diff --git "a/train.log" "b/train.log"
--- "a/train.log"
+++ "b/train.log"
@@ -32530,3 +32530,4235 @@ Eval results for step (35000 / 100000 | Eval Loss: 1.0786126852035522 | Eval wer
 
 60%|██████    | 3/5 [02:18<01:08, 34.46s/it]
 
 80%|████████  | 4/5 [02:19<00:21, 21.10s/it]
 
100%|██████████| 5/5 [02:20<00:00, 13.69s/it]
100%|██████████| 5/5 [02:20<00:00, 28.02s/it]
+
+
+
Evaluating eval...:   0%|          | 0/1900 [00:00<?, ?it/s]
+
+
Evaluating eval...:   0%|          | 1/1900 [00:03<1:49:34,  3.46s/it]
+
+
Evaluating eval...:   0%|          | 2/1900 [00:04<1:08:40,  2.17s/it]
+
+
Evaluating eval...:   0%|          | 3/1900 [00:05<55:37,  1.76s/it]  
+
+
Evaluating eval...:   0%|          | 4/1900 [00:07<48:45,  1.54s/it]
+
+
Evaluating eval...:   0%|          | 5/1900 [00:08<44:58,  1.42s/it]
+
+
Evaluating eval...:   0%|          | 6/1900 [00:09<42:07,  1.33s/it]
+
+
Evaluating eval...:   0%|          | 7/1900 [00:10<40:40,  1.29s/it]
+
+
Evaluating eval...:   0%|          | 8/1900 [00:11<39:25,  1.25s/it]
+
+
Evaluating eval...:   0%|          | 9/1900 [00:13<38:22,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 10/1900 [00:14<38:14,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 11/1900 [00:15<38:13,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 12/1900 [00:16<37:57,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 13/1900 [00:17<37:52,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 14/1900 [00:19<37:20,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 15/1900 [00:20<37:11,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 16/1900 [00:21<37:07,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 17/1900 [00:22<37:11,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 18/1900 [00:23<37:03,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 19/1900 [00:24<36:36,  1.17s/it]
+
+
Evaluating eval...:   1%|          | 20/1900 [00:26<36:50,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 21/1900 [00:27<37:13,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 22/1900 [00:28<37:06,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 23/1900 [00:29<36:42,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 24/1900 [00:30<36:54,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 25/1900 [00:31<36:28,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 26/1900 [00:33<36:13,  1.16s/it]
+
+
Evaluating eval...:   1%|▏         | 27/1900 [00:34<36:50,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 28/1900 [00:35<36:32,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 29/1900 [00:36<36:29,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 30/1900 [00:37<36:28,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 31/1900 [00:38<36:25,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 32/1900 [00:40<36:47,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 33/1900 [00:41<37:05,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 34/1900 [00:42<37:58,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 35/1900 [00:43<38:09,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 36/1900 [00:45<38:11,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 37/1900 [00:46<37:53,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 38/1900 [00:47<37:21,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 39/1900 [00:48<37:06,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 40/1900 [00:49<36:57,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 41/1900 [00:51<36:36,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 42/1900 [00:52<37:07,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 43/1900 [00:53<37:00,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 44/1900 [00:54<37:08,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 45/1900 [00:55<36:35,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 46/1900 [00:57<36:24,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 47/1900 [00:58<35:59,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 48/1900 [00:59<35:42,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 49/1900 [01:00<35:34,  1.15s/it]
+
+
Evaluating eval...:   3%|▎         | 50/1900 [01:01<36:05,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 51/1900 [01:02<36:14,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 52/1900 [01:03<35:53,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 53/1900 [01:05<35:43,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 54/1900 [01:06<36:13,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 55/1900 [01:07<36:56,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 56/1900 [01:08<37:14,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 57/1900 [01:10<37:12,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 58/1900 [01:11<37:06,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 59/1900 [01:12<36:49,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 60/1900 [01:13<36:15,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 61/1900 [01:14<37:20,  1.22s/it]
+
+
Evaluating eval...:   3%|▎         | 62/1900 [01:16<36:51,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 63/1900 [01:17<36:36,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 64/1900 [01:18<36:13,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 65/1900 [01:19<35:52,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 66/1900 [01:20<35:42,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 67/1900 [01:21<35:41,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 68/1900 [01:23<37:12,  1.22s/it]
+
+
Evaluating eval...:   4%|▎         | 69/1900 [01:24<36:28,  1.20s/it]
+
+
Evaluating eval...:   4%|▎         | 70/1900 [01:25<36:47,  1.21s/it]
+
+
Evaluating eval...:   4%|▎         | 71/1900 [01:26<36:40,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 72/1900 [01:27<36:41,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 73/1900 [01:29<36:30,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 74/1900 [01:30<36:22,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 75/1900 [01:31<36:06,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 76/1900 [01:32<36:05,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 77/1900 [01:33<36:04,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 78/1900 [01:35<36:08,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 79/1900 [01:36<36:13,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 80/1900 [01:37<36:02,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 81/1900 [01:38<35:52,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 82/1900 [01:39<36:42,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 83/1900 [01:41<37:10,  1.23s/it]
+
+
Evaluating eval...:   4%|▍         | 84/1900 [01:42<36:49,  1.22s/it]
+
+
Evaluating eval...:   4%|▍         | 85/1900 [01:43<36:31,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 86/1900 [01:44<35:48,  1.18s/it]
+
+
Evaluating eval...:   5%|▍         | 87/1900 [01:45<36:07,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 88/1900 [01:47<35:56,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 89/1900 [01:48<37:18,  1.24s/it]
+
+
Evaluating eval...:   5%|▍         | 90/1900 [01:49<36:48,  1.22s/it]
+
+
Evaluating eval...:   5%|▍         | 91/1900 [01:50<36:46,  1.22s/it]
+
+
Evaluating eval...:   5%|▍         | 92/1900 [01:51<36:10,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 93/1900 [01:53<35:56,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 94/1900 [01:54<35:34,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 95/1900 [01:55<35:04,  1.17s/it]
+
+
Evaluating eval...:   5%|▌         | 96/1900 [01:56<35:58,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 97/1900 [01:57<35:24,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 98/1900 [01:59<36:07,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 99/1900 [02:00<35:56,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 100/1900 [02:01<35:44,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 101/1900 [02:02<36:31,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 102/1900 [02:04<37:03,  1.24s/it]
+
+
Evaluating eval...:   5%|▌         | 103/1900 [02:05<36:39,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 104/1900 [02:06<36:08,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 105/1900 [02:07<36:15,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 106/1900 [02:08<35:34,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 107/1900 [02:09<35:52,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 108/1900 [02:11<35:14,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 109/1900 [02:12<35:18,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 110/1900 [02:13<35:03,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 111/1900 [02:14<35:20,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 112/1900 [02:15<36:12,  1.22s/it]
+
+
Evaluating eval...:   6%|▌         | 113/1900 [02:17<35:47,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 114/1900 [02:18<35:21,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 115/1900 [02:19<35:08,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 116/1900 [02:20<34:38,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 117/1900 [02:21<34:47,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 118/1900 [02:22<35:07,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 119/1900 [02:24<35:01,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 120/1900 [02:25<35:31,  1.20s/it]
+
+
Evaluating eval...:   6%|▋         | 121/1900 [02:26<35:05,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 122/1900 [02:27<35:20,  1.19s/it]
+
+
Evaluating eval...:   6%|▋         | 123/1900 [02:28<35:14,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 124/1900 [02:30<35:05,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 125/1900 [02:31<35:05,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 126/1900 [02:32<35:18,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 127/1900 [02:33<35:31,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 128/1900 [02:34<35:08,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 129/1900 [02:36<34:47,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 130/1900 [02:37<34:34,  1.17s/it]
+
+
Evaluating eval...:   7%|▋         | 131/1900 [02:38<34:44,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 132/1900 [02:39<35:18,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 133/1900 [02:40<34:49,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 134/1900 [02:41<34:53,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 135/1900 [02:43<35:05,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 136/1900 [02:44<35:37,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 137/1900 [02:45<36:33,  1.24s/it]
+
+
Evaluating eval...:   7%|▋         | 138/1900 [02:46<36:14,  1.23s/it]
+
+
Evaluating eval...:   7%|▋         | 139/1900 [02:48<35:38,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 140/1900 [02:49<35:29,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 141/1900 [02:50<35:16,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 142/1900 [02:51<35:56,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 143/1900 [02:53<35:51,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 144/1900 [02:54<35:03,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 145/1900 [02:55<35:06,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 146/1900 [02:56<34:45,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 147/1900 [02:57<35:08,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 148/1900 [02:58<34:37,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 149/1900 [03:00<34:42,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 150/1900 [03:01<35:38,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 151/1900 [03:02<35:22,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 152/1900 [03:03<35:29,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 153/1900 [03:05<35:25,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 154/1900 [03:06<35:17,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 155/1900 [03:07<34:55,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 156/1900 [03:08<34:47,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 157/1900 [03:10<43:39,  1.50s/it]
+
+
Evaluating eval...:   8%|▊         | 158/1900 [03:12<40:55,  1.41s/it]
+
+
Evaluating eval...:   8%|▊         | 159/1900 [03:13<38:34,  1.33s/it]
+
+
Evaluating eval...:   8%|▊         | 160/1900 [03:14<37:16,  1.29s/it]
+
+
Evaluating eval...:   8%|▊         | 161/1900 [03:15<37:13,  1.28s/it]
+
+
Evaluating eval...:   9%|▊         | 162/1900 [03:16<36:06,  1.25s/it]
+
+
Evaluating eval...:   9%|▊         | 163/1900 [03:17<35:03,  1.21s/it]
+
+
Evaluating eval...:   9%|▊         | 164/1900 [03:19<35:00,  1.21s/it]
+
+
Evaluating eval...:   9%|▊         | 165/1900 [03:20<34:48,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 166/1900 [03:21<34:27,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 167/1900 [03:22<35:14,  1.22s/it]
+
+
Evaluating eval...:   9%|▉         | 168/1900 [03:23<34:29,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 169/1900 [03:25<34:13,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 170/1900 [03:26<34:06,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 171/1900 [03:27<34:00,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 172/1900 [03:28<34:14,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 173/1900 [03:29<34:19,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 174/1900 [03:31<34:32,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 175/1900 [03:32<34:02,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 176/1900 [03:33<33:36,  1.17s/it]
+
+
Evaluating eval...:   9%|▉         | 177/1900 [03:34<35:09,  1.22s/it]
+
+
Evaluating eval...:   9%|▉         | 178/1900 [03:35<35:13,  1.23s/it]
+
+
Evaluating eval...:   9%|▉         | 179/1900 [03:37<34:37,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 180/1900 [03:38<34:26,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 181/1900 [03:39<34:17,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 182/1900 [03:40<35:17,  1.23s/it]
+
+
Evaluating eval...:  10%|▉         | 183/1900 [03:41<35:10,  1.23s/it]
+
+
Evaluating eval...:  10%|▉         | 184/1900 [03:43<34:37,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 185/1900 [03:44<34:18,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 186/1900 [03:45<33:53,  1.19s/it]
+
+
Evaluating eval...:  10%|▉         | 187/1900 [03:46<34:07,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 188/1900 [03:47<34:08,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 189/1900 [03:49<33:47,  1.19s/it]
+
+
Evaluating eval...:  10%|█         | 190/1900 [03:50<33:38,  1.18s/it]
+
+
Evaluating eval...:  10%|█         | 191/1900 [03:51<33:24,  1.17s/it]
+
+
Evaluating eval...:  10%|█         | 192/1900 [03:52<34:25,  1.21s/it]
+
+
Evaluating eval...:  10%|█         | 193/1900 [03:53<35:17,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 194/1900 [03:55<35:09,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 195/1900 [03:56<35:09,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 196/1900 [03:57<34:43,  1.22s/it]
+
+
Evaluating eval...:  10%|█         | 197/1900 [03:58<35:40,  1.26s/it]
+
+
Evaluating eval...:  10%|█         | 198/1900 [04:00<35:39,  1.26s/it]
+
+
Evaluating eval...:  10%|█         | 199/1900 [04:01<34:51,  1.23s/it]
+
+
Evaluating eval...:  11%|█         | 200/1900 [04:02<34:10,  1.21s/it]
+
+
Evaluating eval...:  11%|█         | 201/1900 [04:03<33:38,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 202/1900 [04:04<33:12,  1.17s/it]
+
+
Evaluating eval...:  11%|█         | 203/1900 [04:06<33:33,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 204/1900 [04:07<33:19,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 205/1900 [04:08<33:21,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 206/1900 [04:09<33:18,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 207/1900 [04:10<33:55,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 208/1900 [04:11<33:27,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 209/1900 [04:13<33:18,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 210/1900 [04:14<33:12,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 211/1900 [04:15<33:19,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 212/1900 [04:16<33:15,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 213/1900 [04:17<34:04,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 214/1900 [04:19<34:05,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 215/1900 [04:20<33:45,  1.20s/it]
+
+
Evaluating eval...:  11%|█▏        | 216/1900 [04:21<33:27,  1.19s/it]
+
+
Evaluating eval...:  11%|█▏        | 217/1900 [04:22<33:27,  1.19s/it]
+
+
Evaluating eval...:  11%|█▏        | 218/1900 [04:23<33:47,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 219/1900 [04:25<33:37,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 220/1900 [04:26<33:54,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 221/1900 [04:27<33:40,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 222/1900 [04:28<33:22,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 223/1900 [04:29<32:56,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 224/1900 [04:31<32:36,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 225/1900 [04:32<32:33,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 226/1900 [04:33<32:36,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 227/1900 [04:34<32:34,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 228/1900 [04:35<32:58,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 229/1900 [04:36<32:34,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 230/1900 [04:38<32:42,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 231/1900 [04:39<32:48,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 232/1900 [04:40<32:32,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 233/1900 [04:41<32:30,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 234/1900 [04:42<32:27,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 235/1900 [04:43<32:35,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 236/1900 [04:45<33:00,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 237/1900 [04:46<33:22,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 238/1900 [04:47<33:30,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 239/1900 [04:48<34:00,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 240/1900 [04:50<33:23,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 241/1900 [04:51<32:58,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 242/1900 [04:52<33:01,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 243/1900 [04:53<32:38,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 244/1900 [04:54<32:33,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 245/1900 [04:55<33:02,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 246/1900 [04:57<33:04,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 247/1900 [04:58<33:00,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 248/1900 [04:59<33:01,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 249/1900 [05:00<32:34,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 250/1900 [05:01<32:49,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 251/1900 [05:03<33:25,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 252/1900 [05:04<32:50,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 253/1900 [05:05<33:13,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 254/1900 [05:06<32:56,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 255/1900 [05:07<32:50,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 256/1900 [05:09<32:35,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 257/1900 [05:10<32:11,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 258/1900 [05:11<32:00,  1.17s/it]
+
+
Evaluating eval...:  14%|█▎        | 259/1900 [05:12<32:02,  1.17s/it]
+
+
Evaluating eval...:  14%|█▎        | 260/1900 [05:13<32:15,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 261/1900 [05:14<32:16,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 262/1900 [05:16<32:00,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 263/1900 [05:17<32:10,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 264/1900 [05:18<32:04,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 265/1900 [05:19<32:10,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 266/1900 [05:20<32:02,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 267/1900 [05:22<32:09,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 268/1900 [05:23<32:02,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 269/1900 [05:24<32:01,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 270/1900 [05:25<31:52,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 271/1900 [05:26<31:37,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 272/1900 [05:27<32:11,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 273/1900 [05:29<32:17,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 274/1900 [05:30<32:21,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 275/1900 [05:31<32:25,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 276/1900 [05:32<32:50,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 277/1900 [05:33<32:17,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 278/1900 [05:35<32:05,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 279/1900 [05:36<32:14,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 280/1900 [05:37<32:22,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 281/1900 [05:38<32:24,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 282/1900 [05:39<32:04,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 283/1900 [05:41<31:54,  1.18s/it]
+
+
Evaluating eval...:  15%|█▍        | 284/1900 [05:42<32:01,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 285/1900 [05:43<31:43,  1.18s/it]
+
+
Evaluating eval...:  15%|█▌        | 286/1900 [05:44<32:15,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 287/1900 [05:45<32:06,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 288/1900 [05:47<33:36,  1.25s/it]
+
+
Evaluating eval...:  15%|█▌        | 289/1900 [05:48<33:01,  1.23s/it]
+
+
Evaluating eval...:  15%|█▌        | 290/1900 [05:49<32:31,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 291/1900 [05:50<32:11,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 292/1900 [05:51<32:06,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 293/1900 [05:53<31:43,  1.18s/it]
+
+
Evaluating eval...:  15%|█▌        | 294/1900 [05:54<31:30,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 295/1900 [05:55<31:38,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 296/1900 [05:56<31:59,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 297/1900 [05:57<32:13,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 298/1900 [05:59<32:27,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 299/1900 [06:00<31:56,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 300/1900 [06:01<32:02,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 301/1900 [06:02<32:25,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 302/1900 [06:03<32:13,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 303/1900 [06:05<31:53,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 304/1900 [06:06<31:27,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 305/1900 [06:07<31:28,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 306/1900 [06:08<31:24,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 307/1900 [06:09<31:16,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 308/1900 [06:11<31:13,  1.18s/it]
+
+
Evaluating eval...:  16%|█▋        | 309/1900 [06:12<31:15,  1.18s/it]
+
+
Evaluating eval...:  16%|█▋        | 310/1900 [06:13<31:35,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 311/1900 [06:14<31:48,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 312/1900 [06:15<31:41,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 313/1900 [06:16<31:22,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 314/1900 [06:18<31:17,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 315/1900 [06:19<31:28,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 316/1900 [06:20<31:11,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 317/1900 [06:21<31:34,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 318/1900 [06:22<31:27,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 319/1900 [06:24<31:34,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 320/1900 [06:25<31:24,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 321/1900 [06:26<30:59,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 322/1900 [06:27<31:01,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 323/1900 [06:28<31:12,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 324/1900 [06:30<30:45,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 325/1900 [06:31<30:41,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 326/1900 [06:32<30:35,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 327/1900 [06:33<30:31,  1.16s/it]
+
+
Evaluating eval...:  17%|█▋        | 328/1900 [06:34<30:52,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 329/1900 [06:35<30:31,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 330/1900 [06:37<30:53,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 331/1900 [06:38<31:50,  1.22s/it]
+
+
Evaluating eval...:  17%|█▋        | 332/1900 [06:39<31:52,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 333/1900 [06:40<31:37,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 334/1900 [06:41<31:11,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 335/1900 [06:43<30:35,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 336/1900 [06:44<30:38,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 337/1900 [06:45<30:30,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 338/1900 [06:46<31:10,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 339/1900 [06:47<31:21,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 340/1900 [06:49<31:05,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 341/1900 [06:50<31:15,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 342/1900 [06:51<30:46,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 343/1900 [06:52<30:35,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 344/1900 [06:53<30:39,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 345/1900 [06:54<30:40,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 346/1900 [06:56<30:22,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 347/1900 [06:57<30:27,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 348/1900 [06:58<30:08,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 349/1900 [06:59<30:00,  1.16s/it]
+
+
Evaluating eval...:  18%|█▊        | 350/1900 [07:00<30:05,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 351/1900 [07:02<30:44,  1.19s/it]
+
+
Evaluating eval...:  19%|█▊        | 352/1900 [07:03<30:40,  1.19s/it]
+
+
Evaluating eval...:  19%|█▊        | 353/1900 [07:04<30:54,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 354/1900 [07:05<30:51,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 355/1900 [07:06<31:17,  1.22s/it]
+
+
Evaluating eval...:  19%|█▊        | 356/1900 [07:08<31:17,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 357/1900 [07:09<30:49,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 358/1900 [07:10<30:58,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 359/1900 [07:11<30:36,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 360/1900 [07:12<30:42,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 361/1900 [07:13<30:20,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 362/1900 [07:15<31:04,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 363/1900 [07:16<30:30,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 364/1900 [07:17<30:15,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 365/1900 [07:18<30:08,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 366/1900 [07:19<29:52,  1.17s/it]
+
+
Evaluating eval...:  19%|█▉        | 367/1900 [07:21<30:58,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 368/1900 [07:22<31:29,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 369/1900 [07:23<31:14,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 370/1900 [07:24<30:51,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 371/1900 [07:26<30:36,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 372/1900 [07:27<30:20,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 373/1900 [07:28<30:08,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 374/1900 [07:29<29:59,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 375/1900 [07:30<29:43,  1.17s/it]
+
+
Evaluating eval...:  20%|█▉        | 376/1900 [07:31<29:56,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 377/1900 [07:33<30:29,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 378/1900 [07:34<30:31,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 379/1900 [07:35<30:15,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 380/1900 [07:36<30:20,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 381/1900 [07:37<30:32,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 382/1900 [07:39<30:49,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 383/1900 [07:40<30:29,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 384/1900 [07:41<30:13,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 385/1900 [07:42<30:06,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 386/1900 [07:43<30:21,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 387/1900 [07:45<30:08,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 388/1900 [07:46<30:09,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 389/1900 [07:47<30:15,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 390/1900 [07:48<30:02,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 391/1900 [07:49<30:06,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 392/1900 [07:51<29:42,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 393/1900 [07:52<29:35,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 394/1900 [07:53<29:42,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 395/1900 [07:54<29:31,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 396/1900 [07:55<30:12,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 397/1900 [07:57<30:24,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 398/1900 [07:58<30:00,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 399/1900 [07:59<30:16,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 400/1900 [08:00<30:03,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 401/1900 [08:01<29:58,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 402/1900 [08:03<29:38,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 403/1900 [08:04<29:56,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 404/1900 [08:05<30:06,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 405/1900 [08:06<30:19,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 406/1900 [08:07<29:48,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 407/1900 [08:09<29:44,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 408/1900 [08:10<30:12,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 409/1900 [08:11<30:11,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 410/1900 [08:12<30:03,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 411/1900 [08:13<29:46,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 412/1900 [08:15<29:23,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 413/1900 [08:16<29:52,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 414/1900 [08:17<29:50,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 415/1900 [08:18<29:18,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 416/1900 [08:19<28:54,  1.17s/it]
+
+
Evaluating eval...:  22%|██▏       | 417/1900 [08:21<29:30,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 418/1900 [08:22<29:18,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 419/1900 [08:23<29:02,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 420/1900 [08:24<29:30,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 421/1900 [08:25<29:34,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 422/1900 [08:27<29:21,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 423/1900 [08:28<29:37,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 424/1900 [08:29<29:42,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 425/1900 [08:30<29:42,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 426/1900 [08:31<29:44,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 427/1900 [08:33<29:25,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 428/1900 [08:34<29:01,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 429/1900 [08:35<29:18,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 430/1900 [08:36<28:55,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 431/1900 [08:37<28:56,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 432/1900 [08:39<29:22,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 433/1900 [08:40<29:17,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 434/1900 [08:41<30:06,  1.23s/it]
+
+
Evaluating eval...:  23%|██▎       | 435/1900 [08:42<29:34,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 436/1900 [08:43<29:44,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 437/1900 [08:45<29:04,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 438/1900 [08:46<28:51,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 439/1900 [08:47<29:02,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 440/1900 [08:48<28:46,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 441/1900 [08:49<28:37,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 442/1900 [08:50<28:16,  1.16s/it]
+
+
Evaluating eval...:  23%|██▎       | 443/1900 [08:52<28:34,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 444/1900 [08:53<28:34,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 445/1900 [08:54<28:54,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 446/1900 [08:55<29:02,  1.20s/it]
+
+
Evaluating eval...:  24%|██▎       | 447/1900 [08:56<28:48,  1.19s/it]
+
+
Evaluating eval...:  24%|██▎       | 448/1900 [08:58<28:35,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 449/1900 [08:59<28:31,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 450/1900 [09:00<28:25,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 451/1900 [09:01<28:50,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 452/1900 [09:02<28:30,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 453/1900 [09:04<28:58,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 454/1900 [09:05<29:08,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 455/1900 [09:06<29:05,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 456/1900 [09:07<29:17,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 457/1900 [09:08<29:21,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 458/1900 [09:10<29:01,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 459/1900 [09:11<28:30,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 460/1900 [09:12<28:21,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 461/1900 [09:13<28:49,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 462/1900 [09:14<28:33,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 463/1900 [09:15<28:29,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 464/1900 [09:17<28:38,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 465/1900 [09:18<28:40,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 466/1900 [09:19<28:16,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 467/1900 [09:20<28:31,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 468/1900 [09:21<28:30,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 469/1900 [09:23<28:25,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 470/1900 [09:24<28:18,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 471/1900 [09:25<28:19,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 472/1900 [09:26<29:02,  1.22s/it]
+
+
Evaluating eval...:  25%|██▍       | 473/1900 [09:27<28:30,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 474/1900 [09:29<28:13,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 475/1900 [09:30<28:08,  1.18s/it]
+
+
Evaluating eval...:  25%|██▌       | 476/1900 [09:31<27:51,  1.17s/it]
+
+
Evaluating eval...:  25%|██▌       | 477/1900 [09:32<28:25,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 478/1900 [09:33<28:27,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 479/1900 [09:35<28:42,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 480/1900 [09:36<28:27,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 481/1900 [09:37<29:10,  1.23s/it]
+
+
Evaluating eval...:  25%|██▌       | 482/1900 [09:38<28:32,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 483/1900 [09:39<28:17,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 484/1900 [09:41<28:42,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 485/1900 [09:42<28:21,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 486/1900 [09:43<27:55,  1.18s/it]
+
+
Evaluating eval...:  26%|██▌       | 487/1900 [09:44<27:51,  1.18s/it]
+
+
Evaluating eval...:  26%|██▌       | 488/1900 [09:45<28:12,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 489/1900 [09:47<28:14,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 490/1900 [09:48<28:02,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 491/1900 [09:49<28:03,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 492/1900 [09:50<27:58,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 493/1900 [09:51<28:05,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 494/1900 [09:53<27:55,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 495/1900 [09:54<27:36,  1.18s/it]
+
+
Evaluating eval...:  26%|██▌       | 496/1900 [09:55<27:52,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 497/1900 [09:56<28:22,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 498/1900 [09:58<28:41,  1.23s/it]
+
+
Evaluating eval...:  26%|██▋       | 499/1900 [09:59<28:21,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 500/1900 [10:00<28:15,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 501/1900 [10:01<28:14,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 502/1900 [10:02<28:16,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 503/1900 [10:04<28:36,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 504/1900 [10:05<29:03,  1.25s/it]
+
+
Evaluating eval...:  27%|██▋       | 505/1900 [10:06<28:53,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 506/1900 [10:07<28:24,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 507/1900 [10:08<28:03,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 508/1900 [10:10<28:13,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 509/1900 [10:11<28:49,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 510/1900 [10:12<28:15,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 511/1900 [10:13<27:49,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 512/1900 [10:15<27:34,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 513/1900 [10:16<27:10,  1.18s/it]
+
+
Evaluating eval...:  27%|██▋       | 514/1900 [10:17<27:04,  1.17s/it]
+
+
Evaluating eval...:  27%|██▋       | 515/1900 [10:18<27:50,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 516/1900 [10:19<27:46,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 517/1900 [10:20<27:27,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 518/1900 [10:22<27:48,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 519/1900 [10:23<28:14,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 520/1900 [10:24<27:52,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 521/1900 [10:25<28:03,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 522/1900 [10:27<27:49,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 523/1900 [10:28<27:57,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 524/1900 [10:29<27:48,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 525/1900 [10:30<27:38,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 526/1900 [10:31<27:37,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 527/1900 [10:33<27:50,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 528/1900 [10:34<27:44,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 529/1900 [10:35<27:50,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 530/1900 [10:36<27:28,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 531/1900 [10:37<27:17,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 532/1900 [10:39<27:43,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 533/1900 [10:40<27:23,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 534/1900 [10:41<27:26,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 535/1900 [10:42<27:07,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 536/1900 [10:43<27:12,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 537/1900 [10:45<27:12,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 538/1900 [10:46<27:07,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 539/1900 [10:47<27:12,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 540/1900 [10:48<27:05,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 541/1900 [10:49<26:47,  1.18s/it]
+
+
Evaluating eval...:  29%|██▊       | 542/1900 [10:51<27:18,  1.21s/it]
+
+
Evaluating eval...:  29%|██▊       | 543/1900 [10:52<26:58,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 544/1900 [10:53<27:00,  1.20s/it]
+
+
Evaluating eval...:  29%|██▊       | 545/1900 [10:54<28:07,  1.25s/it]
+
+
Evaluating eval...:  29%|██▊       | 546/1900 [10:56<27:47,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 547/1900 [10:57<27:44,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 548/1900 [10:58<27:46,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 549/1900 [10:59<27:44,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 550/1900 [11:00<27:39,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 551/1900 [11:02<27:21,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 552/1900 [11:03<27:32,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 553/1900 [11:04<27:16,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 554/1900 [11:05<26:56,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 555/1900 [11:06<26:59,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 556/1900 [11:08<27:04,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 557/1900 [11:09<26:44,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 558/1900 [11:10<26:48,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 559/1900 [11:11<26:29,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 560/1900 [11:12<26:46,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 561/1900 [11:14<26:44,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 562/1900 [11:15<26:53,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 563/1900 [11:16<27:12,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 564/1900 [11:17<27:32,  1.24s/it]
+
+
Evaluating eval...:  30%|██▉       | 565/1900 [11:19<27:13,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 566/1900 [11:20<27:18,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 567/1900 [11:21<27:16,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 568/1900 [11:22<27:24,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 569/1900 [11:24<27:11,  1.23s/it]
+
+
Evaluating eval...:  30%|███       | 570/1900 [11:25<27:48,  1.25s/it]
+
+
Evaluating eval...:  30%|███       | 571/1900 [11:26<27:11,  1.23s/it]
+
+
Evaluating eval...:  30%|███       | 572/1900 [11:27<26:53,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 573/1900 [11:28<26:31,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 574/1900 [11:30<26:23,  1.19s/it]
+
+
Evaluating eval...:  30%|███       | 575/1900 [11:31<26:09,  1.18s/it]
+
+
Evaluating eval...:  30%|███       | 576/1900 [11:32<26:23,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 577/1900 [11:33<26:29,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 578/1900 [11:34<26:20,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 579/1900 [11:36<26:17,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 580/1900 [11:37<26:07,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 581/1900 [11:38<25:55,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 582/1900 [11:39<27:23,  1.25s/it]
+
+
Evaluating eval...:  31%|███       | 583/1900 [11:40<26:48,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 584/1900 [11:42<26:23,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 585/1900 [11:43<26:07,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 586/1900 [11:44<26:28,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 587/1900 [11:45<26:05,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 588/1900 [11:46<25:46,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 589/1900 [11:47<25:51,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 590/1900 [11:49<25:49,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 591/1900 [11:50<25:48,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 592/1900 [11:51<25:56,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 593/1900 [11:52<25:48,  1.19s/it]
+
+
Evaluating eval...:  31%|███▏      | 594/1900 [11:53<26:04,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 595/1900 [11:55<25:43,  1.18s/it]
+
+
Evaluating eval...:  31%|███▏      | 596/1900 [11:56<25:52,  1.19s/it]
+
+
Evaluating eval...:  31%|███▏      | 597/1900 [11:57<26:14,  1.21s/it]
+
+
Evaluating eval...:  31%|███▏      | 598/1900 [11:58<26:08,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 599/1900 [11:59<26:03,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 600/1900 [12:01<26:44,  1.23s/it]
+
+
Evaluating eval...:  32%|███▏      | 601/1900 [12:02<26:23,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 602/1900 [12:03<25:51,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 603/1900 [12:04<25:39,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 604/1900 [12:05<25:37,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 605/1900 [12:07<25:47,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 606/1900 [12:08<25:56,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 607/1900 [12:09<25:29,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 608/1900 [12:10<26:02,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 609/1900 [12:11<25:57,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 610/1900 [12:13<25:35,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 611/1900 [12:14<25:15,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 612/1900 [12:15<25:31,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 613/1900 [12:16<25:26,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 614/1900 [12:17<25:42,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 615/1900 [12:19<25:27,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 616/1900 [12:20<25:15,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 617/1900 [12:21<25:05,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 618/1900 [12:22<24:56,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 619/1900 [12:23<25:31,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 620/1900 [12:24<25:14,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 621/1900 [12:26<25:17,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 622/1900 [12:27<25:21,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 623/1900 [12:28<25:23,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 624/1900 [12:29<26:00,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 625/1900 [12:31<26:16,  1.24s/it]
+
+
Evaluating eval...:  33%|███▎      | 626/1900 [12:32<25:46,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 627/1900 [12:33<25:23,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 628/1900 [12:34<25:14,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 629/1900 [12:35<25:36,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 630/1900 [12:37<25:30,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 631/1900 [12:38<25:48,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 632/1900 [12:39<25:19,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 633/1900 [12:40<24:57,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 634/1900 [12:41<24:34,  1.16s/it]
+
+
Evaluating eval...:  33%|███▎      | 635/1900 [12:42<24:34,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 636/1900 [12:44<24:50,  1.18s/it]
+
+
Evaluating eval...:  34%|███▎      | 637/1900 [12:45<24:58,  1.19s/it]
+
+
Evaluating eval...:  34%|███▎      | 638/1900 [12:46<25:12,  1.20s/it]
+
+
Evaluating eval...:  34%|███▎      | 639/1900 [12:47<25:11,  1.20s/it]
+
+
Evaluating eval...:  34%|███▎      | 640/1900 [12:48<25:22,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 641/1900 [12:50<25:15,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 642/1900 [12:51<25:06,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 643/1900 [12:52<25:27,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 644/1900 [12:53<25:18,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 645/1900 [12:55<25:19,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 646/1900 [12:56<25:47,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 647/1900 [12:57<25:24,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 648/1900 [12:58<24:59,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 649/1900 [12:59<25:12,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 650/1900 [13:01<25:15,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 651/1900 [13:02<25:09,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 652/1900 [13:03<24:44,  1.19s/it]
+
+
Evaluating eval...:  34%|███▍      | 653/1900 [13:04<24:29,  1.18s/it]
+
+
Evaluating eval...:  34%|███▍      | 654/1900 [13:05<24:54,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 655/1900 [13:07<24:59,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 656/1900 [13:08<24:47,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 657/1900 [13:09<24:36,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 658/1900 [13:10<24:59,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 659/1900 [13:11<24:58,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 660/1900 [13:13<24:40,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 661/1900 [13:14<24:43,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 662/1900 [13:15<25:20,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 663/1900 [13:16<25:23,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 664/1900 [13:17<25:17,  1.23s/it]
+
+
Evaluating eval...:  35%|███▌      | 665/1900 [13:19<25:04,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 666/1900 [13:20<24:48,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 667/1900 [13:21<25:39,  1.25s/it]
+
+
Evaluating eval...:  35%|███▌      | 668/1900 [13:22<25:07,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 669/1900 [13:24<24:41,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 670/1900 [13:25<24:50,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 671/1900 [13:26<24:48,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 672/1900 [13:27<24:35,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 673/1900 [13:28<24:26,  1.19s/it]
+
+
Evaluating eval...:  35%|███▌      | 674/1900 [13:30<24:28,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 675/1900 [13:31<24:23,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 676/1900 [13:32<24:13,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 677/1900 [13:33<24:14,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 678/1900 [13:34<24:30,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 679/1900 [13:35<24:07,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 680/1900 [13:37<24:20,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 681/1900 [13:38<24:52,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 682/1900 [13:39<24:39,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 683/1900 [13:40<24:35,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 684/1900 [13:42<24:11,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 685/1900 [13:43<23:57,  1.18s/it]
+
+
Evaluating eval...:  36%|███▌      | 686/1900 [13:44<24:22,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 687/1900 [13:45<24:21,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 688/1900 [13:46<24:03,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 689/1900 [13:47<23:53,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 690/1900 [13:49<23:57,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 691/1900 [13:50<23:56,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 692/1900 [13:51<23:42,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 693/1900 [13:52<23:45,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 694/1900 [13:53<23:44,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 695/1900 [13:55<24:09,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 696/1900 [13:56<24:09,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 697/1900 [13:57<24:03,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 698/1900 [13:58<24:04,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 699/1900 [13:59<24:13,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 700/1900 [14:01<23:54,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 701/1900 [14:02<23:57,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 702/1900 [14:03<23:57,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 703/1900 [14:04<23:33,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 704/1900 [14:06<24:37,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 705/1900 [14:07<24:18,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 706/1900 [14:08<24:07,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 707/1900 [14:09<23:42,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 708/1900 [14:10<24:07,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 709/1900 [14:11<23:54,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 710/1900 [14:13<24:01,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 711/1900 [14:14<24:27,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 712/1900 [14:15<24:11,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 713/1900 [14:17<25:22,  1.28s/it]
+
+
Evaluating eval...:  38%|███▊      | 714/1900 [14:18<24:32,  1.24s/it]
+
+
Evaluating eval...:  38%|███▊      | 715/1900 [14:19<24:06,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 716/1900 [14:20<23:50,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 717/1900 [14:21<23:38,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 718/1900 [14:23<23:53,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 719/1900 [14:24<23:45,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 720/1900 [14:25<23:34,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 721/1900 [14:26<23:56,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 722/1900 [14:27<23:37,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 723/1900 [14:29<23:39,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 724/1900 [14:30<23:33,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 725/1900 [14:31<23:21,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 726/1900 [14:32<23:26,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 727/1900 [14:33<23:12,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 728/1900 [14:35<23:45,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 729/1900 [14:36<23:24,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 730/1900 [14:37<23:41,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 731/1900 [14:38<23:33,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 732/1900 [14:39<23:16,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 733/1900 [14:41<23:25,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 734/1900 [14:42<23:17,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 735/1900 [14:43<23:05,  1.19s/it]
+
+
Evaluating eval...:  39%|███▊      | 736/1900 [14:44<23:01,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 737/1900 [14:45<22:48,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 738/1900 [14:46<23:07,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 739/1900 [14:48<22:58,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 740/1900 [14:49<23:09,  1.20s/it]
+
+
Evaluating eval...:  39%|███▉      | 741/1900 [14:50<23:58,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 742/1900 [14:51<23:45,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 743/1900 [14:53<23:51,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 744/1900 [14:54<23:34,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 745/1900 [14:55<24:02,  1.25s/it]
+
+
Evaluating eval...:  39%|███▉      | 746/1900 [14:56<23:49,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 747/1900 [14:58<23:56,  1.25s/it]
+
+
Evaluating eval...:  39%|███▉      | 748/1900 [14:59<23:24,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 749/1900 [15:00<23:38,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 750/1900 [15:01<23:28,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 751/1900 [15:03<23:28,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 752/1900 [15:04<23:31,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 753/1900 [15:05<23:29,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 754/1900 [15:06<23:04,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 755/1900 [15:07<22:49,  1.20s/it]
+
+
Evaluating eval...:  40%|███▉      | 756/1900 [15:09<23:14,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 757/1900 [15:10<23:09,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 758/1900 [15:11<23:21,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 759/1900 [15:12<23:16,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 760/1900 [15:14<23:18,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 761/1900 [15:15<23:00,  1.21s/it]
+
+
Evaluating eval...:  40%|████      | 762/1900 [15:16<22:32,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 763/1900 [15:17<22:21,  1.18s/it]
+
+
Evaluating eval...:  40%|████      | 764/1900 [15:18<22:16,  1.18s/it]
+
+
Evaluating eval...:  40%|████      | 765/1900 [15:19<22:43,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 766/1900 [15:21<22:44,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 767/1900 [15:22<23:02,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 768/1900 [15:23<23:49,  1.26s/it]
+
+
Evaluating eval...:  40%|████      | 769/1900 [15:24<23:28,  1.25s/it]
+
+
Evaluating eval...:  41%|████      | 770/1900 [15:26<23:01,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 771/1900 [15:27<23:06,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 772/1900 [15:28<23:16,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 773/1900 [15:29<23:04,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 774/1900 [15:30<22:42,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 775/1900 [15:32<23:01,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 776/1900 [15:33<22:59,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 777/1900 [15:34<23:00,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 778/1900 [15:35<22:42,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 779/1900 [15:37<22:35,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 780/1900 [15:38<23:28,  1.26s/it]
+
+
Evaluating eval...:  41%|████      | 781/1900 [15:39<23:01,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 782/1900 [15:40<23:29,  1.26s/it]
+
+
Evaluating eval...:  41%|████      | 783/1900 [15:42<23:14,  1.25s/it]
+
+
Evaluating eval...:  41%|████▏     | 784/1900 [15:43<23:00,  1.24s/it]
+
+
Evaluating eval...:  41%|████▏     | 785/1900 [15:44<22:34,  1.21s/it]
+
+
Evaluating eval...:  41%|████▏     | 786/1900 [15:45<22:20,  1.20s/it]
+
+
Evaluating eval...:  41%|████▏     | 787/1900 [15:46<22:15,  1.20s/it]
+
+
Evaluating eval...:  41%|████▏     | 788/1900 [15:48<22:14,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 789/1900 [15:49<22:21,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 790/1900 [15:50<22:15,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 791/1900 [15:51<22:23,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 792/1900 [15:53<22:31,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 793/1900 [15:54<22:23,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 794/1900 [15:55<22:12,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 795/1900 [15:56<22:08,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 796/1900 [15:57<21:55,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 797/1900 [15:58<21:52,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 798/1900 [16:00<21:52,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 799/1900 [16:01<21:53,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 800/1900 [16:02<22:09,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 801/1900 [16:03<22:00,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 802/1900 [16:04<21:37,  1.18s/it]
+
+
Evaluating eval...:  42%|████▏     | 803/1900 [16:06<22:02,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 804/1900 [16:07<21:53,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 805/1900 [16:08<22:14,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 806/1900 [16:09<21:52,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 807/1900 [16:10<21:44,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 808/1900 [16:12<22:18,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 809/1900 [16:13<22:34,  1.24s/it]
+
+
Evaluating eval...:  43%|████▎     | 810/1900 [16:14<22:15,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 811/1900 [16:15<22:01,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 812/1900 [16:17<22:17,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 813/1900 [16:18<21:50,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 814/1900 [16:19<21:49,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 815/1900 [16:20<21:41,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 816/1900 [16:21<21:47,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 817/1900 [16:23<21:32,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 818/1900 [16:24<21:37,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 819/1900 [16:25<21:28,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 820/1900 [16:26<21:32,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 821/1900 [16:27<21:17,  1.18s/it]
+
+
Evaluating eval...:  43%|████▎     | 822/1900 [16:29<21:30,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 823/1900 [16:30<21:46,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 824/1900 [16:31<21:59,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 825/1900 [16:32<21:38,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 826/1900 [16:33<21:45,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 827/1900 [16:35<21:39,  1.21s/it]
+
+
Evaluating eval...:  44%|████▎     | 828/1900 [16:36<21:36,  1.21s/it]
+
+
Evaluating eval...:  44%|████▎     | 829/1900 [16:37<21:20,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 830/1900 [16:38<21:23,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 831/1900 [16:39<21:06,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 832/1900 [16:41<21:07,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 833/1900 [16:42<21:23,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 834/1900 [16:43<21:04,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 835/1900 [16:44<21:23,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 836/1900 [16:45<21:26,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 837/1900 [16:47<21:10,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 838/1900 [16:48<20:50,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 839/1900 [16:49<20:40,  1.17s/it]
+
+
Evaluating eval...:  44%|████▍     | 840/1900 [16:50<20:42,  1.17s/it]
+
+
Evaluating eval...:  44%|████▍     | 841/1900 [16:51<21:15,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 842/1900 [16:53<21:23,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 843/1900 [16:54<21:06,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 844/1900 [16:55<20:46,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 845/1900 [16:56<20:45,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 846/1900 [16:57<21:15,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 847/1900 [16:59<20:54,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 848/1900 [17:00<20:56,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 849/1900 [17:01<20:55,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 850/1900 [17:02<21:01,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 851/1900 [17:03<20:52,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 852/1900 [17:05<21:16,  1.22s/it]
+
+
Evaluating eval...:  45%|████▍     | 853/1900 [17:06<21:18,  1.22s/it]
+
+
Evaluating eval...:  45%|████▍     | 854/1900 [17:07<21:15,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 855/1900 [17:08<21:16,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 856/1900 [17:09<20:58,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 857/1900 [17:11<20:47,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 858/1900 [17:12<21:05,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 859/1900 [17:13<21:03,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 860/1900 [17:14<20:58,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 861/1900 [17:15<21:09,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 862/1900 [17:17<21:01,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 863/1900 [17:18<20:34,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 864/1900 [17:19<20:24,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 865/1900 [17:20<20:09,  1.17s/it]
+
+
Evaluating eval...:  46%|████▌     | 866/1900 [17:21<20:12,  1.17s/it]
+
+
Evaluating eval...:  46%|████▌     | 867/1900 [17:23<20:27,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 868/1900 [17:24<20:55,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 869/1900 [17:25<20:36,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 870/1900 [17:26<20:46,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 871/1900 [17:27<20:52,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 872/1900 [17:29<20:36,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 873/1900 [17:30<20:26,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 874/1900 [17:31<20:41,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 875/1900 [17:32<20:37,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 876/1900 [17:33<20:23,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 877/1900 [17:35<20:04,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 878/1900 [17:36<20:24,  1.20s/it]
+
+
Evaluating eval...:  46%|████▋     | 879/1900 [17:37<20:11,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 880/1900 [17:38<20:00,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 881/1900 [17:39<19:50,  1.17s/it]
+
+
Evaluating eval...:  46%|████▋     | 882/1900 [17:40<20:05,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 883/1900 [17:42<20:23,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 884/1900 [17:43<20:18,  1.20s/it]
+
+
Evaluating eval...:  47%|███��▋     | 885/1900 [17:44<20:02,  1.18s/it]
+
+
Evaluating eval...:  47%|████▋     | 886/1900 [17:45<19:56,  1.18s/it]
+
+
Evaluating eval...:  47%|████▋     | 887/1900 [17:46<20:05,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 888/1900 [17:48<20:06,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 889/1900 [17:49<20:04,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 890/1900 [17:50<19:58,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 891/1900 [17:51<20:24,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 892/1900 [17:53<20:32,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 893/1900 [17:54<20:35,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 894/1900 [17:55<20:16,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 895/1900 [17:56<20:24,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 896/1900 [17:57<20:15,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 897/1900 [17:59<20:08,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 898/1900 [18:00<20:36,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 899/1900 [18:01<20:13,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 900/1900 [18:02<20:14,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 901/1900 [18:03<19:58,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 902/1900 [18:05<20:18,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 903/1900 [18:06<20:25,  1.23s/it]
+
+
Evaluating eval...:  48%|████▊     | 904/1900 [18:07<20:17,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 905/1900 [18:08<20:06,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 906/1900 [18:10<20:04,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 907/1900 [18:11<20:25,  1.23s/it]
+
+
Evaluating eval...:  48%|████▊     | 908/1900 [18:12<20:06,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 909/1900 [18:13<20:02,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 910/1900 [18:14<19:54,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 911/1900 [18:16<20:10,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 912/1900 [18:17<20:01,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 913/1900 [18:18<19:56,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 914/1900 [18:19<19:50,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 915/1900 [18:21<20:13,  1.23s/it]
+
+
Evaluating eval...:  48%|████▊     | 916/1900 [18:22<20:01,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 917/1900 [18:23<19:48,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 918/1900 [18:24<19:38,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 919/1900 [18:25<19:39,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 920/1900 [18:26<19:26,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 921/1900 [18:28<19:20,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 922/1900 [18:29<19:15,  1.18s/it]
+
+
Evaluating eval...:  49%|████▊     | 923/1900 [18:30<19:53,  1.22s/it]
+
+
Evaluating eval...:  49%|████▊     | 924/1900 [18:31<19:31,  1.20s/it]
+
+
Evaluating eval...:  49%|████▊     | 925/1900 [18:33<19:38,  1.21s/it]
+
+
Evaluating eval...:  49%|████▊     | 926/1900 [18:34<19:29,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 927/1900 [18:35<19:12,  1.18s/it]
+
+
Evaluating eval...:  49%|████▉     | 928/1900 [18:36<19:30,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 929/1900 [18:37<19:14,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 930/1900 [18:38<18:57,  1.17s/it]
+
+
Evaluating eval...:  49%|████▉     | 931/1900 [18:40<19:20,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 932/1900 [18:41<19:35,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 933/1900 [18:42<19:40,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 934/1900 [18:43<19:25,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 935/1900 [18:45<19:29,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 936/1900 [18:46<19:44,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 937/1900 [18:47<19:37,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 938/1900 [18:48<19:37,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 939/1900 [18:49<19:48,  1.24s/it]
+
+
Evaluating eval...:  49%|████▉     | 940/1900 [18:51<19:44,  1.23s/it]
+
+
Evaluating eval...:  50%|████▉     | 941/1900 [18:52<19:38,  1.23s/it]
+
+
Evaluating eval...:  50%|████▉     | 942/1900 [18:53<19:59,  1.25s/it]
+
+
Evaluating eval...:  50%|████▉     | 943/1900 [18:54<19:40,  1.23s/it]
+
+
Evaluating eval...:  50%|████▉     | 944/1900 [18:56<19:28,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 945/1900 [18:57<19:06,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 946/1900 [18:58<19:18,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 947/1900 [18:59<19:15,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 948/1900 [19:00<19:07,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 949/1900 [19:02<19:08,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 950/1900 [19:03<19:04,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 951/1900 [19:04<19:37,  1.24s/it]
+
+
Evaluating eval...:  50%|█████     | 952/1900 [19:05<19:44,  1.25s/it]
+
+
Evaluating eval...:  50%|█████     | 953/1900 [19:07<19:12,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 954/1900 [19:08<18:53,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 955/1900 [19:09<18:59,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 956/1900 [19:10<18:48,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 957/1900 [19:11<18:37,  1.18s/it]
+
+
Evaluating eval...:  50%|█████     | 958/1900 [19:12<18:40,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 959/1900 [19:14<18:35,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 960/1900 [19:15<18:48,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 961/1900 [19:16<19:09,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 962/1900 [19:17<19:00,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 963/1900 [19:19<19:06,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 964/1900 [19:20<19:11,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 965/1900 [19:21<19:05,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 966/1900 [19:22<18:41,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 967/1900 [19:23<18:29,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 968/1900 [19:25<18:28,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 969/1900 [19:26<18:35,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 970/1900 [19:27<18:52,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 971/1900 [19:28<18:36,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 972/1900 [19:29<18:39,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 973/1900 [19:31<18:26,  1.19s/it]
+
+
Evaluating eval...:  51%|█████▏    | 974/1900 [19:32<18:21,  1.19s/it]
+
+
Evaluating eval...:  51%|█████▏    | 975/1900 [19:33<18:42,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 976/1900 [19:34<18:42,  1.22s/it]
+
+
Evaluating eval...:  51%|█████▏    | 977/1900 [19:35<18:23,  1.20s/it]
+
+
Evaluating eval...:  51%|█████▏    | 978/1900 [19:37<18:35,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 979/1900 [19:38<18:29,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 980/1900 [19:39<18:26,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 981/1900 [19:40<18:09,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 982/1900 [19:41<18:05,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 983/1900 [19:43<18:23,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 984/1900 [19:44<18:16,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 985/1900 [19:45<18:07,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 986/1900 [19:46<18:06,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 987/1900 [19:47<18:05,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 988/1900 [19:49<17:59,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 989/1900 [19:50<18:15,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 990/1900 [19:51<18:42,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 991/1900 [19:52<18:22,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 992/1900 [19:53<18:11,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 993/1900 [19:55<18:20,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 994/1900 [19:56<18:05,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 995/1900 [19:57<18:34,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 996/1900 [19:58<18:15,  1.21s/it]
+
+
Evaluating eval...:  52%|████���▏    | 997/1900 [19:59<18:09,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 998/1900 [20:01<18:07,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 999/1900 [20:02<18:04,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1000/1900 [20:03<17:57,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1001/1900 [20:04<17:47,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1002/1900 [20:05<17:49,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1003/1900 [20:07<18:02,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1004/1900 [20:08<18:12,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1005/1900 [20:09<17:56,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1006/1900 [20:10<17:56,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1007/1900 [20:11<17:50,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1008/1900 [20:13<17:36,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1009/1900 [20:14<17:38,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1010/1900 [20:15<17:28,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1011/1900 [20:16<17:38,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1012/1900 [20:17<18:04,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1013/1900 [20:19<17:44,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1014/1900 [20:20<18:07,  1.23s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1015/1900 [20:21<17:50,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1016/1900 [20:22<18:20,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1017/1900 [20:24<18:18,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1018/1900 [20:25<18:13,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1019/1900 [20:26<18:32,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1020/1900 [20:27<18:17,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1021/1900 [20:29<17:57,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1022/1900 [20:30<17:54,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1023/1900 [20:31<17:57,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1024/1900 [20:32<17:46,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1025/1900 [20:33<17:26,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1026/1900 [20:35<17:44,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1027/1900 [20:36<17:41,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1028/1900 [20:37<17:27,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1029/1900 [20:38<17:27,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1030/1900 [20:39<17:21,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1031/1900 [20:41<17:43,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1032/1900 [20:42<17:32,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1033/1900 [20:43<17:14,  1.19s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1034/1900 [20:44<17:55,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1035/1900 [20:46<17:39,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1036/1900 [20:47<17:36,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1037/1900 [20:48<17:48,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1038/1900 [20:49<17:39,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1039/1900 [20:51<17:35,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1040/1900 [20:52<17:16,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1041/1900 [20:53<17:15,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1042/1900 [20:54<17:16,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1043/1900 [20:55<17:05,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1044/1900 [20:56<17:04,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1045/1900 [20:58<16:50,  1.18s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1046/1900 [20:59<16:46,  1.18s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1047/1900 [21:00<16:43,  1.18s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1048/1900 [21:01<16:56,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1049/1900 [21:02<17:04,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1050/1900 [21:04<17:20,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1051/1900 [21:05<17:19,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1052/1900 [21:06<17:20,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1053/1900 [21:07<17:13,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1054/1900 [21:09<17:03,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1055/1900 [21:10<16:51,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1056/1900 [21:11<17:06,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1057/1900 [21:12<17:19,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1058/1900 [21:13<17:17,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1059/1900 [21:15<16:52,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1060/1900 [21:16<16:45,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1061/1900 [21:17<16:41,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1062/1900 [21:18<16:27,  1.18s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1063/1900 [21:19<16:32,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1064/1900 [21:20<16:31,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1065/1900 [21:22<16:37,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1066/1900 [21:23<16:34,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1067/1900 [21:24<16:41,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1068/1900 [21:25<16:32,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1069/1900 [21:27<16:43,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1070/1900 [21:28<16:40,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1071/1900 [21:29<16:46,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1072/1900 [21:30<16:45,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1073/1900 [21:31<16:30,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1074/1900 [21:33<16:29,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1075/1900 [21:34<16:30,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1076/1900 [21:35<16:39,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1077/1900 [21:36<16:42,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1078/1900 [21:37<16:20,  1.19s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1079/1900 [21:39<16:30,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1080/1900 [21:40<17:02,  1.25s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1081/1900 [21:41<16:51,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1082/1900 [21:42<16:34,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1083/1900 [21:44<16:40,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1084/1900 [21:45<16:29,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1085/1900 [21:46<16:26,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1086/1900 [21:47<16:30,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1087/1900 [21:48<16:22,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1088/1900 [21:50<16:18,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1089/1900 [21:51<16:31,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1090/1900 [21:52<16:15,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1091/1900 [21:53<16:05,  1.19s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1092/1900 [21:54<16:26,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1093/1900 [21:56<16:14,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1094/1900 [21:57<16:09,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1095/1900 [21:58<16:04,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1096/1900 [21:59<15:49,  1.18s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1097/1900 [22:00<15:39,  1.17s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1098/1900 [22:02<15:57,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1099/1900 [22:03<16:00,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1100/1900 [22:04<16:01,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1101/1900 [22:05<15:52,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1102/1900 [22:06<15:45,  1.18s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1103/1900 [22:08<16:08,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1104/1900 [22:09<15:49,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1105/1900 [22:10<16:23,  1.24s/it]
+
+
Evaluating eval...:  58%|███���█▊    | 1106/1900 [22:11<16:23,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1107/1900 [22:13<16:19,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1108/1900 [22:14<16:19,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1109/1900 [22:15<16:05,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1110/1900 [22:16<15:54,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1111/1900 [22:17<16:23,  1.25s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1112/1900 [22:19<16:04,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1113/1900 [22:20<16:13,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1114/1900 [22:21<16:03,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1115/1900 [22:22<16:03,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1116/1900 [22:24<16:06,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1117/1900 [22:25<15:59,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1118/1900 [22:26<15:46,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1119/1900 [22:27<15:59,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1120/1900 [22:28<16:00,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1121/1900 [22:30<15:47,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1122/1900 [22:31<15:33,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1123/1900 [22:32<15:48,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1124/1900 [22:33<15:46,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1125/1900 [22:34<15:35,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1126/1900 [22:36<15:33,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1127/1900 [22:37<15:27,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1128/1900 [22:38<15:40,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1129/1900 [22:39<15:23,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1130/1900 [22:40<15:10,  1.18s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1131/1900 [22:42<15:19,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1132/1900 [22:43<15:25,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1133/1900 [22:44<15:25,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1134/1900 [22:45<15:23,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1135/1900 [22:47<15:49,  1.24s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1136/1900 [22:48<15:34,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1137/1900 [22:49<15:19,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1138/1900 [22:50<15:31,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1139/1900 [22:51<15:23,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1140/1900 [22:53<15:26,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1141/1900 [22:54<15:23,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1142/1900 [22:55<15:08,  1.20s/it]
+
+
Evaluating eval...:  60%|██████    | 1143/1900 [22:56<15:00,  1.19s/it]
+
+
Evaluating eval...:  60%|██████    | 1144/1900 [22:57<15:08,  1.20s/it]
+
+
Evaluating eval...:  60%|██████    | 1145/1900 [22:59<15:07,  1.20s/it]
+
+
Evaluating eval...:  60%|██████    | 1146/1900 [23:00<15:14,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1147/1900 [23:01<15:19,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1148/1900 [23:02<15:13,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1149/1900 [23:03<15:02,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1150/1900 [23:05<15:08,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1151/1900 [23:06<14:59,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1152/1900 [23:07<14:53,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1153/1900 [23:08<15:05,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1154/1900 [23:10<15:01,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1155/1900 [23:11<14:53,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1156/1900 [23:12<14:39,  1.18s/it]
+
+
Evaluating eval...:  61%|██████    | 1157/1900 [23:13<14:38,  1.18s/it]
+
+
Evaluating eval...:  61%|██████    | 1158/1900 [23:14<14:59,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1159/1900 [23:15<14:45,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1160/1900 [23:17<14:50,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1161/1900 [23:18<14:47,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1162/1900 [23:19<14:39,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1163/1900 [23:20<14:35,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1164/1900 [23:21<14:27,  1.18s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1165/1900 [23:23<14:31,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1166/1900 [23:24<14:40,  1.20s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1167/1900 [23:25<14:45,  1.21s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1168/1900 [23:26<14:47,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1169/1900 [23:27<14:46,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1170/1900 [23:29<14:49,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1171/1900 [23:30<14:51,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1172/1900 [23:31<14:38,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1173/1900 [23:32<14:27,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1174/1900 [23:33<14:21,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1175/1900 [23:35<14:32,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1176/1900 [23:36<14:49,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1177/1900 [23:37<14:36,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1178/1900 [23:38<14:23,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1179/1900 [23:40<14:25,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1180/1900 [23:41<14:30,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1181/1900 [23:42<14:25,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1182/1900 [23:43<14:32,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1183/1900 [23:44<14:36,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1184/1900 [23:46<14:39,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1185/1900 [23:47<14:28,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1186/1900 [23:48<14:36,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1187/1900 [23:49<14:28,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1188/1900 [23:50<14:17,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1189/1900 [23:52<14:07,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1190/1900 [23:53<13:59,  1.18s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1191/1900 [23:54<14:09,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1192/1900 [23:55<14:22,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1193/1900 [23:56<14:18,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1194/1900 [23:58<14:31,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1195/1900 [23:59<14:28,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1196/1900 [24:00<14:15,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1197/1900 [24:01<14:25,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1198/1900 [24:03<14:13,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1199/1900 [24:04<14:27,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1200/1900 [24:05<14:15,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1201/1900 [24:06<14:04,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1202/1900 [24:07<13:53,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1203/1900 [24:09<14:13,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1204/1900 [24:10<14:20,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1205/1900 [24:11<14:14,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1206/1900 [24:12<14:21,  1.24s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1207/1900 [24:14<14:07,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1208/1900 [24:15<14:01,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1209/1900 [24:16<13:51,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1210/1900 [24:17<14:06,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1211/1900 [24:19<14:03,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1212/1900 [24:20<14:01,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1213/1900 [24:21<13:48,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1214/1900 [24:22<13:43,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1215/1900 [24:23<13:40,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1216/1900 [24:25<13:48,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1217/1900 [24:26<13:44,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1218/1900 [24:27<13:52,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1219/1900 [24:28<13:43,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1220/1900 [24:29<13:39,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1221/1900 [24:31<13:33,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1222/1900 [24:32<13:25,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1223/1900 [24:33<13:30,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1224/1900 [24:34<13:24,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1225/1900 [24:35<13:28,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1226/1900 [24:37<13:32,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1227/1900 [24:38<13:26,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1228/1900 [24:39<13:19,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1229/1900 [24:40<13:18,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1230/1900 [24:41<13:22,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1231/1900 [24:43<13:24,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1232/1900 [24:44<13:20,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1233/1900 [24:45<13:15,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1234/1900 [24:46<13:19,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1235/1900 [24:47<13:34,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1236/1900 [24:49<13:23,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1237/1900 [24:50<13:16,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1238/1900 [24:51<13:11,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1239/1900 [24:52<13:19,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1240/1900 [24:54<13:50,  1.26s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1241/1900 [24:55<13:41,  1.25s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1242/1900 [24:56<13:40,  1.25s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1243/1900 [24:57<13:55,  1.27s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1244/1900 [24:58<13:28,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1245/1900 [25:00<13:14,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1246/1900 [25:01<13:20,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1247/1900 [25:02<13:07,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1248/1900 [25:03<12:58,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1249/1900 [25:04<13:00,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1250/1900 [25:06<12:55,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1251/1900 [25:07<12:46,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1252/1900 [25:08<12:41,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1253/1900 [25:09<12:46,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1254/1900 [25:10<12:55,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1255/1900 [25:12<13:14,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1256/1900 [25:13<13:13,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1257/1900 [25:14<12:56,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1258/1900 [25:15<13:04,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1259/1900 [25:16<12:53,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1260/1900 [25:18<12:51,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1261/1900 [25:19<12:59,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1262/1900 [25:20<12:47,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1263/1900 [25:21<12:41,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1264/1900 [25:23<12:45,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1265/1900 [25:24<12:43,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1266/1900 [25:25<12:51,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1267/1900 [25:26<12:50,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1268/1900 [25:27<12:46,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1269/1900 [25:29<12:49,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1270/1900 [25:30<12:38,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1271/1900 [25:31<12:44,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1272/1900 [25:32<12:35,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1273/1900 [25:33<12:33,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1274/1900 [25:35<12:28,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1275/1900 [25:36<12:22,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1276/1900 [25:37<12:26,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1277/1900 [25:38<12:31,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1278/1900 [25:39<12:22,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1279/1900 [25:41<12:20,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1280/1900 [25:42<12:16,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1281/1900 [25:43<12:09,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1282/1900 [25:44<12:08,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1283/1900 [25:45<12:13,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1284/1900 [25:46<12:13,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1285/1900 [25:48<12:18,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1286/1900 [25:49<12:22,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1287/1900 [25:50<12:37,  1.24s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1288/1900 [25:51<12:36,  1.24s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1289/1900 [25:53<12:30,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1290/1900 [25:54<12:21,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1291/1900 [25:55<12:12,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1292/1900 [25:56<12:18,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1293/1900 [25:57<12:18,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1294/1900 [25:59<12:23,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1295/1900 [26:00<12:16,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1296/1900 [26:01<12:14,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1297/1900 [26:02<12:04,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1298/1900 [26:04<12:07,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1299/1900 [26:05<12:09,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1300/1900 [26:06<12:14,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1301/1900 [26:07<12:19,  1.24s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1302/1900 [26:08<12:12,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1303/1900 [26:10<12:08,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1304/1900 [26:11<12:05,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1305/1900 [26:12<11:59,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1306/1900 [26:13<11:54,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1307/1900 [26:14<11:45,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1308/1900 [26:16<11:42,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1309/1900 [26:17<11:44,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1310/1900 [26:18<11:38,  1.18s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1311/1900 [26:19<11:45,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1312/1900 [26:20<11:43,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1313/1900 [26:22<11:45,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1314/1900 [26:23<11:36,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1315/1900 [26:24<11:36,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1316/1900 [26:25<11:45,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1317/1900 [26:26<11:42,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1318/1900 [26:28<11:46,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1319/1900 [26:29<11:42,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1320/1900 [26:30<11:32,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1321/1900 [26:31<11:44,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1322/1900 [26:32<11:38,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1323/1900 [26:34<11:37,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1324/1900 [26:35<11:29,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1325/1900 [26:36<11:20,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1326/1900 [26:37<11:22,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1327/1900 [26:38<11:18,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1328/1900 [26:40<11:35,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1329/1900 [26:41<11:28,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1330/1900 [26:42<11:30,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1331/1900 [26:43<11:26,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1332/1900 [26:44<11:21,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1333/1900 [26:46<11:19,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1334/1900 [26:47<11:22,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1335/1900 [26:48<11:19,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1336/1900 [26:49<11:21,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1337/1900 [26:51<11:24,  1.22s/it]
+
+
Evaluating eval...:  70%|███████   | 1338/1900 [26:52<11:18,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1339/1900 [26:53<11:14,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1340/1900 [26:54<11:12,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1341/1900 [26:55<11:10,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1342/1900 [26:57<11:12,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1343/1900 [26:58<11:06,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1344/1900 [26:59<11:09,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1345/1900 [27:00<11:16,  1.22s/it]
+
+
Evaluating eval...:  71%|███████   | 1346/1900 [27:02<11:40,  1.26s/it]
+
+
Evaluating eval...:  71%|███████   | 1347/1900 [27:03<11:24,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1348/1900 [27:04<11:09,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1349/1900 [27:05<11:26,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1350/1900 [27:06<11:21,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1351/1900 [27:08<11:15,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1352/1900 [27:09<11:13,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1353/1900 [27:10<11:23,  1.25s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1354/1900 [27:11<11:14,  1.24s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1355/1900 [27:13<11:04,  1.22s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1356/1900 [27:14<11:06,  1.22s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1357/1900 [27:15<10:58,  1.21s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1358/1900 [27:16<10:51,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1359/1900 [27:17<10:50,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1360/1900 [27:19<10:48,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1361/1900 [27:20<10:50,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1362/1900 [27:21<10:38,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1363/1900 [27:22<10:43,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1364/1900 [27:23<10:38,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1365/1900 [27:24<10:32,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1366/1900 [27:26<10:25,  1.17s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1367/1900 [27:27<10:30,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1368/1900 [27:28<10:35,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1369/1900 [27:29<10:33,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1370/1900 [27:31<10:47,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1371/1900 [27:32<10:51,  1.23s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1372/1900 [27:33<10:46,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1373/1900 [27:34<10:40,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1374/1900 [27:35<10:37,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1375/1900 [27:37<10:33,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1376/1900 [27:38<10:33,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1377/1900 [27:39<10:29,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1378/1900 [27:40<10:19,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1379/1900 [27:41<10:19,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1380/1900 [27:43<10:17,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1381/1900 [27:44<10:19,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1382/1900 [27:45<10:21,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1383/1900 [27:46<10:22,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1384/1900 [27:47<10:19,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1385/1900 [27:49<10:19,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1386/1900 [27:50<10:21,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1387/1900 [27:51<10:15,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1388/1900 [27:52<10:11,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1389/1900 [27:53<10:04,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1390/1900 [27:55<10:21,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1391/1900 [27:56<10:21,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1392/1900 [27:57<10:14,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1393/1900 [27:58<10:09,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1394/1900 [27:59<10:25,  1.24s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1395/1900 [28:01<10:17,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1396/1900 [28:02<10:08,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1397/1900 [28:03<09:59,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1398/1900 [28:04<10:04,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1399/1900 [28:05<10:03,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1400/1900 [28:07<09:56,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1401/1900 [28:08<10:09,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1402/1900 [28:09<09:57,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1403/1900 [28:10<09:50,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1404/1900 [28:11<09:46,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1405/1900 [28:13<09:41,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1406/1900 [28:14<09:44,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1407/1900 [28:15<09:47,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1408/1900 [28:16<09:57,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1409/1900 [28:17<09:54,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1410/1900 [28:19<09:50,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1411/1900 [28:20<09:49,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1412/1900 [28:21<09:47,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1413/1900 [28:22<09:46,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1414/1900 [28:23<09:42,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1415/1900 [28:25<09:39,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1416/1900 [28:26<09:33,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1417/1900 [28:27<09:35,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1418/1900 [28:28<09:29,  1.18s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1419/1900 [28:29<09:52,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1420/1900 [28:31<09:48,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1421/1900 [28:32<09:43,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1422/1900 [28:33<09:52,  1.24s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1423/1900 [28:34<09:40,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1424/1900 [28:36<09:43,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1425/1900 [28:37<09:36,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1426/1900 [28:38<09:31,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1427/1900 [28:39<09:30,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1428/1900 [28:40<09:35,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1429/1900 [28:42<09:31,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1430/1900 [28:43<09:23,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1431/1900 [28:44<09:29,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1432/1900 [28:45<09:51,  1.26s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1433/1900 [28:47<09:38,  1.24s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1434/1900 [28:48<09:33,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1435/1900 [28:49<09:28,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1436/1900 [28:50<09:29,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1437/1900 [28:51<09:21,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1438/1900 [28:53<09:19,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1439/1900 [28:54<09:16,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1440/1900 [28:55<09:17,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1441/1900 [28:56<09:13,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1442/1900 [28:57<09:17,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1443/1900 [28:59<09:20,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1444/1900 [29:00<09:12,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1445/1900 [29:01<09:11,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1446/1900 [29:02<09:08,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1447/1900 [29:04<09:04,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1448/1900 [29:05<09:01,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1449/1900 [29:06<09:00,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1450/1900 [29:07<09:03,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1451/1900 [29:08<09:03,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1452/1900 [29:10<09:00,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1453/1900 [29:11<09:02,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1454/1900 [29:12<09:13,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1455/1900 [29:13<09:05,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1456/1900 [29:14<09:00,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1457/1900 [29:16<09:00,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1458/1900 [29:17<09:00,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1459/1900 [29:18<08:50,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1460/1900 [29:19<08:42,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1461/1900 [29:20<08:40,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1462/1900 [29:22<08:40,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1463/1900 [29:23<08:36,  1.18s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1464/1900 [29:24<08:40,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1465/1900 [29:25<08:39,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1466/1900 [29:26<08:49,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1467/1900 [29:28<08:42,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1468/1900 [29:29<08:56,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1469/1900 [29:30<08:55,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1470/1900 [29:31<08:42,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1471/1900 [29:33<08:41,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1472/1900 [29:34<08:35,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1473/1900 [29:35<08:33,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1474/1900 [29:36<08:30,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1475/1900 [29:37<08:36,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1476/1900 [29:39<08:36,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1477/1900 [29:40<08:32,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1478/1900 [29:41<08:34,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1479/1900 [29:42<08:42,  1.24s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1480/1900 [29:43<08:29,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1481/1900 [29:45<08:29,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1482/1900 [29:46<08:23,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1483/1900 [29:47<08:15,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1484/1900 [29:48<08:16,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1485/1900 [29:50<08:26,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1486/1900 [29:51<08:24,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1487/1900 [29:52<08:26,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1488/1900 [29:53<08:16,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1489/1900 [29:54<08:11,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1490/1900 [29:56<08:15,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1491/1900 [29:57<08:09,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1492/1900 [29:58<08:14,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1493/1900 [29:59<08:14,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1494/1900 [30:00<08:09,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1495/1900 [30:02<08:08,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1496/1900 [30:03<08:03,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1497/1900 [30:04<08:00,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1498/1900 [30:05<08:11,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1499/1900 [30:06<08:10,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1500/1900 [30:08<08:06,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1501/1900 [30:09<07:58,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1502/1900 [30:10<07:52,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1503/1900 [30:11<07:51,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1504/1900 [30:12<07:47,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1505/1900 [30:14<07:46,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1506/1900 [30:15<07:50,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1507/1900 [30:16<07:51,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1508/1900 [30:17<07:53,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1509/1900 [30:18<07:53,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1510/1900 [30:20<07:50,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1511/1900 [30:21<07:50,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1512/1900 [30:22<07:52,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1513/1900 [30:23<07:52,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1514/1900 [30:24<07:49,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1515/1900 [30:26<07:57,  1.24s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1516/1900 [30:27<07:54,  1.24s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1517/1900 [30:28<07:46,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1518/1900 [30:29<07:36,  1.19s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1519/1900 [30:30<07:29,  1.18s/it]
+
+
Evaluating eval...:  80%|████████  | 1520/1900 [30:32<07:34,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1521/1900 [30:33<07:36,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1522/1900 [30:34<07:30,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1523/1900 [30:35<07:31,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1524/1900 [30:37<07:35,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1525/1900 [30:38<07:33,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1526/1900 [30:39<07:27,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1527/1900 [30:40<07:26,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1528/1900 [30:41<07:25,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1529/1900 [30:43<07:24,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1530/1900 [30:44<07:30,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1531/1900 [30:45<07:27,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1532/1900 [30:46<07:33,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1533/1900 [30:47<07:26,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1534/1900 [30:49<07:22,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1535/1900 [30:50<07:15,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1536/1900 [30:51<07:10,  1.18s/it]
+
+
Evaluating eval...:  81%|████████  | 1537/1900 [30:52<07:15,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1538/1900 [30:53<07:11,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1539/1900 [30:55<07:19,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1540/1900 [30:56<07:14,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1541/1900 [30:57<07:27,  1.25s/it]
+
+
Evaluating eval...:  81%|████████  | 1542/1900 [30:58<07:19,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1543/1900 [31:00<07:19,  1.23s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1544/1900 [31:01<07:11,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1545/1900 [31:02<07:04,  1.20s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1546/1900 [31:03<07:09,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1547/1900 [31:04<07:14,  1.23s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1548/1900 [31:06<07:08,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1549/1900 [31:07<07:02,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1550/1900 [31:08<07:06,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1551/1900 [31:09<07:03,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1552/1900 [31:10<06:56,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1553/1900 [31:12<06:56,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1554/1900 [31:13<06:56,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1555/1900 [31:14<06:53,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1556/1900 [31:15<07:06,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1557/1900 [31:17<06:58,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1558/1900 [31:18<07:03,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1559/1900 [31:19<07:03,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1560/1900 [31:20<06:53,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1561/1900 [31:21<06:53,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1562/1900 [31:23<06:57,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1563/1900 [31:24<06:53,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1564/1900 [31:25<06:45,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1565/1900 [31:26<06:43,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1566/1900 [31:28<06:46,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1567/1900 [31:29<06:43,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1568/1900 [31:30<06:50,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1569/1900 [31:31<06:50,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1570/1900 [31:32<06:45,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1571/1900 [31:34<06:39,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1572/1900 [31:35<06:40,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1573/1900 [31:36<06:33,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1574/1900 [31:37<06:30,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1575/1900 [31:38<06:31,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1576/1900 [31:40<06:26,  1.19s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1577/1900 [31:41<06:29,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1578/1900 [31:42<06:29,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1579/1900 [31:43<06:25,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1580/1900 [31:45<06:32,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1581/1900 [31:46<06:39,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1582/1900 [31:47<06:37,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1583/1900 [31:48<06:32,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1584/1900 [31:50<06:39,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1585/1900 [31:51<06:38,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1586/1900 [31:52<06:31,  1.25s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1587/1900 [31:53<06:20,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1588/1900 [31:54<06:12,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1589/1900 [31:56<06:12,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1590/1900 [31:57<06:15,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1591/1900 [31:58<06:18,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1592/1900 [31:59<06:12,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1593/1900 [32:01<06:13,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1594/1900 [32:02<06:13,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1595/1900 [32:03<06:13,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1596/1900 [32:04<06:15,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1597/1900 [32:05<06:14,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1598/1900 [32:07<06:05,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1599/1900 [32:08<05:58,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1600/1900 [32:09<05:54,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1601/1900 [32:10<05:52,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1602/1900 [32:11<05:53,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1603/1900 [32:12<05:52,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1604/1900 [32:14<05:55,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1605/1900 [32:15<05:48,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1606/1900 [32:16<05:49,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1607/1900 [32:17<05:50,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1608/1900 [32:18<05:50,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1609/1900 [32:20<05:53,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1610/1900 [32:21<05:48,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1611/1900 [32:22<05:42,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1612/1900 [32:23<05:39,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1613/1900 [32:24<05:34,  1.16s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1614/1900 [32:26<05:36,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1615/1900 [32:27<05:37,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1616/1900 [32:28<05:33,  1.17s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1617/1900 [32:29<05:37,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1618/1900 [32:30<05:39,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1619/1900 [32:32<05:39,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1620/1900 [32:33<05:37,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1621/1900 [32:34<05:33,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1622/1900 [32:35<05:27,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1623/1900 [32:36<05:26,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1624/1900 [32:37<05:22,  1.17s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1625/1900 [32:39<05:27,  1.19s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1626/1900 [32:40<05:28,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1627/1900 [32:41<05:29,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1628/1900 [32:42<05:28,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1629/1900 [32:43<05:25,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1630/1900 [32:45<05:24,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1631/1900 [32:46<05:32,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1632/1900 [32:47<05:27,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1633/1900 [32:48<05:23,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1634/1900 [32:50<05:19,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1635/1900 [32:51<05:15,  1.19s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1636/1900 [32:52<05:15,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1637/1900 [32:53<05:19,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1638/1900 [32:54<05:12,  1.19s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1639/1900 [32:56<05:15,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1640/1900 [32:57<05:15,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1641/1900 [32:58<05:10,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1642/1900 [32:59<05:10,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1643/1900 [33:00<05:06,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1644/1900 [33:01<04:59,  1.17s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1645/1900 [33:03<04:56,  1.16s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1646/1900 [33:04<04:58,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1647/1900 [33:05<04:59,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1648/1900 [33:06<05:01,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1649/1900 [33:07<04:59,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1650/1900 [33:09<05:00,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1651/1900 [33:10<04:54,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1652/1900 [33:11<04:53,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1653/1900 [33:12<04:52,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1654/1900 [33:13<04:52,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1655/1900 [33:15<04:54,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1656/1900 [33:16<04:54,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1657/1900 [33:17<04:55,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1658/1900 [33:18<04:52,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1659/1900 [33:20<05:00,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1660/1900 [33:21<04:56,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1661/1900 [33:22<04:56,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1662/1900 [33:23<04:50,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1663/1900 [33:24<04:45,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1664/1900 [33:26<04:48,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1665/1900 [33:27<04:46,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1666/1900 [33:28<04:58,  1.27s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1667/1900 [33:29<04:53,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1668/1900 [33:31<04:47,  1.24s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1669/1900 [33:32<04:42,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1670/1900 [33:33<04:42,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1671/1900 [33:34<04:41,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1672/1900 [33:36<04:39,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1673/1900 [33:37<04:44,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1674/1900 [33:38<04:42,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1675/1900 [33:39<04:37,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1676/1900 [33:40<04:32,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1677/1900 [33:42<04:27,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1678/1900 [33:43<04:23,  1.19s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1679/1900 [33:44<04:24,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1680/1900 [33:45<04:22,  1.19s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1681/1900 [33:46<04:23,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1682/1900 [33:48<04:20,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1683/1900 [33:49<04:22,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1684/1900 [33:50<04:20,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1685/1900 [33:51<04:15,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1686/1900 [33:52<04:15,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1687/1900 [33:54<04:17,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1688/1900 [33:55<04:16,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1689/1900 [33:56<04:13,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1690/1900 [33:57<04:11,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1691/1900 [33:58<04:12,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1692/1900 [34:00<04:08,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1693/1900 [34:01<04:11,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1694/1900 [34:02<04:11,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1695/1900 [34:03<04:09,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1696/1900 [34:05<04:06,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1697/1900 [34:06<04:09,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1698/1900 [34:07<04:09,  1.24s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1699/1900 [34:08<04:04,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1700/1900 [34:09<04:03,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1701/1900 [34:11<04:05,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1702/1900 [34:12<04:04,  1.24s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1703/1900 [34:13<04:02,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1704/1900 [34:14<03:56,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1705/1900 [34:15<03:51,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1706/1900 [34:17<03:52,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1707/1900 [34:18<03:49,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1708/1900 [34:19<03:50,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1709/1900 [34:20<03:49,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1710/1900 [34:22<03:48,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1711/1900 [34:23<03:45,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1712/1900 [34:24<03:43,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1713/1900 [34:25<03:39,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1714/1900 [34:26<03:37,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1715/1900 [34:27<03:38,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1716/1900 [34:28<03:35,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1717/1900 [34:30<03:43,  1.22s/it]
+
+
Evaluating eval...:  90%|█████████ | 1718/1900 [34:31<03:42,  1.22s/it]
+
+
Evaluating eval...:  90%|█████████ | 1719/1900 [34:32<03:39,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1720/1900 [34:33<03:40,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1721/1900 [34:35<03:36,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1722/1900 [34:36<03:36,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1723/1900 [34:37<03:32,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1724/1900 [34:38<03:35,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1725/1900 [34:40<03:34,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1726/1900 [34:41<03:32,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1727/1900 [34:42<03:35,  1.25s/it]
+
+
Evaluating eval...:  91%|█████████ | 1728/1900 [34:43<03:29,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1729/1900 [34:44<03:25,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1730/1900 [34:46<03:26,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1731/1900 [34:47<03:23,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1732/1900 [34:48<03:22,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1733/1900 [34:49<03:21,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1734/1900 [34:50<03:18,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1735/1900 [34:52<03:16,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1736/1900 [34:53<03:21,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1737/1900 [34:54<03:20,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1738/1900 [34:55<03:18,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1739/1900 [34:57<03:18,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1740/1900 [34:58<03:16,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1741/1900 [34:59<03:14,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1742/1900 [35:00<03:10,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1743/1900 [35:01<03:07,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1744/1900 [35:03<03:05,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1745/1900 [35:04<03:02,  1.18s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1746/1900 [35:05<03:06,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1747/1900 [35:06<03:04,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1748/1900 [35:07<03:04,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1749/1900 [35:09<03:05,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1750/1900 [35:10<03:04,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1751/1900 [35:11<03:02,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1752/1900 [35:12<02:59,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1753/1900 [35:13<02:55,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1754/1900 [35:15<02:55,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1755/1900 [35:16<02:56,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1756/1900 [35:17<02:54,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1757/1900 [35:18<02:58,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1758/1900 [35:20<02:54,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1759/1900 [35:21<02:50,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1760/1900 [35:22<02:46,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1761/1900 [35:23<02:45,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1762/1900 [35:24<02:44,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1763/1900 [35:26<02:42,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1764/1900 [35:27<02:45,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1765/1900 [35:28<02:46,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1766/1900 [35:29<02:43,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1767/1900 [35:30<02:41,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1768/1900 [35:32<02:40,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1769/1900 [35:33<02:40,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1770/1900 [35:34<02:41,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1771/1900 [35:35<02:38,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1772/1900 [35:37<02:35,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1773/1900 [35:38<02:34,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1774/1900 [35:39<02:31,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1775/1900 [35:40<02:31,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1776/1900 [35:41<02:28,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1777/1900 [35:43<02:27,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1778/1900 [35:44<02:25,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1779/1900 [35:45<02:21,  1.17s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1780/1900 [35:46<02:20,  1.17s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1781/1900 [35:47<02:18,  1.16s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1782/1900 [35:48<02:20,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1783/1900 [35:50<02:20,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1784/1900 [35:51<02:18,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1785/1900 [35:52<02:16,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1786/1900 [35:53<02:15,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1787/1900 [35:54<02:14,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1788/1900 [35:56<02:13,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1789/1900 [35:57<02:11,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1790/1900 [35:58<02:11,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1791/1900 [35:59<02:11,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1792/1900 [36:01<02:12,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1793/1900 [36:02<02:12,  1.24s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1794/1900 [36:03<02:08,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1795/1900 [36:04<02:06,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1796/1900 [36:05<02:03,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1797/1900 [36:06<02:03,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1798/1900 [36:08<02:04,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1799/1900 [36:09<02:01,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1800/1900 [36:10<01:59,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1801/1900 [36:11<01:57,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1802/1900 [36:12<01:56,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1803/1900 [36:14<01:56,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1804/1900 [36:15<01:53,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1805/1900 [36:16<01:51,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1806/1900 [36:17<01:51,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1807/1900 [36:18<01:49,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1808/1900 [36:20<01:48,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1809/1900 [36:21<01:46,  1.17s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1810/1900 [36:22<01:46,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1811/1900 [36:23<01:46,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1812/1900 [36:24<01:45,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1813/1900 [36:26<01:44,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1814/1900 [36:27<01:42,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1815/1900 [36:28<01:40,  1.18s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1816/1900 [36:29<01:39,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1817/1900 [36:30<01:41,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1818/1900 [36:32<01:39,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1819/1900 [36:33<01:37,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1820/1900 [36:34<01:36,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1821/1900 [36:35<01:36,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1822/1900 [36:36<01:34,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1823/1900 [36:38<01:32,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1824/1900 [36:39<01:31,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1825/1900 [36:40<01:30,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1826/1900 [36:41<01:29,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1827/1900 [36:42<01:28,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1828/1900 [36:44<01:27,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1829/1900 [36:45<01:28,  1.24s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1830/1900 [36:46<01:25,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1831/1900 [36:47<01:23,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1832/1900 [36:48<01:21,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1833/1900 [36:50<01:20,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1834/1900 [36:51<01:19,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1835/1900 [36:52<01:17,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1836/1900 [36:53<01:16,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1837/1900 [36:55<01:17,  1.23s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1838/1900 [36:56<01:15,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1839/1900 [36:57<01:13,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1840/1900 [36:58<01:13,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1841/1900 [36:59<01:11,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1842/1900 [37:01<01:10,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1843/1900 [37:02<01:08,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1844/1900 [37:03<01:07,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1845/1900 [37:04<01:06,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1846/1900 [37:05<01:05,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1847/1900 [37:07<01:04,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1848/1900 [37:08<01:03,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1849/1900 [37:09<01:02,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1850/1900 [37:10<01:00,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1851/1900 [37:11<00:58,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1852/1900 [37:13<00:57,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1853/1900 [37:14<00:56,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1854/1900 [37:15<00:54,  1.18s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1855/1900 [37:16<00:54,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1856/1900 [37:17<00:52,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1857/1900 [37:19<00:51,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1858/1900 [37:20<00:50,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1859/1900 [37:21<00:49,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1860/1900 [37:22<00:48,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1861/1900 [37:23<00:46,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1862/1900 [37:25<00:45,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1863/1900 [37:26<00:43,  1.18s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1864/1900 [37:27<00:42,  1.18s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1865/1900 [37:28<00:41,  1.18s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1866/1900 [37:29<00:40,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1867/1900 [37:31<00:39,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1868/1900 [37:32<00:38,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1869/1900 [37:33<00:37,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1870/1900 [37:34<00:35,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1871/1900 [37:36<00:35,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1872/1900 [37:37<00:34,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1873/1900 [37:38<00:33,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1874/1900 [37:39<00:31,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1875/1900 [37:40<00:30,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1876/1900 [37:42<00:29,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1877/1900 [37:43<00:27,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1878/1900 [37:44<00:26,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1879/1900 [37:45<00:25,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1880/1900 [37:46<00:23,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1881/1900 [37:47<00:22,  1.18s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1882/1900 [37:49<00:21,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1883/1900 [37:50<00:20,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1884/1900 [37:51<00:19,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1885/1900 [37:52<00:18,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1886/1900 [37:54<00:16,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1887/1900 [37:55<00:15,  1.18s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1888/1900 [37:56<00:14,  1.18s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1889/1900 [37:57<00:12,  1.18s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1890/1900 [37:58<00:11,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1891/1900 [37:59<00:10,  1.16s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1892/1900 [38:01<00:09,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1893/1900 [38:02<00:08,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1894/1900 [38:03<00:06,  1.16s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1895/1900 [38:04<00:05,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1896/1900 [38:05<00:04,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1897/1900 [38:06<00:03,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1898/1900 [38:08<00:02,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1899/1900 [38:09<00:01,  1.17s/it]
+
+
Evaluating eval...: 100%|██████████| 1900/1900 [38:10<00:00,  1.29s/it]
Evaluating eval...: 100%|██████████| 1900/1900 [38:10<00:00,  1.21s/it]
+Eval results for step (40000 / 100000 | Eval Loss: 1.0607950687408447 | Eval wer: 26.800018211082516 | Eval wer_ortho: 30.123852128389977 |)
+
                                                                             
