diff --git "a/train.log" "b/train.log"
--- "a/train.log"
+++ "b/train.log"
@@ -11390,3 +11390,4228 @@ Eval results for step (10000 / 100000 | Eval Loss: 1.414140224456787 | Eval wer:
 
 60%|██████    | 3/5 [02:25<01:12, 36.20s/it]
 
 80%|████████  | 4/5 [02:26<00:22, 22.16s/it]
 
100%|██████████| 5/5 [02:26<00:00, 14.41s/it]
100%|██████████| 5/5 [02:26<00:00, 29.36s/it]
+
+
+
Evaluating eval...:   0%|          | 0/1900 [00:00<?, ?it/s]
+
+
Evaluating eval...:   0%|          | 1/1900 [00:03<1:47:38,  3.40s/it]
+
+
Evaluating eval...:   0%|          | 2/1900 [00:04<1:08:01,  2.15s/it]
+
+
Evaluating eval...:   0%|          | 3/1900 [00:05<54:57,  1.74s/it]  
+
+
Evaluating eval...:   0%|          | 4/1900 [00:07<48:26,  1.53s/it]
+
+
Evaluating eval...:   0%|          | 5/1900 [00:08<44:29,  1.41s/it]
+
+
Evaluating eval...:   0%|          | 6/1900 [00:09<41:50,  1.33s/it]
+
+
Evaluating eval...:   0%|          | 7/1900 [00:10<40:10,  1.27s/it]
+
+
Evaluating eval...:   0%|          | 8/1900 [00:11<39:07,  1.24s/it]
+
+
Evaluating eval...:   0%|          | 9/1900 [00:12<38:02,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 10/1900 [00:14<38:07,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 11/1900 [00:15<38:19,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 12/1900 [00:16<37:47,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 13/1900 [00:17<37:44,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 14/1900 [00:18<37:16,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 15/1900 [00:20<37:07,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 16/1900 [00:21<37:03,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 17/1900 [00:22<37:13,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 18/1900 [00:23<37:07,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 19/1900 [00:24<36:41,  1.17s/it]
+
+
Evaluating eval...:   1%|          | 20/1900 [00:25<36:52,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 21/1900 [00:27<37:20,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 22/1900 [00:28<37:07,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 23/1900 [00:29<36:45,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 24/1900 [00:30<37:04,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 25/1900 [00:31<36:34,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 26/1900 [00:33<36:13,  1.16s/it]
+
+
Evaluating eval...:   1%|▏         | 27/1900 [00:34<37:05,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 28/1900 [00:35<36:43,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 29/1900 [00:36<36:32,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 30/1900 [00:37<36:40,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 31/1900 [00:38<36:33,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 32/1900 [00:40<36:53,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 33/1900 [00:41<37:02,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 34/1900 [00:42<37:49,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 35/1900 [00:43<38:05,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 36/1900 [00:45<38:08,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 37/1900 [00:46<37:53,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 38/1900 [00:47<37:35,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 39/1900 [00:48<37:17,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 40/1900 [00:49<37:06,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 41/1900 [00:51<36:38,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 42/1900 [00:52<37:11,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 43/1900 [00:53<36:58,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 44/1900 [00:54<37:04,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 45/1900 [00:55<36:32,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 46/1900 [00:56<36:26,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 47/1900 [00:58<35:59,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 48/1900 [00:59<35:45,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 49/1900 [01:00<35:40,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 50/1900 [01:01<36:10,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 51/1900 [01:02<36:22,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 52/1900 [01:03<36:10,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 53/1900 [01:05<36:01,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 54/1900 [01:06<36:19,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 55/1900 [01:07<36:53,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 56/1900 [01:08<36:56,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 57/1900 [01:09<36:47,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 58/1900 [01:11<36:45,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 59/1900 [01:12<36:34,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 60/1900 [01:13<36:03,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 61/1900 [01:14<37:02,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 62/1900 [01:15<36:40,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 63/1900 [01:17<36:30,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 64/1900 [01:18<36:25,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 65/1900 [01:19<36:06,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 66/1900 [01:20<35:52,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 67/1900 [01:21<35:43,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 68/1900 [01:23<36:47,  1.20s/it]
+
+
Evaluating eval...:   4%|▎         | 69/1900 [01:24<36:09,  1.18s/it]
+
+
Evaluating eval...:   4%|▎         | 70/1900 [01:25<36:42,  1.20s/it]
+
+
Evaluating eval...:   4%|▎         | 71/1900 [01:26<36:41,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 72/1900 [01:27<36:53,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 73/1900 [01:29<36:39,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 74/1900 [01:30<36:26,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 75/1900 [01:31<36:00,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 76/1900 [01:32<35:50,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 77/1900 [01:33<35:53,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 78/1900 [01:34<35:42,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 79/1900 [01:36<35:49,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 80/1900 [01:37<35:49,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 81/1900 [01:38<35:31,  1.17s/it]
+
+
Evaluating eval...:   4%|▍         | 82/1900 [01:39<36:07,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 83/1900 [01:40<36:59,  1.22s/it]
+
+
Evaluating eval...:   4%|▍         | 84/1900 [01:42<36:26,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 85/1900 [01:43<36:17,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 86/1900 [01:44<35:38,  1.18s/it]
+
+
Evaluating eval...:   5%|▍         | 87/1900 [01:45<35:55,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 88/1900 [01:46<35:38,  1.18s/it]
+
+
Evaluating eval...:   5%|▍         | 89/1900 [01:48<36:53,  1.22s/it]
+
+
Evaluating eval...:   5%|▍         | 90/1900 [01:49<36:32,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 91/1900 [01:50<36:48,  1.22s/it]
+
+
Evaluating eval...:   5%|▍         | 92/1900 [01:51<36:11,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 93/1900 [01:52<36:00,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 94/1900 [01:54<35:31,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 95/1900 [01:55<35:06,  1.17s/it]
+
+
Evaluating eval...:   5%|▌         | 96/1900 [01:56<36:07,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 97/1900 [01:57<35:29,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 98/1900 [01:58<36:17,  1.21s/it]
+
+
Evaluating eval...:   5%|▌         | 99/1900 [02:00<35:49,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 100/1900 [02:01<35:31,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 101/1900 [02:02<36:26,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 102/1900 [02:03<36:57,  1.23s/it]
+
+
Evaluating eval...:   5%|▌         | 103/1900 [02:04<36:26,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 104/1900 [02:06<36:02,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 105/1900 [02:07<35:58,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 106/1900 [02:08<35:19,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 107/1900 [02:09<35:46,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 108/1900 [02:10<35:05,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 109/1900 [02:12<35:25,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 110/1900 [02:13<35:05,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 111/1900 [02:14<35:22,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 112/1900 [02:15<36:00,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 113/1900 [02:16<35:33,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 114/1900 [02:17<35:11,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 115/1900 [02:19<34:55,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 116/1900 [02:20<34:29,  1.16s/it]
+
+
Evaluating eval...:   6%|▌         | 117/1900 [02:21<34:35,  1.16s/it]
+
+
Evaluating eval...:   6%|▌         | 118/1900 [02:22<35:03,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 119/1900 [02:23<34:55,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 120/1900 [02:25<35:05,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 121/1900 [02:26<34:48,  1.17s/it]
+
+
Evaluating eval...:   6%|▋         | 122/1900 [02:27<34:57,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 123/1900 [02:28<34:54,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 124/1900 [02:29<35:05,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 125/1900 [02:30<35:09,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 126/1900 [02:32<35:31,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 127/1900 [02:33<35:43,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 128/1900 [02:34<35:14,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 129/1900 [02:35<34:50,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 130/1900 [02:36<34:40,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 131/1900 [02:38<35:04,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 132/1900 [02:39<35:19,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 133/1900 [02:40<34:43,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 134/1900 [02:41<34:47,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 135/1900 [02:42<35:08,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 136/1900 [02:44<35:41,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 137/1900 [02:45<36:02,  1.23s/it]
+
+
Evaluating eval...:   7%|▋         | 138/1900 [02:46<35:51,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 139/1900 [02:47<35:29,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 140/1900 [02:48<35:31,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 141/1900 [02:50<35:15,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 142/1900 [02:51<35:26,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 143/1900 [02:52<35:41,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 144/1900 [02:53<34:56,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 145/1900 [02:54<35:00,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 146/1900 [02:56<34:39,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 147/1900 [02:57<35:00,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 148/1900 [02:58<34:28,  1.18s/it]
+
+
Evaluating eval...:   8%|▊         | 149/1900 [02:59<34:36,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 150/1900 [03:00<35:36,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 151/1900 [03:02<35:13,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 152/1900 [03:03<35:09,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 153/1900 [03:04<35:19,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 154/1900 [03:05<35:11,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 155/1900 [03:06<34:48,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 156/1900 [03:08<34:43,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 157/1900 [03:09<36:04,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 158/1900 [03:10<35:34,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 159/1900 [03:11<34:45,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 160/1900 [03:12<34:28,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 161/1900 [03:14<35:02,  1.21s/it]
+
+
Evaluating eval...:   9%|▊         | 162/1900 [03:15<34:29,  1.19s/it]
+
+
Evaluating eval...:   9%|▊         | 163/1900 [03:16<33:56,  1.17s/it]
+
+
Evaluating eval...:   9%|▊         | 164/1900 [03:17<34:07,  1.18s/it]
+
+
Evaluating eval...:   9%|▊         | 165/1900 [03:18<34:14,  1.18s/it]
+
+
Evaluating eval...:   9%|▊         | 166/1900 [03:20<34:09,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 167/1900 [03:21<34:52,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 168/1900 [03:22<34:12,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 169/1900 [03:23<33:58,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 170/1900 [03:24<33:56,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 171/1900 [03:25<33:45,  1.17s/it]
+
+
Evaluating eval...:   9%|▉         | 172/1900 [03:27<34:20,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 173/1900 [03:28<34:23,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 174/1900 [03:29<34:24,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 175/1900 [03:30<33:54,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 176/1900 [03:31<33:31,  1.17s/it]
+
+
Evaluating eval...:   9%|▉         | 177/1900 [03:34<42:31,  1.48s/it]
+
+
Evaluating eval...:   9%|▉         | 178/1900 [03:35<40:19,  1.41s/it]
+
+
Evaluating eval...:   9%|▉         | 179/1900 [03:36<38:11,  1.33s/it]
+
+
Evaluating eval...:   9%|▉         | 180/1900 [03:37<36:54,  1.29s/it]
+
+
Evaluating eval...:  10%|▉         | 181/1900 [03:38<35:51,  1.25s/it]
+
+
Evaluating eval...:  10%|▉         | 182/1900 [03:40<36:23,  1.27s/it]
+
+
Evaluating eval...:  10%|▉         | 183/1900 [03:41<35:45,  1.25s/it]
+
+
Evaluating eval...:  10%|▉         | 184/1900 [03:42<35:07,  1.23s/it]
+
+
Evaluating eval...:  10%|▉         | 185/1900 [03:43<34:43,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 186/1900 [03:44<34:08,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 187/1900 [03:46<34:13,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 188/1900 [03:47<34:21,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 189/1900 [03:48<33:56,  1.19s/it]
+
+
Evaluating eval...:  10%|█         | 190/1900 [03:49<33:50,  1.19s/it]
+
+
Evaluating eval...:  10%|█         | 191/1900 [03:50<33:31,  1.18s/it]
+
+
Evaluating eval...:  10%|█         | 192/1900 [03:52<34:25,  1.21s/it]
+
+
Evaluating eval...:  10%|█         | 193/1900 [03:53<34:31,  1.21s/it]
+
+
Evaluating eval...:  10%|█         | 194/1900 [03:54<34:25,  1.21s/it]
+
+
Evaluating eval...:  10%|█         | 195/1900 [03:55<34:26,  1.21s/it]
+
+
Evaluating eval...:  10%|█         | 196/1900 [03:56<34:21,  1.21s/it]
+
+
Evaluating eval...:  10%|█         | 197/1900 [03:58<35:17,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 198/1900 [03:59<35:27,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 199/1900 [04:00<34:39,  1.22s/it]
+
+
Evaluating eval...:  11%|█         | 200/1900 [04:01<34:01,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 201/1900 [04:02<33:33,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 202/1900 [04:04<33:12,  1.17s/it]
+
+
Evaluating eval...:  11%|█         | 203/1900 [04:05<33:35,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 204/1900 [04:06<33:25,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 205/1900 [04:07<33:23,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 206/1900 [04:08<33:19,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 207/1900 [04:10<33:54,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 208/1900 [04:11<33:27,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 209/1900 [04:12<33:17,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 210/1900 [04:13<33:06,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 211/1900 [04:14<33:12,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 212/1900 [04:15<33:14,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 213/1900 [04:17<33:57,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 214/1900 [04:18<33:56,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 215/1900 [04:19<33:37,  1.20s/it]
+
+
Evaluating eval...:  11%|█▏        | 216/1900 [04:20<33:28,  1.19s/it]
+
+
Evaluating eval...:  11%|█▏        | 217/1900 [04:21<33:25,  1.19s/it]
+
+
Evaluating eval...:  11%|█▏        | 218/1900 [04:23<33:47,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 219/1900 [04:24<33:38,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 220/1900 [04:25<33:50,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 221/1900 [04:26<33:39,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 222/1900 [04:28<33:19,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 223/1900 [04:29<32:45,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 224/1900 [04:30<32:30,  1.16s/it]
+
+
Evaluating eval...:  12%|█▏        | 225/1900 [04:31<32:25,  1.16s/it]
+
+
Evaluating eval...:  12%|█▏        | 226/1900 [04:32<32:21,  1.16s/it]
+
+
Evaluating eval...:  12%|█▏        | 227/1900 [04:33<32:24,  1.16s/it]
+
+
Evaluating eval...:  12%|█▏        | 228/1900 [04:34<33:01,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 229/1900 [04:36<32:36,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 230/1900 [04:37<32:47,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 231/1900 [04:38<32:46,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 232/1900 [04:39<32:32,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 233/1900 [04:40<32:35,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 234/1900 [04:42<32:34,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 235/1900 [04:43<32:45,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 236/1900 [04:44<33:15,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 237/1900 [04:45<33:19,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 238/1900 [04:46<33:23,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 239/1900 [04:48<33:57,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 240/1900 [04:49<33:21,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 241/1900 [04:50<33:22,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 242/1900 [04:51<33:22,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 243/1900 [04:52<32:53,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 244/1900 [04:54<32:43,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 245/1900 [04:55<33:03,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 246/1900 [04:56<33:21,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 247/1900 [04:57<33:08,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 248/1900 [04:58<33:09,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 249/1900 [05:00<32:35,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 250/1900 [05:01<32:51,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 251/1900 [05:02<33:13,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 252/1900 [05:03<32:48,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 253/1900 [05:04<33:29,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 254/1900 [05:06<33:07,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 255/1900 [05:07<33:10,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 256/1900 [05:08<32:54,  1.20s/it]
+
+
Evaluating eval...:  14%|█▎        | 257/1900 [05:09<32:25,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 258/1900 [05:10<32:17,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 259/1900 [05:12<32:15,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 260/1900 [05:13<32:15,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 261/1900 [05:14<32:21,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 262/1900 [05:15<32:04,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 263/1900 [05:16<32:22,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 264/1900 [05:17<32:13,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 265/1900 [05:19<32:22,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 266/1900 [05:20<32:11,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 267/1900 [05:21<32:35,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 268/1900 [05:22<32:21,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 269/1900 [05:23<32:12,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 270/1900 [05:25<32:01,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 271/1900 [05:26<31:43,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 272/1900 [05:27<31:43,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 273/1900 [05:28<32:24,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 274/1900 [05:29<32:18,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 275/1900 [05:31<32:20,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 276/1900 [05:32<32:33,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 277/1900 [05:33<32:14,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 278/1900 [05:34<31:52,  1.18s/it]
