07:04<5:42:13,  1.71it/s]
Train steps ... :  65%|██████▍   | 64977/100000 [19:07:05<5:43:13,  1.70it/s]
Train steps ... :  65%|██████▍   | 64978/100000 [19:07:05<5:42:20,  1.71it/s]
Train steps ... :  65%|██████▍   | 64979/100000 [19:07:06<5:42:17,  1.71it/s]
Train steps ... :  65%|██████▍   | 64980/100000 [19:07:06<5:41:31,  1.71it/s]
Train steps ... :  65%|██████▍   | 64981/100000 [19:07:07<5:41:13,  1.71it/s]
Train steps ... :  65%|██████▍   | 64982/100000 [19:07:07<5:41:40,  1.71it/s]
Train steps ... :  65%|██████▍   | 64983/100000 [19:07:08<5:43:28,  1.70it/s]
Train steps ... :  65%|██████▍   | 64984/100000 [19:07:09<5:42:52,  1.70it/s]
Train steps ... :  65%|██████▍   | 64985/100000 [19:07:09<5:42:31,  1.70it/s]
Train steps ... :  65%|██████▍   | 64986/100000 [19:07:10<5:42:37,  1.70it/s]
Train steps ... :  65%|██████▍   | 64987/100000 [19:07:10<5:42:20,  1.70it/s]
Train steps ... :  65%|██████▍   | 64988/100000 [19:07:11<5:42:30,  1.70it/s]
Train steps ... :  65%|██████▍   | 64989/100000 [19:07:12<5:42:42,  1.70it/s]
Train steps ... :  65%|██████▍   | 64990/100000 [19:07:12<5:43:24,  1.70it/s]
Train steps ... :  65%|██████▍   | 64991/100000 [19:07:13<5:42:29,  1.70it/s]
Train steps ... :  65%|██████▍   | 64992/100000 [19:07:13<5:42:20,  1.70it/s]
Train steps ... :  65%|██████▍   | 64993/100000 [19:07:14<5:41:57,  1.71it/s]
Train steps ... :  65%|██████▍   | 64994/100000 [19:07:15<5:42:59,  1.70it/s]
Train steps ... :  65%|██████▍   | 64995/100000 [19:07:15<5:42:33,  1.70it/s]
Train steps ... :  65%|██████▍   | 64996/100000 [19:07:16<5:41:41,  1.71it/s]
Train steps ... :  65%|██████▍   | 64997/100000 [19:07:16<5:41:54,  1.71it/s]
Train steps ... :  65%|██████▍   | 64998/100000 [19:07:17<5:41:21,  1.71it/s]
Train steps ... :  65%|██████▍   | 64999/100000 [19:07:17<5:42:17,  1.70it/s]
Train steps ... :  65%|██████▌   | 65000/100000 [19:07:18<5:41:57,  1.71it/s]Step... (65000 / 100000 | Loss: 0.6801362037658691, Learning Rate: 3.517587939698493e-05)
+
                                                                             
Step... (65000 / 100000 | Loss: 0.8061666488647461, Learning Rate: 3.517587939698493e-05)
+
Train steps ... :  65%|██████▌   | 65000/100000 [19:07:18<5:41:57,  1.71it/s]06/18/2024 11:01:45 - INFO - accelerate.accelerator - Saving current state to ./checkpoint-65000-epoch-3
+06/18/2024 11:01:45 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/18/2024 11:01:48 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-65000-epoch-3/model.safetensors
+06/18/2024 11:01:48 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/18/2024 11:01:52 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-65000-epoch-3/model_1.safetensors
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Optimizer state saved in checkpoint-65000-epoch-3/optimizer.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Scheduler state saved in checkpoint-65000-epoch-3/scheduler.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in checkpoint-65000-epoch-3/sampler.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in checkpoint-65000-epoch-3/sampler_1.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 2 saved in checkpoint-65000-epoch-3/sampler_2.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 3 saved in checkpoint-65000-epoch-3/sampler_3.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 4 saved in checkpoint-65000-epoch-3/sampler_4.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 5 saved in checkpoint-65000-epoch-3/sampler_5.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 6 saved in checkpoint-65000-epoch-3/sampler_6.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 7 saved in checkpoint-65000-epoch-3/sampler_7.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 8 saved in checkpoint-65000-epoch-3/sampler_8.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 9 saved in checkpoint-65000-epoch-3/sampler_9.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 10 saved in checkpoint-65000-epoch-3/sampler_10.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 11 saved in checkpoint-65000-epoch-3/sampler_11.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 12 saved in checkpoint-65000-epoch-3/sampler_12.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 13 saved in checkpoint-65000-epoch-3/sampler_13.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 14 saved in checkpoint-65000-epoch-3/sampler_14.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 15 saved in checkpoint-65000-epoch-3/sampler_15.bin
+06/18/2024 11:01:53 - INFO - accelerate.checkpointing - Random states saved in checkpoint-65000-epoch-3/random_states_0.pkl
+06/18/2024 11:01:53 - INFO - __main__ - Deleting older checkpoint [checkpoint-40000-epoch-2] due to args.save_total_limit
+
+
  0%|          | 0/5 [00:00<?, ?it/s]
+
 20%|██        | 1/5 [01:48<07:12, 108.10s/it]
+
 40%|████      | 2/5 [02:24<03:17, 65.92s/it] 
+
 60%|██████    | 3/5 [02:25<01:12, 36.08s/it]
+
 80%|████████  | 4/5 [02:25<00:22, 22.06s/it]
+
100%|██████████| 5/5 [02:26<00:00, 14.33s/it]
100%|██████████| 5/5 [02:26<00:00, 29.25s/it]