Eval results for step (40000 / 100000 | Eval Loss: 1.0607950687408447 | Eval wer: 26.800018211082516 | Eval wer_ortho: 30.123852128389977 |)
+
Train steps ... :  40%|████      | 40000/100000 [12:14:23<9:44:43,  1.71it/s]
Train steps ... :  40%|████      | 40001/100000 [12:14:23<12621:02:42, 757.28s/it]
Train steps ... :  40%|████      | 40002/100000 [12:14:23<8837:30:12, 530.27s/it] 
Train steps ... :  40%|████      | 40003/100000 [12:14:24<6189:04:39, 371.36s/it]
Train steps ... :  40%|████      | 40004/100000 [12:14:25<4335:12:08, 260.13s/it]
Train steps ... :  40%|████      | 40005/100000 [12:14:25<3037:30:09, 182.27s/it]
Train steps ... :  40%|████      | 40006/100000 [12:14:26<2129:08:01, 127.76s/it]
Train steps ... :  40%|████      | 40007/100000 [12:14:26<1493:17:13, 89.61s/it] 
Train steps ... :  40%|████      | 40008/100000 [12:14:27<1048:12:00, 62.90s/it]
Train steps ... :  40%|████      | 40009/100000 [12:14:27<736:38:52, 44.21s/it] 
Train steps ... :  40%|████      | 40010/100000 [12:14:28<518:33:25, 31.12s/it]
Train steps ... :  40%|████      | 40011/100000 [12:14:29<365:54:23, 21.96s/it]
Train steps ... :  40%|████      | 40012/100000 [12:14:29<259:03:31, 15.55s/it]
Train steps ... :  40%|████      | 40013/100000 [12:14:30<184:15:31, 11.06s/it]
Train steps ... :  40%|████      | 40014/100000 [12:14:30<131:53:41,  7.92s/it]
Train steps ... :  40%|████      | 40015/100000 [12:14:31<95:14:31,  5.72s/it] 
Train steps ... :  40%|████      | 40016/100000 [12:14:32<69:35:24,  4.18s/it]
Train steps ... :  40%|████      | 40017/100000 [12:14:32<51:37:28,  3.10s/it]
Train steps ... :  40%|████      | 40018/100000 [12:14:33<39:03:52,  2.34s/it]
Train steps ... :  40%|████      | 40019/100000 [12:14:33<30:15:13,  1.82s/it]
Train steps ... :  40%|████      | 40020/100000 [12:14:34<24:05:49,  1.45s/it]
Train steps ... :  40%|████      | 40021/100000 [12:14:34<19:46:53,  1.19s/it]
Train steps ... :  40%|████      | 40022/100000 [12:14:35<16:45:54,  1.01s/it]
Train steps ... :  40%|████      | 40023/100000 [12:14:36<14:38:47,  1.14it/s]
Train steps ... :  40%|████      | 40024/100000 [12:14:36<13:12:02,  1.26it/s]
Train steps ... :  40%|████      | 40025/100000 [12:14:37<12:10:18,  1.37it/s]Step... (40025 / 100000 | Loss: 0.9765567779541016, Learning Rate: 6.027638190954774e-05)
+
                                                                              
Step... (40025 / 100000 | Loss: 0.7904983758926392, Learning Rate: 6.027638190954774e-05)
+
Train steps ... :  40%|████      | 40025/100000 [12:14:37<12:10:18,  1.37it/s]
Train steps ... :  40%|████      | 40026/100000 [12:14:37<11:25:16,  1.46it/s]
Train steps ... :  40%|████      | 40027/100000 [12:14:38<10:54:24,  1.53it/s]
Train steps ... :  40%|████      | 40028/100000 [12:14:39<10:33:31,  1.58it/s]
Train steps ... :  40%|████      | 40029/100000 [12:14:39<10:19:16,  1.61it/s]
Train steps ... :  40%|████      | 40030/100000 [12:14:40<10:09:46,  1.64it/s]
Train steps ... :  40%|████      | 40031/100000 [12:14:40<10:01:51,  1.66it/s]
Train steps ... :  40%|████      | 40032/100000 [12:14:41<9:56:15,  1.68it/s] 
Train steps ... :  40%|████      | 40033/100000 [12:14:41<9:52:43,  1.69it/s]
Train steps ... :  40%|████      | 40034/100000 [12:14:42<9:50:00,  1.69it/s]
Train steps ... :  40%|████      | 40035/100000 [12:14:43<9:47:50,  1.70it/s]
Train steps ... :  40%|████      | 40036/100000 [12:14:43<9:47:02,  1.70it/s]
Train steps ... :  40%|████      | 40037/100000 [12:14:44<9:45:34,  1.71it/s]
Train steps ... :  40%|████      | 40038/100000 [12:14:44<9:44:40,  1.71it/s]
Train steps ... :  40%|████      | 40039/100000 [12:14:45<9:44:04,  1.71it/s]
Train steps ... :  40%|████      | 40040/100000 [12:14:46<9:43:41,  1.71it/s]
Train steps ... :  40%|████      | 40041/100000 [12:14:46<9:43:31,  1.71it/s]
Train steps ... :  40%|████      | 40042/100000 [12:14:47<9:43:19,  1.71it/s]
Train steps ... :  40%|████      | 40043/100000 [12:14:47<9:42:46,  1.71it/s]
Train steps ... :  40%|████      | 40044/100000 [12:14:48<9:43:17,  1.71it/s]
Train steps ... :  40%|████      | 40045/100000 [12:14:48<9:43:22,  1.71it/s]
Train steps ... :  40%|████      | 40046/100000 [12:14:49<9:43:20,  1.71it/s]
Train steps ... :  40%|████      | 40047/100000 [12:14:50<9:43:21,  1.71it/s]
Train steps ... :  40%|████      | 40048/100000 [12:14:50<9:43:48,  1.71it/s]
Train steps ... :  40%|████      | 40049/100000 [12:14:51<9:43:12,  1.71it/s]
Train steps ... :  40%|████      | 40050/100000 [12:14:51<9:43:12,  1.71it/s]Step... (40050 / 100000 | Loss: 1.1584501266479492, Learning Rate: 6.025125628140704e-05)
+
                                                                             
Step... (40050 / 100000 | Loss: 1.0287508964538574, Learning Rate: 6.025125628140704e-05)
+
Train steps ... :  40%|████      | 40050/100000 [12:14:52<9:43:12,  1.71it/s]
Train steps ... :  40%|████      | 40051/100000 [12:14:52<9:44:04,  1.71it/s]
Train steps ... :  40%|████      | 40052/100000 [12:14:53<9:44:06,  1.71it/s]
Train steps ... :  40%|████      | 40053/100000 [12:14:53<9:43:18,  1.71it/s]
Train steps ... :  40%|████      | 40054/100000 [12:14:54<9:43:29,  1.71it/s]
Train steps ... :  40%|████      | 40055/100000 [12:14:54<9:42:48,  1.71it/s]
Train steps ... :  40%|████      | 40056/100000 [12:14:55<9:42:37,  1.71it/s]
Train steps ... :  40%|████      | 40057/100000 [12:14:56<9:43:01,  1.71it/s]
Train steps ... :  40%|████      | 40058/100000 [12:14:56<9:42:36,  1.71it/s]
Train steps ... :  40%|████      | 40059/100000 [12:14:57<9:42:32,  1.71it/s]
Train steps ... :  40%|████      | 40060/100000 [12:14:57<9:42:21,  1.72it/s]
Train steps ... :  40%|████      | 40061/100000 [12:14:58<9:43:01,  1.71it/s]
Train steps ... :  40%|████      | 40062/100000 [12:14:58<9:43:09,  1.71it/s]
Train steps ... :  40%|████      | 40063/100000 [12:14:59<9:42:44,  1.71it/s]
Train steps ... :  40%|████      | 40064/100000 [12:15:00<9:42:40,  1.71it/s]
Train steps ... :  40%|████      | 40065/100000 [12:15:00<9:43:20,  1.71it/s]
Train steps ... :  40%|████      | 40066/100000 [12:15:01<9:43:25,  1.71it/s]
Train steps ... :  40%|████      | 40067/100000 [12:15:01<9:43:59,  1.71it/s]
Train steps ... :  40%|████      | 40068/100000 [12:15:02<9:43:38,  1.71it/s]
Train steps ... :  40%|████      | 40069/100000 [12:15:03<9:43:37,  1.71it/s]
Train steps ... :  40%|████      | 40070/100000 [12:15:03<9:43:45,  1.71it/s]
Train steps ... :  40%|████      | 40071/100000 [12:15:04<9:43:18,  1.71it/s]
Train steps ... :  40%|████      | 40072/100000 [12:15:04<9:42:53,  1.71it/s]
Train steps ... :  40%|████      | 40073/100000 [12:15:05<9:42:33,  1.71it/s]
Train steps ... :  40%|████      | 40074/100000 [12:15:05<9:42:32,  1.71it/s]
Train steps ... :  40%|████      | 40075/100000 [12:15:06<9:44:08,  1.71it/s]Step... (40075 / 100000 | Loss: 0.8795410394668579, Learning Rate: 6.022613065326633e-05)
+
                                                                             
Step... (40075 / 100000 | Loss: 0.7284708023071289, Learning Rate: 6.022613065326633e-05)
+
Train steps ... :  40%|████      | 40075/100000 [12:15:06<9:44:08,  1.71it/s]
Train steps ... :  40%|████      | 40076/100000 [12:15:07<9:44:22,  1.71it/s]
Train steps ... :  40%|████      | 40077/100000 [12:15:07<9:44:49,  1.71it/s]
Train steps ... :  40%|████      | 40078/100000 [12:15:08<9:45:43,  1.71it/s]
Train steps ... :  40%|████      | 40079/100000 [12:15:08<9:44:32,  1.71it/s]
Train steps ... :  40%|████      | 40080/100000 [12:15:09<9:43:27,  1.71it/s]
Train steps ... :  40%|████      | 40081/100000 [12:15:10<9:42:56,  1.71it/s]
Train steps ... :  40%|████      | 40082/100000 [12:15:10<9:43:47,  1.71it/s]
Train steps ... :  40%|██���█      | 40083/100000 [12:15:11<9:43:39,  1.71it/s]
Train steps ... :  40%|████      | 40084/100000 [12:15:11<9:43:49,  1.71it/s]
Train steps ... :  40%|████      | 40085/100000 [12:15:12<9:43:58,  1.71it/s]
Train steps ... :  40%|████      | 40086/100000 [12:15:12<9:43:50,  1.71it/s]
Train steps ... :  40%|████      | 40087/100000 [12:15:13<9:44:12,  1.71it/s]
Train steps ... :  40%|████      | 40088/100000 [12:15:14<9:45:49,  1.70it/s]
Train steps ... :  40%|████      | 40089/100000 [12:15:14<9:43:14,  1.71it/s]
Train steps ... :  40%|████      | 40090/100000 [12:15:15<9:43:40,  1.71it/s]
Train steps ... :  40%|████      | 40091/100000 [12:15:15<9:43:50,  1.71it/s]
Train steps ... :  40%|████      | 40092/100000 [12:15:16<9:42:53,  1.71it/s]
Train steps ... :  40%|████      | 40093/100000 [12:15:17<9:42:33,  1.71it/s]
Train steps ... :  40%|████      | 40094/100000 [12:15:17<9:42:27,  1.71it/s]
Train steps ... :  40%|████      | 40095/100000 [12:15:18<9:42:12,  1.71it/s]
Train steps ... :  40%|████      | 40096/100000 [12:15:18<9:42:45,  1.71it/s]
Train steps ... :  40%|████      | 40097/100000 [12:15:19<9:43:01,  1.71it/s]
Train steps ... :  40%|████      | 40098/100000 [12:15:19<9:42:54,  1.71it/s]
Train steps ... :  40%|████      | 40099/100000 [12:15:20<9:43:07,  1.71it/s]
Train steps ... :  40%|████      | 40100/100000 [12:15:21<9:43:07,  1.71it/s]Step... (40100 / 100000 | Loss: 1.1629191637039185, Learning Rate: 6.0201005025125635e-05)
+
                                                                             
Step... (40100 / 100000 | Loss: 1.509408950805664, Learning Rate: 6.0201005025125635e-05)
+
Train steps ... :  40%|████      | 40100/100000 [12:15:21<9:43:07,  1.71it/s]
Train steps ... :  40%|████      | 40101/100000 [12:15:21<9:43:37,  1.71it/s]
Train steps ... :  40%|████      | 40102/100000 [12:15:22<9:43:37,  1.71it/s]
Train steps ... :  40%|████      | 40103/100000 [12:15:22<9:43:03,  1.71it/s]
Train steps ... :  40%|████      | 40104/100000 [12:15:23<9:43:01,  1.71it/s]
Train steps ... :  40%|████      | 40105/100000 [12:15:24<9:43:58,  1.71it/s]
Train steps ... :  40%|████      | 40106/100000 [12:15:24<9:43:27,  1.71it/s]
Train steps ... :  40%|████      | 40107/100000 [12:15:25<9:43:31,  1.71it/s]
Train steps ... :  40%|████      | 40108/100000 [12:15:25<9:42:43,  1.71it/s]
Train steps ... :  40%|████      | 40109/100000 [12:15:26<9:42:52,  1.71it/s]
Train steps ... :  40%|████      | 40110/100000 [12:15:26<9:42:34,  1.71it/s]
Train steps ... :  40%|████      | 40111/100000 [12:15:27<9:43:01,  1.71it/s]
Train steps ... :  40%|████      | 40112/100000 [12:15:28<9:43:09,  1.71it/s]
Train steps ... :  40%|████      | 40113/100000 [12:15:28<9:43:31,  1.71it/s]
Train steps ... :  40%|████      | 40114/100000 [12:15:29<9:43:02,  1.71it/s]
Train steps ... :  40%|████      | 40115/100000 [12:15:29<9:43:14,  1.71it/s]
Train steps ... :  40%|████      | 40116/100000 [12:15:30<9:42:38,  1.71it/s]
Train steps ... :  40%|████      | 40117/100000 [12:15:31<9:42:22,  1.71it/s]
Train steps ... :  40%|████      | 40118/100000 [12:15:31<9:42:36,  1.71it/s]
Train steps ... :  40%|████      | 40119/100000 [12:15:32<9:42:24,  1.71it/s]
Train steps ... :  40%|████      | 40120/100000 [12:15:32<9:42:19,  1.71it/s]
Train steps ... :  40%|████      | 40121/100000 [12:15:33<9:42:04,  1.71it/s]
Train steps ... :  40%|████      | 40122/100000 [12:15:33<9:42:36,  1.71it/s]
Train steps ... :  40%|████      | 40123/100000 [12:15:34<9:42:30,  1.71it/s]
Train steps ... :  40%|████      | 40124/100000 [12:15:35<9:41:53,  1.71it/s]
Train steps ... :  40%|████      | 40125/100000 [12:15:35<9:41:52,  1.71it/s]Step... (40125 / 100000 | Loss: 0.841076135635376, Learning Rate: 6.0175879396984925e-05)
+
                                                                             
Step... (40125 / 100000 | Loss: 0.9902659058570862, Learning Rate: 6.0175879396984925e-05)
+
Train steps ... :  40%|████      | 40125/100000 [12:15:36<9:41:52,  1.71it/s]
Train steps ... :  40%|████      | 40126/100000 [12:15:36<9:42:02,  1.71it/s]
Train steps ... :  40%|████      | 40127/100000 [12:15:36<9:42:38,  1.71it/s]
Train steps ... :  40%|████      | 40128/100000 [12:15:37<9:42:31,  1.71it/s]
Train steps ... :  40%|████      | 40129/100000 [12:15:38<9:43:18,  1.71it/s]
Train steps ... :  40%|████      | 40130/100000 [12:15:38<9:43:35,  1.71it/s]
Train steps ... :  40%|████      | 40131/100000 [12:15:39<9:42:41,  1.71it/s]
Train steps ... :  40%|████      | 40132/100000 [12:15:39<9:43:45,  1.71it/s]
Train steps ... :  40%|████      | 40133/100000 [12:15:40<9:44:01,  1.71it/s]
Train steps ... :  40%|████      | 40134/100000 [12:15:40<9:43:04,  1.71it/s]
Train steps ... :  40%|████      | 40135/100000 [12:15:41<9:43:18,  1.71it/s]
Train steps ... :  40%|████      | 40136/100000 [12:15:42<9:42:43,  1.71it/s]
Train steps ... :  40%|████      | 40137/100000 [12:15:42<9:42:44,  1.71it/s]
Train steps ... :  40%|████      | 40138/100000 [12:15:43<9:42:36,  1.71it/s]
Train steps ... :  40%|████      | 40139/100000 [12:15:43<9:42:40,  1.71it/s]
Train steps ... :  40%|████      | 40140/100000 [12:15:44<9:42:33,  1.71it/s]
Train steps ... :  40%|████      | 40141/100000 [12:15:45<9:43:15,  1.71it/s]
Train steps ... :  40%|████      | 40142/100000 [12:15:45<9:42:58,  1.71it/s]
Train steps ... :  40%|████      | 40143/100000 [12:15:46<9:43:07,  1.71it/s]
Train steps ... :  40%|████      | 40144/100000 [12:15:46<9:42:36,  1.71it/s]
Train steps ... :  40%|████      | 40145/100000 [12:15:47<9:43:15,  1.71it/s]
Train steps ... :  40%|████      | 40146/100000 [12:15:47<9:43:51,  1.71it/s]
Train steps ... :  40%|████      | 40147/100000 [12:15:48<9:43:54,  1.71it/s]
Train steps ... :  40%|████      | 40148/100000 [12:15:49<9:43:23,  1.71it/s]
Train steps ... :  40%|████      | 40149/100000 [12:15:49<9:43:53,  1.71it/s]
Train steps ... :  40%|████      | 40150/100000 [12:15:50<9:43:23,  1.71it/s]Step... (40150 / 100000 | Loss: 0.7332507371902466, Learning Rate: 6.015075376884423e-05)
+
                                                                             
Step... (40150 / 100000 | Loss: 1.0075725317001343, Learning Rate: 6.015075376884423e-05)
+
Train steps ... :  40%|████      | 40150/100000 [12:15:50<9:43:23,  1.71it/s]
Train steps ... :  40%|████      | 40151/100000 [12:15:50<9:43:41,  1.71it/s]
Train steps ... :  40%|████      | 40152/100000 [12:15:51<9:43:48,  1.71it/s]
Train steps ... :  40%|████      | 40153/100000 [12:15:52<9:43:43,  1.71it/s]
Train steps ... :  40%|████      | 40154/100000 [12:15:52<9:43:34,  1.71it/s]
Train steps ... :  40%|████      | 40155/100000 [12:15:53<9:42:43,  1.71it/s]
Train steps ... :  40%|████      | 40156/100000 [12:15:53<9:42:13,  1.71it/s]
Train steps ... :  40%|████      | 40157/100000 [12:15:54<9:42:26,  1.71it/s]
Train steps ... :  40%|████      | 40158/100000 [12:15:55<9:42:09,  1.71it/s]
Train steps ... :  40%|████      | 40159/100000 [12:15:55<9:43:01,  1.71it/s]
Train steps ... :  40%|████      | 40160/100000 [12:15:56<9:45:02,  1.70it/s]
Train steps ... :  40%|████      | 40161/100000 [12:15:56<9:43:58,  1.71it/s]
Train steps ... :  40%|████      | 40162/100000 [12:15:57<9:42:22,  1.71it/s]
Train steps ... :  40%|████      | 40163/100000 [12:15:57<9:42:51,  1.71it/s]
Train steps ... :  40%|████      | 40164/100000 [12:15:58<9:42:05,  1.71it/s]
Train steps ... :  40%|████      | 40165/100000 [12:15:59<9:42:08,  1.71it/s]
Train steps ... :  40%|████      | 40166/100000 [12:15:59<9:43:01,  1.71it/s]
Train steps ... :  40%|████      | 40167/100000 [12:16:00<9:42:19,  1.71it/s]
Train steps ... :  40%|████      | 40168/100000 [12:16:00<9:41:55,  1.71it/s]
Train steps ... :  40%|████      | 40169/100000 [12:16:01<9:41:44,  1.71it/s]
Train steps ... :  40%|████      | 40170/100000 [12:16:02<9:41:54,  1.71it/s]
Train steps ... :  40%|████      | 40171/100000 [12:16:02<9:41:39,  1.71it/s]
Train steps ... :  40%|████      | 40172/100000 [12:16:03<9:41:54,  1.71it/s]
Train steps ... :  40%|████      | 40173/100000 [12:16:03<9:42:38,  1.71it/s]
Train steps ... :  40%|████      | 40174/100000 [12:16:04<9:42:29,  1.71it/s]
Train steps ... :  40%|████      | 40175/100000 [12:16:04<9:42:52,  1.71it/s]Step... (40175 / 100000 | Loss: 0.5870554447174072, Learning Rate: 6.012562814070352e-05)
+
                                                                             
Step... (40175 / 100000 | Loss: 1.592329740524292, Learning Rate: 6.012562814070352e-05)
+
Train steps ... :  40%|████      | 40175/100000 [12:16:05<9:42:52,  1.71it/s]
Train steps ... :  40%|████      | 40176/100000 [12:16:05<9:42:46,  1.71it/s]
Train steps ... :  40%|████      | 40177/100000 [12:16:06<9:42:13,  1.71it/s]
Train steps ... :  40%|████      | 40178/100000 [12:16:06<9:43:16,  1.71it/s]
Train steps ... :  40%|████      | 40179/100000 [12:16:07<9:42:50,  1.71it/s]
Train steps ... :  40%|████      | 40180/100000 [12:16:07<9:42:43,  1.71it/s]
Train steps ... :  40%|████      | 40181/100000 [12:16:08<9:41:52,  1.71it/s]
Train steps ... :  40%|████      | 40182/100000 [12:16:09<9:41:29,  1.71it/s]
Train steps ... :  40%|████      | 40183/100000 [12:16:09<9:42:31,  1.71it/s]
Train steps ... :  40%|████      | 40184/100000 [12:16:10<9:42:10,  1.71it/s]
Train steps ... :  40%|████      | 40185/100000 [12:16:10<9:42:39,  1.71it/s]
Train steps ... :  40%|████      | 40186/100000 [12:16:11<9:43:13,  1.71it/s]
Train steps ... :  40%|████      | 40187/100000 [12:16:11<9:43:20,  1.71it/s]
Train steps ... :  40%|████      | 40188/100000 [12:16:12<9:43:23,  1.71it/s]
Train steps ... :  40%|████      | 40189/100000 [12:16:13<9:44:08,  1.71it/s]
Train steps ... :  40%|████      | 40190/100000 [12:16:13<9:43:05,  1.71it/s]
Train steps ... :  40%|████      | 40191/100000 [12:16:14<9:42:19,  1.71it/s]
Train steps ... :  40%|████      | 40192/100000 [12:16:14<9:43:09,  1.71it/s]
Train steps ... :  40%|████      | 40193/100000 [12:16:15<9:42:06,  1.71it/s]
Train steps ... :  40%|████      | 40194/100000 [12:16:16<9:42:44,  1.71it/s]
Train steps ... :  40%|████      | 40195/100000 [12:16:16<9:42:57,  1.71it/s]
Train steps ... :  40%|████      | 40196/100000 [12:16:17<9:43:43,  1.71it/s]
Train steps ... :  40%|████      | 40197/100000 [12:16:17<9:42:41,  1.71it/s]
Train steps ... :  40%|████      | 40198/100000 [12:16:18<9:41:59,  1.71it/s]
Train steps ... :  40%|████      | 40199/100000 [12:16:18<9:42:08,  1.71it/s]
Train steps ... :  40%|████      | 40200/100000 [12:16:19<9:41:40,  1.71it/s]Step... (40200 / 100000 | Loss: 1.1781991720199585, Learning Rate: 6.0100502512562815e-05)
+
                                                                             
Step... (40200 / 100000 | Loss: 0.904681921005249, Learning Rate: 6.0100502512562815e-05)
+
Train steps ... :  40%|████      | 40200/100000 [12:16:19<9:41:40,  1.71it/s]
Train steps ... :  40%|████      | 40201/100000 [12:16:20<9:42:28,  1.71it/s]
Train steps ... :  40%|████      | 40202/100000 [12:16:20<9:41:46,  1.71it/s]
Train steps ... :  40%|████      | 40203/100000 [12:16:21<9:41:49,  1.71it/s]
Train steps ... :  40%|████      | 40204/100000 [12:16:21<9:42:52,  1.71it/s]
Train steps ... :  40%|████      | 40205/100000 [12:16:22<9:41:56,  1.71it/s]
Train steps ... :  40%|████      | 40206/100000 [12:16:23<9:42:12,  1.71it/s]
Train steps ... :  40%|████      | 40207/100000 [12:16:23<9:42:56,  1.71it/s]
Train steps ... :  40%|████      | 40208/100000 [12:16:24<9:42:47,  1.71it/s]
Train steps ... :  40%|████      | 40209/100000 [12:16:24<9:42:16,  1.71it/s]
Train steps ... :  40%|████      | 40210/100000 [12:16:25<9:42:20,  1.71it/s]
Train steps ... :  40%|████      | 40211/100000 [12:16:25<9:42:12,  1.71it/s]
Train steps ... :  40%|████      | 40212/100000 [12:16:26<9:41:07,  1.71it/s]
Train steps ... :  40%|████      | 40213/100000 [12:16:27<9:41:12,  1.71it/s]
Train steps ... :  40%|████      | 40214/100000 [12:16:27<9:41:10,  1.71it/s]
Train steps ... :  40%|████      | 40215/100000 [12:16:28<9:41:29,  1.71it/s]
Train steps ... :  40%|████      | 40216/100000 [12:16:28<9:42:00,  1.71it/s]
Train steps ... :  40%|████      | 40217/100000 [12:16:29<9:40:53,  1.72it/s]
Train steps ... :  40%|████      | 40218/100000 [12:16:30<9:41:32,  1.71it/s]
Train steps ... :  40%|████      | 40219/100000 [12:16:30<9:41:36,  1.71it/s]
Train steps ... :  40%|████      | 40220/100000 [12:16:31<9:41:36,  1.71it/s]
Train steps ... :  40%|████      | 40221/100000 [12:16:31<9:42:43,  1.71it/s]
Train steps ... :  40%|████      | 40222/100000 [12:16:32<9:41:19,  1.71it/s]
Train steps ... :  40%|████      | 40223/100000 [12:16:32<9:41:26,  1.71it/s]
Train steps ... :  40%|████      | 40224/100000 [12:16:33<9:41:17,  1.71it/s]
Train steps ... :  40%|████      | 40225/100000 [12:16:34<9:42:34,  1.71it/s]Step... (40225 / 100000 | Loss: 0.8048956394195557, Learning Rate: 6.007537688442212e-05)
+
                                                                             
Step... (40225 / 100000 | Loss: 0.6737524271011353, Learning Rate: 6.007537688442212e-05)
+
Train steps ... :  40%|████      | 40225/100000 [12:16:34<9:42:34,  1.71it/s]
Train steps ... :  40%|████      | 40226/100000 [12:16:34<9:42:28,  1.71it/s]
Train steps ... :  40%|████      | 40227/100000 [12:16:35<9:41:31,  1.71it/s]
Train steps ... :  40%|████      | 40228/100000 [12:16:35<9:42:24,  1.71it/s]
Train steps ... :  40%|████      | 40229/100000 [12:16:36<9:41:45,  1.71it/s]
Train steps ... :  40%|████      | 40230/100000 [12:16:37<9:41:38,  1.71it/s]
Train steps ... :  40%|████      | 40231/100000 [12:16:37<9:41:09,  1.71it/s]
Train steps ... :  40%|████      | 40232/100000 [12:16:38<9:40:24,  1.72it/s]
Train steps ... :  40%|████      | 40233/100000 [12:16:38<9:40:58,  1.71it/s]
Train steps ... :  40%|████      | 40234/100000 [12:16:39<9:40:57,  1.71it/s]
Train steps ... :  40%|████      | 40235/100000 [12:16:39<9:42:40,  1.71it/s]
Train steps ... :  40%|████      | 40236/100000 [12:16:40<9:41:48,  1.71it/s]
Train steps ... :  40%|████      | 40237/100000 [12:16:41<9:41:35,  1.71it/s]
Train steps ... :  40%|████      | 40238/100000 [12:16:41<9:42:42,  1.71it/s]
Train steps ... :  40%|████      | 40239/100000 [12:16:42<9:42:34,  1.71it/s]
Train steps ... :  40%|████      | 40240/100000 [12:16:42<9:42:02,  1.71it/s]
Train steps ... :  40%|████      | 40241/100000 [12:16:43<9:42:53,  1.71it/s]
Train steps ... :  40%|████      | 40242/100000 [12:16:44<9:42:04,  1.71it/s]
Train steps ... :  40%|████      | 40243/100000 [12:16:44<9:42:20,  1.71it/s]
Train steps ... :  40%|████      | 40244/100000 [12:16:45<9:42:54,  1.71it/s]
Train steps ... :  40%|████      | 40245/100000 [12:16:45<9:44:18,  1.70it/s]
Train steps ... :  40%|████      | 40246/100000 [12:16:46<9:42:36,  1.71it/s]
Train steps ... :  40%|████      | 40247/100000 [12:16:47<9:41:58,  1.71it/s]
Train steps ... :  40%|████      | 40248/100000 [12:16:47<9:42:59,  1.71it/s]
Train steps ... :  40%|████      | 40249/100000 [12:16:48<9:42:19,  1.71it/s]
Train steps ... :  40%|████      | 40250/100000 [12:16:48<9:41:39,  1.71it/s]Step... (40250 / 100000 | Loss: 0.7901502251625061, Learning Rate: 6.005025125628141e-05)
+
                                                                             
Step... (40250 / 100000 | Loss: 1.0662109851837158, Learning Rate: 6.005025125628141e-05)
+
Train steps ... :  40%|████      | 40250/100000 [12:16:49<9:41:39,  1.71it/s]
Train steps ... :  40%|████      | 40251/100000 [12:16:49<9:42:37,  1.71it/s]
Train steps ... :  40%|████      | 40252/100000 [12:16:49<9:42:14,  1.71it/s]
Train steps ... :  40%|████      | 40253/100000 [12:16:50<9:41:47,  1.71it/s]
Train steps ... :  40%|████      | 40254/100000 [12:16:51<9:43:37,  1.71it/s]
Train steps ... :  40%|████      | 40255/100000 [12:16:51<9:41:38,  1.71it/s]
Train steps ... :  40%|████      | 40256/100000 [12:16:52<9:42:15,  1.71it/s]
Train steps ... :  40%|████      | 40257/100000 [12:16:52<9:42:44,  1.71it/s]
Train steps ... :  40%|████      | 40258/100000 [12:16:53<9:42:03,  1.71it/s]
Train steps ... :  40%|████      | 40259/100000 [12:16:54<9:43:04,  1.71it/s]
Train steps ... :  40%|████      | 40260/100000 [12:16:54<9:41:07,  1.71it/s]
Train steps ... :  40%|████      | 40261/100000 [12:16:55<9:41:16,  1.71it/s]
Train steps ... :  40%|████      | 40262/100000 [12:16:55<9:42:24,  1.71it/s]
Train steps ... :  40%|████      | 40263/100000 [12:16:56<9:42:01,  1.71it/s]
Train steps ... :  40%|████      | 40264/100000 [12:16:56<9:44:10,  1.70it/s]
Train steps ... :  40%|████      | 40265/100000 [12:16:57<9:41:45,  1.71it/s]
Train steps ... :  40%|████      | 40266/100000 [12:16:58<9:41:18,  1.71it/s]
Train steps ... :  40%|████      | 40267/100000 [12:16:58<9:40:56,  1.71it/s]
Train steps ... :  40%|████      | 40268/100000 [12:16:59<9:41:00,  1.71it/s]
Train steps ... :  40%|████      | 40269/100000 [12:16:59<9:41:29,  1.71it/s]
Train steps ... :  40%|████      | 40270/100000 [12:17:00<9:41:13,  1.71it/s]
Train steps ... :  40%|████      | 40271/100000 [12:17:01<9:42:28,  1.71it/s]
Train steps ... :  40%|████      | 40272/100000 [12:17:01<9:41:51,  1.71it/s]
Train steps ... :  40%|████      | 40273/100000 [12:17:02<9:41:00,  1.71it/s]
Train steps ... :  40%|████      | 40274/100000 [12:17:02<9:40:44,  1.71it/s]
Train steps ... :  40%|████      | 40275/100000 [12:17:03<9:40:34,  1.71it/s]Step... (40275 / 100000 | Loss: 0.6827285289764404, Learning Rate: 6.002512562814071e-05)
+
                                                                             
Step... (40275 / 100000 | Loss: 1.4302093982696533, Learning Rate: 6.002512562814071e-05)
+
Train steps ... :  40%|████      | 40275/100000 [12:17:03<9:40:34,  1.71it/s]
Train steps ... :  40%|████      | 40276/100000 [12:17:03<9:40:44,  1.71it/s]
Train steps ... :  40%|████      | 40277/100000 [12:17:04<9:40:26,  1.71it/s]
Train steps ... :  40%|████      | 40278/100000 [12:17:05<9:40:19,  1.72it/s]
Train steps ... :  40%|████      | 40279/100000 [12:17:05<9:41:15,  1.71it/s]
Train steps ... :  40%|████      | 40280/100000 [12:17:06<9:41:35,  1.71it/s]
Train steps ... :  40%|████      | 40281/100000 [12:17:06<9:41:01,  1.71it/s]
Train steps ... :  40%|████      | 40282/100000 [12:17:07<9:40:25,  1.71it/s]
Train steps ... :  40%|████      | 40283/100000 [12:17:08<9:40:10,  1.72it/s]
Train steps ... :  40%|████      | 40284/100000 [12:17:08<9:41:00,  1.71it/s]
Train steps ... :  40%|████      | 40285/100000 [12:17:09<9:40:52,  1.71it/s]
Train steps ... :  40%|████      | 40286/100000 [12:17:09<9:40:12,  1.72it/s]
Train steps ... :  40%|████      | 40287/100000 [12:17:10<9:40:18,  1.71it/s]
Train steps ... :  40%|████      | 40288/100000 [12:17:10<9:40:11,  1.72it/s]
Train steps ... :  40%|████      | 40289/100000 [12:17:11<9:40:40,  1.71it/s]
Train steps ... :  40%|████      | 40290/100000 [12:17:12<9:40:14,  1.72it/s]
Train steps ... :  40%|████      | 40291/100000 [12:17:12<9:39:53,  1.72it/s]
Train steps ... :  40%|████      | 40292/100000 [12:17:13<9:40:53,  1.71it/s]
Train steps ... :  40%|████      | 40293/100000 [12:17:13<9:41:26,  1.71it/s]
Train steps ... :  40%|████      | 40294/100000 [12:17:14<9:41:05,  1.71it/s]
Train steps ... :  40%|████      | 40295/100000 [12:17:15<9:41:03,  1.71it/s]
Train steps ... :  40%|████      | 40296/100000 [12:17:15<9:41:25,  1.71it/s]
Train steps ... :  40%|████      | 40297/100000 [12:17:16<9:41:11,  1.71it/s]
Train steps ... :  40%|████      | 40298/100000 [12:17:16<9:40:38,  1.71it/s]
Train steps ... :  40%|████      | 40299/100000 [12:17:17<9:40:46,  1.71it/s]
Train steps ... :  40%|████      | 40300/100000 [12:17:17<9:40:32,  1.71it/s]Step... (40300 / 100000 | Loss: 1.210361361503601, Learning Rate: 6e-05)
+
                                                                             
Step... (40300 / 100000 | Loss: 0.9771835803985596, Learning Rate: 6e-05)
+
Train steps ... :  40%|████      | 40300/100000 [12:17:18<9:40:32,  1.71it/s]
Train steps ... :  40%|████      | 40301/100000 [12:17:18<9:40:41,  1.71it/s]
Train steps ... :  40%|████      | 40302/100000 [12:17:19<9:40:32,  1.71it/s]
Train steps ... :  40%|████      | 40303/100000 [12:17:19<9:40:15,  1.71it/s]
Train steps ... :  40%|████      | 40304/100000 [12:17:20<9:40:23,  1.71it/s]
Train steps ... :  40%|████      | 40305/100000 [12:17:20<9:40:20,  1.71it/s]
Train steps ... :  40%|████      | 40306/100000 [12:17:21<9:40:14,  1.71it/s]
Train steps ... :  40%|████      | 40307/100000 [12:17:22<9:40:25,  1.71it/s]
Train steps ... :  40%|████      | 40308/100000 [12:17:22<9:40:37,  1.71it/s]
Train steps ... :  40%|████      | 40309/100000 [12:17:23<9:41:08,  1.71it/s]
Train steps ... :  40%|████      | 40310/100000 [12:17:23<9:41:42,  1.71it/s]
Train steps ... :  40%|████      | 40311/100000 [12:17:24<9:40:55,  1.71it/s]
Train steps ... :  40%|████      | 40312/100000 [12:17:24<9:41:18,  1.71it/s]
Train steps ... :  40%|████      | 40313/100000 [12:17:25<9:41:17,  1.71it/s]
Train steps ... :  40%|████      | 40314/100000 [12:17:26<9:40:40,  1.71it/s]
Train steps ... :  40%|████      | 40315/100000 [12:17:26<9:40:24,  1.71it/s]
Train steps ... :  40%|████      | 40316/100000 [12:17:27<9:40:20,  1.71it/s]
Train steps ... :  40%|████      | 40317/100000 [12:17:27<9:40:01,  1.71it/s]
Train steps ... :  40%|████      | 40318/100000 [12:17:28<9:39:48,  1.72it/s]
Train steps ... :  40%|████      | 40319/100000 [12:17:29<9:40:10,  1.71it/s]
Train steps ... :  40%|████      | 40320/100000 [12:17:29<9:40:26,  1.71it/s]
Train steps ... :  40%|████      | 40321/100000 [12:17:30<9:40:07,  1.71it/s]
Train steps ... :  40%|████      | 40322/100000 [12:17:30<9:41:00,  1.71it/s]
Train steps ... :  40%|████      | 40323/100000 [12:17:31<9:40:43,  1.71it/s]
Train steps ... :  40%|████      | 40324/100000 [12:17:31<9:40:26,  1.71it/s]
Train steps ... :  40%|████      | 40325/100000 [12:17:32<9:41:02,  1.71it/s]Step... (40325 / 100000 | Loss: 1.2024939060211182, Learning Rate: 5.9974874371859305e-05)
+
                                                                             
Step... (40325 / 100000 | Loss: 0.9713431000709534, Learning Rate: 5.9974874371859305e-05)
+
Train steps ... :  40%|████      | 40325/100000 [12:17:32<9:41:02,  1.71it/s]
Train steps ... :  40%|████      | 40326/100000 [12:17:33<9:40:58,  1.71it/s]
Train steps ... :  40%|████      | 40327/100000 [12:17:33<9:41:18,  1.71it/s]
Train steps ... :  40%|████      | 40328/100000 [12:17:34<9:40:59,  1.71it/s]
Train steps ... :  40%|████      | 40329/100000 [12:17:34<9:40:31,  1.71it/s]
Train steps ... :  40%|████      | 40330/100000 [12:17:35<9:40:18,  1.71it/s]
Train steps ... :  40%|████      | 40331/100000 [12:17:36<9:40:53,  1.71it/s]
Train steps ... :  40%|████      | 40332/100000 [12:17:36<9:41:08,  1.71it/s]
Train steps ... :  40%|████      | 40333/100000 [12:17:37<9:41:02,  1.71it/s]
Train steps ... :  40%|████      | 40334/100000 [12:17:37<9:41:04,  1.71it/s]
Train steps ... :  40%|████      | 40335/100000 [12:17:38<9:40:27,  1.71it/s]
Train steps ... :  40%|████      | 40336/100000 [12:17:38<9:40:24,  1.71it/s]
Train steps ... :  40%|████      | 40337/100000 [12:17:39<9:40:15,  1.71it/s]
Train steps ... :  40%|████      | 40338/100000 [12:17:40<9:40:13,  1.71it/s]
Train steps ... :  40%|████      | 40339/100000 [12:17:40<9:40:44,  1.71it/s]
Train steps ... :  40%|████      | 40340/100000 [12:17:41<9:40:31,  1.71it/s]
Train steps ... :  40%|████      | 40341/100000 [12:17:41<9:39:56,  1.71it/s]
Train steps ... :  40%|████      | 40342/100000 [12:17:42<9:40:14,  1.71it/s]
Train steps ... :  40%|████      | 40343/100000 [12:17:43<9:40:28,  1.71it/s]
Train steps ... :  40%|████      | 40344/100000 [12:17:43<9:39:55,  1.71it/s]
Train steps ... :  40%|████      | 40345/100000 [12:17:44<9:39:47,  1.71it/s]
Train steps ... :  40%|████      | 40346/100000 [12:17:44<9:40:25,  1.71it/s]
Train steps ... :  40%|████      | 40347/100000 [12:17:45<9:40:00,  1.71it/s]
Train steps ... :  40%|████      | 40348/100000 [12:17:45<9:40:30,  1.71it/s]
Train steps ... :  40%|████      | 40349/100000 [12:17:46<9:40:09,  1.71it/s]
Train steps ... :  40%|████      | 40350/100000 [12:17:47<9:40:44,  1.71it/s]Step... (40350 / 100000 | Loss: 1.022369384765625, Learning Rate: 5.9949748743718595e-05)
+
                                                                             
Step... (40350 / 100000 | Loss: 0.8591836094856262, Learning Rate: 5.9949748743718595e-05)
+
Train steps ... :  40%|████      | 40350/100000 [12:17:47<9:40:44,  1.71it/s]
Train steps ... :  40%|████      | 40351/100000 [12:17:47<9:40:52,  1.71it/s]
Train steps ... :  40%|████      | 40352/100000 [12:17:48<9:40:33,  1.71it/s]
Train steps ... :  40%|████      | 40353/100000 [12:17:48<9:40:30,  1.71it/s]
Train steps ... :  40%|████      | 40354/100000 [12:17:49<9:40:56,  1.71it/s]
Train steps ... :  40%|████      | 40355/100000 [12:17:50<9:41:21,  1.71it/s]
Train steps ... :  40%|████      | 40356/100000 [12:17:50<9:40:40,  1.71it/s]
Train steps ... :  40%|████      | 40357/100000 [12:17:51<9:40:11,  1.71it/s]
Train steps ... :  40%|████      | 40358/100000 [12:17:51<9:40:46,  1.71it/s]
Train steps ... :  40%|████      | 40359/100000 [12:17:52<9:40:32,  1.71it/s]
Train steps ... :  40%|████      | 40360/100000 [12:17:52<9:40:01,  1.71it/s]
Train steps ... :  40%|████      | 40361/100000 [12:17:53<9:40:12,  1.71it/s]
Train steps ... :  40%|████      | 40362/100000 [12:17:54<9:40:10,  1.71it/s]
Train steps ... :  40%|████      | 40363/100000 [12:17:54<9:40:45,  1.71it/s]
Train steps ... :  40%|████      | 40364/100000 [12:17:55<9:39:40,  1.71it/s]
Train steps ... :  40%|████      | 40365/100000 [12:17:55<9:40:11,  1.71it/s]
Train steps ... :  40%|████      | 40366/100000 [12:17:56<9:40:35,  1.71it/s]
Train steps ... :  40%|████      | 40367/100000 [12:17:57<9:40:25,  1.71it/s]
Train steps ... :  40%|████      | 40368/100000 [12:17:57<9:40:58,  1.71it/s]
Train steps ... :  40%|████      | 40369/100000 [12:17:58<9:41:03,  1.71it/s]
Train steps ... :  40%|████      | 40370/100000 [12:17:58<9:40:36,  1.71it/s]
Train steps ... :  40%|████      | 40371/100000 [12:17:59<9:40:44,  1.71it/s]
Train steps ... :  40%|████      | 40372/100000 [12:18:00<9:39:54,  1.71it/s]
Train steps ... :  40%|████      | 40373/100000 [12:18:00<9:39:59,  1.71it/s]
Train steps ... :  40%|████      | 40374/100000 [12:18:01<9:40:48,  1.71it/s]
Train steps ... :  40%|████      | 40375/100000 [12:18:01<9:40:16,  1.71it/s]Step... (40375 / 100000 | Loss: 0.8335682153701782, Learning Rate: 5.992462311557789e-05)
+
                                                                             
Step... (40375 / 100000 | Loss: 0.6272789239883423, Learning Rate: 5.992462311557789e-05)
+
Train steps ... :  40%|████      | 40375/100000 [12:18:02<9:40:16,  1.71it/s]
Train steps ... :  40%|████      | 40376/100000 [12:18:02<9:40:41,  1.71it/s]
Train steps ... :  40%|████      | 40377/100000 [12:18:02<9:40:14,  1.71it/s]
Train steps ... :  40%|████      | 40378/100000 [12:18:03<9:40:05,  1.71it/s]
Train steps ... :  40%|████      | 40379/100000 [12:18:04<9:39:53,  1.71it/s]
Train steps ... :  40%|████      | 40380/100000 [12:18:04<9:39:23,  1.72it/s]
Train steps ... :  40%|████      | 40381/100000 [12:18:05<9:39:30,  1.71it/s]
Train steps ... :  40%|████      | 40382/100000 [12:18:05<9:40:06,  1.71it/s]
Train steps ... :  40%|████      | 40383/100000 [12:18:06<9:40:06,  1.71it/s]
Train steps ... :  40%|████      | 40384/100000 [12:18:07<9:40:34,  1.71it/s]
Train steps ... :  40%|████      | 40385/100000 [12:18:07<9:41:03,  1.71it/s]
Train steps ... :  40%|████      | 40386/100000 [12:18:08<9:40:25,  1.71it/s]
Train steps ... :  40%|████      | 40387/100000 [12:18:08<9:39:34,  1.71it/s]
Train steps ... :  40%|████      | 40388/100000 [12:18:09<9:40:03,  1.71it/s]
Train steps ... :  40%|████      | 40389/100000 [12:18:09<9:39:59,  1.71it/s]
Train steps ... :  40%|████      | 40390/100000 [12:18:10<9:39:32,  1.71it/s]
Train steps ... :  40%|████      | 40391/100000 [12:18:11<9:39:19,  1.71it/s]
Train steps ... :  40%|████      | 40392/100000 [12:18:11<9:39:36,  1.71it/s]
Train steps ... :  40%|████      | 40393/100000 [12:18:12<9:39:20,  1.71it/s]
Train steps ... :  40%|████      | 40394/100000 [12:18:12<9:39:23,  1.71it/s]
Train steps ... :  40%|████      | 40395/100000 [12:18:13<9:39:53,  1.71it/s]
Train steps ... :  40%|████      | 40396/100000 [12:18:14<9:39:50,  1.71it/s]
Train steps ... :  40%|████      | 40397/100000 [12:18:14<9:40:08,  1.71it/s]
Train steps ... :  40%|████      | 40398/100000 [12:18:15<9:40:31,  1.71it/s]
Train steps ... :  40%|████      | 40399/100000 [12:18:15<9:39:48,  1.71it/s]
Train steps ... :  40%|████      | 40400/100000 [12:18:16<9:39:53,  1.71it/s]Step... (40400 / 100000 | Loss: 0.5989758372306824, Learning Rate: 5.989949748743718e-05)
+
                                                                             
Step... (40400 / 100000 | Loss: 0.7898679971694946, Learning Rate: 5.989949748743718e-05)
+
Train steps ... :  40%|████      | 40400/100000 [12:18:16<9:39:53,  1.71it/s]
Train steps ... :  40%|████      | 40401/100000 [12:18:16<9:39:55,  1.71it/s]
Train steps ... :  40%|████      | 40402/100000 [12:18:17<9:39:41,  1.71it/s]
Train steps ... :  40%|████      | 40403/100000 [12:18:18<9:39:00,  1.72it/s]
Train steps ... :  40%|████      | 40404/100000 [12:18:18<9:39:28,  1.71it/s]
Train steps ... :  40%|████      | 40405/100000 [12:18:19<9:39:06,  1.72it/s]
Train steps ... :  40%|████      | 40406/100000 [12:18:19<9:39:21,  1.71it/s]
Train steps ... :  40%|████      | 40407/100000 [12:18:20<9:38:52,  1.72it/s]
Train steps ... :  40%|████      | 40408/100000 [12:18:21<9:38:43,  1.72it/s]
Train steps ... :  40%|████      | 40409/100000 [12:18:21<9:38:54,  1.72it/s]
Train steps ... :  40%|████      | 40410/100000 [12:18:22<9:39:00,  1.72it/s]
Train steps ... :  40%|████      | 40411/100000 [12:18:22<9:39:48,  1.71it/s]
Train steps ... :  40%|████      | 40412/100000 [12:18:23<9:39:43,  1.71it/s]
Train steps ... :  40%|████      | 40413/100000 [12:18:23<9:39:41,  1.71it/s]
Train steps ... :  40%|████      | 40414/100000 [12:18:24<9:39:22,  1.71it/s]
Train steps ... :  40%|████      | 40415/100000 [12:18:25<9:39:46,  1.71it/s]
Train steps ... :  40%|████      | 40416/100000 [12:18:25<9:40:50,  1.71it/s]
Train steps ... :  40%|████      | 40417/100000 [12:18:26<9:41:16,  1.71it/s]
Train steps ... :  40%|████      | 40418/100000 [12:18:26<9:40:31,  1.71it/s]
Train steps ... :  40%|████      | 40419/100000 [12:18:27<9:40:13,  1.71it/s]
Train steps ... :  40%|████      | 40420/100000 [12:18:28<9:40:05,  1.71it/s]
Train steps ... :  40%|████      | 40421/100000 [12:18:28<9:39:38,  1.71it/s]
Train steps ... :  40%|████      | 40422/100000 [12:18:29<9:40:02,  1.71it/s]
Train steps ... :  40%|████      | 40423/100000 [12:18:29<9:39:49,  1.71it/s]
Train steps ... :  40%|████      | 40424/100000 [12:18:30<9:39:36,  1.71it/s]
Train steps ... :  40%|████      | 40425/100000 [12:18:30<9:39:45,  1.71it/s]Step... (40425 / 100000 | Loss: 0.651218593120575, Learning Rate: 5.9874371859296485e-05)
+
                                                                             
Step... (40425 / 100000 | Loss: 0.8173749446868896, Learning Rate: 5.9874371859296485e-05)
+
Train steps ... :  40%|████      | 40425/100000 [12:18:31<9:39:45,  1.71it/s]
Train steps ... :  40%|████      | 40426/100000 [12:18:31<9:40:03,  1.71it/s]
Train steps ... :  40%|████      | 40427/100000 [12:18:32<9:39:52,  1.71it/s]
Train steps ... :  40%|████      | 40428/100000 [12:18:32<9:39:33,  1.71it/s]
Train steps ... :  40%|████      | 40429/100000 [12:18:33<9:40:12,  1.71it/s]
Train steps ... :  40%|████      | 40430/100000 [12:18:33<9:39:39,  1.71it/s]
Train steps ... :  40%|████      | 40431/100000 [12:18:34<9:40:41,  1.71it/s]
Train steps ... :  40%|████      | 40432/100000 [12:18:35<9:41:13,  1.71it/s]
Train steps ... :  40%|████      | 40433/100000 [12:18:35<9:40:38,  1.71it/s]
Train steps ... :  40%|████      | 40434/100000 [12:18:36<9:39:39,  1.71it/s]
Train steps ... :  40%|████      | 40435/100000 [12:18:36<9:39:31,  1.71it/s]
Train steps ... :  40%|████      | 40436/100000 [12:18:37<9:39:13,  1.71it/s]
Train steps ... :  40%|████      | 40437/100000 [12:18:37<9:39:35,  1.71it/s]
Train steps ... :  40%|████      | 40438/100000 [12:18:38<9:39:39,  1.71it/s]
Train steps ... :  40%|████      | 40439/100000 [12:18:39<9:39:06,  1.71it/s]
Train steps ... :  40%|████      | 40440/100000 [12:18:39<9:39:56,  1.71it/s]
Train steps ... :  40%|████      | 40441/100000 [12:18:40<9:39:41,  1.71it/s]
Train steps ... :  40%|████      | 40442/100000 [12:18:40<9:39:44,  1.71it/s]
Train steps ... :  40%|████      | 40443/100000 [12:18:41<9:39:02,  1.71it/s]
Train steps ... :  40%|████      | 40444/100000 [12:18:42<9:40:31,  1.71it/s]
Train steps ... :  40%|████      | 40445/100000 [12:18:42<9:39:32,  1.71it/s]
Train steps ... :  40%|████      | 40446/100000 [12:18:43<9:39:41,  1.71it/s]
Train steps ... :  40%|████      | 40447/100000 [12:18:43<9:39:21,  1.71it/s]
Train steps ... :  40%|████      | 40448/100000 [12:18:44<9:39:28,  1.71it/s]
Train steps ... :  40%|████      | 40449/100000 [12:18:44<9:38:50,  1.71it/s]
Train steps ... :  40%|████      | 40450/100000 [12:18:45<9:38:36,  1.72it/s]Step... (40450 / 100000 | Loss: 0.762963056564331, Learning Rate: 5.984924623115579e-05)
+
                                                                             
Step... (40450 / 100000 | Loss: 1.0367777347564697, Learning Rate: 5.984924623115579e-05)
+
Train steps ... :  40%|████      | 40450/100000 [12:18:45<9:38:36,  1.72it/s]
Train steps ... :  40%|████      | 40451/100000 [12:18:46<9:39:04,  1.71it/s]
Train steps ... :  40%|████      | 40452/100000 [12:18:46<9:39:13,  1.71it/s]
Train steps ... :  40%|████      | 40453/100000 [12:18:47<9:39:18,  1.71it/s]
Train steps ... :  40%|████      | 40454/100000 [12:18:47<9:38:50,  1.71it/s]
Train steps ... :  40%|████      | 40455/100000 [12:18:48<9:39:05,  1.71it/s]
Train steps ... :  40%|████      | 40456/100000 [12:18:49<9:39:56,  1.71it/s]
Train steps ... :  40%|████      | 40457/100000 [12:18:49<9:39:47,  1.71it/s]
Train steps ... :  40%|████      | 40458/100000 [12:18:50<9:39:46,  1.71it/s]
Train steps ... :  40%|████      | 40459/100000 [12:18:50<9:40:18,  1.71it/s]
Train steps ... :  40%|████      | 40460/100000 [12:18:51<9:39:21,  1.71it/s]
Train steps ... :  40%|████      | 40461/100000 [12:18:51<9:39:10,  1.71it/s]
Train steps ... :  40%|████      | 40462/100000 [12:18:52<9:38:51,  1.71it/s]
Train steps ... :  40%|████      | 40463/100000 [12:18:53<9:39:01,  1.71it/s]
Train steps ... :  40%|████      | 40464/100000 [12:18:53<9:39:33,  1.71it/s]
Train steps ... :  40%|████      | 40465/100000 [12:18:54<9:39:19,  1.71it/s]
Train steps ... :  40%|████      | 40466/100000 [12:18:54<9:39:42,  1.71it/s]
Train steps ... :  40%|████      | 40467/100000 [12:18:55<9:40:06,  1.71it/s]
Train steps ... :  40%|████      | 40468/100000 [12:18:56<9:39:16,  1.71it/s]
Train steps ... :  40%|████      | 40469/100000 [12:18:56<9:39:24,  1.71it/s]
Train steps ... :  40%|████      | 40470/100000 [12:18:57<9:39:30,  1.71it/s]
Train steps ... :  40%|████      | 40471/100000 [12:18:57<9:39:34,  1.71it/s]
Train steps ... :  40%|████      | 40472/100000 [12:18:58<9:39:34,  1.71it/s]
Train steps ... :  40%|████      | 40473/100000 [12:18:58<9:40:01,  1.71it/s]
Train steps ... :  40%|████      | 40474/100000 [12:18:59<9:40:32,  1.71it/s]
Train steps ... :  40%|████      | 40475/100000 [12:19:00<9:40:13,  1.71it/s]Step... (40475 / 100000 | Loss: 0.894070029258728, Learning Rate: 5.982412060301508e-05)
+
                                                                             
Step... (40475 / 100000 | Loss: 0.9223302006721497, Learning Rate: 5.982412060301508e-05)
+
Train steps ... :  40%|████      | 40475/100000 [12:19:00<9:40:13,  1.71it/s]
Train steps ... :  40%|████      | 40476/100000 [12:19:00<9:40:02,  1.71it/s]
Train steps ... :  40%|████      | 40477/100000 [12:19:01<9:39:35,  1.71it/s]
Train steps ... :  40%|████      | 40478/100000 [12:19:01<9:39:31,  1.71it/s]
Train steps ... :  40%|████      | 40479/100000 [12:19:02<9:39:23,  1.71it/s]
Train steps ... :  40%|████      | 40480/100000 [12:19:03<9:39:48,  1.71it/s]
Train steps ... :  40%|████      | 40481/100000 [12:19:03<9:39:41,  1.71it/s]
Train steps ... :  40%|████      | 40482/100000 [12:19:04<9:39:04,  1.71it/s]
Train steps ... :  40%|████      | 40483/100000 [12:19:04<9:38:52,  1.71it/s]
Train steps ... :  40%|████      | 40484/100000 [12:19:05<9:39:29,  1.71it/s]
Train steps ... :  40%|████      | 40485/100000 [12:19:05<9:39:04,  1.71it/s]
Train steps ... :  40%|████      | 40486/100000 [12:19:06<9:38:55,  1.71it/s]
Train steps ... :  40%|████      | 40487/100000 [12:19:07<9:38:55,  1.71it/s]
Train steps ... :  40%|████      | 40488/100000 [12:19:07<9:38:48,  1.71it/s]
Train steps ... :  40%|████      | 40489/100000 [12:19:08<9:38:36,  1.71it/s]
Train steps ... :  40%|████      | 40490/100000 [12:19:08<9:38:48,  1.71it/s]
Train steps ... :  40%|████      | 40491/100000 [12:19:09<9:39:43,  1.71it/s]
Train steps ... :  40%|████      | 40492/100000 [12:19:10<9:39:22,  1.71it/s]
Train steps ... :  40%|████      | 40493/100000 [12:19:10<9:38:58,  1.71it/s]
Train steps ... :  40%|████      | 40494/100000 [12:19:11<9:39:08,  1.71it/s]
Train steps ... :  40%|████      | 40495/100000 [12:19:11<9:40:06,  1.71it/s]
Train steps ... :  40%|████      | 40496/100000 [12:19:12<9:40:08,  1.71it/s]
Train steps ... :  40%|████      | 40497/100000 [12:19:12<9:38:44,  1.71it/s]
Train steps ... :  40%|████      | 40498/100000 [12:19:13<9:39:49,  1.71it/s]
Train steps ... :  40%|████      | 40499/100000 [12:19:14<9:39:57,  1.71it/s]
Train steps ... :  40%|████      | 40500/100000 [12:19:14<9:39:07,  1.71it/s]Step... (40500 / 100000 | Loss: 0.9859069585800171, Learning Rate: 5.979899497487438e-05)
+
                                                                             
Step... (40500 / 100000 | Loss: 0.7681830525398254, Learning Rate: 5.979899497487438e-05)
+
Train steps ... :  40%|████      | 40500/100000 [12:19:15<9:39:07,  1.71it/s]
Train steps ... :  41%|████      | 40501/100000 [12:19:15<9:39:07,  1.71it/s]
Train steps ... :  41%|████      | 40502/100000 [12:19:15<9:39:01,  1.71it/s]
Train steps ... :  41%|████      | 40503/100000 [12:19:16<9:38:49,  1.71it/s]
Train steps ... :  41%|████      | 40504/100000 [12:19:17<9:38:44,  1.71it/s]
Train steps ... :  41%|████      | 40505/100000 [12:19:17<9:39:13,  1.71it/s]
Train steps ... :  41%|████      | 40506/100000 [12:19:18<9:39:25,  1.71it/s]
Train steps ... :  41%|████      | 40507/100000 [12:19:18<9:39:37,  1.71it/s]
Train steps ... :  41%|████      | 40508/100000 [12:19:19<9:38:43,  1.71it/s]
Train steps ... :  41%|████      | 40509/100000 [12:19:20<9:39:31,  1.71it/s]
Train steps ... :  41%|████      | 40510/100000 [12:19:20<9:39:00,  1.71it/s]
Train steps ... :  41%|████      | 40511/100000 [12:19:21<9:38:45,  1.71it/s]
Train steps ... :  41%|████      | 40512/100000 [12:19:21<9:38:38,  1.71it/s]
Train steps ... :  41%|████      | 40513/100000 [12:19:22<9:39:06,  1.71it/s]
Train steps ... :  41%|████      | 40514/100000 [12:19:22<9:39:31,  1.71it/s]
Train steps ... :  41%|████      | 40515/100000 [12:19:23<9:39:26,  1.71it/s]
Train steps ... :  41%|████      | 40516/100000 [12:19:24<9:38:19,  1.71it/s]
Train steps ... :  41%|████      | 40517/100000 [12:19:24<9:38:52,  1.71it/s]
Train steps ... :  41%|████      | 40518/100000 [12:19:25<9:39:01,  1.71it/s]
Train steps ... :  41%|████      | 40519/100000 [12:19:25<9:39:23,  1.71it/s]
Train steps ... :  41%|████      | 40520/100000 [12:19:26<9:39:27,  1.71it/s]
Train steps ... :  41%|████      | 40521/100000 [12:19:27<9:39:48,  1.71it/s]
Train steps ... :  41%|████      | 40522/100000 [12:19:27<9:39:30,  1.71it/s]
Train steps ... :  41%|████      | 40523/100000 [12:19:28<9:38:59,  1.71it/s]
Train steps ... :  41%|████      | 40524/100000 [12:19:28<9:38:18,  1.71it/s]
Train steps ... :  41%|████      | 40525/100000 [12:19:29<9:38:48,  1.71it/s]Step... (40525 / 100000 | Loss: 0.6800838112831116, Learning Rate: 5.977386934673367e-05)
+
                                                                             
Step... (40525 / 100000 | Loss: 0.8852962255477905, Learning Rate: 5.977386934673367e-05)
+
Train steps ... :  41%|████      | 40525/100000 [12:19:29<9:38:48,  1.71it/s]
Train steps ... :  41%|████      | 40526/100000 [12:19:29<9:38:57,  1.71it/s]
Train steps ... :  41%|████      | 40527/100000 [12:19:30<9:38:33,  1.71it/s]
Train steps ... :  41%|████      | 40528/100000 [12:19:31<9:38:50,  1.71it/s]
Train steps ... :  41%|████      | 40529/100000 [12:19:31<9:38:41,  1.71it/s]
Train steps ... :  41%|████      | 40530/100000 [12:19:32<9:38:20,  1.71it/s]
Train steps ... :  41%|████      | 40531/100000 [12:19:32<9:38:25,  1.71it/s]
Train steps ... :  41%|████      | 40532/100000 [12:19:33<9:39:13,  1.71it/s]
Train steps ... :  41%|████      | 40533/100000 [12:19:34<9:39:39,  1.71it/s]
Train steps ... :  41%|████      | 40534/100000 [12:19:34<9:39:44,  1.71it/s]
Train steps ... :  41%|████      | 40535/100000 [12:19:35<9:38:53,  1.71it/s]
Train steps ... :  41%|████      | 40536/100000 [12:19:35<9:38:13,  1.71it/s]
Train steps ... :  41%|████      | 40537/100000 [12:19:36<9:39:01,  1.71it/s]
Train steps ... :  41%|████      | 40538/100000 [12:19:36<9:38:31,  1.71it/s]
Train steps ... :  41%|████      | 40539/100000 [12:19:37<9:38:25,  1.71it/s]
Train steps ... :  41%|████      | 40540/100000 [12:19:38<9:38:14,  1.71it/s]
Train steps ... :  41%|████      | 40541/100000 [12:19:38<9:38:27,  1.71it/s]
Train steps ... :  41%|████      | 40542/100000 [12:19:39<9:39:14,  1.71it/s]
Train steps ... :  41%|████      | 40543/100000 [12:19:39<9:39:41,  1.71it/s]
Train steps ... :  41%|████      | 40544/100000 [12:19:40<9:39:35,  1.71it/s]
Train steps ... :  41%|████      | 40545/100000 [12:19:41<9:38:57,  1.71it/s]
Train steps ... :  41%|████      | 40546/100000 [12:19:41<9:39:40,  1.71it/s]
Train steps ... :  41%|████      | 40547/100000 [12:19:42<9:38:54,  1.71it/s]
Train steps ... :  41%|████      | 40548/100000 [12:19:42<9:38:41,  1.71it/s]
Train steps ... :  41%|████      | 40549/100000 [12:19:43<9:38:43,  1.71it/s]
Train steps ... :  41%|████      | 40550/100000 [12:19:43<9:39:08,  1.71it/s]Step... (40550 / 100000 | Loss: 1.1110241413116455, Learning Rate: 5.974874371859297e-05)
+
                                                                             
Step... (40550 / 100000 | Loss: 0.7223339080810547, Learning Rate: 5.974874371859297e-05)
+
Train steps ... :  41%|████      | 40550/100000 [12:19:44<9:39:08,  1.71it/s]
Train steps ... :  41%|████      | 40551/100000 [12:19:44<9:39:01,  1.71it/s]
Train steps ... :  41%|████      | 40552/100000 [12:19:45<9:38:33,  1.71it/s]
Train steps ... :  41%|████      | 40553/100000 [12:19:45<9:39:01,  1.71it/s]
Train steps ... :  41%|████      | 40554/100000 [12:19:46<9:38:32,  1.71it/s]
Train steps ... :  41%|████      | 40555/100000 [12:19:46<9:38:26,  1.71it/s]
Train steps ... :  41%|████      | 40556/100000 [12:19:47<9:38:19,  1.71it/s]
Train steps ... :  41%|████      | 40557/100000 [12:19:48<9:38:17,  1.71it/s]
Train steps ... :  41%|████      | 40558/100000 [12:19:48<9:38:02,  1.71it/s]
Train steps ... :  41%|████      | 40559/100000 [12:19:49<9:38:11,  1.71it/s]
Train steps ... :  41%|████      | 40560/100000 [12:19:49<9:38:24,  1.71it/s]
Train steps ... :  41%|████      | 40561/100000 [12:19:50<9:38:53,  1.71it/s]
Train steps ... :  41%|████      | 40562/100000 [12:19:50<9:39:01,  1.71it/s]
Train steps ... :  41%|████      | 40563/100000 [12:19:51<9:38:56,  1.71it/s]
Train steps ... :  41%|████      | 40564/100000 [12:19:52<9:38:50,  1.71it/s]
Train steps ... :  41%|████      | 40565/100000 [12:19:52<9:38:42,  1.71it/s]
Train steps ... :  41%|████      | 40566/100000 [12:19:53<9:38:07,  1.71it/s]
Train steps ... :  41%|████      | 40567/100000 [12:19:53<9:37:56,  1.71it/s]
Train steps ... :  41%|████      | 40568/100000 [12:19:54<9:37:43,  1.71it/s]
Train steps ... :  41%|████      | 40569/100000 [12:19:55<9:38:28,  1.71it/s]
Train steps ... :  41%|████      | 40570/100000 [12:19:55<9:38:58,  1.71it/s]
Train steps ... :  41%|████      | 40571/100000 [12:19:56<9:38:52,  1.71it/s]
Train steps ... :  41%|████      | 40572/100000 [12:19:56<9:38:27,  1.71it/s]
Train steps ... :  41%|████      | 40573/100000 [12:19:57<9:38:33,  1.71it/s]
Train steps ... :  41%|████      | 40574/100000 [12:19:57<9:38:22,  1.71it/s]
Train steps ... :  41%|████      | 40575/100000 [12:19:58<9:38:00,  1.71it/s]Step... (40575 / 100000 | Loss: 1.1288775205612183, Learning Rate: 5.972361809045226e-05)
+
                                                                             
Step... (40575 / 100000 | Loss: 0.7650863528251648, Learning Rate: 5.972361809045226e-05)
+
Train steps ... :  41%|████      | 40575/100000 [12:19:58<9:38:00,  1.71it/s]
Train steps ... :  41%|████      | 40576/100000 [12:19:59<9:38:13,  1.71it/s]
Train steps ... :  41%|████      | 40577/100000 [12:19:59<9:38:18,  1.71it/s]
Train steps ... :  41%|████      | 40578/100000 [12:20:00<9:37:53,  1.71it/s]
Train steps ... :  41%|████      | 40579/100000 [12:20:00<9:39:09,  1.71it/s]
Train steps ... :  41%|████      | 40580/100000 [12:20:01<9:39:44,  1.71it/s]
Train steps ... :  41%|████      | 40581/100000 [12:20:02<9:39:46,  1.71it/s]
Train steps ... :  41%|████      | 40582/100000 [12:20:02<9:38:55,  1.71it/s]
Train steps ... :  41%|████      | 40583/100000 [12:20:03<9:38:57,  1.71it/s]
Train steps ... :  41%|████      | 40584/100000 [12:20:03<9:38:25,  1.71it/s]
Train steps ... :  41%|████      | 40585/100000 [12:20:04<9:38:34,  1.71it/s]
Train steps ... :  41%|████      | 40586/100000 [12:20:04<9:38:55,  1.71it/s]
Train steps ... :  41%|████      | 40587/100000 [12:20:05<9:38:51,  1.71it/s]
Train steps ... :  41%|████      | 40588/100000 [12:20:06<9:38:47,  1.71it/s]
Train steps ... :  41%|████      | 40589/100000 [12:20:06<9:38:11,  1.71it/s]
Train steps ... :  41%|████      | 40590/100000 [12:20:07<9:39:14,  1.71it/s]
Train steps ... :  41%|████      | 40591/100000 [12:20:07<9:38:31,  1.71it/s]
Train steps ... :  41%|████      | 40592/100000 [12:20:08<9:39:27,  1.71it/s]
Train steps ... :  41%|████      | 40593/100000 [12:20:09<9:39:59,  1.71it/s]
Train steps ... :  41%|████      | 40594/100000 [12:20:09<9:39:09,  1.71it/s]
Train steps ... :  41%|████      | 40595/100000 [12:20:10<9:38:29,  1.71it/s]
Train steps ... :  41%|████      | 40596/100000 [12:20:10<9:39:04,  1.71it/s]
Train steps ... :  41%|████      | 40597/100000 [12:20:11<9:38:47,  1.71it/s]
Train steps ... :  41%|████      | 40598/100000 [12:20:12<9:39:06,  1.71it/s]
Train steps ... :  41%|████      | 40599/100000 [12:20:12<9:39:13,  1.71it/s]
Train steps ... :  41%|████      | 40600/100000 [12:20:13<9:38:37,  1.71it/s]Step... (40600 / 100000 | Loss: 1.3653382062911987, Learning Rate: 5.969849246231156e-05)
+
                                                                             
Step... (40600 / 100000 | Loss: 0.890068531036377, Learning Rate: 5.969849246231156e-05)
+
Train steps ... :  41%|████      | 40600/100000 [12:20:13<9:38:37,  1.71it/s]
Train steps ... :  41%|████      | 40601/100000 [12:20:13<9:38:43,  1.71it/s]
Train steps ... :  41%|████      | 40602/100000 [12:20:14<9:37:57,  1.71it/s]
Train steps ... :  41%|████      | 40603/100000 [12:20:14<9:38:56,  1.71it/s]
Train steps ... :  41%|████      | 40604/100000 [12:20:15<9:38:36,  1.71it/s]
Train steps ... :  41%|████      | 40605/100000 [12:20:16<9:38:30,  1.71it/s]
Train steps ... :  41%|████      | 40606/100000 [12:20:16<9:38:24,  1.71it/s]
Train steps ... :  41%|████      | 40607/100000 [12:20:17<9:38:29,  1.71it/s]
Train steps ... :  41%|████      | 40608/100000 [12:20:17<9:38:47,  1.71it/s]
Train steps ... :  41%|████      | 40609/100000 [12:20:18<9:38:48,  1.71it/s]
Train steps ... :  41%|████      | 40610/100000 [12:20:19<9:38:59,  1.71it/s]
Train steps ... :  41%|████      | 40611/100000 [12:20:19<9:37:50,  1.71it/s]
Train steps ... :  41%|████      | 40612/100000 [12:20:20<9:39:05,  1.71it/s]
Train steps ... :  41%|████      | 40613/100000 [12:20:20<9:40:35,  1.70it/s]
Train steps ... :  41%|████      | 40614/100000 [12:20:21<9:39:50,  1.71it/s]
Train steps ... :  41%|████      | 40615/100000 [12:20:21<9:38:15,  1.71it/s]
Train steps ... :  41%|████      | 40616/100000 [12:20:22<9:38:31,  1.71it/s]
Train steps ... :  41%|████      | 40617/100000 [12:20:23<9:37:23,  1.71it/s]
Train steps ... :  41%|████      | 40618/100000 [12:20:23<9:38:22,  1.71it/s]
Train steps ... :  41%|████      | 40619/100000 [12:20:24<9:37:32,  1.71it/s]
Train steps ... :  41%|████      | 40620/100000 [12:20:24<9:37:48,  1.71it/s]
Train steps ... :  41%|████      | 40621/100000 [12:20:25<9:38:08,  1.71it/s]
Train steps ... :  41%|████      | 40622/100000 [12:20:26<9:38:42,  1.71it/s]
Train steps ... :  41%|████      | 40623/100000 [12:20:26<9:39:50,  1.71it/s]
Train steps ... :  41%|████      | 40624/100000 [12:20:27<9:39:12,  1.71it/s]
Train steps ... :  41%|████      | 40625/100000 [12:20:27<9:38:48,  1.71it/s]Step... (40625 / 100000 | Loss: 0.7927108407020569, Learning Rate: 5.967336683417085e-05)
+
                                                                             