+
+
Evaluating eval...:  15%|█▍        | 279/1900 [05:35<32:23,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 280/1900 [05:36<32:27,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 281/1900 [05:38<32:29,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 282/1900 [05:39<32:15,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 283/1900 [05:40<32:00,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 284/1900 [05:41<31:56,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 285/1900 [05:42<31:40,  1.18s/it]
+
+
Evaluating eval...:  15%|█▌        | 286/1900 [05:44<32:17,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 287/1900 [05:45<32:11,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 288/1900 [05:46<33:03,  1.23s/it]
+
+
Evaluating eval...:  15%|█▌        | 289/1900 [05:47<32:34,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 290/1900 [05:48<32:09,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 291/1900 [05:50<31:56,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 292/1900 [05:51<31:53,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 293/1900 [05:52<31:36,  1.18s/it]
+
+
Evaluating eval...:  15%|█▌        | 294/1900 [05:53<31:24,  1.17s/it]
+
+
Evaluating eval...:  16%|█▌        | 295/1900 [05:54<31:36,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 296/1900 [05:56<31:58,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 297/1900 [05:57<32:16,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 298/1900 [05:58<32:25,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 299/1900 [05:59<31:54,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 300/1900 [06:00<32:02,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 301/1900 [06:02<32:32,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 302/1900 [06:03<32:10,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 303/1900 [06:04<31:43,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 304/1900 [06:05<31:23,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 305/1900 [06:06<31:27,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 306/1900 [06:08<31:34,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 307/1900 [06:09<31:27,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 308/1900 [06:10<31:41,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 309/1900 [06:11<31:34,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 310/1900 [06:12<31:50,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 311/1900 [06:14<32:27,  1.23s/it]
+
+
Evaluating eval...:  16%|█▋        | 312/1900 [06:15<32:21,  1.22s/it]
+
+
Evaluating eval...:  16%|█▋        | 313/1900 [06:16<31:55,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 314/1900 [06:17<31:42,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 315/1900 [06:18<31:52,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 316/1900 [06:20<31:34,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 317/1900 [06:21<31:50,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 318/1900 [06:22<31:24,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 319/1900 [06:23<31:24,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 320/1900 [06:24<31:18,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 321/1900 [06:26<30:52,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 322/1900 [06:27<31:00,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 323/1900 [06:28<31:14,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 324/1900 [06:29<30:47,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 325/1900 [06:30<30:43,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 326/1900 [06:31<30:44,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 327/1900 [06:33<30:36,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 328/1900 [06:34<30:57,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 329/1900 [06:35<30:37,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 330/1900 [06:36<30:56,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 331/1900 [06:37<31:56,  1.22s/it]
+
+
Evaluating eval...:  17%|█▋        | 332/1900 [06:39<31:37,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 333/1900 [06:40<31:26,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 334/1900 [06:41<30:54,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 335/1900 [06:42<30:28,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 336/1900 [06:43<30:37,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 337/1900 [06:44<30:24,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 338/1900 [06:46<31:00,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 339/1900 [06:47<31:33,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 340/1900 [06:48<31:15,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 341/1900 [06:49<31:21,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 342/1900 [06:50<30:49,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 343/1900 [06:52<30:41,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 344/1900 [06:53<30:49,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 345/1900 [06:54<30:44,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 346/1900 [06:55<30:32,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 347/1900 [06:56<30:33,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 348/1900 [06:57<30:12,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 349/1900 [06:59<30:01,  1.16s/it]
+
+
Evaluating eval...:  18%|█▊        | 350/1900 [07:00<30:04,  1.16s/it]
+
+
Evaluating eval...:  18%|█▊        | 351/1900 [07:01<30:42,  1.19s/it]
+
+
Evaluating eval...:  19%|█▊        | 352/1900 [07:02<30:53,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 353/1900 [07:04<31:36,  1.23s/it]
+
+
Evaluating eval...:  19%|█▊        | 354/1900 [07:05<31:20,  1.22s/it]
+
+
Evaluating eval...:  19%|█▊        | 355/1900 [07:06<31:42,  1.23s/it]
+
+
Evaluating eval...:  19%|█▊        | 356/1900 [07:07<31:52,  1.24s/it]
+
+
Evaluating eval...:  19%|█▉        | 357/1900 [07:08<31:13,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 358/1900 [07:10<31:21,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 359/1900 [07:11<30:54,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 360/1900 [07:12<31:04,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 361/1900 [07:13<30:38,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 362/1900 [07:15<31:24,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 363/1900 [07:16<30:54,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 364/1900 [07:17<30:33,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 365/1900 [07:18<30:27,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 366/1900 [07:19<30:04,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 367/1900 [07:20<30:44,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 368/1900 [07:22<31:04,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 369/1900 [07:23<31:00,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 370/1900 [07:24<30:38,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 371/1900 [07:25<30:26,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 372/1900 [07:26<30:15,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 373/1900 [07:28<30:11,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 374/1900 [07:29<30:00,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 375/1900 [07:30<29:44,  1.17s/it]
+
+
Evaluating eval...:  20%|█▉        | 376/1900 [07:31<30:04,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 377/1900 [07:32<30:42,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 378/1900 [07:34<30:51,  1.22s/it]
+
+
Evaluating eval...:  20%|█▉        | 379/1900 [07:35<30:57,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 380/1900 [07:36<30:50,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 381/1900 [07:37<30:46,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 382/1900 [07:39<31:10,  1.23s/it]
+
+
Evaluating eval...:  20%|██        | 383/1900 [07:40<30:34,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 384/1900 [07:41<30:12,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 385/1900 [07:42<30:04,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 386/1900 [07:43<30:25,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 387/1900 [07:44<30:05,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 388/1900 [07:46<30:01,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 389/1900 [07:47<30:02,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 390/1900 [07:48<29:50,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 391/1900 [07:49<30:05,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 392/1900 [07:50<29:49,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 393/1900 [07:52<29:34,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 394/1900 [07:53<29:40,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 395/1900 [07:54<29:26,  1.17s/it]
+
+
Evaluating eval...:  21%|██        | 396/1900 [07:55<30:24,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 397/1900 [07:56<30:24,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 398/1900 [07:58<30:08,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 399/1900 [07:59<30:40,  1.23s/it]
+
+
Evaluating eval...:  21%|██        | 400/1900 [08:00<30:17,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 401/1900 [08:01<30:12,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 402/1900 [08:02<29:50,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 403/1900 [08:04<30:16,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 404/1900 [08:05<30:16,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 405/1900 [08:06<30:23,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 406/1900 [08:07<30:07,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 407/1900 [08:09<30:03,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 408/1900 [08:10<30:31,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 409/1900 [08:11<30:32,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 410/1900 [08:12<30:28,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 411/1900 [08:13<30:10,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 412/1900 [08:15<29:40,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 413/1900 [08:16<30:17,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 414/1900 [08:17<29:59,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 415/1900 [08:18<29:16,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 416/1900 [08:19<28:59,  1.17s/it]
+
+
Evaluating eval...:  22%|██▏       | 417/1900 [08:21<29:35,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 418/1900 [08:22<29:23,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 419/1900 [08:23<29:05,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 420/1900 [08:24<29:39,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 421/1900 [08:25<29:47,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 422/1900 [08:27<29:42,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 423/1900 [08:28<29:59,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 424/1900 [08:29<30:06,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 425/1900 [08:30<29:54,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 426/1900 [08:31<29:47,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 427/1900 [08:33<29:27,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 428/1900 [08:34<29:00,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 429/1900 [08:35<29:19,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 430/1900 [08:36<28:55,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 431/1900 [08:37<28:50,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 432/1900 [08:39<29:15,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 433/1900 [08:40<29:24,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 434/1900 [08:41<30:05,  1.23s/it]
+
+
Evaluating eval...:  23%|██▎       | 435/1900 [08:42<29:29,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 436/1900 [08:43<29:29,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 437/1900 [08:45<28:57,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 438/1900 [08:46<29:02,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 439/1900 [08:47<29:19,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 440/1900 [08:48<29:14,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 441/1900 [08:49<28:59,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 442/1900 [08:51<28:39,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 443/1900 [08:52<28:52,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 444/1900 [08:53<28:44,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 445/1900 [08:54<28:56,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 446/1900 [08:55<28:53,  1.19s/it]
+
+
Evaluating eval...:  24%|██▎       | 447/1900 [08:56<28:33,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 448/1900 [08:58<28:28,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 449/1900 [08:59<28:48,  1.19s/it]
+
+
Evaluating eval...:  24%|██▎       | 450/1900 [09:00<28:43,  1.19s/it]
+
+
Evaluating eval...:  24%|██▎       | 451/1900 [09:01<28:50,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 452/1900 [09:02<28:37,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 453/1900 [09:04<29:06,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 454/1900 [09:05<29:27,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 455/1900 [09:06<29:28,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 456/1900 [09:07<29:25,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 457/1900 [09:09<29:31,  1.23s/it]
+
+
Evaluating eval...:  24%|██▍       | 458/1900 [09:10<29:21,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 459/1900 [09:11<28:51,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 460/1900 [09:12<28:35,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 461/1900 [09:13<29:03,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 462/1900 [09:15<28:55,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 463/1900 [09:16<28:49,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 464/1900 [09:17<29:02,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 465/1900 [09:18<29:00,  1.21s/it]
+
+
Evaluating eval...:  25%|██▍       | 466/1900 [09:19<28:31,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 467/1900 [09:21<28:28,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 468/1900 [09:22<28:36,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 469/1900 [09:23<28:36,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 470/1900 [09:24<28:36,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 471/1900 [09:25<28:37,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 472/1900 [09:27<29:18,  1.23s/it]
+
+
Evaluating eval...:  25%|██▍       | 473/1900 [09:28<28:42,  1.21s/it]
+
+
Evaluating eval...:  25%|██▍       | 474/1900 [09:29<28:22,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 475/1900 [09:30<28:16,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 476/1900 [09:31<27:54,  1.18s/it]
+
+
Evaluating eval...:  25%|██▌       | 477/1900 [09:33<28:42,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 478/1900 [09:34<28:36,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 479/1900 [09:35<28:44,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 480/1900 [09:36<28:21,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 481/1900 [09:37<28:46,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 482/1900 [09:39<28:10,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 483/1900 [09:40<27:54,  1.18s/it]
+
+
Evaluating eval...:  25%|██▌       | 484/1900 [09:41<28:30,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 485/1900 [09:42<28:19,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 486/1900 [09:43<27:59,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 487/1900 [09:45<27:55,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 488/1900 [09:46<28:17,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 489/1900 [09:47<28:17,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 490/1900 [09:48<28:02,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 491/1900 [09:49<28:06,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 492/1900 [09:51<27:55,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 493/1900 [09:52<28:06,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 494/1900 [09:53<27:53,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 495/1900 [09:54<27:47,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 496/1900 [09:55<27:42,  1.18s/it]
+
+
Evaluating eval...:  26%|██▌       | 497/1900 [09:57<28:01,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 498/1900 [09:58<28:46,  1.23s/it]
+
+
Evaluating eval...:  26%|██▋       | 499/1900 [09:59<28:26,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 500/1900 [10:00<28:17,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 501/1900 [10:01<28:19,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 502/1900 [10:03<28:07,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 503/1900 [10:04<28:34,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 504/1900 [10:05<29:39,  1.27s/it]
+
+
Evaluating eval...:  27%|██▋       | 505/1900 [10:07<29:22,  1.26s/it]
+
+
Evaluating eval...:  27%|██▋       | 506/1900 [10:08<28:46,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 507/1900 [10:09<28:20,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 508/1900 [10:10<28:44,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 509/1900 [10:11<29:11,  1.26s/it]
+
+
Evaluating eval...:  27%|██▋       | 510/1900 [10:13<28:36,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 511/1900 [10:14<28:00,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 512/1900 [10:15<27:41,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 513/1900 [10:16<27:21,  1.18s/it]
+
+
Evaluating eval...:  27%|██▋       | 514/1900 [10:17<27:09,  1.18s/it]
+
+
Evaluating eval...:  27%|██▋       | 515/1900 [10:19<27:31,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 516/1900 [10:20<27:28,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 517/1900 [10:21<27:22,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 518/1900 [10:22<27:59,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 519/1900 [10:23<28:32,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 520/1900 [10:25<28:07,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 521/1900 [10:26<28:16,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 522/1900 [10:27<27:53,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 523/1900 [10:28<27:44,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 524/1900 [10:30<27:46,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 525/1900 [10:31<27:24,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 526/1900 [10:32<27:18,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 527/1900 [10:33<27:40,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 528/1900 [10:34<27:31,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 529/1900 [10:36<27:44,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 530/1900 [10:37<27:23,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 531/1900 [10:38<27:28,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 532/1900 [10:39<27:49,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 533/1900 [10:40<27:29,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 534/1900 [10:42<27:35,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 535/1900 [10:43<27:16,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 536/1900 [10:44<27:03,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 537/1900 [10:45<27:10,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 538/1900 [10:46<27:27,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 539/1900 [10:48<27:30,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 540/1900 [10:49<27:14,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 541/1900 [10:50<26:51,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 542/1900 [10:51<27:13,  1.20s/it]
+
+
Evaluating eval...:  29%|██▊       | 543/1900 [10:52<26:58,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 544/1900 [10:53<26:52,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 545/1900 [10:55<27:38,  1.22s/it]
+
+
Evaluating eval...:  29%|██▊       | 546/1900 [10:56<27:21,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 547/1900 [10:57<27:26,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 548/1900 [10:58<27:35,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 549/1900 [11:00<27:45,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 550/1900 [11:01<27:49,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 551/1900 [11:02<27:31,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 552/1900 [11:03<27:38,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 553/1900 [11:05<27:20,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 554/1900 [11:06<26:53,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 555/1900 [11:07<26:47,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 556/1900 [11:08<26:42,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 557/1900 [11:09<26:26,  1.18s/it]
+
+
Evaluating eval...:  29%|██▉       | 558/1900 [11:10<26:34,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 559/1900 [11:12<26:21,  1.18s/it]
+
+
Evaluating eval...:  29%|██▉       | 560/1900 [11:13<26:39,  1.19s/it]
+
+
Evaluating eval...:  30%|██▉       | 561/1900 [11:14<26:37,  1.19s/it]
+
+
Evaluating eval...:  30%|██▉       | 562/1900 [11:15<26:41,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 563/1900 [11:16<26:47,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 564/1900 [11:18<27:04,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 565/1900 [11:19<26:56,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 566/1900 [11:20<26:58,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 567/1900 [11:21<26:59,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 568/1900 [11:23<27:09,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 569/1900 [11:24<27:09,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 570/1900 [11:25<28:02,  1.27s/it]
+
+
Evaluating eval...:  30%|███       | 571/1900 [11:26<27:14,  1.23s/it]
+
+
Evaluating eval...:  30%|███       | 572/1900 [11:28<27:05,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 573/1900 [11:29<26:37,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 574/1900 [11:30<26:41,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 575/1900 [11:31<26:21,  1.19s/it]
+
+
Evaluating eval...:  30%|███       | 576/1900 [11:32<26:34,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 577/1900 [11:33<26:30,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 578/1900 [11:35<26:39,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 579/1900 [11:36<26:53,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 580/1900 [11:37<26:45,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 581/1900 [11:38<26:21,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 582/1900 [11:41<33:18,  1.52s/it]
+
+
Evaluating eval...:  31%|███       | 583/1900 [11:42<30:55,  1.41s/it]
+
+
Evaluating eval...:  31%|███       | 584/1900 [11:43<29:27,  1.34s/it]
+
+
Evaluating eval...:  31%|███       | 585/1900 [11:44<28:19,  1.29s/it]
+
+
Evaluating eval...:  31%|███       | 586/1900 [11:45<27:57,  1.28s/it]
+
+
Evaluating eval...:  31%|███       | 587/1900 [11:47<27:17,  1.25s/it]
+
+
Evaluating eval...:  31%|███       | 588/1900 [11:48<26:38,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 589/1900 [11:49<26:29,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 590/1900 [11:50<26:18,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 591/1900 [11:51<26:10,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 592/1900 [11:52<25:52,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 593/1900 [11:54<25:52,  1.19s/it]
+
+
Evaluating eval...:  31%|███▏      | 594/1900 [11:55<25:51,  1.19s/it]
+
+
Evaluating eval...:  31%|███▏      | 595/1900 [11:56<25:38,  1.18s/it]
+
+
Evaluating eval...:  31%|███▏      | 596/1900 [11:57<26:04,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 597/1900 [11:58<26:28,  1.22s/it]
+
+
Evaluating eval...:  31%|███▏      | 598/1900 [12:00<26:10,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 599/1900 [12:01<26:16,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 600/1900 [12:02<26:22,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 601/1900 [12:03<26:09,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 602/1900 [12:04<25:41,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 603/1900 [12:06<25:49,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 604/1900 [12:07<25:45,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 605/1900 [12:08<25:43,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 606/1900 [12:09<25:58,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 607/1900 [12:10<25:34,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 608/1900 [12:12<26:10,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 609/1900 [12:13<26:18,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 610/1900 [12:14<25:52,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 611/1900 [12:15<25:38,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 612/1900 [12:17<26:07,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 613/1900 [12:18<25:48,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 614/1900 [12:19<26:16,  1.23s/it]
+
+
Evaluating eval...:  32%|███▏      | 615/1900 [12:20<25:51,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 616/1900 [12:21<25:31,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 617/1900 [12:22<25:15,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 618/1900 [12:24<25:02,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 619/1900 [12:25<25:24,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 620/1900 [12:26<25:16,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 621/1900 [12:27<25:28,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 622/1900 [12:28<25:33,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 623/1900 [12:30<25:27,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 624/1900 [12:31<25:35,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 625/1900 [12:32<25:49,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 626/1900 [12:33<25:19,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 627/1900 [12:34<25:05,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 628/1900 [12:36<25:03,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 629/1900 [12:37<25:21,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 630/1900 [12:38<25:19,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 631/1900 [12:39<25:42,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 632/1900 [12:40<25:17,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 633/1900 [12:42<25:01,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 634/1900 [12:43<24:42,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 635/1900 [12:44<24:49,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 636/1900 [12:45<25:07,  1.19s/it]
+
+
Evaluating eval...:  34%|███▎      | 637/1900 [12:46<25:27,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 638/1900 [12:48<25:36,  1.22s/it]
+
+
Evaluating eval...:  34%|███▎      | 639/1900 [12:49<25:38,  1.22s/it]
+
+
Evaluating eval...:  34%|███▎      | 640/1900 [12:50<25:48,  1.23s/it]
+
+
Evaluating eval...:  34%|███▎      | 641/1900 [12:51<25:47,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 642/1900 [12:53<25:46,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 643/1900 [12:54<25:52,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 644/1900 [12:55<25:38,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 645/1900 [12:56<25:37,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 646/1900 [12:58<26:09,  1.25s/it]
+
+
Evaluating eval...:  34%|███▍      | 647/1900 [12:59<25:44,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 648/1900 [13:00<25:19,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 649/1900 [13:01<25:45,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 650/1900 [13:02<25:48,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 651/1900 [13:04<25:41,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 652/1900 [13:05<25:11,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 653/1900 [13:06<24:53,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 654/1900 [13:07<25:04,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 655/1900 [13:08<25:05,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 656/1900 [13:10<24:52,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 657/1900 [13:11<24:42,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 658/1900 [13:12<25:20,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 659/1900 [13:13<25:11,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 660/1900 [13:14<24:47,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 661/1900 [13:16<24:39,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 662/1900 [13:17<25:03,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 663/1900 [13:18<25:23,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 664/1900 [13:19<25:11,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 665/1900 [13:20<24:49,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 666/1900 [13:22<24:47,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 667/1900 [13:23<25:33,  1.24s/it]
+
+
Evaluating eval...:  35%|███▌      | 668/1900 [13:24<25:05,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 669/1900 [13:25<24:50,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 670/1900 [13:27<24:52,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 671/1900 [13:28<24:51,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 672/1900 [13:29<24:39,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 673/1900 [13:30<24:27,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 674/1900 [13:31<24:26,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 675/1900 [13:33<24:19,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 676/1900 [13:34<24:14,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 677/1900 [13:35<24:04,  1.18s/it]
+
+
Evaluating eval...:  36%|███▌      | 678/1900 [13:36<24:31,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 679/1900 [13:37<24:02,  1.18s/it]
+
+
Evaluating eval...:  36%|███▌      | 680/1900 [13:39<24:20,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 681/1900 [13:40<24:30,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 682/1900 [13:41<24:37,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 683/1900 [13:42<24:32,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 684/1900 [13:43<24:14,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 685/1900 [13:45<24:01,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 686/1900 [13:46<24:19,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 687/1900 [13:47<24:07,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 688/1900 [13:48<23:48,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 689/1900 [13:49<23:41,  1.17s/it]
+
+
Evaluating eval...:  36%|███▋      | 690/1900 [13:50<23:53,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 691/1900 [13:52<23:45,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 692/1900 [13:53<23:35,  1.17s/it]
+
+
Evaluating eval...:  36%|███▋      | 693/1900 [13:54<23:37,  1.17s/it]
+
+
Evaluating eval...:  37%|███▋      | 694/1900 [13:55<23:49,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 695/1900 [13:56<24:05,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 696/1900 [13:58<24:02,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 697/1900 [13:59<23:56,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 698/1900 [14:00<23:45,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 699/1900 [14:01<24:01,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 700/1900 [14:02<23:49,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 701/1900 [14:04<23:53,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 702/1900 [14:05<23:53,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 703/1900 [14:06<23:28,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 704/1900 [14:07<24:34,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 705/1900 [14:08<24:20,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 706/1900 [14:10<23:58,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 707/1900 [14:11<23:40,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 708/1900 [14:12<24:01,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 709/1900 [14:13<23:50,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 710/1900 [14:14<23:48,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 711/1900 [14:16<24:35,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 712/1900 [14:17<24:25,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 713/1900 [14:18<24:47,  1.25s/it]
+
+
Evaluating eval...:  38%|███▊      | 714/1900 [14:19<24:08,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 715/1900 [14:21<23:48,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 716/1900 [14:22<23:28,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 717/1900 [14:23<23:22,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 718/1900 [14:24<23:45,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 719/1900 [14:25<23:46,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 720/1900 [14:27<23:38,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 721/1900 [14:28<24:15,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 722/1900 [14:29<23:52,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 723/1900 [14:30<23:45,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 724/1900 [14:31<23:42,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 725/1900 [14:33<23:28,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 726/1900 [14:34<23:26,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 727/1900 [14:35<23:13,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 728/1900 [14:36<23:27,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 729/1900 [14:37<23:07,  1.18s/it]
+
+
Evaluating eval...:  38%|███▊      | 730/1900 [14:39<23:45,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 731/1900 [14:40<23:44,  1.22s/it]
+
+
Evaluating eval...:  39%|███▊      | 732/1900 [14:41<23:28,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 733/1900 [14:42<23:20,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 734/1900 [14:43<23:18,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 735/1900 [14:45<23:00,  1.18s/it]
+
+
Evaluating eval...:  39%|███▊      | 736/1900 [14:46<23:08,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 737/1900 [14:47<22:53,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 738/1900 [14:48<23:13,  1.20s/it]
+
+
Evaluating eval...:  39%|███▉      | 739/1900 [14:49<23:02,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 740/1900 [14:51<22:59,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 741/1900 [14:52<23:35,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 742/1900 [14:53<23:27,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 743/1900 [14:54<23:48,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 744/1900 [14:55<23:20,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 745/1900 [14:57<23:55,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 746/1900 [14:58<23:56,  1.25s/it]
+
+
Evaluating eval...:  39%|███▉      | 747/1900 [14:59<24:02,  1.25s/it]
+
+
Evaluating eval...:  39%|███▉      | 748/1900 [15:00<23:28,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 749/1900 [15:02<23:25,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 750/1900 [15:03<23:11,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 751/1900 [15:04<23:10,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 752/1900 [15:05<23:05,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 753/1900 [15:06<23:08,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 754/1900 [15:08<22:48,  1.19s/it]
+
+
Evaluating eval...:  40%|███▉      | 755/1900 [15:09<22:32,  1.18s/it]
+
+
Evaluating eval...:  40%|███▉      | 756/1900 [15:10<22:54,  1.20s/it]
+
+
Evaluating eval...:  40%|███▉      | 757/1900 [15:11<23:04,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 758/1900 [15:12<22:58,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 759/1900 [15:14<23:13,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 760/1900 [15:15<23:29,  1.24s/it]
+
+
Evaluating eval...:  40%|████      | 761/1900 [15:16<23:06,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 762/1900 [15:17<22:42,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 763/1900 [15:18<22:28,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 764/1900 [15:20<22:15,  1.18s/it]
+
+
Evaluating eval...:  40%|████      | 765/1900 [15:21<22:25,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 766/1900 [15:22<22:37,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 767/1900 [15:23<23:07,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 768/1900 [15:25<23:35,  1.25s/it]
+
+
Evaluating eval...:  40%|████      | 769/1900 [15:26<23:23,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 770/1900 [15:27<22:52,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 771/1900 [15:28<22:47,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 772/1900 [15:29<22:43,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 773/1900 [15:31<22:35,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 774/1900 [15:32<22:15,  1.19s/it]
+
+
Evaluating eval...:  41%|████      | 775/1900 [15:33<22:36,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 776/1900 [15:34<22:32,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 777/1900 [15:36<22:58,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 778/1900 [15:37<22:36,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 779/1900 [15:38<22:22,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 780/1900 [15:39<23:08,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 781/1900 [15:40<23:05,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 782/1900 [15:42<23:11,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 783/1900 [15:43<22:59,  1.23s/it]
+
+
Evaluating eval...:  41%|████▏     | 784/1900 [15:44<22:55,  1.23s/it]
+
+
Evaluating eval...:  41%|████▏     | 785/1900 [15:45<22:28,  1.21s/it]
+
+
Evaluating eval...:  41%|████▏     | 786/1900 [15:46<22:18,  1.20s/it]
+
+
Evaluating eval...:  41%|████▏     | 787/1900 [15:48<22:20,  1.20s/it]
+
+
Evaluating eval...:  41%|████▏     | 788/1900 [15:49<22:28,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 789/1900 [15:50<22:49,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 790/1900 [15:51<22:45,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 791/1900 [15:53<22:48,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 792/1900 [15:54<22:55,  1.24s/it]
+
+
Evaluating eval...:  42%|████▏     | 793/1900 [15:55<22:30,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 794/1900 [15:56<22:24,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 795/1900 [15:58<22:26,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 796/1900 [15:59<22:17,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 797/1900 [16:00<22:16,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 798/1900 [16:01<22:18,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 799/1900 [16:02<22:04,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 800/1900 [16:04<22:38,  1.24s/it]
+
+