Step... (40625 / 100000 | Loss: 0.6626235842704773, Learning Rate: 5.967336683417085e-05)
+
Train steps ... :  41%|████      | 40625/100000 [12:20:28<9:38:48,  1.71it/s]
Train steps ... :  41%|████      | 40626/100000 [12:20:28<9:39:43,  1.71it/s]
Train steps ... :  41%|████      | 40627/100000 [12:20:28<9:38:32,  1.71it/s]
Train steps ... :  41%|████      | 40628/100000 [12:20:29<9:39:01,  1.71it/s]
Train steps ... :  41%|████      | 40629/100000 [12:20:30<9:38:58,  1.71it/s]
Train steps ... :  41%|████      | 40630/100000 [12:20:30<9:39:29,  1.71it/s]
Train steps ... :  41%|████      | 40631/100000 [12:20:31<9:37:54,  1.71it/s]
Train steps ... :  41%|████      | 40632/100000 [12:20:31<9:39:28,  1.71it/s]
Train steps ... :  41%|████      | 40633/100000 [12:20:32<9:39:00,  1.71it/s]
Train steps ... :  41%|████      | 40634/100000 [12:20:33<9:38:49,  1.71it/s]
Train steps ... :  41%|████      | 40635/100000 [12:20:33<9:37:54,  1.71it/s]
Train steps ... :  41%|████      | 40636/100000 [12:20:34<9:39:12,  1.71it/s]
Train steps ... :  41%|████      | 40637/100000 [12:20:34<9:39:41,  1.71it/s]
Train steps ... :  41%|████      | 40638/100000 [12:20:35<9:39:19,  1.71it/s]
Train steps ... :  41%|████      | 40639/100000 [12:20:35<9:39:19,  1.71it/s]
Train steps ... :  41%|████      | 40640/100000 [12:20:36<9:39:43,  1.71it/s]
Train steps ... :  41%|████      | 40641/100000 [12:20:37<9:39:09,  1.71it/s]
Train steps ... :  41%|████      | 40642/100000 [12:20:37<9:39:23,  1.71it/s]
Train steps ... :  41%|████      | 40643/100000 [12:20:38<9:39:17,  1.71it/s]
Train steps ... :  41%|████      | 40644/100000 [12:20:38<9:39:35,  1.71it/s]
Train steps ... :  41%|████      | 40645/100000 [12:20:39<9:38:59,  1.71it/s]
Train steps ... :  41%|████      | 40646/100000 [12:20:40<9:39:27,  1.71it/s]
Train steps ... :  41%|████      | 40647/100000 [12:20:40<9:39:51,  1.71it/s]
Train steps ... :  41%|████      | 40648/100000 [12:20:41<9:39:23,  1.71it/s]
Train steps ... :  41%|████      | 40649/100000 [12:20:41<9:40:26,  1.70it/s]
Train steps ... :  41%|████      | 40650/100000 [12:20:42<9:39:33,  1.71it/s]Step... (40650 / 100000 | Loss: 0.7667802572250366, Learning Rate: 5.9648241206030154e-05)
+
                                                                             
Step... (40650 / 100000 | Loss: 0.7908971309661865, Learning Rate: 5.9648241206030154e-05)
+
Train steps ... :  41%|████      | 40650/100000 [12:20:42<9:39:33,  1.71it/s]
Train steps ... :  41%|████      | 40651/100000 [12:20:43<9:39:48,  1.71it/s]
Train steps ... :  41%|████      | 40652/100000 [12:20:43<9:38:53,  1.71it/s]
Train steps ... :  41%|████      | 40653/100000 [12:20:44<9:39:01,  1.71it/s]
Train steps ... :  41%|████      | 40654/100000 [12:20:44<9:38:37,  1.71it/s]
Train steps ... :  41%|████      | 40655/100000 [12:20:45<9:38:33,  1.71it/s]
Train steps ... :  41%|████      | 40656/100000 [12:20:45<9:39:50,  1.71it/s]
Train steps ... :  41%|████      | 40657/100000 [12:20:46<9:40:00,  1.71it/s]
Train steps ... :  41%|████      | 40658/100000 [12:20:47<9:39:40,  1.71it/s]
Train steps ... :  41%|████      | 40659/100000 [12:20:47<9:39:48,  1.71it/s]
Train steps ... :  41%|████      | 40660/100000 [12:20:48<9:38:58,  1.71it/s]
Train steps ... :  41%|████      | 40661/100000 [12:20:48<9:38:33,  1.71it/s]
Train steps ... :  41%|████      | 40662/100000 [12:20:49<9:38:52,  1.71it/s]
Train steps ... :  41%|████      | 40663/100000 [12:20:50<9:39:06,  1.71it/s]
Train steps ... :  41%|████      | 40664/100000 [12:20:50<9:38:21,  1.71it/s]
Train steps ... :  41%|████      | 40665/100000 [12:20:51<9:38:04,  1.71it/s]
Train steps ... :  41%|████      | 40666/100000 [12:20:51<9:37:50,  1.71it/s]
Train steps ... :  41%|████      | 40667/100000 [12:20:52<9:37:21,  1.71it/s]
Train steps ... :  41%|████      | 40668/100000 [12:20:52<9:38:07,  1.71it/s]
Train steps ... :  41%|████      | 40669/100000 [12:20:53<9:39:00,  1.71it/s]
Train steps ... :  41%|████      | 40670/100000 [12:20:54<9:38:17,  1.71it/s]
Train steps ... :  41%|████      | 40671/100000 [12:20:54<9:38:38,  1.71it/s]
Train steps ... :  41%|████      | 40672/100000 [12:20:55<9:38:43,  1.71it/s]
Train steps ... :  41%|████      | 40673/100000 [12:20:55<9:38:30,  1.71it/s]
Train steps ... :  41%|████      | 40674/100000 [12:20:56<9:39:14,  1.71it/s]
Train steps ... :  41%|████      | 40675/100000 [12:20:57<9:38:24,  1.71it/s]Step... (40675 / 100000 | Loss: 0.9092292189598083, Learning Rate: 5.962311557788946e-05)
+
                                                                             
Step... (40675 / 100000 | Loss: 0.6561262607574463, Learning Rate: 5.962311557788946e-05)
+
Train steps ... :  41%|████      | 40675/100000 [12:20:57<9:38:24,  1.71it/s]
Train steps ... :  41%|████      | 40676/100000 [12:20:57<9:37:44,  1.71it/s]
Train steps ... :  41%|████      | 40677/100000 [12:20:58<9:38:06,  1.71it/s]
Train steps ... :  41%|████      | 40678/100000 [12:20:58<9:37:45,  1.71it/s]
Train steps ... :  41%|████      | 40679/100000 [12:20:59<9:38:33,  1.71it/s]
Train steps ... :  41%|████      | 40680/100000 [12:20:59<9:38:02,  1.71it/s]
Train steps ... :  41%|████      | 40681/100000 [12:21:00<9:37:40,  1.71it/s]
Train steps ... :  41%|████      | 40682/100000 [12:21:01<9:38:04,  1.71it/s]
Train steps ... :  41%|████      | 40683/100000 [12:21:01<9:39:34,  1.71it/s]
Train steps ... :  41%|████      | 40684/100000 [12:21:02<9:37:01,  1.71it/s]
Train steps ... :  41%|████      | 40685/100000 [12:21:02<9:37:34,  1.71it/s]
Train steps ... :  41%|████      | 40686/100000 [12:21:03<9:39:16,  1.71it/s]
Train steps ... :  41%|████      | 40687/100000 [12:21:04<9:39:37,  1.71it/s]
Train steps ... :  41%|████      | 40688/100000 [12:21:04<9:39:21,  1.71it/s]
Train steps ... :  41%|████      | 40689/100000 [12:21:05<9:38:13,  1.71it/s]
Train steps ... :  41%|████      | 40690/100000 [12:21:05<9:37:45,  1.71it/s]
Train steps ... :  41%|████      | 40691/100000 [12:21:06<9:37:51,  1.71it/s]
Train steps ... :  41%|████      | 40692/100000 [12:21:06<9:37:54,  1.71it/s]
Train steps ... :  41%|████      | 40693/100000 [12:21:07<9:36:58,  1.71it/s]
Train steps ... :  41%|████      | 40694/100000 [12:21:08<9:39:01,  1.71it/s]
Train steps ... :  41%|████      | 40695/100000 [12:21:08<9:37:55,  1.71it/s]
Train steps ... :  41%|████      | 40696/100000 [12:21:09<9:38:48,  1.71it/s]
Train steps ... :  41%|████      | 40697/100000 [12:21:09<9:38:25,  1.71it/s]
Train steps ... :  41%|████      | 40698/100000 [12:21:10<9:37:28,  1.71it/s]
Train steps ... :  41%|████      | 40699/100000 [12:21:11<9:37:05,  1.71it/s]
Train steps ... :  41%|████      | 40700/100000 [12:21:11<9:37:24,  1.71it/s]Step... (40700 / 100000 | Loss: 0.9117903709411621, Learning Rate: 5.959798994974875e-05)
+
                                                                             
Step... (40700 / 100000 | Loss: 0.9639416933059692, Learning Rate: 5.959798994974875e-05)
+
Train steps ... :  41%|████      | 40700/100000 [12:21:12<9:37:24,  1.71it/s]
Train steps ... :  41%|████      | 40701/100000 [12:21:12<9:37:36,  1.71it/s]
Train steps ... :  41%|████      | 40702/100000 [12:21:12<9:38:56,  1.71it/s]
Train steps ... :  41%|████      | 40703/100000 [12:21:13<9:41:00,  1.70it/s]
Train steps ... :  41%|████      | 40704/100000 [12:21:14<9:40:19,  1.70it/s]
Train steps ... :  41%|████      | 40705/100000 [12:21:14<9:40:16,  1.70it/s]
Train steps ... :  41%|████      | 40706/100000 [12:21:15<9:38:39,  1.71it/s]
Train steps ... :  41%|████      | 40707/100000 [12:21:15<9:38:58,  1.71it/s]
Train steps ... :  41%|████      | 40708/100000 [12:21:16<9:37:26,  1.71it/s]
Train steps ... :  41%|████      | 40709/100000 [12:21:16<9:37:02,  1.71it/s]
Train steps ... :  41%|████      | 40710/100000 [12:21:17<9:36:28,  1.71it/s]
Train steps ... :  41%|████      | 40711/100000 [12:21:18<9:37:50,  1.71it/s]
Train steps ... :  41%|████      | 40712/100000 [12:21:18<9:37:34,  1.71it/s]
Train steps ... :  41%|████      | 40713/100000 [12:21:19<9:37:20,  1.71it/s]
Train steps ... :  41%|████      | 40714/100000 [12:21:19<9:37:20,  1.71it/s]
Train steps ... :  41%|████      | 40715/100000 [12:21:20<9:37:52,  1.71it/s]
Train steps ... :  41%|████      | 40716/100000 [12:21:21<9:38:08,  1.71it/s]
Train steps ... :  41%|████      | 40717/100000 [12:21:21<9:37:47,  1.71it/s]
Train steps ... :  41%|████      | 40718/100000 [12:21:22<9:37:51,  1.71it/s]
Train steps ... :  41%|████      | 40719/100000 [12:21:22<9:37:50,  1.71it/s]
Train steps ... :  41%|████      | 40720/100000 [12:21:23<9:37:56,  1.71it/s]
Train steps ... :  41%|████      | 40721/100000 [12:21:23<9:37:25,  1.71it/s]
Train steps ... :  41%|████      | 40722/100000 [12:21:24<9:37:30,  1.71it/s]
Train steps ... :  41%|████      | 40723/100000 [12:21:25<9:37:38,  1.71it/s]
Train steps ... :  41%|████      | 40724/100000 [12:21:25<9:37:47,  1.71it/s]
Train steps ... :  41%|████      | 40725/100000 [12:21:26<9:37:41,  1.71it/s]Step... (40725 / 100000 | Loss: 0.758019745349884, Learning Rate: 5.9572864321608044e-05)
+
                                                                             
Step... (40725 / 100000 | Loss: 0.927613377571106, Learning Rate: 5.9572864321608044e-05)
+
Train steps ... :  41%|████      | 40725/100000 [12:21:26<9:37:41,  1.71it/s]
Train steps ... :  41%|████      | 40726/100000 [12:21:26<9:37:52,  1.71it/s]
Train steps ... :  41%|████      | 40727/100000 [12:21:27<9:37:47,  1.71it/s]
Train steps ... :  41%|████      | 40728/100000 [12:21:28<9:38:05,  1.71it/s]
Train steps ... :  41%|████      | 40729/100000 [12:21:28<9:37:46,  1.71it/s]
Train steps ... :  41%|████      | 40730/100000 [12:21:29<9:37:47,  1.71it/s]
Train steps ... :  41%|████      | 40731/100000 [12:21:29<9:37:21,  1.71it/s]
Train steps ... :  41%|████      | 40732/100000 [12:21:30<9:37:01,  1.71it/s]
Train steps ... :  41%|████      | 40733/100000 [12:21:30<9:38:08,  1.71it/s]
Train steps ... :  41%|████      | 40734/100000 [12:21:31<9:37:34,  1.71it/s]
Train steps ... :  41%|████      | 40735/100000 [12:21:32<9:37:13,  1.71it/s]
Train steps ... :  41%|████      | 40736/100000 [12:21:32<9:37:19,  1.71it/s]
Train steps ... :  41%|████      | 40737/100000 [12:21:33<9:38:11,  1.71it/s]
Train steps ... :  41%|████      | 40738/100000 [12:21:33<9:37:30,  1.71it/s]
Train steps ... :  41%|████      | 40739/100000 [12:21:34<9:37:27,  1.71it/s]
Train steps ... :  41%|████      | 40740/100000 [12:21:35<9:37:16,  1.71it/s]
Train steps ... :  41%|████      | 40741/100000 [12:21:35<9:37:07,  1.71it/s]
Train steps ... :  41%|████      | 40742/100000 [12:21:36<9:36:40,  1.71it/s]
Train steps ... :  41%|████      | 40743/100000 [12:21:36<9:37:32,  1.71it/s]
Train steps ... :  41%|████      | 40744/100000 [12:21:37<9:37:29,  1.71it/s]
Train steps ... :  41%|████      | 40745/100000 [12:21:37<9:37:11,  1.71it/s]
Train steps ... :  41%|████      | 40746/100000 [12:21:38<9:37:14,  1.71it/s]
Train steps ... :  41%|████      | 40747/100000 [12:21:39<9:37:48,  1.71it/s]
Train steps ... :  41%|████      | 40748/100000 [12:21:39<9:38:22,  1.71it/s]
Train steps ... :  41%|████      | 40749/100000 [12:21:40<9:38:58,  1.71it/s]
Train steps ... :  41%|████      | 40750/100000 [12:21:40<9:38:44,  1.71it/s]Step... (40750 / 100000 | Loss: 0.6409479379653931, Learning Rate: 5.9547738693467334e-05)
+
                                                                             
Step... (40750 / 100000 | Loss: 0.9081125259399414, Learning Rate: 5.9547738693467334e-05)
+
Train steps ... :  41%|████      | 40750/100000 [12:21:41<9:38:44,  1.71it/s]
Train steps ... :  41%|████      | 40751/100000 [12:21:41<9:37:41,  1.71it/s]
Train steps ... :  41%|████      | 40752/100000 [12:21:42<9:37:52,  1.71it/s]
Train steps ... :  41%|████      | 40753/100000 [12:21:42<9:38:11,  1.71it/s]
Train steps ... :  41%|████      | 40754/100000 [12:21:43<9:38:26,  1.71it/s]
Train steps ... :  41%|████      | 40755/100000 [12:21:43<9:37:25,  1.71it/s]
Train steps ... :  41%|████      | 40756/100000 [12:21:44<9:36:53,  1.71it/s]
Train steps ... :  41%|████      | 40757/100000 [12:21:45<9:37:26,  1.71it/s]
Train steps ... :  41%|████      | 40758/100000 [12:21:45<9:36:50,  1.71it/s]
Train steps ... :  41%|████      | 40759/100000 [12:21:46<9:36:56,  1.71it/s]
Train steps ... :  41%|████      | 40760/100000 [12:21:46<9:37:21,  1.71it/s]
Train steps ... :  41%|████      | 40761/100000 [12:21:47<9:37:12,  1.71it/s]
Train steps ... :  41%|████      | 40762/100000 [12:21:47<9:37:37,  1.71it/s]
Train steps ... :  41%|████      | 40763/100000 [12:21:48<9:38:21,  1.71it/s]
Train steps ... :  41%|████      | 40764/100000 [12:21:49<9:37:54,  1.71it/s]
Train steps ... :  41%|████      | 40765/100000 [12:21:49<9:38:11,  1.71it/s]
Train steps ... :  41%|████      | 40766/100000 [12:21:50<9:37:16,  1.71it/s]
Train steps ... :  41%|████      | 40767/100000 [12:21:50<9:38:30,  1.71it/s]
Train steps ... :  41%|████      | 40768/100000 [12:21:51<9:38:08,  1.71it/s]
Train steps ... :  41%|████      | 40769/100000 [12:21:52<9:37:29,  1.71it/s]
Train steps ... :  41%|████      | 40770/100000 [12:21:52<9:37:08,  1.71it/s]
Train steps ... :  41%|████      | 40771/100000 [12:21:53<9:36:58,  1.71it/s]
Train steps ... :  41%|████      | 40772/100000 [12:21:53<9:38:29,  1.71it/s]
Train steps ... :  41%|████      | 40773/100000 [12:21:54<9:38:37,  1.71it/s]
Train steps ... :  41%|████      | 40774/100000 [12:21:54<9:37:48,  1.71it/s]
Train steps ... :  41%|████      | 40775/100000 [12:21:55<9:38:53,  1.71it/s]Step... (40775 / 100000 | Loss: 0.9349840879440308, Learning Rate: 5.952261306532664e-05)
+
                                                                             
Step... (40775 / 100000 | Loss: 0.8973078727722168, Learning Rate: 5.952261306532664e-05)
+
Train steps ... :  41%|████      | 40775/100000 [12:21:55<9:38:53,  1.71it/s]
Train steps ... :  41%|████      | 40776/100000 [12:21:56<9:40:03,  1.70it/s]
Train steps ... :  41%|████      | 40777/100000 [12:21:56<9:38:13,  1.71it/s]
Train steps ... :  41%|████      | 40778/100000 [12:21:57<9:37:25,  1.71it/s]
Train steps ... :  41%|████      | 40779/100000 [12:21:57<9:37:34,  1.71it/s]
Train steps ... :  41%|████      | 40780/100000 [12:21:58<9:38:05,  1.71it/s]
Train steps ... :  41%|████      | 40781/100000 [12:21:59<9:37:24,  1.71it/s]
Train steps ... :  41%|████      | 40782/100000 [12:21:59<9:38:48,  1.71it/s]
Train steps ... :  41%|████      | 40783/100000 [12:22:00<9:37:10,  1.71it/s]
Train steps ... :  41%|████      | 40784/100000 [12:22:00<9:37:14,  1.71it/s]
Train steps ... :  41%|████      | 40785/100000 [12:22:01<9:36:34,  1.71it/s]
Train steps ... :  41%|████      | 40786/100000 [12:22:01<9:36:29,  1.71it/s]
Train steps ... :  41%|████      | 40787/100000 [12:22:02<9:36:25,  1.71it/s]
Train steps ... :  41%|████      | 40788/100000 [12:22:03<9:39:07,  1.70it/s]
Train steps ... :  41%|████      | 40789/100000 [12:22:03<9:38:27,  1.71it/s]
Train steps ... :  41%|████      | 40790/100000 [12:22:04<9:37:56,  1.71it/s]
Train steps ... :  41%|████      | 40791/100000 [12:22:04<9:38:15,  1.71it/s]
Train steps ... :  41%|████      | 40792/100000 [12:22:05<9:37:47,  1.71it/s]
Train steps ... :  41%|████      | 40793/100000 [12:22:06<9:39:10,  1.70it/s]
Train steps ... :  41%|████      | 40794/100000 [12:22:06<9:37:04,  1.71it/s]
Train steps ... :  41%|████      | 40795/100000 [12:22:07<9:36:34,  1.71it/s]
Train steps ... :  41%|████      | 40796/100000 [12:22:07<9:37:38,  1.71it/s]
Train steps ... :  41%|████      | 40797/100000 [12:22:08<9:37:39,  1.71it/s]
Train steps ... :  41%|████      | 40798/100000 [12:22:09<9:37:01,  1.71it/s]
Train steps ... :  41%|████      | 40799/100000 [12:22:09<9:36:41,  1.71it/s]
Train steps ... :  41%|████      | 40800/100000 [12:22:10<9:37:38,  1.71it/s]Step... (40800 / 100000 | Loss: 0.7240376472473145, Learning Rate: 5.949748743718593e-05)
+
                                                                             
Step... (40800 / 100000 | Loss: 0.9121416211128235, Learning Rate: 5.949748743718593e-05)
+
Train steps ... :  41%|████      | 40800/100000 [12:22:10<9:37:38,  1.71it/s]
Train steps ... :  41%|████      | 40801/100000 [12:22:10<9:37:19,  1.71it/s]
Train steps ... :  41%|████      | 40802/100000 [12:22:11<9:38:22,  1.71it/s]
Train steps ... :  41%|████      | 40803/100000 [12:22:11<9:36:48,  1.71it/s]
Train steps ... :  41%|████      | 40804/100000 [12:22:12<9:37:56,  1.71it/s]
Train steps ... :  41%|████      | 40805/100000 [12:22:13<9:36:40,  1.71it/s]
Train steps ... :  41%|████      | 40806/100000 [12:22:13<9:37:14,  1.71it/s]
Train steps ... :  41%|████      | 40807/100000 [12:22:14<9:38:12,  1.71it/s]
Train steps ... :  41%|████      | 40808/100000 [12:22:14<9:37:28,  1.71it/s]
Train steps ... :  41%|████      | 40809/100000 [12:22:15<9:37:25,  1.71it/s]
Train steps ... :  41%|████      | 40810/100000 [12:22:16<9:37:23,  1.71it/s]
Train steps ... :  41%|████      | 40811/100000 [12:22:16<9:38:15,  1.71it/s]
Train steps ... :  41%|████      | 40812/100000 [12:22:17<9:38:33,  1.71it/s]
Train steps ... :  41%|████      | 40813/100000 [12:22:17<9:37:16,  1.71it/s]
Train steps ... :  41%|████      | 40814/100000 [12:22:18<9:36:52,  1.71it/s]
Train steps ... :  41%|████      | 40815/100000 [12:22:18<9:38:12,  1.71it/s]
Train steps ... :  41%|████      | 40816/100000 [12:22:19<9:37:22,  1.71it/s]
Train steps ... :  41%|████      | 40817/100000 [12:22:20<9:37:51,  1.71it/s]
Train steps ... :  41%|████      | 40818/100000 [12:22:20<9:36:46,  1.71it/s]
Train steps ... :  41%|████      | 40819/100000 [12:22:21<9:36:47,  1.71it/s]
Train steps ... :  41%|████      | 40820/100000 [12:22:21<9:38:16,  1.71it/s]
Train steps ... :  41%|████      | 40821/100000 [12:22:22<9:36:57,  1.71it/s]
Train steps ... :  41%|████      | 40822/100000 [12:22:23<9:38:26,  1.71it/s]
Train steps ... :  41%|████      | 40823/100000 [12:22:23<9:37:30,  1.71it/s]
Train steps ... :  41%|████      | 40824/100000 [12:22:24<9:37:09,  1.71it/s]
Train steps ... :  41%|████      | 40825/100000 [12:22:24<9:37:15,  1.71it/s]Step... (40825 / 100000 | Loss: 0.9484007358551025, Learning Rate: 5.947236180904523e-05)
+
                                                                             
Step... (40825 / 100000 | Loss: 0.6683954000473022, Learning Rate: 5.947236180904523e-05)
+
Train steps ... :  41%|████      | 40825/100000 [12:22:25<9:37:15,  1.71it/s]
Train steps ... :  41%|████      | 40826/100000 [12:22:25<9:36:41,  1.71it/s]
Train steps ... :  41%|████      | 40827/100000 [12:22:25<9:36:52,  1.71it/s]
Train steps ... :  41%|████      | 40828/100000 [12:22:26<9:36:56,  1.71it/s]
Train steps ... :  41%|████      | 40829/100000 [12:22:27<9:36:57,  1.71it/s]
Train steps ... :  41%|████      | 40830/100000 [12:22:27<9:36:30,  1.71it/s]
Train steps ... :  41%|████      | 40831/100000 [12:22:28<9:37:17,  1.71it/s]
Train steps ... :  41%|████      | 40832/100000 [12:22:28<9:36:47,  1.71it/s]
Train steps ... :  41%|████      | 40833/100000 [12:22:29<9:36:49,  1.71it/s]
Train steps ... :  41%|████      | 40834/100000 [12:22:30<9:36:33,  1.71it/s]
Train steps ... :  41%|████      | 40835/100000 [12:22:30<9:36:13,  1.71it/s]
Train steps ... :  41%|████      | 40836/100000 [12:22:31<9:36:40,  1.71it/s]
Train steps ... :  41%|████      | 40837/100000 [12:22:31<9:36:42,  1.71it/s]
Train steps ... :  41%|████      | 40838/100000 [12:22:32<9:35:42,  1.71it/s]
Train steps ... :  41%|████      | 40839/100000 [12:22:33<9:36:14,  1.71it/s]
Train steps ... :  41%|████      | 40840/100000 [12:22:33<9:35:48,  1.71it/s]
Train steps ... :  41%|████      | 40841/100000 [12:22:34<9:36:33,  1.71it/s]
Train steps ... :  41%|████      | 40842/100000 [12:22:34<9:36:12,  1.71it/s]
Train steps ... :  41%|████      | 40843/100000 [12:22:35<9:36:31,  1.71it/s]
Train steps ... :  41%|████      | 40844/100000 [12:22:35<9:36:58,  1.71it/s]
Train steps ... :  41%|████      | 40845/100000 [12:22:36<9:36:14,  1.71it/s]
Train steps ... :  41%|████      | 40846/100000 [12:22:37<9:36:22,  1.71it/s]
Train steps ... :  41%|████      | 40847/100000 [12:22:37<9:36:24,  1.71it/s]
Train steps ... :  41%|████      | 40848/100000 [12:22:38<9:37:23,  1.71it/s]
Train steps ... :  41%|████      | 40849/100000 [12:22:38<9:37:15,  1.71it/s]
Train steps ... :  41%|████      | 40850/100000 [12:22:39<9:36:56,  1.71it/s]Step... (40850 / 100000 | Loss: 0.771990180015564, Learning Rate: 5.9447236180904534e-05)
+
                                                                             
Step... (40850 / 100000 | Loss: 0.6850495338439941, Learning Rate: 5.9447236180904534e-05)
+
Train steps ... :  41%|████      | 40850/100000 [12:22:39<9:36:56,  1.71it/s]
Train steps ... :  41%|████      | 40851/100000 [12:22:40<9:36:36,  1.71it/s]
Train steps ... :  41%|████      | 40852/100000 [12:22:40<9:38:49,  1.70it/s]
Train steps ... :  41%|████      | 40853/100000 [12:22:41<9:37:01,  1.71it/s]
Train steps ... :  41%|████      | 40854/100000 [12:22:41<9:37:48,  1.71it/s]
Train steps ... :  41%|████      | 40855/100000 [12:22:42<9:37:04,  1.71it/s]
Train steps ... :  41%|████      | 40856/100000 [12:22:42<9:38:33,  1.70it/s]
Train steps ... :  41%|████      | 40857/100000 [12:22:43<9:38:02,  1.71it/s]
Train steps ... :  41%|████      | 40858/100000 [12:22:44<9:40:01,  1.70it/s]
Train steps ... :  41%|████      | 40859/100000 [12:22:44<9:39:09,  1.70it/s]
Train steps ... :  41%|████      | 40860/100000 [12:22:45<9:38:34,  1.70it/s]
Train steps ... :  41%|████      | 40861/100000 [12:22:45<9:37:31,  1.71it/s]
Train steps ... :  41%|████      | 40862/100000 [12:22:46<9:36:48,  1.71it/s]
Train steps ... :  41%|████      | 40863/100000 [12:22:47<9:36:09,  1.71it/s]
Train steps ... :  41%|████      | 40864/100000 [12:22:47<9:37:02,  1.71it/s]
Train steps ... :  41%|████      | 40865/100000 [12:22:48<9:36:31,  1.71it/s]
Train steps ... :  41%|████      | 40866/100000 [12:22:48<9:37:54,  1.71it/s]
Train steps ... :  41%|████      | 40867/100000 [12:22:49<9:35:20,  1.71it/s]
Train steps ... :  41%|████      | 40868/100000 [12:22:49<9:35:49,  1.71it/s]
Train steps ... :  41%|████      | 40869/100000 [12:22:50<9:36:41,  1.71it/s]
Train steps ... :  41%|████      | 40870/100000 [12:22:51<9:38:42,  1.70it/s]
Train steps ... :  41%|████      | 40871/100000 [12:22:51<9:37:28,  1.71it/s]
Train steps ... :  41%|████      | 40872/100000 [12:22:52<9:37:18,  1.71it/s]
Train steps ... :  41%|████      | 40873/100000 [12:22:52<9:37:35,  1.71it/s]
Train steps ... :  41%|████      | 40874/100000 [12:22:53<9:37:12,  1.71it/s]
Train steps ... :  41%|████      | 40875/100000 [12:22:54<9:35:56,  1.71it/s]Step... (40875 / 100000 | Loss: 0.8561035394668579, Learning Rate: 5.9422110552763824e-05)
+
                                                                             
Step... (40875 / 100000 | Loss: 1.4452426433563232, Learning Rate: 5.9422110552763824e-05)
+
Train steps ... :  41%|████      | 40875/100000 [12:22:54<9:35:56,  1.71it/s]
Train steps ... :  41%|████      | 40876/100000 [12:22:54<9:36:27,  1.71it/s]
Train steps ... :  41%|████      | 40877/100000 [12:22:55<9:35:45,  1.71it/s]
Train steps ... :  41%|████      | 40878/100000 [12:22:55<9:35:27,  1.71it/s]
Train steps ... :  41%|████      | 40879/100000 [12:22:56<9:35:12,  1.71it/s]
Train steps ... :  41%|████      | 40880/100000 [12:22:57<9:36:52,  1.71it/s]
Train steps ... :  41%|████      | 40881/100000 [12:22:57<9:37:48,  1.71it/s]
Train steps ... :  41%|████      | 40882/100000 [12:22:58<9:36:06,  1.71it/s]
Train steps ... :  41%|████      | 40883/100000 [12:22:58<9:37:35,  1.71it/s]
Train steps ... :  41%|████      | 40884/100000 [12:22:59<9:36:18,  1.71it/s]
Train steps ... :  41%|████      | 40885/100000 [12:22:59<9:37:14,  1.71it/s]
Train steps ... :  41%|████      | 40886/100000 [12:23:00<9:36:49,  1.71it/s]
Train steps ... :  41%|████      | 40887/100000 [12:23:01<9:38:39,  1.70it/s]
Train steps ... :  41%|████      | 40888/100000 [12:23:01<9:36:43,  1.71it/s]
Train steps ... :  41%|████      | 40889/100000 [12:23:02<9:35:50,  1.71it/s]
Train steps ... :  41%|████      | 40890/100000 [12:23:02<9:36:30,  1.71it/s]
Train steps ... :  41%|████      | 40891/100000 [12:23:03<9:36:08,  1.71it/s]
Train steps ... :  41%|████      | 40892/100000 [12:23:04<9:35:49,  1.71it/s]
Train steps ... :  41%|████      | 40893/100000 [12:23:04<9:36:03,  1.71it/s]
Train steps ... :  41%|████      | 40894/100000 [12:23:05<9:36:54,  1.71it/s]
Train steps ... :  41%|████      | 40895/100000 [12:23:05<9:36:13,  1.71it/s]
Train steps ... :  41%|████      | 40896/100000 [12:23:06<9:37:49,  1.70it/s]
Train steps ... :  41%|████      | 40897/100000 [12:23:06<9:39:17,  1.70it/s]
Train steps ... :  41%|████      | 40898/100000 [12:23:07<9:38:41,  1.70it/s]
Train steps ... :  41%|████      | 40899/100000 [12:23:08<9:38:17,  1.70it/s]
Train steps ... :  41%|████      | 40900/100000 [12:23:08<9:37:22,  1.71it/s]Step... (40900 / 100000 | Loss: 0.6227597594261169, Learning Rate: 5.939698492462312e-05)
+
                                                                             
Step... (40900 / 100000 | Loss: 1.2064011096954346, Learning Rate: 5.939698492462312e-05)
+
Train steps ... :  41%|████      | 40900/100000 [12:23:09<9:37:22,  1.71it/s]
Train steps ... :  41%|████      | 40901/100000 [12:23:09<9:39:17,  1.70it/s]
Train steps ... :  41%|████      | 40902/100000 [12:23:09<9:38:19,  1.70it/s]
Train steps ... :  41%|████      | 40903/100000 [12:23:10<9:36:55,  1.71it/s]
Train steps ... :  41%|████      | 40904/100000 [12:23:11<9:37:54,  1.70it/s]
Train steps ... :  41%|████      | 40905/100000 [12:23:11<9:38:59,  1.70it/s]
Train steps ... :  41%|████      | 40906/100000 [12:23:12<9:38:06,  1.70it/s]
Train steps ... :  41%|████      | 40907/100000 [12:23:12<9:37:26,  1.71it/s]
Train steps ... :  41%|████      | 40908/100000 [12:23:13<9:36:35,  1.71it/s]
Train steps ... :  41%|████      | 40909/100000 [12:23:14<9:36:01,  1.71it/s]
Train steps ... :  41%|████      | 40910/100000 [12:23:14<9:36:17,  1.71it/s]
Train steps ... :  41%|████      | 40911/100000 [12:23:15<9:35:53,  1.71it/s]
Train steps ... :  41%|████      | 40912/100000 [12:23:15<9:37:01,  1.71it/s]
Train steps ... :  41%|████      | 40913/100000 [12:23:16<9:36:09,  1.71it/s]
Train steps ... :  41%|████      | 40914/100000 [12:23:16<9:36:10,  1.71it/s]
Train steps ... :  41%|████      | 40915/100000 [12:23:17<9:36:20,  1.71it/s]
Train steps ... :  41%|████      | 40916/100000 [12:23:18<9:37:01,  1.71it/s]
Train steps ... :  41%|████      | 40917/100000 [12:23:18<9:36:33,  1.71it/s]
Train steps ... :  41%|████      | 40918/100000 [12:23:19<9:36:33,  1.71it/s]
Train steps ... :  41%|████      | 40919/100000 [12:23:19<9:37:01,  1.71it/s]
Train steps ... :  41%|████      | 40920/100000 [12:23:20<9:37:02,  1.71it/s]
Train steps ... :  41%|████      | 40921/100000 [12:23:21<9:38:33,  1.70it/s]
Train steps ... :  41%|████      | 40922/100000 [12:23:21<9:37:42,  1.70it/s]
Train steps ... :  41%|████      | 40923/100000 [12:23:22<9:36:34,  1.71it/s]
Train steps ... :  41%|████      | 40924/100000 [12:23:22<9:36:38,  1.71it/s]
Train steps ... :  41%|████      | 40925/100000 [12:23:23<9:36:10,  1.71it/s]Step... (40925 / 100000 | Loss: 0.8493732213973999, Learning Rate: 5.937185929648241e-05)
+
                                                                             
Step... (40925 / 100000 | Loss: 0.6125530004501343, Learning Rate: 5.937185929648241e-05)
+
Train steps ... :  41%|████      | 40925/100000 [12:23:23<9:36:10,  1.71it/s]
Train steps ... :  41%|████      | 40926/100000 [12:23:23<9:37:39,  1.70it/s]
Train steps ... :  41%|████      | 40927/100000 [12:23:24<9:35:33,  1.71it/s]
Train steps ... :  41%|████      | 40928/100000 [12:23:25<9:36:16,  1.71it/s]
Train steps ... :  41%|████      | 40929/100000 [12:23:25<9:36:55,  1.71it/s]
Train steps ... :  41%|████      | 40930/100000 [12:23:26<9:36:44,  1.71it/s]
Train steps ... :  41%|████      | 40931/100000 [12:23:26<9:36:49,  1.71it/s]
Train steps ... :  41%|████      | 40932/100000 [12:23:27<9:36:56,  1.71it/s]
Train steps ... :  41%|████      | 40933/100000 [12:23:28<9:36:53,  1.71it/s]
Train steps ... :  41%|████      | 40934/100000 [12:23:28<9:36:06,  1.71it/s]
Train steps ... :  41%|████      | 40935/100000 [12:23:29<9:37:03,  1.71it/s]
Train steps ... :  41%|████      | 40936/100000 [12:23:29<9:37:42,  1.70it/s]
Train steps ... :  41%|████      | 40937/100000 [12:23:30<9:35:59,  1.71it/s]
Train steps ... :  41%|████      | 40938/100000 [12:23:30<9:36:17,  1.71it/s]
Train steps ... :  41%|████      | 40939/100000 [12:23:31<9:35:44,  1.71it/s]
Train steps ... :  41%|████      | 40940/100000 [12:23:32<9:36:10,  1.71it/s]
Train steps ... :  41%|████      | 40941/100000 [12:23:32<9:35:42,  1.71it/s]
Train steps ... :  41%|████      | 40942/100000 [12:23:33<9:35:49,  1.71it/s]
Train steps ... :  41%|████      | 40943/100000 [12:23:33<9:35:43,  1.71it/s]
Train steps ... :  41%|████      | 40944/100000 [12:23:34<9:36:44,  1.71it/s]
Train steps ... :  41%|████      | 40945/100000 [12:23:35<9:35:27,  1.71it/s]
Train steps ... :  41%|████      | 40946/100000 [12:23:35<9:35:09,  1.71it/s]
Train steps ... :  41%|████      | 40947/100000 [12:23:36<9:35:50,  1.71it/s]
Train steps ... :  41%|████      | 40948/100000 [12:23:36<9:34:44,  1.71it/s]
Train steps ... :  41%|████      | 40949/100000 [12:23:37<9:35:23,  1.71it/s]
Train steps ... :  41%|████      | 40950/100000 [12:23:38<9:37:07,  1.71it/s]Step... (40950 / 100000 | Loss: 0.7351630926132202, Learning Rate: 5.9346733668341714e-05)
+
                                                                             
Step... (40950 / 100000 | Loss: 0.8695780634880066, Learning Rate: 5.9346733668341714e-05)
+
Train steps ... :  41%|████      | 40950/100000 [12:23:38<9:37:07,  1.71it/s]
Train steps ... :  41%|████      | 40951/100000 [12:23:38<9:35:55,  1.71it/s]
Train steps ... :  41%|████      | 40952/100000 [12:23:39<9:35:16,  1.71it/s]
Train steps ... :  41%|████      | 40953/100000 [12:23:39<9:35:29,  1.71it/s]
Train steps ... :  41%|████      | 40954/100000 [12:23:40<9:35:45,  1.71it/s]
Train steps ... :  41%|████      | 40955/100000 [12:23:40<9:36:07,  1.71it/s]
Train steps ... :  41%|████      | 40956/100000 [12:23:41<9:37:32,  1.70it/s]
Train steps ... :  41%|████      | 40957/100000 [12:23:42<9:36:40,  1.71it/s]
Train steps ... :  41%|████      | 40958/100000 [12:23:42<9:36:40,  1.71it/s]
Train steps ... :  41%|████      | 40959/100000 [12:23:43<9:36:55,  1.71it/s]
Train steps ... :  41%|████      | 40960/100000 [12:23:43<9:35:33,  1.71it/s]
Train steps ... :  41%|████      | 40961/100000 [12:23:44<9:36:46,  1.71it/s]
Train steps ... :  41%|████      | 40962/100000 [12:23:45<9:35:22,  1.71it/s]
Train steps ... :  41%|████      | 40963/100000 [12:23:45<9:36:03,  1.71it/s]
Train steps ... :  41%|████      | 40964/100000 [12:23:46<9:37:10,  1.70it/s]
Train steps ... :  41%|████      | 40965/100000 [12:23:46<9:36:20,  1.71it/s]
Train steps ... :  41%|████      | 40966/100000 [12:23:47<9:36:06,  1.71it/s]
Train steps ... :  41%|████      | 40967/100000 [12:23:47<9:35:10,  1.71it/s]
Train steps ... :  41%|████      | 40968/100000 [12:23:48<9:35:12,  1.71it/s]
Train steps ... :  41%|████      | 40969/100000 [12:23:49<9:36:03,  1.71it/s]
Train steps ... :  41%|████      | 40970/100000 [12:23:49<9:36:19,  1.71it/s]
Train steps ... :  41%|████      | 40971/100000 [12:23:50<9:35:48,  1.71it/s]
Train steps ... :  41%|████      | 40972/100000 [12:23:50<9:35:57,  1.71it/s]
Train steps ... :  41%|████      | 40973/100000 [12:23:51<9:36:44,  1.71it/s]
Train steps ... :  41%|████      | 40974/100000 [12:23:52<9:35:32,  1.71it/s]
Train steps ... :  41%|████      | 40975/100000 [12:23:52<9:36:09,  1.71it/s]Step... (40975 / 100000 | Loss: 0.9025496244430542, Learning Rate: 5.9321608040201004e-05)
+
                                                                             
Step... (40975 / 100000 | Loss: 0.8528794646263123, Learning Rate: 5.9321608040201004e-05)
+
Train steps ... :  41%|████      | 40975/100000 [12:23:52<9:36:09,  1.71it/s]
Train steps ... :  41%|████      | 40976/100000 [12:23:53<9:35:01,  1.71it/s]
Train steps ... :  41%|████      | 40977/100000 [12:23:53<9:35:03,  1.71it/s]
Train steps ... :  41%|████      | 40978/100000 [12:23:54<9:34:46,  1.71it/s]
Train steps ... :  41%|████      | 40979/100000 [12:23:54<9:35:59,  1.71it/s]
Train steps ... :  41%|████      | 40980/100000 [12:23:55<9:36:11,  1.71it/s]
Train steps ... :  41%|████      | 40981/100000 [12:23:56<9:36:11,  1.71it/s]
Train steps ... :  41%|████      | 40982/100000 [12:23:56<9:35:50,  1.71it/s]
Train steps ... :  41%|████      | 40983/100000 [12:23:57<9:35:53,  1.71it/s]
Train steps ... :  41%|████      | 40984/100000 [12:23:57<9:35:43,  1.71it/s]
Train steps ... :  41%|████      | 40985/100000 [12:23:58<9:36:47,  1.71it/s]
Train steps ... :  41%|████      | 40986/100000 [12:23:59<9:37:09,  1.70it/s]
Train steps ... :  41%|████      | 40987/100000 [12:23:59<9:38:12,  1.70it/s]
Train steps ... :  41%|████      | 40988/100000 [12:24:00<9:35:57,  1.71it/s]
Train steps ... :  41%|████      | 40989/100000 [12:24:00<9:35:51,  1.71it/s]
Train steps ... :  41%|████      | 40990/100000 [12:24:01<9:35:10,  1.71it/s]
Train steps ... :  41%|████      | 40991/100000 [12:24:02<9:34:56,  1.71it/s]
Train steps ... :  41%|████      | 40992/100000 [12:24:02<9:34:46,  1.71it/s]
Train steps ... :  41%|████      | 40993/100000 [12:24:03<9:35:55,  1.71it/s]
Train steps ... :  41%|████      | 40994/100000 [12:24:03<9:36:32,  1.71it/s]
Train steps ... :  41%|████      | 40995/100000 [12:24:04<9:36:23,  1.71it/s]
Train steps ... :  41%|████      | 40996/100000 [12:24:04<9:36:16,  1.71it/s]
Train steps ... :  41%|████      | 40997/100000 [12:24:05<9:35:26,  1.71it/s]
Train steps ... :  41%|████      | 40998/100000 [12:24:06<9:36:09,  1.71it/s]
Train steps ... :  41%|████      | 40999/100000 [12:24:06<9:35:56,  1.71it/s]
Train steps ... :  41%|████      | 41000/100000 [12:24:07<9:36:08,  1.71it/s]Step... (41000 / 100000 | Loss: 0.9923937320709229, Learning Rate: 5.929648241206031e-05)
+
                                                                             
Step... (41000 / 100000 | Loss: 0.7669867277145386, Learning Rate: 5.929648241206031e-05)
+
Train steps ... :  41%|████      | 41000/100000 [12:24:07<9:36:08,  1.71it/s]
Train steps ... :  41%|████      | 41001/100000 [12:24:07<9:35:29,  1.71it/s]
Train steps ... :  41%|████      | 41002/100000 [12:24:08<9:35:01,  1.71it/s]
Train steps ... :  41%|████      | 41003/100000 [12:24:09<9:35:24,  1.71it/s]
Train steps ... :  41%|████      | 41004/100000 [12:24:09<9:35:09,  1.71it/s]
Train steps ... :  41%|████      | 41005/100000 [12:24:10<9:34:26,  1.71it/s]
Train steps ... :  41%|████      | 41006/100000 [12:24:10<9:34:04,  1.71it/s]
Train steps ... :  41%|████      | 41007/100000 [12:24:11<9:34:59,  1.71it/s]
Train steps ... :  41%|████      | 41008/100000 [12:24:11<9:35:37,  1.71it/s]
Train steps ... :  41%|████      | 41009/100000 [12:24:12<9:35:48,  1.71it/s]
Train steps ... :  41%|████      | 41010/100000 [12:24:13<9:35:32,  1.71it/s]
Train steps ... :  41%|████      | 41011/100000 [12:24:13<9:35:07,  1.71it/s]
Train steps ... :  41%|████      | 41012/100000 [12:24:14<9:34:40,  1.71it/s]
Train steps ... :  41%|████      | 41013/100000 [12:24:14<9:34:32,  1.71it/s]
Train steps ... :  41%|████      | 41014/100000 [12:24:15<9:34:17,  1.71it/s]
Train steps ... :  41%|████      | 41015/100000 [12:24:16<9:35:07,  1.71it/s]
Train steps ... :  41%|████      | 41016/100000 [12:24:16<9:36:00,  1.71it/s]
Train steps ... :  41%|████      | 41017/100000 [12:24:17<9:34:22,  1.71it/s]
Train steps ... :  41%|████      | 41018/100000 [12:24:17<9:35:04,  1.71it/s]
Train steps ... :  41%|████      | 41019/100000 [12:24:18<9:34:34,  1.71it/s]
Train steps ... :  41%|████      | 41020/100000 [12:24:18<9:34:23,  1.71it/s]
Train steps ... :  41%|████      | 41021/100000 [12:24:19<9:34:27,  1.71it/s]
Train steps ... :  41%|████      | 41022/100000 [12:24:20<9:35:00,  1.71it/s]
Train steps ... :  41%|████      | 41023/100000 [12:24:20<9:34:44,  1.71it/s]
Train steps ... :  41%|████      | 41024/100000 [12:24:21<9:36:35,  1.70it/s]
Train steps ... :  41%|████      | 41025/100000 [12:24:21<9:36:11,  1.71it/s]Step... (41025 / 100000 | Loss: 0.8567390441894531, Learning Rate: 5.92713567839196e-05)
+
                                                                             
Step... (41025 / 100000 | Loss: 0.6873393058776855, Learning Rate: 5.92713567839196e-05)
+
Train steps ... :  41%|████      | 41025/100000 [12:24:22<9:36:11,  1.71it/s]
Train steps ... :  41%|████      | 41026/100000 [12:24:22<9:36:58,  1.70it/s]
Train steps ... :  41%|████      | 41027/100000 [12:24:23<9:36:45,  1.70it/s]
Train steps ... :  41%|████      | 41028/100000 [12:24:23<9:34:48,  1.71it/s]
Train steps ... :  41%|████      | 41029/100000 [12:24:24<9:34:44,  1.71it/s]
Train steps ... :  41%|████      | 41030/100000 [12:24:24<9:34:46,  1.71it/s]
Train steps ... :  41%|████      | 41031/100000 [12:24:25<9:36:12,  1.71it/s]
Train steps ... :  41%|████      | 41032/100000 [12:24:26<9:35:28,  1.71it/s]
Train steps ... :  41%|████      | 41033/100000 [12:24:26<9:35:32,  1.71it/s]
Train steps ... :  41%|████      | 41034/100000 [12:24:27<9:35:19,  1.71it/s]
Train steps ... :  41%|████      | 41035/100000 [12:24:27<9:35:56,  1.71it/s]
Train steps ... :  41%|████      | 41036/100000 [12:24:28<9:35:07,  1.71it/s]
Train steps ... :  41%|████      | 41037/100000 [12:24:28<9:34:42,  1.71it/s]
Train steps ... :  41%|████      | 41038/100000 [12:24:29<9:35:22,  1.71it/s]
Train steps ... :  41%|████      | 41039/100000 [12:24:30<9:35:27,  1.71it/s]
Train steps ... :  41%|████      | 41040/100000 [12:24:30<9:35:48,  1.71it/s]
Train steps ... :  41%|████      | 41041/100000 [12:24:31<9:34:30,  1.71it/s]
Train steps ... :  41%|████      | 41042/100000 [12:24:31<9:35:01,  1.71it/s]
Train steps ... :  41%|████      | 41043/100000 [12:24:32<9:33:46,  1.71it/s]
Train steps ... :  41%|████      | 41044/100000 [12:24:33<9:34:06,  1.71it/s]
Train steps ... :  41%|████      | 41045/100000 [12:24:33<9:34:20,  1.71it/s]
Train steps ... :  41%|████      | 41046/100000 [12:24:34<9:34:15,  1.71it/s]
Train steps ... :  41%|████      | 41047/100000 [12:24:34<9:34:51,  1.71it/s]
Train steps ... :  41%|████      | 41048/100000 [12:24:35<9:34:58,  1.71it/s]
Train steps ... :  41%|████      | 41049/100000 [12:24:35<9:34:44,  1.71it/s]
Train steps ... :  41%|████      | 41050/100000 [12:24:36<9:34:55,  1.71it/s]Step... (41050 / 100000 | Loss: 0.8058891296386719, Learning Rate: 5.92462311557789e-05)
+
                                                                             
Step... (41050 / 100000 | Loss: 0.8010613918304443, Learning Rate: 5.92462311557789e-05)
+
Train steps ... :  41%|████      | 41050/100000 [12:24:36<9:34:55,  1.71it/s]
Train steps ... :  41%|████      | 41051/100000 [12:24:37<9:35:48,  1.71it/s]
Train steps ... :  41%|████      | 41052/100000 [12:24:37<9:34:59,  1.71it/s]
Train steps ... :  41%|████      | 41053/100000 [12:24:38<9:35:46,  1.71it/s]
Train steps ... :  41%|████      | 41054/100000 [12:24:38<9:34:48,  1.71it/s]
Train steps ... :  41%|████      | 41055/100000 [12:24:39<9:35:36,  1.71it/s]
Train steps ... :  41%|████      | 41056/100000 [12:24:40<9:34:28,  1.71it/s]
Train steps ... :  41%|████      | 41057/100000 [12:24:40<9:36:02,  1.71it/s]
Train steps ... :  41%|████      | 41058/100000 [12:24:41<9:37:03,  1.70it/s]
Train steps ... :  41%|████      | 41059/100000 [12:24:41<9:36:22,  1.70it/s]
Train steps ... :  41%|████      | 41060/100000 [12:24:42<9:33:56,  1.71it/s]
Train steps ... :  41%|████      | 41061/100000 [12:24:42<9:34:55,  1.71it/s]
Train steps ... :  41%|████      | 41062/100000 [12:24:43<9:35:24,  1.71it/s]
Train steps ... :  41%|████      | 41063/100000 [12:24:44<9:34:35,  1.71it/s]
Train steps ... :  41%|████      | 41064/100000 [12:24:44<9:34:02,  1.71it/s]
Train steps ... :  41%|████      | 41065/100000 [12:24:45<9:34:27,  1.71it/s]
Train steps ... :  41%|████      | 41066/100000 [12:24:45<9:34:07,  1.71it/s]
Train steps ... :  41%|████      | 41067/100000 [12:24:46<9:33:52,  1.71it/s]
Train steps ... :  41%|████      | 41068/100000 [12:24:47<9:33:43,  1.71it/s]
Train steps ... :  41%|████      | 41069/100000 [12:24:47<9:33:37,  1.71it/s]
Train steps ... :  41%|████      | 41070/100000 [12:24:48<9:33:26,  1.71it/s]
Train steps ... :  41%|████      | 41071/100000 [12:24:48<9:33:30,  1.71it/s]
Train steps ... :  41%|████      | 41072/100000 [12:24:49<9:34:09,  1.71it/s]
Train steps ... :  41%|████      | 41073/100000 [12:24:50<9:33:42,  1.71it/s]
Train steps ... :  41%|████      | 41074/100000 [12:24:50<9:33:57,  1.71it/s]
Train steps ... :  41%|████      | 41075/100000 [12:24:51<9:33:41,  1.71it/s]Step... (41075 / 100000 | Loss: 0.8116430044174194, Learning Rate: 5.92211055276382e-05)
+
                                                                             
Step... (41075 / 100000 | Loss: 0.7485056519508362, Learning Rate: 5.92211055276382e-05)
+
Train steps ... :  41%|████      | 41075/100000 [12:24:51<9:33:41,  1.71it/s]
Train steps ... :  41%|████      | 41076/100000 [12:24:51<9:34:17,  1.71it/s]
Train steps ... :  41%|████      | 41077/100000 [12:24:52<9:33:31,  1.71it/s]
Train steps ... :  41%|████      | 41078/100000 [12:24:52<9:34:02,  1.71it/s]
Train steps ... :  41%|████      | 41079/100000 [12:24:53<9:34:00,  1.71it/s]
Train steps ... :  41%|████      | 41080/100000 [12:24:54<9:35:59,  1.70it/s]
Train steps ... :  41%|████      | 41081/100000 [12:24:54<9:35:08,  1.71it/s]
Train steps ... :  41%|████      | 41082/100000 [12:24:55<9:35:14,  1.71it/s]
Train steps ... :  41%|████      | 41083/100000 [12:24:55<9:34:16,  1.71it/s]
Train steps ... :  41%|████      | 41084/100000 [12:24:56<9:33:43,  1.71it/s]
Train steps ... :  41%|████      | 41085/100000 [12:24:57<9:34:06,  1.71it/s]
Train steps ... :  41%|████      | 41086/100000 [12:24:57<9:34:13,  1.71it/s]
Train steps ... :  41%|████      | 41087/100000 [12:24:58<9:33:51,  1.71it/s]
Train steps ... :  41%|████      | 41088/100000 [12:24:58<9:33:46,  1.71it/s]
Train steps ... :  41%|████      | 41089/100000 [12:24:59<9:34:19,  1.71it/s]
Train steps ... :  41%|████      | 41090/100000 [12:24:59<9:33:30,  1.71it/s]
Train steps ... :  41%|████      | 41091/100000 [12:25:00<9:34:07,  1.71it/s]
Train steps ... :  41%|████      | 41092/100000 [12:25:01<9:34:03,  1.71it/s]
Train steps ... :  41%|████      | 41093/100000 [12:25:01<9:34:17,  1.71it/s]
Train steps ... :  41%|████      | 41094/100000 [12:25:02<9:34:42,  1.71it/s]
Train steps ... :  41%|████      | 41095/100000 [12:25:02<9:34:06,  1.71it/s]
Train steps ... :  41%|████      | 41096/100000 [12:25:03<9:34:04,  1.71it/s]
Train steps ... :  41%|████      | 41097/100000 [12:25:04<9:34:16,  1.71it/s]
Train steps ... :  41%|████      | 41098/100000 [12:25:04<9:33:06,  1.71it/s]
Train steps ... :  41%|████      | 41099/100000 [12:25:05<9:33:08,  1.71it/s]
Train steps ... :  41%|████      | 41100/100000 [12:25:05<9:34:11,  1.71it/s]Step... (41100 / 100000 | Loss: 1.0109858512878418, Learning Rate: 5.9195979899497487e-05)
+
                                                                             
Step... (41100 / 100000 | Loss: 0.9378949403762817, Learning Rate: 5.9195979899497487e-05)
+
Train steps ... :  41%|████      | 41100/100000 [12:25:06<9:34:11,  1.71it/s]
Train steps ... :  41%|████      | 41101/100000 [12:25:06<9:34:19,  1.71it/s]
Train steps ... :  41%|████      | 41102/100000 [12:25:06<9:33:35,  1.71it/s]
Train steps ... :  41%|████      | 41103/100000 [12:25:07<9:34:57,  1.71it/s]
Train steps ... :  41%|████      | 41104/100000 [12:25:08<9:34:25,  1.71it/s]
Train steps ... :  41%|████      | 41105/100000 [12:25:08<9:34:39,  1.71it/s]
Train steps ... :  41%|████      | 41106/100000 [12:25:09<9:35:26,  1.71it/s]
Train steps ... :  41%|████      | 41107/100000 [12:25:09<9:34:52,  1.71it/s]
Train steps ... :  41%|████      | 41108/100000 [12:25:10<9:35:12,  1.71it/s]
Train steps ... :  41%|████      | 41109/100000 [12:25:11<9:35:08,  1.71it/s]
Train steps ... :  41%|████      | 41110/100000 [12:25:11<9:34:42,  1.71it/s]
Train steps ... :  41%|████      | 41111/100000 [12:25:12<9:34:28,  1.71it/s]
Train steps ... :  41%|████      | 41112/100000 [12:25:12<9:33:46,  1.71it/s]
Train steps ... :  41%|████      | 41113/100000 [12:25:13<9:33:43,  1.71it/s]
Train steps ... :  41%|████      | 41114/100000 [12:25:13<9:33:18,  1.71it/s]
Train steps ... :  41%|████      | 41115/100000 [12:25:14<9:33:40,  1.71it/s]
Train steps ... :  41%|████      | 41116/100000 [12:25:15<9:34:20,  1.71it/s]
Train steps ... :  41%|████      | 41117/100000 [12:25:15<9:34:21,  1.71it/s]
Train steps ... :  41%|████      | 41118/100000 [12:25:16<9:34:27,  1.71it/s]
Train steps ... :  41%|████      | 41119/100000 [12:25:16<9:35:02,  1.71it/s]
Train steps ... :  41%|████      | 41120/100000 [12:25:17<9:34:01,  1.71it/s]
Train steps ... :  41%|████      | 41121/100000 [12:25:18<9:33:48,  1.71it/s]
Train steps ... :  41%|████      | 41122/100000 [12:25:18<9:33:46,  1.71it/s]
Train steps ... :  41%|████      | 41123/100000 [12:25:19<9:33:34,  1.71it/s]
Train steps ... :  41%|████      | 41124/100000 [12:25:19<9:33:02,  1.71it/s]
Train steps ... :  41%|████      | 41125/100000 [12:25:20<9:33:06,  1.71it/s]Step... (41125 / 100000 | Loss: 0.6946523785591125, Learning Rate: 5.917085427135679e-05)
+
                                                                             
Step... (41125 / 100000 | Loss: 0.8637049794197083, Learning Rate: 5.917085427135679e-05)
+
Train steps ... :  41%|████      | 41125/100000 [12:25:20<9:33:06,  1.71it/s]
Train steps ... :  41%|████      | 41126/100000 [12:25:21<9:33:41,  1.71it/s]
Train steps ... :  41%|████      | 41127/100000 [12:25:21<9:33:32,  1.71it/s]
Train steps ... :  41%|████      | 41128/100000 [12:25:22<9:33:19,  1.71it/s]
Train steps ... :  41%|████      | 41129/100000 [12:25:22<9:32:54,  1.71it/s]
Train steps ... :  41%|████      | 41130/100000 [12:25:23<9:33:45,  1.71it/s]
Train steps ... :  41%|████      | 41131/100000 [12:25:23<9:33:56,  1.71it/s]
Train steps ... :  41%|████      | 41132/100000 [12:25:24<9:33:22,  1.71it/s]
Train steps ... :  41%|████      | 41133/100000 [12:25:25<9:33:12,  1.71it/s]
Train steps ... :  41%|████      | 41134/100000 [12:25:25<9:32:45,  1.71it/s]
Train steps ... :  41%|████      | 41135/100000 [12:25:26<9:34:02,  1.71it/s]
Train steps ... :  41%|████      | 41136/100000 [12:25:26<9:34:24,  1.71it/s]
Train steps ... :  41%|████      | 41137/100000 [12:25:27<9:34:03,  1.71it/s]
Train steps ... :  41%|████      | 41138/100000 [12:25:28<9:34:48,  1.71it/s]
Train steps ... :  41%|████      | 41139/100000 [12:25:28<9:35:05,  1.71it/s]
Train steps ... :  41%|████      | 41140/100000 [12:25:29<9:34:00,  1.71it/s]
Train steps ... :  41%|████      | 41141/100000 [12:25:29<9:33:57,  1.71it/s]
Train steps ... :  41%|████      | 41142/100000 [12:25:30<9:33:49,  1.71it/s]
Train steps ... :  41%|████      | 41143/100000 [12:25:30<9:34:20,  1.71it/s]
Train steps ... :  41%|████      | 41144/100000 [12:25:31<9:34:11,  1.71it/s]
Train steps ... :  41%|████      | 41145/100000 [12:25:32<9:34:11,  1.71it/s]
Train steps ... :  41%|████      | 41146/100000 [12:25:32<9:33:33,  1.71it/s]
Train steps ... :  41%|████      | 41147/100000 [12:25:33<9:33:04,  1.71it/s]
Train steps ... :  41%|████      | 41148/100000 [12:25:33<9:32:48,  1.71it/s]
Train steps ... :  41%|████      | 41149/100000 [12:25:34<9:32:32,  1.71it/s]
Train steps ... :  41%|████      | 41150/100000 [12:25:35<9:32:36,  1.71it/s]Step... (41150 / 100000 | Loss: 1.0799663066864014, Learning Rate: 5.914572864321608e-05)
+
                                                                             
Step... (41150 / 100000 | Loss: 0.8936412334442139, Learning Rate: 5.914572864321608e-05)
+
Train steps ... :  41%|████      | 41150/100000 [12:25:35<9:32:36,  1.71it/s]
Train steps ... :  41%|████      | 41151/100000 [12:25:35<9:33:11,  1.71it/s]
Train steps ... :  41%|████      | 41152/100000 [12:25:36<9:33:00,  1.71it/s]
Train steps ... :  41%|████      | 41153/100000 [12:25:36<9:33:35,  1.71it/s]
Train steps ... :  41%|████      | 41154/100000 [12:25:37<9:33:10,  1.71it/s]
Train steps ... :  41%|████      | 41155/100000 [12:25:37<9:32:55,  1.71it/s]
Train steps ... :  41%|████      | 41156/100000 [12:25:38<9:32:50,  1.71it/s]
Train steps ... :  41%|████      | 41157/100000 [12:25:39<9:33:07,  1.71it/s]
Train steps ... :  41%|████      | 41158/100000 [12:25:39<9:33:32,  1.71it/s]
Train steps ... :  41%|████      | 41159/100000 [12:25:40<9:33:35,  1.71it/s]
Train steps ... :  41%|██���█      | 41160/100000 [12:25:40<9:33:35,  1.71it/s]
Train steps ... :  41%|████      | 41161/100000 [12:25:41<9:32:46,  1.71it/s]
Train steps ... :  41%|████      | 41162/100000 [12:25:42<9:33:33,  1.71it/s]
Train steps ... :  41%|████      | 41163/100000 [12:25:42<9:34:06,  1.71it/s]
Train steps ... :  41%|████      | 41164/100000 [12:25:43<9:34:54,  1.71it/s]
Train steps ... :  41%|████      | 41165/100000 [12:25:43<9:33:55,  1.71it/s]
Train steps ... :  41%|████      | 41166/100000 [12:25:44<9:33:28,  1.71it/s]
Train steps ... :  41%|████      | 41167/100000 [12:25:44<9:34:14,  1.71it/s]
Train steps ... :  41%|████      | 41168/100000 [12:25:45<9:33:09,  1.71it/s]
Train steps ... :  41%|████      | 41169/100000 [12:25:46<9:34:38,  1.71it/s]
Train steps ... :  41%|████      | 41170/100000 [12:25:46<9:34:41,  1.71it/s]
Train steps ... :  41%|████      | 41171/100000 [12:25:47<9:33:19,  1.71it/s]
Train steps ... :  41%|████      | 41172/100000 [12:25:47<9:33:55,  1.71it/s]
Train steps ... :  41%|████      | 41173/100000 [12:25:48<9:34:01,  1.71it/s]
Train steps ... :  41%|████      | 41174/100000 [12:25:49<9:34:16,  1.71it/s]
Train steps ... :  41%|████      | 41175/100000 [12:25:49<9:33:34,  1.71it/s]Step... (41175 / 100000 | Loss: 0.9959688186645508, Learning Rate: 5.912060301507538e-05)
+
                                                                             
Step... (41175 / 100000 | Loss: 1.0480127334594727, Learning Rate: 5.912060301507538e-05)
+
Train steps ... :  41%|████      | 41175/100000 [12:25:49<9:33:34,  1.71it/s]
Train steps ... :  41%|████      | 41176/100000 [12:25:50<9:33:32,  1.71it/s]
Train steps ... :  41%|████      | 41177/100000 [12:25:50<9:32:43,  1.71it/s]
Train steps ... :  41%|████      | 41178/100000 [12:25:51<9:34:08,  1.71it/s]
Train steps ... :  41%|████      | 41179/100000 [12:25:52<9:33:23,  1.71it/s]
Train steps ... :  41%|████      | 41180/100000 [12:25:52<9:33:00,  1.71it/s]
Train steps ... :  41%|████      | 41181/100000 [12:25:53<9:33:37,  1.71it/s]
Train steps ... :  41%|████      | 41182/100000 [12:25:53<9:33:13,  1.71it/s]
Train steps ... :  41%|████      | 41183/100000 [12:25:54<9:32:40,  1.71it/s]
Train steps ... :  41%|████      | 41184/100000 [12:25:54<9:32:21,  1.71it/s]
Train steps ... :  41%|████      | 41185/100000 [12:25:55<9:33:13,  1.71it/s]
Train steps ... :  41%|████      | 41186/100000 [12:25:56<9:32:47,  1.71it/s]
Train steps ... :  41%|████      | 41187/100000 [12:25:56<9:32:21,  1.71it/s]
Train steps ... :  41%|████      | 41188/100000 [12:25:57<9:32:21,  1.71it/s]
Train steps ... :  41%|████      | 41189/100000 [12:25:57<9:32:22,  1.71it/s]
Train steps ... :  41%|████      | 41190/100000 [12:25:58<9:32:25,  1.71it/s]
Train steps ... :  41%|████      | 41191/100000 [12:25:59<9:32:25,  1.71it/s]
Train steps ... :  41%|████      | 41192/100000 [12:25:59<9:32:08,  1.71it/s]
Train steps ... :  41%|████      | 41193/100000 [12:26:00<9:31:22,  1.72it/s]
Train steps ... :  41%|████      | 41194/100000 [12:26:00<9:32:43,  1.71it/s]
Train steps ... :  41%|████      | 41195/100000 [12:26:01<9:32:33,  1.71it/s]
Train steps ... :  41%|████      | 41196/100000 [12:26:01<9:33:28,  1.71it/s]
Train steps ... :  41%|████      | 41197/100000 [12:26:02<9:33:51,  1.71it/s]
Train steps ... :  41%|████      | 41198/100000 [12:26:03<9:34:05,  1.71it/s]
Train steps ... :  41%|████      | 41199/100000 [12:26:03<9:33:08,  1.71it/s]
Train steps ... :  41%|████      | 41200/100000 [12:26:04<9:34:38,  1.71it/s]Step... (41200 / 100000 | Loss: 1.008450984954834, Learning Rate: 5.909547738693467e-05)
+
                                                                             
Step... (41200 / 100000 | Loss: 0.6604515314102173, Learning Rate: 5.909547738693467e-05)
+
Train steps ... :  41%|████      | 41200/100000 [12:26:04<9:34:38,  1.71it/s]
Train steps ... :  41%|████      | 41201/100000 [12:26:04<9:33:43,  1.71it/s]
Train steps ... :  41%|████      | 41202/100000 [12:26:05<9:33:03,  1.71it/s]
Train steps ... :  41%|████      | 41203/100000 [12:26:06<9:32:33,  1.71it/s]
Train steps ... :  41%|████      | 41204/100000 [12:26:06<9:32:04,  1.71it/s]
Train steps ... :  41%|████      | 41205/100000 [12:26:07<9:32:08,  1.71it/s]
Train steps ... :  41%|████      | 41206/100000 [12:26:07<9:32:40,  1.71it/s]
Train steps ... :  41%|████      | 41207/100000 [12:26:08<9:33:22,  1.71it/s]
Train steps ... :  41%|████      | 41208/100000 [12:26:08<9:32:39,  1.71it/s]
Train steps ... :  41%|████      | 41209/100000 [12:26:09<9:33:14,  1.71it/s]
Train steps ... :  41%|████      | 41210/100000 [12:26:10<9:32:13,  1.71it/s]
Train steps ... :  41%|████      | 41211/100000 [12:26:10<9:32:32,  1.71it/s]
Train steps ... :  41%|████      | 41212/100000 [12:26:11<9:33:18,  1.71it/s]
Train steps ... :  41%|████      | 41213/100000 [12:26:11<9:33:17,  1.71it/s]
Train steps ... :  41%|████      | 41214/100000 [12:26:12<9:33:21,  1.71it/s]
Train steps ... :  41%|████      | 41215/100000 [12:26:13<9:32:49,  1.71it/s]
Train steps ... :  41%|████      | 41216/100000 [12:26:13<9:33:39,  1.71it/s]
Train steps ... :  41%|████      | 41217/100000 [12:26:14<9:34:14,  1.71it/s]
Train steps ... :  41%|████      | 41218/100000 [12:26:14<9:34:37,  1.70it/s]
Train steps ... :  41%|████      | 41219/100000 [12:26:15<9:33:02,  1.71it/s]
Train steps ... :  41%|████      | 41220/100000 [12:26:15<9:32:59,  1.71it/s]
Train steps ... :  41%|████      | 41221/100000 [12:26:16<9:32:21,  1.71it/s]
Train steps ... :  41%|████      | 41222/100000 [12:26:17<9:31:58,  1.71it/s]
Train steps ... :  41%|████      | 41223/100000 [12:26:17<9:33:06,  1.71it/s]
Train steps ... :  41%|████      | 41224/100000 [12:26:18<9:32:25,  1.71it/s]
Train steps ... :  41%|████      | 41225/100000 [12:26:18<9:32:44,  1.71it/s]Step... (41225 / 100000 | Loss: 0.7714177966117859, Learning Rate: 5.9070351758793976e-05)
+
                                                                             
Step... (41225 / 100000 | Loss: 0.8474186658859253, Learning Rate: 5.9070351758793976e-05)
+
Train steps ... :  41%|████      | 41225/100000 [12:26:19<9:32:44,  1.71it/s]
Train steps ... :  41%|████      | 41226/100000 [12:26:19<9:33:07,  1.71it/s]
Train steps ... :  41%|████      | 41227/100000 [12:26:20<9:32:51,  1.71it/s]
Train steps ... :  41%|████      | 41228/100000 [12:26:20<9:32:32,  1.71it/s]
Train steps ... :  41%|████      | 41229/100000 [12:26:21<9:32:33,  1.71it/s]
Train steps ... :  41%|████      | 41230/100000 [12:26:21<9:33:06,  1.71it/s]
Train steps ... :  41%|████      | 41231/100000 [12:26:22<9:33:45,  1.71it/s]
Train steps ... :  41%|████      | 41232/100000 [12:26:22<9:33:30,  1.71it/s]
Train steps ... :  41%|████      | 41233/100000 [12:26:23<9:34:18,  1.71it/s]
Train steps ... :  41%|████      | 41234/100000 [12:26:24<9:33:38,  1.71it/s]
Train steps ... :  41%|████      | 41235/100000 [12:26:24<9:32:42,  1.71it/s]
Train steps ... :  41%|████      | 41236/100000 [12:26:25<9:33:10,  1.71it/s]
Train steps ... :  41%|████      | 41237/100000 [12:26:25<9:32:51,  1.71it/s]
Train steps ... :  41%|████      | 41238/100000 [12:26:26<9:32:16,  1.71it/s]
Train steps ... :  41%|████      | 41239/100000 [12:26:27<9:32:27,  1.71it/s]
Train steps ... :  41%|████      | 41240/100000 [12:26:27<9:32:06,  1.71it/s]
Train steps ... :  41%|████      | 41241/100000 [12:26:28<9:31:39,  1.71it/s]
Train steps ... :  41%|████      | 41242/100000 [12:26:28<9:31:41,  1.71it/s]
Train steps ... :  41%|████      | 41243/100000 [12:26:29<9:32:11,  1.71it/s]
Train steps ... :  41%|████      | 41244/100000 [12:26:30<9:31:45,  1.71it/s]
Train steps ... :  41%|████      | 41245/100000 [12:26:30<9:31:59,  1.71it/s]
Train steps ... :  41%|████      | 41246/100000 [12:26:31<9:32:38,  1.71it/s]
Train steps ... :  41%|████      | 41247/100000 [12:26:31<9:32:12,  1.71it/s]
Train steps ... :  41%|████      | 41248/100000 [12:26:32<9:31:58,  1.71it/s]
Train steps ... :  41%|████      | 41249/100000 [12:26:32<9:32:21,  1.71it/s]
Train steps ... :  41%|████▏     | 41250/100000 [12:26:33<9:32:21,  1.71it/s]Step... (41250 / 100000 | Loss: 0.7562360763549805, Learning Rate: 5.9045226130653266e-05)
+
                                                                             
Step... (41250 / 100000 | Loss: 1.2060565948486328, Learning Rate: 5.9045226130653266e-05)
+
Train steps ... :  41%|████▏     | 41250/100000 [12:26:33<9:32:21,  1.71it/s]
Train steps ... :  41%|████▏     | 41251/100000 [12:26:34<9:33:03,  1.71it/s]
Train steps ... :  41%|████▏     | 41252/100000 [12:26:34<9:33:21,  1.71it/s]
Train steps ... :  41%|████▏     | 41253/100000 [12:26:35<9:32:49,  1.71it/s]
Train steps ... :  41%|████▏     | 41254/100000 [12:26:35<9:33:27,  1.71it/s]
Train steps ... :  41%|████▏     | 41255/100000 [12:26:36<9:33:18,  1.71it/s]
Train steps ... :  41%|████▏     | 41256/100000 [12:26:37<9:33:13,  1.71it/s]
Train steps ... :  41%|████▏     | 41257/100000 [12:26:37<9:33:08,  1.71it/s]
Train steps ... :  41%|████▏     | 41258/100000 [12:26:38<9:33:12,  1.71it/s]
Train steps ... :  41%|████▏     | 41259/100000 [12:26:38<9:32:52,  1.71it/s]
Train steps ... :  41%|████▏     | 41260/100000 [12:26:39<9:31:59,  1.71it/s]
Train steps ... :  41%|████▏     | 41261/100000 [12:26:39<9:32:22,  1.71it/s]
Train steps ... :  41%|████▏     | 41262/100000 [12:26:40<9:32:47,  1.71it/s]
Train steps ... :  41%|████▏     | 41263/100000 [12:26:41<9:32:59,  1.71it/s]
Train steps ... :  41%|████▏     | 41264/100000 [12:26:41<9:32:38,  1.71it/s]
Train steps ... :  41%|████▏     | 41265/100000 [12:26:42<9:33:23,  1.71it/s]
Train steps ... :  41%|████▏     | 41266/100000 [12:26:42<9:32:47,  1.71it/s]
Train steps ... :  41%|████▏     | 41267/100000 [12:26:43<9:32:33,  1.71it/s]
Train steps ... :  41%|████▏     | 41268/100000 [12:26:44<9:32:42,  1.71it/s]
Train steps ... :  41%|████▏     | 41269/100000 [12:26:44<9:32:43,  1.71it/s]
Train steps ... :  41%|████▏     | 41270/100000 [12:26:45<9:32:06,  1.71it/s]
Train steps ... :  41%|████▏     | 41271/100000 [12:26:45<9:32:00,  1.71it/s]
Train steps ... :  41%|████▏     | 41272/100000 [12:26:46<9:31:41,  1.71it/s]
Train steps ... :  41%|████▏     | 41273/100000 [12:26:46<9:31:30,  1.71it/s]
Train steps ... :  41%|████▏     | 41274/100000 [12:26:47<9:31:16,  1.71it/s]
Train steps ... :  41%|████▏     | 41275/100000 [12:26:48<9:32:07,  1.71it/s]Step... (41275 / 100000 | Loss: 0.837999701499939, Learning Rate: 5.902010050251256e-05)
+
                                                                             
Step... (41275 / 100000 | Loss: 1.2806286811828613, Learning Rate: 5.902010050251256e-05)
+
Train steps ... :  41%|████▏     | 41275/100000 [12:26:48<9:32:07,  1.71it/s]
Train steps ... :  41%|████▏     | 41276/100000 [12:26:48<9:32:39,  1.71it/s]
Train steps ... :  41%|████▏     | 41277/100000 [12:26:49<9:31:49,  1.71it/s]
Train steps ... :  41%|████▏     | 41278/100000 [12:26:49<9:33:14,  1.71it/s]
Train steps ... :  41%|████▏     | 41279/100000 [12:26:50<9:33:14,  1.71it/s]
Train steps ... :  41%|████▏     | 41280/100000 [12:26:51<9:33:46,  1.71it/s]
Train steps ... :  41%|████▏     | 41281/100000 [12:26:51<9:32:53,  1.71it/s]
Train steps ... :  41%|████▏     | 41282/100000 [12:26:52<9:31:59,  1.71it/s]
Train steps ... :  41%|████▏     | 41283/100000 [12:26:52<9:32:06,  1.71it/s]
Train steps ... :  41%|████▏     | 41284/100000 [12:26:53<9:31:50,  1.71it/s]
Train steps ... :  41%|████▏     | 41285/100000 [12:26:53<9:31:39,  1.71it/s]
Train steps ... :  41%|████▏     | 41286/100000 [12:26:54<9:31:24,  1.71it/s]
Train steps ... :  41%|████▏     | 41287/100000 [12:26:55<9:31:01,  1.71it/s]
Train steps ... :  41%|████▏     | 41288/100000 [12:26:55<9:30:53,  1.71it/s]
Train steps ... :  41%|████▏     | 41289/100000 [12:26:56<9:31:20,  1.71it/s]
Train steps ... :  41%|████▏     | 41290/100000 [12:26:56<9:32:48,  1.71it/s]
Train steps ... :  41%|████▏     | 41291/100000 [12:26:57<9:31:39,  1.71it/s]
Train steps ... :  41%|████▏     | 41292/100000 [12:26:58<9:31:51,  1.71it/s]
Train steps ... :  41%|████▏     | 41293/100000 [12:26:58<9:31:52,  1.71it/s]
Train steps ... :  41%|████▏     | 41294/100000 [12:26:59<9:31:16,  1.71it/s]
Train steps ... :  41%|████▏     | 41295/100000 [12:26:59<9:31:08,  1.71it/s]
Train steps ... :  41%|████▏     | 41296/100000 [12:27:00<9:31:40,  1.71it/s]
Train steps ... :  41%|████▏     | 41297/100000 [12:27:00<9:31:20,  1.71it/s]
Train steps ... :  41%|████▏     | 41298/100000 [12:27:01<9:31:39,  1.71it/s]
Train steps ... :  41%|████▏     | 41299/100000 [12:27:02<9:31:39,  1.71it/s]
Train steps ... :  41%|████▏     | 41300/100000 [12:27:02<9:31:41,  1.71it/s]Step... (41300 / 100000 | Loss: 0.7350180149078369, Learning Rate: 5.8994974874371866e-05)
+
                                                                             