Evaluating eval...:  42%|████▏     | 801/1900 [16:05<22:25,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 802/1900 [16:06<22:02,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 803/1900 [16:07<22:09,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 804/1900 [16:08<21:58,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 805/1900 [16:10<22:04,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 806/1900 [16:11<21:48,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 807/1900 [16:12<21:36,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 808/1900 [16:13<22:01,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 809/1900 [16:14<22:10,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 810/1900 [16:16<22:09,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 811/1900 [16:17<22:02,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 812/1900 [16:18<22:19,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 813/1900 [16:19<21:50,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 814/1900 [16:20<21:52,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 815/1900 [16:22<21:56,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 816/1900 [16:23<22:02,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 817/1900 [16:24<21:54,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 818/1900 [16:25<22:11,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 819/1900 [16:27<22:11,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 820/1900 [16:28<22:03,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 821/1900 [16:29<21:45,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 822/1900 [16:30<21:37,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 823/1900 [16:31<21:43,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 824/1900 [16:33<21:30,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 825/1900 [16:34<21:14,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 826/1900 [16:35<21:46,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 827/1900 [16:36<21:35,  1.21s/it]
+
+
Evaluating eval...:  44%|████▎     | 828/1900 [16:37<21:30,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 829/1900 [16:39<21:19,  1.19s/it]
+
+
Evaluating eval...:  44%|████▎     | 830/1900 [16:40<21:20,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 831/1900 [16:41<21:02,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 832/1900 [16:42<21:12,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 833/1900 [16:43<21:18,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 834/1900 [16:45<21:03,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 835/1900 [16:46<21:17,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 836/1900 [16:47<21:16,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 837/1900 [16:48<21:08,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 838/1900 [16:49<20:54,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 839/1900 [16:50<20:45,  1.17s/it]
+
+
Evaluating eval...:  44%|████▍     | 840/1900 [16:52<20:48,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 841/1900 [16:53<21:06,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 842/1900 [16:54<21:11,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 843/1900 [16:55<21:04,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 844/1900 [16:56<20:44,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 845/1900 [16:58<20:50,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 846/1900 [16:59<21:24,  1.22s/it]
+
+
Evaluating eval...:  45%|████▍     | 847/1900 [17:00<20:59,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 848/1900 [17:01<20:54,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 849/1900 [17:02<20:48,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 850/1900 [17:04<21:02,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 851/1900 [17:05<20:49,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 852/1900 [17:06<21:13,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 853/1900 [17:07<20:56,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 854/1900 [17:09<21:15,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 855/1900 [17:10<21:03,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 856/1900 [17:11<20:50,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 857/1900 [17:12<20:38,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 858/1900 [17:13<21:00,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 859/1900 [17:15<20:57,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 860/1900 [17:16<20:53,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 861/1900 [17:17<20:58,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 862/1900 [17:18<20:58,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 863/1900 [17:19<20:32,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 864/1900 [17:20<20:27,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 865/1900 [17:22<20:11,  1.17s/it]
+
+
Evaluating eval...:  46%|████▌     | 866/1900 [17:23<20:14,  1.17s/it]
+
+
Evaluating eval...:  46%|████▌     | 867/1900 [17:24<20:36,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 868/1900 [17:25<21:02,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 869/1900 [17:26<20:36,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 870/1900 [17:28<20:41,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 871/1900 [17:29<20:58,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 872/1900 [17:30<20:40,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 873/1900 [17:31<20:28,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 874/1900 [17:33<20:44,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 875/1900 [17:34<20:44,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 876/1900 [17:35<20:25,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 877/1900 [17:36<20:07,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 878/1900 [17:37<20:21,  1.20s/it]
+
+
Evaluating eval...:  46%|████▋     | 879/1900 [17:38<20:13,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 880/1900 [17:40<20:01,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 881/1900 [17:41<20:01,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 882/1900 [17:42<20:04,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 883/1900 [17:43<20:31,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 884/1900 [17:44<20:19,  1.20s/it]
+
+
Evaluating eval...:  47%|███��▋     | 885/1900 [17:46<20:04,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 886/1900 [17:47<19:56,  1.18s/it]
+
+
Evaluating eval...:  47%|████▋     | 887/1900 [17:48<20:06,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 888/1900 [17:49<20:16,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 889/1900 [17:50<20:13,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 890/1900 [17:52<20:04,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 891/1900 [17:53<20:33,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 892/1900 [17:54<20:28,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 893/1900 [17:55<20:31,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 894/1900 [17:56<20:12,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 895/1900 [17:58<20:24,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 896/1900 [17:59<20:08,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 897/1900 [18:00<19:57,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 898/1900 [18:01<20:23,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 899/1900 [18:03<20:01,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 900/1900 [18:04<20:08,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 901/1900 [18:05<19:54,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 902/1900 [18:06<20:15,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 903/1900 [18:07<20:12,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 904/1900 [18:09<20:06,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 905/1900 [18:10<19:56,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 906/1900 [18:11<19:59,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 907/1900 [18:12<20:14,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 908/1900 [18:13<19:56,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 909/1900 [18:15<19:55,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 910/1900 [18:16<19:49,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 911/1900 [18:17<20:14,  1.23s/it]
+
+
Evaluating eval...:  48%|████▊     | 912/1900 [18:18<20:03,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 913/1900 [18:19<19:55,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 914/1900 [18:21<19:49,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 915/1900 [18:22<20:25,  1.24s/it]
+
+
Evaluating eval...:  48%|████▊     | 916/1900 [18:23<20:17,  1.24s/it]
+
+
Evaluating eval...:  48%|████▊     | 917/1900 [18:24<19:49,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 918/1900 [18:26<19:36,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 919/1900 [18:27<19:48,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 920/1900 [18:28<19:43,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 921/1900 [18:29<19:24,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 922/1900 [18:30<19:17,  1.18s/it]
+
+
Evaluating eval...:  49%|████▊     | 923/1900 [18:32<19:51,  1.22s/it]
+
+
Evaluating eval...:  49%|████▊     | 924/1900 [18:33<19:29,  1.20s/it]
+
+
Evaluating eval...:  49%|████▊     | 925/1900 [18:34<19:40,  1.21s/it]
+
+
Evaluating eval...:  49%|████▊     | 926/1900 [18:35<19:41,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 927/1900 [18:36<19:27,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 928/1900 [18:38<19:54,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 929/1900 [18:39<19:28,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 930/1900 [18:40<19:11,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 931/1900 [18:41<19:32,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 932/1900 [18:43<19:51,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 933/1900 [18:44<19:51,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 934/1900 [18:45<19:30,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 935/1900 [18:46<19:41,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 936/1900 [18:48<20:23,  1.27s/it]
+
+
Evaluating eval...:  49%|████▉     | 937/1900 [18:49<20:09,  1.26s/it]
+
+
Evaluating eval...:  49%|████▉     | 938/1900 [18:50<19:45,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 939/1900 [18:51<19:39,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 940/1900 [18:52<19:41,  1.23s/it]
+
+
Evaluating eval...:  50%|████▉     | 941/1900 [18:54<19:33,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 942/1900 [18:55<19:47,  1.24s/it]
+
+
Evaluating eval...:  50%|████▉     | 943/1900 [18:56<19:30,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 944/1900 [18:57<19:20,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 945/1900 [18:58<19:04,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 946/1900 [19:00<19:15,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 947/1900 [19:01<19:25,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 948/1900 [19:02<19:17,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 949/1900 [19:03<19:21,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 950/1900 [19:05<19:09,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 951/1900 [19:06<19:34,  1.24s/it]
+
+
Evaluating eval...:  50%|█████     | 952/1900 [19:07<19:42,  1.25s/it]
+
+
Evaluating eval...:  50%|█████     | 953/1900 [19:08<19:15,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 954/1900 [19:09<19:00,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 955/1900 [19:11<19:15,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 956/1900 [19:12<18:58,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 957/1900 [19:13<18:45,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 958/1900 [19:14<18:57,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 959/1900 [19:15<18:53,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 960/1900 [19:17<19:05,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 961/1900 [19:18<19:37,  1.25s/it]
+
+
Evaluating eval...:  51%|█████     | 962/1900 [19:19<19:18,  1.24s/it]
+
+
Evaluating eval...:  51%|█████     | 963/1900 [19:21<19:32,  1.25s/it]
+
+
Evaluating eval...:  51%|█████     | 964/1900 [19:22<19:38,  1.26s/it]
+
+
Evaluating eval...:  51%|█████     | 965/1900 [19:23<19:20,  1.24s/it]
+
+
Evaluating eval...:  51%|█████     | 966/1900 [19:24<18:51,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 967/1900 [19:25<18:38,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 968/1900 [19:27<18:33,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 969/1900 [19:28<18:44,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 970/1900 [19:29<18:55,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 971/1900 [19:30<18:41,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 972/1900 [19:31<18:55,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 973/1900 [19:33<18:41,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 974/1900 [19:34<18:31,  1.20s/it]
+
+
Evaluating eval...:  51%|█████▏    | 975/1900 [19:35<19:06,  1.24s/it]
+
+
Evaluating eval...:  51%|█████▏    | 976/1900 [19:36<19:14,  1.25s/it]
+
+
Evaluating eval...:  51%|█████▏    | 977/1900 [19:38<18:46,  1.22s/it]
+
+
Evaluating eval...:  51%|█████▏    | 978/1900 [19:39<18:49,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 979/1900 [19:40<18:36,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 980/1900 [19:41<18:33,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 981/1900 [19:42<18:17,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 982/1900 [19:43<18:03,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 983/1900 [19:45<18:20,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 984/1900 [19:46<18:11,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 985/1900 [19:47<18:07,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 986/1900 [19:48<17:56,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 987/1900 [19:49<17:55,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 988/1900 [19:51<17:48,  1.17s/it]
+
+
Evaluating eval...:  52%|█████▏    | 989/1900 [19:52<18:04,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 990/1900 [19:53<18:34,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 991/1900 [19:54<18:25,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 992/1900 [19:56<18:18,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 993/1900 [19:57<18:24,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 994/1900 [19:58<18:05,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 995/1900 [19:59<18:25,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 996/1900 [20:00<18:06,  1.20s/it]
+
+
Evaluating eval...:  52%|████���▏    | 997/1900 [20:01<17:53,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 998/1900 [20:03<17:53,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 999/1900 [20:04<17:54,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1000/1900 [20:05<17:46,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1001/1900 [20:06<17:46,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1002/1900 [20:07<17:52,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1003/1900 [20:09<18:13,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1004/1900 [20:10<18:14,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1005/1900 [20:11<17:57,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1006/1900 [20:12<18:00,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1007/1900 [20:14<18:03,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1008/1900 [20:15<18:00,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1009/1900 [20:16<17:52,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1010/1900 [20:17<17:57,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1011/1900 [20:18<17:54,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1012/1900 [20:20<18:17,  1.24s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1013/1900 [20:21<18:05,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1014/1900 [20:22<18:25,  1.25s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1015/1900 [20:23<18:07,  1.23s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1016/1900 [20:25<18:48,  1.28s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1017/1900 [20:26<18:35,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1018/1900 [20:27<18:22,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1019/1900 [20:29<18:37,  1.27s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1020/1900 [20:30<18:32,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1021/1900 [20:31<18:11,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1022/1900 [20:32<18:11,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1023/1900 [20:33<18:14,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1024/1900 [20:35<18:07,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1025/1900 [20:36<17:45,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1026/1900 [20:37<17:55,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1027/1900 [20:38<17:48,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1028/1900 [20:39<17:36,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1029/1900 [20:41<17:24,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1030/1900 [20:42<17:10,  1.18s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1031/1900 [20:43<17:33,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1032/1900 [20:44<17:30,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1033/1900 [20:45<17:17,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1034/1900 [20:47<17:59,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1035/1900 [20:48<17:35,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1036/1900 [20:49<17:37,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1037/1900 [20:50<17:45,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1038/1900 [20:52<17:37,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1039/1900 [20:53<17:45,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1040/1900 [20:54<17:34,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1041/1900 [20:55<17:36,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1042/1900 [20:57<17:27,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1043/1900 [20:58<17:15,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1044/1900 [20:59<17:07,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1045/1900 [21:00<16:53,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1046/1900 [21:01<16:51,  1.18s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1047/1900 [21:02<16:48,  1.18s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1048/1900 [21:04<16:55,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1049/1900 [21:05<16:58,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1050/1900 [21:06<17:36,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1051/1900 [21:07<17:21,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1052/1900 [21:09<17:18,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1053/1900 [21:10<17:11,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1054/1900 [21:11<17:00,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1055/1900 [21:12<16:42,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1056/1900 [21:13<17:11,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1057/1900 [21:15<17:28,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1058/1900 [21:16<17:22,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1059/1900 [21:17<16:57,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1060/1900 [21:18<16:41,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1061/1900 [21:19<16:39,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1062/1900 [21:21<16:32,  1.18s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1063/1900 [21:22<16:38,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1064/1900 [21:23<17:24,  1.25s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1065/1900 [21:24<17:12,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1066/1900 [21:26<16:58,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1067/1900 [21:27<16:58,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1068/1900 [21:28<16:46,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1069/1900 [21:29<16:49,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1070/1900 [21:30<16:41,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1071/1900 [21:32<16:46,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1072/1900 [21:33<16:47,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1073/1900 [21:34<16:33,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1074/1900 [21:35<16:32,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1075/1900 [21:36<16:34,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1076/1900 [21:38<16:40,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1077/1900 [21:39<16:46,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1078/1900 [21:40<16:23,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1079/1900 [21:41<16:44,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1080/1900 [21:43<17:10,  1.26s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1081/1900 [21:44<16:56,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1082/1900 [21:45<16:43,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1083/1900 [21:46<16:49,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1084/1900 [21:48<16:29,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1085/1900 [21:49<16:38,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1086/1900 [21:50<16:39,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1087/1900 [21:51<16:24,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1088/1900 [21:52<16:18,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1089/1900 [21:54<16:41,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1090/1900 [21:55<16:24,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1091/1900 [21:56<16:16,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1092/1900 [21:57<16:49,  1.25s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1093/1900 [21:59<16:34,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1094/1900 [22:00<16:20,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1095/1900 [22:01<16:11,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1096/1900 [22:02<15:57,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1097/1900 [22:03<15:46,  1.18s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1098/1900 [22:05<16:14,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1099/1900 [22:06<16:33,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1100/1900 [22:07<16:15,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1101/1900 [22:08<16:01,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1102/1900 [22:09<15:53,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1103/1900 [22:11<15:58,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1104/1900 [22:12<15:43,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1105/1900 [22:13<16:26,  1.24s/it]
+
+
Evaluating eval...:  58%|███���█▊    | 1106/1900 [22:14<16:34,  1.25s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1107/1900 [22:16<16:31,  1.25s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1108/1900 [22:17<16:22,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1109/1900 [22:18<16:17,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1110/1900 [22:19<16:07,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1111/1900 [22:21<16:34,  1.26s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1112/1900 [22:22<16:15,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1113/1900 [22:23<16:13,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1114/1900 [22:24<16:07,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1115/1900 [22:25<16:02,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1116/1900 [22:27<16:03,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1117/1900 [22:28<15:53,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1118/1900 [22:29<15:44,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1119/1900 [22:30<15:50,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1120/1900 [22:31<15:41,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1121/1900 [22:33<15:46,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1122/1900 [22:34<15:33,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1123/1900 [22:35<15:38,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1124/1900 [22:36<15:36,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1125/1900 [22:38<15:37,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1126/1900 [22:39<15:42,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1127/1900 [22:40<15:48,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1128/1900 [22:41<15:58,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1129/1900 [22:42<15:36,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1130/1900 [22:44<15:21,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1131/1900 [22:45<15:25,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1132/1900 [22:46<15:30,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1133/1900 [22:47<15:31,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1134/1900 [22:48<15:23,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1135/1900 [22:50<15:55,  1.25s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1136/1900 [22:51<15:37,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1137/1900 [22:52<15:18,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1138/1900 [22:53<15:36,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1139/1900 [22:55<15:37,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1140/1900 [22:56<15:41,  1.24s/it]
+
+
Evaluating eval...:  60%|██████    | 1141/1900 [22:57<15:36,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1142/1900 [22:58<15:21,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1143/1900 [22:59<15:10,  1.20s/it]
+
+
Evaluating eval...:  60%|██████    | 1144/1900 [23:01<15:15,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1145/1900 [23:02<15:09,  1.20s/it]
+
+
Evaluating eval...:  60%|██████    | 1146/1900 [23:03<15:11,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1147/1900 [23:04<15:17,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1148/1900 [23:06<15:12,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1149/1900 [23:07<14:54,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1150/1900 [23:08<15:01,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1151/1900 [23:09<14:50,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1152/1900 [23:10<14:48,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1153/1900 [23:12<14:54,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1154/1900 [23:13<14:49,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1155/1900 [23:14<14:46,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1156/1900 [23:15<14:39,  1.18s/it]
+
+
Evaluating eval...:  61%|██████    | 1157/1900 [23:16<14:49,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1158/1900 [23:18<15:08,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1159/1900 [23:19<14:59,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1160/1900 [23:20<14:56,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1161/1900 [23:21<14:56,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1162/1900 [23:22<14:42,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1163/1900 [23:23<14:37,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1164/1900 [23:25<14:28,  1.18s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1165/1900 [23:26<14:27,  1.18s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1166/1900 [23:27<14:32,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1167/1900 [23:28<14:39,  1.20s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1168/1900 [23:29<14:41,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1169/1900 [23:31<14:34,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1170/1900 [23:32<14:45,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1171/1900 [23:33<14:42,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1172/1900 [23:34<14:46,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1173/1900 [23:36<14:37,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1174/1900 [23:37<14:32,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1175/1900 [23:38<14:56,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1176/1900 [23:39<14:58,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1177/1900 [23:40<14:39,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1178/1900 [23:42<14:24,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1179/1900 [23:43<14:21,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1180/1900 [23:44<14:30,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1181/1900 [23:45<14:16,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1182/1900 [23:46<14:23,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1183/1900 [23:48<14:24,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1184/1900 [23:49<14:33,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1185/1900 [23:50<14:30,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1186/1900 [23:51<14:41,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1187/1900 [23:53<14:28,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1188/1900 [23:54<14:24,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1189/1900 [23:55<14:22,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1190/1900 [23:56<14:08,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1191/1900 [23:57<14:21,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1192/1900 [23:59<14:40,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1193/1900 [24:00<14:26,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1194/1900 [24:01<14:35,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1195/1900 [24:02<14:25,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1196/1900 [24:04<14:18,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1197/1900 [24:05<14:14,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1198/1900 [24:06<14:17,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1199/1900 [24:07<14:42,  1.26s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1200/1900 [24:09<14:34,  1.25s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1201/1900 [24:10<14:26,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1202/1900 [24:11<14:05,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1203/1900 [24:12<14:11,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1204/1900 [24:13<14:12,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1205/1900 [24:15<14:03,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1206/1900 [24:16<14:08,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1207/1900 [24:17<13:51,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1208/1900 [24:18<13:48,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1209/1900 [24:19<13:35,  1.18s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1210/1900 [24:21<13:51,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1211/1900 [24:22<13:52,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1212/1900 [24:23<13:46,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1213/1900 [24:24<13:43,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1214/1900 [24:25<13:39,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1215/1900 [24:27<13:32,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1216/1900 [24:28<13:41,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1217/1900 [24:29<13:51,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1218/1900 [24:30<14:00,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1219/1900 [24:31<13:43,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1220/1900 [24:33<13:42,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1221/1900 [24:34<13:38,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1222/1900 [24:35<13:27,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1223/1900 [24:36<13:27,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1224/1900 [24:37<13:24,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1225/1900 [24:39<13:33,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1226/1900 [24:40<13:32,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1227/1900 [24:41<13:32,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1228/1900 [24:42<13:21,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1229/1900 [24:43<13:23,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1230/1900 [24:45<13:29,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1231/1900 [24:46<13:31,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1232/1900 [24:47<13:31,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1233/1900 [24:48<13:28,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1234/1900 [24:49<13:27,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1235/1900 [24:51<13:30,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1236/1900 [24:52<13:18,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1237/1900 [24:53<13:10,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1238/1900 [24:54<13:06,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1239/1900 [24:55<13:13,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1240/1900 [24:57<13:33,  1.23s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1241/1900 [24:58<13:22,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1242/1900 [24:59<13:14,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1243/1900 [25:00<13:23,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1244/1900 [25:02<13:08,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1245/1900 [25:03<12:57,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1246/1900 [25:04<12:58,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1247/1900 [25:05<12:51,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1248/1900 [25:06<12:49,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1249/1900 [25:07<12:59,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1250/1900 [25:09<12:55,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1251/1900 [25:10<12:47,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1252/1900 [25:11<12:44,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1253/1900 [25:12<12:53,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1254/1900 [25:13<12:58,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1255/1900 [25:15<13:09,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1256/1900 [25:16<13:14,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1257/1900 [25:17<12:55,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1258/1900 [25:18<13:07,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1259/1900 [25:20<12:59,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1260/1900 [25:21<12:54,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1261/1900 [25:22<12:54,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1262/1900 [25:23<12:45,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1263/1900 [25:24<12:46,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1264/1900 [25:26<12:46,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1265/1900 [25:27<12:49,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1266/1900 [25:28<12:51,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1267/1900 [25:29<12:46,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1268/1900 [25:30<12:43,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1269/1900 [25:32<12:47,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1270/1900 [25:33<12:48,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1271/1900 [25:34<12:50,  1.23s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1272/1900 [25:35<12:39,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1273/1900 [25:37<12:38,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1274/1900 [25:38<12:39,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1275/1900 [25:39<12:35,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1276/1900 [25:40<12:40,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1277/1900 [25:41<12:38,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1278/1900 [25:43<12:28,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1279/1900 [25:44<12:27,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1280/1900 [25:45<12:23,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1281/1900 [25:46<12:13,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1282/1900 [25:47<12:08,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1283/1900 [25:48<12:09,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1284/1900 [25:50<12:11,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1285/1900 [25:51<12:18,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1286/1900 [25:52<12:20,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1287/1900 [25:53<12:33,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1288/1900 [25:55<12:34,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1289/1900 [25:56<12:19,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1290/1900 [25:57<12:09,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1291/1900 [25:58<12:04,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1292/1900 [25:59<12:11,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1293/1900 [26:01<12:11,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1294/1900 [26:02<12:15,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1295/1900 [26:03<12:08,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1296/1900 [26:04<12:12,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1297/1900 [26:05<12:03,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1298/1900 [26:07<12:08,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1299/1900 [26:08<12:13,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1300/1900 [26:09<12:16,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1301/1900 [26:10<12:19,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1302/1900 [26:12<12:09,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1303/1900 [26:13<12:02,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1304/1900 [26:14<12:03,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1305/1900 [26:15<12:03,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1306/1900 [26:16<12:01,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1307/1900 [26:18<11:51,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1308/1900 [26:19<11:47,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1309/1900 [26:20<11:46,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1310/1900 [26:21<11:45,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1311/1900 [26:22<11:50,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1312/1900 [26:24<11:47,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1313/1900 [26:25<11:45,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1314/1900 [26:26<11:36,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1315/1900 [26:27<11:34,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1316/1900 [26:28<11:42,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1317/1900 [26:30<11:41,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1318/1900 [26:31<11:52,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1319/1900 [26:32<11:45,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1320/1900 [26:33<11:35,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1321/1900 [26:34<11:49,  1.23s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1322/1900 [26:36<11:47,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1323/1900 [26:37<11:50,  1.23s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1324/1900 [26:38<11:42,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1325/1900 [26:39<11:31,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1326/1900 [26:41<11:40,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1327/1900 [26:42<11:38,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1328/1900 [26:43<12:00,  1.26s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1329/1900 [26:44<11:44,  1.23s/it]
+
+
Evaluating eval...:  70%|███████   | 1330/1900 [26:46<11:43,  1.23s/it]
+
+
Evaluating eval...:  70%|███████   | 1331/1900 [26:47<11:34,  1.22s/it]
+
+
Evaluating eval...:  70%|███████   | 1332/1900 [26:48<11:26,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1333/1900 [26:49<11:23,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1334/1900 [26:50<11:27,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1335/1900 [26:52<11:22,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1336/1900 [26:53<11:21,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1337/1900 [26:54<11:25,  1.22s/it]
+
+
Evaluating eval...:  70%|███████   | 1338/1900 [26:55<11:14,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1339/1900 [26:56<11:09,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1340/1900 [26:58<11:14,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1341/1900 [26:59<11:04,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1342/1900 [27:00<11:05,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1343/1900 [27:01<11:00,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1344/1900 [27:02<10:56,  1.18s/it]
+
+