Step... (41300 / 100000 | Loss: 0.9557095766067505, Learning Rate: 5.8994974874371866e-05)
+
Train steps ... :  41%|████▏     | 41300/100000 [12:27:03<9:31:41,  1.71it/s]
Train steps ... :  41%|████▏     | 41301/100000 [12:27:03<9:31:59,  1.71it/s]
Train steps ... :  41%|████▏     | 41302/100000 [12:27:03<9:31:40,  1.71it/s]
Train steps ... :  41%|████▏     | 41303/100000 [12:27:04<9:31:30,  1.71it/s]
Train steps ... :  41%|████▏     | 41304/100000 [12:27:05<9:31:30,  1.71it/s]
Train steps ... :  41%|████▏     | 41305/100000 [12:27:05<9:31:13,  1.71it/s]
Train steps ... :  41%|████▏     | 41306/100000 [12:27:06<9:31:42,  1.71it/s]
Train steps ... :  41%|████▏     | 41307/100000 [12:27:06<9:31:21,  1.71it/s]
Train steps ... :  41%|████▏     | 41308/100000 [12:27:07<9:32:00,  1.71it/s]
Train steps ... :  41%|████▏     | 41309/100000 [12:27:08<9:31:29,  1.71it/s]
Train steps ... :  41%|████▏     | 41310/100000 [12:27:08<9:32:50,  1.71it/s]
Train steps ... :  41%|████▏     | 41311/100000 [12:27:09<9:31:45,  1.71it/s]
Train steps ... :  41%|████▏     | 41312/100000 [12:27:09<9:31:29,  1.71it/s]
Train steps ... :  41%|████▏     | 41313/100000 [12:27:10<9:32:08,  1.71it/s]
Train steps ... :  41%|████▏     | 41314/100000 [12:27:10<9:32:01,  1.71it/s]
Train steps ... :  41%|████▏     | 41315/100000 [12:27:11<9:32:08,  1.71it/s]
Train steps ... :  41%|████▏     | 41316/100000 [12:27:12<9:31:43,  1.71it/s]
Train steps ... :  41%|████▏     | 41317/100000 [12:27:12<9:33:15,  1.71it/s]
Train steps ... :  41%|████▏     | 41318/100000 [12:27:13<9:33:47,  1.70it/s]
Train steps ... :  41%|████▏     | 41319/100000 [12:27:13<9:32:51,  1.71it/s]
Train steps ... :  41%|████▏     | 41320/100000 [12:27:14<9:32:19,  1.71it/s]
Train steps ... :  41%|████▏     | 41321/100000 [12:27:15<9:33:41,  1.70it/s]
Train steps ... :  41%|████▏     | 41322/100000 [12:27:15<9:31:34,  1.71it/s]
Train steps ... :  41%|████▏     | 41323/100000 [12:27:16<9:31:45,  1.71it/s]
Train steps ... :  41%|████▏     | 41324/100000 [12:27:16<9:31:22,  1.71it/s]
Train steps ... :  41%|████▏     | 41325/100000 [12:27:17<9:31:33,  1.71it/s]Step... (41325 / 100000 | Loss: 0.7064238786697388, Learning Rate: 5.8969849246231156e-05)
+
                                                                             
Step... (41325 / 100000 | Loss: 0.9356588125228882, Learning Rate: 5.8969849246231156e-05)
+
Train steps ... :  41%|████▏     | 41325/100000 [12:27:17<9:31:33,  1.71it/s]
Train steps ... :  41%|████▏     | 41326/100000 [12:27:17<9:31:17,  1.71it/s]
Train steps ... :  41%|████▏     | 41327/100000 [12:27:18<9:31:26,  1.71it/s]
Train steps ... :  41%|████▏     | 41328/100000 [12:27:19<9:31:13,  1.71it/s]
Train steps ... :  41%|████▏     | 41329/100000 [12:27:19<9:31:24,  1.71it/s]
Train steps ... :  41%|████▏     | 41330/100000 [12:27:20<9:31:03,  1.71it/s]
Train steps ... :  41%|████▏     | 41331/100000 [12:27:20<9:31:17,  1.71it/s]
Train steps ... :  41%|████▏     | 41332/100000 [12:27:21<9:30:47,  1.71it/s]
Train steps ... :  41%|████▏     | 41333/100000 [12:27:22<9:31:20,  1.71it/s]
Train steps ... :  41%|████▏     | 41334/100000 [12:27:22<9:31:30,  1.71it/s]
Train steps ... :  41%|████▏     | 41335/100000 [12:27:23<9:31:37,  1.71it/s]
Train steps ... :  41%|████▏     | 41336/100000 [12:27:23<9:31:09,  1.71it/s]
Train steps ... :  41%|████▏     | 41337/100000 [12:27:24<9:30:57,  1.71it/s]
Train steps ... :  41%|████▏     | 41338/100000 [12:27:24<9:31:18,  1.71it/s]
Train steps ... :  41%|████▏     | 41339/100000 [12:27:25<9:31:24,  1.71it/s]
Train steps ... :  41%|████▏     | 41340/100000 [12:27:26<9:31:59,  1.71it/s]
Train steps ... :  41%|████▏     | 41341/100000 [12:27:26<9:32:10,  1.71it/s]
Train steps ... :  41%|████▏     | 41342/100000 [12:27:27<9:31:33,  1.71it/s]
Train steps ... :  41%|████▏     | 41343/100000 [12:27:27<9:31:43,  1.71it/s]
Train steps ... :  41%|████▏     | 41344/100000 [12:27:28<9:31:38,  1.71it/s]
Train steps ... :  41%|████▏     | 41345/100000 [12:27:29<9:32:06,  1.71it/s]
Train steps ... :  41%|████▏     | 41346/100000 [12:27:29<9:31:31,  1.71it/s]
Train steps ... :  41%|████▏     | 41347/100000 [12:27:30<9:31:25,  1.71it/s]
Train steps ... :  41%|████▏     | 41348/100000 [12:27:30<9:31:00,  1.71it/s]
Train steps ... :  41%|████▏     | 41349/100000 [12:27:31<9:31:12,  1.71it/s]
Train steps ... :  41%|████▏     | 41350/100000 [12:27:31<9:31:29,  1.71it/s]Step... (41350 / 100000 | Loss: 0.7758146524429321, Learning Rate: 5.894472361809046e-05)
+
                                                                             
Step... (41350 / 100000 | Loss: 0.8892589807510376, Learning Rate: 5.894472361809046e-05)
+
Train steps ... :  41%|████▏     | 41350/100000 [12:27:32<9:31:29,  1.71it/s]
Train steps ... :  41%|████▏     | 41351/100000 [12:27:32<9:31:22,  1.71it/s]
Train steps ... :  41%|████▏     | 41352/100000 [12:27:33<9:31:38,  1.71it/s]
Train steps ... :  41%|████▏     | 41353/100000 [12:27:33<9:31:23,  1.71it/s]
Train steps ... :  41%|████▏     | 41354/100000 [12:27:34<9:30:48,  1.71it/s]
Train steps ... :  41%|████▏     | 41355/100000 [12:27:34<9:30:42,  1.71it/s]
Train steps ... :  41%|████▏     | 41356/100000 [12:27:35<9:30:41,  1.71it/s]
Train steps ... :  41%|████▏     | 41357/100000 [12:27:36<9:30:56,  1.71it/s]
Train steps ... :  41%|████▏     | 41358/100000 [12:27:36<9:30:24,  1.71it/s]
Train steps ... :  41%|████▏     | 41359/100000 [12:27:37<9:30:21,  1.71it/s]
Train steps ... :  41%|████▏     | 41360/100000 [12:27:37<9:30:18,  1.71it/s]
Train steps ... :  41%|████▏     | 41361/100000 [12:27:38<9:30:26,  1.71it/s]
Train steps ... :  41%|████▏     | 41362/100000 [12:27:38<9:31:47,  1.71it/s]
Train steps ... :  41%|███��▏     | 41363/100000 [12:27:39<9:31:01,  1.71it/s]
Train steps ... :  41%|████▏     | 41364/100000 [12:27:40<9:31:02,  1.71it/s]
Train steps ... :  41%|████▏     | 41365/100000 [12:27:40<9:31:59,  1.71it/s]
Train steps ... :  41%|████▏     | 41366/100000 [12:27:41<9:31:30,  1.71it/s]
Train steps ... :  41%|████▏     | 41367/100000 [12:27:41<9:31:13,  1.71it/s]
Train steps ... :  41%|████▏     | 41368/100000 [12:27:42<9:31:11,  1.71it/s]
Train steps ... :  41%|████▏     | 41369/100000 [12:27:43<9:32:02,  1.71it/s]
Train steps ... :  41%|████▏     | 41370/100000 [12:27:43<9:31:38,  1.71it/s]
Train steps ... :  41%|████▏     | 41371/100000 [12:27:44<9:31:06,  1.71it/s]
Train steps ... :  41%|████▏     | 41372/100000 [12:27:44<9:31:10,  1.71it/s]
Train steps ... :  41%|████▏     | 41373/100000 [12:27:45<9:30:59,  1.71it/s]
Train steps ... :  41%|████▏     | 41374/100000 [12:27:46<9:30:54,  1.71it/s]
Train steps ... :  41%|████▏     | 41375/100000 [12:27:46<9:32:13,  1.71it/s]Step... (41375 / 100000 | Loss: 0.7591068744659424, Learning Rate: 5.891959798994975e-05)
+
                                                                             
Step... (41375 / 100000 | Loss: 0.8442152738571167, Learning Rate: 5.891959798994975e-05)
+
Train steps ... :  41%|████▏     | 41375/100000 [12:27:46<9:32:13,  1.71it/s]
Train steps ... :  41%|████▏     | 41376/100000 [12:27:47<9:31:42,  1.71it/s]
Train steps ... :  41%|████▏     | 41377/100000 [12:27:47<9:30:55,  1.71it/s]
Train steps ... :  41%|████▏     | 41378/100000 [12:27:48<9:30:56,  1.71it/s]
Train steps ... :  41%|████▏     | 41379/100000 [12:27:48<9:30:58,  1.71it/s]
Train steps ... :  41%|████▏     | 41380/100000 [12:27:49<9:30:38,  1.71it/s]
Train steps ... :  41%|████▏     | 41381/100000 [12:27:50<9:31:02,  1.71it/s]
Train steps ... :  41%|████▏     | 41382/100000 [12:27:50<9:30:31,  1.71it/s]
Train steps ... :  41%|████▏     | 41383/100000 [12:27:51<9:30:43,  1.71it/s]
Train steps ... :  41%|████▏     | 41384/100000 [12:27:51<9:30:32,  1.71it/s]
Train steps ... :  41%|████▏     | 41385/100000 [12:27:52<9:30:27,  1.71it/s]
Train steps ... :  41%|████▏     | 41386/100000 [12:27:53<9:31:02,  1.71it/s]
Train steps ... :  41%|████▏     | 41387/100000 [12:27:53<9:30:49,  1.71it/s]
Train steps ... :  41%|████▏     | 41388/100000 [12:27:54<9:30:15,  1.71it/s]
Train steps ... :  41%|████▏     | 41389/100000 [12:27:54<9:31:11,  1.71it/s]
Train steps ... :  41%|████▏     | 41390/100000 [12:27:55<9:30:03,  1.71it/s]
Train steps ... :  41%|████▏     | 41391/100000 [12:27:55<9:30:45,  1.71it/s]
Train steps ... :  41%|████▏     | 41392/100000 [12:27:56<9:30:21,  1.71it/s]
Train steps ... :  41%|████▏     | 41393/100000 [12:27:57<9:30:42,  1.71it/s]
Train steps ... :  41%|████▏     | 41394/100000 [12:27:57<9:31:05,  1.71it/s]
Train steps ... :  41%|████▏     | 41395/100000 [12:27:58<9:30:33,  1.71it/s]
Train steps ... :  41%|████▏     | 41396/100000 [12:27:58<9:30:11,  1.71it/s]
Train steps ... :  41%|████▏     | 41397/100000 [12:27:59<9:30:24,  1.71it/s]
Train steps ... :  41%|████▏     | 41398/100000 [12:28:00<9:30:48,  1.71it/s]
Train steps ... :  41%|████▏     | 41399/100000 [12:28:00<9:30:26,  1.71it/s]
Train steps ... :  41%|████▏     | 41400/100000 [12:28:01<9:31:01,  1.71it/s]Step... (41400 / 100000 | Loss: 1.0451409816741943, Learning Rate: 5.889447236180905e-05)
+
                                                                             
Step... (41400 / 100000 | Loss: 1.0324517488479614, Learning Rate: 5.889447236180905e-05)
+
Train steps ... :  41%|████▏     | 41400/100000 [12:28:01<9:31:01,  1.71it/s]
Train steps ... :  41%|████▏     | 41401/100000 [12:28:01<9:31:01,  1.71it/s]
Train steps ... :  41%|████▏     | 41402/100000 [12:28:02<9:30:26,  1.71it/s]
Train steps ... :  41%|████▏     | 41403/100000 [12:28:02<9:30:10,  1.71it/s]
Train steps ... :  41%|████▏     | 41404/100000 [12:28:03<9:30:14,  1.71it/s]
Train steps ... :  41%|████▏     | 41405/100000 [12:28:04<9:30:19,  1.71it/s]
Train steps ... :  41%|████▏     | 41406/100000 [12:28:04<9:29:59,  1.71it/s]
Train steps ... :  41%|████▏     | 41407/100000 [12:28:05<9:30:32,  1.71it/s]
Train steps ... :  41%|████▏     | 41408/100000 [12:28:05<9:30:21,  1.71it/s]
Train steps ... :  41%|████▏     | 41409/100000 [12:28:06<9:30:14,  1.71it/s]
Train steps ... :  41%|████▏     | 41410/100000 [12:28:07<9:30:09,  1.71it/s]
Train steps ... :  41%|████▏     | 41411/100000 [12:28:07<9:30:12,  1.71it/s]
Train steps ... :  41%|████▏     | 41412/100000 [12:28:08<9:29:51,  1.71it/s]
Train steps ... :  41%|████▏     | 41413/100000 [12:28:08<9:30:26,  1.71it/s]
Train steps ... :  41%|████▏     | 41414/100000 [12:28:09<9:30:41,  1.71it/s]
Train steps ... :  41%|████▏     | 41415/100000 [12:28:09<9:31:25,  1.71it/s]
Train steps ... :  41%|████▏     | 41416/100000 [12:28:10<9:30:32,  1.71it/s]
Train steps ... :  41%|████▏     | 41417/100000 [12:28:11<9:30:10,  1.71it/s]
Train steps ... :  41%|████▏     | 41418/100000 [12:28:11<9:30:31,  1.71it/s]
Train steps ... :  41%|████▏     | 41419/100000 [12:28:12<9:30:22,  1.71it/s]
Train steps ... :  41%|████▏     | 41420/100000 [12:28:12<9:29:57,  1.71it/s]
Train steps ... :  41%|████▏     | 41421/100000 [12:28:13<9:30:06,  1.71it/s]
Train steps ... :  41%|████▏     | 41422/100000 [12:28:14<9:30:38,  1.71it/s]
Train steps ... :  41%|████▏     | 41423/100000 [12:28:14<9:30:39,  1.71it/s]
Train steps ... :  41%|████▏     | 41424/100000 [12:28:15<9:30:10,  1.71it/s]
Train steps ... :  41%|████▏     | 41425/100000 [12:28:15<9:30:08,  1.71it/s]Step... (41425 / 100000 | Loss: 0.9337307810783386, Learning Rate: 5.886934673366834e-05)
+
                                                                             
Step... (41425 / 100000 | Loss: 0.6069217920303345, Learning Rate: 5.886934673366834e-05)
+
Train steps ... :  41%|████▏     | 41425/100000 [12:28:16<9:30:08,  1.71it/s]
Train steps ... :  41%|████▏     | 41426/100000 [12:28:16<9:31:28,  1.71it/s]
Train steps ... :  41%|████▏     | 41427/100000 [12:28:16<9:31:19,  1.71it/s]
Train steps ... :  41%|████▏     | 41428/100000 [12:28:17<9:31:44,  1.71it/s]
Train steps ... :  41%|████▏     | 41429/100000 [12:28:18<9:30:44,  1.71it/s]
Train steps ... :  41%|████▏     | 41430/100000 [12:28:18<9:30:09,  1.71it/s]
Train steps ... :  41%|████▏     | 41431/100000 [12:28:19<9:30:54,  1.71it/s]
Train steps ... :  41%|████▏     | 41432/100000 [12:28:19<9:31:56,  1.71it/s]
Train steps ... :  41%|████▏     | 41433/100000 [12:28:20<9:31:44,  1.71it/s]
Train steps ... :  41%|████▏     | 41434/100000 [12:28:21<9:31:46,  1.71it/s]
Train steps ... :  41%|████▏     | 41435/100000 [12:28:21<9:31:09,  1.71it/s]
Train steps ... :  41%|████▏     | 41436/100000 [12:28:22<9:30:53,  1.71it/s]
Train steps ... :  41%|████▏     | 41437/100000 [12:28:22<9:30:54,  1.71it/s]
Train steps ... :  41%|████▏     | 41438/100000 [12:28:23<9:31:46,  1.71it/s]
Train steps ... :  41%|████▏     | 41439/100000 [12:28:23<9:31:30,  1.71it/s]
Train steps ... :  41%|████▏     | 41440/100000 [12:28:24<9:32:15,  1.71it/s]
Train steps ... :  41%|████▏     | 41441/100000 [12:28:25<9:31:28,  1.71it/s]
Train steps ... :  41%|████▏     | 41442/100000 [12:28:25<9:31:01,  1.71it/s]
Train steps ... :  41%|████▏     | 41443/100000 [12:28:26<9:31:14,  1.71it/s]
Train steps ... :  41%|████▏     | 41444/100000 [12:28:26<9:31:25,  1.71it/s]
Train steps ... :  41%|████▏     | 41445/100000 [12:28:27<9:31:23,  1.71it/s]
Train steps ... :  41%|████▏     | 41446/100000 [12:28:28<9:30:42,  1.71it/s]
Train steps ... :  41%|████▏     | 41447/100000 [12:28:28<9:30:48,  1.71it/s]
Train steps ... :  41%|████▏     | 41448/100000 [12:28:29<9:31:02,  1.71it/s]
Train steps ... :  41%|████▏     | 41449/100000 [12:28:29<9:30:43,  1.71it/s]
Train steps ... :  41%|████▏     | 41450/100000 [12:28:30<9:30:08,  1.71it/s]Step... (41450 / 100000 | Loss: 0.9356809258460999, Learning Rate: 5.884422110552764e-05)
+
                                                                             
Step... (41450 / 100000 | Loss: 0.6949267983436584, Learning Rate: 5.884422110552764e-05)
+
Train steps ... :  41%|████▏     | 41450/100000 [12:28:30<9:30:08,  1.71it/s]
Train steps ... :  41%|████▏     | 41451/100000 [12:28:31<9:30:07,  1.71it/s]
Train steps ... :  41%|████▏     | 41452/100000 [12:28:31<9:30:22,  1.71it/s]
Train steps ... :  41%|████▏     | 41453/100000 [12:28:32<9:31:02,  1.71it/s]
Train steps ... :  41%|████▏     | 41454/100000 [12:28:32<9:30:56,  1.71it/s]
Train steps ... :  41%|████▏     | 41455/100000 [12:28:33<9:30:54,  1.71it/s]
Train steps ... :  41%|████▏     | 41456/100000 [12:28:33<9:31:12,  1.71it/s]
Train steps ... :  41%|████▏     | 41457/100000 [12:28:34<9:31:54,  1.71it/s]
Train steps ... :  41%|████▏     | 41458/100000 [12:28:35<9:31:38,  1.71it/s]
Train steps ... :  41%|████▏     | 41459/100000 [12:28:35<9:30:20,  1.71it/s]
Train steps ... :  41%|████▏     | 41460/100000 [12:28:36<9:30:23,  1.71it/s]
Train steps ... :  41%|████▏     | 41461/100000 [12:28:36<9:30:46,  1.71it/s]
Train steps ... :  41%|████▏     | 41462/100000 [12:28:37<9:31:11,  1.71it/s]
Train steps ... :  41%|████▏     | 41463/100000 [12:28:38<9:30:50,  1.71it/s]
Train steps ... :  41%|████▏     | 41464/100000 [12:28:38<9:30:56,  1.71it/s]
Train steps ... :  41%|████▏     | 41465/100000 [12:28:39<9:30:59,  1.71it/s]
Train steps ... :  41%|████▏     | 41466/100000 [12:28:39<9:31:33,  1.71it/s]
Train steps ... :  41%|████▏     | 41467/100000 [12:28:40<9:30:41,  1.71it/s]
Train steps ... :  41%|████▏     | 41468/100000 [12:28:40<9:30:39,  1.71it/s]
Train steps ... :  41%|████▏     | 41469/100000 [12:28:41<9:30:27,  1.71it/s]
Train steps ... :  41%|████▏     | 41470/100000 [12:28:42<9:31:49,  1.71it/s]
Train steps ... :  41%|████▏     | 41471/100000 [12:28:42<9:30:20,  1.71it/s]
Train steps ... :  41%|████▏     | 41472/100000 [12:28:43<9:31:17,  1.71it/s]
Train steps ... :  41%|████▏     | 41473/100000 [12:28:43<9:30:29,  1.71it/s]
Train steps ... :  41%|████▏     | 41474/100000 [12:28:44<9:30:24,  1.71it/s]
Train steps ... :  41%|████▏     | 41475/100000 [12:28:45<9:30:24,  1.71it/s]Step... (41475 / 100000 | Loss: 0.87060546875, Learning Rate: 5.881909547738694e-05)
+
                                                                             
Step... (41475 / 100000 | Loss: 0.6839607954025269, Learning Rate: 5.881909547738694e-05)
+
Train steps ... :  41%|████▏     | 41475/100000 [12:28:45<9:30:24,  1.71it/s]
Train steps ... :  41%|████▏     | 41476/100000 [12:28:45<9:30:37,  1.71it/s]
Train steps ... :  41%|████▏     | 41477/100000 [12:28:46<9:30:20,  1.71it/s]
Train steps ... :  41%|████▏     | 41478/100000 [12:28:46<9:30:14,  1.71it/s]
Train steps ... :  41%|████▏     | 41479/100000 [12:28:47<9:30:42,  1.71it/s]
Train steps ... :  41%|████▏     | 41480/100000 [12:28:47<9:30:53,  1.71it/s]
Train steps ... :  41%|████▏     | 41481/100000 [12:28:48<9:30:49,  1.71it/s]
Train steps ... :  41%|████▏     | 41482/100000 [12:28:49<9:30:32,  1.71it/s]
Train steps ... :  41%|████▏     | 41483/100000 [12:28:49<9:30:56,  1.71it/s]
Train steps ... :  41%|████▏     | 41484/100000 [12:28:50<9:31:12,  1.71it/s]
Train steps ... :  41%|████▏     | 41485/100000 [12:28:50<9:31:19,  1.71it/s]
Train steps ... :  41%|████▏     | 41486/100000 [12:28:51<9:29:44,  1.71it/s]
Train steps ... :  41%|████▏     | 41487/100000 [12:28:52<9:30:55,  1.71it/s]
Train steps ... :  41%|████▏     | 41488/100000 [12:28:52<9:30:32,  1.71it/s]
Train steps ... :  41%|████▏     | 41489/100000 [12:28:53<9:29:34,  1.71it/s]
Train steps ... :  41%|████▏     | 41490/100000 [12:28:53<9:30:12,  1.71it/s]
Train steps ... :  41%|████▏     | 41491/100000 [12:28:54<9:30:27,  1.71it/s]
Train steps ... :  41%|████▏     | 41492/100000 [12:28:55<9:31:02,  1.71it/s]
Train steps ... :  41%|████▏     | 41493/100000 [12:28:55<9:30:34,  1.71it/s]
Train steps ... :  41%|████▏     | 41494/100000 [12:28:56<9:30:48,  1.71it/s]
Train steps ... :  41%|████▏     | 41495/100000 [12:28:56<9:30:29,  1.71it/s]
Train steps ... :  41%|████▏     | 41496/100000 [12:28:57<9:30:14,  1.71it/s]
Train steps ... :  41%|████▏     | 41497/100000 [12:28:57<9:31:19,  1.71it/s]
Train steps ... :  41%|████▏     | 41498/100000 [12:28:58<9:31:15,  1.71it/s]
Train steps ... :  41%|████▏     | 41499/100000 [12:28:59<9:31:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41500/100000 [12:28:59<9:30:29,  1.71it/s]Step... (41500 / 100000 | Loss: 0.606288731098175, Learning Rate: 5.879396984924623e-05)
+
                                                                             
Step... (41500 / 100000 | Loss: 0.6765711307525635, Learning Rate: 5.879396984924623e-05)
+
Train steps ... :  42%|████▏     | 41500/100000 [12:29:00<9:30:29,  1.71it/s]
Train steps ... :  42%|████▏     | 41501/100000 [12:29:00<9:31:00,  1.71it/s]
Train steps ... :  42%|████▏     | 41502/100000 [12:29:00<9:30:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41503/100000 [12:29:01<9:30:28,  1.71it/s]
Train steps ... :  42%|████▏     | 41504/100000 [12:29:02<9:31:36,  1.71it/s]
Train steps ... :  42%|████▏     | 41505/100000 [12:29:02<9:30:53,  1.71it/s]
Train steps ... :  42%|████▏     | 41506/100000 [12:29:03<9:31:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41507/100000 [12:29:03<9:30:53,  1.71it/s]
Train steps ... :  42%|████▏     | 41508/100000 [12:29:04<9:30:33,  1.71it/s]
Train steps ... :  42%|████▏     | 41509/100000 [12:29:04<9:30:08,  1.71it/s]
Train steps ... :  42%|████▏     | 41510/100000 [12:29:05<9:29:41,  1.71it/s]
Train steps ... :  42%|████▏     | 41511/100000 [12:29:06<9:30:23,  1.71it/s]
Train steps ... :  42%|████▏     | 41512/100000 [12:29:06<9:30:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41513/100000 [12:29:07<9:30:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41514/100000 [12:29:07<9:29:38,  1.71it/s]
Train steps ... :  42%|████▏     | 41515/100000 [12:29:08<9:29:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41516/100000 [12:29:09<9:31:00,  1.71it/s]
Train steps ... :  42%|████▏     | 41517/100000 [12:29:09<9:30:32,  1.71it/s]
Train steps ... :  42%|████▏     | 41518/100000 [12:29:10<9:29:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41519/100000 [12:29:10<9:31:13,  1.71it/s]
Train steps ... :  42%|████▏     | 41520/100000 [12:29:11<9:30:26,  1.71it/s]
Train steps ... :  42%|████▏     | 41521/100000 [12:29:11<9:31:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41522/100000 [12:29:12<9:30:28,  1.71it/s]
Train steps ... :  42%|████▏     | 41523/100000 [12:29:13<9:29:37,  1.71it/s]
Train steps ... :  42%|████▏     | 41524/100000 [12:29:13<9:30:16,  1.71it/s]
Train steps ... :  42%|████▏     | 41525/100000 [12:29:14<9:30:30,  1.71it/s]Step... (41525 / 100000 | Loss: 0.7462254762649536, Learning Rate: 5.8768844221105536e-05)
+
                                                                             
Step... (41525 / 100000 | Loss: 1.2923672199249268, Learning Rate: 5.8768844221105536e-05)
+
Train steps ... :  42%|████▏     | 41525/100000 [12:29:14<9:30:30,  1.71it/s]
Train steps ... :  42%|████▏     | 41526/100000 [12:29:14<9:31:02,  1.71it/s]
Train steps ... :  42%|████▏     | 41527/100000 [12:29:15<9:30:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41528/100000 [12:29:16<9:30:16,  1.71it/s]
Train steps ... :  42%|████▏     | 41529/100000 [12:29:16<9:30:38,  1.71it/s]
Train steps ... :  42%|████▏     | 41530/100000 [12:29:17<9:29:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41531/100000 [12:29:17<9:30:55,  1.71it/s]
Train steps ... :  42%|████▏     | 41532/100000 [12:29:18<9:30:57,  1.71it/s]
Train steps ... :  42%|████▏     | 41533/100000 [12:29:19<9:31:17,  1.71it/s]
Train steps ... :  42%|████▏     | 41534/100000 [12:29:19<9:30:42,  1.71it/s]
Train steps ... :  42%|████▏     | 41535/100000 [12:29:20<9:31:09,  1.71it/s]
Train steps ... :  42%|████▏     | 41536/100000 [12:29:20<9:30:15,  1.71it/s]
Train steps ... :  42%|████▏     | 41537/100000 [12:29:21<9:30:38,  1.71it/s]
Train steps ... :  42%|████▏     | 41538/100000 [12:29:21<9:31:27,  1.71it/s]
Train steps ... :  42%|████▏     | 41539/100000 [12:29:22<9:30:46,  1.71it/s]
Train steps ... :  42%|████▏     | 41540/100000 [12:29:23<9:30:20,  1.71it/s]
Train steps ... :  42%|████▏     | 41541/100000 [12:29:23<9:30:23,  1.71it/s]
Train steps ... :  42%|████▏     | 41542/100000 [12:29:24<9:31:40,  1.70it/s]
Train steps ... :  42%|████▏     | 41543/100000 [12:29:24<9:30:30,  1.71it/s]
Train steps ... :  42%|████▏     | 41544/100000 [12:29:25<9:29:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41545/100000 [12:29:26<9:30:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41546/100000 [12:29:26<9:29:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41547/100000 [12:29:27<9:28:56,  1.71it/s]
Train steps ... :  42%|████▏     | 41548/100000 [12:29:27<9:29:09,  1.71it/s]
Train steps ... :  42%|████▏     | 41549/100000 [12:29:28<9:30:44,  1.71it/s]
Train steps ... :  42%|████▏     | 41550/100000 [12:29:28<9:30:14,  1.71it/s]Step... (41550 / 100000 | Loss: 0.8344532251358032, Learning Rate: 5.8743718592964826e-05)
+
                                                                             
Step... (41550 / 100000 | Loss: 0.6808561086654663, Learning Rate: 5.8743718592964826e-05)
+
Train steps ... :  42%|████▏     | 41550/100000 [12:29:29<9:30:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41551/100000 [12:29:29<9:31:47,  1.70it/s]
Train steps ... :  42%|████▏     | 41552/100000 [12:29:30<9:31:20,  1.70it/s]
Train steps ... :  42%|████▏     | 41553/100000 [12:29:30<9:31:12,  1.71it/s]
Train steps ... :  42%|████▏     | 41554/100000 [12:29:31<9:32:45,  1.70it/s]
Train steps ... :  42%|████▏     | 41555/100000 [12:29:31<9:30:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41556/100000 [12:29:32<9:30:23,  1.71it/s]
Train steps ... :  42%|████▏     | 41557/100000 [12:29:33<9:30:59,  1.71it/s]
Train steps ... :  42%|████▏     | 41558/100000 [12:29:33<9:30:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41559/100000 [12:29:34<9:30:02,  1.71it/s]
Train steps ... :  42%|████▏     | 41560/100000 [12:29:34<9:31:13,  1.71it/s]
Train steps ... :  42%|████▏     | 41561/100000 [12:29:35<9:31:17,  1.70it/s]
Train steps ... :  42%|████▏     | 41562/100000 [12:29:35<9:31:29,  1.70it/s]
Train steps ... :  42%|████▏     | 41563/100000 [12:29:36<9:29:24,  1.71it/s]
Train steps ... :  42%|████���     | 41564/100000 [12:29:37<9:30:27,  1.71it/s]
Train steps ... :  42%|████▏     | 41565/100000 [12:29:37<9:28:28,  1.71it/s]
Train steps ... :  42%|████▏     | 41566/100000 [12:29:38<9:29:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41567/100000 [12:29:38<9:29:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41568/100000 [12:29:39<9:31:30,  1.70it/s]
Train steps ... :  42%|████▏     | 41569/100000 [12:29:40<9:30:32,  1.71it/s]
Train steps ... :  42%|████▏     | 41570/100000 [12:29:40<9:29:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41571/100000 [12:29:41<9:29:44,  1.71it/s]
Train steps ... :  42%|████▏     | 41572/100000 [12:29:41<9:29:40,  1.71it/s]
Train steps ... :  42%|████▏     | 41573/100000 [12:29:42<9:30:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41574/100000 [12:29:43<9:30:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41575/100000 [12:29:43<9:30:11,  1.71it/s]Step... (41575 / 100000 | Loss: 0.8458901047706604, Learning Rate: 5.871859296482413e-05)
+
                                                                             
Step... (41575 / 100000 | Loss: 0.8844505548477173, Learning Rate: 5.871859296482413e-05)
+
Train steps ... :  42%|████▏     | 41575/100000 [12:29:43<9:30:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41576/100000 [12:29:44<9:30:31,  1.71it/s]
Train steps ... :  42%|████▏     | 41577/100000 [12:29:44<9:30:52,  1.71it/s]
Train steps ... :  42%|████▏     | 41578/100000 [12:29:45<9:30:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41579/100000 [12:29:45<9:30:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41580/100000 [12:29:46<9:29:48,  1.71it/s]
Train steps ... :  42%|████▏     | 41581/100000 [12:29:47<9:28:47,  1.71it/s]
Train steps ... :  42%|████▏     | 41582/100000 [12:29:47<9:28:40,  1.71it/s]
Train steps ... :  42%|████▏     | 41583/100000 [12:29:48<9:29:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41584/100000 [12:29:48<9:30:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41585/100000 [12:29:49<9:29:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41586/100000 [12:29:50<9:29:46,  1.71it/s]
Train steps ... :  42%|████▏     | 41587/100000 [12:29:50<9:30:56,  1.71it/s]
Train steps ... :  42%|████▏     | 41588/100000 [12:29:51<9:30:55,  1.71it/s]
Train steps ... :  42%|████▏     | 41589/100000 [12:29:51<9:31:06,  1.70it/s]
Train steps ... :  42%|████▏     | 41590/100000 [12:29:52<9:30:04,  1.71it/s]
Train steps ... :  42%|████▏     | 41591/100000 [12:29:52<9:29:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41592/100000 [12:29:53<9:29:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41593/100000 [12:29:54<9:29:59,  1.71it/s]
Train steps ... :  42%|████▏     | 41594/100000 [12:29:54<9:29:18,  1.71it/s]
Train steps ... :  42%|████▏     | 41595/100000 [12:29:55<9:29:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41596/100000 [12:29:55<9:29:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41597/100000 [12:29:56<9:28:51,  1.71it/s]
Train steps ... :  42%|████▏     | 41598/100000 [12:29:57<9:28:47,  1.71it/s]
Train steps ... :  42%|████▏     | 41599/100000 [12:29:57<9:28:31,  1.71it/s]
Train steps ... :  42%|████▏     | 41600/100000 [12:29:58<9:28:44,  1.71it/s]Step... (41600 / 100000 | Loss: 0.8528699278831482, Learning Rate: 5.869346733668342e-05)
+
                                                                             
Step... (41600 / 100000 | Loss: 0.5763496160507202, Learning Rate: 5.869346733668342e-05)
+
Train steps ... :  42%|████▏     | 41600/100000 [12:29:58<9:28:44,  1.71it/s]
Train steps ... :  42%|████▏     | 41601/100000 [12:29:58<9:29:08,  1.71it/s]
Train steps ... :  42%|████▏     | 41602/100000 [12:29:59<9:28:55,  1.71it/s]
Train steps ... :  42%|████▏     | 41603/100000 [12:29:59<9:28:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41604/100000 [12:30:00<9:28:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41605/100000 [12:30:01<9:28:18,  1.71it/s]
Train steps ... :  42%|████▏     | 41606/100000 [12:30:01<9:30:03,  1.71it/s]
Train steps ... :  42%|████▏     | 41607/100000 [12:30:02<9:29:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41608/100000 [12:30:02<9:29:06,  1.71it/s]
Train steps ... :  42%|████▏     | 41609/100000 [12:30:03<9:29:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41610/100000 [12:30:04<9:28:24,  1.71it/s]
Train steps ... :  42%|████▏     | 41611/100000 [12:30:04<9:28:20,  1.71it/s]
Train steps ... :  42%|████▏     | 41612/100000 [12:30:05<9:27:56,  1.71it/s]
Train steps ... :  42%|████▏     | 41613/100000 [12:30:05<9:27:52,  1.71it/s]
Train steps ... :  42%|████▏     | 41614/100000 [12:30:06<9:28:22,  1.71it/s]
Train steps ... :  42%|████▏     | 41615/100000 [12:30:06<9:28:16,  1.71it/s]
Train steps ... :  42%|████▏     | 41616/100000 [12:30:07<9:28:29,  1.71it/s]
Train steps ... :  42%|████▏     | 41617/100000 [12:30:08<9:28:09,  1.71it/s]
Train steps ... :  42%|████▏     | 41618/100000 [12:30:08<9:28:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41619/100000 [12:30:09<9:28:12,  1.71it/s]
Train steps ... :  42%|████▏     | 41620/100000 [12:30:09<9:28:03,  1.71it/s]
Train steps ... :  42%|████▏     | 41621/100000 [12:30:10<9:28:36,  1.71it/s]
Train steps ... :  42%|████▏     | 41622/100000 [12:30:11<9:28:04,  1.71it/s]
Train steps ... :  42%|████▏     | 41623/100000 [12:30:11<9:27:58,  1.71it/s]
Train steps ... :  42%|████▏     | 41624/100000 [12:30:12<9:28:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41625/100000 [12:30:12<9:28:53,  1.71it/s]Step... (41625 / 100000 | Loss: 0.8344874382019043, Learning Rate: 5.8668341708542716e-05)
+
                                                                             
Step... (41625 / 100000 | Loss: 0.8549162149429321, Learning Rate: 5.8668341708542716e-05)
+
Train steps ... :  42%|████▏     | 41625/100000 [12:30:13<9:28:53,  1.71it/s]
Train steps ... :  42%|████▏     | 41626/100000 [12:30:13<9:29:36,  1.71it/s]
Train steps ... :  42%|████▏     | 41627/100000 [12:30:14<9:29:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41628/100000 [12:30:14<9:29:13,  1.71it/s]
Train steps ... :  42%|████▏     | 41629/100000 [12:30:15<9:28:27,  1.71it/s]
Train steps ... :  42%|████▏     | 41630/100000 [12:30:15<9:28:43,  1.71it/s]
Train steps ... :  42%|████▏     | 41631/100000 [12:30:16<9:29:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41632/100000 [12:30:16<9:28:30,  1.71it/s]
Train steps ... :  42%|████▏     | 41633/100000 [12:30:17<9:28:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41634/100000 [12:30:18<9:28:27,  1.71it/s]
Train steps ... :  42%|████▏     | 41635/100000 [12:30:18<9:28:12,  1.71it/s]
Train steps ... :  42%|████▏     | 41636/100000 [12:30:19<9:28:04,  1.71it/s]
Train steps ... :  42%|████▏     | 41637/100000 [12:30:19<9:27:51,  1.71it/s]
Train steps ... :  42%|████▏     | 41638/100000 [12:30:20<9:28:43,  1.71it/s]
Train steps ... :  42%|████▏     | 41639/100000 [12:30:21<9:29:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41640/100000 [12:30:21<9:28:51,  1.71it/s]
Train steps ... :  42%|████▏     | 41641/100000 [12:30:22<9:28:13,  1.71it/s]
Train steps ... :  42%|████▏     | 41642/100000 [12:30:22<9:28:00,  1.71it/s]
Train steps ... :  42%|████▏     | 41643/100000 [12:30:23<9:28:53,  1.71it/s]
Train steps ... :  42%|████▏     | 41644/100000 [12:30:23<9:28:41,  1.71it/s]
Train steps ... :  42%|████▏     | 41645/100000 [12:30:24<9:28:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41646/100000 [12:30:25<9:28:55,  1.71it/s]
Train steps ... :  42%|████▏     | 41647/100000 [12:30:25<9:28:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41648/100000 [12:30:26<9:28:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41649/100000 [12:30:26<9:28:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41650/100000 [12:30:27<9:28:29,  1.71it/s]Step... (41650 / 100000 | Loss: 1.143481969833374, Learning Rate: 5.8643216080402005e-05)
+
                                                                             
Step... (41650 / 100000 | Loss: 0.7359275817871094, Learning Rate: 5.8643216080402005e-05)
+
Train steps ... :  42%|████▏     | 41650/100000 [12:30:27<9:28:29,  1.71it/s]
Train steps ... :  42%|████▏     | 41651/100000 [12:30:28<9:28:33,  1.71it/s]
Train steps ... :  42%|████▏     | 41652/100000 [12:30:28<9:27:41,  1.71it/s]
Train steps ... :  42%|████▏     | 41653/100000 [12:30:29<9:27:51,  1.71it/s]
Train steps ... :  42%|████▏     | 41654/100000 [12:30:29<9:28:17,  1.71it/s]
Train steps ... :  42%|████▏     | 41655/100000 [12:30:30<9:27:59,  1.71it/s]
Train steps ... :  42%|████▏     | 41656/100000 [12:30:30<9:28:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41657/100000 [12:30:31<9:28:36,  1.71it/s]
Train steps ... :  42%|████▏     | 41658/100000 [12:30:32<9:28:53,  1.71it/s]
Train steps ... :  42%|████▏     | 41659/100000 [12:30:32<9:28:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41660/100000 [12:30:33<9:28:29,  1.71it/s]
Train steps ... :  42%|████▏     | 41661/100000 [12:30:33<9:28:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41662/100000 [12:30:34<9:28:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41663/100000 [12:30:35<9:28:17,  1.71it/s]
Train steps ... :  42%|████▏     | 41664/100000 [12:30:35<9:28:47,  1.71it/s]
Train steps ... :  42%|████▏     | 41665/100000 [12:30:36<9:28:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41666/100000 [12:30:36<9:27:46,  1.71it/s]
Train steps ... :  42%|████▏     | 41667/100000 [12:30:37<9:27:51,  1.71it/s]
Train steps ... :  42%|████▏     | 41668/100000 [12:30:37<9:28:50,  1.71it/s]
Train steps ... :  42%|████▏     | 41669/100000 [12:30:38<9:27:59,  1.71it/s]
Train steps ... :  42%|████▏     | 41670/100000 [12:30:39<9:28:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41671/100000 [12:30:39<9:27:46,  1.71it/s]
Train steps ... :  42%|████▏     | 41672/100000 [12:30:40<9:27:48,  1.71it/s]
Train steps ... :  42%|████▏     | 41673/100000 [12:30:40<9:28:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41674/100000 [12:30:41<9:27:41,  1.71it/s]
Train steps ... :  42%|████▏     | 41675/100000 [12:30:42<9:27:35,  1.71it/s]Step... (41675 / 100000 | Loss: 0.6641148328781128, Learning Rate: 5.861809045226131e-05)
+
                                                                             
Step... (41675 / 100000 | Loss: 0.7586590051651001, Learning Rate: 5.861809045226131e-05)
+
Train steps ... :  42%|████▏     | 41675/100000 [12:30:42<9:27:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41676/100000 [12:30:42<9:28:40,  1.71it/s]
Train steps ... :  42%|████▏     | 41677/100000 [12:30:43<9:29:07,  1.71it/s]
Train steps ... :  42%|████▏     | 41678/100000 [12:30:43<9:29:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41679/100000 [12:30:44<9:28:43,  1.71it/s]
Train steps ... :  42%|████▏     | 41680/100000 [12:30:44<9:28:15,  1.71it/s]
Train steps ... :  42%|████▏     | 41681/100000 [12:30:45<9:28:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41682/100000 [12:30:46<9:28:39,  1.71it/s]
Train steps ... :  42%|████▏     | 41683/100000 [12:30:46<9:28:09,  1.71it/s]
Train steps ... :  42%|████▏     | 41684/100000 [12:30:47<9:28:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41685/100000 [12:30:47<9:28:52,  1.71it/s]
Train steps ... :  42%|████▏     | 41686/100000 [12:30:48<9:28:29,  1.71it/s]
Train steps ... :  42%|████▏     | 41687/100000 [12:30:49<9:28:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41688/100000 [12:30:49<9:28:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41689/100000 [12:30:50<9:27:37,  1.71it/s]
Train steps ... :  42%|████▏     | 41690/100000 [12:30:50<9:27:38,  1.71it/s]
Train steps ... :  42%|████▏     | 41691/100000 [12:30:51<9:27:29,  1.71it/s]
Train steps ... :  42%|████▏     | 41692/100000 [12:30:52<9:28:04,  1.71it/s]
Train steps ... :  42%|████▏     | 41693/100000 [12:30:52<9:27:47,  1.71it/s]
Train steps ... :  42%|████▏     | 41694/100000 [12:30:53<9:27:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41695/100000 [12:30:53<9:27:07,  1.71it/s]
Train steps ... :  42%|████▏     | 41696/100000 [12:30:54<9:27:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41697/100000 [12:30:54<9:27:18,  1.71it/s]
Train steps ... :  42%|████▏     | 41698/100000 [12:30:55<9:27:29,  1.71it/s]
Train steps ... :  42%|████▏     | 41699/100000 [12:30:56<9:27:41,  1.71it/s]
Train steps ... :  42%|████▏     | 41700/100000 [12:30:56<9:27:49,  1.71it/s]Step... (41700 / 100000 | Loss: 0.7053974866867065, Learning Rate: 5.859296482412061e-05)
+
                                                                             
Step... (41700 / 100000 | Loss: 0.809008002281189, Learning Rate: 5.859296482412061e-05)
+
Train steps ... :  42%|████▏     | 41700/100000 [12:30:57<9:27:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41701/100000 [12:30:57<9:28:45,  1.71it/s]
Train steps ... :  42%|████▏     | 41702/100000 [12:30:57<9:28:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41703/100000 [12:30:58<9:28:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41704/100000 [12:30:59<9:28:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41705/100000 [12:30:59<9:27:51,  1.71it/s]
Train steps ... :  42%|████▏     | 41706/100000 [12:31:00<9:28:23,  1.71it/s]
Train steps ... :  42%|████▏     | 41707/100000 [12:31:00<9:28:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41708/100000 [12:31:01<9:28:32,  1.71it/s]
Train steps ... :  42%|████▏     | 41709/100000 [12:31:01<9:28:31,  1.71it/s]
Train steps ... :  42%|████▏     | 41710/100000 [12:31:02<9:28:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41711/100000 [12:31:03<9:27:55,  1.71it/s]
Train steps ... :  42%|████▏     | 41712/100000 [12:31:03<9:27:26,  1.71it/s]
Train steps ... :  42%|████▏     | 41713/100000 [12:31:04<9:28:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41714/100000 [12:31:04<9:28:09,  1.71it/s]
Train steps ... :  42%|████▏     | 41715/100000 [12:31:05<9:27:42,  1.71it/s]
Train steps ... :  42%|████▏     | 41716/100000 [12:31:06<9:28:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41717/100000 [12:31:06<9:28:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41718/100000 [12:31:07<9:27:46,  1.71it/s]
Train steps ... :  42%|████▏     | 41719/100000 [12:31:07<9:28:03,  1.71it/s]
Train steps ... :  42%|████▏     | 41720/100000 [12:31:08<9:27:50,  1.71it/s]
Train steps ... :  42%|████▏     | 41721/100000 [12:31:08<9:27:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41722/100000 [12:31:09<9:27:40,  1.71it/s]
Train steps ... :  42%|████▏     | 41723/100000 [12:31:10<9:28:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41724/100000 [12:31:10<9:27:46,  1.71it/s]
Train steps ... :  42%|████▏     | 41725/100000 [12:31:11<9:27:31,  1.71it/s]Step... (41725 / 100000 | Loss: 0.7184252142906189, Learning Rate: 5.85678391959799e-05)
+
                                                                             
Step... (41725 / 100000 | Loss: 0.749024510383606, Learning Rate: 5.85678391959799e-05)
+
Train steps ... :  42%|████▏     | 41725/100000 [12:31:11<9:27:31,  1.71it/s]
Train steps ... :  42%|████▏     | 41726/100000 [12:31:11<9:28:08,  1.71it/s]
Train steps ... :  42%|████▏     | 41727/100000 [12:31:12<9:27:30,  1.71it/s]
Train steps ... :  42%|████▏     | 41728/100000 [12:31:13<9:27:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41729/100000 [12:31:13<9:28:02,  1.71it/s]
Train steps ... :  42%|████▏     | 41730/100000 [12:31:14<9:28:44,  1.71it/s]
Train steps ... :  42%|████▏     | 41731/100000 [12:31:14<9:28:44,  1.71it/s]
Train steps ... :  42%|████▏     | 41732/100000 [12:31:15<9:28:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41733/100000 [12:31:15<9:28:02,  1.71it/s]
Train steps ... :  42%|████▏     | 41734/100000 [12:31:16<9:27:27,  1.71it/s]
Train steps ... :  42%|████▏     | 41735/100000 [12:31:17<9:28:03,  1.71it/s]
Train steps ... :  42%|████▏     | 41736/100000 [12:31:17<9:27:36,  1.71it/s]
Train steps ... :  42%|████▏     | 41737/100000 [12:31:18<9:27:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41738/100000 [12:31:18<9:27:50,  1.71it/s]
Train steps ... :  42%|████▏     | 41739/100000 [12:31:19<9:27:41,  1.71it/s]
Train steps ... :  42%|████▏     | 41740/100000 [12:31:20<9:27:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41741/100000 [12:31:20<9:28:07,  1.71it/s]
Train steps ... :  42%|████▏     | 41742/100000 [12:31:21<9:28:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41743/100000 [12:31:21<9:27:45,  1.71it/s]
Train steps ... :  42%|████▏     | 41744/100000 [12:31:22<9:27:27,  1.71it/s]
Train steps ... :  42%|████▏     | 41745/100000 [12:31:22<9:27:03,  1.71it/s]
Train steps ... :  42%|████▏     | 41746/100000 [12:31:23<9:27:13,  1.71it/s]
Train steps ... :  42%|████▏     | 41747/100000 [12:31:24<9:27:33,  1.71it/s]
Train steps ... :  42%|████▏     | 41748/100000 [12:31:24<9:27:18,  1.71it/s]
Train steps ... :  42%|████▏     | 41749/100000 [12:31:25<9:27:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41750/100000 [12:31:25<9:27:11,  1.71it/s]Step... (41750 / 100000 | Loss: 0.8618513345718384, Learning Rate: 5.8542713567839206e-05)
+
                                                                             
Step... (41750 / 100000 | Loss: 0.8172416687011719, Learning Rate: 5.8542713567839206e-05)
+
Train steps ... :  42%|████▏     | 41750/100000 [12:31:26<9:27:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41751/100000 [12:31:26<9:28:09,  1.71it/s]
Train steps ... :  42%|████▏     | 41752/100000 [12:31:27<9:27:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41753/100000 [12:31:27<9:27:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41754/100000 [12:31:28<9:27:45,  1.71it/s]
Train steps ... :  42%|████▏     | 41755/100000 [12:31:28<9:28:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41756/100000 [12:31:29<9:28:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41757/100000 [12:31:30<9:27:51,  1.71it/s]
Train steps ... :  42%|████▏     | 41758/100000 [12:31:30<9:27:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41759/100000 [12:31:31<9:26:58,  1.71it/s]
Train steps ... :  42%|████▏     | 41760/100000 [12:31:31<9:27:07,  1.71it/s]
Train steps ... :  42%|████▏     | 41761/100000 [12:31:32<9:27:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41762/100000 [12:31:32<9:27:28,  1.71it/s]
Train steps ... :  42%|████▏     | 41763/100000 [12:31:33<9:27:36,  1.71it/s]
Train steps ... :  42%|████▏     | 41764/100000 [12:31:34<9:28:08,  1.71it/s]
Train steps ... :  42%|████▏     | 41765/100000 [12:31:34<9:28:27,  1.71it/s]
Train steps ... :  42%|████▏     | 41766/100000 [12:31:35<9:28:43,  1.71it/s]
Train steps ... :  42%|████▏     | 41767/100000 [12:31:35<9:27:56,  1.71it/s]
Train steps ... :  42%|████▏     | 41768/100000 [12:31:36<9:27:40,  1.71it/s]
Train steps ... :  42%|████▏     | 41769/100000 [12:31:37<9:27:50,  1.71it/s]
Train steps ... :  42%|████▏     | 41770/100000 [12:31:37<9:27:57,  1.71it/s]
Train steps ... :  42%|████▏     | 41771/100000 [12:31:38<9:27:18,  1.71it/s]
Train steps ... :  42%|████▏     | 41772/100000 [12:31:38<9:27:33,  1.71it/s]
Train steps ... :  42%|████▏     | 41773/100000 [12:31:39<9:27:28,  1.71it/s]
Train steps ... :  42%|████▏     | 41774/100000 [12:31:39<9:26:58,  1.71it/s]
Train steps ... :  42%|████▏     | 41775/100000 [12:31:40<9:27:07,  1.71it/s]Step... (41775 / 100000 | Loss: 0.737848162651062, Learning Rate: 5.8517587939698495e-05)
+
                                                                             
Step... (41775 / 100000 | Loss: 0.8105188608169556, Learning Rate: 5.8517587939698495e-05)
+
Train steps ... :  42%|████▏     | 41775/100000 [12:31:40<9:27:07,  1.71it/s]
Train steps ... :  42%|████▏     | 41776/100000 [12:31:41<9:27:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41777/100000 [12:31:41<9:27:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41778/100000 [12:31:42<9:28:09,  1.71it/s]
Train steps ... :  42%|████▏     | 41779/100000 [12:31:42<9:28:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41780/100000 [12:31:43<9:27:15,  1.71it/s]
Train steps ... :  42%|████▏     | 41781/100000 [12:31:44<9:27:08,  1.71it/s]
Train steps ... :  42%|████▏     | 41782/100000 [12:31:44<9:27:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41783/100000 [12:31:45<9:27:33,  1.71it/s]
Train steps ... :  42%|████▏     | 41784/100000 [12:31:45<9:27:33,  1.71it/s]
Train steps ... :  42%|████▏     | 41785/100000 [12:31:46<9:27:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41786/100000 [12:31:46<9:28:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41787/100000 [12:31:47<9:27:20,  1.71it/s]
Train steps ... :  42%|████▏     | 41788/100000 [12:31:48<9:28:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41789/100000 [12:31:48<9:27:32,  1.71it/s]
Train steps ... :  42%|████▏     | 41790/100000 [12:31:49<9:28:04,  1.71it/s]
Train steps ... :  42%|████▏     | 41791/100000 [12:31:49<9:28:18,  1.71it/s]
Train steps ... :  42%|████▏     | 41792/100000 [12:31:50<9:27:38,  1.71it/s]
Train steps ... :  42%|████▏     | 41793/100000 [12:31:51<9:27:39,  1.71it/s]
Train steps ... :  42%|████▏     | 41794/100000 [12:31:51<9:27:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41795/100000 [12:31:52<9:27:31,  1.71it/s]
Train steps ... :  42%|████▏     | 41796/100000 [12:31:52<9:26:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41797/100000 [12:31:53<9:26:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41798/100000 [12:31:53<9:27:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41799/100000 [12:31:54<9:27:30,  1.71it/s]
Train steps ... :  42%|████▏     | 41800/100000 [12:31:55<9:26:48,  1.71it/s]Step... (41800 / 100000 | Loss: 0.7823370695114136, Learning Rate: 5.849246231155779e-05)
+
                                                                             
Step... (41800 / 100000 | Loss: 0.7590306401252747, Learning Rate: 5.849246231155779e-05)
+
Train steps ... :  42%|████▏     | 41800/100000 [12:31:55<9:26:48,  1.71it/s]
Train steps ... :  42%|████▏     | 41801/100000 [12:31:55<9:27:06,  1.71it/s]
Train steps ... :  42%|████▏     | 41802/100000 [12:31:56<9:26:36,  1.71it/s]
Train steps ... :  42%|████▏     | 41803/100000 [12:31:56<9:27:16,  1.71it/s]
Train steps ... :  42%|████▏     | 41804/100000 [12:31:57<9:27:40,  1.71it/s]
Train steps ... :  42%|████▏     | 41805/100000 [12:31:58<9:27:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41806/100000 [12:31:58<9:26:39,  1.71it/s]
Train steps ... :  42%|████▏     | 41807/100000 [12:31:59<9:26:40,  1.71it/s]
Train steps ... :  42%|████▏     | 41808/100000 [12:31:59<9:26:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41809/100000 [12:32:00<9:26:30,  1.71it/s]
Train steps ... :  42%|████▏     | 41810/100000 [12:32:01<9:26:27,  1.71it/s]
Train steps ... :  42%|████▏     | 41811/100000 [12:32:01<9:26:24,  1.71it/s]
Train steps ... :  42%|████▏     | 41812/100000 [12:32:02<9:26:45,  1.71it/s]
Train steps ... :  42%|████▏     | 41813/100000 [12:32:02<9:26:53,  1.71it/s]
Train steps ... :  42%|████▏     | 41814/100000 [12:32:03<9:26:32,  1.71it/s]
Train steps ... :  42%|████▏     | 41815/100000 [12:32:03<9:26:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41816/100000 [12:32:04<9:27:15,  1.71it/s]
Train steps ... :  42%|████▏     | 41817/100000 [12:32:05<9:26:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41818/100000 [12:32:05<9:26:44,  1.71it/s]
Train steps ... :  42%|████▏     | 41819/100000 [12:32:06<9:26:40,  1.71it/s]
Train steps ... :  42%|████▏     | 41820/100000 [12:32:06<9:26:17,  1.71it/s]
Train steps ... :  42%|████▏     | 41821/100000 [12:32:07<9:26:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41822/100000 [12:32:08<9:26:02,  1.71it/s]
Train steps ... :  42%|████▏     | 41823/100000 [12:32:08<9:26:50,  1.71it/s]
Train steps ... :  42%|████▏     | 41824/100000 [12:32:09<9:27:12,  1.71it/s]
Train steps ... :  42%|████▏     | 41825/100000 [12:32:09<9:27:43,  1.71it/s]Step... (41825 / 100000 | Loss: 0.8305652141571045, Learning Rate: 5.846733668341708e-05)
+
                                                                             
Step... (41825 / 100000 | Loss: 0.8353204131126404, Learning Rate: 5.846733668341708e-05)
+
Train steps ... :  42%|████▏     | 41825/100000 [12:32:10<9:27:43,  1.71it/s]
Train steps ... :  42%|████▏     | 41826/100000 [12:32:10<9:27:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41827/100000 [12:32:10<9:26:42,  1.71it/s]
Train steps ... :  42%|████▏     | 41828/100000 [12:32:11<9:26:23,  1.71it/s]
Train steps ... :  42%|████▏     | 41829/100000 [12:32:12<9:26:17,  1.71it/s]
Train steps ... :  42%|████▏     | 41830/100000 [12:32:12<9:26:38,  1.71it/s]
Train steps ... :  42%|████▏     | 41831/100000 [12:32:13<9:26:47,  1.71it/s]
Train steps ... :  42%|████▏     | 41832/100000 [12:32:13<9:26:28,  1.71it/s]
Train steps ... :  42%|████▏     | 41833/100000 [12:32:14<9:26:37,  1.71it/s]
Train steps ... :  42%|████▏     | 41834/100000 [12:32:15<9:26:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41835/100000 [12:32:15<9:26:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41836/100000 [12:32:16<9:26:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41837/100000 [12:32:16<9:25:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41838/100000 [12:32:17<9:26:16,  1.71it/s]
Train steps ... :  42%|████▏     | 41839/100000 [12:32:17<9:26:57,  1.71it/s]
Train steps ... :  42%|████▏     | 41840/100000 [12:32:18<9:26:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41841/100000 [12:32:19<9:27:13,  1.71it/s]
Train steps ... :  42%|████▏     | 41842/100000 [12:32:19<9:26:42,  1.71it/s]
Train steps ... :  42%|████▏     | 41843/100000 [12:32:20<9:26:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41844/100000 [12:32:20<9:26:38,  1.71it/s]
Train steps ... :  42%|████▏     | 41845/100000 [12:32:21<9:26:24,  1.71it/s]
Train steps ... :  42%|████▏     | 41846/100000 [12:32:22<9:26:48,  1.71it/s]
Train steps ... :  42%|████▏     | 41847/100000 [12:32:22<9:27:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41848/100000 [12:32:23<9:26:48,  1.71it/s]
Train steps ... :  42%|████▏     | 41849/100000 [12:32:23<9:26:18,  1.71it/s]
Train steps ... :  42%|████▏     | 41850/100000 [12:32:24<9:27:14,  1.71it/s]Step... (41850 / 100000 | Loss: 0.5891907811164856, Learning Rate: 5.8442211055276385e-05)
+
                                                                             
Step... (41850 / 100000 | Loss: 1.1943695545196533, Learning Rate: 5.8442211055276385e-05)
+
Train steps ... :  42%|████▏     | 41850/100000 [12:32:24<9:27:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41851/100000 [12:32:24<9:27:07,  1.71it/s]
Train steps ... :  42%|████▏     | 41852/100000 [12:32:25<9:27:43,  1.71it/s]
Train steps ... :  42%|████▏     | 41853/100000 [12:32:26<9:27:43,  1.71it/s]
Train steps ... :  42%|████▏     | 41854/100000 [12:32:26<9:27:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41855/100000 [12:32:27<9:27:12,  1.71it/s]
Train steps ... :  42%|████▏     | 41856/100000 [12:32:27<9:26:43,  1.71it/s]
Train steps ... :  42%|████▏     | 41857/100000 [12:32:28<9:26:13,  1.71it/s]
Train steps ... :  42%|████▏     | 41858/100000 [12:32:29<9:26:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41859/100000 [12:32:29<9:25:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41860/100000 [12:32:30<9:25:48,  1.71it/s]
Train steps ... :  42%|████▏     | 41861/100000 [12:32:30<9:26:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41862/100000 [12:32:31<9:26:00,  1.71it/s]
Train steps ... :  42%|████▏     | 41863/100000 [12:32:31<9:25:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41864/100000 [12:32:32<9:25:50,  1.71it/s]
Train steps ... :  42%|████▏     | 41865/100000 [12:32:33<9:26:22,  1.71it/s]
Train steps ... :  42%|████▏     | 41866/100000 [12:32:33<9:26:18,  1.71it/s]
Train steps ... :  42%|████▏     | 41867/100000 [12:32:34<9:26:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41868/100000 [12:32:34<9:25:40,  1.71it/s]
Train steps ... :  42%|████▏     | 41869/100000 [12:32:35<9:25:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41870/100000 [12:32:36<9:26:24,  1.71it/s]
Train steps ... :  42%|████▏     | 41871/100000 [12:32:36<9:26:28,  1.71it/s]
Train steps ... :  42%|████▏     | 41872/100000 [12:32:37<9:26:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41873/100000 [12:32:37<9:27:07,  1.71it/s]
Train steps ... :  42%|████▏     | 41874/100000 [12:32:38<9:26:59,  1.71it/s]
Train steps ... :  42%|████▏     | 41875/100000 [12:32:39<9:26:29,  1.71it/s]Step... (41875 / 100000 | Loss: 1.2386473417282104, Learning Rate: 5.8417085427135675e-05)
+
                                                                             
Step... (41875 / 100000 | Loss: 1.0593721866607666, Learning Rate: 5.8417085427135675e-05)
+
Train steps ... :  42%|████▏     | 41875/100000 [12:32:39<9:26:29,  1.71it/s]
Train steps ... :  42%|████▏     | 41876/100000 [12:32:39<9:27:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41877/100000 [12:32:40<9:27:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41878/100000 [12:32:40<9:26:31,  1.71it/s]
Train steps ... :  42%|████▏     | 41879/100000 [12:32:41<9:27:33,  1.71it/s]
Train steps ... :  42%|████▏     | 41880/100000 [12:32:41<9:26:55,  1.71it/s]
Train steps ... :  42%|████▏     | 41881/100000 [12:32:42<9:27:11,  1.71it/s]
Train steps ... :  42%|████▏     | 41882/100000 [12:32:43<9:26:56,  1.71it/s]
Train steps ... :  42%|████▏     | 41883/100000 [12:32:43<9:26:38,  1.71it/s]
Train steps ... :  42%|████▏     | 41884/100000 [12:32:44<9:27:09,  1.71it/s]
Train steps ... :  42%|████▏     | 41885/100000 [12:32:44<9:26:15,  1.71it/s]
Train steps ... :  42%|████▏     | 41886/100000 [12:32:45<9:26:07,  1.71it/s]
Train steps ... :  42%|████▏     | 41887/100000 [12:32:46<9:25:57,  1.71it/s]
Train steps ... :  42%|████▏     | 41888/100000 [12:32:46<9:26:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41889/100000 [12:32:47<9:25:41,  1.71it/s]
Train steps ... :  42%|████▏     | 41890/100000 [12:32:47<9:26:17,  1.71it/s]
Train steps ... :  42%|████▏     | 41891/100000 [12:32:48<9:26:08,  1.71it/s]
Train steps ... :  42%|████▏     | 41892/100000 [12:32:48<9:26:02,  1.71it/s]
Train steps ... :  42%|████▏     | 41893/100000 [12:32:49<9:25:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41894/100000 [12:32:50<9:25:26,  1.71it/s]
Train steps ... :  42%|████▏     | 41895/100000 [12:32:50<9:25:29,  1.71it/s]
Train steps ... :  42%|████▏     | 41896/100000 [12:32:51<9:25:42,  1.71it/s]
Train steps ... :  42%|████▏     | 41897/100000 [12:32:51<9:25:36,  1.71it/s]
Train steps ... :  42%|████▏     | 41898/100000 [12:32:52<9:25:38,  1.71it/s]
Train steps ... :  42%|████▏     | 41899/100000 [12:32:53<9:25:51,  1.71it/s]
Train steps ... :  42%|████▏     | 41900/100000 [12:32:53<9:26:08,  1.71it/s]Step... (41900 / 100000 | Loss: 1.232933521270752, Learning Rate: 5.839195979899498e-05)
+
                                                                             
Step... (41900 / 100000 | Loss: 0.6987292766571045, Learning Rate: 5.839195979899498e-05)
+
Train steps ... :  42%|████▏     | 41900/100000 [12:32:53<9:26:08,  1.71it/s]
Train steps ... :  42%|████▏     | 41901/100000 [12:32:54<9:25:48,  1.71it/s]
Train steps ... :  42%|████▏     | 41902/100000 [12:32:54<9:25:19,  1.71it/s]
Train steps ... :  42%|████▏     | 41903/100000 [12:32:55<9:25:51,  1.71it/s]
Train steps ... :  42%|████▏     | 41904/100000 [12:32:55<9:26:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41905/100000 [12:32:56<9:25:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41906/100000 [12:32:57<9:26:22,  1.71it/s]
Train steps ... :  42%|████▏     | 41907/100000 [12:32:57<9:26:46,  1.71it/s]
Train steps ... :  42%|████▏     | 41908/100000 [12:32:58<9:26:07,  1.71it/s]
Train steps ... :  42%|████▏     | 41909/100000 [12:32:58<9:26:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41910/100000 [12:32:59<9:26:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41911/100000 [12:33:00<9:26:13,  1.71it/s]
Train steps ... :  42%|████▏     | 41912/100000 [12:33:00<9:26:38,  1.71it/s]
Train steps ... :  42%|████▏     | 41913/100000 [12:33:01<9:26:39,  1.71it/s]
Train steps ... :  42%|████▏     | 41914/100000 [12:33:01<9:26:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41915/100000 [12:33:02<9:26:52,  1.71it/s]
Train steps ... :  42%|████▏     | 41916/100000 [12:33:02<9:27:00,  1.71it/s]
Train steps ... :  42%|████▏     | 41917/100000 [12:33:03<9:25:55,  1.71it/s]
Train steps ... :  42%|████▏     | 41918/100000 [12:33:04<9:25:37,  1.71it/s]
Train steps ... :  42%|████▏     | 41919/100000 [12:33:04<9:25:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41920/100000 [12:33:05<9:25:57,  1.71it/s]
Train steps ... :  42%|████▏     | 41921/100000 [12:33:05<9:26:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41922/100000 [12:33:06<9:26:17,  1.71it/s]
Train steps ... :  42%|████▏     | 41923/100000 [12:33:07<9:25:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41924/100000 [12:33:07<9:25:22,  1.71it/s]
Train steps ... :  42%|████▏     | 41925/100000 [12:33:08<9:25:26,  1.71it/s]Step... (41925 / 100000 | Loss: 0.719221830368042, Learning Rate: 5.836683417085428e-05)
+
                                                                             
Step... (41925 / 100000 | Loss: 0.968509316444397, Learning Rate: 5.836683417085428e-05)
+
Train steps ... :  42%|████▏     | 41925/100000 [12:33:08<9:25:26,  1.71it/s]
Train steps ... :  42%|████▏     | 41926/100000 [12:33:08<9:25:45,  1.71it/s]
Train steps ... :  42%|████▏     | 41927/100000 [12:33:09<9:25:31,  1.71it/s]
Train steps ... :  42%|████▏     | 41928/100000 [12:33:09<9:25:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41929/100000 [12:33:10<9:25:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41930/100000 [12:33:11<9:25:45,  1.71it/s]
Train steps ... :  42%|████▏     | 41931/100000 [12:33:11<9:25:57,  1.71it/s]
Train steps ... :  42%|████▏     | 41932/100000 [12:33:12<9:25:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41933/100000 [12:33:12<9:25:35,  1.71it/s]
Train steps ... :  42%|████▏     | 41934/100000 [12:33:13<9:25:49,  1.71it/s]
Train steps ... :  42%|████▏     | 41935/100000 [12:33:14<9:25:59,  1.71it/s]
Train steps ... :  42%|████▏     | 41936/100000 [12:33:14<9:25:25,  1.71it/s]
Train steps ... :  42%|████▏     | 41937/100000 [12:33:15<9:25:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41938/100000 [12:33:15<9:25:31,  1.71it/s]
Train steps ... :  42%|████▏     | 41939/100000 [12:33:16<9:25:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41940/100000 [12:33:17<9:25:29,  1.71it/s]
Train steps ... :  42%|████▏     | 41941/100000 [12:33:17<9:25:22,  1.71it/s]
Train steps ... :  42%|████▏     | 41942/100000 [12:33:18<9:25:13,  1.71it/s]
Train steps ... :  42%|████▏     | 41943/100000 [12:33:18<9:25:10,  1.71it/s]
Train steps ... :  42%|████▏     | 41944/100000 [12:33:19<9:25:08,  1.71it/s]
Train steps ... :  42%|████▏     | 41945/100000 [12:33:19<9:25:12,  1.71it/s]
Train steps ... :  42%|████▏     | 41946/100000 [12:33:20<9:25:04,  1.71it/s]
Train steps ... :  42%|████▏     | 41947/100000 [12:33:21<9:25:02,  1.71it/s]
Train steps ... :  42%|████▏     | 41948/100000 [12:33:21<9:25:58,  1.71it/s]
Train steps ... :  42%|████▏     | 41949/100000 [12:33:22<9:25:32,  1.71it/s]
Train steps ... :  42%|████▏     | 41950/100000 [12:33:22<9:26:08,  1.71it/s]Step... (41950 / 100000 | Loss: 1.136063575744629, Learning Rate: 5.834170854271357e-05)
+
                                                                             
Step... (41950 / 100000 | Loss: 0.8760538697242737, Learning Rate: 5.834170854271357e-05)
+
Train steps ... :  42%|████▏     | 41950/100000 [12:33:23<9:26:08,  1.71it/s]
Train steps ... :  42%|████▏     | 41951/100000 [12:33:23<9:26:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41952/100000 [12:33:24<9:25:34,  1.71it/s]
Train steps ... :  42%|████▏     | 41953/100000 [12:33:24<9:25:45,  1.71it/s]
Train steps ... :  42%|████▏     | 41954/100000 [12:33:25<9:25:22,  1.71it/s]
Train steps ... :  42%|████▏     | 41955/100000 [12:33:25<9:25:06,  1.71it/s]
Train steps ... :  42%|████▏     | 41956/100000 [12:33:26<9:25:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41957/100000 [12:33:26<9:25:24,  1.71it/s]
Train steps ... :  42%|████▏     | 41958/100000 [12:33:27<9:26:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41959/100000 [12:33:28<9:25:46,  1.71it/s]
Train steps ... :  42%|████▏     | 41960/100000 [12:33:28<9:25:50,  1.71it/s]
Train steps ... :  42%|████▏     | 41961/100000 [12:33:29<9:25:31,  1.71it/s]
Train steps ... :  42%|████▏     | 41962/100000 [12:33:29<9:25:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41963/100000 [12:33:30<9:25:45,  1.71it/s]
Train steps ... :  42%|████▏     | 41964/100000 [12:33:31<9:25:57,  1.71it/s]
Train steps ... :  42%|████▏     | 41965/100000 [12:33:31<9:25:37,  1.71it/s]
Train steps ... :  42%|███��▏     | 41966/100000 [12:33:32<9:25:21,  1.71it/s]
Train steps ... :  42%|████▏     | 41967/100000 [12:33:32<9:25:45,  1.71it/s]
Train steps ... :  42%|████▏     | 41968/100000 [12:33:33<9:25:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41969/100000 [12:33:33<9:25:12,  1.71it/s]
Train steps ... :  42%|████▏     | 41970/100000 [12:33:34<9:25:36,  1.71it/s]
Train steps ... :  42%|████▏     | 41971/100000 [12:33:35<9:25:26,  1.71it/s]
Train steps ... :  42%|████▏     | 41972/100000 [12:33:35<9:25:46,  1.71it/s]
Train steps ... :  42%|████▏     | 41973/100000 [12:33:36<9:25:41,  1.71it/s]
Train steps ... :  42%|████▏     | 41974/100000 [12:33:36<9:25:31,  1.71it/s]
Train steps ... :  42%|████▏     | 41975/100000 [12:33:37<9:25:51,  1.71it/s]Step... (41975 / 100000 | Loss: 0.7347231507301331, Learning Rate: 5.831658291457287e-05)
+
                                                                             
Step... (41975 / 100000 | Loss: 0.7080293893814087, Learning Rate: 5.831658291457287e-05)
+
Train steps ... :  42%|████▏     | 41975/100000 [12:33:37<9:25:51,  1.71it/s]
Train steps ... :  42%|████▏     | 41976/100000 [12:33:38<9:25:22,  1.71it/s]
Train steps ... :  42%|████▏     | 41977/100000 [12:33:38<9:25:44,  1.71it/s]
Train steps ... :  42%|████▏     | 41978/100000 [12:33:39<9:25:07,  1.71it/s]
Train steps ... :  42%|████▏     | 41979/100000 [12:33:39<9:25:04,  1.71it/s]
Train steps ... :  42%|████▏     | 41980/100000 [12:33:40<9:25:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41981/100000 [12:33:40<9:24:50,  1.71it/s]
Train steps ... :  42%|████▏     | 41982/100000 [12:33:41<9:25:36,  1.71it/s]
Train steps ... :  42%|████▏     | 41983/100000 [12:33:42<9:25:01,  1.71it/s]
Train steps ... :  42%|████▏     | 41984/100000 [12:33:42<9:25:05,  1.71it/s]
Train steps ... :  42%|████▏     | 41985/100000 [12:33:43<9:25:32,  1.71it/s]
Train steps ... :  42%|████▏     | 41986/100000 [12:33:43<9:25:09,  1.71it/s]
Train steps ... :  42%|████▏     | 41987/100000 [12:33:44<9:24:59,  1.71it/s]
Train steps ... :  42%|████▏     | 41988/100000 [12:33:45<9:25:22,  1.71it/s]
Train steps ... :  42%|████▏     | 41989/100000 [12:33:45<9:24:56,  1.71it/s]
Train steps ... :  42%|████▏     | 41990/100000 [12:33:46<9:26:14,  1.71it/s]
Train steps ... :  42%|████▏     | 41991/100000 [12:33:46<9:26:18,  1.71it/s]
Train steps ... :  42%|████▏     | 41992/100000 [12:33:47<9:25:40,  1.71it/s]
Train steps ... :  42%|████▏     | 41993/100000 [12:33:47<9:25:46,  1.71it/s]
Train steps ... :  42%|████▏     | 41994/100000 [12:33:48<9:25:58,  1.71it/s]
Train steps ... :  42%|████▏     | 41995/100000 [12:33:49<9:24:54,  1.71it/s]
Train steps ... :  42%|████▏     | 41996/100000 [12:33:49<9:25:18,  1.71it/s]
Train steps ... :  42%|████▏     | 41997/100000 [12:33:50<9:24:47,  1.71it/s]
Train steps ... :  42%|████▏     | 41998/100000 [12:33:50<9:24:43,  1.71it/s]
Train steps ... :  42%|████▏     | 41999/100000 [12:33:51<9:24:54,  1.71it/s]
Train steps ... :  42%|████▏     | 42000/100000 [12:33:52<9:25:45,  1.71it/s]Step... (42000 / 100000 | Loss: 0.7149822115898132, Learning Rate: 5.829145728643216e-05)
+
                                                                             
Step... (42000 / 100000 | Loss: 0.991937518119812, Learning Rate: 5.829145728643216e-05)
+
Train steps ... :  42%|████▏     | 42000/100000 [12:33:52<9:25:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42001/100000 [12:33:52<9:26:10,  1.71it/s]
Train steps ... :  42%|████▏     | 42002/100000 [12:33:53<9:25:19,  1.71it/s]
Train steps ... :  42%|████▏     | 42003/100000 [12:33:53<9:25:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42004/100000 [12:33:54<9:24:49,  1.71it/s]
Train steps ... :  42%|████▏     | 42005/100000 [12:33:55<9:24:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42006/100000 [12:33:55<9:24:38,  1.71it/s]
Train steps ... :  42%|████▏     | 42007/100000 [12:33:56<9:25:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42008/100000 [12:33:56<9:24:54,  1.71it/s]
Train steps ... :  42%|████▏     | 42009/100000 [12:33:57<9:24:39,  1.71it/s]
Train steps ... :  42%|████▏     | 42010/100000 [12:33:57<9:24:32,  1.71it/s]
Train steps ... :  42%|████▏     | 42011/100000 [12:33:58<9:24:35,  1.71it/s]
Train steps ... :  42%|████▏     | 42012/100000 [12:33:59<9:24:18,  1.71it/s]
Train steps ... :  42%|████▏     | 42013/100000 [12:33:59<9:24:36,  1.71it/s]
Train steps ... :  42%|████▏     | 42014/100000 [12:34:00<9:25:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42015/100000 [12:34:00<9:25:13,  1.71it/s]
Train steps ... :  42%|████▏     | 42016/100000 [12:34:01<9:25:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42017/100000 [12:34:02<9:24:59,  1.71it/s]
Train steps ... :  42%|████▏     | 42018/100000 [12:34:02<9:25:30,  1.71it/s]
Train steps ... :  42%|████▏     | 42019/100000 [12:34:03<9:25:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42020/100000 [12:34:03<9:25:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42021/100000 [12:34:04<9:25:16,  1.71it/s]
Train steps ... :  42%|████▏     | 42022/100000 [12:34:04<9:24:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42023/100000 [12:34:05<9:24:25,  1.71it/s]
Train steps ... :  42%|████▏     | 42024/100000 [12:34:06<9:25:13,  1.71it/s]
Train steps ... :  42%|████▏     | 42025/100000 [12:34:06<9:25:22,  1.71it/s]Step... (42025 / 100000 | Loss: 0.7836665511131287, Learning Rate: 5.826633165829146e-05)
+
                                                                             
Step... (42025 / 100000 | Loss: 0.7319509983062744, Learning Rate: 5.826633165829146e-05)
+
Train steps ... :  42%|████▏     | 42025/100000 [12:34:07<9:25:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42026/100000 [12:34:07<9:24:37,  1.71it/s]
Train steps ... :  42%|████▏     | 42027/100000 [12:34:07<9:25:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42028/100000 [12:34:08<9:25:19,  1.71it/s]
Train steps ... :  42%|████▏     | 42029/100000 [12:34:09<9:25:33,  1.71it/s]
Train steps ... :  42%|████▏     | 42030/100000 [12:34:09<9:24:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42031/100000 [12:34:10<9:24:18,  1.71it/s]
Train steps ... :  42%|████▏     | 42032/100000 [12:34:10<9:25:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42033/100000 [12:34:11<9:24:58,  1.71it/s]
Train steps ... :  42%|████▏     | 42034/100000 [12:34:11<9:25:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42035/100000 [12:34:12<9:25:34,  1.71it/s]
Train steps ... :  42%|████▏     | 42036/100000 [12:34:13<9:25:37,  1.71it/s]
Train steps ... :  42%|████▏     | 42037/100000 [12:34:13<9:24:54,  1.71it/s]
Train steps ... :  42%|████▏     | 42038/100000 [12:34:14<9:24:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42039/100000 [12:34:14<9:24:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42040/100000 [12:34:15<9:24:58,  1.71it/s]
Train steps ... :  42%|████▏     | 42041/100000 [12:34:16<9:24:29,  1.71it/s]
Train steps ... :  42%|████▏     | 42042/100000 [12:34:16<9:24:10,  1.71it/s]
Train steps ... :  42%|████▏     | 42043/100000 [12:34:17<9:24:02,  1.71it/s]
Train steps ... :  42%|████▏     | 42044/100000 [12:34:17<9:24:00,  1.71it/s]
Train steps ... :  42%|████▏     | 42045/100000 [12:34:18<9:24:18,  1.71it/s]
Train steps ... :  42%|████▏     | 42046/100000 [12:34:18<9:24:39,  1.71it/s]
Train steps ... :  42%|████▏     | 42047/100000 [12:34:19<9:24:02,  1.71it/s]
Train steps ... :  42%|████▏     | 42048/100000 [12:34:20<9:23:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42049/100000 [12:34:20<9:24:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42050/100000 [12:34:21<9:23:52,  1.71it/s]Step... (42050 / 100000 | Loss: 1.0694866180419922, Learning Rate: 5.824120603015075e-05)
+
                                                                             
Step... (42050 / 100000 | Loss: 0.9504271745681763, Learning Rate: 5.824120603015075e-05)
+
Train steps ... :  42%|████▏     | 42050/100000 [12:34:21<9:23:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42051/100000 [12:34:21<9:24:10,  1.71it/s]
Train steps ... :  42%|████▏     | 42052/100000 [12:34:22<9:23:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42053/100000 [12:34:23<9:24:33,  1.71it/s]
Train steps ... :  42%|████▏     | 42054/100000 [12:34:23<9:24:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42055/100000 [12:34:24<9:26:07,  1.71it/s]
Train steps ... :  42%|████▏     | 42056/100000 [12:34:24<9:25:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42057/100000 [12:34:25<9:25:35,  1.71it/s]
Train steps ... :  42%|████▏     | 42058/100000 [12:34:25<9:25:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42059/100000 [12:34:26<9:24:35,  1.71it/s]
Train steps ... :  42%|████▏     | 42060/100000 [12:34:27<9:24:10,  1.71it/s]
Train steps ... :  42%|████▏     | 42061/100000 [12:34:27<9:24:32,  1.71it/s]
Train steps ... :  42%|████▏     | 42062/100000 [12:34:28<9:25:07,  1.71it/s]
Train steps ... :  42%|████▏     | 42063/100000 [12:34:28<9:25:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42064/100000 [12:34:29<9:24:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42065/100000 [12:34:30<9:25:00,  1.71it/s]
Train steps ... :  42%|████▏     | 42066/100000 [12:34:30<9:24:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42067/100000 [12:34:31<9:24:48,  1.71it/s]
Train steps ... :  42%|████▏     | 42068/100000 [12:34:31<9:24:23,  1.71it/s]
Train steps ... :  42%|████▏     | 42069/100000 [12:34:32<9:24:20,  1.71it/s]
Train steps ... :  42%|████▏     | 42070/100000 [12:34:33<9:25:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42071/100000 [12:34:33<9:24:18,  1.71it/s]
Train steps ... :  42%|████▏     | 42072/100000 [12:34:34<9:23:53,  1.71it/s]
Train steps ... :  42%|████▏     | 42073/100000 [12:34:34<9:24:07,  1.71it/s]
Train steps ... :  42%|████▏     | 42074/100000 [12:34:35<9:24:10,  1.71it/s]
Train steps ... :  42%|████▏     | 42075/100000 [12:34:35<9:23:41,  1.71it/s]Step... (42075 / 100000 | Loss: 0.8204107284545898, Learning Rate: 5.8216080402010055e-05)
+
                                                                             
Step... (42075 / 100000 | Loss: 0.7821612358093262, Learning Rate: 5.8216080402010055e-05)
+
Train steps ... :  42%|████▏     | 42075/100000 [12:34:36<9:23:41,  1.71it/s]
Train steps ... :  42%|████▏     | 42076/100000 [12:34:36<9:23:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42077/100000 [12:34:37<9:23:15,  1.71it/s]
Train steps ... :  42%|████▏     | 42078/100000 [12:34:37<9:24:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42079/100000 [12:34:38<9:24:16,  1.71it/s]
Train steps ... :  42%|████▏     | 42080/100000 [12:34:38<9:23:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42081/100000 [12:34:39<9:23:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42082/100000 [12:34:40<9:23:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42083/100000 [12:34:40<9:23:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42084/100000 [12:34:41<9:24:07,  1.71it/s]
Train steps ... :  42%|████▏     | 42085/100000 [12:34:41<9:23:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42086/100000 [12:34:42<9:23:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42087/100000 [12:34:42<9:23:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42088/100000 [12:34:43<9:23:36,  1.71it/s]
Train steps ... :  42%|████▏     | 42089/100000 [12:34:44<9:23:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42090/100000 [12:34:44<9:23:58,  1.71it/s]
Train steps ... :  42%|████▏     | 42091/100000 [12:34:45<9:24:20,  1.71it/s]
Train steps ... :  42%|████▏     | 42092/100000 [12:34:45<9:23:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42093/100000 [12:34:46<9:23:48,  1.71it/s]
Train steps ... :  42%|████▏     | 42094/100000 [12:34:47<9:23:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42095/100000 [12:34:47<9:23:54,  1.71it/s]
Train steps ... :  42%|████▏     | 42096/100000 [12:34:48<9:23:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42097/100000 [12:34:48<9:23:35,  1.71it/s]
Train steps ... :  42%|████▏     | 42098/100000 [12:34:49<9:23:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42099/100000 [12:34:49<9:23:38,  1.71it/s]
Train steps ... :  42%|████▏     | 42100/100000 [12:34:50<9:23:45,  1.71it/s]Step... (42100 / 100000 | Loss: 0.9841731786727905, Learning Rate: 5.819095477386936e-05)
+
                                                                             
Step... (42100 / 100000 | Loss: 0.8162007331848145, Learning Rate: 5.819095477386936e-05)
+
Train steps ... :  42%|████▏     | 42100/100000 [12:34:50<9:23:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42101/100000 [12:34:51<9:23:59,  1.71it/s]
Train steps ... :  42%|████▏     | 42102/100000 [12:34:51<9:24:04,  1.71it/s]
Train steps ... :  42%|████▏     | 42103/100000 [12:34:52<9:24:34,  1.71it/s]
Train steps ... :  42%|████▏     | 42104/100000 [12:34:52<9:24:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42105/100000 [12:34:53<9:24:34,  1.71it/s]
Train steps ... :  42%|████▏     | 42106/100000 [12:34:54<9:24:06,  1.71it/s]
Train steps ... :  42%|████▏     | 42107/100000 [12:34:54<9:23:53,  1.71it/s]
Train steps ... :  42%|████▏     | 42108/100000 [12:34:55<9:23:47,  1.71it/s]
Train steps ... :  42%|████▏     | 42109/100000 [12:34:55<9:23:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42110/100000 [12:34:56<9:24:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42111/100000 [12:34:56<9:24:25,  1.71it/s]
Train steps ... :  42%|████▏     | 42112/100000 [12:34:57<9:24:03,  1.71it/s]
Train steps ... :  42%|████▏     | 42113/100000 [12:34:58<9:24:10,  1.71it/s]
Train steps ... :  42%|████▏     | 42114/100000 [12:34:58<9:23:49,  1.71it/s]
Train steps ... :  42%|████▏     | 42115/100000 [12:34:59<9:24:04,  1.71it/s]
Train steps ... :  42%|████▏     | 42116/100000 [12:34:59<9:24:04,  1.71it/s]
Train steps ... :  42%|████▏     | 42117/100000 [12:35:00<9:23:39,  1.71it/s]
Train steps ... :  42%|████▏     | 42118/100000 [12:35:01<9:23:53,  1.71it/s]
Train steps ... :  42%|████▏     | 42119/100000 [12:35:01<9:23:15,  1.71it/s]
Train steps ... :  42%|████▏     | 42120/100000 [12:35:02<9:23:29,  1.71it/s]
Train steps ... :  42%|████▏     | 42121/100000 [12:35:02<9:24:59,  1.71it/s]
Train steps ... :  42%|████▏     | 42122/100000 [12:35:03<9:24:20,  1.71it/s]
Train steps ... :  42%|████▏     | 42123/100000 [12:35:03<9:24:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42124/100000 [12:35:04<9:24:41,  1.71it/s]
Train steps ... :  42%|████▏     | 42125/100000 [12:35:05<9:24:05,  1.71it/s]Step... (42125 / 100000 | Loss: 0.765762448310852, Learning Rate: 5.816582914572865e-05)
+
                                                                             
Step... (42125 / 100000 | Loss: 0.6475550532341003, Learning Rate: 5.816582914572865e-05)
+
Train steps ... :  42%|████▏     | 42125/100000 [12:35:05<9:24:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42126/100000 [12:35:05<9:23:46,  1.71it/s]
Train steps ... :  42%|████▏     | 42127/100000 [12:35:06<9:23:37,  1.71it/s]
Train steps ... :  42%|████▏     | 42128/100000 [12:35:06<9:23:26,  1.71it/s]
Train steps ... :  42%|████▏     | 42129/100000 [12:35:07<9:23:58,  1.71it/s]
Train steps ... :  42%|████▏     | 42130/100000 [12:35:08<9:23:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42131/100000 [12:35:08<9:23:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42132/100000 [12:35:09<9:24:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42133/100000 [12:35:09<9:25:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42134/100000 [12:35:10<9:23:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42135/100000 [12:35:11<9:23:27,  1.71it/s]
Train steps ... :  42%|████▏     | 42136/100000 [12:35:11<9:23:29,  1.71it/s]
Train steps ... :  42%|████▏     | 42137/100000 [12:35:12<9:23:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42138/100000 [12:35:12<9:24:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42139/100000 [12:35:13<9:24:03,  1.71it/s]
Train steps ... :  42%|████▏     | 42140/100000 [12:35:13<9:23:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42141/100000 [12:35:14<9:24:03,  1.71it/s]
Train steps ... :  42%|████▏     | 42142/100000 [12:35:15<9:23:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42143/100000 [12:35:15<9:23:30,  1.71it/s]
Train steps ... :  42%|████▏     | 42144/100000 [12:35:16<9:23:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42145/100000 [12:35:16<9:22:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42146/100000 [12:35:17<9:22:56,  1.71it/s]
Train steps ... :  42%|████▏     | 42147/100000 [12:35:18<9:22:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42148/100000 [12:35:18<9:22:37,  1.71it/s]
Train steps ... :  42%|████▏     | 42149/100000 [12:35:19<9:23:00,  1.71it/s]
Train steps ... :  42%|████▏     | 42150/100000 [12:35:19<9:23:53,  1.71it/s]Step... (42150 / 100000 | Loss: 0.63811194896698, Learning Rate: 5.8140703517587945e-05)
+
                                                                             
Step... (42150 / 100000 | Loss: 0.6903371810913086, Learning Rate: 5.8140703517587945e-05)
+
Train steps ... :  42%|████▏     | 42150/100000 [12:35:20<9:23:53,  1.71it/s]
Train steps ... :  42%|████▏     | 42151/100000 [12:35:20<9:24:10,  1.71it/s]
Train steps ... :  42%|████▏     | 42152/100000 [12:35:20<9:23:33,  1.71it/s]
Train steps ... :  42%|████▏     | 42153/100000 [12:35:21<9:23:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42154/100000 [12:35:22<9:24:23,  1.71it/s]
Train steps ... :  42%|████▏     | 42155/100000 [12:35:22<9:23:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42156/100000 [12:35:23<9:23:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42157/100000 [12:35:23<9:23:23,  1.71it/s]
Train steps ... :  42%|████▏     | 42158/100000 [12:35:24<9:24:48,  1.71it/s]
Train steps ... :  42%|████▏     | 42159/100000 [12:35:25<9:23:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42160/100000 [12:35:25<9:24:25,  1.71it/s]
Train steps ... :  42%|████▏     | 42161/100000 [12:35:26<9:23:47,  1.71it/s]
Train steps ... :  42%|████▏     | 42162/100000 [12:35:26<9:23:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42163/100000 [12:35:27<9:23:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42164/100000 [12:35:27<9:23:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42165/100000 [12:35:28<9:23:27,  1.71it/s]
Train steps ... :  42%|████▏     | 42166/100000 [12:35:29<9:23:14,  1.71it/s]
Train steps ... :  42%|███��▏     | 42167/100000 [12:35:29<9:23:29,  1.71it/s]
Train steps ... :  42%|████▏     | 42168/100000 [12:35:30<9:22:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42169/100000 [12:35:30<9:22:54,  1.71it/s]
Train steps ... :  42%|████▏     | 42170/100000 [12:35:31<9:22:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42171/100000 [12:35:32<9:23:03,  1.71it/s]
Train steps ... :  42%|████▏     | 42172/100000 [12:35:32<9:24:07,  1.71it/s]
Train steps ... :  42%|████▏     | 42173/100000 [12:35:33<9:24:04,  1.71it/s]
Train steps ... :  42%|████▏     | 42174/100000 [12:35:33<9:24:19,  1.71it/s]
Train steps ... :  42%|████▏     | 42175/100000 [12:35:34<9:23:31,  1.71it/s]Step... (42175 / 100000 | Loss: 0.9885089993476868, Learning Rate: 5.8115577889447235e-05)
+
                                                                             
Step... (42175 / 100000 | Loss: 0.6221808195114136, Learning Rate: 5.8115577889447235e-05)
+
Train steps ... :  42%|████▏     | 42175/100000 [12:35:34<9:23:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42176/100000 [12:35:34<9:24:01,  1.71it/s]
Train steps ... :  42%|████▏     | 42177/100000 [12:35:35<9:23:29,  1.71it/s]
Train steps ... :  42%|████▏     | 42178/100000 [12:35:36<9:23:53,  1.71it/s]
Train steps ... :  42%|████▏     | 42179/100000 [12:35:36<9:24:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42180/100000 [12:35:37<9:24:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42181/100000 [12:35:37<9:24:38,  1.71it/s]
Train steps ... :  42%|████▏     | 42182/100000 [12:35:38<9:24:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42183/100000 [12:35:39<9:23:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42184/100000 [12:35:39<9:23:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42185/100000 [12:35:40<9:23:07,  1.71it/s]
Train steps ... :  42%|████▏     | 42186/100000 [12:35:40<9:23:04,  1.71it/s]
Train steps ... :  42%|████▏     | 42187/100000 [12:35:41<9:22:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42188/100000 [12:35:41<9:22:49,  1.71it/s]
Train steps ... :  42%|████▏     | 42189/100000 [12:35:42<9:23:19,  1.71it/s]
Train steps ... :  42%|████▏     | 42190/100000 [12:35:43<9:23:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42191/100000 [12:35:43<9:23:07,  1.71it/s]
Train steps ... :  42%|████▏     | 42192/100000 [12:35:44<9:22:37,  1.71it/s]
Train steps ... :  42%|████▏     | 42193/100000 [12:35:44<9:22:49,  1.71it/s]
Train steps ... :  42%|████▏     | 42194/100000 [12:35:45<9:22:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42195/100000 [12:35:46<9:22:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42196/100000 [12:35:46<9:23:16,  1.71it/s]
Train steps ... :  42%|████▏     | 42197/100000 [12:35:47<9:23:01,  1.71it/s]
Train steps ... :  42%|████▏     | 42198/100000 [12:35:47<9:22:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42199/100000 [12:35:48<9:23:30,  1.71it/s]
Train steps ... :  42%|████▏     | 42200/100000 [12:35:49<9:23:08,  1.71it/s]Step... (42200 / 100000 | Loss: 0.9242298603057861, Learning Rate: 5.809045226130654e-05)
+
                                                                             
Step... (42200 / 100000 | Loss: 0.7043487429618835, Learning Rate: 5.809045226130654e-05)
+
Train steps ... :  42%|████▏     | 42200/100000 [12:35:49<9:23:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42201/100000 [12:35:49<9:23:26,  1.71it/s]
Train steps ... :  42%|████▏     | 42202/100000 [12:35:50<9:23:30,  1.71it/s]
Train steps ... :  42%|████▏     | 42203/100000 [12:35:50<9:23:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42204/100000 [12:35:51<9:23:54,  1.71it/s]
Train steps ... :  42%|████▏     | 42205/100000 [12:35:51<9:23:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42206/100000 [12:35:52<9:23:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42207/100000 [12:35:53<9:23:16,  1.71it/s]
Train steps ... :  42%|████▏     | 42208/100000 [12:35:53<9:23:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42209/100000 [12:35:54<9:22:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42210/100000 [12:35:54<9:23:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42211/100000 [12:35:55<9:22:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42212/100000 [12:35:56<9:22:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42213/100000 [12:35:56<9:22:36,  1.71it/s]
Train steps ... :  42%|████▏     | 42214/100000 [12:35:57<9:23:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42215/100000 [12:35:57<9:23:33,  1.71it/s]
Train steps ... :  42%|████▏     | 42216/100000 [12:35:58<9:23:38,  1.71it/s]
Train steps ... :  42%|████▏     | 42217/100000 [12:35:58<9:23:35,  1.71it/s]
Train steps ... :  42%|████▏     | 42218/100000 [12:35:59<9:23:00,  1.71it/s]
Train steps ... :  42%|████▏     | 42219/100000 [12:36:00<9:23:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42220/100000 [12:36:00<9:22:59,  1.71it/s]
Train steps ... :  42%|████▏     | 42221/100000 [12:36:01<9:22:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42222/100000 [12:36:01<9:23:03,  1.71it/s]
Train steps ... :  42%|████▏     | 42223/100000 [12:36:02<9:22:35,  1.71it/s]
Train steps ... :  42%|████▏     | 42224/100000 [12:36:03<9:22:34,  1.71it/s]
Train steps ... :  42%|████▏     | 42225/100000 [12:36:03<9:22:33,  1.71it/s]Step... (42225 / 100000 | Loss: 0.8147785663604736, Learning Rate: 5.806532663316583e-05)
+
                                                                             
Step... (42225 / 100000 | Loss: 0.8321430683135986, Learning Rate: 5.806532663316583e-05)
+
Train steps ... :  42%|████▏     | 42225/100000 [12:36:03<9:22:33,  1.71it/s]
Train steps ... :  42%|████▏     | 42226/100000 [12:36:04<9:22:48,  1.71it/s]
Train steps ... :  42%|████▏     | 42227/100000 [12:36:04<9:22:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42228/100000 [12:36:05<9:22:03,  1.71it/s]
Train steps ... :  42%|████▏     | 42229/100000 [12:36:05<9:22:01,  1.71it/s]
Train steps ... :  42%|████▏     | 42230/100000 [12:36:06<9:22:11,  1.71it/s]
Train steps ... :  42%|████▏     | 42231/100000 [12:36:07<9:22:42,  1.71it/s]
Train steps ... :  42%|████▏     | 42232/100000 [12:36:07<9:22:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42233/100000 [12:36:08<9:22:34,  1.71it/s]
Train steps ... :  42%|████▏     | 42234/100000 [12:36:08<9:22:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42235/100000 [12:36:09<9:22:56,  1.71it/s]
Train steps ... :  42%|████▏     | 42236/100000 [12:36:10<9:23:10,  1.71it/s]
Train steps ... :  42%|████▏     | 42237/100000 [12:36:10<9:22:59,  1.71it/s]
Train steps ... :  42%|████▏     | 42238/100000 [12:36:11<9:23:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42239/100000 [12:36:11<9:23:33,  1.71it/s]
Train steps ... :  42%|████▏     | 42240/100000 [12:36:12<9:23:04,  1.71it/s]
Train steps ... :  42%|████▏     | 42241/100000 [12:36:12<9:22:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42242/100000 [12:36:13<9:22:36,  1.71it/s]
Train steps ... :  42%|████▏     | 42243/100000 [12:36:14<9:22:42,  1.71it/s]
Train steps ... :  42%|████▏     | 42244/100000 [12:36:14<9:22:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42245/100000 [12:36:15<9:22:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42246/100000 [12:36:15<9:22:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42247/100000 [12:36:16<9:22:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42248/100000 [12:36:17<9:22:30,  1.71it/s]
Train steps ... :  42%|████▏     | 42249/100000 [12:36:17<9:22:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42250/100000 [12:36:18<9:21:41,  1.71it/s]Step... (42250 / 100000 | Loss: 0.9382926225662231, Learning Rate: 5.804020100502513e-05)
+
                                                                             
Step... (42250 / 100000 | Loss: 0.6078376173973083, Learning Rate: 5.804020100502513e-05)
+
Train steps ... :  42%|████▏     | 42250/100000 [12:36:18<9:21:41,  1.71it/s]
Train steps ... :  42%|████▏     | 42251/100000 [12:36:18<9:22:27,  1.71it/s]
Train steps ... :  42%|████▏     | 42252/100000 [12:36:19<9:21:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42253/100000 [12:36:19<9:21:29,  1.71it/s]
Train steps ... :  42%|████▏     | 42254/100000 [12:36:20<9:21:37,  1.71it/s]
Train steps ... :  42%|████▏     | 42255/100000 [12:36:21<9:22:38,  1.71it/s]
Train steps ... :  42%|████▏     | 42256/100000 [12:36:21<9:23:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42257/100000 [12:36:22<9:22:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42258/100000 [12:36:22<9:23:10,  1.71it/s]
Train steps ... :  42%|████▏     | 42259/100000 [12:36:23<9:22:37,  1.71it/s]
Train steps ... :  42%|████▏     | 42260/100000 [12:36:24<9:22:14,  1.71it/s]
Train steps ... :  42%|████▏     | 42261/100000 [12:36:24<9:22:00,  1.71it/s]
Train steps ... :  42%|████▏     | 42262/100000 [12:36:25<9:21:59,  1.71it/s]
Train steps ... :  42%|████▏     | 42263/100000 [12:36:25<9:22:34,  1.71it/s]
Train steps ... :  42%|████▏     | 42264/100000 [12:36:26<9:21:58,  1.71it/s]
Train steps ... :  42%|████▏     | 42265/100000 [12:36:26<9:21:58,  1.71it/s]
Train steps ... :  42%|████▏     | 42266/100000 [12:36:27<9:22:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42267/100000 [12:36:28<9:22:17,  1.71it/s]
Train steps ... :  42%|████▏     | 42268/100000 [12:36:28<9:22:01,  1.71it/s]
Train steps ... :  42%|████▏     | 42269/100000 [12:36:29<9:21:59,  1.71it/s]
Train steps ... :  42%|████▏     | 42270/100000 [12:36:29<9:22:00,  1.71it/s]
Train steps ... :  42%|████▏     | 42271/100000 [12:36:30<9:22:13,  1.71it/s]
Train steps ... :  42%|████▏     | 42272/100000 [12:36:31<9:21:49,  1.71it/s]
Train steps ... :  42%|████▏     | 42273/100000 [12:36:31<9:22:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42274/100000 [12:36:32<9:21:47,  1.71it/s]
Train steps ... :  42%|████▏     | 42275/100000 [12:36:32<9:21:53,  1.71it/s]Step... (42275 / 100000 | Loss: 0.8192398548126221, Learning Rate: 5.801507537688442e-05)
+
                                                                             
Step... (42275 / 100000 | Loss: 0.7199429273605347, Learning Rate: 5.801507537688442e-05)
+
Train steps ... :  42%|████▏     | 42275/100000 [12:36:33<9:21:53,  1.71it/s]
Train steps ... :  42%|████▏     | 42276/100000 [12:36:33<9:21:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42277/100000 [12:36:34<9:22:20,  1.71it/s]
Train steps ... :  42%|████▏     | 42278/100000 [12:36:34<9:21:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42279/100000 [12:36:35<9:22:34,  1.71it/s]
Train steps ... :  42%|████▏     | 42280/100000 [12:36:35<9:22:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42281/100000 [12:36:36<9:21:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42282/100000 [12:36:36<9:21:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42283/100000 [12:36:37<9:21:39,  1.71it/s]
Train steps ... :  42%|████▏     | 42284/100000 [12:36:38<9:21:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42285/100000 [12:36:38<9:21:14,  1.71it/s]
Train steps ... :  42%|████▏     | 42286/100000 [12:36:39<9:21:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42287/100000 [12:36:39<9:22:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42288/100000 [12:36:40<9:22:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42289/100000 [12:36:41<9:23:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42290/100000 [12:36:41<9:22:42,  1.71it/s]
Train steps ... :  42%|████▏     | 42291/100000 [12:36:42<9:22:16,  1.71it/s]
Train steps ... :  42%|████▏     | 42292/100000 [12:36:42<9:22:36,  1.71it/s]
Train steps ... :  42%|████▏     | 42293/100000 [12:36:43<9:22:54,  1.71it/s]
Train steps ... :  42%|████▏     | 42294/100000 [12:36:43<9:22:33,  1.71it/s]
Train steps ... :  42%|████▏     | 42295/100000 [12:36:44<9:22:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42296/100000 [12:36:45<9:21:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42297/100000 [12:36:45<9:22:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42298/100000 [12:36:46<9:22:13,  1.71it/s]
Train steps ... :  42%|████▏     | 42299/100000 [12:36:46<9:22:29,  1.71it/s]
Train steps ... :  42%|████▏     | 42300/100000 [12:36:47<9:22:11,  1.71it/s]Step... (42300 / 100000 | Loss: 0.9214398860931396, Learning Rate: 5.7989949748743724e-05)
+
                                                                             
Step... (42300 / 100000 | Loss: 0.669952929019928, Learning Rate: 5.7989949748743724e-05)
+
Train steps ... :  42%|████▏     | 42300/100000 [12:36:47<9:22:11,  1.71it/s]
Train steps ... :  42%|████▏     | 42301/100000 [12:36:48<9:22:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42302/100000 [12:36:48<9:23:02,  1.71it/s]
Train steps ... :  42%|████▏     | 42303/100000 [12:36:49<9:23:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42304/100000 [12:36:49<9:22:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42305/100000 [12:36:50<9:22:48,  1.71it/s]
Train steps ... :  42%|████▏     | 42306/100000 [12:36:50<9:22:41,  1.71it/s]
Train steps ... :  42%|████▏     | 42307/100000 [12:36:51<9:22:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42308/100000 [12:36:52<9:22:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42309/100000 [12:36:52<9:22:17,  1.71it/s]
Train steps ... :  42%|████▏     | 42310/100000 [12:36:53<9:22:16,  1.71it/s]
Train steps ... :  42%|████▏     | 42311/100000 [12:36:53<9:22:00,  1.71it/s]
Train steps ... :  42%|████▏     | 42312/100000 [12:36:54<9:22:14,  1.71it/s]
Train steps ... :  42%|████▏     | 42313/100000 [12:36:55<9:22:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42314/100000 [12:36:55<9:22:20,  1.71it/s]
Train steps ... :  42%|████▏     | 42315/100000 [12:36:56<9:22:48,  1.71it/s]
Train steps ... :  42%|████▏     | 42316/100000 [12:36:56<9:22:04,  1.71it/s]
Train steps ... :  42%|████▏     | 42317/100000 [12:36:57<9:22:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42318/100000 [12:36:57<9:23:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42319/100000 [12:36:58<9:22:29,  1.71it/s]
Train steps ... :  42%|████▏     | 42320/100000 [12:36:59<9:22:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42321/100000 [12:36:59<9:22:32,  1.71it/s]
Train steps ... :  42%|████▏     | 42322/100000 [12:37:00<9:22:39,  1.71it/s]
Train steps ... :  42%|████▏     | 42323/100000 [12:37:00<9:23:14,  1.71it/s]
Train steps ... :  42%|████▏     | 42324/100000 [12:37:01<9:22:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42325/100000 [12:37:02<9:21:50,  1.71it/s]Step... (42325 / 100000 | Loss: 0.844418466091156, Learning Rate: 5.796482412060302e-05)
+
                                                                             
Step... (42325 / 100000 | Loss: 1.019063949584961, Learning Rate: 5.796482412060302e-05)
+
Train steps ... :  42%|████▏     | 42325/100000 [12:37:02<9:21:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42326/100000 [12:37:02<9:23:02,  1.71it/s]
Train steps ... :  42%|████▏     | 42327/100000 [12:37:03<9:22:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42328/100000 [12:37:03<9:22:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42329/100000 [12:37:04<9:22:06,  1.71it/s]
Train steps ... :  42%|████▏     | 42330/100000 [12:37:05<9:21:37,  1.71it/s]
Train steps ... :  42%|████▏     | 42331/100000 [12:37:05<9:21:23,  1.71it/s]
Train steps ... :  42%|████▏     | 42332/100000 [12:37:06<9:21:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42333/100000 [12:37:06<9:21:41,  1.71it/s]
Train steps ... :  42%|████▏     | 42334/100000 [12:37:07<9:21:06,  1.71it/s]
Train steps ... :  42%|████▏     | 42335/100000 [12:37:07<9:21:54,  1.71it/s]
Train steps ... :  42%|████▏     | 42336/100000 [12:37:08<9:21:35,  1.71it/s]
Train steps ... :  42%|████▏     | 42337/100000 [12:37:09<9:22:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42338/100000 [12:37:09<9:22:16,  1.71it/s]
Train steps ... :  42%|████▏     | 42339/100000 [12:37:10<9:21:39,  1.71it/s]
Train steps ... :  42%|████▏     | 42340/100000 [12:37:10<9:21:27,  1.71it/s]
Train steps ... :  42%|████▏     | 42341/100000 [12:37:11<9:21:47,  1.71it/s]
Train steps ... :  42%|████▏     | 42342/100000 [12:37:12<9:21:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42343/100000 [12:37:12<9:21:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42344/100000 [12:37:13<9:21:38,  1.71it/s]
Train steps ... :  42%|████▏     | 42345/100000 [12:37:13<9:21:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42346/100000 [12:37:14<9:21:38,  1.71it/s]
Train steps ... :  42%|████▏     | 42347/100000 [12:37:14<9:21:14,  1.71it/s]
Train steps ... :  42%|████▏     | 42348/100000 [12:37:15<9:21:02,  1.71it/s]
Train steps ... :  42%|████▏     | 42349/100000 [12:37:16<9:21:06,  1.71it/s]
Train steps ... :  42%|████▏     | 42350/100000 [12:37:16<9:21:50,  1.71it/s]Step... (42350 / 100000 | Loss: 0.8419795036315918, Learning Rate: 5.793969849246231e-05)
+
                                                                             
Step... (42350 / 100000 | Loss: 1.1031699180603027, Learning Rate: 5.793969849246231e-05)
+
Train steps ... :  42%|████▏     | 42350/100000 [12:37:17<9:21:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42351/100000 [12:37:17<9:21:24,  1.71it/s]
Train steps ... :  42%|████▏     | 42352/100000 [12:37:17<9:21:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42353/100000 [12:37:18<9:21:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42354/100000 [12:37:19<9:21:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42355/100000 [12:37:19<9:21:36,  1.71it/s]
Train steps ... :  42%|████▏     | 42356/100000 [12:37:20<9:21:47,  1.71it/s]
Train steps ... :  42%|████▏     | 42357/100000 [12:37:20<9:21:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42358/100000 [12:37:21<9:20:56,  1.71it/s]
Train steps ... :  42%|████▏     | 42359/100000 [12:37:21<9:20:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42360/100000 [12:37:22<9:20:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42361/100000 [12:37:23<9:21:00,  1.71it/s]
Train steps ... :  42%|████▏     | 42362/100000 [12:37:23<9:20:53,  1.71it/s]
Train steps ... :  42%|████▏     | 42363/100000 [12:37:24<9:21:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42364/100000 [12:37:24<9:21:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42365/100000 [12:37:25<9:21:49,  1.71it/s]
Train steps ... :  42%|████▏     | 42366/100000 [12:37:26<9:21:06,  1.71it/s]
Train steps ... :  42%|████▏     | 42367/100000 [12:37:26<9:21:51,  1.71it/s]
Train steps ... :  42%|███���▏     | 42368/100000 [12:37:27<9:21:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42369/100000 [12:37:27<9:21:06,  1.71it/s]
Train steps ... :  42%|████▏     | 42370/100000 [12:37:28<9:20:56,  1.71it/s]
Train steps ... :  42%|████▏     | 42371/100000 [12:37:28<9:21:01,  1.71it/s]
Train steps ... :  42%|████▏     | 42372/100000 [12:37:29<9:20:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42373/100000 [12:37:30<9:20:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42374/100000 [12:37:30<9:21:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42375/100000 [12:37:31<9:21:08,  1.71it/s]Step... (42375 / 100000 | Loss: 0.7580180764198303, Learning Rate: 5.7914572864321614e-05)
+
                                                                             
Step... (42375 / 100000 | Loss: 1.0352973937988281, Learning Rate: 5.7914572864321614e-05)
+
Train steps ... :  42%|████▏     | 42375/100000 [12:37:31<9:21:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42376/100000 [12:37:31<9:21:38,  1.71it/s]
Train steps ... :  42%|████▏     | 42377/100000 [12:37:32<9:21:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42378/100000 [12:37:33<9:21:47,  1.71it/s]
Train steps ... :  42%|████▏     | 42379/100000 [12:37:33<9:21:19,  1.71it/s]
Train steps ... :  42%|████▏     | 42380/100000 [12:37:34<9:20:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42381/100000 [12:37:34<9:21:18,  1.71it/s]
Train steps ... :  42%|████▏     | 42382/100000 [12:37:35<9:21:24,  1.71it/s]
Train steps ... :  42%|████▏     | 42383/100000 [12:37:35<9:21:04,  1.71it/s]
Train steps ... :  42%|████▏     | 42384/100000 [12:37:36<9:20:35,  1.71it/s]
Train steps ... :  42%|████▏     | 42385/100000 [12:37:37<9:20:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42386/100000 [12:37:37<9:20:38,  1.71it/s]
Train steps ... :  42%|████▏     | 42387/100000 [12:37:38<9:20:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42388/100000 [12:37:38<9:20:30,  1.71it/s]
Train steps ... :  42%|████▏     | 42389/100000 [12:37:39<9:21:14,  1.71it/s]
Train steps ... :  42%|████▏     | 42390/100000 [12:37:40<9:21:36,  1.71it/s]
Train steps ... :  42%|████▏     | 42391/100000 [12:37:40<9:21:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42392/100000 [12:37:41<9:21:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42393/100000 [12:37:41<9:21:02,  1.71it/s]
Train steps ... :  42%|████▏     | 42394/100000 [12:37:42<9:21:46,  1.71it/s]
Train steps ... :  42%|████▏     | 42395/100000 [12:37:42<9:21:20,  1.71it/s]
Train steps ... :  42%|████▏     | 42396/100000 [12:37:43<9:21:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42397/100000 [12:37:44<9:20:58,  1.71it/s]
Train steps ... :  42%|████▏     | 42398/100000 [12:37:44<9:22:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42399/100000 [12:37:45<9:22:23,  1.71it/s]
Train steps ... :  42%|████▏     | 42400/100000 [12:37:45<9:21:51,  1.71it/s]Step... (42400 / 100000 | Loss: 0.5537760853767395, Learning Rate: 5.7889447236180904e-05)
+
                                                                             
Step... (42400 / 100000 | Loss: 0.8691272735595703, Learning Rate: 5.7889447236180904e-05)
+
Train steps ... :  42%|████▏     | 42400/100000 [12:37:46<9:21:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42401/100000 [12:37:46<9:21:40,  1.71it/s]
Train steps ... :  42%|████▏     | 42402/100000 [12:37:47<9:22:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42403/100000 [12:37:47<9:21:26,  1.71it/s]
Train steps ... :  42%|████▏     | 42404/100000 [12:37:48<9:20:59,  1.71it/s]
Train steps ... :  42%|████▏     | 42405/100000 [12:37:48<9:21:46,  1.71it/s]
Train steps ... :  42%|████▏     | 42406/100000 [12:37:49<9:21:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42407/100000 [12:37:50<9:20:58,  1.71it/s]
Train steps ... :  42%|████▏     | 42408/100000 [12:37:50<9:20:41,  1.71it/s]
Train steps ... :  42%|████▏     | 42409/100000 [12:37:51<9:21:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42410/100000 [12:37:51<9:21:49,  1.71it/s]
Train steps ... :  42%|████▏     | 42411/100000 [12:37:52<9:21:22,  1.71it/s]
Train steps ... :  42%|████▏     | 42412/100000 [12:37:52<9:21:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42413/100000 [12:37:53<9:20:48,  1.71it/s]
Train steps ... :  42%|████▏     | 42414/100000 [12:37:54<9:20:38,  1.71it/s]
Train steps ... :  42%|████▏     | 42415/100000 [12:37:54<9:21:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42416/100000 [12:37:55<9:21:50,  1.71it/s]
Train steps ... :  42%|████▏     | 42417/100000 [12:37:55<9:21:27,  1.71it/s]
Train steps ... :  42%|████▏     | 42418/100000 [12:37:56<9:21:32,  1.71it/s]
Train steps ... :  42%|████▏     | 42419/100000 [12:37:57<9:20:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42420/100000 [12:37:57<9:21:32,  1.71it/s]
Train steps ... :  42%|████▏     | 42421/100000 [12:37:58<9:21:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42422/100000 [12:37:58<9:21:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42423/100000 [12:37:59<9:20:46,  1.71it/s]
Train steps ... :  42%|████▏     | 42424/100000 [12:37:59<9:20:18,  1.71it/s]
Train steps ... :  42%|████▏     | 42425/100000 [12:38:00<9:20:28,  1.71it/s]Step... (42425 / 100000 | Loss: 0.6440857648849487, Learning Rate: 5.786432160804021e-05)
+
                                                                             
Step... (42425 / 100000 | Loss: 0.6683669090270996, Learning Rate: 5.786432160804021e-05)
+
Train steps ... :  42%|████▏     | 42425/100000 [12:38:00<9:20:28,  1.71it/s]
Train steps ... :  42%|████▏     | 42426/100000 [12:38:01<9:21:33,  1.71it/s]
Train steps ... :  42%|████▏     | 42427/100000 [12:38:01<9:21:48,  1.71it/s]
Train steps ... :  42%|████▏     | 42428/100000 [12:38:02<9:21:19,  1.71it/s]
Train steps ... :  42%|████▏     | 42429/100000 [12:38:02<9:21:08,  1.71it/s]
Train steps ... :  42%|████▏     | 42430/100000 [12:38:03<9:21:01,  1.71it/s]
Train steps ... :  42%|████▏     | 42431/100000 [12:38:04<9:21:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42432/100000 [12:38:04<9:21:18,  1.71it/s]
Train steps ... :  42%|████▏     | 42433/100000 [12:38:05<9:22:42,  1.71it/s]
Train steps ... :  42%|████▏     | 42434/100000 [12:38:05<9:22:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42435/100000 [12:38:06<9:21:46,  1.71it/s]
Train steps ... :  42%|████▏     | 42436/100000 [12:38:06<9:20:57,  1.71it/s]
Train steps ... :  42%|████▏     | 42437/100000 [12:38:07<9:20:47,  1.71it/s]
Train steps ... :  42%|████▏     | 42438/100000 [12:38:08<9:20:23,  1.71it/s]
Train steps ... :  42%|████▏     | 42439/100000 [12:38:08<9:20:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42440/100000 [12:38:09<9:20:47,  1.71it/s]
Train steps ... :  42%|████▏     | 42441/100000 [12:38:09<9:20:26,  1.71it/s]
Train steps ... :  42%|████▏     | 42442/100000 [12:38:10<9:20:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42443/100000 [12:38:11<9:20:36,  1.71it/s]
Train steps ... :  42%|████▏     | 42444/100000 [12:38:11<9:20:14,  1.71it/s]
Train steps ... :  42%|████▏     | 42445/100000 [12:38:12<9:20:24,  1.71it/s]
Train steps ... :  42%|████▏     | 42446/100000 [12:38:12<9:21:33,  1.71it/s]
Train steps ... :  42%|████▏     | 42447/100000 [12:38:13<9:21:03,  1.71it/s]
Train steps ... :  42%|████▏     | 42448/100000 [12:38:13<9:20:46,  1.71it/s]
Train steps ... :  42%|████▏     | 42449/100000 [12:38:14<9:20:46,  1.71it/s]
Train steps ... :  42%|████▏     | 42450/100000 [12:38:15<9:20:45,  1.71it/s]Step... (42450 / 100000 | Loss: 0.5925736427307129, Learning Rate: 5.78391959798995e-05)
+
                                                                             
Step... (42450 / 100000 | Loss: 0.6771271824836731, Learning Rate: 5.78391959798995e-05)
+
Train steps ... :  42%|████▏     | 42450/100000 [12:38:15<9:20:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42451/100000 [12:38:15<9:21:46,  1.71it/s]
Train steps ... :  42%|████▏     | 42452/100000 [12:38:16<9:20:47,  1.71it/s]
Train steps ... :  42%|████▏     | 42453/100000 [12:38:16<9:20:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42454/100000 [12:38:17<9:20:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42455/100000 [12:38:18<9:21:02,  1.71it/s]
Train steps ... :  42%|████▏     | 42456/100000 [12:38:18<9:20:39,  1.71it/s]
Train steps ... :  42%|████▏     | 42457/100000 [12:38:19<9:20:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42458/100000 [12:38:19<9:20:42,  1.71it/s]
Train steps ... :  42%|████▏     | 42459/100000 [12:38:20<9:20:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42460/100000 [12:38:21<9:20:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42461/100000 [12:38:21<9:21:00,  1.71it/s]
Train steps ... :  42%|████▏     | 42462/100000 [12:38:22<9:21:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42463/100000 [12:38:22<9:21:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42464/100000 [12:38:23<9:20:27,  1.71it/s]
Train steps ... :  42%|████▏     | 42465/100000 [12:38:23<9:20:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42466/100000 [12:38:24<9:21:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42467/100000 [12:38:25<9:20:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42468/100000 [12:38:25<9:20:29,  1.71it/s]
Train steps ... :  42%|████▏     | 42469/100000 [12:38:26<9:20:33,  1.71it/s]
Train steps ... :  42%|████▏     | 42470/100000 [12:38:26<9:20:49,  1.71it/s]
Train steps ... :  42%|████▏     | 42471/100000 [12:38:27<9:20:25,  1.71it/s]
Train steps ... :  42%|████▏     | 42472/100000 [12:38:28<9:20:12,  1.71it/s]
Train steps ... :  42%|████▏     | 42473/100000 [12:38:28<9:20:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42474/100000 [12:38:29<9:20:05,  1.71it/s]
Train steps ... :  42%|████▏     | 42475/100000 [12:38:29<9:20:51,  1.71it/s]Step... (42475 / 100000 | Loss: 1.1012835502624512, Learning Rate: 5.78140703517588e-05)
+
                                                                             
Step... (42475 / 100000 | Loss: 0.9436130523681641, Learning Rate: 5.78140703517588e-05)
+
Train steps ... :  42%|████▏     | 42475/100000 [12:38:30<9:20:51,  1.71it/s]
Train steps ... :  42%|████▏     | 42476/100000 [12:38:30<9:21:24,  1.71it/s]
Train steps ... :  42%|████▏     | 42477/100000 [12:38:30<9:20:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42478/100000 [12:38:31<9:20:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42479/100000 [12:38:32<9:20:55,  1.71it/s]
Train steps ... :  42%|████▏     | 42480/100000 [12:38:32<9:21:15,  1.71it/s]
Train steps ... :  42%|████▏     | 42481/100000 [12:38:33<9:21:15,  1.71it/s]
Train steps ... :  42%|████▏     | 42482/100000 [12:38:33<9:20:30,  1.71it/s]
Train steps ... :  42%|████▏     | 42483/100000 [12:38:34<9:20:59,  1.71it/s]
Train steps ... :  42%|████▏     | 42484/100000 [12:38:35<9:20:37,  1.71it/s]
Train steps ... :  42%|████▏     | 42485/100000 [12:38:35<9:20:32,  1.71it/s]
Train steps ... :  42%|████▏     | 42486/100000 [12:38:36<9:20:52,  1.71it/s]
Train steps ... :  42%|████▏     | 42487/100000 [12:38:36<9:20:45,  1.71it/s]
Train steps ... :  42%|████▏     | 42488/100000 [12:38:37<9:20:47,  1.71it/s]
Train steps ... :  42%|████▏     | 42489/100000 [12:38:37<9:20:31,  1.71it/s]
Train steps ... :  42%|████▏     | 42490/100000 [12:38:38<9:20:26,  1.71it/s]
Train steps ... :  42%|████▏     | 42491/100000 [12:38:39<9:20:56,  1.71it/s]
Train steps ... :  42%|████▏     | 42492/100000 [12:38:39<9:20:27,  1.71it/s]
Train steps ... :  42%|████▏     | 42493/100000 [12:38:40<9:20:58,  1.71it/s]
Train steps ... :  42%|████▏     | 42494/100000 [12:38:40<9:21:09,  1.71it/s]
Train steps ... :  42%|████▏     | 42495/100000 [12:38:41<9:20:41,  1.71it/s]
Train steps ... :  42%|████▏     | 42496/100000 [12:38:42<9:21:21,  1.71it/s]
Train steps ... :  42%|████▏     | 42497/100000 [12:38:42<9:20:43,  1.71it/s]
Train steps ... :  42%|████▏     | 42498/100000 [12:38:43<9:20:44,  1.71it/s]
Train steps ... :  42%|████▏     | 42499/100000 [12:38:43<9:20:42,  1.71it/s]
Train steps ... :  42%|████▎     | 42500/100000 [12:38:44<9:20:38,  1.71it/s]Step... (42500 / 100000 | Loss: 0.9083905220031738, Learning Rate: 5.778894472361809e-05)
+
                                                                             
Step... (42500 / 100000 | Loss: 0.7088048458099365, Learning Rate: 5.778894472361809e-05)
+
Train steps ... :  42%|████▎     | 42500/100000 [12:38:44<9:20:38,  1.71it/s]
Train steps ... :  43%|████▎     | 42501/100000 [12:38:44<9:20:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42502/100000 [12:38:45<9:20:30,  1.71it/s]
Train steps ... :  43%|████▎     | 42503/100000 [12:38:46<9:20:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42504/100000 [12:38:46<9:20:37,  1.71it/s]
Train steps ... :  43%|████▎     | 42505/100000 [12:38:47<9:20:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42506/100000 [12:38:47<9:20:24,  1.71it/s]
Train steps ... :  43%|████▎     | 42507/100000 [12:38:48<9:19:52,  1.71it/s]
Train steps ... :  43%|████▎     | 42508/100000 [12:38:49<9:20:46,  1.71it/s]
Train steps ... :  43%|████▎     | 42509/100000 [12:38:49<9:20:21,  1.71it/s]
Train steps ... :  43%|████▎     | 42510/100000 [12:38:50<9:20:43,  1.71it/s]
Train steps ... :  43%|████▎     | 42511/100000 [12:38:50<9:19:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42512/100000 [12:38:51<9:20:48,  1.71it/s]
Train steps ... :  43%|████▎     | 42513/100000 [12:38:52<9:21:51,  1.71it/s]
Train steps ... :  43%|████▎     | 42514/100000 [12:38:52<9:21:40,  1.71it/s]
Train steps ... :  43%|████▎     | 42515/100000 [12:38:53<9:21:53,  1.71it/s]
Train steps ... :  43%|████▎     | 42516/100000 [12:38:53<9:20:40,  1.71it/s]
Train steps ... :  43%|████▎     | 42517/100000 [12:38:54<9:20:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42518/100000 [12:38:54<9:20:34,  1.71it/s]
Train steps ... :  43%|████▎     | 42519/100000 [12:38:55<9:20:53,  1.71it/s]
Train steps ... :  43%|████▎     | 42520/100000 [12:38:56<9:21:01,  1.71it/s]
Train steps ... :  43%|████▎     | 42521/100000 [12:38:56<9:20:54,  1.71it/s]
Train steps ... :  43%|████▎     | 42522/100000 [12:38:57<9:21:13,  1.71it/s]
Train steps ... :  43%|████▎     | 42523/100000 [12:38:57<9:20:54,  1.71it/s]
Train steps ... :  43%|████▎     | 42524/100000 [12:38:58<9:21:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42525/100000 [12:38:59<9:20:25,  1.71it/s]Step... (42525 / 100000 | Loss: 0.8183258771896362, Learning Rate: 5.776381909547739e-05)
+
                                                                             
Step... (42525 / 100000 | Loss: 0.7254930734634399, Learning Rate: 5.776381909547739e-05)
+
Train steps ... :  43%|████▎     | 42525/100000 [12:38:59<9:20:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42526/100000 [12:38:59<9:20:23,  1.71it/s]
Train steps ... :  43%|████▎     | 42527/100000 [12:39:00<9:20:26,  1.71it/s]
Train steps ... :  43%|████▎     | 42528/100000 [12:39:00<9:21:06,  1.71it/s]
Train steps ... :  43%|████▎     | 42529/100000 [12:39:01<9:20:24,  1.71it/s]
Train steps ... :  43%|████▎     | 42530/100000 [12:39:01<9:20:40,  1.71it/s]
Train steps ... :  43%|████▎     | 42531/100000 [12:39:02<9:20:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42532/100000 [12:39:03<9:20:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42533/100000 [12:39:03<9:19:57,  1.71it/s]
Train steps ... :  43%|████▎     | 42534/100000 [12:39:04<9:20:02,  1.71it/s]
Train steps ... :  43%|████▎     | 42535/100000 [12:39:04<9:20:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42536/100000 [12:39:05<9:20:21,  1.71it/s]
Train steps ... :  43%|████▎     | 42537/100000 [12:39:06<9:21:17,  1.71it/s]
Train steps ... :  43%|████▎     | 42538/100000 [12:39:06<9:21:07,  1.71it/s]
Train steps ... :  43%|████▎     | 42539/100000 [12:39:07<9:20:32,  1.71it/s]
Train steps ... :  43%|████▎     | 42540/100000 [12:39:07<9:20:47,  1.71it/s]
Train steps ... :  43%|████▎     | 42541/100000 [12:39:08<9:19:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42542/100000 [12:39:08<9:20:06,  1.71it/s]
Train steps ... :  43%|████▎     | 42543/100000 [12:39:09<9:20:47,  1.71it/s]
Train steps ... :  43%|████▎     | 42544/100000 [12:39:10<9:20:54,  1.71it/s]
Train steps ... :  43%|████▎     | 42545/100000 [12:39:10<9:20:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42546/100000 [12:39:11<9:20:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42547/100000 [12:39:11<9:19:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42548/100000 [12:39:12<9:20:14,  1.71it/s]
Train steps ... :  43%|████▎     | 42549/100000 [12:39:13<9:19:53,  1.71it/s]
Train steps ... :  43%|████▎     | 42550/100000 [12:39:13<9:19:51,  1.71it/s]Step... (42550 / 100000 | Loss: 0.7627314329147339, Learning Rate: 5.773869346733669e-05)
+
                                                                             
Step... (42550 / 100000 | Loss: 0.7853183746337891, Learning Rate: 5.773869346733669e-05)
+
Train steps ... :  43%|████▎     | 42550/100000 [12:39:13<9:19:51,  1.71it/s]
Train steps ... :  43%|████▎     | 42551/100000 [12:39:14<9:19:57,  1.71it/s]
Train steps ... :  43%|████▎     | 42552/100000 [12:39:14<9:19:40,  1.71it/s]
Train steps ... :  43%|████▎     | 42553/100000 [12:39:15<9:20:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42554/100000 [12:39:16<9:19:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42555/100000 [12:39:16<9:20:05,  1.71it/s]
Train steps ... :  43%|████▎     | 42556/100000 [12:39:17<9:19:56,  1.71it/s]
Train steps ... :  43%|████▎     | 42557/100000 [12:39:17<9:20:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42558/100000 [12:39:18<9:20:16,  1.71it/s]
Train steps ... :  43%|████▎     | 42559/100000 [12:39:18<9:19:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42560/100000 [12:39:19<9:19:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42561/100000 [12:39:20<9:20:26,  1.71it/s]
Train steps ... :  43%|████▎     | 42562/100000 [12:39:20<9:19:30,  1.71it/s]
Train steps ... :  43%|████▎     | 42563/100000 [12:39:21<9:20:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42564/100000 [12:39:21<9:19:33,  1.71it/s]
Train steps ... :  43%|████▎     | 42565/100000 [12:39:22<9:19:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42566/100000 [12:39:23<9:19:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42567/100000 [12:39:23<9:19:22,  1.71it/s]
Train steps ... :  43%|████▎     | 42568/100000 [12:39:24<9:19:20,  1.71it/s]
Train steps ... :  43%|███���▎     | 42569/100000 [12:39:24<9:19:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42570/100000 [12:39:25<9:19:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42571/100000 [12:39:25<9:19:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42572/100000 [12:39:26<9:18:46,  1.71it/s]
Train steps ... :  43%|████▎     | 42573/100000 [12:39:27<9:18:45,  1.71it/s]
Train steps ... :  43%|████▎     | 42574/100000 [12:39:27<9:18:59,  1.71it/s]
Train steps ... :  43%|████▎     | 42575/100000 [12:39:28<9:19:15,  1.71it/s]Step... (42575 / 100000 | Loss: 0.9200044870376587, Learning Rate: 5.771356783919598e-05)
+
                                                                             
Step... (42575 / 100000 | Loss: 0.7750226259231567, Learning Rate: 5.771356783919598e-05)
+
Train steps ... :  43%|████▎     | 42575/100000 [12:39:28<9:19:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42576/100000 [12:39:28<9:20:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42577/100000 [12:39:29<9:19:44,  1.71it/s]
Train steps ... :  43%|████▎     | 42578/100000 [12:39:30<9:19:26,  1.71it/s]
Train steps ... :  43%|████▎     | 42579/100000 [12:39:30<9:19:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42580/100000 [12:39:31<9:20:13,  1.71it/s]
Train steps ... :  43%|████▎     | 42581/100000 [12:39:31<9:19:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42582/100000 [12:39:32<9:19:10,  1.71it/s]
Train steps ... :  43%|████▎     | 42583/100000 [12:39:32<9:19:19,  1.71it/s]
Train steps ... :  43%|████▎     | 42584/100000 [12:39:33<9:19:45,  1.71it/s]
Train steps ... :  43%|████▎     | 42585/100000 [12:39:34<9:19:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42586/100000 [12:39:34<9:19:08,  1.71it/s]
Train steps ... :  43%|████▎     | 42587/100000 [12:39:35<9:19:12,  1.71it/s]
Train steps ... :  43%|████▎     | 42588/100000 [12:39:35<9:19:06,  1.71it/s]
Train steps ... :  43%|████▎     | 42589/100000 [12:39:36<9:19:09,  1.71it/s]
Train steps ... :  43%|████▎     | 42590/100000 [12:39:37<9:18:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42591/100000 [12:39:37<9:18:18,  1.71it/s]
Train steps ... :  43%|████▎     | 42592/100000 [12:39:38<9:18:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42593/100000 [12:39:38<9:18:24,  1.71it/s]
Train steps ... :  43%|████▎     | 42594/100000 [12:39:39<9:18:40,  1.71it/s]
Train steps ... :  43%|████▎     | 42595/100000 [12:39:39<9:18:17,  1.71it/s]
Train steps ... :  43%|████▎     | 42596/100000 [12:39:40<9:18:42,  1.71it/s]
Train steps ... :  43%|████▎     | 42597/100000 [12:39:41<9:19:07,  1.71it/s]
Train steps ... :  43%|████▎     | 42598/100000 [12:39:41<9:21:02,  1.71it/s]
Train steps ... :  43%|████▎     | 42599/100000 [12:39:42<9:20:21,  1.71it/s]
Train steps ... :  43%|████▎     | 42600/100000 [12:39:42<9:19:25,  1.71it/s]Step... (42600 / 100000 | Loss: 0.6583173871040344, Learning Rate: 5.7688442211055284e-05)
+
                                                                             
Step... (42600 / 100000 | Loss: 0.6642059087753296, Learning Rate: 5.7688442211055284e-05)
+
Train steps ... :  43%|████▎     | 42600/100000 [12:39:43<9:19:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42601/100000 [12:39:43<9:19:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42602/100000 [12:39:44<9:19:30,  1.71it/s]
Train steps ... :  43%|████▎     | 42603/100000 [12:39:44<9:19:10,  1.71it/s]
Train steps ... :  43%|████▎     | 42604/100000 [12:39:45<9:19:44,  1.71it/s]
Train steps ... :  43%|████▎     | 42605/100000 [12:39:45<9:19:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42606/100000 [12:39:46<9:19:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42607/100000 [12:39:46<9:19:13,  1.71it/s]
Train steps ... :  43%|████▎     | 42608/100000 [12:39:47<9:20:42,  1.71it/s]
Train steps ... :  43%|████▎     | 42609/100000 [12:39:48<9:19:54,  1.71it/s]
Train steps ... :  43%|████▎     | 42610/100000 [12:39:48<9:19:22,  1.71it/s]
Train steps ... :  43%|████▎     | 42611/100000 [12:39:49<9:19:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42612/100000 [12:39:49<9:19:17,  1.71it/s]
Train steps ... :  43%|████▎     | 42613/100000 [12:39:50<9:19:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42614/100000 [12:39:51<9:19:54,  1.71it/s]
Train steps ... :  43%|████▎     | 42615/100000 [12:39:51<9:19:17,  1.71it/s]
Train steps ... :  43%|████▎     | 42616/100000 [12:39:52<9:19:16,  1.71it/s]
Train steps ... :  43%|████▎     | 42617/100000 [12:39:52<9:19:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42618/100000 [12:39:53<9:19:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42619/100000 [12:39:54<9:19:07,  1.71it/s]
Train steps ... :  43%|████▎     | 42620/100000 [12:39:54<9:19:07,  1.71it/s]
Train steps ... :  43%|████▎     | 42621/100000 [12:39:55<9:18:56,  1.71it/s]
Train steps ... :  43%|████▎     | 42622/100000 [12:39:55<9:19:07,  1.71it/s]
Train steps ... :  43%|████▎     | 42623/100000 [12:39:56<9:19:13,  1.71it/s]
Train steps ... :  43%|████▎     | 42624/100000 [12:39:56<9:18:42,  1.71it/s]
Train steps ... :  43%|████▎     | 42625/100000 [12:39:57<9:18:37,  1.71it/s]Step... (42625 / 100000 | Loss: 0.8080276250839233, Learning Rate: 5.7663316582914574e-05)
+
                                                                             
Step... (42625 / 100000 | Loss: 1.2045027017593384, Learning Rate: 5.7663316582914574e-05)
+
Train steps ... :  43%|████▎     | 42625/100000 [12:39:57<9:18:37,  1.71it/s]
Train steps ... :  43%|████▎     | 42626/100000 [12:39:58<9:19:05,  1.71it/s]
Train steps ... :  43%|████▎     | 42627/100000 [12:39:58<9:18:41,  1.71it/s]
Train steps ... :  43%|████▎     | 42628/100000 [12:39:59<9:18:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42629/100000 [12:39:59<9:18:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42630/100000 [12:40:00<9:19:08,  1.71it/s]
Train steps ... :  43%|████▎     | 42631/100000 [12:40:01<9:19:23,  1.71it/s]
Train steps ... :  43%|████▎     | 42632/100000 [12:40:01<9:20:20,  1.71it/s]
Train steps ... :  43%|████▎     | 42633/100000 [12:40:02<9:19:52,  1.71it/s]
Train steps ... :  43%|████▎     | 42634/100000 [12:40:02<9:19:53,  1.71it/s]
Train steps ... :  43%|████▎     | 42635/100000 [12:40:03<9:19:42,  1.71it/s]
Train steps ... :  43%|████▎     | 42636/100000 [12:40:03<9:19:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42637/100000 [12:40:04<9:19:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42638/100000 [12:40:05<9:19:16,  1.71it/s]
Train steps ... :  43%|████▎     | 42639/100000 [12:40:05<9:19:39,  1.71it/s]
Train steps ... :  43%|████▎     | 42640/100000 [12:40:06<9:19:38,  1.71it/s]
Train steps ... :  43%|████▎     | 42641/100000 [12:40:06<9:19:08,  1.71it/s]
Train steps ... :  43%|████▎     | 42642/100000 [12:40:07<9:18:52,  1.71it/s]
Train steps ... :  43%|████▎     | 42643/100000 [12:40:08<9:18:33,  1.71it/s]
Train steps ... :  43%|████▎     | 42644/100000 [12:40:08<9:19:08,  1.71it/s]
Train steps ... :  43%|████▎     | 42645/100000 [12:40:09<9:18:56,  1.71it/s]
Train steps ... :  43%|████▎     | 42646/100000 [12:40:09<9:18:37,  1.71it/s]
Train steps ... :  43%|████▎     | 42647/100000 [12:40:10<9:18:49,  1.71it/s]
Train steps ... :  43%|████▎     | 42648/100000 [12:40:10<9:19:12,  1.71it/s]
Train steps ... :  43%|████▎     | 42649/100000 [12:40:11<9:18:51,  1.71it/s]
Train steps ... :  43%|████▎     | 42650/100000 [12:40:12<9:18:27,  1.71it/s]Step... (42650 / 100000 | Loss: 0.8876054286956787, Learning Rate: 5.763819095477388e-05)
+
                                                                             
Step... (42650 / 100000 | Loss: 0.9935067892074585, Learning Rate: 5.763819095477388e-05)
+
Train steps ... :  43%|████▎     | 42650/100000 [12:40:12<9:18:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42651/100000 [12:40:12<9:18:39,  1.71it/s]
Train steps ... :  43%|████▎     | 42652/100000 [12:40:13<9:18:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42653/100000 [12:40:13<9:18:19,  1.71it/s]
Train steps ... :  43%|████▎     | 42654/100000 [12:40:14<9:18:24,  1.71it/s]
Train steps ... :  43%|████▎     | 42655/100000 [12:40:15<9:18:20,  1.71it/s]
Train steps ... :  43%|████▎     | 42656/100000 [12:40:15<9:18:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42657/100000 [12:40:16<9:18:57,  1.71it/s]
Train steps ... :  43%|████▎     | 42658/100000 [12:40:16<9:19:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42659/100000 [12:40:17<9:18:23,  1.71it/s]
Train steps ... :  43%|████▎     | 42660/100000 [12:40:17<9:18:57,  1.71it/s]
Train steps ... :  43%|████▎     | 42661/100000 [12:40:18<9:18:23,  1.71it/s]
Train steps ... :  43%|████▎     | 42662/100000 [12:40:19<9:18:32,  1.71it/s]
Train steps ... :  43%|████▎     | 42663/100000 [12:40:19<9:18:16,  1.71it/s]
Train steps ... :  43%|████▎     | 42664/100000 [12:40:20<9:18:06,  1.71it/s]
Train steps ... :  43%|████▎     | 42665/100000 [12:40:20<9:18:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42666/100000 [12:40:21<9:19:09,  1.71it/s]
Train steps ... :  43%|████▎     | 42667/100000 [12:40:22<9:18:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42668/100000 [12:40:22<9:18:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42669/100000 [12:40:23<9:18:10,  1.71it/s]
Train steps ... :  43%|████▎     | 42670/100000 [12:40:23<9:18:03,  1.71it/s]
Train steps ... :  43%|████▎     | 42671/100000 [12:40:24<9:17:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42672/100000 [12:40:24<9:18:31,  1.71it/s]
Train steps ... :  43%|████▎     | 42673/100000 [12:40:25<9:18:51,  1.71it/s]
Train steps ... :  43%|████▎     | 42674/100000 [12:40:26<9:18:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42675/100000 [12:40:26<9:18:01,  1.71it/s]Step... (42675 / 100000 | Loss: 1.0707255601882935, Learning Rate: 5.761306532663317e-05)
+
                                                                             
Step... (42675 / 100000 | Loss: 0.7921087741851807, Learning Rate: 5.761306532663317e-05)
+
Train steps ... :  43%|████▎     | 42675/100000 [12:40:27<9:18:01,  1.71it/s]
Train steps ... :  43%|████▎     | 42676/100000 [12:40:27<9:18:32,  1.71it/s]
Train steps ... :  43%|████▎     | 42677/100000 [12:40:27<9:18:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42678/100000 [12:40:28<9:18:31,  1.71it/s]
Train steps ... :  43%|████▎     | 42679/100000 [12:40:29<9:18:07,  1.71it/s]
Train steps ... :  43%|████▎     | 42680/100000 [12:40:29<9:18:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42681/100000 [12:40:30<9:18:07,  1.71it/s]
Train steps ... :  43%|████▎     | 42682/100000 [12:40:30<9:18:46,  1.71it/s]
Train steps ... :  43%|████▎     | 42683/100000 [12:40:31<9:18:24,  1.71it/s]
Train steps ... :  43%|████▎     | 42684/100000 [12:40:32<9:18:44,  1.71it/s]
Train steps ... :  43%|████▎     | 42685/100000 [12:40:32<9:18:38,  1.71it/s]
Train steps ... :  43%|████▎     | 42686/100000 [12:40:33<9:19:08,  1.71it/s]
Train steps ... :  43%|████▎     | 42687/100000 [12:40:33<9:19:24,  1.71it/s]
Train steps ... :  43%|████▎     | 42688/100000 [12:40:34<9:19:06,  1.71it/s]
Train steps ... :  43%|████▎     | 42689/100000 [12:40:34<9:19:42,  1.71it/s]
Train steps ... :  43%|████▎     | 42690/100000 [12:40:35<9:19:18,  1.71it/s]
Train steps ... :  43%|████▎     | 42691/100000 [12:40:36<9:18:38,  1.71it/s]
Train steps ... :  43%|████▎     | 42692/100000 [12:40:36<9:18:12,  1.71it/s]
Train steps ... :  43%|████▎     | 42693/100000 [12:40:37<9:17:57,  1.71it/s]
Train steps ... :  43%|████▎     | 42694/100000 [12:40:37<9:18:23,  1.71it/s]
Train steps ... :  43%|████▎     | 42695/100000 [12:40:38<9:18:02,  1.71it/s]
Train steps ... :  43%|████▎     | 42696/100000 [12:40:39<9:18:34,  1.71it/s]
Train steps ... :  43%|████▎     | 42697/100000 [12:40:39<9:18:34,  1.71it/s]
Train steps ... :  43%|████▎     | 42698/100000 [12:40:40<9:18:39,  1.71it/s]
Train steps ... :  43%|████▎     | 42699/100000 [12:40:40<9:18:46,  1.71it/s]
Train steps ... :  43%|████▎     | 42700/100000 [12:40:41<9:18:49,  1.71it/s]Step... (42700 / 100000 | Loss: 0.8878862857818604, Learning Rate: 5.7587939698492464e-05)
+
                                                                             
Step... (42700 / 100000 | Loss: 0.697946310043335, Learning Rate: 5.7587939698492464e-05)
+
Train steps ... :  43%|████▎     | 42700/100000 [12:40:41<9:18:49,  1.71it/s]
Train steps ... :  43%|████▎     | 42701/100000 [12:40:41<9:19:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42702/100000 [12:40:42<9:19:02,  1.71it/s]
Train steps ... :  43%|████▎     | 42703/100000 [12:40:43<9:18:56,  1.71it/s]
Train steps ... :  43%|████▎     | 42704/100000 [12:40:43<9:18:49,  1.71it/s]
Train steps ... :  43%|████▎     | 42705/100000 [12:40:44<9:18:53,  1.71it/s]
Train steps ... :  43%|████▎     | 42706/100000 [12:40:44<9:19:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42707/100000 [12:40:45<9:18:33,  1.71it/s]
Train steps ... :  43%|████▎     | 42708/100000 [12:40:46<9:18:41,  1.71it/s]
Train steps ... :  43%|████▎     | 42709/100000 [12:40:46<9:18:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42710/100000 [12:40:47<9:17:49,  1.71it/s]
Train steps ... :  43%|████▎     | 42711/100000 [12:40:47<9:17:54,  1.71it/s]
Train steps ... :  43%|████▎     | 42712/100000 [12:40:48<9:18:03,  1.71it/s]
Train steps ... :  43%|████▎     | 42713/100000 [12:40:48<9:17:48,  1.71it/s]
Train steps ... :  43%|████▎     | 42714/100000 [12:40:49<9:17:44,  1.71it/s]
Train steps ... :  43%|████▎     | 42715/100000 [12:40:50<9:17:42,  1.71it/s]
Train steps ... :  43%|████▎     | 42716/100000 [12:40:50<9:17:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42717/100000 [12:40:51<9:17:32,  1.71it/s]
Train steps ... :  43%|████▎     | 42718/100000 [12:40:51<9:17:29,  1.71it/s]
Train steps ... :  43%|████▎     | 42719/100000 [12:40:52<9:17:51,  1.71it/s]
Train steps ... :  43%|████▎     | 42720/100000 [12:40:53<9:17:39,  1.71it/s]
Train steps ... :  43%|████▎     | 42721/100000 [12:40:53<9:17:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42722/100000 [12:40:54<9:17:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42723/100000 [12:40:54<9:17:43,  1.71it/s]
Train steps ... :  43%|████▎     | 42724/100000 [12:40:55<9:17:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42725/100000 [12:40:55<9:17:43,  1.71it/s]Step... (42725 / 100000 | Loss: 0.6029142141342163, Learning Rate: 5.756281407035177e-05)
+
                                                                             
Step... (42725 / 100000 | Loss: 0.9665566682815552, Learning Rate: 5.756281407035177e-05)
+
Train steps ... :  43%|████▎     | 42725/100000 [12:40:56<9:17:43,  1.71it/s]
Train steps ... :  43%|████▎     | 42726/100000 [12:40:56<9:18:03,  1.71it/s]
Train steps ... :  43%|████▎     | 42727/100000 [12:40:57<9:17:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42728/100000 [12:40:57<9:17:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42729/100000 [12:40:58<9:18:08,  1.71it/s]
Train steps ... :  43%|████▎     | 42730/100000 [12:40:58<9:17:38,  1.71it/s]
Train steps ... :  43%|████▎     | 42731/100000 [12:40:59<9:17:02,  1.71it/s]
Train steps ... :  43%|████▎     | 42732/100000 [12:41:00<9:16:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42733/100000 [12:41:00<9:17:03,  1.71it/s]
Train steps ... :  43%|████▎     | 42734/100000 [12:41:01<9:17:43,  1.71it/s]
Train steps ... :  43%|████▎     | 42735/100000 [12:41:01<9:18:43,  1.71it/s]
Train steps ... :  43%|████▎     | 42736/100000 [12:41:02<9:20:18,  1.70it/s]
Train steps ... :  43%|████▎     | 42737/100000 [12:41:03<9:18:12,  1.71it/s]
Train steps ... :  43%|████▎     | 42738/100000 [12:41:03<9:18:04,  1.71it/s]
Train steps ... :  43%|████▎     | 42739/100000 [12:41:04<9:17:53,  1.71it/s]
Train steps ... :  43%|████▎     | 42740/100000 [12:41:04<9:17:37,  1.71it/s]
Train steps ... :  43%|████▎     | 42741/100000 [12:41:05<9:18:18,  1.71it/s]
Train steps ... :  43%|████▎     | 42742/100000 [12:41:05<9:18:33,  1.71it/s]
Train steps ... :  43%|████▎     | 42743/100000 [12:41:06<9:18:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42744/100000 [12:41:07<9:19:12,  1.71it/s]
Train steps ... :  43%|████▎     | 42745/100000 [12:41:07<9:18:40,  1.71it/s]
Train steps ... :  43%|████▎     | 42746/100000 [12:41:08<9:18:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42747/100000 [12:41:08<9:18:08,  1.71it/s]
Train steps ... :  43%|████▎     | 42748/100000 [12:41:09<9:17:49,  1.71it/s]
Train steps ... :  43%|████▎     | 42749/100000 [12:41:10<9:17:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42750/100000 [12:41:10<9:17:38,  1.71it/s]Step... (42750 / 100000 | Loss: 0.8212011456489563, Learning Rate: 5.753768844221106e-05)
+
                                                                             
Step... (42750 / 100000 | Loss: 0.8660953044891357, Learning Rate: 5.753768844221106e-05)
+
Train steps ... :  43%|████▎     | 42750/100000 [12:41:10<9:17:38,  1.71it/s]
Train steps ... :  43%|████▎     | 42751/100000 [12:41:11<9:19:02,  1.71it/s]
Train steps ... :  43%|████▎     | 42752/100000 [12:41:11<9:18:33,  1.71it/s]
Train steps ... :  43%|████▎     | 42753/100000 [12:41:12<9:20:01,  1.70it/s]
Train steps ... :  43%|████▎     | 42754/100000 [12:41:12<9:20:13,  1.70it/s]
Train steps ... :  43%|████▎     | 42755/100000 [12:41:13<9:18:57,  1.71it/s]
Train steps ... :  43%|████▎     | 42756/100000 [12:41:14<9:18:26,  1.71it/s]
Train steps ... :  43%|████▎     | 42757/100000 [12:41:14<9:18:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42758/100000 [12:41:15<9:17:41,  1.71it/s]
Train steps ... :  43%|████▎     | 42759/100000 [12:41:15<9:18:08,  1.71it/s]
Train steps ... :  43%|████▎     | 42760/100000 [12:41:16<9:18:04,  1.71it/s]
Train steps ... :  43%|████▎     | 42761/100000 [12:41:17<9:18:01,  1.71it/s]
Train steps ... :  43%|████▎     | 42762/100000 [12:41:17<9:18:16,  1.71it/s]
Train steps ... :  43%|████▎     | 42763/100000 [12:41:18<9:17:43,  1.71it/s]
Train steps ... :  43%|████▎     | 42764/100000 [12:41:18<9:18:21,  1.71it/s]
Train steps ... :  43%|████▎     | 42765/100000 [12:41:19<9:17:49,  1.71it/s]
Train steps ... :  43%|████▎     | 42766/100000 [12:41:19<9:17:52,  1.71it/s]
Train steps ... :  43%|████▎     | 42767/100000 [12:41:20<9:17:07,  1.71it/s]
Train steps ... :  43%|████▎     | 42768/100000 [12:41:21<9:18:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42769/100000 [12:41:21<9:18:39,  1.71it/s]
Train steps ... :  43%|█��██▎     | 42770/100000 [12:41:22<9:18:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42771/100000 [12:41:22<9:18:30,  1.71it/s]
Train steps ... :  43%|████▎     | 42772/100000 [12:41:23<9:18:01,  1.71it/s]
Train steps ... :  43%|████▎     | 42773/100000 [12:41:24<9:17:33,  1.71it/s]
Train steps ... :  43%|████▎     | 42774/100000 [12:41:24<9:17:18,  1.71it/s]
Train steps ... :  43%|████▎     | 42775/100000 [12:41:25<9:17:20,  1.71it/s]Step... (42775 / 100000 | Loss: 1.0157793760299683, Learning Rate: 5.751256281407036e-05)
+
                                                                             
Step... (42775 / 100000 | Loss: 1.160001277923584, Learning Rate: 5.751256281407036e-05)
+
Train steps ... :  43%|████▎     | 42775/100000 [12:41:25<9:17:20,  1.71it/s]
Train steps ... :  43%|████▎     | 42776/100000 [12:41:25<9:17:18,  1.71it/s]
Train steps ... :  43%|████▎     | 42777/100000 [12:41:26<9:16:38,  1.71it/s]
Train steps ... :  43%|████▎     | 42778/100000 [12:41:26<9:17:33,  1.71it/s]
Train steps ... :  43%|████▎     | 42779/100000 [12:41:27<9:17:56,  1.71it/s]
Train steps ... :  43%|████▎     | 42780/100000 [12:41:28<9:18:14,  1.71it/s]
Train steps ... :  43%|████▎     | 42781/100000 [12:41:28<9:17:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42782/100000 [12:41:29<9:17:07,  1.71it/s]
Train steps ... :  43%|████▎     | 42783/100000 [12:41:29<9:17:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42784/100000 [12:41:30<9:17:10,  1.71it/s]
Train steps ... :  43%|████▎     | 42785/100000 [12:41:31<9:17:24,  1.71it/s]
Train steps ... :  43%|████▎     | 42786/100000 [12:41:31<9:17:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42787/100000 [12:41:32<9:17:13,  1.71it/s]
Train steps ... :  43%|████▎     | 42788/100000 [12:41:32<9:17:01,  1.71it/s]
Train steps ... :  43%|████▎     | 42789/100000 [12:41:33<9:16:59,  1.71it/s]
Train steps ... :  43%|████▎     | 42790/100000 [12:41:34<9:17:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42791/100000 [12:41:34<9:16:42,  1.71it/s]
Train steps ... :  43%|████▎     | 42792/100000 [12:41:35<9:17:19,  1.71it/s]
Train steps ... :  43%|████▎     | 42793/100000 [12:41:35<9:17:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42794/100000 [12:41:36<9:18:09,  1.71it/s]
Train steps ... :  43%|████▎     | 42795/100000 [12:41:36<9:17:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42796/100000 [12:41:37<9:17:33,  1.71it/s]
Train steps ... :  43%|████▎     | 42797/100000 [12:41:38<9:17:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42798/100000 [12:41:38<9:16:51,  1.71it/s]
Train steps ... :  43%|████▎     | 42799/100000 [12:41:39<9:16:37,  1.71it/s]
Train steps ... :  43%|████▎     | 42800/100000 [12:41:39<9:17:31,  1.71it/s]Step... (42800 / 100000 | Loss: 0.7399595379829407, Learning Rate: 5.748743718592965e-05)
+
                                                                             
Step... (42800 / 100000 | Loss: 0.6920804977416992, Learning Rate: 5.748743718592965e-05)
+
Train steps ... :  43%|████▎     | 42800/100000 [12:41:40<9:17:31,  1.71it/s]
Train steps ... :  43%|████▎     | 42801/100000 [12:41:40<9:17:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42802/100000 [12:41:41<9:17:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42803/100000 [12:41:41<9:17:18,  1.71it/s]
Train steps ... :  43%|████▎     | 42804/100000 [12:41:42<9:17:21,  1.71it/s]
Train steps ... :  43%|████▎     | 42805/100000 [12:41:42<9:17:10,  1.71it/s]
Train steps ... :  43%|████▎     | 42806/100000 [12:41:43<9:17:05,  1.71it/s]
Train steps ... :  43%|████▎     | 42807/100000 [12:41:43<9:17:01,  1.71it/s]
Train steps ... :  43%|████▎     | 42808/100000 [12:41:44<9:17:30,  1.71it/s]
Train steps ... :  43%|████▎     | 42809/100000 [12:41:45<9:17:03,  1.71it/s]
Train steps ... :  43%|████▎     | 42810/100000 [12:41:45<9:16:57,  1.71it/s]
Train steps ... :  43%|████▎     | 42811/100000 [12:41:46<9:16:48,  1.71it/s]
Train steps ... :  43%|████▎     | 42812/100000 [12:41:46<9:16:40,  1.71it/s]
Train steps ... :  43%|████▎     | 42813/100000 [12:41:47<9:16:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42814/100000 [12:41:48<9:17:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42815/100000 [12:41:48<9:17:31,  1.71it/s]
Train steps ... :  43%|████▎     | 42816/100000 [12:41:49<9:17:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42817/100000 [12:41:49<9:18:08,  1.71it/s]
Train steps ... :  43%|████▎     | 42818/100000 [12:41:50<9:17:42,  1.71it/s]
Train steps ... :  43%|████▎     | 42819/100000 [12:41:50<9:17:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42820/100000 [12:41:51<9:17:02,  1.71it/s]
Train steps ... :  43%|████▎     | 42821/100000 [12:41:52<9:17:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42822/100000 [12:41:52<9:17:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42823/100000 [12:41:53<9:17:10,  1.71it/s]
Train steps ... :  43%|████▎     | 42824/100000 [12:41:53<9:17:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42825/100000 [12:41:54<9:16:39,  1.71it/s]Step... (42825 / 100000 | Loss: 0.8234848976135254, Learning Rate: 5.7462311557788953e-05)
+
                                                                             
Step... (42825 / 100000 | Loss: 0.9060609340667725, Learning Rate: 5.7462311557788953e-05)
+
Train steps ... :  43%|████▎     | 42825/100000 [12:41:54<9:16:39,  1.71it/s]
Train steps ... :  43%|████▎     | 42826/100000 [12:41:55<9:17:09,  1.71it/s]
Train steps ... :  43%|████▎     | 42827/100000 [12:41:55<9:17:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42828/100000 [12:41:56<9:17:03,  1.71it/s]
Train steps ... :  43%|████▎     | 42829/100000 [12:41:56<9:16:52,  1.71it/s]
Train steps ... :  43%|████▎     | 42830/100000 [12:41:57<9:16:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42831/100000 [12:41:57<9:16:20,  1.71it/s]
Train steps ... :  43%|████▎     | 42832/100000 [12:41:58<9:16:17,  1.71it/s]
Train steps ... :  43%|████▎     | 42833/100000 [12:41:59<9:15:42,  1.71it/s]
Train steps ... :  43%|████▎     | 42834/100000 [12:41:59<9:16:17,  1.71it/s]
Train steps ... :  43%|████▎     | 42835/100000 [12:42:00<9:17:43,  1.71it/s]
Train steps ... :  43%|████▎     | 42836/100000 [12:42:00<9:16:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42837/100000 [12:42:01<9:16:48,  1.71it/s]
Train steps ... :  43%|████▎     | 42838/100000 [12:42:02<9:17:12,  1.71it/s]
Train steps ... :  43%|████▎     | 42839/100000 [12:42:02<9:17:10,  1.71it/s]
Train steps ... :  43%|████▎     | 42840/100000 [12:42:03<9:17:54,  1.71it/s]
Train steps ... :  43%|████▎     | 42841/100000 [12:42:03<9:17:01,  1.71it/s]
Train steps ... :  43%|████▎     | 42842/100000 [12:42:04<9:16:48,  1.71it/s]
Train steps ... :  43%|████▎     | 42843/100000 [12:42:04<9:17:06,  1.71it/s]
Train steps ... :  43%|████▎     | 42844/100000 [12:42:05<9:16:47,  1.71it/s]
Train steps ... :  43%|████▎     | 42845/100000 [12:42:06<9:16:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42846/100000 [12:42:06<9:17:13,  1.71it/s]
Train steps ... :  43%|████▎     | 42847/100000 [12:42:07<9:17:19,  1.71it/s]
Train steps ... :  43%|████▎     | 42848/100000 [12:42:07<9:17:05,  1.71it/s]
Train steps ... :  43%|████▎     | 42849/100000 [12:42:08<9:16:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42850/100000 [12:42:09<9:17:04,  1.71it/s]Step... (42850 / 100000 | Loss: 0.7841888070106506, Learning Rate: 5.743718592964824e-05)
+
                                                                             