Evaluating eval...:  71%|███████   | 1345/1900 [27:03<11:06,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1346/1900 [27:05<11:28,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1347/1900 [27:06<11:20,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1348/1900 [27:07<11:05,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1349/1900 [27:09<11:29,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1350/1900 [27:10<11:21,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1351/1900 [27:11<11:23,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1352/1900 [27:12<11:22,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1353/1900 [27:14<11:22,  1.25s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1354/1900 [27:15<11:15,  1.24s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1355/1900 [27:16<11:04,  1.22s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1356/1900 [27:17<11:02,  1.22s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1357/1900 [27:18<10:55,  1.21s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1358/1900 [27:19<10:49,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1359/1900 [27:21<10:53,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1360/1900 [27:22<10:45,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1361/1900 [27:23<10:55,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1362/1900 [27:24<10:44,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1363/1900 [27:26<10:56,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1364/1900 [27:27<10:45,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1365/1900 [27:28<10:44,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1366/1900 [27:29<10:38,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1367/1900 [27:30<10:41,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1368/1900 [27:32<10:46,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1369/1900 [27:33<10:42,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1370/1900 [27:34<10:44,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1371/1900 [27:35<10:39,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1372/1900 [27:36<10:33,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1373/1900 [27:38<10:28,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1374/1900 [27:39<10:25,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1375/1900 [27:40<10:26,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1376/1900 [27:41<10:26,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1377/1900 [27:42<10:26,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1378/1900 [27:43<10:17,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1379/1900 [27:45<10:21,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1380/1900 [27:46<10:27,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1381/1900 [27:47<10:32,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1382/1900 [27:48<10:27,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1383/1900 [27:50<10:29,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1384/1900 [27:51<10:24,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1385/1900 [27:52<10:22,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1386/1900 [27:53<10:24,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1387/1900 [27:54<10:13,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1388/1900 [27:56<10:17,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1389/1900 [27:57<10:14,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1390/1900 [27:58<10:18,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1391/1900 [27:59<10:16,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1392/1900 [28:00<10:10,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1393/1900 [28:02<10:04,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1394/1900 [28:03<10:13,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1395/1900 [28:04<10:09,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1396/1900 [28:05<10:04,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1397/1900 [28:06<10:01,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1398/1900 [28:08<10:15,  1.23s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1399/1900 [28:09<10:10,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1400/1900 [28:10<10:01,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1401/1900 [28:11<10:06,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1402/1900 [28:12<09:53,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1403/1900 [28:14<09:47,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1404/1900 [28:15<09:41,  1.17s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1405/1900 [28:16<09:37,  1.17s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1406/1900 [28:17<09:42,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1407/1900 [28:18<09:53,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1408/1900 [28:20<09:59,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1409/1900 [28:21<09:52,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1410/1900 [28:22<09:46,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1411/1900 [28:23<09:46,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1412/1900 [28:24<09:44,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1413/1900 [28:26<09:43,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1414/1900 [28:27<09:45,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1415/1900 [28:28<09:39,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1416/1900 [28:29<09:33,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1417/1900 [28:30<09:34,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1418/1900 [28:32<09:28,  1.18s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1419/1900 [28:33<09:53,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1420/1900 [28:34<09:48,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1421/1900 [28:35<09:41,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1422/1900 [28:37<09:48,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1423/1900 [28:38<09:38,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1424/1900 [28:39<09:42,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1425/1900 [28:40<09:39,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1426/1900 [28:41<09:34,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1427/1900 [28:43<09:34,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1428/1900 [28:44<09:38,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1429/1900 [28:45<09:39,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1430/1900 [28:46<09:37,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1431/1900 [28:48<09:38,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1432/1900 [28:49<10:12,  1.31s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1433/1900 [28:50<09:55,  1.28s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1434/1900 [28:51<09:41,  1.25s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1435/1900 [28:53<09:34,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1436/1900 [28:54<09:35,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1437/1900 [28:55<09:28,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1438/1900 [28:56<09:26,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1439/1900 [28:57<09:19,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1440/1900 [28:59<09:26,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1441/1900 [29:00<09:19,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1442/1900 [29:01<09:23,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1443/1900 [29:02<09:26,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1444/1900 [29:04<09:13,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1445/1900 [29:05<09:11,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1446/1900 [29:06<09:08,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1447/1900 [29:07<09:00,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1448/1900 [29:08<09:00,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1449/1900 [29:10<08:59,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1450/1900 [29:11<09:09,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1451/1900 [29:12<09:14,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1452/1900 [29:13<09:04,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1453/1900 [29:15<09:00,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1454/1900 [29:16<09:11,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1455/1900 [29:17<09:04,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1456/1900 [29:18<09:03,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1457/1900 [29:19<09:01,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1458/1900 [29:21<09:02,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1459/1900 [29:22<08:53,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1460/1900 [29:23<08:46,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1461/1900 [29:24<08:46,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1462/1900 [29:25<08:45,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1463/1900 [29:27<08:43,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1464/1900 [29:28<08:47,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1465/1900 [29:29<08:43,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1466/1900 [29:30<08:58,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1467/1900 [29:32<08:47,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1468/1900 [29:33<09:02,  1.26s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1469/1900 [29:34<08:56,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1470/1900 [29:35<08:43,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1471/1900 [29:36<08:44,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1472/1900 [29:38<08:35,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1473/1900 [29:39<08:36,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1474/1900 [29:40<08:32,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1475/1900 [29:41<08:38,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1476/1900 [29:43<08:37,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1477/1900 [29:44<08:37,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1478/1900 [29:45<08:35,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1479/1900 [29:46<08:51,  1.26s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1480/1900 [29:48<08:37,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1481/1900 [29:49<08:36,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1482/1900 [29:50<08:28,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1483/1900 [29:51<08:19,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1484/1900 [29:52<08:15,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1485/1900 [29:53<08:18,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1486/1900 [29:55<08:16,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1487/1900 [29:56<08:24,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1488/1900 [29:57<08:14,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1489/1900 [29:58<08:09,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1490/1900 [29:59<08:10,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1491/1900 [30:01<08:04,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1492/1900 [30:02<08:08,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1493/1900 [30:03<08:12,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1494/1900 [30:04<08:04,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1495/1900 [30:05<08:01,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1496/1900 [30:07<07:56,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1497/1900 [30:08<07:56,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1498/1900 [30:09<08:06,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1499/1900 [30:10<08:05,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1500/1900 [30:11<08:00,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1501/1900 [30:13<07:56,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1502/1900 [30:14<07:56,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1503/1900 [30:15<07:53,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1504/1900 [30:16<07:47,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1505/1900 [30:17<07:49,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1506/1900 [30:19<07:53,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1507/1900 [30:20<07:53,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1508/1900 [30:21<07:53,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1509/1900 [30:22<07:56,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1510/1900 [30:23<07:51,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1511/1900 [30:25<07:48,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1512/1900 [30:26<07:53,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1513/1900 [30:27<07:57,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1514/1900 [30:28<07:54,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1515/1900 [30:30<07:58,  1.24s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1516/1900 [30:31<07:58,  1.25s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1517/1900 [30:32<07:46,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1518/1900 [30:33<07:36,  1.19s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1519/1900 [30:34<07:29,  1.18s/it]
+
+
Evaluating eval...:  80%|████████  | 1520/1900 [30:36<07:33,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1521/1900 [30:37<07:35,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1522/1900 [30:38<07:28,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1523/1900 [30:39<07:28,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1524/1900 [30:40<07:33,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1525/1900 [30:42<07:34,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1526/1900 [30:43<07:26,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1527/1900 [30:44<07:25,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1528/1900 [30:45<07:27,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1529/1900 [30:46<07:23,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1530/1900 [30:48<07:25,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1531/1900 [30:49<07:25,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1532/1900 [30:50<07:31,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1533/1900 [30:51<07:25,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1534/1900 [30:52<07:22,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1535/1900 [30:54<07:14,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1536/1900 [30:55<07:09,  1.18s/it]
+
+
Evaluating eval...:  81%|████████  | 1537/1900 [30:56<07:11,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1538/1900 [30:57<07:09,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1539/1900 [30:58<07:10,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1540/1900 [31:00<07:09,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1541/1900 [31:01<07:18,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1542/1900 [31:02<07:16,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1543/1900 [31:03<07:14,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1544/1900 [31:04<07:13,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1545/1900 [31:06<07:08,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1546/1900 [31:07<07:06,  1.20s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1547/1900 [31:08<07:11,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1548/1900 [31:09<07:06,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1549/1900 [31:10<07:00,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1550/1900 [31:12<07:10,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1551/1900 [31:13<07:10,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1552/1900 [31:14<07:02,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1553/1900 [31:15<06:59,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1554/1900 [31:17<06:56,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1555/1900 [31:18<06:53,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1556/1900 [31:19<07:01,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1557/1900 [31:20<06:57,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1558/1900 [31:22<07:10,  1.26s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1559/1900 [31:23<07:08,  1.26s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1560/1900 [31:24<06:58,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1561/1900 [31:25<07:00,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1562/1900 [31:27<07:02,  1.25s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1563/1900 [31:28<07:00,  1.25s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1564/1900 [31:29<06:52,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1565/1900 [31:30<06:46,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1566/1900 [31:31<06:48,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1567/1900 [31:33<06:44,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1568/1900 [31:34<07:02,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1569/1900 [31:35<07:03,  1.28s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1570/1900 [31:37<06:57,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1571/1900 [31:38<06:49,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1572/1900 [31:39<06:46,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1573/1900 [31:40<06:38,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1574/1900 [31:41<06:33,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1575/1900 [31:43<06:31,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1576/1900 [31:44<06:29,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1577/1900 [31:45<06:32,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1578/1900 [31:46<06:30,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1579/1900 [31:47<06:23,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1580/1900 [31:49<06:31,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1581/1900 [31:50<06:41,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1582/1900 [31:51<06:38,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1583/1900 [31:52<06:33,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1584/1900 [31:54<06:42,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1585/1900 [31:55<06:41,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1586/1900 [31:56<06:35,  1.26s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1587/1900 [31:57<06:23,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1588/1900 [31:59<06:15,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1589/1900 [32:00<06:18,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1590/1900 [32:01<06:17,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1591/1900 [32:02<06:21,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1592/1900 [32:03<06:12,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1593/1900 [32:05<06:11,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1594/1900 [32:06<06:17,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1595/1900 [32:07<06:17,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1596/1900 [32:08<06:18,  1.25s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1597/1900 [32:10<06:14,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1598/1900 [32:11<06:05,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1599/1900 [32:12<05:58,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1600/1900 [32:13<05:51,  1.17s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1601/1900 [32:14<05:51,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1602/1900 [32:16<05:54,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1603/1900 [32:17<05:54,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1604/1900 [32:18<05:57,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1605/1900 [32:19<05:50,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1606/1900 [32:20<05:49,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1607/1900 [32:22<05:51,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1608/1900 [32:23<05:53,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1609/1900 [32:24<05:57,  1.23s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1610/1900 [32:25<05:53,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1611/1900 [32:26<05:47,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1612/1900 [32:28<05:43,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1613/1900 [32:29<05:39,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1614/1900 [32:30<05:42,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1615/1900 [32:31<05:39,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1616/1900 [32:32<05:38,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1617/1900 [32:34<05:40,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1618/1900 [32:35<05:42,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1619/1900 [32:36<05:40,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1620/1900 [32:37<05:39,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1621/1900 [32:38<05:33,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1622/1900 [32:40<05:28,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1623/1900 [32:41<05:29,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1624/1900 [32:42<05:26,  