Step... (42850 / 100000 | Loss: 0.8591797351837158, Learning Rate: 5.743718592964824e-05)
+
Train steps ... :  43%|████▎     | 42850/100000 [12:42:09<9:17:04,  1.71it/s]
Train steps ... :  43%|████▎     | 42851/100000 [12:42:09<9:17:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42852/100000 [12:42:10<9:17:26,  1.71it/s]
Train steps ... :  43%|████▎     | 42853/100000 [12:42:10<9:18:04,  1.71it/s]
Train steps ... :  43%|████▎     | 42854/100000 [12:42:11<9:18:12,  1.71it/s]
Train steps ... :  43%|████▎     | 42855/100000 [12:42:12<9:17:52,  1.71it/s]
Train steps ... :  43%|████▎     | 42856/100000 [12:42:12<9:17:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42857/100000 [12:42:13<9:17:46,  1.71it/s]
Train steps ... :  43%|████▎     | 42858/100000 [12:42:13<9:16:59,  1.71it/s]
Train steps ... :  43%|████▎     | 42859/100000 [12:42:14<9:17:19,  1.71it/s]
Train steps ... :  43%|████▎     | 42860/100000 [12:42:14<9:18:02,  1.71it/s]
Train steps ... :  43%|████▎     | 42861/100000 [12:42:15<9:17:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42862/100000 [12:42:16<9:17:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42863/100000 [12:42:16<9:16:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42864/100000 [12:42:17<9:17:17,  1.71it/s]
Train steps ... :  43%|████▎     | 42865/100000 [12:42:17<9:17:51,  1.71it/s]
Train steps ... :  43%|████▎     | 42866/100000 [12:42:18<9:17:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42867/100000 [12:42:19<9:16:38,  1.71it/s]
Train steps ... :  43%|████▎     | 42868/100000 [12:42:19<9:17:12,  1.71it/s]
Train steps ... :  43%|████▎     | 42869/100000 [12:42:20<9:17:26,  1.71it/s]
Train steps ... :  43%|████▎     | 42870/100000 [12:42:20<9:18:02,  1.71it/s]
Train steps ... :  43%|████▎     | 42871/100000 [12:42:21<9:16:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42872/100000 [12:42:21<9:16:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42873/100000 [12:42:22<9:16:41,  1.71it/s]
Train steps ... :  43%|████▎     | 42874/100000 [12:42:23<9:16:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42875/100000 [12:42:23<9:16:35,  1.71it/s]Step... (42875 / 100000 | Loss: 0.9776922464370728, Learning Rate: 5.741206030150754e-05)
+
                                                                             
Step... (42875 / 100000 | Loss: 0.7101457118988037, Learning Rate: 5.741206030150754e-05)
+
Train steps ... :  43%|████▎     | 42875/100000 [12:42:24<9:16:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42876/100000 [12:42:24<9:17:33,  1.71it/s]
Train steps ... :  43%|████▎     | 42877/100000 [12:42:24<9:16:56,  1.71it/s]
Train steps ... :  43%|████▎     | 42878/100000 [12:42:25<9:17:52,  1.71it/s]
Train steps ... :  43%|████▎     | 42879/100000 [12:42:26<9:16:51,  1.71it/s]
Train steps ... :  43%|████▎     | 42880/100000 [12:42:26<9:17:23,  1.71it/s]
Train steps ... :  43%|████▎     | 42881/100000 [12:42:27<9:17:23,  1.71it/s]
Train steps ... :  43%|████▎     | 42882/100000 [12:42:27<9:16:46,  1.71it/s]
Train steps ... :  43%|████▎     | 42883/100000 [12:42:28<9:16:14,  1.71it/s]
Train steps ... :  43%|████▎     | 42884/100000 [12:42:28<9:16:01,  1.71it/s]
Train steps ... :  43%|████▎     | 42885/100000 [12:42:29<9:17:10,  1.71it/s]
Train steps ... :  43%|████▎     | 42886/100000 [12:42:30<9:17:02,  1.71it/s]
Train steps ... :  43%|████▎     | 42887/100000 [12:42:30<9:17:22,  1.71it/s]
Train steps ... :  43%|████▎     | 42888/100000 [12:42:31<9:17:01,  1.71it/s]
Train steps ... :  43%|████▎     | 42889/100000 [12:42:31<9:16:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42890/100000 [12:42:32<9:16:48,  1.71it/s]
Train steps ... :  43%|████▎     | 42891/100000 [12:42:33<9:17:03,  1.71it/s]
Train steps ... :  43%|████▎     | 42892/100000 [12:42:33<9:16:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42893/100000 [12:42:34<9:16:22,  1.71it/s]
Train steps ... :  43%|████▎     | 42894/100000 [12:42:34<9:16:37,  1.71it/s]
Train steps ... :  43%|████▎     | 42895/100000 [12:42:35<9:16:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42896/100000 [12:42:35<9:16:04,  1.71it/s]
Train steps ... :  43%|████▎     | 42897/100000 [12:42:36<9:16:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42898/100000 [12:42:37<9:16:48,  1.71it/s]
Train steps ... :  43%|████▎     | 42899/100000 [12:42:37<9:15:12,  1.71it/s]
Train steps ... :  43%|████▎     | 42900/100000 [12:42:38<9:16:11,  1.71it/s]Step... (42900 / 100000 | Loss: 0.6464129090309143, Learning Rate: 5.738693467336683e-05)
+
                                                                             
Step... (42900 / 100000 | Loss: 1.1062462329864502, Learning Rate: 5.738693467336683e-05)
+
Train steps ... :  43%|████▎     | 42900/100000 [12:42:38<9:16:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42901/100000 [12:42:38<9:16:03,  1.71it/s]
Train steps ... :  43%|████▎     | 42902/100000 [12:42:39<9:15:59,  1.71it/s]
Train steps ... :  43%|████▎     | 42903/100000 [12:42:40<9:16:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42904/100000 [12:42:40<9:15:18,  1.71it/s]
Train steps ... :  43%|████▎     | 42905/100000 [12:42:41<9:15:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42906/100000 [12:42:41<9:15:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42907/100000 [12:42:42<9:15:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42908/100000 [12:42:43<9:15:34,  1.71it/s]
Train steps ... :  43%|████▎     | 42909/100000 [12:42:43<9:15:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42910/100000 [12:42:44<9:15:39,  1.71it/s]
Train steps ... :  43%|████▎     | 42911/100000 [12:42:44<9:15:38,  1.71it/s]
Train steps ... :  43%|████▎     | 42912/100000 [12:42:45<9:15:57,  1.71it/s]
Train steps ... :  43%|████▎     | 42913/100000 [12:42:45<9:16:37,  1.71it/s]
Train steps ... :  43%|████▎     | 42914/100000 [12:42:46<9:16:26,  1.71it/s]
Train steps ... :  43%|████▎     | 42915/100000 [12:42:47<9:15:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42916/100000 [12:42:47<9:15:29,  1.71it/s]
Train steps ... :  43%|████▎     | 42917/100000 [12:42:48<9:15:31,  1.71it/s]
Train steps ... :  43%|████▎     | 42918/100000 [12:42:48<9:15:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42919/100000 [12:42:49<9:15:51,  1.71it/s]
Train steps ... :  43%|████▎     | 42920/100000 [12:42:50<9:15:54,  1.71it/s]
Train steps ... :  43%|████▎     | 42921/100000 [12:42:50<9:16:32,  1.71it/s]
Train steps ... :  43%|████▎     | 42922/100000 [12:42:51<9:15:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42923/100000 [12:42:51<9:15:44,  1.71it/s]
Train steps ... :  43%|████▎     | 42924/100000 [12:42:52<9:15:57,  1.71it/s]
Train steps ... :  43%|████▎     | 42925/100000 [12:42:52<9:15:46,  1.71it/s]Step... (42925 / 100000 | Loss: 0.8026376962661743, Learning Rate: 5.736180904522613e-05)
+
                                                                             
Step... (42925 / 100000 | Loss: 0.596493661403656, Learning Rate: 5.736180904522613e-05)
+
Train steps ... :  43%|████▎     | 42925/100000 [12:42:53<9:15:46,  1.71it/s]
Train steps ... :  43%|████▎     | 42926/100000 [12:42:53<9:15:49,  1.71it/s]
Train steps ... :  43%|████▎     | 42927/100000 [12:42:54<9:15:34,  1.71it/s]
Train steps ... :  43%|████▎     | 42928/100000 [12:42:54<9:16:24,  1.71it/s]
Train steps ... :  43%|████▎     | 42929/100000 [12:42:55<9:16:37,  1.71it/s]
Train steps ... :  43%|████▎     | 42930/100000 [12:42:55<9:16:40,  1.71it/s]
Train steps ... :  43%|████▎     | 42931/100000 [12:42:56<9:15:53,  1.71it/s]
Train steps ... :  43%|████▎     | 42932/100000 [12:42:57<9:16:16,  1.71it/s]
Train steps ... :  43%|████▎     | 42933/100000 [12:42:57<9:15:32,  1.71it/s]
Train steps ... :  43%|████▎     | 42934/100000 [12:42:58<9:16:14,  1.71it/s]
Train steps ... :  43%|████▎     | 42935/100000 [12:42:58<9:16:43,  1.71it/s]
Train steps ... :  43%|████▎     | 42936/100000 [12:42:59<9:16:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42937/100000 [12:42:59<9:16:59,  1.71it/s]
Train steps ... :  43%|████▎     | 42938/100000 [12:43:00<9:17:33,  1.71it/s]
Train steps ... :  43%|████▎     | 42939/100000 [12:43:01<9:16:34,  1.71it/s]
Train steps ... :  43%|████▎     | 42940/100000 [12:43:01<9:17:26,  1.71it/s]
Train steps ... :  43%|████▎     | 42941/100000 [12:43:02<9:15:57,  1.71it/s]
Train steps ... :  43%|████▎     | 42942/100000 [12:43:02<9:15:16,  1.71it/s]
Train steps ... :  43%|████▎     | 42943/100000 [12:43:03<9:15:28,  1.71it/s]
Train steps ... :  43%|████▎     | 42944/100000 [12:43:04<9:15:23,  1.71it/s]
Train steps ... :  43%|████▎     | 42945/100000 [12:43:04<9:15:53,  1.71it/s]
Train steps ... :  43%|████▎     | 42946/100000 [12:43:05<9:16:12,  1.71it/s]
Train steps ... :  43%|████▎     | 42947/100000 [12:43:05<9:16:17,  1.71it/s]
Train steps ... :  43%|████▎     | 42948/100000 [12:43:06<9:15:46,  1.71it/s]
Train steps ... :  43%|████▎     | 42949/100000 [12:43:06<9:15:36,  1.71it/s]
Train steps ... :  43%|████▎     | 42950/100000 [12:43:07<9:15:47,  1.71it/s]Step... (42950 / 100000 | Loss: 0.8661254644393921, Learning Rate: 5.7336683417085437e-05)
+
                                                                             
Step... (42950 / 100000 | Loss: 0.9048373699188232, Learning Rate: 5.7336683417085437e-05)
+
Train steps ... :  43%|████▎     | 42950/100000 [12:43:07<9:15:47,  1.71it/s]
Train steps ... :  43%|████▎     | 42951/100000 [12:43:08<9:15:43,  1.71it/s]
Train steps ... :  43%|████▎     | 42952/100000 [12:43:08<9:15:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42953/100000 [12:43:09<9:16:17,  1.71it/s]
Train steps ... :  43%|████▎     | 42954/100000 [12:43:09<9:15:51,  1.71it/s]
Train steps ... :  43%|████▎     | 42955/100000 [12:43:10<9:15:37,  1.71it/s]
Train steps ... :  43%|████▎     | 42956/100000 [12:43:11<9:16:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42957/100000 [12:43:11<9:15:49,  1.71it/s]
Train steps ... :  43%|████▎     | 42958/100000 [12:43:12<9:16:11,  1.71it/s]
Train steps ... :  43%|████▎     | 42959/100000 [12:43:12<9:15:59,  1.71it/s]
Train steps ... :  43%|████▎     | 42960/100000 [12:43:13<9:16:06,  1.71it/s]
Train steps ... :  43%|████▎     | 42961/100000 [12:43:13<9:15:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42962/100000 [12:43:14<9:16:06,  1.71it/s]
Train steps ... :  43%|████▎     | 42963/100000 [12:43:15<9:15:53,  1.71it/s]
Train steps ... :  43%|████▎     | 42964/100000 [12:43:15<9:15:50,  1.71it/s]
Train steps ... :  43%|████▎     | 42965/100000 [12:43:16<9:16:05,  1.71it/s]
Train steps ... :  43%|████▎     | 42966/100000 [12:43:16<9:15:34,  1.71it/s]
Train steps ... :  43%|████▎     | 42967/100000 [12:43:17<9:15:52,  1.71it/s]
Train steps ... :  43%|████▎     | 42968/100000 [12:43:18<9:14:56,  1.71it/s]
Train steps ... :  43%|████▎     | 42969/100000 [12:43:18<9:14:54,  1.71it/s]
Train steps ... :  43%|████▎     | 42970/100000 [12:43:19<9:15:04,  1.71it/s]
Train steps ... :  43%|████▎     | 42971/100000 [12:43:19<9:15:14,  1.71it/s]
Train steps ... :  43%|████▎     | 42972/100000 [12:43:20<9:15:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42973/100000 [12:43:21<9:14:58,  1.71it/s]
Train steps ... :  43%|████▎     | 42974/100000 [12:43:21<9:15:53,  1.71it/s]
Train steps ... :  43%|████▎     | 42975/100000 [12:43:22<9:15:49,  1.71it/s]Step... (42975 / 100000 | Loss: 0.7091888189315796, Learning Rate: 5.7311557788944726e-05)
+
                                                                             
Step... (42975 / 100000 | Loss: 0.6312949061393738, Learning Rate: 5.7311557788944726e-05)
+
Train steps ... :  43%|████▎     | 42975/100000 [12:43:22<9:15:49,  1.71it/s]
Train steps ... :  43%|████▎     | 42976/100000 [12:43:22<9:15:24,  1.71it/s]
Train steps ... :  43%|████▎     | 42977/100000 [12:43:23<9:15:38,  1.71it/s]
Train steps ... :  43%|████▎     | 42978/100000 [12:43:23<9:14:55,  1.71it/s]
Train steps ... :  43%|████▎     | 42979/100000 [12:43:24<9:14:46,  1.71it/s]
Train steps ... :  43%|████▎     | 42980/100000 [12:43:25<9:15:00,  1.71it/s]
Train steps ... :  43%|████▎     | 42981/100000 [12:43:25<9:14:54,  1.71it/s]
Train steps ... :  43%|████▎     | 42982/100000 [12:43:26<9:15:06,  1.71it/s]
Train steps ... :  43%|████▎     | 42983/100000 [12:43:26<9:15:35,  1.71it/s]
Train steps ... :  43%|████▎     | 42984/100000 [12:43:27<9:16:13,  1.71it/s]
Train steps ... :  43%|████▎     | 42985/100000 [12:43:28<9:15:34,  1.71it/s]
Train steps ... :  43%|████▎     | 42986/100000 [12:43:28<9:15:29,  1.71it/s]
Train steps ... :  43%|████▎     | 42987/100000 [12:43:29<9:15:42,  1.71it/s]
Train steps ... :  43%|████▎     | 42988/100000 [12:43:29<9:15:15,  1.71it/s]
Train steps ... :  43%|████▎     | 42989/100000 [12:43:30<9:15:22,  1.71it/s]
Train steps ... :  43%|████▎     | 42990/100000 [12:43:30<9:15:41,  1.71it/s]
Train steps ... :  43%|████▎     | 42991/100000 [12:43:31<9:15:24,  1.71it/s]
Train steps ... :  43%|████▎     | 42992/100000 [12:43:32<9:15:03,  1.71it/s]
Train steps ... :  43%|████▎     | 42993/100000 [12:43:32<9:15:56,  1.71it/s]
Train steps ... :  43%|████▎     | 42994/100000 [12:43:33<9:14:52,  1.71it/s]
Train steps ... :  43%|████▎     | 42995/100000 [12:43:33<9:14:27,  1.71it/s]
Train steps ... :  43%|████▎     | 42996/100000 [12:43:34<9:14:26,  1.71it/s]
Train steps ... :  43%|████▎     | 42997/100000 [12:43:35<9:14:20,  1.71it/s]
Train steps ... :  43%|████▎     | 42998/100000 [12:43:35<9:14:25,  1.71it/s]
Train steps ... :  43%|████▎     | 42999/100000 [12:43:36<9:14:22,  1.71it/s]
Train steps ... :  43%|████▎     | 43000/100000 [12:43:36<9:15:49,  1.71it/s]Step... (43000 / 100000 | Loss: 0.7180966138839722, Learning Rate: 5.728643216080403e-05)
+
                                                                             
Step... (43000 / 100000 | Loss: 1.0522644519805908, Learning Rate: 5.728643216080403e-05)
+
Train steps ... :  43%|████▎     | 43000/100000 [12:43:37<9:15:49,  1.71it/s]
Train steps ... :  43%|████▎     | 43001/100000 [12:43:37<9:15:26,  1.71it/s]
Train steps ... :  43%|████▎     | 43002/100000 [12:43:37<9:15:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43003/100000 [12:43:38<9:15:18,  1.71it/s]
Train steps ... :  43%|████▎     | 43004/100000 [12:43:39<9:14:39,  1.71it/s]
Train steps ... :  43%|████▎     | 43005/100000 [12:43:39<9:14:56,  1.71it/s]
Train steps ... :  43%|████▎     | 43006/100000 [12:43:40<9:15:21,  1.71it/s]
Train steps ... :  43%|████▎     | 43007/100000 [12:43:40<9:15:32,  1.71it/s]
Train steps ... :  43%|████▎     | 43008/100000 [12:43:41<9:15:50,  1.71it/s]
Train steps ... :  43%|████▎     | 43009/100000 [12:43:42<9:15:17,  1.71it/s]
Train steps ... :  43%|████▎     | 43010/100000 [12:43:42<9:15:23,  1.71it/s]
Train steps ... :  43%|████▎     | 43011/100000 [12:43:43<9:15:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43012/100000 [12:43:43<9:15:30,  1.71it/s]
Train steps ... :  43%|████▎     | 43013/100000 [12:43:44<9:15:17,  1.71it/s]
Train steps ... :  43%|████▎     | 43014/100000 [12:43:44<9:15:59,  1.71it/s]
Train steps ... :  43%|████▎     | 43015/100000 [12:43:45<9:15:23,  1.71it/s]
Train steps ... :  43%|████▎     | 43016/100000 [12:43:46<9:15:38,  1.71it/s]
Train steps ... :  43%|████▎     | 43017/100000 [12:43:46<9:15:39,  1.71it/s]
Train steps ... :  43%|████▎     | 43018/100000 [12:43:47<9:15:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43019/100000 [12:43:47<9:15:14,  1.71it/s]
Train steps ... :  43%|████▎     | 43020/100000 [12:43:48<9:15:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43021/100000 [12:43:49<9:15:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43022/100000 [12:43:49<9:15:20,  1.71it/s]
Train steps ... :  43%|████▎     | 43023/100000 [12:43:50<9:15:03,  1.71it/s]
Train steps ... :  43%|████▎     | 43024/100000 [12:43:50<9:15:32,  1.71it/s]
Train steps ... :  43%|████▎     | 43025/100000 [12:43:51<9:14:46,  1.71it/s]Step... (43025 / 100000 | Loss: 0.6036837100982666, Learning Rate: 5.726130653266332e-05)
+
                                                                             
Step... (43025 / 100000 | Loss: 0.7153917551040649, Learning Rate: 5.726130653266332e-05)
+
Train steps ... :  43%|████▎     | 43025/100000 [12:43:51<9:14:46,  1.71it/s]
Train steps ... :  43%|████▎     | 43026/100000 [12:43:51<9:15:33,  1.71it/s]
Train steps ... :  43%|████▎     | 43027/100000 [12:43:52<9:15:21,  1.71it/s]
Train steps ... :  43%|████▎     | 43028/100000 [12:43:53<9:15:07,  1.71it/s]
Train steps ... :  43%|████▎     | 43029/100000 [12:43:53<9:15:22,  1.71it/s]
Train steps ... :  43%|████▎     | 43030/100000 [12:43:54<9:14:51,  1.71it/s]
Train steps ... :  43%|████▎     | 43031/100000 [12:43:54<9:14:51,  1.71it/s]
Train steps ... :  43%|████▎     | 43032/100000 [12:43:55<9:14:33,  1.71it/s]
Train steps ... :  43%|████▎     | 43033/100000 [12:43:56<9:15:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43034/100000 [12:43:56<9:15:27,  1.71it/s]
Train steps ... :  43%|████▎     | 43035/100000 [12:43:57<9:14:56,  1.71it/s]
Train steps ... :  43%|████▎     | 43036/100000 [12:43:57<9:15:08,  1.71it/s]
Train steps ... :  43%|████▎     | 43037/100000 [12:43:58<9:15:40,  1.71it/s]
Train steps ... :  43%|████▎     | 43038/100000 [12:43:59<9:15:40,  1.71it/s]
Train steps ... :  43%|████▎     | 43039/100000 [12:43:59<9:14:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43040/100000 [12:44:00<9:15:17,  1.71it/s]
Train steps ... :  43%|████▎     | 43041/100000 [12:44:00<9:14:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43042/100000 [12:44:01<9:14:14,  1.71it/s]
Train steps ... :  43%|████▎     | 43043/100000 [12:44:01<9:14:58,  1.71it/s]
Train steps ... :  43%|████▎     | 43044/100000 [12:44:02<9:15:57,  1.71it/s]
Train steps ... :  43%|████▎     | 43045/100000 [12:44:03<9:14:32,  1.71it/s]
Train steps ... :  43%|████▎     | 43046/100000 [12:44:03<9:14:50,  1.71it/s]
Train steps ... :  43%|████▎     | 43047/100000 [12:44:04<9:15:08,  1.71it/s]
Train steps ... :  43%|████▎     | 43048/100000 [12:44:04<9:15:47,  1.71it/s]
Train steps ... :  43%|████▎     | 43049/100000 [12:44:05<9:15:16,  1.71it/s]
Train steps ... :  43%|████▎     | 43050/100000 [12:44:06<9:15:51,  1.71it/s]Step... (43050 / 100000 | Loss: 1.0740199089050293, Learning Rate: 5.7236180904522616e-05)
+
                                                                             
Step... (43050 / 100000 | Loss: 0.8092279434204102, Learning Rate: 5.7236180904522616e-05)
+
Train steps ... :  43%|████▎     | 43050/100000 [12:44:06<9:15:51,  1.71it/s]
Train steps ... :  43%|████▎     | 43051/100000 [12:44:06<9:16:00,  1.71it/s]
Train steps ... :  43%|████▎     | 43052/100000 [12:44:07<9:15:07,  1.71it/s]
Train steps ... :  43%|████▎     | 43053/100000 [12:44:07<9:14:38,  1.71it/s]
Train steps ... :  43%|████▎     | 43054/100000 [12:44:08<9:14:54,  1.71it/s]
Train steps ... :  43%|████▎     | 43055/100000 [12:44:08<9:14:45,  1.71it/s]
Train steps ... :  43%|████▎     | 43056/100000 [12:44:09<9:14:23,  1.71it/s]
Train steps ... :  43%|████▎     | 43057/100000 [12:44:10<9:14:17,  1.71it/s]
Train steps ... :  43%|████▎     | 43058/100000 [12:44:10<9:14:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43059/100000 [12:44:11<9:14:47,  1.71it/s]
Train steps ... :  43%|████▎     | 43060/100000 [12:44:11<9:14:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43061/100000 [12:44:12<9:15:00,  1.71it/s]
Train steps ... :  43%|████▎     | 43062/100000 [12:44:13<9:14:16,  1.71it/s]
Train steps ... :  43%|████▎     | 43063/100000 [12:44:13<9:14:38,  1.71it/s]
Train steps ... :  43%|████▎     | 43064/100000 [12:44:14<9:14:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43065/100000 [12:44:14<9:14:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43066/100000 [12:44:15<9:14:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43067/100000 [12:44:15<9:14:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43068/100000 [12:44:16<9:14:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43069/100000 [12:44:17<9:14:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43070/100000 [12:44:17<9:14:20,  1.71it/s]
Train steps ... :  43%|████▎     | 43071/100000 [12:44:18<9:14:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43072/100000 [12:44:18<9:13:50,  1.71it/s]
Train steps ... :  43%|████▎     | 43073/100000 [12:44:19<9:14:42,  1.71it/s]
Train steps ... :  43%|████▎     | 43074/100000 [12:44:20<9:14:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43075/100000 [12:44:20<9:14:41,  1.71it/s]Step... (43075 / 100000 | Loss: 0.8736311197280884, Learning Rate: 5.7211055276381906e-05)
+
                                                                             
Step... (43075 / 100000 | Loss: 0.6253199577331543, Learning Rate: 5.7211055276381906e-05)
+
Train steps ... :  43%|████▎     | 43075/100000 [12:44:20<9:14:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43076/100000 [12:44:21<9:16:57,  1.70it/s]
Train steps ... :  43%|████▎     | 43077/100000 [12:44:21<9:14:50,  1.71it/s]
Train steps ... :  43%|████▎     | 43078/100000 [12:44:22<9:14:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43079/100000 [12:44:22<9:14:52,  1.71it/s]
Train steps ... :  43%|████▎     | 43080/100000 [12:44:23<9:15:17,  1.71it/s]
Train steps ... :  43%|████▎     | 43081/100000 [12:44:24<9:15:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43082/100000 [12:44:24<9:14:46,  1.71it/s]
Train steps ... :  43%|████▎     | 43083/100000 [12:44:25<9:15:25,  1.71it/s]
Train steps ... :  43%|████▎     | 43084/100000 [12:44:25<9:15:35,  1.71it/s]
Train steps ... :  43%|████▎     | 43085/100000 [12:44:26<9:15:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43086/100000 [12:44:27<9:15:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43087/100000 [12:44:27<9:14:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43088/100000 [12:44:28<9:15:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43089/100000 [12:44:28<9:15:46,  1.71it/s]
Train steps ... :  43%|████▎     | 43090/100000 [12:44:29<9:15:15,  1.71it/s]
Train steps ... :  43%|████▎     | 43091/100000 [12:44:29<9:14:49,  1.71it/s]
Train steps ... :  43%|████▎     | 43092/100000 [12:44:30<9:14:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43093/100000 [12:44:31<9:14:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43094/100000 [12:44:31<9:14:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43095/100000 [12:44:32<9:15:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43096/100000 [12:44:32<9:13:52,  1.71it/s]
Train steps ... :  43%|████▎     | 43097/100000 [12:44:33<9:14:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43098/100000 [12:44:34<9:14:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43099/100000 [12:44:34<9:13:58,  1.71it/s]
Train steps ... :  43%|████▎     | 43100/100000 [12:44:35<9:14:12,  1.71it/s]Step... (43100 / 100000 | Loss: 1.0810050964355469, Learning Rate: 5.718592964824121e-05)
+
                                                                             
Step... (43100 / 100000 | Loss: 0.6285210251808167, Learning Rate: 5.718592964824121e-05)
+
Train steps ... :  43%|████▎     | 43100/100000 [12:44:35<9:14:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43101/100000 [12:44:35<9:13:57,  1.71it/s]
Train steps ... :  43%|████▎     | 43102/100000 [12:44:36<9:14:30,  1.71it/s]
Train steps ... :  43%|████▎     | 43103/100000 [12:44:37<9:14:20,  1.71it/s]
Train steps ... :  43%|████▎     | 43104/100000 [12:44:37<9:14:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43105/100000 [12:44:38<9:14:11,  1.71it/s]
Train steps ... :  43%|████▎     | 43106/100000 [12:44:38<9:14:50,  1.71it/s]
Train steps ... :  43%|████▎     | 43107/100000 [12:44:39<9:14:57,  1.71it/s]
Train steps ... :  43%|████▎     | 43108/100000 [12:44:39<9:14:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43109/100000 [12:44:40<9:13:46,  1.71it/s]
Train steps ... :  43%|████▎     | 43110/100000 [12:44:41<9:14:24,  1.71it/s]
Train steps ... :  43%|████▎     | 43111/100000 [12:44:41<9:14:50,  1.71it/s]
Train steps ... :  43%|████▎     | 43112/100000 [12:44:42<9:14:33,  1.71it/s]
Train steps ... :  43%|████▎     | 43113/100000 [12:44:42<9:14:03,  1.71it/s]
Train steps ... :  43%|████▎     | 43114/100000 [12:44:43<9:14:01,  1.71it/s]
Train steps ... :  43%|████▎     | 43115/100000 [12:44:44<9:14:03,  1.71it/s]
Train steps ... :  43%|████▎     | 43116/100000 [12:44:44<9:14:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43117/100000 [12:44:45<9:14:11,  1.71it/s]
Train steps ... :  43%|████▎     | 43118/100000 [12:44:45<9:14:39,  1.71it/s]
Train steps ... :  43%|████▎     | 43119/100000 [12:44:46<9:14:36,  1.71it/s]
Train steps ... :  43%|████▎     | 43120/100000 [12:44:46<9:14:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43121/100000 [12:44:47<9:14:14,  1.71it/s]
Train steps ... :  43%|████▎     | 43122/100000 [12:44:48<9:14:03,  1.71it/s]
Train steps ... :  43%|████▎     | 43123/100000 [12:44:48<9:13:36,  1.71it/s]
Train steps ... :  43%|████▎     | 43124/100000 [12:44:49<9:13:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43125/100000 [12:44:49<9:13:36,  1.71it/s]Step... (43125 / 100000 | Loss: 0.906683087348938, Learning Rate: 5.71608040201005e-05)
+
                                                                             
Step... (43125 / 100000 | Loss: 0.6192018985748291, Learning Rate: 5.71608040201005e-05)
+
Train steps ... :  43%|████▎     | 43125/100000 [12:44:50<9:13:36,  1.71it/s]
Train steps ... :  43%|████▎     | 43126/100000 [12:44:50<9:13:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43127/100000 [12:44:51<9:13:28,  1.71it/s]
Train steps ... :  43%|████▎     | 43128/100000 [12:44:51<9:13:28,  1.71it/s]
Train steps ... :  43%|████▎     | 43129/100000 [12:44:52<9:13:25,  1.71it/s]
Train steps ... :  43%|████▎     | 43130/100000 [12:44:52<9:14:15,  1.71it/s]
Train steps ... :  43%|████▎     | 43131/100000 [12:44:53<9:15:18,  1.71it/s]
Train steps ... :  43%|████▎     | 43132/100000 [12:44:53<9:14:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43133/100000 [12:44:54<9:13:46,  1.71it/s]
Train steps ... :  43%|████▎     | 43134/100000 [12:44:55<9:14:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43135/100000 [12:44:55<9:14:43,  1.71it/s]
Train steps ... :  43%|████▎     | 43136/100000 [12:44:56<9:14:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43137/100000 [12:44:56<9:13:43,  1.71it/s]
Train steps ... :  43%|████▎     | 43138/100000 [12:44:57<9:13:25,  1.71it/s]
Train steps ... :  43%|████▎     | 43139/100000 [12:44:58<9:13:54,  1.71it/s]
Train steps ... :  43%|████▎     | 43140/100000 [12:44:58<9:13:51,  1.71it/s]
Train steps ... :  43%|████▎     | 43141/100000 [12:44:59<9:14:17,  1.71it/s]
Train steps ... :  43%|████▎     | 43142/100000 [12:44:59<9:14:21,  1.71it/s]
Train steps ... :  43%|████▎     | 43143/100000 [12:45:00<9:13:26,  1.71it/s]
Train steps ... :  43%|████▎     | 43144/100000 [12:45:00<9:14:18,  1.71it/s]
Train steps ... :  43%|████▎     | 43145/100000 [12:45:01<9:14:53,  1.71it/s]
Train steps ... :  43%|████▎     | 43146/100000 [12:45:02<9:14:57,  1.71it/s]
Train steps ... :  43%|████▎     | 43147/100000 [12:45:02<9:14:53,  1.71it/s]
Train steps ... :  43%|████▎     | 43148/100000 [12:45:03<9:14:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43149/100000 [12:45:03<9:15:25,  1.71it/s]
Train steps ... :  43%|████▎     | 43150/100000 [12:45:04<9:15:04,  1.71it/s]Step... (43150 / 100000 | Loss: 0.7662903666496277, Learning Rate: 5.71356783919598e-05)
+
                                                                             
Step... (43150 / 100000 | Loss: 0.5833225846290588, Learning Rate: 5.71356783919598e-05)
+
Train steps ... :  43%|████▎     | 43150/100000 [12:45:04<9:15:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43151/100000 [12:45:05<9:14:39,  1.71it/s]
Train steps ... :  43%|████▎     | 43152/100000 [12:45:05<9:14:42,  1.71it/s]
Train steps ... :  43%|████▎     | 43153/100000 [12:45:06<9:14:08,  1.71it/s]
Train steps ... :  43%|████▎     | 43154/100000 [12:45:06<9:13:58,  1.71it/s]
Train steps ... :  43%|████▎     | 43155/100000 [12:45:07<9:13:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43156/100000 [12:45:08<9:14:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43157/100000 [12:45:08<9:13:28,  1.71it/s]
Train steps ... :  43%|████▎     | 43158/100000 [12:45:09<9:14:01,  1.71it/s]
Train steps ... :  43%|████▎     | 43159/100000 [12:45:09<9:13:28,  1.71it/s]
Train steps ... :  43%|████▎     | 43160/100000 [12:45:10<9:13:39,  1.71it/s]
Train steps ... :  43%|████▎     | 43161/100000 [12:45:10<9:13:27,  1.71it/s]
Train steps ... :  43%|████▎     | 43162/100000 [12:45:11<9:13:30,  1.71it/s]
Train steps ... :  43%|████▎     | 43163/100000 [12:45:12<9:13:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43164/100000 [12:45:12<9:12:46,  1.71it/s]
Train steps ... :  43%|████▎     | 43165/100000 [12:45:13<9:13:54,  1.71it/s]
Train steps ... :  43%|████▎     | 43166/100000 [12:45:13<9:14:03,  1.71it/s]
Train steps ... :  43%|████▎     | 43167/100000 [12:45:14<9:13:08,  1.71it/s]
Train steps ... :  43%|████▎     | 43168/100000 [12:45:15<9:13:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43169/100000 [12:45:15<9:13:40,  1.71it/s]
Train steps ... :  43%|████▎     | 43170/100000 [12:45:16<9:14:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43171/100000 [12:45:16<9:13:37,  1.71it/s]
Train steps ... :  43%|��███▎     | 43172/100000 [12:45:17<9:14:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43173/100000 [12:45:17<9:14:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43174/100000 [12:45:18<9:14:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43175/100000 [12:45:19<9:14:31,  1.71it/s]Step... (43175 / 100000 | Loss: 0.6631896495819092, Learning Rate: 5.7110552763819106e-05)
+
                                                                             
Step... (43175 / 100000 | Loss: 0.5742429494857788, Learning Rate: 5.7110552763819106e-05)
+
Train steps ... :  43%|████▎     | 43175/100000 [12:45:19<9:14:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43176/100000 [12:45:19<9:14:23,  1.71it/s]
Train steps ... :  43%|████▎     | 43177/100000 [12:45:20<9:13:57,  1.71it/s]
Train steps ... :  43%|████▎     | 43178/100000 [12:45:20<9:13:42,  1.71it/s]
Train steps ... :  43%|████▎     | 43179/100000 [12:45:21<9:13:07,  1.71it/s]
Train steps ... :  43%|████▎     | 43180/100000 [12:45:22<9:12:40,  1.71it/s]
Train steps ... :  43%|████▎     | 43181/100000 [12:45:22<9:12:46,  1.71it/s]
Train steps ... :  43%|████▎     | 43182/100000 [12:45:23<9:13:20,  1.71it/s]
Train steps ... :  43%|████▎     | 43183/100000 [12:45:23<9:13:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43184/100000 [12:45:24<9:13:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43185/100000 [12:45:24<9:13:20,  1.71it/s]
Train steps ... :  43%|████▎     | 43186/100000 [12:45:25<9:13:21,  1.71it/s]
Train steps ... :  43%|████▎     | 43187/100000 [12:45:26<9:13:52,  1.71it/s]
Train steps ... :  43%|████▎     | 43188/100000 [12:45:26<9:13:50,  1.71it/s]
Train steps ... :  43%|████▎     | 43189/100000 [12:45:27<9:13:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43190/100000 [12:45:27<9:13:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43191/100000 [12:45:28<9:12:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43192/100000 [12:45:29<9:13:07,  1.71it/s]
Train steps ... :  43%|████▎     | 43193/100000 [12:45:29<9:13:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43194/100000 [12:45:30<9:13:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43195/100000 [12:45:30<9:13:35,  1.71it/s]
Train steps ... :  43%|████▎     | 43196/100000 [12:45:31<9:13:15,  1.71it/s]
Train steps ... :  43%|████▎     | 43197/100000 [12:45:31<9:13:43,  1.71it/s]
Train steps ... :  43%|████▎     | 43198/100000 [12:45:32<9:13:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43199/100000 [12:45:33<9:13:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43200/100000 [12:45:33<9:13:26,  1.71it/s]Step... (43200 / 100000 | Loss: 1.1755297183990479, Learning Rate: 5.7085427135678396e-05)
+
                                                                             
Step... (43200 / 100000 | Loss: 0.7260657548904419, Learning Rate: 5.7085427135678396e-05)
+
Train steps ... :  43%|████▎     | 43200/100000 [12:45:34<9:13:26,  1.71it/s]
Train steps ... :  43%|████▎     | 43201/100000 [12:45:34<9:14:23,  1.71it/s]
Train steps ... :  43%|████▎     | 43202/100000 [12:45:34<9:14:11,  1.71it/s]
Train steps ... :  43%|████▎     | 43203/100000 [12:45:35<9:13:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43204/100000 [12:45:36<9:13:21,  1.71it/s]
Train steps ... :  43%|████▎     | 43205/100000 [12:45:36<9:13:39,  1.71it/s]
Train steps ... :  43%|████▎     | 43206/100000 [12:45:37<9:14:21,  1.71it/s]
Train steps ... :  43%|████▎     | 43207/100000 [12:45:37<9:14:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43208/100000 [12:45:38<9:13:46,  1.71it/s]
Train steps ... :  43%|████▎     | 43209/100000 [12:45:38<9:14:34,  1.71it/s]
Train steps ... :  43%|████▎     | 43210/100000 [12:45:39<9:15:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43211/100000 [12:45:40<9:14:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43212/100000 [12:45:40<9:13:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43213/100000 [12:45:41<9:13:46,  1.71it/s]
Train steps ... :  43%|████▎     | 43214/100000 [12:45:41<9:13:51,  1.71it/s]
Train steps ... :  43%|████▎     | 43215/100000 [12:45:42<9:14:11,  1.71it/s]
Train steps ... :  43%|████▎     | 43216/100000 [12:45:43<9:13:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43217/100000 [12:45:43<9:13:35,  1.71it/s]
Train steps ... :  43%|████▎     | 43218/100000 [12:45:44<9:13:11,  1.71it/s]
Train steps ... :  43%|████▎     | 43219/100000 [12:45:44<9:12:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43220/100000 [12:45:45<9:12:47,  1.71it/s]
Train steps ... :  43%|████▎     | 43221/100000 [12:45:46<9:12:35,  1.71it/s]
Train steps ... :  43%|████▎     | 43222/100000 [12:45:46<9:13:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43223/100000 [12:45:47<9:12:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43224/100000 [12:45:47<9:12:45,  1.71it/s]
Train steps ... :  43%|████▎     | 43225/100000 [12:45:48<9:12:39,  1.71it/s]Step... (43225 / 100000 | Loss: 1.0147705078125, Learning Rate: 5.706030150753769e-05)
+
                                                                             
Step... (43225 / 100000 | Loss: 0.8214808702468872, Learning Rate: 5.706030150753769e-05)
+
Train steps ... :  43%|████▎     | 43225/100000 [12:45:48<9:12:39,  1.71it/s]
Train steps ... :  43%|████▎     | 43226/100000 [12:45:48<9:12:51,  1.71it/s]
Train steps ... :  43%|████▎     | 43227/100000 [12:45:49<9:13:08,  1.71it/s]
Train steps ... :  43%|████▎     | 43228/100000 [12:45:50<9:13:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43229/100000 [12:45:50<9:13:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43230/100000 [12:45:51<9:13:53,  1.71it/s]
Train steps ... :  43%|████▎     | 43231/100000 [12:45:51<9:13:36,  1.71it/s]
Train steps ... :  43%|████▎     | 43232/100000 [12:45:52<9:14:19,  1.71it/s]
Train steps ... :  43%|████▎     | 43233/100000 [12:45:53<9:13:58,  1.71it/s]
Train steps ... :  43%|████▎     | 43234/100000 [12:45:53<9:13:23,  1.71it/s]
Train steps ... :  43%|████▎     | 43235/100000 [12:45:54<9:13:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43236/100000 [12:45:54<9:13:43,  1.71it/s]
Train steps ... :  43%|████▎     | 43237/100000 [12:45:55<9:14:20,  1.71it/s]
Train steps ... :  43%|████▎     | 43238/100000 [12:45:55<9:13:52,  1.71it/s]
Train steps ... :  43%|████▎     | 43239/100000 [12:45:56<9:13:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43240/100000 [12:45:57<9:13:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43241/100000 [12:45:57<9:12:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43242/100000 [12:45:58<9:12:22,  1.71it/s]
Train steps ... :  43%|████▎     | 43243/100000 [12:45:58<9:12:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43244/100000 [12:45:59<9:12:23,  1.71it/s]
Train steps ... :  43%|████▎     | 43245/100000 [12:46:00<9:11:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43246/100000 [12:46:00<9:12:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43247/100000 [12:46:01<9:12:28,  1.71it/s]
Train steps ... :  43%|████▎     | 43248/100000 [12:46:01<9:13:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43249/100000 [12:46:02<9:12:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43250/100000 [12:46:02<9:12:05,  1.71it/s]Step... (43250 / 100000 | Loss: 1.1293706893920898, Learning Rate: 5.703517587939698e-05)
+
                                                                             
Step... (43250 / 100000 | Loss: 0.7205689549446106, Learning Rate: 5.703517587939698e-05)
+
Train steps ... :  43%|████▎     | 43250/100000 [12:46:03<9:12:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43251/100000 [12:46:03<9:13:15,  1.71it/s]
Train steps ... :  43%|████▎     | 43252/100000 [12:46:04<9:13:26,  1.71it/s]
Train steps ... :  43%|████▎     | 43253/100000 [12:46:04<9:13:39,  1.71it/s]
Train steps ... :  43%|████▎     | 43254/100000 [12:46:05<9:13:02,  1.71it/s]
Train steps ... :  43%|████▎     | 43255/100000 [12:46:05<9:13:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43256/100000 [12:46:06<9:13:08,  1.71it/s]
Train steps ... :  43%|████▎     | 43257/100000 [12:46:07<9:12:34,  1.71it/s]
Train steps ... :  43%|████▎     | 43258/100000 [12:46:07<9:12:58,  1.71it/s]
Train steps ... :  43%|████▎     | 43259/100000 [12:46:08<9:12:47,  1.71it/s]
Train steps ... :  43%|████▎     | 43260/100000 [12:46:08<9:12:33,  1.71it/s]
Train steps ... :  43%|████▎     | 43261/100000 [12:46:09<9:12:25,  1.71it/s]
Train steps ... :  43%|████▎     | 43262/100000 [12:46:09<9:12:50,  1.71it/s]
Train steps ... :  43%|████▎     | 43263/100000 [12:46:10<9:12:20,  1.71it/s]
Train steps ... :  43%|████▎     | 43264/100000 [12:46:11<9:12:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43265/100000 [12:46:11<9:13:15,  1.71it/s]
Train steps ... :  43%|████▎     | 43266/100000 [12:46:12<9:12:47,  1.71it/s]
Train steps ... :  43%|████▎     | 43267/100000 [12:46:12<9:12:27,  1.71it/s]
Train steps ... :  43%|████▎     | 43268/100000 [12:46:13<9:13:32,  1.71it/s]
Train steps ... :  43%|████▎     | 43269/100000 [12:46:14<9:13:57,  1.71it/s]
Train steps ... :  43%|████▎     | 43270/100000 [12:46:14<9:13:32,  1.71it/s]
Train steps ... :  43%|████▎     | 43271/100000 [12:46:15<9:12:56,  1.71it/s]
Train steps ... :  43%|████▎     | 43272/100000 [12:46:15<9:12:26,  1.71it/s]
Train steps ... :  43%|████▎     | 43273/100000 [12:46:16<9:12:24,  1.71it/s]
Train steps ... :  43%|████▎     | 43274/100000 [12:46:16<9:12:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43275/100000 [12:46:17<9:12:11,  1.71it/s]Step... (43275 / 100000 | Loss: 0.7063236236572266, Learning Rate: 5.7010050251256286e-05)
+
                                                                             
Step... (43275 / 100000 | Loss: 0.7663590908050537, Learning Rate: 5.7010050251256286e-05)
+
Train steps ... :  43%|████▎     | 43275/100000 [12:46:17<9:12:11,  1.71it/s]
Train steps ... :  43%|████▎     | 43276/100000 [12:46:18<9:12:38,  1.71it/s]
Train steps ... :  43%|████▎     | 43277/100000 [12:46:18<9:12:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43278/100000 [12:46:19<9:13:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43279/100000 [12:46:19<9:12:23,  1.71it/s]
Train steps ... :  43%|████▎     | 43280/100000 [12:46:20<9:12:17,  1.71it/s]
Train steps ... :  43%|████▎     | 43281/100000 [12:46:21<9:12:57,  1.71it/s]
Train steps ... :  43%|████▎     | 43282/100000 [12:46:21<9:12:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43283/100000 [12:46:22<9:12:16,  1.71it/s]
Train steps ... :  43%|████▎     | 43284/100000 [12:46:22<9:12:56,  1.71it/s]
Train steps ... :  43%|████▎     | 43285/100000 [12:46:23<9:12:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43286/100000 [12:46:24<9:12:59,  1.71it/s]
Train steps ... :  43%|████▎     | 43287/100000 [12:46:24<9:13:16,  1.71it/s]
Train steps ... :  43%|████▎     | 43288/100000 [12:46:25<9:13:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43289/100000 [12:46:25<9:12:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43290/100000 [12:46:26<9:11:58,  1.71it/s]
Train steps ... :  43%|████▎     | 43291/100000 [12:46:26<9:12:01,  1.71it/s]
Train steps ... :  43%|████▎     | 43292/100000 [12:46:27<9:11:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43293/100000 [12:46:28<9:11:40,  1.71it/s]
Train steps ... :  43%|████▎     | 43294/100000 [12:46:28<9:11:28,  1.71it/s]
Train steps ... :  43%|████▎     | 43295/100000 [12:46:29<9:11:43,  1.71it/s]
Train steps ... :  43%|████▎     | 43296/100000 [12:46:29<9:11:53,  1.71it/s]
Train steps ... :  43%|████▎     | 43297/100000 [12:46:30<9:11:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43298/100000 [12:46:31<9:12:07,  1.71it/s]
Train steps ... :  43%|████▎     | 43299/100000 [12:46:31<9:11:40,  1.71it/s]
Train steps ... :  43%|████▎     | 43300/100000 [12:46:32<9:12:13,  1.71it/s]Step... (43300 / 100000 | Loss: 1.0814601182937622, Learning Rate: 5.6984924623115576e-05)
+
                                                                             
Step... (43300 / 100000 | Loss: 0.8650766611099243, Learning Rate: 5.6984924623115576e-05)
+
Train steps ... :  43%|████▎     | 43300/100000 [12:46:32<9:12:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43301/100000 [12:46:32<9:14:11,  1.71it/s]
Train steps ... :  43%|████▎     | 43302/100000 [12:46:33<9:12:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43303/100000 [12:46:33<9:12:43,  1.71it/s]
Train steps ... :  43%|████▎     | 43304/100000 [12:46:34<9:12:18,  1.71it/s]
Train steps ... :  43%|████▎     | 43305/100000 [12:46:35<9:11:54,  1.71it/s]
Train steps ... :  43%|████▎     | 43306/100000 [12:46:35<9:12:08,  1.71it/s]
Train steps ... :  43%|████▎     | 43307/100000 [12:46:36<9:11:59,  1.71it/s]
Train steps ... :  43%|████▎     | 43308/100000 [12:46:36<9:12:16,  1.71it/s]
Train steps ... :  43%|████▎     | 43309/100000 [12:46:37<9:11:53,  1.71it/s]
Train steps ... :  43%|████▎     | 43310/100000 [12:46:38<9:12:24,  1.71it/s]
Train steps ... :  43%|████▎     | 43311/100000 [12:46:38<9:11:52,  1.71it/s]
Train steps ... :  43%|████▎     | 43312/100000 [12:46:39<9:12:02,  1.71it/s]
Train steps ... :  43%|████▎     | 43313/100000 [12:46:39<9:12:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43314/100000 [12:46:40<9:12:30,  1.71it/s]
Train steps ... :  43%|████▎     | 43315/100000 [12:46:40<9:12:45,  1.71it/s]
Train steps ... :  43%|████▎     | 43316/100000 [12:46:41<9:12:08,  1.71it/s]
Train steps ... :  43%|████▎     | 43317/100000 [12:46:42<9:12:43,  1.71it/s]
Train steps ... :  43%|████▎     | 43318/100000 [12:46:42<9:12:54,  1.71it/s]
Train steps ... :  43%|████▎     | 43319/100000 [12:46:43<9:11:32,  1.71it/s]
Train steps ... :  43%|████▎     | 43320/100000 [12:46:43<9:11:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43321/100000 [12:46:44<9:11:22,  1.71it/s]
Train steps ... :  43%|████▎     | 43322/100000 [12:46:45<9:11:42,  1.71it/s]
Train steps ... :  43%|████▎     | 43323/100000 [12:46:45<9:11:15,  1.71it/s]
Train steps ... :  43%|████▎     | 43324/100000 [12:46:46<9:10:58,  1.71it/s]
Train steps ... :  43%|████▎     | 43325/100000 [12:46:46<9:11:00,  1.71it/s]Step... (43325 / 100000 | Loss: 0.8158516883850098, Learning Rate: 5.695979899497488e-05)
+
                                                                             
Step... (43325 / 100000 | Loss: 0.8993954658508301, Learning Rate: 5.695979899497488e-05)
+
Train steps ... :  43%|████▎     | 43325/100000 [12:46:47<9:11:00,  1.71it/s]
Train steps ... :  43%|████▎     | 43326/100000 [12:46:47<9:11:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43327/100000 [12:46:47<9:10:41,  1.72it/s]
Train steps ... :  43%|████▎     | 43328/100000 [12:46:48<9:10:53,  1.71it/s]
Train steps ... :  43%|████▎     | 43329/100000 [12:46:49<9:11:13,  1.71it/s]
Train steps ... :  43%|████▎     | 43330/100000 [12:46:49<9:11:11,  1.71it/s]
Train steps ... :  43%|████▎     | 43331/100000 [12:46:50<9:11:08,  1.71it/s]
Train steps ... :  43%|████▎     | 43332/100000 [12:46:50<9:11:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43333/100000 [12:46:51<9:11:32,  1.71it/s]
Train steps ... :  43%|████▎     | 43334/100000 [12:46:52<9:11:48,  1.71it/s]
Train steps ... :  43%|████▎     | 43335/100000 [12:46:52<9:11:25,  1.71it/s]
Train steps ... :  43%|████▎     | 43336/100000 [12:46:53<9:11:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43337/100000 [12:46:53<9:11:42,  1.71it/s]
Train steps ... :  43%|████▎     | 43338/100000 [12:46:54<9:11:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43339/100000 [12:46:54<9:11:01,  1.71it/s]
Train steps ... :  43%|████▎     | 43340/100000 [12:46:55<9:11:00,  1.71it/s]
Train steps ... :  43%|████▎     | 43341/100000 [12:46:56<9:11:40,  1.71it/s]
Train steps ... :  43%|████▎     | 43342/100000 [12:46:56<9:12:02,  1.71it/s]
Train steps ... :  43%|████▎     | 43343/100000 [12:46:57<9:13:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43344/100000 [12:46:57<9:12:18,  1.71it/s]
Train steps ... :  43%|████▎     | 43345/100000 [12:46:58<9:12:21,  1.71it/s]
Train steps ... :  43%|████▎     | 43346/100000 [12:46:59<9:11:50,  1.71it/s]
Train steps ... :  43%|████▎     | 43347/100000 [12:46:59<9:12:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43348/100000 [12:47:00<9:12:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43349/100000 [12:47:00<9:12:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43350/100000 [12:47:01<9:12:49,  1.71it/s]Step... (43350 / 100000 | Loss: 0.6038047075271606, Learning Rate: 5.693467336683417e-05)
+
                                                                             
Step... (43350 / 100000 | Loss: 0.7621583938598633, Learning Rate: 5.693467336683417e-05)
+
Train steps ... :  43%|████▎     | 43350/100000 [12:47:01<9:12:49,  1.71it/s]
Train steps ... :  43%|████▎     | 43351/100000 [12:47:01<9:13:02,  1.71it/s]
Train steps ... :  43%|████▎     | 43352/100000 [12:47:02<9:13:00,  1.71it/s]
Train steps ... :  43%|████▎     | 43353/100000 [12:47:03<9:12:39,  1.71it/s]
Train steps ... :  43%|████▎     | 43354/100000 [12:47:03<9:12:33,  1.71it/s]
Train steps ... :  43%|████▎     | 43355/100000 [12:47:04<9:11:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43356/100000 [12:47:04<9:11:08,  1.71it/s]
Train steps ... :  43%|████▎     | 43357/100000 [12:47:05<9:11:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43358/100000 [12:47:06<9:11:01,  1.71it/s]
Train steps ... :  43%|████▎     | 43359/100000 [12:47:06<9:11:36,  1.71it/s]
Train steps ... :  43%|████▎     | 43360/100000 [12:47:07<9:11:50,  1.71it/s]
Train steps ... :  43%|████▎     | 43361/100000 [12:47:07<9:11:27,  1.71it/s]
Train steps ... :  43%|████▎     | 43362/100000 [12:47:08<9:11:33,  1.71it/s]
Train steps ... :  43%|████▎     | 43363/100000 [12:47:09<9:12:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43364/100000 [12:47:09<9:11:24,  1.71it/s]
Train steps ... :  43%|████▎     | 43365/100000 [12:47:10<9:11:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43366/100000 [12:47:10<9:11:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43367/100000 [12:47:11<9:10:49,  1.71it/s]
Train steps ... :  43%|████▎     | 43368/100000 [12:47:11<9:11:23,  1.71it/s]
Train steps ... :  43%|████▎     | 43369/100000 [12:47:12<9:12:58,  1.71it/s]
Train steps ... :  43%|████▎     | 43370/100000 [12:47:13<9:11:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43371/100000 [12:47:13<9:11:59,  1.71it/s]
Train steps ... :  43%|████▎     | 43372/100000 [12:47:14<9:12:19,  1.71it/s]
Train steps ... :  43%|████▎     | 43373/100000 [12:47:14<9:12:20,  1.71it/s]
Train steps ... :  43%|████▎     | 43374/100000 [12:47:15<9:12:27,  1.71it/s]
Train steps ... :  43%|████▎     | 43375/100000 [12:47:16<9:12:02,  1.71it/s]Step... (43375 / 100000 | Loss: 0.9710694551467896, Learning Rate: 5.690954773869347e-05)
+
                                                                             
Step... (43375 / 100000 | Loss: 0.575354814529419, Learning Rate: 5.690954773869347e-05)
+
Train steps ... :  43%|████▎     | 43375/100000 [12:47:16<9:12:02,  1.71it/s]
Train steps ... :  43%|████▎     | 43376/100000 [12:47:16<9:11:59,  1.71it/s]
Train steps ... :  43%|████▎     | 43377/100000 [12:47:17<9:12:36,  1.71it/s]
Train steps ... :  43%|████▎     | 43378/100000 [12:47:17<9:12:01,  1.71it/s]
Train steps ... :  43%|████▎     | 43379/100000 [12:47:18<9:11:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43380/100000 [12:47:18<9:11:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43381/100000 [12:47:19<9:10:27,  1.71it/s]
Train steps ... :  43%|████▎     | 43382/100000 [12:47:20<9:10:46,  1.71it/s]
Train steps ... :  43%|████▎     | 43383/100000 [12:47:20<9:11:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43384/100000 [12:47:21<9:11:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43385/100000 [12:47:21<9:11:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43386/100000 [12:47:22<9:11:23,  1.71it/s]
Train steps ... :  43%|████▎     | 43387/100000 [12:47:23<9:11:21,  1.71it/s]
Train steps ... :  43%|████▎     | 43388/100000 [12:47:23<9:10:34,  1.71it/s]
Train steps ... :  43%|████▎     | 43389/100000 [12:47:24<9:10:26,  1.71it/s]
Train steps ... :  43%|████▎     | 43390/100000 [12:47:24<9:11:18,  1.71it/s]
Train steps ... :  43%|████▎     | 43391/100000 [12:47:25<9:11:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43392/100000 [12:47:25<9:11:32,  1.71it/s]
Train steps ... :  43%|████▎     | 43393/100000 [12:47:26<9:11:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43394/100000 [12:47:27<9:11:07,  1.71it/s]
Train steps ... :  43%|████▎     | 43395/100000 [12:47:27<9:10:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43396/100000 [12:47:28<9:11:14,  1.71it/s]
Train steps ... :  43%|████▎     | 43397/100000 [12:47:28<9:11:16,  1.71it/s]
Train steps ... :  43%|████▎     | 43398/100000 [12:47:29<9:11:47,  1.71it/s]
Train steps ... :  43%|████▎     | 43399/100000 [12:47:30<9:13:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43400/100000 [12:47:30<9:12:33,  1.71it/s]Step... (43400 / 100000 | Loss: 1.160267949104309, Learning Rate: 5.688442211055277e-05)
+
                                                                             
Step... (43400 / 100000 | Loss: 0.7863116264343262, Learning Rate: 5.688442211055277e-05)
+
Train steps ... :  43%|████▎     | 43400/100000 [12:47:30<9:12:33,  1.71it/s]
Train steps ... :  43%|████▎     | 43401/100000 [12:47:31<9:12:25,  1.71it/s]
Train steps ... :  43%|████▎     | 43402/100000 [12:47:31<9:11:20,  1.71it/s]
Train steps ... :  43%|████▎     | 43403/100000 [12:47:32<9:11:59,  1.71it/s]
Train steps ... :  43%|████▎     | 43404/100000 [12:47:32<9:11:57,  1.71it/s]
Train steps ... :  43%|████▎     | 43405/100000 [12:47:33<9:11:44,  1.71it/s]
Train steps ... :  43%|████▎     | 43406/100000 [12:47:34<9:11:26,  1.71it/s]
Train steps ... :  43%|████▎     | 43407/100000 [12:47:34<9:11:35,  1.71it/s]
Train steps ... :  43%|████▎     | 43408/100000 [12:47:35<9:11:15,  1.71it/s]
Train steps ... :  43%|████▎     | 43409/100000 [12:47:35<9:11:18,  1.71it/s]
Train steps ... :  43%|████▎     | 43410/100000 [12:47:36<9:11:20,  1.71it/s]
Train steps ... :  43%|████▎     | 43411/100000 [12:47:37<9:11:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43412/100000 [12:47:37<9:11:21,  1.71it/s]
Train steps ... :  43%|████▎     | 43413/100000 [12:47:38<9:11:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43414/100000 [12:47:38<9:11:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43415/100000 [12:47:39<9:11:32,  1.71it/s]
Train steps ... :  43%|████▎     | 43416/100000 [12:47:39<9:11:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43417/100000 [12:47:40<9:10:47,  1.71it/s]
Train steps ... :  43%|████▎     | 43418/100000 [12:47:41<9:11:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43419/100000 [12:47:41<9:10:34,  1.71it/s]
Train steps ... :  43%|████▎     | 43420/100000 [12:47:42<9:11:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43421/100000 [12:47:42<9:11:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43422/100000 [12:47:43<9:11:45,  1.71it/s]
Train steps ... :  43%|████▎     | 43423/100000 [12:47:44<9:11:48,  1.71it/s]
Train steps ... :  43%|████▎     | 43424/100000 [12:47:44<9:12:00,  1.71it/s]
Train steps ... :  43%|████▎     | 43425/100000 [12:47:45<9:11:16,  1.71it/s]Step... (43425 / 100000 | Loss: 0.6261258125305176, Learning Rate: 5.685929648241206e-05)
+
                                                                             
Step... (43425 / 100000 | Loss: 0.9580222368240356, Learning Rate: 5.685929648241206e-05)
+
Train steps ... :  43%|████▎     | 43425/100000 [12:47:45<9:11:16,  1.71it/s]
Train steps ... :  43%|████▎     | 43426/100000 [12:47:45<9:11:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43427/100000 [12:47:46<9:10:52,  1.71it/s]
Train steps ... :  43%|████▎     | 43428/100000 [12:47:46<9:10:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43429/100000 [12:47:47<9:10:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43430/100000 [12:47:48<9:10:15,  1.71it/s]
Train steps ... :  43%|████▎     | 43431/100000 [12:47:48<9:10:04,  1.71it/s]
Train steps ... :  43%|████▎     | 43432/100000 [12:47:49<9:10:01,  1.71it/s]
Train steps ... :  43%|████▎     | 43433/100000 [12:47:49<9:10:24,  1.71it/s]
Train steps ... :  43%|████▎     | 43434/100000 [12:47:50<9:10:15,  1.71it/s]
Train steps ... :  43%|████▎     | 43435/100000 [12:47:51<9:10:03,  1.71it/s]
Train steps ... :  43%|████▎     | 43436/100000 [12:47:51<9:10:48,  1.71it/s]
Train steps ... :  43%|████▎     | 43437/100000 [12:47:52<9:10:49,  1.71it/s]
Train steps ... :  43%|████▎     | 43438/100000 [12:47:52<9:11:00,  1.71it/s]
Train steps ... :  43%|████▎     | 43439/100000 [12:47:53<9:10:48,  1.71it/s]
Train steps ... :  43%|████▎     | 43440/100000 [12:47:54<9:11:31,  1.71it/s]
Train steps ... :  43%|████▎     | 43441/100000 [12:47:54<9:11:49,  1.71it/s]
Train steps ... :  43%|████▎     | 43442/100000 [12:47:55<9:11:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43443/100000 [12:47:55<9:10:57,  1.71it/s]
Train steps ... :  43%|████▎     | 43444/100000 [12:47:56<9:10:32,  1.71it/s]
Train steps ... :  43%|████▎     | 43445/100000 [12:47:56<9:10:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43446/100000 [12:47:57<9:10:35,  1.71it/s]
Train steps ... :  43%|████▎     | 43447/100000 [12:47:58<9:10:30,  1.71it/s]
Train steps ... :  43%|████▎     | 43448/100000 [12:47:58<9:11:11,  1.71it/s]
Train steps ... :  43%|████▎     | 43449/100000 [12:47:59<9:10:38,  1.71it/s]
Train steps ... :  43%|████▎     | 43450/100000 [12:47:59<9:09:55,  1.71it/s]Step... (43450 / 100000 | Loss: 0.6622324585914612, Learning Rate: 5.683417085427136e-05)
+
                                                                             
Step... (43450 / 100000 | Loss: 0.7582593560218811, Learning Rate: 5.683417085427136e-05)
+
Train steps ... :  43%|████▎     | 43450/100000 [12:48:00<9:09:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43451/100000 [12:48:00<9:10:33,  1.71it/s]
Train steps ... :  43%|████▎     | 43452/100000 [12:48:01<9:10:41,  1.71it/s]
Train steps ... :  43%|████▎     | 43453/100000 [12:48:01<9:10:19,  1.71it/s]
Train steps ... :  43%|████▎     | 43454/100000 [12:48:02<9:11:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43455/100000 [12:48:02<9:10:54,  1.71it/s]
Train steps ... :  43%|████▎     | 43456/100000 [12:48:03<9:11:02,  1.71it/s]
Train steps ... :  43%|████▎     | 43457/100000 [12:48:03<9:11:39,  1.71it/s]
Train steps ... :  43%|████▎     | 43458/100000 [12:48:04<9:11:26,  1.71it/s]
Train steps ... :  43%|████▎     | 43459/100000 [12:48:05<9:11:37,  1.71it/s]
Train steps ... :  43%|████▎     | 43460/100000 [12:48:05<9:10:48,  1.71it/s]
Train steps ... :  43%|████▎     | 43461/100000 [12:48:06<9:10:30,  1.71it/s]
Train steps ... :  43%|████▎     | 43462/100000 [12:48:06<9:10:25,  1.71it/s]
Train steps ... :  43%|████▎     | 43463/100000 [12:48:07<9:10:02,  1.71it/s]
Train steps ... :  43%|████▎     | 43464/100000 [12:48:08<9:10:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43465/100000 [12:48:08<9:10:01,  1.71it/s]
Train steps ... :  43%|████▎     | 43466/100000 [12:48:09<9:10:17,  1.71it/s]
Train steps ... :  43%|████▎     | 43467/100000 [12:48:09<9:10:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43468/100000 [12:48:10<9:09:55,  1.71it/s]
Train steps ... :  43%|████▎     | 43469/100000 [12:48:10<9:09:51,  1.71it/s]
Train steps ... :  43%|████▎     | 43470/100000 [12:48:11<9:10:12,  1.71it/s]
Train steps ... :  43%|████▎     | 43471/100000 [12:48:12<9:09:29,  1.71it/s]
Train steps ... :  43%|████▎     | 43472/100000 [12:48:12<9:10:21,  1.71it/s]
Train steps ... :  43%|████▎     | 43473/100000 [12:48:13<9:10:57,  1.71it/s]
Train steps ... :  43%|████▎     | 43474/100000 [12:48:13<9:10:19,  1.71it/s]
Train steps ... :  43%|████▎     | 43475/100000 [12:48:14<9:10:43,  1.71it/s]Step... (43475 / 100000 | Loss: 0.7281447052955627, Learning Rate: 5.680904522613065e-05)
+
                                                                             
Step... (43475 / 100000 | Loss: 1.1673903465270996, Learning Rate: 5.680904522613065e-05)
+
Train steps ... :  43%|████▎     | 43475/100000 [12:48:14<9:10:43,  1.71it/s]
Train steps ... :  43%|████▎     | 43476/100000 [12:48:15<9:10:30,  1.71it/s]
Train steps ... :  43%|████▎     | 43477/100000 [12:48:15<9:10:18,  1.71it/s]
Train steps ... :  43%|████▎     | 43478/100000 [12:48:16<9:10:40,  1.71it/s]
Train steps ... :  43%|████▎     | 43479/100000 [12:48:16<9:10:51,  1.71it/s]
Train steps ... :  43%|████▎     | 43480/100000 [12:48:17<9:10:43,  1.71it/s]
Train steps ... :  43%|████▎     | 43481/100000 [12:48:17<9:10:38,  1.71it/s]
Train steps ... :  43%|████▎     | 43482/100000 [12:48:18<9:11:10,  1.71it/s]
Train steps ... :  43%|████▎     | 43483/100000 [12:48:19<9:10:36,  1.71it/s]
Train steps ... :  43%|████▎     | 43484/100000 [12:48:19<9:09:53,  1.71it/s]
Train steps ... :  43%|████▎     | 43485/100000 [12:48:20<9:09:47,  1.71it/s]
Train steps ... :  43%|████▎     | 43486/100000 [12:48:20<9:09:53,  1.71it/s]
Train steps ... :  43%|████▎     | 43487/100000 [12:48:21<9:09:49,  1.71it/s]
Train steps ... :  43%|████▎     | 43488/100000 [12:48:22<9:10:30,  1.71it/s]
Train steps ... :  43%|████▎     | 43489/100000 [12:48:22<9:11:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43490/100000 [12:48:23<9:09:33,  1.71it/s]
Train steps ... :  43%|████▎     | 43491/100000 [12:48:23<9:10:03,  1.71it/s]
Train steps ... :  43%|████▎     | 43492/100000 [12:48:24<9:10:05,  1.71it/s]
Train steps ... :  43%|████▎     | 43493/100000 [12:48:24<9:10:09,  1.71it/s]
Train steps ... :  43%|████▎     | 43494/100000 [12:48:25<9:09:56,  1.71it/s]
Train steps ... :  43%|████▎     | 43495/100000 [12:48:26<9:10:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43496/100000 [12:48:26<9:10:06,  1.71it/s]
Train steps ... :  43%|████▎     | 43497/100000 [12:48:27<9:09:27,  1.71it/s]
Train steps ... :  43%|████▎     | 43498/100000 [12:48:27<9:10:17,  1.71it/s]
Train steps ... :  43%|████▎     | 43499/100000 [12:48:28<9:09:58,  1.71it/s]
Train steps ... :  44%|████▎     | 43500/100000 [12:48:29<9:10:31,  1.71it/s]Step... (43500 / 100000 | Loss: 0.8977996110916138, Learning Rate: 5.6783919597989955e-05)
+
                                                                             
Step... (43500 / 100000 | Loss: 0.7002304196357727, Learning Rate: 5.6783919597989955e-05)
+
Train steps ... :  44%|████▎     | 43500/100000 [12:48:29<9:10:31,  1.71it/s]
Train steps ... :  44%|████▎     | 43501/100000 [12:48:29<9:10:02,  1.71it/s]
Train steps ... :  44%|████▎     | 43502/100000 [12:48:30<9:10:04,  1.71it/s]
Train steps ... :  44%|████▎     | 43503/100000 [12:48:30<9:10:09,  1.71it/s]
Train steps ... :  44%|████▎     | 43504/100000 [12:48:31<9:09:50,  1.71it/s]
Train steps ... :  44%|████▎     | 43505/100000 [12:48:31<9:09:27,  1.71it/s]
Train steps ... :  44%|████▎     | 43506/100000 [12:48:32<9:10:47,  1.71it/s]
Train steps ... :  44%|████▎     | 43507/100000 [12:48:33<9:11:05,  1.71it/s]
Train steps ... :  44%|████▎     | 43508/100000 [12:48:33<9:11:15,  1.71it/s]
Train steps ... :  44%|████▎     | 43509/100000 [12:48:34<9:10:49,  1.71it/s]
Train steps ... :  44%|████▎     | 43510/100000 [12:48:34<9:10:57,  1.71it/s]
Train steps ... :  44%|████▎     | 43511/100000 [12:48:35<9:10:53,  1.71it/s]
Train steps ... :  44%|████▎     | 43512/100000 [12:48:36<9:11:28,  1.71it/s]
Train steps ... :  44%|████▎     | 43513/100000 [12:48:36<9:11:35,  1.71it/s]
Train steps ... :  44%|████▎     | 43514/100000 [12:48:37<9:10:47,  1.71it/s]
Train steps ... :  44%|████▎     | 43515/100000 [12:48:37<9:10:21,  1.71it/s]
Train steps ... :  44%|████▎     | 43516/100000 [12:48:38<9:09:48,  1.71it/s]
Train steps ... :  44%|████▎     | 43517/100000 [12:48:39<9:09:28,  1.71it/s]
Train steps ... :  44%|████▎     | 43518/100000 [12:48:39<9:09:37,  1.71it/s]
Train steps ... :  44%|████▎     | 43519/100000 [12:48:40<9:09:25,  1.71it/s]
Train steps ... :  44%|████▎     | 43520/100000 [12:48:40<9:09:13,  1.71it/s]
Train steps ... :  44%|████▎     | 43521/100000 [12:48:41<9:08:52,  1.72it/s]
Train steps ... :  44%|████▎     | 43522/100000 [12:48:41<9:09:00,  1.71it/s]
Train steps ... :  44%|████▎     | 43523/100000 [12:48:42<9:08:53,  1.71it/s]
Train steps ... :  44%|████▎     | 43524/100000 [12:48:43<9:09:07,  1.71it/s]
Train steps ... :  44%|████▎     | 43525/100000 [12:48:43<9:09:47,  1.71it/s]Step... (43525 / 100000 | Loss: 1.1385036706924438, Learning Rate: 5.6758793969849245e-05)
+
                                                                             
Step... (43525 / 100000 | Loss: 0.7568336725234985, Learning Rate: 5.6758793969849245e-05)
+
Train steps ... :  44%|████▎     | 43525/100000 [12:48:44<9:09:47,  1.71it/s]
Train steps ... :  44%|████▎     | 43526/100000 [12:48:44<9:09:15,  1.71it/s]
Train steps ... :  44%|████▎     | 43527/100000 [12:48:44<9:09:48,  1.71it/s]
Train steps ... :  44%|████▎     | 43528/100000 [12:48:45<9:10:08,  1.71it/s]
Train steps ... :  44%|████▎     | 43529/100000 [12:48:46<9:10:37,  1.71it/s]
Train steps ... :  44%|████▎     | 43530/100000 [12:48:46<9:11:22,  1.71it/s]
Train steps ... :  44%|████▎     | 43531/100000 [12:48:47<9:10:41,  1.71it/s]
Train steps ... :  44%|████▎     | 43532/100000 [12:48:47<9:10:04,  1.71it/s]
Train steps ... :  44%|████▎     | 43533/100000 [12:48:48<9:09:42,  1.71it/s]
Train steps ... :  44%|████▎     | 43534/100000 [12:48:48<9:09:54,  1.71it/s]
Train steps ... :  44%|████▎     | 43535/100000 [12:48:49<9:10:10,  1.71it/s]
Train steps ... :  44%|████▎     | 43536/100000 [12:48:50<9:10:08,  1.71it/s]
Train steps ... :  44%|████▎     | 43537/100000 [12:48:50<9:10:07,  1.71it/s]
Train steps ... :  44%|████▎     | 43538/100000 [12:48:51<9:09:48,  1.71it/s]
Train steps ... :  44%|████▎     | 43539/100000 [12:48:51<9:09:15,  1.71it/s]
Train steps ... :  44%|████▎     | 43540/100000 [12:48:52<9:08:54,  1.71it/s]
Train steps ... :  44%|████▎     | 43541/100000 [12:48:53<9:08:39,  1.72it/s]
Train steps ... :  44%|████▎     | 43542/100000 [12:48:53<9:09:06,  1.71it/s]
Train steps ... :  44%|████▎     | 43543/100000 [12:48:54<9:09:09,  1.71it/s]
Train steps ... :  44%|████▎     | 43544/100000 [12:48:54<9:09:48,  1.71it/s]
Train steps ... :  44%|████▎     | 43545/100000 [12:48:55<9:10:23,  1.71it/s]
Train steps ... :  44%|████▎     | 43546/100000 [12:48:55<9:10:05,  1.71it/s]
Train steps ... :  44%|████▎     | 43547/100000 [12:48:56<9:09:54,  1.71it/s]
Train steps ... :  44%|████▎     | 43548/100000 [12:48:57<9:10:01,  1.71it/s]
Train steps ... :  44%|████▎     | 43549/100000 [12:48:57<9:10:17,  1.71it/s]
Train steps ... :  44%|████▎     | 43550/100000 [12:48:58<9:09:59,  1.71it/s]Step... (43550 / 100000 | Loss: 0.7094392776489258, Learning Rate: 5.673366834170855e-05)
+
                                                                             
Step... (43550 / 100000 | Loss: 0.809401273727417, Learning Rate: 5.673366834170855e-05)
+
Train steps ... :  44%|████▎     | 43550/100000 [12:48:58<9:09:59,  1.71it/s]
Train steps ... :  44%|████▎     | 43551/100000 [12:48:58<9:09:35,  1.71it/s]
Train steps ... :  44%|████▎     | 43552/100000 [12:48:59<9:09:20,  1.71it/s]
Train steps ... :  44%|████▎     | 43553/100000 [12:49:00<9:09:45,  1.71it/s]
Train steps ... :  44%|████▎     | 43554/100000 [12:49:00<9:10:07,  1.71it/s]
Train steps ... :  44%|████▎     | 43555/100000 [12:49:01<9:10:55,  1.71it/s]
Train steps ... :  44%|████▎     | 43556/100000 [12:49:01<9:10:13,  1.71it/s]
Train steps ... :  44%|████▎     | 43557/100000 [12:49:02<9:09:58,  1.71it/s]
Train steps ... :  44%|████▎     | 43558/100000 [12:49:02<9:10:04,  1.71it/s]
Train steps ... :  44%|████▎     | 43559/100000 [12:49:03<9:09:23,  1.71it/s]
Train steps ... :  44%|████▎     | 43560/100000 [12:49:04<9:09:40,  1.71it/s]
Train steps ... :  44%|████▎     | 43561/100000 [12:49:04<9:09:53,  1.71it/s]
Train steps ... :  44%|████▎     | 43562/100000 [12:49:05<9:09:30,  1.71it/s]
Train steps ... :  44%|████▎     | 43563/100000 [12:49:05<9:09:10,  1.71it/s]
Train steps ... :  44%|████▎     | 43564/100000 [12:49:06<9:08:54,  1.71it/s]
Train steps ... :  44%|████▎     | 43565/100000 [12:49:07<9:09:31,  1.71it/s]
Train steps ... :  44%|████▎     | 43566/100000 [12:49:07<9:09:41,  1.71it/s]
Train steps ... :  44%|████▎     | 43567/100000 [12:49:08<9:09:04,  1.71it/s]
Train steps ... :  44%|████▎     | 43568/100000 [12:49:08<9:09:08,  1.71it/s]
Train steps ... :  44%|████▎     | 43569/100000 [12:49:09<9:09:07,  1.71it/s]
Train steps ... :  44%|████▎     | 43570/100000 [12:49:09<9:09:11,  1.71it/s]
Train steps ... :  44%|████▎     | 43571/100000 [12:49:10<9:10:32,  1.71it/s]
Train steps ... :  44%|████▎     | 43572/100000 [12:49:11<9:09:20,  1.71it/s]
Train steps ... :  44%|████▎     | 43573/100000 [12:49:11<9:08:58,  1.71it/s]
Train steps ... :  44%|████▎     | 43574/100000 [12:49:12<9:09:29,  1.71it/s]
Train steps ... :  44%|████▎     | 43575/100000 [12:49:12<9:09:10,  1.71it/s]Step... (43575 / 100000 | Loss: 0.7363499402999878, Learning Rate: 5.6708542713567845e-05)
+
                                                                             
Step... (43575 / 100000 | Loss: 0.6809965372085571, Learning Rate: 5.6708542713567845e-05)
+
Train steps ... :  44%|████▎     | 43575/100000 [12:49:13<9:09:10,  1.71it/s]
Train steps ... :  44%|████▎     | 43576/100000 [12:49:13<9:09:26,  1.71it/s]
Train steps ... :  44%|████▎     | 43577/100000 [12:49:14<9:09:18,  1.71it/s]
Train steps ... :  44%|████▎     | 43578/100000 [12:49:14<9:09:00,  1.71it/s]
Train steps ... :  44%|████▎     | 43579/100000 [12:49:15<9:09:13,  1.71it/s]
Train steps ... :  44%|████▎     | 43580/100000 [12:49:15<9:09:23,  1.71it/s]
Train steps ... :  44%|████▎     | 43581/100000 [12:49:16<9:09:59,  1.71it/s]
Train steps ... :  44%|████▎     | 43582/100000 [12:49:16<9:09:45,  1.71it/s]
Train steps ... :  44%|████▎     | 43583/100000 [12:49:17<9:10:11,  1.71it/s]
Train steps ... :  44%|████▎     | 43584/100000 [12:49:18<9:10:12,  1.71it/s]
Train steps ... :  44%|████▎     | 43585/100000 [12:49:18<9:10:03,  1.71it/s]
Train steps ... :  44%|████▎     | 43586/100000 [12:49:19<9:09:48,  1.71it/s]
Train steps ... :  44%|████▎     | 43587/100000 [12:49:19<9:09:32,  1.71it/s]
Train steps ... :  44%|████▎     | 43588/100000 [12:49:20<9:09:38,  1.71it/s]
Train steps ... :  44%|████▎     | 43589/100000 [12:49:21<9:10:17,  1.71it/s]
Train steps ... :  44%|████▎     | 43590/100000 [12:49:21<9:10:04,  1.71it/s]
Train steps ... :  44%|████▎     | 43591/100000 [12:49:22<9:09:45,  1.71it/s]
Train steps ... :  44%|████▎     | 43592/100000 [12:49:22<9:10:05,  1.71it/s]
Train steps ... :  44%|████▎     | 43593/100000 [12:49:23<9:10:01,  1.71it/s]
Train steps ... :  44%|████▎     | 43594/100000 [12:49:24<9:09:50,  1.71it/s]
Train steps ... :  44%|████▎     | 43595/100000 [12:49:24<9:09:19,  1.71it/s]
Train steps ... :  44%|████▎     | 43596/100000 [12:49:25<9:09:38,  1.71it/s]
Train steps ... :  44%|████▎     | 43597/100000 [12:49:25<9:09:06,  1.71it/s]
Train steps ... :  44%|████▎     | 43598/100000 [12:49:26<9:09:42,  1.71it/s]
Train steps ... :  44%|████▎     | 43599/100000 [12:49:26<9:09:11,  1.71it/s]
Train steps ... :  44%|████▎     | 43600/100000 [12:49:27<9:09:06,  1.71it/s]Step... (43600 / 100000 | Loss: 1.0411546230316162, Learning Rate: 5.6683417085427135e-05)
+
                                                                             