1.18s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1625/1900 [32:43<05:33,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1626/1900 [32:44<05:41,  1.25s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1627/1900 [32:46<05:47,  1.27s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1628/1900 [32:47<05:46,  1.27s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1629/1900 [32:48<05:44,  1.27s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1630/1900 [32:50<05:39,  1.26s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1631/1900 [32:51<05:48,  1.29s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1632/1900 [32:52<05:38,  1.26s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1633/1900 [32:53<05:36,  1.26s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1634/1900 [32:55<05:27,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1635/1900 [32:56<05:21,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1636/1900 [32:57<05:19,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1637/1900 [32:58<05:26,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1638/1900 [32:59<05:18,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1639/1900 [33:01<05:18,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1640/1900 [33:02<05:14,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1641/1900 [33:03<05:12,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1642/1900 [33:04<05:10,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1643/1900 [33:05<05:11,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1644/1900 [33:07<05:05,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1645/1900 [33:08<05:01,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1646/1900 [33:09<05:04,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1647/1900 [33:10<05:04,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1648/1900 [33:11<05:04,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1649/1900 [33:13<04:59,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1650/1900 [33:14<05:01,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1651/1900 [33:15<04:55,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1652/1900 [33:16<04:54,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1653/1900 [33:17<04:53,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1654/1900 [33:19<04:52,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1655/1900 [33:20<04:56,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1656/1900 [33:21<04:57,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1657/1900 [33:22<04:56,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1658/1900 [33:23<04:52,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1659/1900 [33:25<05:00,  1.25s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1660/1900 [33:26<04:58,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1661/1900 [33:27<04:54,  1.23s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1662/1900 [33:28<04:49,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1663/1900 [33:30<04:43,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1664/1900 [33:31<04:45,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1665/1900 [33:32<04:41,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1666/1900 [33:33<04:52,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1667/1900 [33:35<04:47,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1668/1900 [33:36<04:42,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1669/1900 [33:37<04:40,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1670/1900 [33:38<04:44,  1.24s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1671/1900 [33:39<04:40,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1672/1900 [33:41<04:40,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1673/1900 [33:42<04:39,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1674/1900 [33:43<04:42,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1675/1900 [33:44<04:39,  1.24s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1676/1900 [33:46<04:36,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1677/1900 [33:47<04:30,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1678/1900 [33:48<04:26,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1679/1900 [33:49<04:25,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1680/1900 [33:50<04:24,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1681/1900 [33:52<04:26,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1682/1900 [33:53<04:22,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1683/1900 [33:55<05:42,  1.58s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1684/1900 [33:56<05:15,  1.46s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1685/1900 [33:58<04:54,  1.37s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1686/1900 [33:59<04:42,  1.32s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1687/1900 [34:00<04:35,  1.29s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1688/1900 [34:01<04:26,  1.26s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1689/1900 [34:02<04:19,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1690/1900 [34:04<04:17,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1691/1900 [34:05<04:18,  1.24s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1692/1900 [34:06<04:13,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1693/1900 [34:07<04:16,  1.24s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1694/1900 [34:09<04:13,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1695/1900 [34:10<04:08,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1696/1900 [34:11<04:05,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1697/1900 [34:12<04:07,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1698/1900 [34:13<04:05,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1699/1900 [34:15<04:02,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1700/1900 [34:16<04:02,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1701/1900 [34:17<04:04,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1702/1900 [34:18<04:02,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1703/1900 [34:19<03:59,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1704/1900 [34:21<03:56,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1705/1900 [34:22<03:51,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1706/1900 [34:23<03:52,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1707/1900 [34:24<03:50,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1708/1900 [34:25<03:53,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1709/1900 [34:27<03:51,  1.21s/it]
+
+
Evaluating eval...:  90%|█████████ | 1710/1900 [34:28<03:50,  1.21s/it]
+
+
Evaluating eval...:  90%|█████████ | 1711/1900 [34:29<03:46,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1712/1900 [34:30<03:45,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1713/1900 [34:31<03:40,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1714/1900 [34:33<03:37,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1715/1900 [34:34<03:39,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1716/1900 [34:35<03:37,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1717/1900 [34:36<03:45,  1.23s/it]
+
+
Evaluating eval...:  90%|█████████ | 1718/1900 [34:38<03:46,  1.24s/it]
+
+
Evaluating eval...:  90%|█████████ | 1719/1900 [34:39<03:40,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1720/1900 [34:40<03:41,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1721/1900 [34:41<03:38,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1722/1900 [34:42<03:37,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1723/1900 [34:44<03:33,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1724/1900 [34:45<03:35,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1725/1900 [34:46<03:35,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1726/1900 [34:47<03:34,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1727/1900 [34:49<03:36,  1.25s/it]
+
+
Evaluating eval...:  91%|█████████ | 1728/1900 [34:50<03:29,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1729/1900 [34:51<03:25,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1730/1900 [34:52<03:26,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1731/1900 [34:53<03:23,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1732/1900 [34:54<03:19,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████ | 1733/1900 [34:56<03:19,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1734/1900 [34:57<03:16,  1.18s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1735/1900 [34:58<03:16,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1736/1900 [34:59<03:18,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1737/1900 [35:00<03:16,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1738/1900 [35:02<03:13,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1739/1900 [35:03<03:13,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1740/1900 [35:04<03:11,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1741/1900 [35:05<03:12,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1742/1900 [35:06<03:08,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1743/1900 [35:08<03:08,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1744/1900 [35:09<03:07,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1745/1900 [35:10<03:04,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1746/1900 [35:11<03:12,  1.25s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1747/1900 [35:13<03:08,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1748/1900 [35:14<03:05,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1749/1900 [35:15<03:04,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1750/1900 [35:16<03:03,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1751/1900 [35:17<03:02,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1752/1900 [35:19<02:58,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1753/1900 [35:20<02:54,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1754/1900 [35:21<02:53,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1755/1900 [35:22<02:54,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1756/1900 [35:23<02:55,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1757/1900 [35:25<02:55,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1758/1900 [35:26<02:53,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1759/1900 [35:27<02:49,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1760/1900 [35:28<02:45,  1.18s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1761/1900 [35:29<02:44,  1.18s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1762/1900 [35:31<02:42,  1.18s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1763/1900 [35:32<02:41,  1.18s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1764/1900 [35:33<02:43,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1765/1900 [35:34<02:43,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1766/1900 [35:35<02:41,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1767/1900 [35:37<02:39,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1768/1900 [35:38<02:39,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1769/1900 [35:39<02:39,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1770/1900 [35:40<02:44,  1.26s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1771/1900 [35:42<02:40,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1772/1900 [35:43<02:36,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1773/1900 [35:44<02:35,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1774/1900 [35:45<02:32,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1775/1900 [35:46<02:32,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1776/1900 [35:48<02:30,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1777/1900 [35:49<02:27,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1778/1900 [35:50<02:25,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1779/1900 [35:51<02:23,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1780/1900 [35:52<02:21,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1781/1900 [35:54<02:19,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1782/1900 [35:55<02:21,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1783/1900 [35:56<02:21,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1784/1900 [35:57<02:19,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1785/1900 [35:58<02:16,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1786/1900 [36:00<02:14,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1787/1900 [36:01<02:13,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1788/1900 [36:02<02:12,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1789/1900 [36:03<02:10,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1790/1900 [36:04<02:10,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1791/1900 [36:05<02:10,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1792/1900 [36:07<02:08,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1793/1900 [36:08<02:08,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1794/1900 [36:09<02:06,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1795/1900 [36:10<02:04,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1796/1900 [36:11<02:03,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1797/1900 [36:13<02:01,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1798/1900 [36:14<02:04,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1799/1900 [36:15<02:03,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1800/1900 [36:16<01:59,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1801/1900 [36:17<01:57,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1802/1900 [36:19<01:56,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1803/1900 [36:20<01:55,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1804/1900 [36:21<01:54,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1805/1900 [36:22<01:52,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1806/1900 [36:23<01:50,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1807/1900 [36:25<01:49,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1808/1900 [36:26<01:47,  1.17s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1809/1900 [36:27<01:45,  1.16s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1810/1900 [36:28<01:46,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1811/1900 [36:29<01:46,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1812/1900 [36:30<01:45,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1813/1900 [36:32<01:43,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1814/1900 [36:33<01:43,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1815/1900 [36:34<01:41,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1816/1900 [36:35<01:41,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1817/1900 [36:37<01:43,  1.24s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1818/1900 [36:38<01:40,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1819/1900 [36:39<01:37,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1820/1900 [36:40<01:36,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1821/1900 [36:41<01:35,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1822/1900 [36:43<01:33,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1823/1900 [36:44<01:31,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1824/1900 [36:45<01:31,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1825/1900 [36:46<01:30,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1826/1900 [36:47<01:29,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1827/1900 [36:49<01:29,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1828/1900 [36:50<01:29,  1.25s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1829/1900 [36:51<01:29,  1.26s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1830/1900 [36:52<01:26,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1831/1900 [36:54<01:23,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1832/1900 [36:55<01:21,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1833/1900 [36:56<01:19,  1.18s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1834/1900 [36:57<01:19,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1835/1900 [36:58<01:17,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1836/1900 [37:00<01:16,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1837/1900 [37:01<01:16,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1838/1900 [37:02<01:14,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1839/1900 [37:03<01:12,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1840/1900 [37:04<01:13,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1841/1900 [37:06<01:11,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1842/1900 [37:07<01:10,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1843/1900 [37:08<01:08,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1844/1900 [37:09<01:07,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1845/1900 [37:10<01:05,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1846/1900 [37:12<01:04,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1847/1900 [37:13<01:03,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1848/1900 [37:14<01:02,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1849/1900 [37:15<01:01,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1850/1900 [37:16<00:59,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1851/1900 [37:18<00:59,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1852/1900 [37:19<00:57,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1853/1900 [37:20<00:56,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1854/1900 [37:21<00:54,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1855/1900 [37:22<00:54,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1856/1900 [37:24<00:52,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1857/1900 [37:25<00:51,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1858/1900 [37:26<00:51,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1859/1900 [37:27<00:49,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1860/1900 [37:28<00:48,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1861/1900 [37:30<00:46,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1862/1900 [37:31<00:45,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1863/1900 [37:32<00:44,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1864/1900 [37:33<00:42,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1865/1900 [37:34<00:41,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1866/1900 [37:36<00:40,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1867/1900 [37:37<00:40,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1868/1900 [37:38<00:38,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1869/1900 [37:39<00:38,  1.25s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1870/1900 [37:41<00:37,  1.24s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1871/1900 [37:42<00:36,  1.27s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1872/1900 [37:43<00:35,  1.26s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1873/1900 [37:44<00:33,  1.25s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1874/1900 [37:46<00:32,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1875/1900 [37:47<00:31,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1876/1900 [37:48<00:29,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1877/1900 [37:49<00:28,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1878/1900 [37:51<00:26,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1879/1900 [37:52<00:25,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1880/1900 [37:53<00:23,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1881/1900 [37:54<00:22,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1882/1900 [37:55<00:21,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1883/1900 [37:57<00:21,  1.25s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1884/1900 [37:58<00:20,  1.26s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1885/1900 [37:59<00:18,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1886/1900 [38:00<00:17,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1887/1900 [38:01<00:15,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1888/1900 [38:03<00:14,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1889/1900 [38:04<00:13,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1890/1900 [38:05<00:11,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1891/1900 [38:06<00:10,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1892/1900 [38:07<00:09,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1893/1900 [38:09<00:08,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1894/1900 [38:10<00:07,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1895/1900 [38:11<00:05,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1896/1900 [38:12<00:04,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1897/1900 [38:13<00:03,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1898/1900 [38:14<00:02,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1899/1900 [38:16<00:01,  1.20s/it]