Step... (43600 / 100000 | Loss: 0.9815977811813354, Learning Rate: 5.6683417085427135e-05)
+
Train steps ... :  44%|████▎     | 43600/100000 [12:49:27<9:09:06,  1.71it/s]
Train steps ... :  44%|████▎     | 43601/100000 [12:49:28<9:09:31,  1.71it/s]
Train steps ... :  44%|████▎     | 43602/100000 [12:49:28<9:08:57,  1.71it/s]
Train steps ... :  44%|████▎     | 43603/100000 [12:49:29<9:08:48,  1.71it/s]
Train steps ... :  44%|████▎     | 43604/100000 [12:49:29<9:09:06,  1.71it/s]
Train steps ... :  44%|████▎     | 43605/100000 [12:49:30<9:08:42,  1.71it/s]
Train steps ... :  44%|████▎     | 43606/100000 [12:49:31<9:08:17,  1.71it/s]
Train steps ... :  44%|████▎     | 43607/100000 [12:49:31<9:08:13,  1.71it/s]
Train steps ... :  44%|████▎     | 43608/100000 [12:49:32<9:09:05,  1.71it/s]
Train steps ... :  44%|████▎     | 43609/100000 [12:49:32<9:08:43,  1.71it/s]
Train steps ... :  44%|████▎     | 43610/100000 [12:49:33<9:08:45,  1.71it/s]
Train steps ... :  44%|████▎     | 43611/100000 [12:49:33<9:08:49,  1.71it/s]
Train steps ... :  44%|████▎     | 43612/100000 [12:49:34<9:09:23,  1.71it/s]
Train steps ... :  44%|████▎     | 43613/100000 [12:49:35<9:09:15,  1.71it/s]
Train steps ... :  44%|████▎     | 43614/100000 [12:49:35<9:08:55,  1.71it/s]
Train steps ... :  44%|████▎     | 43615/100000 [12:49:36<9:09:00,  1.71it/s]
Train steps ... :  44%|████▎     | 43616/100000 [12:49:36<9:09:01,  1.71it/s]
Train steps ... :  44%|████▎     | 43617/100000 [12:49:37<9:09:11,  1.71it/s]
Train steps ... :  44%|████▎     | 43618/100000 [12:49:38<9:09:05,  1.71it/s]
Train steps ... :  44%|████▎     | 43619/100000 [12:49:38<9:09:41,  1.71it/s]
Train steps ... :  44%|████▎     | 43620/100000 [12:49:39<9:10:14,  1.71it/s]
Train steps ... :  44%|████▎     | 43621/100000 [12:49:39<9:09:47,  1.71it/s]
Train steps ... :  44%|████▎     | 43622/100000 [12:49:40<9:09:42,  1.71it/s]
Train steps ... :  44%|████▎     | 43623/100000 [12:49:40<9:09:53,  1.71it/s]
Train steps ... :  44%|████��     | 43624/100000 [12:49:41<9:10:30,  1.71it/s]
Train steps ... :  44%|████▎     | 43625/100000 [12:49:42<9:10:31,  1.71it/s]Step... (43625 / 100000 | Loss: 0.7350447177886963, Learning Rate: 5.665829145728644e-05)
+
                                                                             
Step... (43625 / 100000 | Loss: 0.599724531173706, Learning Rate: 5.665829145728644e-05)
+
Train steps ... :  44%|████▎     | 43625/100000 [12:49:42<9:10:31,  1.71it/s]
Train steps ... :  44%|████▎     | 43626/100000 [12:49:42<9:10:12,  1.71it/s]
Train steps ... :  44%|████▎     | 43627/100000 [12:49:43<9:09:25,  1.71it/s]
Train steps ... :  44%|████▎     | 43628/100000 [12:49:43<9:11:02,  1.71it/s]
Train steps ... :  44%|████▎     | 43629/100000 [12:49:44<9:09:36,  1.71it/s]
Train steps ... :  44%|████▎     | 43630/100000 [12:49:45<9:09:12,  1.71it/s]
Train steps ... :  44%|████▎     | 43631/100000 [12:49:45<9:08:40,  1.71it/s]
Train steps ... :  44%|████▎     | 43632/100000 [12:49:46<9:08:22,  1.71it/s]
Train steps ... :  44%|████▎     | 43633/100000 [12:49:46<9:08:33,  1.71it/s]
Train steps ... :  44%|████▎     | 43634/100000 [12:49:47<9:08:41,  1.71it/s]
Train steps ... :  44%|████▎     | 43635/100000 [12:49:47<9:08:29,  1.71it/s]
Train steps ... :  44%|████▎     | 43636/100000 [12:49:48<9:08:20,  1.71it/s]
Train steps ... :  44%|████▎     | 43637/100000 [12:49:49<9:08:21,  1.71it/s]
Train steps ... :  44%|████▎     | 43638/100000 [12:49:49<9:08:43,  1.71it/s]
Train steps ... :  44%|████▎     | 43639/100000 [12:49:50<9:08:53,  1.71it/s]
Train steps ... :  44%|████▎     | 43640/100000 [12:49:50<9:08:45,  1.71it/s]
Train steps ... :  44%|████▎     | 43641/100000 [12:49:51<9:08:38,  1.71it/s]
Train steps ... :  44%|████▎     | 43642/100000 [12:49:52<9:08:33,  1.71it/s]
Train steps ... :  44%|████▎     | 43643/100000 [12:49:52<9:08:38,  1.71it/s]
Train steps ... :  44%|████▎     | 43644/100000 [12:49:53<9:08:46,  1.71it/s]
Train steps ... :  44%|████▎     | 43645/100000 [12:49:53<9:08:58,  1.71it/s]
Train steps ... :  44%|████▎     | 43646/100000 [12:49:54<9:09:10,  1.71it/s]
Train steps ... :  44%|████▎     | 43647/100000 [12:49:54<9:08:44,  1.71it/s]
Train steps ... :  44%|████▎     | 43648/100000 [12:49:55<9:08:26,  1.71it/s]
Train steps ... :  44%|████▎     | 43649/100000 [12:49:56<9:08:24,  1.71it/s]
Train steps ... :  44%|████▎     | 43650/100000 [12:49:56<9:08:30,  1.71it/s]Step... (43650 / 100000 | Loss: 0.6940417289733887, Learning Rate: 5.663316582914573e-05)
+
                                                                             
Step... (43650 / 100000 | Loss: 0.9212006330490112, Learning Rate: 5.663316582914573e-05)
+
Train steps ... :  44%|████▎     | 43650/100000 [12:49:57<9:08:30,  1.71it/s]
Train steps ... :  44%|████▎     | 43651/100000 [12:49:57<9:08:37,  1.71it/s]
Train steps ... :  44%|████▎     | 43652/100000 [12:49:57<9:09:00,  1.71it/s]
Train steps ... :  44%|████▎     | 43653/100000 [12:49:58<9:09:12,  1.71it/s]
Train steps ... :  44%|████▎     | 43654/100000 [12:49:59<9:09:01,  1.71it/s]
Train steps ... :  44%|████▎     | 43655/100000 [12:49:59<9:08:22,  1.71it/s]
Train steps ... :  44%|████▎     | 43656/100000 [12:50:00<9:08:17,  1.71it/s]
Train steps ... :  44%|████▎     | 43657/100000 [12:50:00<9:07:59,  1.71it/s]
Train steps ... :  44%|████▎     | 43658/100000 [12:50:01<9:08:29,  1.71it/s]
Train steps ... :  44%|████▎     | 43659/100000 [12:50:01<9:07:52,  1.71it/s]
Train steps ... :  44%|████▎     | 43660/100000 [12:50:02<9:08:43,  1.71it/s]
Train steps ... :  44%|████▎     | 43661/100000 [12:50:03<9:08:41,  1.71it/s]
Train steps ... :  44%|████▎     | 43662/100000 [12:50:03<9:08:45,  1.71it/s]
Train steps ... :  44%|████▎     | 43663/100000 [12:50:04<9:08:38,  1.71it/s]
Train steps ... :  44%|████▎     | 43664/100000 [12:50:04<9:08:21,  1.71it/s]
Train steps ... :  44%|████▎     | 43665/100000 [12:50:05<9:08:40,  1.71it/s]
Train steps ... :  44%|████▎     | 43666/100000 [12:50:06<9:08:33,  1.71it/s]
Train steps ... :  44%|████▎     | 43667/100000 [12:50:06<9:08:43,  1.71it/s]
Train steps ... :  44%|████▎     | 43668/100000 [12:50:07<9:08:10,  1.71it/s]
Train steps ... :  44%|████▎     | 43669/100000 [12:50:07<9:07:57,  1.71it/s]
Train steps ... :  44%|████▎     | 43670/100000 [12:50:08<9:08:17,  1.71it/s]
Train steps ... :  44%|████▎     | 43671/100000 [12:50:08<9:08:26,  1.71it/s]
Train steps ... :  44%|████▎     | 43672/100000 [12:50:09<9:08:48,  1.71it/s]
Train steps ... :  44%|████▎     | 43673/100000 [12:50:10<9:09:04,  1.71it/s]
Train steps ... :  44%|████▎     | 43674/100000 [12:50:10<9:08:56,  1.71it/s]
Train steps ... :  44%|████▎     | 43675/100000 [12:50:11<9:09:10,  1.71it/s]Step... (43675 / 100000 | Loss: 0.8487741947174072, Learning Rate: 5.660804020100503e-05)
+
                                                                             
Step... (43675 / 100000 | Loss: 0.8074451684951782, Learning Rate: 5.660804020100503e-05)
+
Train steps ... :  44%|████▎     | 43675/100000 [12:50:11<9:09:10,  1.71it/s]
Train steps ... :  44%|████▎     | 43676/100000 [12:50:11<9:10:59,  1.70it/s]
Train steps ... :  44%|████▎     | 43677/100000 [12:50:12<9:09:16,  1.71it/s]
Train steps ... :  44%|████▎     | 43678/100000 [12:50:13<9:09:06,  1.71it/s]
Train steps ... :  44%|████▎     | 43679/100000 [12:50:13<9:08:33,  1.71it/s]
Train steps ... :  44%|████▎     | 43680/100000 [12:50:14<9:08:22,  1.71it/s]
Train steps ... :  44%|████▎     | 43681/100000 [12:50:14<9:07:52,  1.71it/s]
Train steps ... :  44%|████▎     | 43682/100000 [12:50:15<9:08:16,  1.71it/s]
Train steps ... :  44%|████▎     | 43683/100000 [12:50:16<9:07:52,  1.71it/s]
Train steps ... :  44%|████▎     | 43684/100000 [12:50:16<9:08:06,  1.71it/s]
Train steps ... :  44%|████▎     | 43685/100000 [12:50:17<9:08:02,  1.71it/s]
Train steps ... :  44%|████▎     | 43686/100000 [12:50:17<9:07:46,  1.71it/s]
Train steps ... :  44%|████▎     | 43687/100000 [12:50:18<9:07:39,  1.71it/s]
Train steps ... :  44%|████▎     | 43688/100000 [12:50:18<9:08:31,  1.71it/s]
Train steps ... :  44%|████▎     | 43689/100000 [12:50:19<9:08:01,  1.71it/s]
Train steps ... :  44%|████▎     | 43690/100000 [12:50:20<9:08:06,  1.71it/s]
Train steps ... :  44%|████▎     | 43691/100000 [12:50:20<9:08:02,  1.71it/s]
Train steps ... :  44%|████▎     | 43692/100000 [12:50:21<9:10:56,  1.70it/s]
Train steps ... :  44%|████▎     | 43693/100000 [12:50:21<9:08:49,  1.71it/s]
Train steps ... :  44%|████▎     | 43694/100000 [12:50:22<9:09:05,  1.71it/s]
Train steps ... :  44%|████▎     | 43695/100000 [12:50:23<9:08:58,  1.71it/s]
Train steps ... :  44%|████▎     | 43696/100000 [12:50:23<9:09:01,  1.71it/s]
Train steps ... :  44%|████▎     | 43697/100000 [12:50:24<9:09:15,  1.71it/s]
Train steps ... :  44%|████▎     | 43698/100000 [12:50:24<9:09:12,  1.71it/s]
Train steps ... :  44%|████▎     | 43699/100000 [12:50:25<9:09:07,  1.71it/s]
Train steps ... :  44%|████▎     | 43700/100000 [12:50:25<9:08:37,  1.71it/s]Step... (43700 / 100000 | Loss: 0.728005051612854, Learning Rate: 5.658291457286432e-05)
+
                                                                             
Step... (43700 / 100000 | Loss: 0.7715522050857544, Learning Rate: 5.658291457286432e-05)
+
Train steps ... :  44%|████▎     | 43700/100000 [12:50:26<9:08:37,  1.71it/s]
Train steps ... :  44%|████▎     | 43701/100000 [12:50:26<9:09:02,  1.71it/s]
Train steps ... :  44%|████▎     | 43702/100000 [12:50:27<9:07:49,  1.71it/s]
Train steps ... :  44%|████▎     | 43703/100000 [12:50:27<9:08:19,  1.71it/s]
Train steps ... :  44%|████▎     | 43704/100000 [12:50:28<9:08:00,  1.71it/s]
Train steps ... :  44%|████▎     | 43705/100000 [12:50:28<9:08:24,  1.71it/s]
Train steps ... :  44%|████▎     | 43706/100000 [12:50:29<9:08:49,  1.71it/s]
Train steps ... :  44%|████▎     | 43707/100000 [12:50:30<9:08:13,  1.71it/s]
Train steps ... :  44%|████▎     | 43708/100000 [12:50:30<9:08:30,  1.71it/s]
Train steps ... :  44%|████▎     | 43709/100000 [12:50:31<9:09:00,  1.71it/s]
Train steps ... :  44%|████▎     | 43710/100000 [12:50:31<9:08:53,  1.71it/s]
Train steps ... :  44%|████▎     | 43711/100000 [12:50:32<9:08:27,  1.71it/s]
Train steps ... :  44%|████▎     | 43712/100000 [12:50:32<9:09:21,  1.71it/s]
Train steps ... :  44%|████▎     | 43713/100000 [12:50:33<9:08:37,  1.71it/s]
Train steps ... :  44%|████▎     | 43714/100000 [12:50:34<9:08:30,  1.71it/s]
Train steps ... :  44%|████▎     | 43715/100000 [12:50:34<9:08:14,  1.71it/s]
Train steps ... :  44%|████▎     | 43716/100000 [12:50:35<9:08:56,  1.71it/s]
Train steps ... :  44%|████▎     | 43717/100000 [12:50:35<9:08:45,  1.71it/s]
Train steps ... :  44%|████▎     | 43718/100000 [12:50:36<9:08:47,  1.71it/s]
Train steps ... :  44%|████▎     | 43719/100000 [12:50:37<9:09:30,  1.71it/s]
Train steps ... :  44%|████▎     | 43720/100000 [12:50:37<9:09:51,  1.71it/s]
Train steps ... :  44%|████▎     | 43721/100000 [12:50:38<9:09:17,  1.71it/s]
Train steps ... :  44%|████▎     | 43722/100000 [12:50:38<9:08:54,  1.71it/s]
Train steps ... :  44%|████▎     | 43723/100000 [12:50:39<9:09:02,  1.71it/s]
Train steps ... :  44%|████▎     | 43724/100000 [12:50:39<9:09:02,  1.71it/s]
Train steps ... :  44%|████▎     | 43725/100000 [12:50:40<9:08:35,  1.71it/s]Step... (43725 / 100000 | Loss: 0.9346593022346497, Learning Rate: 5.6557788944723625e-05)
+
                                                                             
Step... (43725 / 100000 | Loss: 0.6795749068260193, Learning Rate: 5.6557788944723625e-05)
+
Train steps ... :  44%|████▎     | 43725/100000 [12:50:40<9:08:35,  1.71it/s]
Train steps ... :  44%|████▎     | 43726/100000 [12:50:41<9:09:27,  1.71it/s]
Train steps ... :  44%|████▎     | 43727/100000 [12:50:41<9:08:24,  1.71it/s]
Train steps ... :  44%|████▎     | 43728/100000 [12:50:42<9:10:39,  1.70it/s]
Train steps ... :  44%|████▎     | 43729/100000 [12:50:42<9:09:37,  1.71it/s]
Train steps ... :  44%|████▎     | 43730/100000 [12:50:43<9:09:23,  1.71it/s]
Train steps ... :  44%|████▎     | 43731/100000 [12:50:44<9:09:57,  1.71it/s]
Train steps ... :  44%|████▎     | 43732/100000 [12:50:44<9:09:34,  1.71it/s]
Train steps ... :  44%|████▎     | 43733/100000 [12:50:45<9:09:35,  1.71it/s]
Train steps ... :  44%|████▎     | 43734/100000 [12:50:45<9:08:58,  1.71it/s]
Train steps ... :  44%|████▎     | 43735/100000 [12:50:46<9:08:47,  1.71it/s]
Train steps ... :  44%|████▎     | 43736/100000 [12:50:47<9:08:47,  1.71it/s]
Train steps ... :  44%|████▎     | 43737/100000 [12:50:47<9:08:43,  1.71it/s]
Train steps ... :  44%|████▎     | 43738/100000 [12:50:48<9:08:29,  1.71it/s]
Train steps ... :  44%|████▎     | 43739/100000 [12:50:48<9:08:42,  1.71it/s]
Train steps ... :  44%|████▎     | 43740/100000 [12:50:49<9:08:51,  1.71it/s]
Train steps ... :  44%|████▎     | 43741/100000 [12:50:49<9:09:11,  1.71it/s]
Train steps ... :  44%|████▎     | 43742/100000 [12:50:50<9:09:03,  1.71it/s]
Train steps ... :  44%|████▎     | 43743/100000 [12:50:51<9:09:09,  1.71it/s]
Train steps ... :  44%|████▎     | 43744/100000 [12:50:51<9:09:28,  1.71it/s]
Train steps ... :  44%|████▎     | 43745/100000 [12:50:52<9:09:01,  1.71it/s]
Train steps ... :  44%|████▎     | 43746/100000 [12:50:52<9:09:08,  1.71it/s]
Train steps ... :  44%|████▎     | 43747/100000 [12:50:53<9:09:21,  1.71it/s]
Train steps ... :  44%|████▎     | 43748/100000 [12:50:54<9:08:52,  1.71it/s]
Train steps ... :  44%|████▎     | 43749/100000 [12:50:54<9:08:06,  1.71it/s]
Train steps ... :  44%|████▍     | 43750/100000 [12:50:55<9:07:40,  1.71it/s]Step... (43750 / 100000 | Loss: 0.9703555107116699, Learning Rate: 5.6532663316582915e-05)
+
                                                                             
Step... (43750 / 100000 | Loss: 1.0076208114624023, Learning Rate: 5.6532663316582915e-05)
+
Train steps ... :  44%|████▍     | 43750/100000 [12:50:55<9:07:40,  1.71it/s]
Train steps ... :  44%|████▍     | 43751/100000 [12:50:55<9:07:49,  1.71it/s]
Train steps ... :  44%|████▍     | 43752/100000 [12:50:56<9:08:37,  1.71it/s]
Train steps ... :  44%|████▍     | 43753/100000 [12:50:56<9:08:31,  1.71it/s]
Train steps ... :  44%|████▍     | 43754/100000 [12:50:57<9:08:29,  1.71it/s]
Train steps ... :  44%|████▍     | 43755/100000 [12:50:58<9:08:52,  1.71it/s]
Train steps ... :  44%|████▍     | 43756/100000 [12:50:58<9:08:19,  1.71it/s]
Train steps ... :  44%|████▍     | 43757/100000 [12:50:59<9:07:56,  1.71it/s]
Train steps ... :  44%|████▍     | 43758/100000 [12:50:59<9:08:43,  1.71it/s]
Train steps ... :  44%|████▍     | 43759/100000 [12:51:00<9:08:55,  1.71it/s]
Train steps ... :  44%|████▍     | 43760/100000 [12:51:01<9:08:26,  1.71it/s]
Train steps ... :  44%|████▍     | 43761/100000 [12:51:01<9:07:44,  1.71it/s]
Train steps ... :  44%|████▍     | 43762/100000 [12:51:02<9:08:38,  1.71it/s]
Train steps ... :  44%|████▍     | 43763/100000 [12:51:02<9:08:07,  1.71it/s]
Train steps ... :  44%|████▍     | 43764/100000 [12:51:03<9:08:15,  1.71it/s]
Train steps ... :  44%|████▍     | 43765/100000 [12:51:03<9:08:18,  1.71it/s]
Train steps ... :  44%|████▍     | 43766/100000 [12:51:04<9:08:05,  1.71it/s]
Train steps ... :  44%|████▍     | 43767/100000 [12:51:05<9:07:45,  1.71it/s]
Train steps ... :  44%|████▍     | 43768/100000 [12:51:05<9:08:22,  1.71it/s]
Train steps ... :  44%|████▍     | 43769/100000 [12:51:06<9:08:10,  1.71it/s]
Train steps ... :  44%|████▍     | 43770/100000 [12:51:06<9:08:57,  1.71it/s]
Train steps ... :  44%|████▍     | 43771/100000 [12:51:07<9:08:22,  1.71it/s]
Train steps ... :  44%|████▍     | 43772/100000 [12:51:08<9:07:52,  1.71it/s]
Train steps ... :  44%|████▍     | 43773/100000 [12:51:08<9:08:16,  1.71it/s]
Train steps ... :  44%|████▍     | 43774/100000 [12:51:09<9:08:14,  1.71it/s]
Train steps ... :  44%|████▍     | 43775/100000 [12:51:09<9:07:30,  1.71it/s]Step... (43775 / 100000 | Loss: 0.8181147575378418, Learning Rate: 5.650753768844221e-05)
+
                                                                             
Step... (43775 / 100000 | Loss: 1.258349895477295, Learning Rate: 5.650753768844221e-05)
+
Train steps ... :  44%|████▍     | 43775/100000 [12:51:10<9:07:30,  1.71it/s]
Train steps ... :  44%|████▍     | 43776/100000 [12:51:10<9:07:54,  1.71it/s]
Train steps ... :  44%|████▍     | 43777/100000 [12:51:11<9:07:36,  1.71it/s]
Train steps ... :  44%|████▍     | 43778/100000 [12:51:11<9:07:35,  1.71it/s]
Train steps ... :  44%|████▍     | 43779/100000 [12:51:12<9:08:32,  1.71it/s]
Train steps ... :  44%|████▍     | 43780/100000 [12:51:12<9:08:07,  1.71it/s]
Train steps ... :  44%|████▍     | 43781/100000 [12:51:13<9:09:41,  1.70it/s]
Train steps ... :  44%|████▍     | 43782/100000 [12:51:13<9:09:50,  1.70it/s]
Train steps ... :  44%|████▍     | 43783/100000 [12:51:14<9:10:09,  1.70it/s]
Train steps ... :  44%|████▍     | 43784/100000 [12:51:15<9:10:13,  1.70it/s]
Train steps ... :  44%|████▍     | 43785/100000 [12:51:15<9:09:03,  1.71it/s]
Train steps ... :  44%|████▍     | 43786/100000 [12:51:16<9:08:40,  1.71it/s]
Train steps ... :  44%|████▍     | 43787/100000 [12:51:16<9:08:08,  1.71it/s]
Train steps ... :  44%|████▍     | 43788/100000 [12:51:17<9:07:40,  1.71it/s]
Train steps ... :  44%|████▍     | 43789/100000 [12:51:18<9:07:12,  1.71it/s]
Train steps ... :  44%|████▍     | 43790/100000 [12:51:18<9:07:24,  1.71it/s]
Train steps ... :  44%|████▍     | 43791/100000 [12:51:19<9:07:25,  1.71it/s]
Train steps ... :  44%|████▍     | 43792/100000 [12:51:19<9:07:59,  1.71it/s]
Train steps ... :  44%|████▍     | 43793/100000 [12:51:20<9:07:30,  1.71it/s]
Train steps ... :  44%|████▍     | 43794/100000 [12:51:20<9:07:57,  1.71it/s]
Train steps ... :  44%|████▍     | 43795/100000 [12:51:21<9:07:40,  1.71it/s]
Train steps ... :  44%|████▍     | 43796/100000 [12:51:22<9:07:42,  1.71it/s]
Train steps ... :  44%|████▍     | 43797/100000 [12:51:22<9:07:40,  1.71it/s]
Train steps ... :  44%|████▍     | 43798/100000 [12:51:23<9:08:43,  1.71it/s]
Train steps ... :  44%|████▍     | 43799/100000 [12:51:23<9:08:23,  1.71it/s]
Train steps ... :  44%|████▍     | 43800/100000 [12:51:24<9:08:40,  1.71it/s]Step... (43800 / 100000 | Loss: 0.9178519248962402, Learning Rate: 5.6482412060301515e-05)
+
                                                                             
Step... (43800 / 100000 | Loss: 0.9257898330688477, Learning Rate: 5.6482412060301515e-05)
+
Train steps ... :  44%|████▍     | 43800/100000 [12:51:24<9:08:40,  1.71it/s]
Train steps ... :  44%|████▍     | 43801/100000 [12:51:25<9:07:32,  1.71it/s]
Train steps ... :  44%|████▍     | 43802/100000 [12:51:25<9:07:39,  1.71it/s]
Train steps ... :  44%|████▍     | 43803/100000 [12:51:26<9:06:53,  1.71it/s]
Train steps ... :  44%|████▍     | 43804/100000 [12:51:26<9:06:47,  1.71it/s]
Train steps ... :  44%|████▍     | 43805/100000 [12:51:27<9:07:21,  1.71it/s]
Train steps ... :  44%|████▍     | 43806/100000 [12:51:27<9:06:52,  1.71it/s]
Train steps ... :  44%|████▍     | 43807/100000 [12:51:28<9:07:11,  1.71it/s]
Train steps ... :  44%|████▍     | 43808/100000 [12:51:29<9:07:19,  1.71it/s]
Train steps ... :  44%|████▍     | 43809/100000 [12:51:29<9:07:22,  1.71it/s]
Train steps ... :  44%|████▍     | 43810/100000 [12:51:30<9:07:17,  1.71it/s]
Train steps ... :  44%|████▍     | 43811/100000 [12:51:30<9:07:15,  1.71it/s]
Train steps ... :  44%|████▍     | 43812/100000 [12:51:31<9:07:48,  1.71it/s]
Train steps ... :  44%|████▍     | 43813/100000 [12:51:32<9:07:27,  1.71it/s]
Train steps ... :  44%|████▍     | 43814/100000 [12:51:32<9:07:38,  1.71it/s]
Train steps ... :  44%|████▍     | 43815/100000 [12:51:33<9:08:06,  1.71it/s]
Train steps ... :  44%|████▍     | 43816/100000 [12:51:33<9:08:13,  1.71it/s]
Train steps ... :  44%|████▍     | 43817/100000 [12:51:34<9:08:06,  1.71it/s]
Train steps ... :  44%|████▍     | 43818/100000 [12:51:34<9:07:43,  1.71it/s]
Train steps ... :  44%|████▍     | 43819/100000 [12:51:35<9:07:52,  1.71it/s]
Train steps ... :  44%|████▍     | 43820/100000 [12:51:36<9:07:12,  1.71it/s]
Train steps ... :  44%|████▍     | 43821/100000 [12:51:36<9:07:21,  1.71it/s]
Train steps ... :  44%|████▍     | 43822/100000 [12:51:37<9:07:31,  1.71it/s]
Train steps ... :  44%|████▍     | 43823/100000 [12:51:37<9:07:42,  1.71it/s]
Train steps ... :  44%|████▍     | 43824/100000 [12:51:38<9:07:45,  1.71it/s]
Train steps ... :  44%|███��▍     | 43825/100000 [12:51:39<9:07:04,  1.71it/s]Step... (43825 / 100000 | Loss: 1.0731418132781982, Learning Rate: 5.6457286432160805e-05)
+
                                                                             
Step... (43825 / 100000 | Loss: 0.6350101232528687, Learning Rate: 5.6457286432160805e-05)
+
Train steps ... :  44%|████▍     | 43825/100000 [12:51:39<9:07:04,  1.71it/s]
Train steps ... :  44%|████▍     | 43826/100000 [12:51:39<9:07:05,  1.71it/s]
Train steps ... :  44%|████▍     | 43827/100000 [12:51:40<9:06:41,  1.71it/s]
Train steps ... :  44%|████▍     | 43828/100000 [12:51:40<9:06:28,  1.71it/s]
Train steps ... :  44%|████▍     | 43829/100000 [12:51:41<9:06:51,  1.71it/s]
Train steps ... :  44%|████▍     | 43830/100000 [12:51:42<9:07:12,  1.71it/s]
Train steps ... :  44%|████▍     | 43831/100000 [12:51:42<9:07:19,  1.71it/s]
Train steps ... :  44%|████▍     | 43832/100000 [12:51:43<9:06:45,  1.71it/s]
Train steps ... :  44%|████▍     | 43833/100000 [12:51:43<9:08:01,  1.71it/s]
Train steps ... :  44%|████▍     | 43834/100000 [12:51:44<9:07:27,  1.71it/s]
Train steps ... :  44%|████▍     | 43835/100000 [12:51:44<9:07:32,  1.71it/s]
Train steps ... :  44%|████▍     | 43836/100000 [12:51:45<9:07:04,  1.71it/s]
Train steps ... :  44%|████▍     | 43837/100000 [12:51:46<9:07:03,  1.71it/s]
Train steps ... :  44%|████▍     | 43838/100000 [12:51:46<9:07:30,  1.71it/s]
Train steps ... :  44%|████▍     | 43839/100000 [12:51:47<9:06:48,  1.71it/s]
Train steps ... :  44%|████▍     | 43840/100000 [12:51:47<9:06:22,  1.71it/s]
Train steps ... :  44%|████▍     | 43841/100000 [12:51:48<9:06:28,  1.71it/s]
Train steps ... :  44%|████▍     | 43842/100000 [12:51:49<9:06:12,  1.71it/s]
Train steps ... :  44%|████▍     | 43843/100000 [12:51:49<9:06:08,  1.71it/s]
Train steps ... :  44%|████▍     | 43844/100000 [12:51:50<9:05:52,  1.71it/s]
Train steps ... :  44%|████▍     | 43845/100000 [12:51:50<9:05:51,  1.71it/s]
Train steps ... :  44%|████▍     | 43846/100000 [12:51:51<9:06:43,  1.71it/s]
Train steps ... :  44%|████▍     | 43847/100000 [12:51:51<9:06:15,  1.71it/s]
Train steps ... :  44%|████▍     | 43848/100000 [12:51:52<9:05:58,  1.71it/s]
Train steps ... :  44%|████▍     | 43849/100000 [12:51:53<9:05:53,  1.71it/s]
Train steps ... :  44%|████▍     | 43850/100000 [12:51:53<9:06:23,  1.71it/s]Step... (43850 / 100000 | Loss: 0.7847995758056641, Learning Rate: 5.643216080402011e-05)
+
                                                                             
Step... (43850 / 100000 | Loss: 1.2753218412399292, Learning Rate: 5.643216080402011e-05)
+
Train steps ... :  44%|████▍     | 43850/100000 [12:51:54<9:06:23,  1.71it/s]
Train steps ... :  44%|████▍     | 43851/100000 [12:51:54<9:06:07,  1.71it/s]
Train steps ... :  44%|████▍     | 43852/100000 [12:51:54<9:06:42,  1.71it/s]
Train steps ... :  44%|████▍     | 43853/100000 [12:51:55<9:08:05,  1.71it/s]
Train steps ... :  44%|████▍     | 43854/100000 [12:51:56<9:08:33,  1.71it/s]
Train steps ... :  44%|████▍     | 43855/100000 [12:51:56<9:06:57,  1.71it/s]
Train steps ... :  44%|████▍     | 43856/100000 [12:51:57<9:06:27,  1.71it/s]
Train steps ... :  44%|████▍     | 43857/100000 [12:51:57<9:06:58,  1.71it/s]
Train steps ... :  44%|████▍     | 43858/100000 [12:51:58<9:06:29,  1.71it/s]
Train steps ... :  44%|████▍     | 43859/100000 [12:51:58<9:06:19,  1.71it/s]
Train steps ... :  44%|████▍     | 43860/100000 [12:51:59<9:05:58,  1.71it/s]
Train steps ... :  44%|████▍     | 43861/100000 [12:52:00<9:06:03,  1.71it/s]
Train steps ... :  44%|████▍     | 43862/100000 [12:52:00<9:06:25,  1.71it/s]
Train steps ... :  44%|████▍     | 43863/100000 [12:52:01<9:05:58,  1.71it/s]
Train steps ... :  44%|████▍     | 43864/100000 [12:52:01<9:06:13,  1.71it/s]
Train steps ... :  44%|████▍     | 43865/100000 [12:52:02<9:06:33,  1.71it/s]
Train steps ... :  44%|████▍     | 43866/100000 [12:52:03<9:07:28,  1.71it/s]
Train steps ... :  44%|████▍     | 43867/100000 [12:52:03<9:06:49,  1.71it/s]
Train steps ... :  44%|████▍     | 43868/100000 [12:52:04<9:07:37,  1.71it/s]
Train steps ... :  44%|████▍     | 43869/100000 [12:52:04<9:07:04,  1.71it/s]
Train steps ... :  44%|████▍     | 43870/100000 [12:52:05<9:07:01,  1.71it/s]
Train steps ... :  44%|████▍     | 43871/100000 [12:52:05<9:06:43,  1.71it/s]
Train steps ... :  44%|████▍     | 43872/100000 [12:52:06<9:06:07,  1.71it/s]
Train steps ... :  44%|████▍     | 43873/100000 [12:52:07<9:06:59,  1.71it/s]
Train steps ... :  44%|████▍     | 43874/100000 [12:52:07<9:06:25,  1.71it/s]
Train steps ... :  44%|████▍     | 43875/100000 [12:52:08<9:05:57,  1.71it/s]Step... (43875 / 100000 | Loss: 1.0210288763046265, Learning Rate: 5.64070351758794e-05)
+
                                                                             
Step... (43875 / 100000 | Loss: 0.6797128915786743, Learning Rate: 5.64070351758794e-05)
+
Train steps ... :  44%|████▍     | 43875/100000 [12:52:08<9:05:57,  1.71it/s]
Train steps ... :  44%|████▍     | 43876/100000 [12:52:08<9:06:59,  1.71it/s]
Train steps ... :  44%|████▍     | 43877/100000 [12:52:09<9:06:30,  1.71it/s]
Train steps ... :  44%|████▍     | 43878/100000 [12:52:10<9:06:14,  1.71it/s]
Train steps ... :  44%|████▍     | 43879/100000 [12:52:10<9:06:13,  1.71it/s]
Train steps ... :  44%|████▍     | 43880/100000 [12:52:11<9:06:08,  1.71it/s]
Train steps ... :  44%|████▍     | 43881/100000 [12:52:11<9:06:26,  1.71it/s]
Train steps ... :  44%|████▍     | 43882/100000 [12:52:12<9:06:19,  1.71it/s]
Train steps ... :  44%|████▍     | 43883/100000 [12:52:12<9:06:36,  1.71it/s]
Train steps ... :  44%|████▍     | 43884/100000 [12:52:13<9:07:03,  1.71it/s]
Train steps ... :  44%|████▍     | 43885/100000 [12:52:14<9:06:41,  1.71it/s]
Train steps ... :  44%|████▍     | 43886/100000 [12:52:14<9:06:37,  1.71it/s]
Train steps ... :  44%|████▍     | 43887/100000 [12:52:15<9:07:08,  1.71it/s]
Train steps ... :  44%|████▍     | 43888/100000 [12:52:15<9:07:03,  1.71it/s]
Train steps ... :  44%|████▍     | 43889/100000 [12:52:16<9:07:08,  1.71it/s]
Train steps ... :  44%|████▍     | 43890/100000 [12:52:17<9:07:06,  1.71it/s]
Train steps ... :  44%|████▍     | 43891/100000 [12:52:17<9:06:39,  1.71it/s]
Train steps ... :  44%|████▍     | 43892/100000 [12:52:18<9:06:32,  1.71it/s]
Train steps ... :  44%|████▍     | 43893/100000 [12:52:18<9:06:21,  1.71it/s]
Train steps ... :  44%|████▍     | 43894/100000 [12:52:19<9:06:21,  1.71it/s]
Train steps ... :  44%|████▍     | 43895/100000 [12:52:19<9:06:23,  1.71it/s]
Train steps ... :  44%|████▍     | 43896/100000 [12:52:20<9:06:34,  1.71it/s]
Train steps ... :  44%|████▍     | 43897/100000 [12:52:21<9:06:10,  1.71it/s]
Train steps ... :  44%|████▍     | 43898/100000 [12:52:21<9:06:41,  1.71it/s]
Train steps ... :  44%|████▍     | 43899/100000 [12:52:22<9:06:51,  1.71it/s]
Train steps ... :  44%|████▍     | 43900/100000 [12:52:22<9:07:37,  1.71it/s]Step... (43900 / 100000 | Loss: 0.8362725973129272, Learning Rate: 5.63819095477387e-05)
+
                                                                             
Step... (43900 / 100000 | Loss: 0.7510668039321899, Learning Rate: 5.63819095477387e-05)
+
Train steps ... :  44%|████▍     | 43900/100000 [12:52:23<9:07:37,  1.71it/s]
Train steps ... :  44%|████▍     | 43901/100000 [12:52:23<9:06:15,  1.71it/s]
Train steps ... :  44%|████▍     | 43902/100000 [12:52:24<9:06:15,  1.71it/s]
Train steps ... :  44%|████▍     | 43903/100000 [12:52:24<9:06:25,  1.71it/s]
Train steps ... :  44%|████▍     | 43904/100000 [12:52:25<9:06:11,  1.71it/s]
Train steps ... :  44%|████▍     | 43905/100000 [12:52:25<9:06:18,  1.71it/s]
Train steps ... :  44%|████▍     | 43906/100000 [12:52:26<9:06:05,  1.71it/s]
Train steps ... :  44%|████▍     | 43907/100000 [12:52:26<9:06:43,  1.71it/s]
Train steps ... :  44%|████▍     | 43908/100000 [12:52:27<9:06:02,  1.71it/s]
Train steps ... :  44%|████▍     | 43909/100000 [12:52:28<9:06:05,  1.71it/s]
Train steps ... :  44%|████▍     | 43910/100000 [12:52:28<9:05:45,  1.71it/s]
Train steps ... :  44%|████▍     | 43911/100000 [12:52:29<9:05:52,  1.71it/s]
Train steps ... :  44%|████▍     | 43912/100000 [12:52:29<9:06:29,  1.71it/s]
Train steps ... :  44%|████▍     | 43913/100000 [12:52:30<9:06:39,  1.71it/s]
Train steps ... :  44%|████▍     | 43914/100000 [12:52:31<9:06:39,  1.71it/s]
Train steps ... :  44%|████▍     | 43915/100000 [12:52:31<9:06:24,  1.71it/s]
Train steps ... :  44%|████▍     | 43916/100000 [12:52:32<9:06:26,  1.71it/s]
Train steps ... :  44%|████▍     | 43917/100000 [12:52:32<9:06:33,  1.71it/s]
Train steps ... :  44%|████▍     | 43918/100000 [12:52:33<9:06:23,  1.71it/s]
Train steps ... :  44%|████▍     | 43919/100000 [12:52:34<9:07:46,  1.71it/s]
Train steps ... :  44%|████▍     | 43920/100000 [12:52:34<9:07:49,  1.71it/s]
Train steps ... :  44%|████▍     | 43921/100000 [12:52:35<9:07:11,  1.71it/s]
Train steps ... :  44%|████▍     | 43922/100000 [12:52:35<9:06:40,  1.71it/s]
Train steps ... :  44%|████▍     | 43923/100000 [12:52:36<9:07:04,  1.71it/s]
Train steps ... :  44%|████▍     | 43924/100000 [12:52:36<9:06:46,  1.71it/s]
Train steps ... :  44%|████▍     | 43925/100000 [12:52:37<9:06:58,  1.71it/s]Step... (43925 / 100000 | Loss: 0.8131299018859863, Learning Rate: 5.635678391959799e-05)
+
                                                                             
Step... (43925 / 100000 | Loss: 0.7013696432113647, Learning Rate: 5.635678391959799e-05)
+
Train steps ... :  44%|████▍     | 43925/100000 [12:52:37<9:06:58,  1.71it/s]
Train steps ... :  44%|████▍     | 43926/100000 [12:52:38<9:07:18,  1.71it/s]
Train steps ... :  44%|████▍     | 43927/100000 [12:52:38<9:06:53,  1.71it/s]
Train steps ... :  44%|████▍     | 43928/100000 [12:52:39<9:06:02,  1.71it/s]
Train steps ... :  44%|████▍     | 43929/100000 [12:52:39<9:06:05,  1.71it/s]
Train steps ... :  44%|████▍     | 43930/100000 [12:52:40<9:06:21,  1.71it/s]
Train steps ... :  44%|████▍     | 43931/100000 [12:52:41<9:05:58,  1.71it/s]
Train steps ... :  44%|████▍     | 43932/100000 [12:52:41<9:05:47,  1.71it/s]
Train steps ... :  44%|████▍     | 43933/100000 [12:52:42<9:06:25,  1.71it/s]
Train steps ... :  44%|████▍     | 43934/100000 [12:52:42<9:05:59,  1.71it/s]
Train steps ... :  44%|████▍     | 43935/100000 [12:52:43<9:05:43,  1.71it/s]
Train steps ... :  44%|████▍     | 43936/100000 [12:52:43<9:05:55,  1.71it/s]
Train steps ... :  44%|████▍     | 43937/100000 [12:52:44<9:05:52,  1.71it/s]
Train steps ... :  44%|████▍     | 43938/100000 [12:52:45<9:06:48,  1.71it/s]
Train steps ... :  44%|████▍     | 43939/100000 [12:52:45<9:06:58,  1.71it/s]
Train steps ... :  44%|████▍     | 43940/100000 [12:52:46<9:06:11,  1.71it/s]
Train steps ... :  44%|████▍     | 43941/100000 [12:52:46<9:05:46,  1.71it/s]
Train steps ... :  44%|████▍     | 43942/100000 [12:52:47<9:05:57,  1.71it/s]
Train steps ... :  44%|████▍     | 43943/100000 [12:52:48<9:06:05,  1.71it/s]
Train steps ... :  44%|████▍     | 43944/100000 [12:52:48<9:06:08,  1.71it/s]
Train steps ... :  44%|████▍     | 43945/100000 [12:52:49<9:06:20,  1.71it/s]
Train steps ... :  44%|████▍     | 43946/100000 [12:52:49<9:05:56,  1.71it/s]
Train steps ... :  44%|████▍     | 43947/100000 [12:52:50<9:05:50,  1.71it/s]
Train steps ... :  44%|████▍     | 43948/100000 [12:52:50<9:06:18,  1.71it/s]
Train steps ... :  44%|████▍     | 43949/100000 [12:52:51<9:06:04,  1.71it/s]
Train steps ... :  44%|████▍     | 43950/100000 [12:52:52<9:05:46,  1.71it/s]Step... (43950 / 100000 | Loss: 1.061354160308838, Learning Rate: 5.633165829145729e-05)
+
                                                                             
Step... (43950 / 100000 | Loss: 0.884288489818573, Learning Rate: 5.633165829145729e-05)
+
Train steps ... :  44%|████▍     | 43950/100000 [12:52:52<9:05:46,  1.71it/s]
Train steps ... :  44%|████▍     | 43951/100000 [12:52:52<9:06:33,  1.71it/s]
Train steps ... :  44%|████▍     | 43952/100000 [12:52:53<9:07:35,  1.71it/s]
Train steps ... :  44%|████▍     | 43953/100000 [12:52:53<9:07:30,  1.71it/s]
Train steps ... :  44%|████▍     | 43954/100000 [12:52:54<9:07:19,  1.71it/s]
Train steps ... :  44%|████▍     | 43955/100000 [12:52:55<9:08:07,  1.70it/s]
Train steps ... :  44%|████▍     | 43956/100000 [12:52:55<9:07:22,  1.71it/s]
Train steps ... :  44%|████▍     | 43957/100000 [12:52:56<9:07:30,  1.71it/s]
Train steps ... :  44%|████▍     | 43958/100000 [12:52:56<9:07:35,  1.71it/s]
Train steps ... :  44%|████▍     | 43959/100000 [12:52:57<9:06:39,  1.71it/s]
Train steps ... :  44%|████▍     | 43960/100000 [12:52:57<9:06:30,  1.71it/s]
Train steps ... :  44%|████▍     | 43961/100000 [12:52:58<9:06:52,  1.71it/s]
Train steps ... :  44%|████▍     | 43962/100000 [12:52:59<9:06:55,  1.71it/s]
Train steps ... :  44%|████▍     | 43963/100000 [12:52:59<9:06:27,  1.71it/s]
Train steps ... :  44%|████▍     | 43964/100000 [12:53:00<9:06:29,  1.71it/s]
Train steps ... :  44%|████▍     | 43965/100000 [12:53:00<9:05:50,  1.71it/s]
Train steps ... :  44%|████▍     | 43966/100000 [12:53:01<9:06:16,  1.71it/s]
Train steps ... :  44%|████▍     | 43967/100000 [12:53:02<9:05:59,  1.71it/s]
Train steps ... :  44%|████▍     | 43968/100000 [12:53:02<9:05:58,  1.71it/s]
Train steps ... :  44%|████▍     | 43969/100000 [12:53:03<9:06:51,  1.71it/s]
Train steps ... :  44%|████▍     | 43970/100000 [12:53:03<9:06:55,  1.71it/s]
Train steps ... :  44%|████▍     | 43971/100000 [12:53:04<9:06:12,  1.71it/s]
Train steps ... :  44%|████▍     | 43972/100000 [12:53:05<9:06:05,  1.71it/s]
Train steps ... :  44%|████▍     | 43973/100000 [12:53:05<9:06:14,  1.71it/s]
Train steps ... :  44%|████▍     | 43974/100000 [12:53:06<9:05:34,  1.71it/s]
Train steps ... :  44%|████▍     | 43975/100000 [12:53:06<9:05:29,  1.71it/s]Step... (43975 / 100000 | Loss: 0.715796172618866, Learning Rate: 5.630653266331658e-05)
+
                                                                             
Step... (43975 / 100000 | Loss: 0.952042281627655, Learning Rate: 5.630653266331658e-05)
+
Train steps ... :  44%|████▍     | 43975/100000 [12:53:07<9:05:29,  1.71it/s]
Train steps ... :  44%|████▍     | 43976/100000 [12:53:07<9:05:21,  1.71it/s]
Train steps ... :  44%|████▍     | 43977/100000 [12:53:07<9:05:30,  1.71it/s]
Train steps ... :  44%|████▍     | 43978/100000 [12:53:08<9:05:02,  1.71it/s]
Train steps ... :  44%|████▍     | 43979/100000 [12:53:09<9:05:18,  1.71it/s]
Train steps ... :  44%|████▍     | 43980/100000 [12:53:09<9:05:18,  1.71it/s]
Train steps ... :  44%|████▍     | 43981/100000 [12:53:10<9:05:22,  1.71it/s]
Train steps ... :  44%|████▍     | 43982/100000 [12:53:10<9:06:22,  1.71it/s]
Train steps ... :  44%|████▍     | 43983/100000 [12:53:11<9:05:27,  1.71it/s]
Train steps ... :  44%|████▍     | 43984/100000 [12:53:12<9:05:11,  1.71it/s]
Train steps ... :  44%|████▍     | 43985/100000 [12:53:12<9:06:28,  1.71it/s]
Train steps ... :  44%|████▍     | 43986/100000 [12:53:13<9:05:22,  1.71it/s]
Train steps ... :  44%|████▍     | 43987/100000 [12:53:13<9:07:21,  1.71it/s]
Train steps ... :  44%|████▍     | 43988/100000 [12:53:14<9:07:45,  1.70it/s]
Train steps ... :  44%|████▍     | 43989/100000 [12:53:14<9:06:23,  1.71it/s]
Train steps ... :  44%|████▍     | 43990/100000 [12:53:15<9:07:00,  1.71it/s]
Train steps ... :  44%|████▍     | 43991/100000 [12:53:16<9:06:51,  1.71it/s]
Train steps ... :  44%|████▍     | 43992/100000 [12:53:16<9:07:16,  1.71it/s]
Train steps ... :  44%|████▍     | 43993/100000 [12:53:17<9:06:26,  1.71it/s]
Train steps ... :  44%|████▍     | 43994/100000 [12:53:17<9:06:05,  1.71it/s]
Train steps ... :  44%|████▍     | 43995/100000 [12:53:18<9:05:53,  1.71it/s]
Train steps ... :  44%|████▍     | 43996/100000 [12:53:19<9:06:10,  1.71it/s]
Train steps ... :  44%|████▍     | 43997/100000 [12:53:19<9:06:15,  1.71it/s]
Train steps ... :  44%|████▍     | 43998/100000 [12:53:20<9:06:18,  1.71it/s]
Train steps ... :  44%|████▍     | 43999/100000 [12:53:20<9:05:48,  1.71it/s]
Train steps ... :  44%|████▍     | 44000/100000 [12:53:21<9:05:40,  1.71it/s]Step... (44000 / 100000 | Loss: 0.9260667562484741, Learning Rate: 5.628140703517588e-05)
+
                                                                             
Step... (44000 / 100000 | Loss: 0.7335336208343506, Learning Rate: 5.628140703517588e-05)
+
Train steps ... :  44%|████▍     | 44000/100000 [12:53:21<9:05:40,  1.71it/s]
Train steps ... :  44%|████▍     | 44001/100000 [12:53:21<9:06:13,  1.71it/s]
Train steps ... :  44%|████▍     | 44002/100000 [12:53:22<9:06:28,  1.71it/s]
Train steps ... :  44%|████▍     | 44003/100000 [12:53:23<9:05:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44004/100000 [12:53:23<9:05:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44005/100000 [12:53:24<9:05:21,  1.71it/s]
Train steps ... :  44%|████▍     | 44006/100000 [12:53:24<9:05:53,  1.71it/s]
Train steps ... :  44%|████▍     | 44007/100000 [12:53:25<9:05:41,  1.71it/s]
Train steps ... :  44%|████▍     | 44008/100000 [12:53:26<9:05:29,  1.71it/s]
Train steps ... :  44%|████▍     | 44009/100000 [12:53:26<9:05:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44010/100000 [12:53:27<9:05:26,  1.71it/s]
Train steps ... :  44%|████▍     | 44011/100000 [12:53:27<9:05:42,  1.71it/s]
Train steps ... :  44%|████▍     | 44012/100000 [12:53:28<9:05:56,  1.71it/s]
Train steps ... :  44%|████▍     | 44013/100000 [12:53:28<9:05:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44014/100000 [12:53:29<9:05:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44015/100000 [12:53:30<9:05:34,  1.71it/s]
Train steps ... :  44%|████▍     | 44016/100000 [12:53:30<9:05:47,  1.71it/s]
Train steps ... :  44%|████▍     | 44017/100000 [12:53:31<9:05:55,  1.71it/s]
Train steps ... :  44%|████▍     | 44018/100000 [12:53:31<9:06:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44019/100000 [12:53:32<9:06:23,  1.71it/s]
Train steps ... :  44%|████▍     | 44020/100000 [12:53:33<9:06:40,  1.71it/s]
Train steps ... :  44%|████▍     | 44021/100000 [12:53:33<9:05:50,  1.71it/s]
Train steps ... :  44%|████▍     | 44022/100000 [12:53:34<9:05:40,  1.71it/s]
Train steps ... :  44%|████▍     | 44023/100000 [12:53:34<9:05:50,  1.71it/s]
Train steps ... :  44%|████▍     | 44024/100000 [12:53:35<9:05:31,  1.71it/s]
Train steps ... :  44%|████▍     | 44025/100000 [12:53:36<9:05:29,  1.71it/s]Step... (44025 / 100000 | Loss: 0.8068627119064331, Learning Rate: 5.6256281407035184e-05)
+
                                                                             
Step... (44025 / 100000 | Loss: 0.7546169757843018, Learning Rate: 5.6256281407035184e-05)
+
Train steps ... :  44%|████▍     | 44025/100000 [12:53:36<9:05:29,  1.71it/s]
Train steps ... :  44%|████▍     | 44026/100000 [12:53:36<9:05:21,  1.71it/s]
Train steps ... :  44%|████▍     | 44027/100000 [12:53:37<9:05:21,  1.71it/s]
Train steps ... :  44%|████▍     | 44028/100000 [12:53:37<9:04:46,  1.71it/s]
Train steps ... :  44%|████▍     | 44029/100000 [12:53:38<9:05:22,  1.71it/s]
Train steps ... :  44%|████▍     | 44030/100000 [12:53:38<9:05:21,  1.71it/s]
Train steps ... :  44%|████▍     | 44031/100000 [12:53:39<9:05:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44032/100000 [12:53:40<9:04:51,  1.71it/s]
Train steps ... :  44%|████▍     | 44033/100000 [12:53:40<9:05:10,  1.71it/s]
Train steps ... :  44%|████▍     | 44034/100000 [12:53:41<9:05:26,  1.71it/s]
Train steps ... :  44%|████▍     | 44035/100000 [12:53:41<9:05:41,  1.71it/s]
Train steps ... :  44%|████▍     | 44036/100000 [12:53:42<9:05:11,  1.71it/s]
Train steps ... :  44%|████▍     | 44037/100000 [12:53:43<9:05:23,  1.71it/s]
Train steps ... :  44%|████▍     | 44038/100000 [12:53:43<9:05:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44039/100000 [12:53:44<9:05:40,  1.71it/s]
Train steps ... :  44%|████▍     | 44040/100000 [12:53:44<9:05:22,  1.71it/s]
Train steps ... :  44%|████▍     | 44041/100000 [12:53:45<9:06:06,  1.71it/s]
Train steps ... :  44%|████▍     | 44042/100000 [12:53:45<9:06:22,  1.71it/s]
Train steps ... :  44%|████▍     | 44043/100000 [12:53:46<9:05:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44044/100000 [12:53:47<9:05:06,  1.71it/s]
Train steps ... :  44%|████▍     | 44045/100000 [12:53:47<9:04:53,  1.71it/s]
Train steps ... :  44%|████▍     | 44046/100000 [12:53:48<9:05:47,  1.71it/s]
Train steps ... :  44%|████▍     | 44047/100000 [12:53:48<9:05:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44048/100000 [12:53:49<9:05:21,  1.71it/s]
Train steps ... :  44%|████▍     | 44049/100000 [12:53:50<9:04:58,  1.71it/s]
Train steps ... :  44%|████▍     | 44050/100000 [12:53:50<9:05:00,  1.71it/s]Step... (44050 / 100000 | Loss: 0.9593422412872314, Learning Rate: 5.6231155778894474e-05)
+
                                                                             
Step... (44050 / 100000 | Loss: 0.6048875451087952, Learning Rate: 5.6231155778894474e-05)
+
Train steps ... :  44%|████▍     | 44050/100000 [12:53:50<9:05:00,  1.71it/s]
Train steps ... :  44%|████▍     | 44051/100000 [12:53:51<9:05:26,  1.71it/s]
Train steps ... :  44%|████▍     | 44052/100000 [12:53:51<9:04:59,  1.71it/s]
Train steps ... :  44%|████▍     | 44053/100000 [12:53:52<9:04:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44054/100000 [12:53:52<9:04:50,  1.71it/s]
Train steps ... :  44%|████▍     | 44055/100000 [12:53:53<9:05:24,  1.71it/s]
Train steps ... :  44%|████▍     | 44056/100000 [12:53:54<9:06:00,  1.71it/s]
Train steps ... :  44%|████▍     | 44057/100000 [12:53:54<9:04:55,  1.71it/s]
Train steps ... :  44%|████▍     | 44058/100000 [12:53:55<9:05:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44059/100000 [12:53:55<9:05:10,  1.71it/s]
Train steps ... :  44%|████▍     | 44060/100000 [12:53:56<9:04:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44061/100000 [12:53:57<9:04:57,  1.71it/s]
Train steps ... :  44%|████▍     | 44062/100000 [12:53:57<9:04:54,  1.71it/s]
Train steps ... :  44%|████▍     | 44063/100000 [12:53:58<9:04:44,  1.71it/s]
Train steps ... :  44%|████▍     | 44064/100000 [12:53:58<9:04:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44065/100000 [12:53:59<9:04:26,  1.71it/s]
Train steps ... :  44%|████▍     | 44066/100000 [12:53:59<9:05:06,  1.71it/s]
Train steps ... :  44%|████▍     | 44067/100000 [12:54:00<9:05:01,  1.71it/s]
Train steps ... :  44%|████▍     | 44068/100000 [12:54:01<9:04:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44069/100000 [12:54:01<9:04:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44070/100000 [12:54:02<9:05:18,  1.71it/s]
Train steps ... :  44%|████▍     | 44071/100000 [12:54:02<9:05:24,  1.71it/s]
Train steps ... :  44%|████▍     | 44072/100000 [12:54:03<9:06:11,  1.71it/s]
Train steps ... :  44%|████▍     | 44073/100000 [12:54:04<9:05:05,  1.71it/s]
Train steps ... :  44%|████▍     | 44074/100000 [12:54:04<9:05:28,  1.71it/s]
Train steps ... :  44%|████▍     | 44075/100000 [12:54:05<9:05:17,  1.71it/s]Step... (44075 / 100000 | Loss: 0.9151829481124878, Learning Rate: 5.620603015075378e-05)
+
                                                                             
Step... (44075 / 100000 | Loss: 1.157460331916809, Learning Rate: 5.620603015075378e-05)
+
Train steps ... :  44%|████▍     | 44075/100000 [12:54:05<9:05:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44076/100000 [12:54:05<9:06:11,  1.71it/s]
Train steps ... :  44%|████▍     | 44077/100000 [12:54:06<9:05:48,  1.71it/s]
Train steps ... :  44%|████▍     | 44078/100000 [12:54:07<9:05:01,  1.71it/s]
Train steps ... :  44%|████▍     | 44079/100000 [12:54:07<9:05:19,  1.71it/s]
Train steps ... :  44%|████▍     | 44080/100000 [12:54:08<9:05:22,  1.71it/s]
Train steps ... :  44%|████▍     | 44081/100000 [12:54:08<9:05:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44082/100000 [12:54:09<9:04:59,  1.71it/s]
Train steps ... :  44%|████▍     | 44083/100000 [12:54:09<9:04:33,  1.71it/s]
Train steps ... :  44%|████▍     | 44084/100000 [12:54:10<9:04:01,  1.71it/s]
Train steps ... :  44%|████▍     | 44085/100000 [12:54:11<9:04:42,  1.71it/s]
Train steps ... :  44%|████▍     | 44086/100000 [12:54:11<9:04:48,  1.71it/s]
Train steps ... :  44%|████▍     | 44087/100000 [12:54:12<9:04:43,  1.71it/s]
Train steps ... :  44%|████▍     | 44088/100000 [12:54:12<9:04:46,  1.71it/s]
Train steps ... :  44%|████▍     | 44089/100000 [12:54:13<9:04:44,  1.71it/s]
Train steps ... :  44%|████▍     | 44090/100000 [12:54:14<9:04:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44091/100000 [12:54:14<9:04:42,  1.71it/s]
Train steps ... :  44%|████▍     | 44092/100000 [12:54:15<9:04:44,  1.71it/s]
Train steps ... :  44%|████▍     | 44093/100000 [12:54:15<9:04:13,  1.71it/s]
Train steps ... :  44%|████▍     | 44094/100000 [12:54:16<9:03:59,  1.71it/s]
Train steps ... :  44%|████▍     | 44095/100000 [12:54:16<9:03:58,  1.71it/s]
Train steps ... :  44%|████▍     | 44096/100000 [12:54:17<9:03:54,  1.71it/s]
Train steps ... :  44%|████▍     | 44097/100000 [12:54:18<9:03:42,  1.71it/s]
Train steps ... :  44%|████▍     | 44098/100000 [12:54:18<9:03:57,  1.71it/s]
Train steps ... :  44%|████▍     | 44099/100000 [12:54:19<9:04:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44100/100000 [12:54:19<9:04:28,  1.71it/s]Step... (44100 / 100000 | Loss: 0.8302603363990784, Learning Rate: 5.618090452261307e-05)
+
                                                                             
Step... (44100 / 100000 | Loss: 1.0643812417984009, Learning Rate: 5.618090452261307e-05)
+
Train steps ... :  44%|████▍     | 44100/100000 [12:54:20<9:04:28,  1.71it/s]
Train steps ... :  44%|████▍     | 44101/100000 [12:54:20<9:04:42,  1.71it/s]
Train steps ... :  44%|████▍     | 44102/100000 [12:54:21<9:04:27,  1.71it/s]
Train steps ... :  44%|████▍     | 44103/100000 [12:54:21<9:05:03,  1.71it/s]
Train steps ... :  44%|████▍     | 44104/100000 [12:54:22<9:04:20,  1.71it/s]
Train steps ... :  44%|████▍     | 44105/100000 [12:54:22<9:03:58,  1.71it/s]
Train steps ... :  44%|████▍     | 44106/100000 [12:54:23<9:03:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44107/100000 [12:54:23<9:03:46,  1.71it/s]
Train steps ... :  44%|████▍     | 44108/100000 [12:54:24<9:04:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44109/100000 [12:54:25<9:03:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44110/100000 [12:54:25<9:04:16,  1.71it/s]
Train steps ... :  44%|████▍     | 44111/100000 [12:54:26<9:03:57,  1.71it/s]
Train steps ... :  44%|████▍     | 44112/100000 [12:54:26<9:03:54,  1.71it/s]
Train steps ... :  44%|████▍     | 44113/100000 [12:54:27<9:03:21,  1.71it/s]
Train steps ... :  44%|████▍     | 44114/100000 [12:54:28<9:03:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44115/100000 [12:54:28<9:04:18,  1.71it/s]
Train steps ... :  44%|████▍     | 44116/100000 [12:54:29<9:04:09,  1.71it/s]
Train steps ... :  44%|████▍     | 44117/100000 [12:54:29<9:06:34,  1.70it/s]
Train steps ... :  44%|████▍     | 44118/100000 [12:54:30<9:05:48,  1.71it/s]
Train steps ... :  44%|████▍     | 44119/100000 [12:54:30<9:05:44,  1.71it/s]
Train steps ... :  44%|████▍     | 44120/100000 [12:54:31<9:04:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44121/100000 [12:54:32<9:04:33,  1.71it/s]
Train steps ... :  44%|████▍     | 44122/100000 [12:54:32<9:04:51,  1.71it/s]
Train steps ... :  44%|████▍     | 44123/100000 [12:54:33<9:04:14,  1.71it/s]
Train steps ... :  44%|████▍     | 44124/100000 [12:54:33<9:04:41,  1.71it/s]
Train steps ... :  44%|████▍     | 44125/100000 [12:54:34<9:04:14,  1.71it/s]Step... (44125 / 100000 | Loss: 0.7081465721130371, Learning Rate: 5.6155778894472364e-05)
+
                                                                             
Step... (44125 / 100000 | Loss: 0.9173715114593506, Learning Rate: 5.6155778894472364e-05)
+
Train steps ... :  44%|████▍     | 44125/100000 [12:54:34<9:04:14,  1.71it/s]
Train steps ... :  44%|████▍     | 44126/100000 [12:54:35<9:05:05,  1.71it/s]
Train steps ... :  44%|████▍     | 44127/100000 [12:54:35<9:04:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44128/100000 [12:54:36<9:04:09,  1.71it/s]
Train steps ... :  44%|████▍     | 44129/100000 [12:54:36<9:03:47,  1.71it/s]
Train steps ... :  44%|████▍     | 44130/100000 [12:54:37<9:04:04,  1.71it/s]
Train steps ... :  44%|████▍     | 44131/100000 [12:54:37<9:03:53,  1.71it/s]
Train steps ... :  44%|████▍     | 44132/100000 [12:54:38<9:03:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44133/100000 [12:54:39<9:03:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44134/100000 [12:54:39<9:03:41,  1.71it/s]
Train steps ... :  44%|████▍     | 44135/100000 [12:54:40<9:04:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44136/100000 [12:54:40<9:04:35,  1.71it/s]
Train steps ... :  44%|████▍     | 44137/100000 [12:54:41<9:04:06,  1.71it/s]
Train steps ... :  44%|████▍     | 44138/100000 [12:54:42<9:04:07,  1.71it/s]
Train steps ... :  44%|████▍     | 44139/100000 [12:54:42<9:04:12,  1.71it/s]
Train steps ... :  44%|████▍     | 44140/100000 [12:54:43<9:05:26,  1.71it/s]
Train steps ... :  44%|████▍     | 44141/100000 [12:54:43<9:03:43,  1.71it/s]
Train steps ... :  44%|████▍     | 44142/100000 [12:54:44<9:04:35,  1.71it/s]
Train steps ... :  44%|████▍     | 44143/100000 [12:54:45<9:04:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44144/100000 [12:54:45<9:04:31,  1.71it/s]
Train steps ... :  44%|████▍     | 44145/100000 [12:54:46<9:04:51,  1.71it/s]
Train steps ... :  44%|████▍     | 44146/100000 [12:54:46<9:05:54,  1.71it/s]
Train steps ... :  44%|████▍     | 44147/100000 [12:54:47<9:05:08,  1.71it/s]
Train steps ... :  44%|████▍     | 44148/100000 [12:54:47<9:04:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44149/100000 [12:54:48<9:04:09,  1.71it/s]
Train steps ... :  44%|████▍     | 44150/100000 [12:54:49<9:04:01,  1.71it/s]Step... (44150 / 100000 | Loss: 1.0705738067626953, Learning Rate: 5.6130653266331654e-05)
+
                                                                             
Step... (44150 / 100000 | Loss: 0.898914635181427, Learning Rate: 5.6130653266331654e-05)
+
Train steps ... :  44%|████▍     | 44150/100000 [12:54:49<9:04:01,  1.71it/s]
Train steps ... :  44%|████▍     | 44151/100000 [12:54:49<9:04:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44152/100000 [12:54:50<9:04:20,  1.71it/s]
Train steps ... :  44%|████▍     | 44153/100000 [12:54:50<9:03:59,  1.71it/s]
Train steps ... :  44%|████▍     | 44154/100000 [12:54:51<9:03:26,  1.71it/s]
Train steps ... :  44%|████▍     | 44155/100000 [12:54:52<9:03:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44156/100000 [12:54:52<9:03:20,  1.71it/s]
Train steps ... :  44%|████▍     | 44157/100000 [12:54:53<9:03:03,  1.71it/s]
Train steps ... :  44%|████▍     | 44158/100000 [12:54:53<9:03:07,  1.71it/s]
Train steps ... :  44%|████▍     | 44159/100000 [12:54:54<9:03:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44160/100000 [12:54:54<9:03:57,  1.71it/s]
Train steps ... :  44%|████▍     | 44161/100000 [12:54:55<9:04:26,  1.71it/s]
Train steps ... :  44%|████▍     | 44162/100000 [12:54:56<9:04:05,  1.71it/s]
Train steps ... :  44%|████▍     | 44163/100000 [12:54:56<9:03:53,  1.71it/s]
Train steps ... :  44%|████▍     | 44164/100000 [12:54:57<9:03:31,  1.71it/s]
Train steps ... :  44%|████▍     | 44165/100000 [12:54:57<9:03:59,  1.71it/s]
Train steps ... :  44%|████▍     | 44166/100000 [12:54:58<9:03:43,  1.71it/s]
Train steps ... :  44%|████▍     | 44167/100000 [12:54:59<9:04:04,  1.71it/s]
Train steps ... :  44%|████▍     | 44168/100000 [12:54:59<9:03:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44169/100000 [12:55:00<9:04:13,  1.71it/s]
Train steps ... :  44%|████▍     | 44170/100000 [12:55:00<9:03:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44171/100000 [12:55:01<9:03:16,  1.71it/s]
Train steps ... :  44%|████▍     | 44172/100000 [12:55:01<9:03:39,  1.71it/s]
Train steps ... :  44%|████▍     | 44173/100000 [12:55:02<9:03:44,  1.71it/s]
Train steps ... :  44%|████▍     | 44174/100000 [12:55:03<9:04:01,  1.71it/s]
Train steps ... :  44%|████▍     | 44175/100000 [12:55:03<9:04:23,  1.71it/s]Step... (44175 / 100000 | Loss: 0.6619841456413269, Learning Rate: 5.610552763819096e-05)
+
                                                                             
Step... (44175 / 100000 | Loss: 0.9230605363845825, Learning Rate: 5.610552763819096e-05)
+
Train steps ... :  44%|████▍     | 44175/100000 [12:55:04<9:04:23,  1.71it/s]
Train steps ... :  44%|████▍     | 44176/100000 [12:55:04<9:04:04,  1.71it/s]
Train steps ... :  44%|████▍     | 44177/100000 [12:55:04<9:03:23,  1.71it/s]
Train steps ... :  44%|████▍     | 44178/100000 [12:55:05<9:03:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44179/100000 [12:55:06<9:03:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44180/100000 [12:55:06<9:04:15,  1.71it/s]
Train steps ... :  44%|████▍     | 44181/100000 [12:55:07<9:04:02,  1.71it/s]
Train steps ... :  44%|████▍     | 44182/100000 [12:55:07<9:04:05,  1.71it/s]
Train steps ... :  44%|████▍     | 44183/100000 [12:55:08<9:04:08,  1.71it/s]
Train steps ... :  44%|████▍     | 44184/100000 [12:55:08<9:03:43,  1.71it/s]
Train steps ... :  44%|████▍     | 44185/100000 [12:55:09<9:03:07,  1.71it/s]
Train steps ... :  44%|████▍     | 44186/100000 [12:55:10<9:03:02,  1.71it/s]
Train steps ... :  44%|████▍     | 44187/100000 [12:55:10<9:03:00,  1.71it/s]
Train steps ... :  44%|████▍     | 44188/100000 [12:55:11<9:03:14,  1.71it/s]
Train steps ... :  44%|████▍     | 44189/100000 [12:55:11<9:03:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44190/100000 [12:55:12<9:03:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44191/100000 [12:55:13<9:04:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44192/100000 [12:55:13<9:04:22,  1.71it/s]
Train steps ... :  44%|████▍     | 44193/100000 [12:55:14<9:04:59,  1.71it/s]
Train steps ... :  44%|████▍     | 44194/100000 [12:55:14<9:03:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44195/100000 [12:55:15<9:04:03,  1.71it/s]
Train steps ... :  44%|████▍     | 44196/100000 [12:55:15<9:03:46,  1.71it/s]
Train steps ... :  44%|████▍     | 44197/100000 [12:55:16<9:03:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44198/100000 [12:55:17<9:03:21,  1.71it/s]
Train steps ... :  44%|████▍     | 44199/100000 [12:55:17<9:03:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44200/100000 [12:55:18<9:03:20,  1.71it/s]Step... (44200 / 100000 | Loss: 0.8545314073562622, Learning Rate: 5.608040201005026e-05)
+
                                                                             
Step... (44200 / 100000 | Loss: 0.6377502679824829, Learning Rate: 5.608040201005026e-05)
+
Train steps ... :  44%|████▍     | 44200/100000 [12:55:18<9:03:20,  1.71it/s]
Train steps ... :  44%|████▍     | 44201/100000 [12:55:18<9:02:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44202/100000 [12:55:19<9:03:13,  1.71it/s]
Train steps ... :  44%|████▍     | 44203/100000 [12:55:20<9:02:34,  1.71it/s]
Train steps ... :  44%|████▍     | 44204/100000 [12:55:20<9:03:26,  1.71it/s]
Train steps ... :  44%|████▍     | 44205/100000 [12:55:21<9:03:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44206/100000 [12:55:21<9:03:03,  1.71it/s]
Train steps ... :  44%|████▍     | 44207/100000 [12:55:22<9:03:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44208/100000 [12:55:22<9:03:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44209/100000 [12:55:23<9:03:24,  1.71it/s]
Train steps ... :  44%|████▍     | 44210/100000 [12:55:24<9:04:22,  1.71it/s]
Train steps ... :  44%|████▍     | 44211/100000 [12:55:24<9:04:53,  1.71it/s]
Train steps ... :  44%|████▍     | 44212/100000 [12:55:25<9:05:05,  1.71it/s]
Train steps ... :  44%|████▍     | 44213/100000 [12:55:25<9:04:06,  1.71it/s]
Train steps ... :  44%|████▍     | 44214/100000 [12:55:26<9:03:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44215/100000 [12:55:27<9:03:46,  1.71it/s]
Train steps ... :  44%|████▍     | 44216/100000 [12:55:27<9:03:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44217/100000 [12:55:28<9:04:11,  1.71it/s]
Train steps ... :  44%|████▍     | 44218/100000 [12:55:28<9:04:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44219/100000 [12:55:29<9:03:51,  1.71it/s]
Train steps ... :  44%|████▍     | 44220/100000 [12:55:30<9:03:40,  1.71it/s]
Train steps ... :  44%|████▍     | 44221/100000 [12:55:30<9:03:07,  1.71it/s]
Train steps ... :  44%|████▍     | 44222/100000 [12:55:31<9:03:55,  1.71it/s]
Train steps ... :  44%|████▍     | 44223/100000 [12:55:31<9:03:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44224/100000 [12:55:32<9:03:13,  1.71it/s]
Train steps ... :  44%|████▍     | 44225/100000 [12:55:32<9:04:03,  1.71it/s]Step... (44225 / 100000 | Loss: 0.5148338079452515, Learning Rate: 5.605527638190955e-05)
+
                                                                             
Step... (44225 / 100000 | Loss: 0.8899519443511963, Learning Rate: 5.605527638190955e-05)
+
Train steps ... :  44%|████▍     | 44225/100000 [12:55:33<9:04:03,  1.71it/s]
Train steps ... :  44%|████▍     | 44226/100000 [12:55:33<9:04:11,  1.71it/s]
Train steps ... :  44%|████▍     | 44227/100000 [12:55:34<9:03:54,  1.71it/s]
Train steps ... :  44%|████▍     | 44228/100000 [12:55:34<9:03:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44229/100000 [12:55:35<9:04:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44230/100000 [12:55:35<9:04:15,  1.71it/s]
Train steps ... :  44%|████▍     | 44231/100000 [12:55:36<9:03:16,  1.71it/s]
Train steps ... :  44%|████▍     | 44232/100000 [12:55:37<9:03:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44233/100000 [12:55:37<9:03:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44234/100000 [12:55:38<9:03:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44235/100000 [12:55:38<9:03:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44236/100000 [12:55:39<9:03:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44237/100000 [12:55:39<9:03:47,  1.71it/s]
Train steps ... :  44%|████▍     | 44238/100000 [12:55:40<9:03:40,  1.71it/s]
Train steps ... :  44%|████▍     | 44239/100000 [12:55:41<9:03:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44240/100000 [12:55:41<9:04:07,  1.71it/s]
Train steps ... :  44%|████▍     | 44241/100000 [12:55:42<9:03:33,  1.71it/s]
Train steps ... :  44%|████▍     | 44242/100000 [12:55:42<9:03:43,  1.71it/s]
Train steps ... :  44%|████▍     | 44243/100000 [12:55:43<9:04:07,  1.71it/s]
Train steps ... :  44%|████▍     | 44244/100000 [12:55:44<9:03:21,  1.71it/s]
Train steps ... :  44%|████▍     | 44245/100000 [12:55:44<9:03:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44246/100000 [12:55:45<9:03:35,  1.71it/s]
Train steps ... :  44%|████▍     | 44247/100000 [12:55:45<9:04:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44248/100000 [12:55:46<9:03:28,  1.71it/s]
Train steps ... :  44%|████▍     | 44249/100000 [12:55:46<9:03:58,  1.71it/s]
Train steps ... :  44%|████▍     | 44250/100000 [12:55:47<9:03:50,  1.71it/s]Step... (44250 / 100000 | Loss: 0.7428478002548218, Learning Rate: 5.6030150753768854e-05)
+
                                                                             
Step... (44250 / 100000 | Loss: 0.7731283903121948, Learning Rate: 5.6030150753768854e-05)
+
Train steps ... :  44%|████▍     | 44250/100000 [12:55:47<9:03:50,  1.71it/s]
Train steps ... :  44%|████▍     | 44251/100000 [12:55:48<9:05:04,  1.70it/s]
Train steps ... :  44%|████▍     | 44252/100000 [12:55:48<9:03:02,  1.71it/s]
Train steps ... :  44%|████▍     | 44253/100000 [12:55:49<9:03:54,  1.71it/s]
Train steps ... :  44%|████▍     | 44254/100000 [12:55:49<9:03:02,  1.71it/s]
Train steps ... :  44%|████▍     | 44255/100000 [12:55:50<9:03:06,  1.71it/s]
Train steps ... :  44%|████▍     | 44256/100000 [12:55:51<9:03:11,  1.71it/s]
Train steps ... :  44%|████▍     | 44257/100000 [12:55:51<9:03:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44258/100000 [12:55:52<9:03:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44259/100000 [12:55:52<9:03:00,  1.71it/s]
Train steps ... :  44%|████▍     | 44260/100000 [12:55:53<9:02:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44261/100000 [12:55:54<9:03:08,  1.71it/s]
Train steps ... :  44%|████▍     | 44262/100000 [12:55:54<9:03:48,  1.71it/s]
Train steps ... :  44%|████▍     | 44263/100000 [12:55:55<9:03:41,  1.71it/s]
Train steps ... :  44%|████▍     | 44264/100000 [12:55:55<9:03:16,  1.71it/s]
Train steps ... :  44%|████▍     | 44265/100000 [12:55:56<9:02:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44266/100000 [12:55:56<9:02:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44267/100000 [12:55:57<9:02:18,  1.71it/s]
Train steps ... :  44%|████▍     | 44268/100000 [12:55:58<9:02:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44269/100000 [12:55:58<9:02:57,  1.71it/s]
Train steps ... :  44%|████▍     | 44270/100000 [12:55:59<9:03:42,  1.71it/s]
Train steps ... :  44%|████▍     | 44271/100000 [12:55:59<9:03:12,  1.71it/s]
Train steps ... :  44%|████▍     | 44272/100000 [12:56:00<9:04:03,  1.71it/s]
Train steps ... :  44%|████▍     | 44273/100000 [12:56:01<9:03:00,  1.71it/s]
Train steps ... :  44%|████▍     | 44274/100000 [12:56:01<9:02:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44275/100000 [12:56:02<9:03:10,  1.71it/s]Step... (44275 / 100000 | Loss: 0.7243778109550476, Learning Rate: 5.6005025125628144e-05)
+
                                                                             
Step... (44275 / 100000 | Loss: 0.7080188393592834, Learning Rate: 5.6005025125628144e-05)
+
Train steps ... :  44%|████▍     | 44275/100000 [12:56:02<9:03:10,  1.71it/s]
Train steps ... :  44%|████▍     | 44276/100000 [12:56:02<9:04:31,  1.71it/s]
Train steps ... :  44%|████▍     | 44277/100000 [12:56:03<9:04:04,  1.71it/s]
Train steps ... :  44%|████▍     | 44278/100000 [12:56:03<9:04:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44279/100000 [12:56:04<9:03:53,  1.71it/s]
Train steps ... :  44%|████▍     | 44280/100000 [12:56:05<9:03:55,  1.71it/s]
Train steps ... :  44%|████▍     | 44281/100000 [12:56:05<9:04:14,  1.71it/s]
Train steps ... :  44%|████▍     | 44282/100000 [12:56:06<9:04:26,  1.71it/s]
Train steps ... :  44%|████▍     | 44283/100000 [12:56:06<9:04:03,  1.71it/s]
Train steps ... :  44%|████▍     | 44284/100000 [12:56:07<9:03:46,  1.71it/s]
Train steps ... :  44%|████▍     | 44285/100000 [12:56:08<9:03:28,  1.71it/s]
Train steps ... :  44%|████▍     | 44286/100000 [12:56:08<9:03:31,  1.71it/s]
Train steps ... :  44%|████▍     | 44287/100000 [12:56:09<9:03:35,  1.71it/s]
Train steps ... :  44%|████▍     | 44288/100000 [12:56:09<9:04:13,  1.71it/s]
Train steps ... :  44%|████▍     | 44289/100000 [12:56:10<9:03:42,  1.71it/s]
Train steps ... :  44%|████▍     | 44290/100000 [12:56:10<9:03:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44291/100000 [12:56:11<9:03:15,  1.71it/s]
Train steps ... :  44%|████▍     | 44292/100000 [12:56:12<9:03:40,  1.71it/s]
Train steps ... :  44%|████▍     | 44293/100000 [12:56:12<9:03:14,  1.71it/s]
Train steps ... :  44%|████▍     | 44294/100000 [12:56:13<9:02:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44295/100000 [12:56:13<9:02:35,  1.71it/s]
Train steps ... :  44%|████▍     | 44296/100000 [12:56:14<9:02:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44297/100000 [12:56:15<9:02:28,  1.71it/s]
Train steps ... :  44%|████▍     | 44298/100000 [12:56:15<9:03:12,  1.71it/s]
Train steps ... :  44%|████▍     | 44299/100000 [12:56:16<9:02:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44300/100000 [12:56:16<9:03:02,  1.71it/s]Step... (44300 / 100000 | Loss: 0.7367573976516724, Learning Rate: 5.597989949748744e-05)
+
                                                                             
Step... (44300 / 100000 | Loss: 0.7739068269729614, Learning Rate: 5.597989949748744e-05)
+
Train steps ... :  44%|████▍     | 44300/100000 [12:56:17<9:03:02,  1.71it/s]
Train steps ... :  44%|████▍     | 44301/100000 [12:56:17<9:02:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44302/100000 [12:56:17<9:03:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44303/100000 [12:56:18<9:04:01,  1.71it/s]
Train steps ... :  44%|████▍     | 44304/100000 [12:56:19<9:03:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44305/100000 [12:56:19<9:03:39,  1.71it/s]
Train steps ... :  44%|████▍     | 44306/100000 [12:56:20<9:03:00,  1.71it/s]
Train steps ... :  44%|████▍     | 44307/100000 [12:56:20<9:02:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44308/100000 [12:56:21<9:02:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44309/100000 [12:56:22<9:03:27,  1.71it/s]
Train steps ... :  44%|████▍     | 44310/100000 [12:56:22<9:04:05,  1.71it/s]
Train steps ... :  44%|████▍     | 44311/100000 [12:56:23<9:03:52,  1.71it/s]
Train steps ... :  44%|████▍     | 44312/100000 [12:56:23<9:04:18,  1.71it/s]
Train steps ... :  44%|████▍     | 44313/100000 [12:56:24<9:04:14,  1.71it/s]
Train steps ... :  44%|████▍     | 44314/100000 [12:56:25<9:04:28,  1.70it/s]
Train steps ... :  44%|████▍     | 44315/100000 [12:56:25<9:05:35,  1.70it/s]
Train steps ... :  44%|████▍     | 44316/100000 [12:56:26<9:05:17,  1.70it/s]
Train steps ... :  44%|████▍     | 44317/100000 [12:56:26<9:03:46,  1.71it/s]
Train steps ... :  44%|████▍     | 44318/100000 [12:56:27<9:04:56,  1.70it/s]
Train steps ... :  44%|████▍     | 44319/100000 [12:56:27<9:03:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44320/100000 [12:56:28<9:03:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44321/100000 [12:56:29<9:02:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44322/100000 [12:56:29<9:03:48,  1.71it/s]
Train steps ... :  44%|████▍     | 44323/100000 [12:56:30<9:03:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44324/100000 [12:56:30<9:03:24,  1.71it/s]
Train steps ... :  44%|████▍     | 44325/100000 [12:56:31<9:03:08,  1.71it/s]Step... (44325 / 100000 | Loss: 1.0898005962371826, Learning Rate: 5.595477386934673e-05)
+
                                                                             
Step... (44325 / 100000 | Loss: 0.5987443923950195, Learning Rate: 5.595477386934673e-05)
+
Train steps ... :  44%|████▍     | 44325/100000 [12:56:31<9:03:08,  1.71it/s]
Train steps ... :  44%|████▍     | 44326/100000 [12:56:32<9:02:58,  1.71it/s]
Train steps ... :  44%|████▍     | 44327/100000 [12:56:32<9:02:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44328/100000 [12:56:33<9:03:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44329/100000 [12:56:33<9:03:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44330/100000 [12:56:34<9:02:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44331/100000 [12:56:34<9:04:49,  1.70it/s]
Train steps ... :  44%|████▍     | 44332/100000 [12:56:35<9:05:10,  1.70it/s]
Train steps ... :  44%|████▍     | 44333/100000 [12:56:36<9:03:47,  1.71it/s]
Train steps ... :  44%|████▍     | 44334/100000 [12:56:36<9:04:10,  1.70it/s]
Train steps ... :  44%|████▍     | 44335/100000 [12:56:37<9:03:04,  1.71it/s]
Train steps ... :  44%|████▍     | 44336/100000 [12:56:37<9:02:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44337/100000 [12:56:38<9:02:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44338/100000 [12:56:39<9:02:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44339/100000 [12:56:39<9:02:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44340/100000 [12:56:40<9:02:46,  1.71it/s]
Train steps ... :  44%|████▍     | 44341/100000 [12:56:40<9:02:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44342/100000 [12:56:41<9:01:59,  1.71it/s]
Train steps ... :  44%|████▍     | 44343/100000 [12:56:42<9:03:01,  1.71it/s]
Train steps ... :  44%|████▍     | 44344/100000 [12:56:42<9:02:50,  1.71it/s]
Train steps ... :  44%|████▍     | 44345/100000 [12:56:43<9:02:28,  1.71it/s]
Train steps ... :  44%|████▍     | 44346/100000 [12:56:43<9:02:53,  1.71it/s]
Train steps ... :  44%|████▍     | 44347/100000 [12:56:44<9:02:40,  1.71it/s]
Train steps ... :  44%|████▍     | 44348/100000 [12:56:44<9:02:52,  1.71it/s]
Train steps ... :  44%|████▍     | 44349/100000 [12:56:45<9:02:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44350/100000 [12:56:46<9:02:59,  1.71it/s]Step... (44350 / 100000 | Loss: 0.887801468372345, Learning Rate: 5.5929648241206034e-05)
+
                                                                             
Step... (44350 / 100000 | Loss: 0.5884763598442078, Learning Rate: 5.5929648241206034e-05)
+
Train steps ... :  44%|████▍     | 44350/100000 [12:56:46<9:02:59,  1.71it/s]
Train steps ... :  44%|████▍     | 44351/100000 [12:56:46<9:03:09,  1.71it/s]
Train steps ... :  44%|████▍     | 44352/100000 [12:56:47<9:02:23,  1.71it/s]
Train steps ... :  44%|████▍     | 44353/100000 [12:56:47<9:03:20,  1.71it/s]
Train steps ... :  44%|████▍     | 44354/100000 [12:56:48<9:02:40,  1.71it/s]
Train steps ... :  44%|████▍     | 44355/100000 [12:56:49<9:03:47,  1.71it/s]
Train steps ... :  44%|████▍     | 44356/100000 [12:56:49<9:03:54,  1.71it/s]
Train steps ... :  44%|████▍     | 44357/100000 [12:56:50<9:03:09,  1.71it/s]
Train steps ... :  44%|████▍     | 44358/100000 [12:56:50<9:03:23,  1.71it/s]
Train steps ... :  44%|████▍     | 44359/100000 [12:56:51<9:03:09,  1.71it/s]
Train steps ... :  44%|████▍     | 44360/100000 [12:56:51<9:03:14,  1.71it/s]
Train steps ... :  44%|████▍     | 44361/100000 [12:56:52<9:03:09,  1.71it/s]
Train steps ... :  44%|████▍     | 44362/100000 [12:56:53<9:02:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44363/100000 [12:56:53<9:02:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44364/100000 [12:56:54<9:02:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44365/100000 [12:56:54<9:02:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44366/100000 [12:56:55<9:02:14,  1.71it/s]
Train steps ... :  44%|████▍     | 44367/100000 [12:56:56<9:02:13,  1.71it/s]
Train steps ... :  44%|████▍     | 44368/100000 [12:56:56<9:01:54,  1.71it/s]
Train steps ... :  44%|████▍     | 44369/100000 [12:56:57<9:01:47,  1.71it/s]
Train steps ... :  44%|████▍     | 44370/100000 [12:56:57<9:02:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44371/100000 [12:56:58<9:03:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44372/100000 [12:56:58<9:02:50,  1.71it/s]
Train steps ... :  44%|████▍     | 44373/100000 [12:56:59<9:03:47,  1.70it/s]
Train steps ... :  44%|████▍     | 44374/100000 [12:57:00<9:02:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44375/100000 [12:57:00<9:02:08,  1.71it/s]Step... (44375 / 100000 | Loss: 0.8013159036636353, Learning Rate: 5.5904522613065324e-05)
+
                                                                             
Step... (44375 / 100000 | Loss: 0.6706590056419373, Learning Rate: 5.5904522613065324e-05)
+
Train steps ... :  44%|████▍     | 44375/100000 [12:57:01<9:02:08,  1.71it/s]
Train steps ... :  44%|████▍     | 44376/100000 [12:57:01<9:01:41,  1.71it/s]
Train steps ... :  44%|████▍     | 44377/100000 [12:57:01<9:02:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44378/100000 [12:57:02<9:02:01,  1.71it/s]
Train steps ... :  44%|████▍     | 44379/100000 [12:57:03<9:02:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44380/100000 [12:57:03<9:02:02,  1.71it/s]
Train steps ... :  44%|████▍     | 44381/100000 [12:57:04<9:01:41,  1.71it/s]
Train steps ... :  44%|████▍     | 44382/100000 [12:57:04<9:01:44,  1.71it/s]
Train steps ... :  44%|████▍     | 44383/100000 [12:57:05<9:01:14,  1.71it/s]
Train steps ... :  44%|████▍     | 44384/100000 [12:57:05<9:01:26,  1.71it/s]
Train steps ... :  44%|████▍     | 44385/100000 [12:57:06<9:01:56,  1.71it/s]
Train steps ... :  44%|████▍     | 44386/100000 [12:57:07<9:02:19,  1.71it/s]
Train steps ... :  44%|████▍     | 44387/100000 [12:57:07<9:01:48,  1.71it/s]
Train steps ... :  44%|████▍     | 44388/100000 [12:57:08<9:01:31,  1.71it/s]
Train steps ... :  44%|████▍     | 44389/100000 [12:57:08<9:01:20,  1.71it/s]
Train steps ... :  44%|████▍     | 44390/100000 [12:57:09<9:01:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44391/100000 [12:57:10<9:01:30,  1.71it/s]
Train steps ... :  44%|████▍     | 44392/100000 [12:57:10<9:02:18,  1.71it/s]
Train steps ... :  44%|████▍     | 44393/100000 [12:57:11<9:02:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44394/100000 [12:57:11<9:01:58,  1.71it/s]
Train steps ... :  44%|████▍     | 44395/100000 [12:57:12<9:01:52,  1.71it/s]
Train steps ... :  44%|████▍     | 44396/100000 [12:57:13<9:02:11,  1.71it/s]
Train steps ... :  44%|████▍     | 44397/100000 [12:57:13<9:01:29,  1.71it/s]
Train steps ... :  44%|████▍     | 44398/100000 [12:57:14<9:01:06,  1.71it/s]
Train steps ... :  44%|████▍     | 44399/100000 [12:57:14<9:00:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44400/100000 [12:57:15<9:01:05,  1.71it/s]Step... (44400 / 100000 | Loss: 0.9391764402389526, Learning Rate: 5.587939698492463e-05)
+
                                                                             
Step... (44400 / 100000 | Loss: 0.9306714534759521, Learning Rate: 5.587939698492463e-05)
+
Train steps ... :  44%|████▍     | 44400/100000 [12:57:15<9:01:05,  1.71it/s]
Train steps ... :  44%|████▍     | 44401/100000 [12:57:15<9:01:22,  1.71it/s]
Train steps ... :  44%|████▍     | 44402/100000 [12:57:16<9:00:55,  1.71it/s]
Train steps ... :  44%|████▍     | 44403/100000 [12:57:17<9:00:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44404/100000 [12:57:17<9:00:28,  1.71it/s]
Train steps ... :  44%|████▍     | 44405/100000 [12:57:18<9:01:23,  1.71it/s]
Train steps ... :  44%|████▍     | 44406/100000 [12:57:18<9:01:41,  1.71it/s]
Train steps ... :  44%|████▍     | 44407/100000 [12:57:19<9:01:29,  1.71it/s]
Train steps ... :  44%|████▍     | 44408/100000 [12:57:20<9:01:16,  1.71it/s]
Train steps ... :  44%|████▍     | 44409/100000 [12:57:20<9:01:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44410/100000 [12:57:21<9:01:42,  1.71it/s]
Train steps ... :  44%|████▍     | 44411/100000 [12:57:21<9:01:43,  1.71it/s]
Train steps ... :  44%|████▍     | 44412/100000 [12:57:22<9:03:37,  1.70it/s]
Train steps ... :  44%|████▍     | 44413/100000 [12:57:22<9:01:39,  1.71it/s]
Train steps ... :  44%|████▍     | 44414/100000 [12:57:23<9:02:23,  1.71it/s]
Train steps ... :  44%|████▍     | 44415/100000 [12:57:24<9:02:02,  1.71it/s]
Train steps ... :  44%|████▍     | 44416/100000 [12:57:24<9:01:53,  1.71it/s]
Train steps ... :  44%|████▍     | 44417/100000 [12:57:25<9:02:25,  1.71it/s]
Train steps ... :  44%|████▍     | 44418/100000 [12:57:25<9:02:31,  1.71it/s]
Train steps ... :  44%|████▍     | 44419/100000 [12:57:26<9:02:57,  1.71it/s]
Train steps ... :  44%|████▍     | 44420/100000 [12:57:27<9:02:28,  1.71it/s]
Train steps ... :  44%|████▍     | 44421/100000 [12:57:27<9:02:20,  1.71it/s]
Train steps ... :  44%|████▍     | 44422/100000 [12:57:28<9:02:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44423/100000 [12:57:28<9:02:21,  1.71it/s]
Train steps ... :  44%|████▍     | 44424/100000 [12:57:29<9:02:07,  1.71it/s]
Train steps ... :  44%|████▍     | 44425/100000 [12:57:29<9:02:48,  1.71it/s]Step... (44425 / 100000 | Loss: 1.0021473169326782, Learning Rate: 5.585427135678393e-05)
+
                                                                             
Step... (44425 / 100000 | Loss: 0.8353023529052734, Learning Rate: 5.585427135678393e-05)
+
Train steps ... :  44%|████▍     | 44425/100000 [12:57:30<9:02:48,  1.71it/s]
Train steps ... :  44%|████▍     | 44426/100000 [12:57:30<9:03:59,  1.70it/s]
Train steps ... :  44%|████▍     | 44427/100000 [12:57:31<9:02:52,  1.71it/s]
Train steps ... :  44%|████▍     | 44428/100000 [12:57:31<9:03:20,  1.70it/s]
Train steps ... :  44%|████▍     | 44429/100000 [12:57:32<9:03:03,  1.71it/s]
Train steps ... :  44%|████▍     | 44430/100000 [12:57:32<9:02:56,  1.71it/s]
Train steps ... :  44%|████▍     | 44431/100000 [12:57:33<9:02:51,  1.71it/s]
Train steps ... :  44%|████▍     | 44432/100000 [12:57:34<9:02:41,  1.71it/s]
Train steps ... :  44%|████▍     | 44433/100000 [12:57:34<9:01:29,  1.71it/s]
Train steps ... :  44%|████▍     | 44434/100000 [12:57:35<9:01:31,  1.71it/s]
Train steps ... :  44%|████▍     | 44435/100000 [12:57:35<9:01:19,  1.71it/s]
Train steps ... :  44%|████▍     | 44436/100000 [12:57:36<9:02:13,  1.71it/s]
Train steps ... :  44%|████▍     | 44437/100000 [12:57:37<9:03:14,  1.70it/s]
Train steps ... :  44%|████▍     | 44438/100000 [12:57:37<9:02:33,  1.71it/s]
Train steps ... :  44%|████▍     | 44439/100000 [12:57:38<9:02:13,  1.71it/s]
Train steps ... :  44%|████▍     | 44440/100000 [12:57:38<9:01:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44441/100000 [12:57:39<9:02:24,  1.71it/s]
Train steps ... :  44%|████▍     | 44442/100000 [12:57:39<9:02:08,  1.71it/s]
Train steps ... :  44%|████▍     | 44443/100000 [12:57:40<9:02:10,  1.71it/s]
Train steps ... :  44%|████▍     | 44444/100000 [12:57:41<9:01:44,  1.71it/s]
Train steps ... :  44%|████▍     | 44445/100000 [12:57:41<9:02:05,  1.71it/s]
Train steps ... :  44%|████▍     | 44446/100000 [12:57:42<9:05:20,  1.70it/s]
Train steps ... :  44%|████▍     | 44447/100000 [12:57:42<9:02:27,  1.71it/s]
Train steps ... :  44%|████▍     | 44448/100000 [12:57:43<9:03:38,  1.70it/s]
Train steps ... :  44%|████▍     | 44449/100000 [12:57:44<9:02:18,  1.71it/s]
Train steps ... :  44%|████▍     | 44450/100000 [12:57:44<9:01:32,  1.71it/s]Step... (44450 / 100000 | Loss: 0.9338620901107788, Learning Rate: 5.582914572864322e-05)
+
                                                                             
Step... (44450 / 100000 | Loss: 0.8409374952316284, Learning Rate: 5.582914572864322e-05)
+
Train steps ... :  44%|████▍     | 44450/100000 [12:57:44<9:01:32,  1.71it/s]
Train steps ... :  44%|████▍     | 44451/100000 [12:57:45<9:02:22,  1.71it/s]
Train steps ... :  44%|████▍     | 44452/100000 [12:57:45<9:02:46,  1.71it/s]
Train steps ... :  44%|████▍     | 44453/100000 [12:57:46<9:01:37,  1.71it/s]
Train steps ... :  44%|████▍     | 44454/100000 [12:57:46<9:01:41,  1.71it/s]
Train steps ... :  44%|████▍     | 44455/100000 [12:57:47<9:01:46,  1.71it/s]
Train steps ... :  44%|████▍     | 44456/100000 [12:57:48<9:01:28,  1.71it/s]
Train steps ... :  44%|████▍     | 44457/100000 [12:57:48<9:02:04,  1.71it/s]
Train steps ... :  44%|████▍     | 44458/100000 [12:57:49<9:01:40,  1.71it/s]
Train steps ... :  44%|████▍     | 44459/100000 [12:57:49<9:01:29,  1.71it/s]
Train steps ... :  44%|████▍     | 44460/100000 [12:57:50<9:03:13,  1.70it/s]
Train steps ... :  44%|████▍     | 44461/100000 [12:57:51<9:03:15,  1.70it/s]
Train steps ... :  44%|████▍     | 44462/100000 [12:57:51<9:02:05,  1.71it/s]
Train steps ... :  44%|████▍     | 44463/100000 [12:57:52<9:02:10,  1.71it/s]
Train steps ... :  44%|████▍     | 44464/100000 [12:57:52<9:01:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44465/100000 [12:57:53<9:02:18,  1.71it/s]
Train steps ... :  44%|████▍     | 44466/100000 [12:57:53<9:01:36,  1.71it/s]
Train steps ... :  44%|████▍     | 44467/100000 [12:57:54<9:03:03,  1.70it/s]
Train steps ... :  44%|████▍     | 44468/100000 [12:57:55<9:01:11,  1.71it/s]
Train steps ... :  44%|████▍     | 44469/100000 [12:57:55<9:00:57,  1.71it/s]
Train steps ... :  44%|████▍     | 44470/100000 [12:57:56<9:01:01,  1.71it/s]
Train steps ... :  44%|████▍     | 44471/100000 [12:57:56<9:02:17,  1.71it/s]
Train steps ... :  44%|████▍     | 44472/100000 [12:57:57<9:01:29,  1.71it/s]
Train steps ... :  44%|████▍     | 44473/100000 [12:57:58<9:02:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44474/100000 [12:57:58<9:02:51,  1.70it/s]
Train steps ... :  44%|████▍     | 44475/100000 [12:57:59<9:02:42,  1.71it/s]Step... (44475 / 100000 | Loss: 0.6742458343505859, Learning Rate: 5.580402010050252e-05)
+
                                                                             
Step... (44475 / 100000 | Loss: 0.8257051706314087, Learning Rate: 5.580402010050252e-05)
+
Train steps ... :  44%|████▍     | 44475/100000 [12:57:59<9:02:42,  1.71it/s]
Train steps ... :  44%|████▍     | 44476/100000 [12:57:59<9:03:59,  1.70it/s]
Train steps ... :  44%|████▍     | 44477/100000 [12:58:00<9:02:09,  1.71it/s]
Train steps ... :  44%|████▍     | 44478/100000 [12:58:01<9:02:27,  1.71it/s]
Train steps ... :  44%|████▍     | 44479/100000 [12:58:01<9:01:49,  1.71it/s]
Train steps ... :  44%|████▍     | 44480/100000 [12:58:02<9:01:50,  1.71it/s]
Train steps ... :  44%|████▍     | 44481/100000 [12:58:02<9:01:13,  1.71it/s]
Train steps ... :  44%|████▍     | 44482/100000 [12:58:03<9:01:11,  1.71it/s]
Train steps ... :  44%|████▍     | 44483/100000 [12:58:03<9:03:37,  1.70it/s]
Train steps ... :  44%|████▍     | 44484/100000 [12:58:04<9:03:12,  1.70it/s]
Train steps ... :  44%|████▍     | 44485/100000 [12:58:05<9:03:28,  1.70it/s]
Train steps ... :  44%|████▍     | 44486/100000 [12:58:05<9:02:51,  1.70it/s]
Train steps ... :  44%|████▍     | 44487/100000 [12:58:06<9:01:48,  1.71it/s]
Train steps ... :  44%|████▍     | 44488/100000 [12:58:06<9:01:55,  1.71it/s]
Train steps ... :  44%|████▍     | 44489/100000 [12:58:07<9:01:27,  1.71it/s]
Train steps ... :  44%|████▍     | 44490/100000 [12:58:08<9:00:51,  1.71it/s]
Train steps ... :  44%|████▍     | 44491/100000 [12:58:08<9:01:45,  1.71it/s]
Train steps ... :  44%|████▍     | 44492/100000 [12:58:09<9:00:38,  1.71it/s]
Train steps ... :  44%|████▍     | 44493/100000 [12:58:09<9:01:39,  1.71it/s]
Train steps ... :  44%|████▍     | 44494/100000 [12:58:10<9:02:18,  1.71it/s]
Train steps ... :  44%|████▍     | 44495/100000 [12:58:10<9:02:51,  1.70it/s]
Train steps ... :  44%|████▍     | 44496/100000 [12:58:11<9:00:48,  1.71it/s]
Train steps ... :  44%|████▍     | 44497/100000 [12:58:12<9:02:04,  1.71it/s]
Train steps ... :  44%|████▍     | 44498/100000 [12:58:12<9:01:22,  1.71it/s]
Train steps ... :  44%|████▍     | 44499/100000 [12:58:13<9:02:20,  1.71it/s]
Train steps ... :  44%|████▍     | 44500/100000 [12:58:13<9:01:28,  1.71it/s]Step... (44500 / 100000 | Loss: 0.8689203262329102, Learning Rate: 5.577889447236181e-05)
+
                                                                             
Step... (44500 / 100000 | Loss: 0.860695481300354, Learning Rate: 5.577889447236181e-05)
+
Train steps ... :  44%|████▍     | 44500/100000 [12:58:14<9:01:28,  1.71it/s]
Train steps ... :  45%|████▍     | 44501/100000 [12:58:14<9:02:47,  1.70it/s]
Train steps ... :  45%|████▍     | 44502/100000 [12:58:15<9:02:25,  1.71it/s]
Train steps ... :  45%|████▍     | 44503/100000 [12:58:15<9:03:07,  1.70it/s]
Train steps ... :  45%|████▍     | 44504/100000 [12:58:16<9:01:41,  1.71it/s]
Train steps ... :  45%|████▍     | 44505/100000 [12:58:16<9:02:04,  1.71it/s]
Train steps ... :  45%|████▍     | 44506/100000 [12:58:17<9:02:05,  1.71it/s]
Train steps ... :  45%|████▍     | 44507/100000 [12:58:18<9:03:02,  1.70it/s]
Train steps ... :  45%|████▍     | 44508/100000 [12:58:18<9:00:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44509/100000 [12:58:19<9:01:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44510/100000 [12:58:19<9:01:22,  1.71it/s]
Train steps ... :  45%|████▍     | 44511/100000 [12:58:20<9:01:56,  1.71it/s]
Train steps ... :  45%|████▍     | 44512/100000 [12:58:20<9:01:17,  1.71it/s]
Train steps ... :  45%|████▍     | 44513/100000 [12:58:21<9:01:13,  1.71it/s]
Train steps ... :  45%|████▍     | 44514/100000 [12:58:22<9:01:16,  1.71it/s]
Train steps ... :  45%|████▍     | 44515/100000 [12:58:22<9:00:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44516/100000 [12:58:23<9:01:53,  1.71it/s]
Train steps ... :  45%|████▍     | 44517/100000 [12:58:23<9:01:24,  1.71it/s]
Train steps ... :  45%|████▍     | 44518/100000 [12:58:24<9:01:20,  1.71it/s]
Train steps ... :  45%|████▍     | 44519/100000 [12:58:25<9:01:28,  1.71it/s]
Train steps ... :  45%|████▍     | 44520/100000 [12:58:25<9:01:19,  1.71it/s]
Train steps ... :  45%|████▍     | 44521/100000 [12:58:26<9:00:33,  1.71it/s]
Train steps ... :  45%|████▍     | 44522/100000 [12:58:26<9:00:46,  1.71it/s]
Train steps ... :  45%|████▍     | 44523/100000 [12:58:27<9:00:22,  1.71it/s]
Train steps ... :  45%|████▍     | 44524/100000 [12:58:27<9:00:49,  1.71it/s]
Train steps ... :  45%|████▍     | 44525/100000 [12:58:28<9:00:38,  1.71it/s]Step... (44525 / 100000 | Loss: 0.849963903427124, Learning Rate: 5.575376884422111e-05)
+
                                                                             
Step... (44525 / 100000 | Loss: 0.9853502511978149, Learning Rate: 5.575376884422111e-05)
+
Train steps ... :  45%|████▍     | 44525/100000 [12:58:28<9:00:38,  1.71it/s]
Train steps ... :  45%|████▍     | 44526/100000 [12:58:29<9:00:48,  1.71it/s]
Train steps ... :  45%|████▍     | 44527/100000 [12:58:29<9:01:36,  1.71it/s]
Train steps ... :  45%|████▍     | 44528/100000 [12:58:30<9:01:02,  1.71it/s]
Train steps ... :  45%|████▍     | 44529/100000 [12:58:30<9:01:03,  1.71it/s]
Train steps ... :  45%|████▍     | 44530/100000 [12:58:31<9:00:35,  1.71it/s]
Train steps ... :  45%|████▍     | 44531/100000 [12:58:32<9:00:39,  1.71it/s]
Train steps ... :  45%|████▍     | 44532/100000 [12:58:32<9:01:48,  1.71it/s]
Train steps ... :  45%|████▍     | 44533/100000 [12:58:33<9:00:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44534/100000 [12:58:33<9:01:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44535/100000 [12:58:34<9:01:05,  1.71it/s]
Train steps ... :  45%|████▍     | 44536/100000 [12:58:34<9:00:43,  1.71it/s]
Train steps ... :  45%|████▍     | 44537/100000 [12:58:35<9:01:14,  1.71it/s]
Train steps ... :  45%|████▍     | 44538/100000 [12:58:36<9:00:35,  1.71it/s]
Train steps ... :  45%|████▍     | 44539/100000 [12:58:36<9:01:12,  1.71it/s]
Train steps ... :  45%|████▍     | 44540/100000 [12:58:37<9:01:28,  1.71it/s]
Train steps ... :  45%|████▍     | 44541/100000 [12:58:37<9:02:12,  1.70it/s]
Train steps ... :  45%|████▍     | 44542/100000 [12:58:38<9:01:34,  1.71it/s]
Train steps ... :  45%|████▍     | 44543/100000 [12:58:39<9:01:18,  1.71it/s]
Train steps ... :  45%|████▍     | 44544/100000 [12:58:39<9:01:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44545/100000 [12:58:40<9:02:16,  1.70it/s]
Train steps ... :  45%|████▍     | 44546/100000 [12:58:40<9:01:29,  1.71it/s]
Train steps ... :  45%|████▍     | 44547/100000 [12:58:41<9:02:42,  1.70it/s]
Train steps ... :  45%|████▍     | 44548/100000 [12:58:42<9:01:33,  1.71it/s]
Train steps ... :  45%|████▍     | 44549/100000 [12:58:42<9:03:16,  1.70it/s]
Train steps ... :  45%|████▍     | 44550/100000 [12:58:43<9:02:54,  1.70it/s]Step... (44550 / 100000 | Loss: 0.624306321144104, Learning Rate: 5.57286432160804e-05)
+
                                                                             
Step... (44550 / 100000 | Loss: 0.9421085119247437, Learning Rate: 5.57286432160804e-05)
+
Train steps ... :  45%|████▍     | 44550/100000 [12:58:43<9:02:54,  1.70it/s]
Train steps ... :  45%|████▍     | 44551/100000 [12:58:43<9:02:01,  1.70it/s]
Train steps ... :  45%|████▍     | 44552/100000 [12:58:44<9:01:42,  1.71it/s]
Train steps ... :  45%|████▍     | 44553/100000 [12:58:44<9:02:10,  1.70it/s]
Train steps ... :  45%|████▍     | 44554/100000 [12:58:45<9:01:14,  1.71it/s]
Train steps ... :  45%|████▍     | 44555/100000 [12:58:46<9:00:41,  1.71it/s]
Train steps ... :  45%|████▍     | 44556/100000 [12:58:46<9:01:15,  1.71it/s]
Train steps ... :  45%|████▍     | 44557/100000 [12:58:47<9:00:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44558/100000 [12:58:47<8:59:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44559/100000 [12:58:48<9:00:43,  1.71it/s]
Train steps ... :  45%|████▍     | 44560/100000 [12:58:49<9:00:45,  1.71it/s]
Train steps ... :  45%|████▍     | 44561/100000 [12:58:49<9:01:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44562/100000 [12:58:50<9:00:40,  1.71it/s]
Train steps ... :  45%|████▍     | 44563/100000 [12:58:50<9:01:28,  1.71it/s]
Train steps ... :  45%|████▍     | 44564/100000 [12:58:51<9:00:22,  1.71it/s]
Train steps ... :  45%|████▍     | 44565/100000 [12:58:51<9:00:39,  1.71it/s]
Train steps ... :  45%|████▍     | 44566/100000 [12:58:52<9:01:06,  1.71it/s]
Train steps ... :  45%|████▍     | 44567/100000 [12:58:53<9:00:34,  1.71it/s]
Train steps ... :  45%|████▍     | 44568/100000 [12:58:53<8:59:41,  1.71it/s]
Train steps ... :  45%|████▍     | 44569/100000 [12:58:54<9:00:31,  1.71it/s]
Train steps ... :  45%|████▍     | 44570/100000 [12:58:54<9:00:32,  1.71it/s]
Train steps ... :  45%|████▍     | 44571/100000 [12:58:55<9:00:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44572/100000 [12:58:56<9:01:27,  1.71it/s]
Train steps ... :  45%|████▍     | 44573/100000 [12:58:56<9:01:18,  1.71it/s]
Train steps ... :  45%|████▍     | 44574/100000 [12:58:57<9:01:18,  1.71it/s]
Train steps ... :  45%|████▍     | 44575/100000 [12:58:57<9:02:07,  1.70it/s]Step... (44575 / 100000 | Loss: 0.7279694676399231, Learning Rate: 5.57035175879397e-05)
+
                                                                             
Step... (44575 / 100000 | Loss: 0.7697399258613586, Learning Rate: 5.57035175879397e-05)
+
Train steps ... :  45%|████▍     | 44575/100000 [12:58:58<9:02:07,  1.70it/s]
Train steps ... :  45%|████▍     | 44576/100000 [12:58:58<9:01:42,  1.71it/s]
Train steps ... :  45%|████▍     | 44577/100000 [12:58:59<9:03:26,  1.70it/s]
Train steps ... :  45%|████▍     | 44578/100000 [12:58:59<9:02:17,  1.70it/s]
Train steps ... :  45%|████▍     | 44579/100000 [12:59:00<9:00:49,  1.71it/s]
Train steps ... :  45%|████▍     | 44580/100000 [12:59:00<9:02:10,  1.70it/s]
Train steps ... :  45%|████▍     | 44581/100000 [12:59:01<9:01:13,  1.71it/s]
Train steps ... :  45%|████▍     | 44582/100000 [12:59:01<9:01:30,  1.71it/s]
Train steps ... :  45%|████▍     | 44583/100000 [12:59:02<9:01:58,  1.70it/s]
Train steps ... :  45%|████▍     | 44584/100000 [12:59:03<9:00:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44585/100000 [12:59:03<9:01:18,  1.71it/s]
Train steps ... :  45%|████▍     | 44586/100000 [12:59:04<9:01:05,  1.71it/s]
Train steps ... :  45%|████▍     | 44587/100000 [12:59:04<9:01:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44588/100000 [12:59:05<9:00:28,  1.71it/s]
Train steps ... :  45%|████▍     | 44589/100000 [12:59:06<9:00:44,  1.71it/s]
Train steps ... :  45%|████▍     | 44590/100000 [12:59:06<9:00:10,  1.71it/s]
Train steps ... :  45%|████▍     | 44591/100000 [12:59:07<9:00:00,  1.71it/s]
Train steps ... :  45%|████▍     | 44592/100000 [12:59:07<8:59:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44593/100000 [12:59:08<8:59:41,  1.71it/s]
Train steps ... :  45%|████▍     | 44594/100000 [12:59:08<9:00:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44595/100000 [12:59:09<8:59:25,  1.71it/s]
Train steps ... :  45%|████▍     | 44596/100000 [12:59:10<8:59:19,  1.71it/s]
Train steps ... :  45%|████▍     | 44597/100000 [12:59:10<8:59:56,  1.71it/s]
Train steps ... :  45%|████▍     | 44598/100000 [12:59:11<8:59:44,  1.71it/s]
Train steps ... :  45%|████▍     | 44599/100000 [12:59:11<9:00:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44600/100000 [12:59:12<9:01:16,  1.71it/s]Step... (44600 / 100000 | Loss: 0.8174381256103516, Learning Rate: 5.567839195979899e-05)
+
                                                                             
Step... (44600 / 100000 | Loss: 0.7952039241790771, Learning Rate: 5.567839195979899e-05)
+
Train steps ... :  45%|████▍     | 44600/100000 [12:59:12<9:01:16,  1.71it/s]
Train steps ... :  45%|████▍     | 44601/100000 [12:59:13<9:00:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44602/100000 [12:59:13<9:00:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44603/100000 [12:59:14<9:00:21,  1.71it/s]
Train steps ... :  45%|████▍     | 44604/100000 [12:59:14<9:01:40,  1.70it/s]
Train steps ... :  45%|████▍     | 44605/100000 [12:59:15<9:00:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44606/100000 [12:59:15<8:59:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44607/100000 [12:59:16<9:00:25,  1.71it/s]
Train steps ... :  45%|████▍     | 44608/100000 [12:59:17<9:00:17,  1.71it/s]
Train steps ... :  45%|████▍     | 44609/100000 [12:59:17<9:00:13,  1.71it/s]
Train steps ... :  45%|████▍     | 44610/100000 [12:59:18<9:01:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44611/100000 [12:59:18<8:59:54,  1.71it/s]
Train steps ... :  45%|████▍     | 44612/100000 [12:59:19<9:00:54,  1.71it/s]
Train steps ... :  45%|████▍     | 44613/100000 [12:59:20<9:01:11,  1.71it/s]
Train steps ... :  45%|████▍     | 44614/100000 [12:59:20<9:00:32,  1.71it/s]
Train steps ... :  45%|████▍     | 44615/100000 [12:59:21<9:00:38,  1.71it/s]
Train steps ... :  45%|████▍     | 44616/100000 [12:59:21<9:00:46,  1.71it/s]
Train steps ... :  45%|████▍     | 44617/100000 [12:59:22<9:01:51,  1.70it/s]
Train steps ... :  45%|████▍     | 44618/100000 [12:59:23<8:59:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44619/100000 [12:59:23<8:59:04,  1.71it/s]
Train steps ... :  45%|████▍     | 44620/100000 [12:59:24<8:59:10,  1.71it/s]
Train steps ... :  45%|████▍     | 44621/100000 [12:59:24<8:59:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44622/100000 [12:59:25<8:59:08,  1.71it/s]
Train steps ... :  45%|████▍     | 44623/100000 [12:59:25<9:00:09,  1.71it/s]
Train steps ... :  45%|████▍     | 44624/100000 [12:59:26<8:59:40,  1.71it/s]
Train steps ... :  45%|████▍     | 44625/100000 [12:59:27<9:00:29,  1.71it/s]Step... (44625 / 100000 | Loss: 0.7691570520401001, Learning Rate: 5.5653266331658297e-05)
+
                                                                             
Step... (44625 / 100000 | Loss: 0.981826663017273, Learning Rate: 5.5653266331658297e-05)
+
Train steps ... :  45%|████���     | 44625/100000 [12:59:27<9:00:29,  1.71it/s]
Train steps ... :  45%|████▍     | 44626/100000 [12:59:27<8:59:42,  1.71it/s]
Train steps ... :  45%|████▍     | 44627/100000 [12:59:28<8:59:21,  1.71it/s]
Train steps ... :  45%|████▍     | 44628/100000 [12:59:28<8:59:40,  1.71it/s]
Train steps ... :  45%|████▍     | 44629/100000 [12:59:29<9:01:06,  1.71it/s]
Train steps ... :  45%|████▍     | 44630/100000 [12:59:30<9:00:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44631/100000 [12:59:30<9:00:21,  1.71it/s]
Train steps ... :  45%|████▍     | 44632/100000 [12:59:31<9:00:21,  1.71it/s]
Train steps ... :  45%|████▍     | 44633/100000 [12:59:31<9:00:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44634/100000 [12:59:32<9:00:39,  1.71it/s]
Train steps ... :  45%|████▍     | 44635/100000 [12:59:32<9:01:44,  1.70it/s]
Train steps ... :  45%|████▍     | 44636/100000 [12:59:33<9:01:21,  1.70it/s]
Train steps ... :  45%|████▍     | 44637/100000 [12:59:34<9:01:24,  1.70it/s]
Train steps ... :  45%|████▍     | 44638/100000 [12:59:34<9:00:55,  1.71it/s]
Train steps ... :  45%|████▍     | 44639/100000 [12:59:35<9:00:29,  1.71it/s]
Train steps ... :  45%|████▍     | 44640/100000 [12:59:35<9:00:45,  1.71it/s]
Train steps ... :  45%|████▍     | 44641/100000 [12:59:36<9:01:32,  1.70it/s]
Train steps ... :  45%|████▍     | 44642/100000 [12:59:37<9:00:49,  1.71it/s]
Train steps ... :  45%|████▍     | 44643/100000 [12:59:37<9:01:27,  1.70it/s]
Train steps ... :  45%|████▍     | 44644/100000 [12:59:38<9:00:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44645/100000 [12:59:38<9:01:24,  1.70it/s]
Train steps ... :  45%|████▍     | 44646/100000 [12:59:39<9:00:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44647/100000 [12:59:40<9:01:08,  1.70it/s]
Train steps ... :  45%|████▍     | 44648/100000 [12:59:40<9:00:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44649/100000 [12:59:41<9:00:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44650/100000 [12:59:41<9:00:10,  1.71it/s]Step... (44650 / 100000 | Loss: 0.8899074196815491, Learning Rate: 5.562814070351759e-05)
+
                                                                             
Step... (44650 / 100000 | Loss: 0.7842229008674622, Learning Rate: 5.562814070351759e-05)
+
Train steps ... :  45%|████▍     | 44650/100000 [12:59:42<9:00:10,  1.71it/s]
Train steps ... :  45%|████▍     | 44651/100000 [12:59:42<8:59:27,  1.71it/s]
Train steps ... :  45%|████▍     | 44652/100000 [12:59:42<9:00:12,  1.71it/s]
Train steps ... :  45%|████▍     | 44653/100000 [12:59:43<9:00:56,  1.71it/s]
Train steps ... :  45%|████▍     | 44654/100000 [12:59:44<9:01:17,  1.70it/s]
Train steps ... :  45%|████▍     | 44655/100000 [12:59:44<9:01:15,  1.70it/s]
Train steps ... :  45%|████▍     | 44656/100000 [12:59:45<9:00:16,  1.71it/s]
Train steps ... :  45%|████▍     | 44657/100000 [12:59:45<8:59:42,  1.71it/s]
Train steps ... :  45%|████▍     | 44658/100000 [12:59:46<8:59:24,  1.71it/s]
Train steps ... :  45%|████▍     | 44659/100000 [12:59:47<8:59:10,  1.71it/s]
Train steps ... :  45%|████▍     | 44660/100000 [12:59:47<8:59:36,  1.71it/s]
Train steps ... :  45%|████▍     | 44661/100000 [12:59:48<8:59:42,  1.71it/s]
Train steps ... :  45%|████▍     | 44662/100000 [12:59:48<8:59:28,  1.71it/s]
Train steps ... :  45%|████▍     | 44663/100000 [12:59:49<8:59:02,  1.71it/s]
Train steps ... :  45%|████▍     | 44664/100000 [12:59:49<8:58:55,  1.71it/s]
Train steps ... :  45%|████▍     | 44665/100000 [12:59:50<8:59:03,  1.71it/s]
Train steps ... :  45%|████▍     | 44666/100000 [12:59:51<9:00:32,  1.71it/s]
Train steps ... :  45%|████▍     | 44667/100000 [12:59:51<9:01:10,  1.70it/s]
Train steps ... :  45%|████▍     | 44668/100000 [12:59:52<8:59:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44669/100000 [12:59:52<8:59:11,  1.71it/s]
Train steps ... :  45%|████▍     | 44670/100000 [12:59:53<8:59:04,  1.71it/s]
Train steps ... :  45%|████▍     | 44671/100000 [12:59:54<8:58:35,  1.71it/s]
Train steps ... :  45%|████▍     | 44672/100000 [12:59:54<8:58:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44673/100000 [12:59:55<9:00:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44674/100000 [12:59:55<8:59:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44675/100000 [12:59:56<8:59:33,  1.71it/s]Step... (44675 / 100000 | Loss: 0.8129656314849854, Learning Rate: 5.560301507537688e-05)
+
                                                                             
Step... (44675 / 100000 | Loss: 0.9433708190917969, Learning Rate: 5.560301507537688e-05)
+
Train steps ... :  45%|████▍     | 44675/100000 [12:59:56<8:59:33,  1.71it/s]
Train steps ... :  45%|████▍     | 44676/100000 [12:59:56<8:59:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44677/100000 [12:59:57<9:00:00,  1.71it/s]
Train steps ... :  45%|████▍     | 44678/100000 [12:59:58<9:00:03,  1.71it/s]
Train steps ... :  45%|████▍     | 44679/100000 [12:59:58<9:00:15,  1.71it/s]
Train steps ... :  45%|████▍     | 44680/100000 [12:59:59<8:58:55,  1.71it/s]
Train steps ... :  45%|████▍     | 44681/100000 [12:59:59<8:59:35,  1.71it/s]
Train steps ... :  45%|████▍     | 44682/100000 [13:00:00<8:59:55,  1.71it/s]
Train steps ... :  45%|████▍     | 44683/100000 [13:00:01<8:59:30,  1.71it/s]
Train steps ... :  45%|████▍     | 44684/100000 [13:00:01<8:59:32,  1.71it/s]
Train steps ... :  45%|████▍     | 44685/100000 [13:00:02<9:00:05,  1.71it/s]
Train steps ... :  45%|████▍     | 44686/100000 [13:00:02<8:59:46,  1.71it/s]
Train steps ... :  45%|████▍     | 44687/100000 [13:00:03<8:59:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44688/100000 [13:00:04<9:00:14,  1.71it/s]
Train steps ... :  45%|████▍     | 44689/100000 [13:00:04<8:59:40,  1.71it/s]
Train steps ... :  45%|████▍     | 44690/100000 [13:00:05<9:00:35,  1.71it/s]
Train steps ... :  45%|████▍     | 44691/100000 [13:00:05<8:59:21,  1.71it/s]
Train steps ... :  45%|████▍     | 44692/100000 [13:00:06<9:00:40,  1.70it/s]
Train steps ... :  45%|████▍     | 44693/100000 [13:00:06<9:00:25,  1.71it/s]
Train steps ... :  45%|████▍     | 44694/100000 [13:00:07<9:01:11,  1.70it/s]
Train steps ... :  45%|████▍     | 44695/100000 [13:00:08<9:00:20,  1.71it/s]
Train steps ... :  45%|████▍     | 44696/100000 [13:00:08<9:00:42,  1.70it/s]
Train steps ... :  45%|████▍     | 44697/100000 [13:00:09<9:00:49,  1.70it/s]
Train steps ... :  45%|████▍     | 44698/100000 [13:00:09<9:01:00,  1.70it/s]
Train steps ... :  45%|████▍     | 44699/100000 [13:00:10<9:01:04,  1.70it/s]
Train steps ... :  45%|████▍     | 44700/100000 [13:00:11<8:59:53,  1.71it/s]Step... (44700 / 100000 | Loss: 0.7133219242095947, Learning Rate: 5.5577889447236186e-05)
+
                                                                             
Step... (44700 / 100000 | Loss: 0.9123474359512329, Learning Rate: 5.5577889447236186e-05)
+
Train steps ... :  45%|████▍     | 44700/100000 [13:00:11<8:59:53,  1.71it/s]
Train steps ... :  45%|████▍     | 44701/100000 [13:00:11<9:00:31,  1.71it/s]
Train steps ... :  45%|████▍     | 44702/100000 [13:00:12<8:59:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44703/100000 [13:00:12<9:00:02,  1.71it/s]
Train steps ... :  45%|████▍     | 44704/100000 [13:00:13<8:59:20,  1.71it/s]
Train steps ... :  45%|████▍     | 44705/100000 [13:00:13<9:00:45,  1.70it/s]
Train steps ... :  45%|████▍     | 44706/100000 [13:00:14<8:59:09,  1.71it/s]
Train steps ... :  45%|████▍     | 44707/100000 [13:00:15<8:59:06,  1.71it/s]
Train steps ... :  45%|████▍     | 44708/100000 [13:00:15<8:59:42,  1.71it/s]
Train steps ... :  45%|████▍     | 44709/100000 [13:00:16<9:01:02,  1.70it/s]
Train steps ... :  45%|████▍     | 44710/100000 [13:00:16<8:59:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44711/100000 [13:00:17<8:59:54,  1.71it/s]
Train steps ... :  45%|████▍     | 44712/100000 [13:00:18<8:59:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44713/100000 [13:00:18<9:00:41,  1.70it/s]
Train steps ... :  45%|████▍     | 44714/100000 [13:00:19<8:59:44,  1.71it/s]
Train steps ... :  45%|████▍     | 44715/100000 [13:00:19<8:59:53,  1.71it/s]
Train steps ... :  45%|████▍     | 44716/100000 [13:00:20<9:00:45,  1.70it/s]
Train steps ... :  45%|████▍     | 44717/100000 [13:00:20<8:59:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44718/100000 [13:00:21<9:00:38,  1.70it/s]
Train steps ... :  45%|████▍     | 44719/100000 [13:00:22<9:01:14,  1.70it/s]
Train steps ... :  45%|████▍     | 44720/100000 [13:00:22<8:59:06,  1.71it/s]
Train steps ... :  45%|████▍     | 44721/100000 [13:00:23<8:59:40,  1.71it/s]
Train steps ... :  45%|████▍     | 44722/100000 [13:00:23<8:59:29,  1.71it/s]
Train steps ... :  45%|████▍     | 44723/100000 [13:00:24<8:58:32,  1.71it/s]
Train steps ... :  45%|████▍     | 44724/100000 [13:00:25<8:59:04,  1.71it/s]
Train steps ... :  45%|████▍     | 44725/100000 [13:00:25<8:58:49,  1.71it/s]Step... (44725 / 100000 | Loss: 0.9643567204475403, Learning Rate: 5.5552763819095476e-05)
+
                                                                             
Step... (44725 / 100000 | Loss: 0.8847037553787231, Learning Rate: 5.5552763819095476e-05)
+
Train steps ... :  45%|████▍     | 44725/100000 [13:00:26<8:58:49,  1.71it/s]
Train steps ... :  45%|████▍     | 44726/100000 [13:00:26<8:58:43,  1.71it/s]
Train steps ... :  45%|████▍     | 44727/100000 [13:00:26<8:59:13,  1.71it/s]
Train steps ... :  45%|████▍     | 44728/100000 [13:00:27<9:00:32,  1.70it/s]
Train steps ... :  45%|████▍     | 44729/100000 [13:00:28<8:59:18,  1.71it/s]
Train steps ... :  45%|████▍     | 44730/100000 [13:00:28<8:59:02,  1.71it/s]
Train steps ... :  45%|████▍     | 44731/100000 [13:00:29<8:59:39,  1.71it/s]
Train steps ... :  45%|████▍     | 44732/100000 [13:00:29<8:59:05,  1.71it/s]
Train steps ... :  45%|████▍     | 44733/100000 [13:00:30<8:59:31,  1.71it/s]
Train steps ... :  45%|████▍     | 44734/100000 [13:00:30<8:58:56,  1.71it/s]
Train steps ... :  45%|████▍     | 44735/100000 [13:00:31<9:01:18,  1.70it/s]
Train steps ... :  45%|████▍     | 44736/100000 [13:00:32<9:01:36,  1.70it/s]
Train steps ... :  45%|████▍     | 44737/100000 [13:00:32<9:00:41,  1.70it/s]
Train steps ... :  45%|████▍     | 44738/100000 [13:00:33<9:01:37,  1.70it/s]
Train steps ... :  45%|████▍     | 44739/100000 [13:00:33<9:01:45,  1.70it/s]
Train steps ... :  45%|████▍     | 44740/100000 [13:00:34<9:00:36,  1.70it/s]
Train steps ... :  45%|████▍     | 44741/100000 [13:00:35<8:59:35,  1.71it/s]
Train steps ... :  45%|████▍     | 44742/100000 [13:00:35<9:00:50,  1.70it/s]
Train steps ... :  45%|████▍     | 44743/100000 [13:00:36<8:59:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44744/100000 [13:00:36<9:00:30,  1.70it/s]
Train steps ... :  45%|████▍     | 44745/100000 [13:00:37<8:58:39,  1.71it/s]
Train steps ... :  45%|████▍     | 44746/100000 [13:00:37<8:59:55,  1.71it/s]
Train steps ... :  45%|████▍     | 44747/100000 [13:00:38<8:59:13,  1.71it/s]
Train steps ... :  45%|████▍     | 44748/100000 [13:00:39<8:58:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44749/100000 [13:00:39<8:59:06,  1.71it/s]
Train steps ... :  45%|████▍     | 44750/100000 [13:00:40<8:58:43,  1.71it/s]Step... (44750 / 100000 | Loss: 0.9413532018661499, Learning Rate: 5.552763819095478e-05)
+
                                                                             
Step... (44750 / 100000 | Loss: 0.8997447490692139, Learning Rate: 5.552763819095478e-05)
+
Train steps ... :  45%|████▍     | 44750/100000 [13:00:40<8:58:43,  1.71it/s]
Train steps ... :  45%|████▍     | 44751/100000 [13:00:40<8:59:43,  1.71it/s]
Train steps ... :  45%|████▍     | 44752/100000 [13:00:41<8:58:38,  1.71it/s]
Train steps ... :  45%|████▍     | 44753/100000 [13:00:42<8:59:45,  1.71it/s]
Train steps ... :  45%|████▍     | 44754/100000 [13:00:42<8:59:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44755/100000 [13:00:43<8:59:45,  1.71it/s]
Train steps ... :  45%|████▍     | 44756/100000 [13:00:43<8:58:57,  1.71it/s]
Train steps ... :  45%|████▍     | 44757/100000 [13:00:44<8:59:16,  1.71it/s]
Train steps ... :  45%|████▍     | 44758/100000 [13:00:45<8:58:30,  1.71it/s]
Train steps ... :  45%|████▍     | 44759/100000 [13:00:45<8:58:36,  1.71it/s]
Train steps ... :  45%|████▍     | 44760/100000 [13:00:46<8:58:03,  1.71it/s]
Train steps ... :  45%|████▍     | 44761/100000 [13:00:46<8:58:38,  1.71it/s]
Train steps ... :  45%|████▍     | 44762/100000 [13:00:47<8:58:45,  1.71it/s]
Train steps ... :  45%|████▍     | 44763/100000 [13:00:47<8:59:21,  1.71it/s]
Train steps ... :  45%|████▍     | 44764/100000 [13:00:48<8:58:24,  1.71it/s]
Train steps ... :  45%|████▍     | 44765/100000 [13:00:49<8:58:46,  1.71it/s]
Train steps ... :  45%|████▍     | 44766/100000 [13:00:49<8:58:34,  1.71it/s]
Train steps ... :  45%|████▍     | 44767/100000 [13:00:50<8:58:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44768/100000 [13:00:50<8:58:21,  1.71it/s]
Train steps ... :  45%|████▍     | 44769/100000 [13:00:51<8:58:06,  1.71it/s]
Train steps ... :  45%|████▍     | 44770/100000 [13:00:52<8:58:24,  1.71it/s]
Train steps ... :  45%|████▍     | 44771/100000 [13:00:52<8:57:59,  1.71it/s]
Train steps ... :  45%|████▍     | 44772/100000 [13:00:53<8:57:44,  1.71it/s]
Train steps ... :  45%|████▍     | 44773/100000 [13:00:53<8:58:04,  1.71it/s]
Train steps ... :  45%|████▍     | 44774/100000 [13:00:54<8:58:00,  1.71it/s]
Train steps ... :  45%|████▍     | 44775/100000 [13:00:54<8:58:58,  1.71it/s]Step... (44775 / 100000 | Loss: 0.8636355400085449, Learning Rate: 5.550251256281407e-05)
+
                                                                             
Step... (44775 / 100000 | Loss: 0.7253701686859131, Learning Rate: 5.550251256281407e-05)
+
Train steps ... :  45%|████▍     | 44775/100000 [13:00:55<8:58:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44776/100000 [13:00:55<8:59:38,  1.71it/s]
Train steps ... :  45%|████▍     | 44777/100000 [13:00:56<8:59:12,  1.71it/s]
Train steps ... :  45%|████▍     | 44778/100000 [13:00:56<8:58:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44779/100000 [13:00:57<8:59:11,  1.71it/s]
Train steps ... :  45%|████▍     | 44780/100000 [13:00:57<8:58:28,  1.71it/s]
Train steps ... :  45%|████▍     | 44781/100000 [13:00:58<8:58:08,  1.71it/s]
Train steps ... :  45%|████▍     | 44782/100000 [13:00:59<9:00:18,  1.70it/s]
Train steps ... :  45%|████▍     | 44783/100000 [13:00:59<8:58:53,  1.71it/s]
Train steps ... :  45%|████▍     | 44784/100000 [13:01:00<8:58:48,  1.71it/s]
Train steps ... :  45%|████▍     | 44785/100000 [13:01:00<8:59:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44786/100000 [13:01:01<8:57:55,  1.71it/s]
Train steps ... :  45%|████▍     | 44787/100000 [13:01:02<9:00:54,  1.70it/s]
Train steps ... :  45%|████▍     | 44788/100000 [13:01:02<9:00:24,  1.70it/s]
Train steps ... :  45%|████▍     | 44789/100000 [13:01:03<8:58:51,  1.71it/s]
Train steps ... :  45%|████▍     | 44790/100000 [13:01:03<8:59:58,  1.70it/s]
Train steps ... :  45%|████▍     | 44791/100000 [13:01:04<8:58:39,  1.71it/s]
Train steps ... :  45%|████▍     | 44792/100000 [13:01:04<8:59:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44793/100000 [13:01:05<8:59:07,  1.71it/s]
Train steps ... :  45%|████▍     | 44794/100000 [13:01:06<8:59:21,  1.71it/s]
Train steps ... :  45%|████▍     | 44795/100000 [13:01:06<8:59:40,  1.70it/s]
Train steps ... :  45%|████▍     | 44796/100000 [13:01:07<8:59:18,  1.71it/s]
Train steps ... :  45%|████▍     | 44797/100000 [13:01:07<8:58:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44798/100000 [13:01:08<8:58:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44799/100000 [13:01:09<8:57:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44800/100000 [13:01:09<8:57:58,  1.71it/s]Step... (44800 / 100000 | Loss: 1.3309566974639893, Learning Rate: 5.547738693467337e-05)
+
                                                                             
Step... (44800 / 100000 | Loss: 0.8225032687187195, Learning Rate: 5.547738693467337e-05)
+
Train steps ... :  45%|████▍     | 44800/100000 [13:01:09<8:57:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44801/100000 [13:01:10<8:57:53,  1.71it/s]
Train steps ... :  45%|████▍     | 44802/100000 [13:01:10<8:58:15,  1.71it/s]
Train steps ... :  45%|████▍     | 44803/100000 [13:01:11<8:57:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44804/100000 [13:01:11<8:58:00,  1.71it/s]
Train steps ... :  45%|████▍     | 44805/100000 [13:01:12<8:59:43,  1.70it/s]
Train steps ... :  45%|████▍     | 44806/100000 [13:01:13<8:59:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44807/100000 [13:01:13<9:00:27,  1.70it/s]
Train steps ... :  45%|████▍     | 44808/100000 [13:01:14<8:59:05,  1.71it/s]
Train steps ... :  45%|████▍     | 44809/100000 [13:01:14<9:00:39,  1.70it/s]
Train steps ... :  45%|████▍     | 44810/100000 [13:01:15<9:00:28,  1.70it/s]
Train steps ... :  45%|████▍     | 44811/100000 [13:01:16<9:01:29,  1.70it/s]
Train steps ... :  45%|████▍     | 44812/100000 [13:01:16<9:00:53,  1.70it/s]
Train steps ... :  45%|████▍     | 44813/100000 [13:01:17<9:00:34,  1.70it/s]
Train steps ... :  45%|████▍     | 44814/100000 [13:01:17<8:58:46,  1.71it/s]
Train steps ... :  45%|████▍     | 44815/100000 [13:01:18<8:59:13,  1.71it/s]
Train steps ... :  45%|████▍     | 44816/100000 [13:01:18<8:59:04,  1.71it/s]
Train steps ... :  45%|████▍     | 44817/100000 [13:01:19<8:59:12,  1.71it/s]
Train steps ... :  45%|████▍     | 44818/100000 [13:01:20<8:58:14,  1.71it/s]
Train steps ... :  45%|████▍     | 44819/100000 [13:01:20<8:57:55,  1.71it/s]
Train steps ... :  45%|████▍     | 44820/100000 [13:01:21<8:59:08,  1.71it/s]
Train steps ... :  45%|████▍     | 44821/100000 [13:01:21<8:58:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44822/100000 [13:01:22<9:00:05,  1.70it/s]
Train steps ... :  45%|████▍     | 44823/100000 [13:01:23<9:00:16,  1.70it/s]
Train steps ... :  45%|████▍     | 44824/100000 [13:01:23<8:58:19,  1.71it/s]
Train steps ... :  45%|████▍     | 44825/100000 [13:01:24<8:58:08,  1.71it/s]Step... (44825 / 100000 | Loss: 0.740262508392334, Learning Rate: 5.545226130653267e-05)
+
                                                                             
Step... (44825 / 100000 | Loss: 0.8008044958114624, Learning Rate: 5.545226130653267e-05)
+
Train steps ... :  45%|████▍     | 44825/100000 [13:01:24<8:58:08,  1.71it/s]
Train steps ... :  45%|███���▍     | 44826/100000 [13:01:24<8:58:43,  1.71it/s]
Train steps ... :  45%|████▍     | 44827/100000 [13:01:25<8:59:28,  1.70it/s]
Train steps ... :  45%|████▍     | 44828/100000 [13:01:26<8:58:39,  1.71it/s]
Train steps ... :  45%|████▍     | 44829/100000 [13:01:26<8:59:29,  1.70it/s]
Train steps ... :  45%|████▍     | 44830/100000 [13:01:27<9:00:03,  1.70it/s]
Train steps ... :  45%|████▍     | 44831/100000 [13:01:27<9:00:02,  1.70it/s]
Train steps ... :  45%|████▍     | 44832/100000 [13:01:28<8:59:36,  1.70it/s]
Train steps ... :  45%|████▍     | 44833/100000 [13:01:28<8:58:46,  1.71it/s]
Train steps ... :  45%|████▍     | 44834/100000 [13:01:29<8:58:48,  1.71it/s]
Train steps ... :  45%|████▍     | 44835/100000 [13:01:30<8:57:59,  1.71it/s]
Train steps ... :  45%|████▍     | 44836/100000 [13:01:30<8:59:46,  1.70it/s]
Train steps ... :  45%|████▍     | 44837/100000 [13:01:31<8:58:53,  1.71it/s]
Train steps ... :  45%|████▍     | 44838/100000 [13:01:31<9:00:35,  1.70it/s]
Train steps ... :  45%|████▍     | 44839/100000 [13:01:32<9:01:26,  1.70it/s]
Train steps ... :  45%|████▍     | 44840/100000 [13:01:33<8:58:22,  1.71it/s]
Train steps ... :  45%|████▍     | 44841/100000 [13:01:33<8:58:10,  1.71it/s]
Train steps ... :  45%|████▍     | 44842/100000 [13:01:34<8:57:46,  1.71it/s]
Train steps ... :  45%|████▍     | 44843/100000 [13:01:34<8:57:28,  1.71it/s]
Train steps ... :  45%|████▍     | 44844/100000 [13:01:35<8:58:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44845/100000 [13:01:35<8:58:56,  1.71it/s]
Train steps ... :  45%|████▍     | 44846/100000 [13:01:36<8:58:42,  1.71it/s]
Train steps ... :  45%|████▍     | 44847/100000 [13:01:37<8:59:13,  1.70it/s]
Train steps ... :  45%|████▍     | 44848/100000 [13:01:37<8:57:51,  1.71it/s]
Train steps ... :  45%|████▍     | 44849/100000 [13:01:38<8:57:10,  1.71it/s]
Train steps ... :  45%|████▍     | 44850/100000 [13:01:38<8:57:27,  1.71it/s]Step... (44850 / 100000 | Loss: 0.6934047937393188, Learning Rate: 5.542713567839196e-05)
+
                                                                             
Step... (44850 / 100000 | Loss: 0.9160825610160828, Learning Rate: 5.542713567839196e-05)
+
Train steps ... :  45%|████▍     | 44850/100000 [13:01:39<8:57:27,  1.71it/s]
Train steps ... :  45%|████▍     | 44851/100000 [13:01:39<8:57:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44852/100000 [13:01:40<8:57:30,  1.71it/s]
Train steps ... :  45%|████▍     | 44853/100000 [13:01:40<8:58:19,  1.71it/s]
Train steps ... :  45%|████▍     | 44854/100000 [13:01:41<8:57:18,  1.71it/s]
Train steps ... :  45%|████▍     | 44855/100000 [13:01:41<8:57:36,  1.71it/s]
Train steps ... :  45%|████▍     | 44856/100000 [13:01:42<8:56:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44857/100000 [13:01:43<8:57:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44858/100000 [13:01:43<8:57:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44859/100000 [13:01:44<8:57:20,  1.71it/s]
Train steps ... :  45%|████▍     | 44860/100000 [13:01:44<8:57:27,  1.71it/s]
Train steps ... :  45%|████▍     | 44861/100000 [13:01:45<8:58:16,  1.71it/s]
Train steps ... :  45%|████▍     | 44862/100000 [13:01:45<8:57:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44863/100000 [13:01:46<8:57:22,  1.71it/s]
Train steps ... :  45%|████▍     | 44864/100000 [13:01:47<8:57:55,  1.71it/s]
Train steps ... :  45%|████▍     | 44865/100000 [13:01:47<8:57:30,  1.71it/s]
Train steps ... :  45%|████▍     | 44866/100000 [13:01:48<8:57:15,  1.71it/s]
Train steps ... :  45%|████▍     | 44867/100000 [13:01:48<8:56:49,  1.71it/s]
Train steps ... :  45%|████▍     | 44868/100000 [13:01:49<8:58:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44869/100000 [13:01:50<8:57:03,  1.71it/s]
Train steps ... :  45%|████▍     | 44870/100000 [13:01:50<8:56:49,  1.71it/s]
Train steps ... :  45%|████▍     | 44871/100000 [13:01:51<8:57:46,  1.71it/s]
Train steps ... :  45%|████▍     | 44872/100000 [13:01:51<8:56:54,  1.71it/s]
Train steps ... :  45%|████▍     | 44873/100000 [13:01:52<8:57:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44874/100000 [13:01:52<8:57:41,  1.71it/s]
Train steps ... :  45%|████▍     | 44875/100000 [13:01:53<8:57:56,  1.71it/s]Step... (44875 / 100000 | Loss: 1.1064555644989014, Learning Rate: 5.540201005025126e-05)
+
                                                                             
Step... (44875 / 100000 | Loss: 0.7475546598434448, Learning Rate: 5.540201005025126e-05)
+
Train steps ... :  45%|████▍     | 44875/100000 [13:01:53<8:57:56,  1.71it/s]
Train steps ... :  45%|████▍     | 44876/100000 [13:01:54<8:58:04,  1.71it/s]
Train steps ... :  45%|████▍     | 44877/100000 [13:01:54<8:58:17,  1.71it/s]
Train steps ... :  45%|████▍     | 44878/100000 [13:01:55<8:57:07,  1.71it/s]
Train steps ... :  45%|████▍     | 44879/100000 [13:01:55<8:57:42,  1.71it/s]
Train steps ... :  45%|████▍     | 44880/100000 [13:01:56<8:57:57,  1.71it/s]
Train steps ... :  45%|████▍     | 44881/100000 [13:01:57<8:58:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44882/100000 [13:01:57<9:00:09,  1.70it/s]
Train steps ... :  45%|████▍     | 44883/100000 [13:01:58<8:58:22,  1.71it/s]
Train steps ... :  45%|████▍     | 44884/100000 [13:01:58<9:00:06,  1.70it/s]
Train steps ... :  45%|████▍     | 44885/100000 [13:01:59<8:57:50,  1.71it/s]
Train steps ... :  45%|████▍     | 44886/100000 [13:01:59<8:57:25,  1.71it/s]
Train steps ... :  45%|████▍     | 44887/100000 [13:02:00<8:57:56,  1.71it/s]
Train steps ... :  45%|████▍     | 44888/100000 [13:02:01<8:58:35,  1.71it/s]
Train steps ... :  45%|████▍     | 44889/100000 [13:02:01<9:00:31,  1.70it/s]
Train steps ... :  45%|████▍     | 44890/100000 [13:02:02<8:59:05,  1.70it/s]
Train steps ... :  45%|████▍     | 44891/100000 [13:02:02<8:59:12,  1.70it/s]
Train steps ... :  45%|████▍     | 44892/100000 [13:02:03<8:57:43,  1.71it/s]
Train steps ... :  45%|████▍     | 44893/100000 [13:02:04<8:58:11,  1.71it/s]
Train steps ... :  45%|████▍     | 44894/100000 [13:02:04<8:58:26,  1.71it/s]
Train steps ... :  45%|████▍     | 44895/100000 [13:02:05<8:57:29,  1.71it/s]
Train steps ... :  45%|████▍     | 44896/100000 [13:02:05<8:57:30,  1.71it/s]
Train steps ... :  45%|████▍     | 44897/100000 [13:02:06<8:57:11,  1.71it/s]
Train steps ... :  45%|████▍     | 44898/100000 [13:02:07<8:57:55,  1.71it/s]
Train steps ... :  45%|████▍     | 44899/100000 [13:02:07<8:57:25,  1.71it/s]
Train steps ... :  45%|████▍     | 44900/100000 [13:02:08<8:57:47,  1.71it/s]Step... (44900 / 100000 | Loss: 0.68998122215271, Learning Rate: 5.537688442211055e-05)
+
                                                                             
Step... (44900 / 100000 | Loss: 0.8279066681861877, Learning Rate: 5.537688442211055e-05)
+
Train steps ... :  45%|████▍     | 44900/100000 [13:02:08<8:57:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44901/100000 [13:02:08<8:57:04,  1.71it/s]
Train steps ... :  45%|████▍     | 44902/100000 [13:02:09<8:58:07,  1.71it/s]
Train steps ... :  45%|████▍     | 44903/100000 [13:02:09<8:57:14,  1.71it/s]
Train steps ... :  45%|████▍     | 44904/100000 [13:02:10<8:56:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44905/100000 [13:02:11<8:56:54,  1.71it/s]
Train steps ... :  45%|████▍     | 44906/100000 [13:02:11<8:57:09,  1.71it/s]
Train steps ... :  45%|████▍     | 44907/100000 [13:02:12<8:58:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44908/100000 [13:02:12<8:57:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44909/100000 [13:02:13<8:57:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44910/100000 [13:02:14<8:56:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44911/100000 [13:02:14<8:58:13,  1.71it/s]
Train steps ... :  45%|████▍     | 44912/100000 [13:02:15<8:57:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44913/100000 [13:02:15<8:57:11,  1.71it/s]
Train steps ... :  45%|████▍     | 44914/100000 [13:02:16<8:57:12,  1.71it/s]
Train steps ... :  45%|████▍     | 44915/100000 [13:02:16<8:58:19,  1.71it/s]
Train steps ... :  45%|████▍     | 44916/100000 [13:02:17<8:58:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44917/100000 [13:02:18<8:57:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44918/100000 [13:02:18<8:57:54,  1.71it/s]
Train steps ... :  45%|████▍     | 44919/100000 [13:02:19<8:58:12,  1.71it/s]
Train steps ... :  45%|████▍     | 44920/100000 [13:02:19<8:57:41,  1.71it/s]
Train steps ... :  45%|████▍     | 44921/100000 [13:02:20<8:58:36,  1.70it/s]
Train steps ... :  45%|████▍     | 44922/100000 [13:02:21<8:58:24,  1.70it/s]
Train steps ... :  45%|████▍     | 44923/100000 [13:02:21<8:57:20,  1.71it/s]
Train steps ... :  45%|████▍     | 44924/100000 [13:02:22<8:57:04,  1.71it/s]
Train steps ... :  45%|████▍     | 44925/100000 [13:02:22<8:57:31,  1.71it/s]Step... (44925 / 100000 | Loss: 0.5738470554351807, Learning Rate: 5.5351758793969856e-05)
+
                                                                             
Step... (44925 / 100000 | Loss: 0.6671558618545532, Learning Rate: 5.5351758793969856e-05)
+
Train steps ... :  45%|████▍     | 44925/100000 [13:02:23<8:57:31,  1.71it/s]
Train steps ... :  45%|████▍     | 44926/100000 [13:02:23<8:57:20,  1.71it/s]
Train steps ... :  45%|████▍     | 44927/100000 [13:02:24<8:57:06,  1.71it/s]
Train steps ... :  45%|████▍     | 44928/100000 [13:02:24<8:57:07,  1.71it/s]
Train steps ... :  45%|████▍     | 44929/100000 [13:02:25<8:56:50,  1.71it/s]
Train steps ... :  45%|████▍     | 44930/100000 [13:02:25<8:56:22,  1.71it/s]
Train steps ... :  45%|████▍     | 44931/100000 [13:02:26<8:56:34,  1.71it/s]
Train steps ... :  45%|████▍     | 44932/100000 [13:02:26<8:56:42,  1.71it/s]
Train steps ... :  45%|████▍     | 44933/100000 [13:02:27<8:56:17,  1.71it/s]
Train steps ... :  45%|████▍     | 44934/100000 [13:02:28<8:56:20,  1.71it/s]
Train steps ... :  45%|████▍     | 44935/100000 [13:02:28<8:56:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44936/100000 [13:02:29<8:57:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44937/100000 [13:02:29<8:57:39,  1.71it/s]
Train steps ... :  45%|████▍     | 44938/100000 [13:02:30<8:56:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44939/100000 [13:02:31<8:57:38,  1.71it/s]
Train steps ... :  45%|████▍     | 44940/100000 [13:02:31<8:56:47,  1.71it/s]
Train steps ... :  45%|████▍     | 44941/100000 [13:02:32<8:57:09,  1.71it/s]
Train steps ... :  45%|████▍     | 44942/100000 [13:02:32<8:56:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44943/100000 [13:02:33<8:56:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44944/100000 [13:02:33<8:57:25,  1.71it/s]
Train steps ... :  45%|████▍     | 44945/100000 [13:02:34<8:56:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44946/100000 [13:02:35<8:56:41,  1.71it/s]
Train steps ... :  45%|████▍     | 44947/100000 [13:02:35<8:56:28,  1.71it/s]
Train steps ... :  45%|████▍     | 44948/100000 [13:02:36<8:56:40,  1.71it/s]
Train steps ... :  45%|████▍     | 44949/100000 [13:02:36<8:56:27,  1.71it/s]
Train steps ... :  45%|████▍     | 44950/100000 [13:02:37<8:56:01,  1.71it/s]Step... (44950 / 100000 | Loss: 1.0452101230621338, Learning Rate: 5.5326633165829146e-05)
+
                                                                             
Step... (44950 / 100000 | Loss: 1.3198940753936768, Learning Rate: 5.5326633165829146e-05)
+
Train steps ... :  45%|████▍     | 44950/100000 [13:02:37<8:56:01,  1.71it/s]
Train steps ... :  45%|████▍     | 44951/100000 [13:02:38<8:55:53,  1.71it/s]
Train steps ... :  45%|████▍     | 44952/100000 [13:02:38<8:55:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44953/100000 [13:02:39<8:56:20,  1.71it/s]
Train steps ... :  45%|████▍     | 44954/100000 [13:02:39<8:56:32,  1.71it/s]
Train steps ... :  45%|████▍     | 44955/100000 [13:02:40<8:56:50,  1.71it/s]
Train steps ... :  45%|████▍     | 44956/100000 [13:02:40<8:56:59,  1.71it/s]
Train steps ... :  45%|████▍     | 44957/100000 [13:02:41<8:57:38,  1.71it/s]
Train steps ... :  45%|████▍     | 44958/100000 [13:02:42<8:56:54,  1.71it/s]
Train steps ... :  45%|████▍     | 44959/100000 [13:02:42<8:57:02,  1.71it/s]
Train steps ... :  45%|████▍     | 44960/100000 [13:02:43<8:56:34,  1.71it/s]
Train steps ... :  45%|████▍     | 44961/100000 [13:02:43<8:56:50,  1.71it/s]
Train steps ... :  45%|████▍     | 44962/100000 [13:02:44<8:57:00,  1.71it/s]
Train steps ... :  45%|████▍     | 44963/100000 [13:02:45<8:56:36,  1.71it/s]
Train steps ... :  45%|████▍     | 44964/100000 [13:02:45<8:56:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44965/100000 [13:02:46<8:56:54,  1.71it/s]
Train steps ... :  45%|████▍     | 44966/100000 [13:02:46<8:56:45,  1.71it/s]
Train steps ... :  45%|████▍     | 44967/100000 [13:02:47<8:56:58,  1.71it/s]
Train steps ... :  45%|████▍     | 44968/100000 [13:02:47<8:58:42,  1.70it/s]
Train steps ... :  45%|████▍     | 44969/100000 [13:02:48<8:57:59,  1.70it/s]
Train steps ... :  45%|████▍     | 44970/100000 [13:02:49<8:57:18,  1.71it/s]
Train steps ... :  45%|████▍     | 44971/100000 [13:02:49<8:57:09,  1.71it/s]
Train steps ... :  45%|████▍     | 44972/100000 [13:02:50<8:56:14,  1.71it/s]
Train steps ... :  45%|████▍     | 44973/100000 [13:02:50<8:56:36,  1.71it/s]
Train steps ... :  45%|████▍     | 44974/100000 [13:02:51<8:55:56,  1.71it/s]
Train steps ... :  45%|████▍     | 44975/100000 [13:02:52<8:57:11,  1.71it/s]Step... (44975 / 100000 | Loss: 0.8245348930358887, Learning Rate: 5.530150753768845e-05)
+
                                                                             
Step... (44975 / 100000 | Loss: 0.7068620920181274, Learning Rate: 5.530150753768845e-05)
+
Train steps ... :  45%|████▍     | 44975/100000 [13:02:52<8:57:11,  1.71it/s]
Train steps ... :  45%|████▍     | 44976/100000 [13:02:52<8:57:51,  1.71it/s]
Train steps ... :  45%|████▍     | 44977/100000 [13:02:53<8:56:50,  1.71it/s]
Train steps ... :  45%|████▍     | 44978/100000 [13:02:53<8:59:02,  1.70it/s]
Train steps ... :  45%|████▍     | 44979/100000 [13:02:54<8:57:00,  1.71it/s]
Train steps ... :  45%|████▍     | 44980/100000 [13:02:55<8:56:53,  1.71it/s]
Train steps ... :  45%|████▍     | 44981/100000 [13:02:55<8:56:31,  1.71it/s]
Train steps ... :  45%|████▍     | 44982/100000 [13:02:56<8:56:33,  1.71it/s]
Train steps ... :  45%|████▍     | 44983/100000 [13:02:56<8:56:44,  1.71it/s]
Train steps ... :  45%|████▍     | 44984/100000 [13:02:57<8:56:23,  1.71it/s]
Train steps ... :  45%|████▍     | 44985/100000 [13:02:57<8:55:59,  1.71it/s]
Train steps ... :  45%|████▍     | 44986/100000 [13:02:58<8:56:52,  1.71it/s]
Train steps ... :  45%|████▍     | 44987/100000 [13:02:59<8:57:10,  1.71it/s]
Train steps ... :  45%|████▍     | 44988/100000 [13:02:59<8:57:47,  1.70it/s]
Train steps ... :  45%|████▍     | 44989/100000 [13:03:00<8:57:02,  1.71it/s]
Train steps ... :  45%|████▍     | 44990/100000 [13:03:00<8:56:37,  1.71it/s]
Train steps ... :  45%|████▍     | 44991/100000 [13:03:01<8:57:04,  1.71it/s]
Train steps ... :  45%|████▍     | 44992/100000 [13:03:02<8:56:38,  1.71it/s]
Train steps ... :  45%|████▍     | 44993/100000 [13:03:02<8:56:42,  1.71it/s]
Train steps ... :  45%|████▍     | 44994/100000 [13:03:03<8:56:20,  1.71it/s]
Train steps ... :  45%|████▍     | 44995/100000 [13:03:03<8:56:38,  1.71it/s]
Train steps ... :  45%|████▍     | 44996/100000 [13:03:04<8:56:20,  1.71it/s]
Train steps ... :  45%|████▍     | 44997/100000 [13:03:04<8:56:55,  1.71it/s]
Train steps ... :  45%|████▍     | 44998/100000 [13:03:05<8:57:46,  1.70it/s]
Train steps ... :  45%|████▍     | 44999/100000 [13:03:06<8:56:15,  1.71it/s]
Train steps ... :  45%|████▌     | 45000/100000 [13:03:06<8:56:08,  1.71it/s]Step... (45000 / 100000 | Loss: 0.8884999752044678, Learning Rate: 5.527638190954774e-05)
+
                                                                             
Step... (45000 / 100000 | Loss: 0.6424363851547241, Learning Rate: 5.527638190954774e-05)
+
Train steps ... :  45%|████▌     | 45000/100000 [13:03:07<8:56:08,  1.71it/s]06/18/2024 04:57:33 - INFO - accelerate.accelerator - Saving current state to ./checkpoint-45000-epoch-2
+06/18/2024 04:57:33 - 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 04:57:37 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-45000-epoch-2/model.safetensors
+06/18/2024 04:57:37 - 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 04:57:41 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-45000-epoch-2/model_1.safetensors
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Optimizer state saved in checkpoint-45000-epoch-2/optimizer.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Scheduler state saved in checkpoint-45000-epoch-2/scheduler.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in checkpoint-45000-epoch-2/sampler.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in checkpoint-45000-epoch-2/sampler_1.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 2 saved in checkpoint-45000-epoch-2/sampler_2.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 3 saved in checkpoint-45000-epoch-2/sampler_3.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 4 saved in checkpoint-45000-epoch-2/sampler_4.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 5 saved in checkpoint-45000-epoch-2/sampler_5.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 6 saved in checkpoint-45000-epoch-2/sampler_6.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 7 saved in checkpoint-45000-epoch-2/sampler_7.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 8 saved in checkpoint-45000-epoch-2/sampler_8.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 9 saved in checkpoint-45000-epoch-2/sampler_9.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Sampler state for dataloader 10 saved in checkpoint-45000-epoch-2/sampler_10.bin
+06/18/2024 04:57:42 - INFO - accelerate.checkpointing - Random states saved in checkpoint-45000-epoch-2/random_states_0.pkl
+06/18/2024 04:57:42 - INFO - __main__ - Deleting older checkpoint [checkpoint-20000-epoch-1] due to args.save_total_limit
+
+
  0%|          | 0/5 [00:00<?, ?it/s]
+
 20%|██        | 1/5 [01:50<07:22, 110.74s/it]
+
 40%|████      | 2/5 [02:24<03:16, 65.58s/it] 
+
 60%|██████    | 3/5 [02:25<01:11, 35.91s/it]
+
 80%|████████  | 4/5 [02:25<00:21, 21.96s/it]
+
100%|██████████| 5/5 [02:26<00:00, 14.25s/it]
100%|██████████| 5/5 [02:26<00:00, 29.29s/it]