+
+
Evaluating eval...: 100%|██████████| 1900/1900 [38:17<00:00,  1.30s/it]
Evaluating eval...: 100%|██████████| 1900/1900 [38:17<00:00,  1.21s/it]
+Eval results for step (15000 / 100000 | Eval Loss: 1.2628703117370605 | Eval wer: 31.11470571694086 | Eval wer_ortho: 34.41388817370408 |)
+
                                                                             
Eval results for step (15000 / 100000 | Eval Loss: 1.2628703117370605 | Eval wer: 31.11470571694086 | Eval wer_ortho: 34.41388817370408 |)
+
Train steps ... :  15%|█▌        | 15000/100000 [4:39:24<13:47:52,  1.71it/s]
Train steps ... :  15%|█▌        | 15001/100000 [4:39:24<17872:34:03, 756.96s/it]
Train steps ... :  15%|█▌        | 15002/100000 [4:39:25<12514:47:08, 530.05s/it]
Train steps ... :  15%|█▌        | 15003/100000 [4:39:25<8764:22:32, 371.21s/it] 
Train steps ... :  15%|█▌        | 15004/100000 [4:39:26<6139:06:54, 260.02s/it]
Train steps ... :  15%|█▌        | 15005/100000 [4:39:27<4301:27:45, 182.19s/it]
Train steps ... :  15%|█▌        | 15006/100000 [4:39:27<3015:06:57, 127.71s/it]
Train steps ... :  15%|█▌        | 15007/100000 [4:39:28<2114:41:52, 89.57s/it] 
Train steps ... :  15%|█▌        | 15008/100000 [4:39:28<1484:23:51, 62.87s/it]
Train steps ... :  15%|█▌        | 15009/100000 [4:39:29<1043:12:36, 44.19s/it]
Train steps ... :  15%|█▌        | 15010/100000 [4:39:30<734:22:16, 31.11s/it] 
Train steps ... :  15%|█▌        | 15011/100000 [4:39:30<518:11:23, 21.95s/it]
Train steps ... :  15%|█▌        | 15012/100000 [4:39:31<366:50:55, 15.54s/it]
Train steps ... :  15%|█▌        | 15013/100000 [4:39:31<260:55:01, 11.05s/it]
Train steps ... :  15%|█▌        | 15014/100000 [4:39:32<186:46:24,  7.91s/it]
Train steps ... :  15%|█▌        | 15015/100000 [4:39:32<134:52:18,  5.71s/it]
Train steps ... :  15%|█▌        | 15016/100000 [4:39:33<98:33:11,  4.17s/it] 
Train steps ... :  15%|█▌        | 15017/100000 [4:39:34<73:08:14,  3.10s/it]
Train steps ... :  15%|█▌        | 15018/100000 [4:39:34<55:19:22,  2.34s/it]
Train steps ... :  15%|█▌        | 15019/100000 [4:39:35<42:50:30,  1.81s/it]
Train steps ... :  15%|█▌        | 15020/100000 [4:39:35<34:07:00,  1.45s/it]
Train steps ... :  15%|█▌        | 15021/100000 [4:39:36<28:01:12,  1.19s/it]
Train steps ... :  15%|█▌        | 15022/100000 [4:39:37<23:44:55,  1.01s/it]
Train steps ... :  15%|█▌        | 15023/100000 [4:39:37<20:45:07,  1.14it/s]
Train steps ... :  15%|█▌        | 15024/100000 [4:39:38<18:39:00,  1.27it/s]
Train steps ... :  15%|█▌        | 15025/100000 [4:39:38<17:11:09,  1.37it/s]Step... (15025 / 100000 | Loss: 0.9627807140350342, Learning Rate: 8.540201005025126e-05)
+
                                                                             
Step... (15025 / 100000 | Loss: 1.1613550186157227, Learning Rate: 8.540201005025126e-05)
+
Train steps ... :  15%|█▌        | 15025/100000 [4:39:39<17:11:09,  1.37it/s]
Train steps ... :  15%|█▌        | 15026/100000 [4:39:39<16:09:27,  1.46it/s]
Train steps ... :  15%|█▌        | 15027/100000 [4:39:39<15:25:58,  1.53it/s]
Train steps ... :  15%|█▌        | 15028/100000 [4:39:40<14:55:39,  1.58it/s]
Train steps ... :  15%|█▌        | 15029/100000 [4:39:41<14:34:41,  1.62it/s]
Train steps ... :  15%|█▌        | 15030/100000 [4:39:41<14:19:45,  1.65it/s]
Train steps ... :  15%|█▌        | 15031/100000 [4:39:42<14:09:56,  1.67it/s]
Train steps ... :  15%|█▌        | 15032/100000 [4:39:42<14:02:47,  1.68it/s]
Train steps ... :  15%|█▌        | 15033/100000 [4:39:43<13:57:32,  1.69it/s]
Train steps ... :  15%|█▌        | 15034/100000 [4:39:44<13:54:14,  1.70it/s]
Train steps ... :  15%|█▌        | 15035/100000 [4:39:44<13:51:06,  1.70it/s]
Train steps ... :  15%|█▌        | 15036/100000 [4:39:45<13:49:44,  1.71it/s]
Train steps ... :  15%|█▌        | 15037/100000 [4:39:45<13:49:49,  1.71it/s]
Train steps ... :  15%|█▌        | 15038/100000 [4:39:46<13:48:09,  1.71it/s]
Train steps ... :  15%|█▌        | 15039/100000 [4:39:46<13:48:21,  1.71it/s]
Train steps ... :  15%|█▌        | 15040/100000 [4:39:47<13:47:17,  1.71it/s]
Train steps ... :  15%|█▌        | 15041/100000 [4:39:48<13:46:54,  1.71it/s]
Train steps ... :  15%|█▌        | 15042/100000 [4:39:48<13:46:17,  1.71it/s]
Train steps ... :  15%|█▌        | 15043/100000 [4:39:49<13:47:14,  1.71it/s]
Train steps ... :  15%|█▌        | 15044/100000 [4:39:49<13:46:15,  1.71it/s]
Train steps ... :  15%|█▌        | 15045/100000 [4:39:50<13:46:22,  1.71it/s]
Train steps ... :  15%|█▌        | 15046/100000 [4:39:51<13:45:48,  1.71it/s]
Train steps ... :  15%|█▌        | 15047/100000 [4:39:51<13:45:20,  1.72it/s]
Train steps ... :  15%|█▌        | 15048/100000 [4:39:52<13:46:52,  1.71it/s]
Train steps ... :  15%|█▌        | 15049/100000 [4:39:52<13:47:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15050/100000 [4:39:53<13:46:47,  1.71it/s]Step... (15050 / 100000 | Loss: 0.940180778503418, Learning Rate: 8.537688442211056e-05)
+
                                                                             
Step... (15050 / 100000 | Loss: 1.0189616680145264, Learning Rate: 8.537688442211056e-05)
+
Train steps ... :  15%|█▌        | 15050/100000 [4:39:53<13:46:47,  1.71it/s]
Train steps ... :  15%|█▌        | 15051/100000 [4:39:53<13:48:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15052/100000 [4:39:54<13:47:19,  1.71it/s]
Train steps ... :  15%|█▌        | 15053/100000 [4:39:55<13:48:07,  1.71it/s]
Train steps ... :  15%|█▌        | 15054/100000 [4:39:55<13:49:31,  1.71it/s]
Train steps ... :  15%|█▌        | 15055/100000 [4:39:56<13:48:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15056/100000 [4:39:56<13:46:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15057/100000 [4:39:57<13:46:26,  1.71it/s]
Train steps ... :  15%|█▌        | 15058/100000 [4:39:58<13:45:59,  1.71it/s]
Train steps ... :  15%|█▌        | 15059/100000 [4:39:58<13:45:33,  1.71it/s]
Train steps ... :  15%|█▌        | 15060/100000 [4:39:59<13:45:51,  1.71it/s]
Train steps ... :  15%|█▌        | 15061/100000 [4:39:59<13:45:43,  1.71it/s]
Train steps ... :  15%|█▌        | 15062/100000 [4:40:00<13:45:43,  1.71it/s]
Train steps ... :  15%|█▌        | 15063/100000 [4:40:00<13:45:15,  1.72it/s]
Train steps ... :  15%|█▌        | 15064/100000 [4:40:01<13:45:21,  1.72it/s]
Train steps ... :  15%|█▌        | 15065/100000 [4:40:02<13:44:35,  1.72it/s]
Train steps ... :  15%|█▌        | 15066/100000 [4:40:02<13:45:49,  1.71it/s]
Train steps ... :  15%|█▌        | 15067/100000 [4:40:03<13:45:28,  1.71it/s]
Train steps ... :  15%|█▌        | 15068/100000 [4:40:03<13:45:53,  1.71it/s]
Train steps ... :  15%|█▌        | 15069/100000 [4:40:04<13:46:28,  1.71it/s]
Train steps ... :  15%|█▌        | 15070/100000 [4:40:05<13:47:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15071/100000 [4:40:05<13:46:47,  1.71it/s]
Train steps ... :  15%|█▌        | 15072/100000 [4:40:06<13:45:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15073/100000 [4:40:06<13:45:32,  1.71it/s]
Train steps ... :  15%|█▌        | 15074/100000 [4:40:07<13:45:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15075/100000 [4:40:07<13:44:43,  1.72it/s]Step... (15075 / 100000 | Loss: 0.9312953948974609, Learning Rate: 8.535175879396985e-05)
+
                                                                             
Step... (15075 / 100000 | Loss: 1.3161377906799316, Learning Rate: 8.535175879396985e-05)
+
Train steps ... :  15%|█▌        | 15075/100000 [4:40:08<13:44:43,  1.72it/s]
Train steps ... :  15%|█▌        | 15076/100000 [4:40:08<13:44:27,  1.72it/s]
Train steps ... :  15%|█▌        | 15077/100000 [4:40:09<13:44:20,  1.72it/s]
Train steps ... :  15%|█▌        | 15078/100000 [4:40:09<13:44:18,  1.72it/s]
Train steps ... :  15%|█▌        | 15079/100000 [4:40:10<13:44:56,  1.72it/s]
Train steps ... :  15%|█▌        | 15080/100000 [4:40:10<13:44:51,  1.72it/s]
Train steps ... :  15%|█▌        | 15081/100000 [4:40:11<13:44:40,  1.72it/s]
Train steps ... :  15%|█▌        | 15082/100000 [4:40:12<13:44:43,  1.72it/s]
Train steps ... :  15%|█▌        | 15083/100000 [4:40:12<13:44:32,  1.72it/s]
Train steps ... :  15%|█▌        | 15084/100000 [4:40:13<13:45:49,  1.71it/s]
Train steps ... :  15%|█▌        | 15085/100000 [4:40:13<13:45:00,  1.72it/s]
Train steps ... :  15%|█▌        | 15086/100000 [4:40:14<13:46:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15087/100000 [4:40:14<13:46:23,  1.71it/s]
Train steps ... :  15%|█▌        | 15088/100000 [4:40:15<13:46:23,  1.71it/s]
Train steps ... :  15%|█▌        | 15089/100000 [4:40:16<13:46:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15090/100000 [4:40:16<13:45:28,  1.71it/s]
Train steps ... :  15%|█▌        | 15091/100000 [4:40:17<13:45:24,  1.71it/s]
Train steps ... :  15%|█▌        | 15092/100000 [4:40:17<13:44:37,  1.72it/s]
Train steps ... :  15%|█▌        | 15093/100000 [4:40:18<13:45:59,  1.71it/s]
Train steps ... :  15%|█▌        | 15094/100000 [4:40:19<13:45:02,  1.72it/s]
Train steps ... :  15%|█▌        | 15095/100000 [4:40:19<13:44:41,  1.72it/s]
Train steps ... :  15%|█▌        | 15096/100000 [4:40:20<13:44:11,  1.72it/s]
Train steps ... :  15%|█▌        | 15097/100000 [4:40:20<13:45:43,  1.71it/s]
Train steps ... :  15%|█▌        | 15098/100000 [4:40:21<13:45:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15099/100000 [4:40:21<13:45:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15100/100000 [4:40:22<13:44:56,  1.72it/s]Step... (15100 / 100000 | Loss: 1.171054720878601, Learning Rate: 8.532663316582915e-05)
+
                                                                             
Step... (15100 / 100000 | Loss: 1.8729169368743896, Learning Rate: 8.532663316582915e-05)
+
Train steps ... :  15%|█▌        | 15100/100000 [4:40:22<13:44:56,  1.72it/s]
Train steps ... :  15%|█▌        | 15101/100000 [4:40:23<13:45:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15102/100000 [4:40:23<13:44:50,  1.72it/s]
Train steps ... :  15%|█▌        | 15103/100000 [4:40:24<13:45:43,  1.71it/s]
Train steps ... :  15%|█▌        | 15104/100000 [4:40:24<13:45:15,  1.71it/s]
Train steps ... :  15%|█▌        | 15105/100000 [4:40:25<13:46:38,  1.71it/s]
Train steps ... :  15%|█▌        | 15106/100000 [4:40:26<13:46:41,  1.71it/s]
Train steps ... :  15%|█▌        | 15107/100000 [4:40:26<13:48:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15108/100000 [4:40:27<13:46:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15109/100000 [4:40:27<13:45:34,  1.71it/s]
Train steps ... :  15%|█▌        | 15110/100000 [4:40:28<13:45:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15111/100000 [4:40:28<13:45:20,  1.71it/s]
Train steps ... :  15%|█▌        | 15112/100000 [4:40:29<13:46:21,  1.71it/s]
Train steps ... :  15%|█▌        | 15113/100000 [4:40:30<13:47:13,  1.71it/s]
Train steps ... :  15%|█▌        | 15114/100000 [4:40:30<13:48:34,  1.71it/s]
Train steps ... :  15%|█▌        | 15115/100000 [4:40:31<13:47:14,  1.71it/s]
Train steps ... :  15%|█▌        | 15116/100000 [4:40:31<13:46:46,  1.71it/s]
Train steps ... :  15%|█▌        | 15117/100000 [4:40:32<13:46:17,  1.71it/s]
Train steps ... :  15%|█▌        | 15118/100000 [4:40:33<13:45:51,  1.71it/s]
Train steps ... :  15%|█▌        | 15119/100000 [4:40:33<13:46:28,  1.71it/s]
Train steps ... :  15%|█▌        | 15120/100000 [4:40:34<13:45:46,  1.71it/s]
Train steps ... :  15%|█▌        | 15121/100000 [4:40:34<13:45:21,  1.71it/s]
Train steps ... :  15%|█▌        | 15122/100000 [4:40:35<13:45:03,  1.71it/s]
Train steps ... :  15%|█▌        | 15123/100000 [4:40:35<13:45:15,  1.71it/s]
Train steps ... :  15%|█▌        | 15124/100000 [4:40:36<13:44:31,  1.72it/s]
Train steps ... :  15%|█▌        | 15125/100000 [4:40:37<13:44:47,  1.72it/s]Step... (15125 / 100000 | Loss: 1.290704607963562, Learning Rate: 8.530150753768845e-05)
+
                                                                             
Step... (15125 / 100000 | Loss: 1.2831604480743408, Learning Rate: 8.530150753768845e-05)
+
Train steps ... :  15%|█▌        | 15125/100000 [4:40:37<13:44:47,  1.72it/s]
Train steps ... :  15%|█▌        | 15126/100000 [4:40:37<13:44:40,  1.72it/s]
Train steps ... :  15%|█▌        | 15127/100000 [4:40:38<13:44:18,  1.72it/s]
Train steps ... :  15%|█▌        | 15128/100000 [4:40:38<13:44:24,  1.72it/s]
Train steps ... :  15%|█▌        | 15129/100000 [4:40:39<13:44:45,  1.72it/s]
Train steps ... :  15%|█▌        | 15130/100000 [4:40:40<13:44:42,  1.72it/s]
Train steps ... :  15%|█▌        | 15131/100000 [4:40:40<13:45:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15132/100000 [4:40:41<13:44:25,  1.72it/s]
Train steps ... :  15%|█▌        | 15133/100000 [4:40:41<13:46:16,  1.71it/s]
Train steps ... :  15%|█▌        | 15134/100000 [4:40:42<13:44:09,  1.72it/s]
Train steps ... :  15%|█▌        | 15135/100000 [4:40:42<13:44:23,  1.72it/s]
Train steps ... :  15%|█▌        | 15136/100000 [4:40:43<13:43:45,  1.72it/s]
Train steps ... :  15%|█▌        | 15137/100000 [4:40:44<13:43:53,  1.72it/s]
Train steps ... :  15%|█▌        | 15138/100000 [4:40:44<13:45:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15139/100000 [4:40:45<13:45:53,  1.71it/s]
Train steps ... :  15%|█▌        | 15140/100000 [4:40:45<13:46:29,  1.71it/s]
Train steps ... :  15%|█▌        | 15141/100000 [4:40:46<13:46:24,  1.71it/s]
Train steps ... :  15%|█▌        | 15142/100000 [4:40:47<13:45:49,  1.71it/s]
Train steps ... :  15%|█▌        | 15143/100000 [4:40:47<13:45:13,  1.71it/s]
Train steps ... :  15%|█▌        | 15144/100000 [4:40:48<13:45:57,  1.71it/s]
Train steps ... :  15%|█▌        | 15145/100000 [4:40:48<13:44:36,  1.72it/s]
Train steps ... :  15%|█▌        | 15146/100000 [4:40:49<13:45:00,  1.71it/s]
Train steps ... :  15%|█▌        | 15147/100000 [4:40:49<13:44:55,  1.71it/s]
Train steps ... :  15%|█▌        | 15148/100000 [4:40:50<13:44:20,  1.72it/s]
Train steps ... :  15%|█▌        | 15149/100000 [4:40:51<13:44:17,  1.72it/s]
Train steps ... :  15%|█▌        | 15150/100000 [4:40:51<13:44:42,  1.71it/s]Step... (15150 / 100000 | Loss: 1.3348679542541504, Learning Rate: 8.527638190954774e-05)
+
                                                                             
Step... (15150 / 100000 | Loss: 1.0007017850875854, Learning Rate: 8.527638190954774e-05)
+
Train steps ... :  15%|█▌        | 15150/100000 [4:40:52<13:44:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15151/100000 [4:40:52<13:44:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15152/100000 [4:40:52<13:43:44,  1.72it/s]
Train steps ... :  15%|█▌        | 15153/100000 [4:40:53<13:44:29,  1.72it/s]
Train steps ... :  15%|█▌        | 15154/100000 [4:40:54<13:44:07,  1.72it/s]
Train steps ... :  15%|█▌        | 15155/100000 [4:40:54<13:43:56,  1.72it/s]
Train steps ... :  15%|█▌        | 15156/100000 [4:40:55<13:44:32,  1.71it/s]
Train steps ... :  15%|█▌        | 15157/100000 [4:40:55<13:44:09,  1.72it/s]
Train steps ... :  15%|█▌        | 15158/100000 [4:40:56<13:44:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15159/100000 [4:40:56<13:44:59,  1.71it/s]
Train steps ... :  15%|█▌        | 15160/100000 [4:40:57<13:45:04,  1.71it/s]
Train steps ... :  15%|█▌        | 15161/100000 [4:40:58<13:45:05,  1.71it/s]
Train steps ... :  15%|█▌        | 15162/100000 [4:40:58<13:44:46,  1.71it/s]
Train steps ... :  15%|█▌        | 15163/100000 [4:40:59<13:44:55,  1.71it/s]
Train steps ... :  15%|█▌        | 15164/100000 [4:40:59<13:44:27,  1.71it/s]
Train steps ... :  15%|█▌        | 15165/100000 [4:41:00<13:44:32,  1.71it/s]
Train steps ... :  15%|█▌        | 15166/100000 [4:41:01<13:44:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15167/100000 [4:41:01<13:44:14,  1.72it/s]
Train steps ... :  15%|█▌        | 15168/100000 [4:41:02<13:43:46,  1.72it/s]
Train steps ... :  15%|█▌        | 15169/100000 [4:41:02<13:44:53,  1.71it/s]
Train steps ... :  15%|█▌        | 15170/100000 [4:41:03<13:44:20,  1.72it/s]
Train steps ... :  15%|█▌        | 15171/100000 [4:41:03<13:44:21,  1.72it/s]
Train steps ... :  15%|█▌        | 15172/100000 [4:41:04<13:44:07,  1.72it/s]
Train steps ... :  15%|█▌        | 15173/100000 [4:41:05<13:43:45,  1.72it/s]
Train steps ... :  15%|█▌        | 15174/100000 [4:41:05<13:44:34,  1.71it/s]
Train steps ... :  15%|█▌        | 15175/100000 [4:41:06<13:43:11,  1.72it/s]Step... (15175 / 100000 | Loss: 1.0093793869018555, Learning Rate: 8.525125628140704e-05)
+
                                                                             
Step... (15175 / 100000 | Loss: 1.0423377752304077, Learning Rate: 8.525125628140704e-05)
+
Train steps ... :  15%|█▌        | 15175/100000 [4:41:06<13:43:11,  1.72it/s]
Train steps ... :  15%|█▌        | 15176/100000 [4:41:06<13:43:31,  1.72it/s]
Train steps ... :  15%|█▌        | 15177/100000 [4:41:07<13:43:27,  1.72it/s]
Train steps ... :  15%|█▌        | 15178/100000 [4:41:08<13:46:00,  1.71it/s]
Train steps ... :  15%|█▌        | 15179/100000 [4:41:08<13:45:05,  1.71it/s]
Train steps ... :  15%|█▌        | 15180/100000 [4:41:09<13:46:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15181/100000 [4:41:09<13:45:26,  1.71it/s]
Train steps ... :  15%|█▌        | 15182/100000 [4:41:10<13:44:52,  1.71it/s]
Train steps ... :  15%|█▌        | 15183/100000 [4:41:10<13:44:50,  1.71it/s]
Train steps ... :  15%|█▌        | 15184/100000 [4:41:11<13:47:51,  1.71it/s]
Train steps ... :  15%|█▌        | 15185/100000 [4:41:12<13:47:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15186/100000 [4:41:12<13:46:44,  1.71it/s]
Train steps ... :  15%|█▌        | 15187/100000 [4:41:13<13:46:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15188/100000 [4:41:13<13:45:29,  1.71it/s]
Train steps ... :  15%|█▌        | 15189/100000 [4:41:14<13:45:41,  1.71it/s]
Train steps ... :  15%|█▌        | 15190/100000 [4:41:15<13:44:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15191/100000 [4:41:15<13:45:16,  1.71it/s]
Train steps ... :  15%|█▌        | 15192/100000 [4:41:16<13:44:50,  1.71it/s]
Train steps ... :  15%|█▌        | 15193/100000 [4:41:16<13:45:00,  1.71it/s]
Train steps ... :  15%|█▌        | 15194/100000 [4:41:17<13:44:28,  1.71it/s]
Train steps ... :  15%|█▌        | 15195/100000 [4:41:17<13:45:29,  1.71it/s]
Train steps ... :  15%|█▌        | 15196/100000 [4:41:18<13:45:19,  1.71it/s]
Train steps ... :  15%|█▌        | 15197/100000 [4:41:19<13:44:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15198/100000 [4:41:19<13:44:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15199/100000 [4:41:20<13:45:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15200/100000 [4:41:20<13:47:14,  1.71it/s]Step... (15200 / 100000 | Loss: 0.9009425640106201, Learning Rate: 8.522613065326634e-05)
+
                                                                             
Step... (15200 / 100000 | Loss: 1.047974705696106, Learning Rate: 8.522613065326634e-05)
+
Train steps ... :  15%|█▌        | 15200/100000 [4:41:21<13:47:14,  1.71it/s]
Train steps ... :  15%|█▌        | 15201/100000 [4:41:21<13:46:03,  1.71it/s]
Train steps ... :  15%|█▌        | 15202/100000 [4:41:22<13:46:54,  1.71it/s]
Train steps ... :  15%|█▌        | 15203/100000 [4:41:22<13:47:04,  1.71it/s]
Train steps ... :  15%|█▌        | 15204/100000 [4:41:23<13:47:35,  1.71it/s]
Train steps ... :  15%|█▌        | 15205/100000 [4:41:23<13:46:29,  1.71it/s]
Train steps ... :  15%|█▌        | 15206/100000 [4:41:24<13:46:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15207/100000 [4:41:24<13:45:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15208/100000 [4:41:25<13:45:53,  1.71it/s]
Train steps ... :  15%|█▌        | 15209/100000 [4:41:26<13:45:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15210/100000 [4:41:26<13:45:04,  1.71it/s]
Train steps ... :  15%|█▌        | 15211/100000 [4:41:27<13:44:45,  1.71it/s]
Train steps ... :  15%|█▌        | 15212/100000 [4:41:27<13:45:00,  1.71it/s]
Train steps ... :  15%|█▌        | 15213/100000 [4:41:28<13:44:24,  1.71it/s]
Train steps ... :  15%|█▌        | 15214/100000 [4:41:29<13:44:25,  1.71it/s]
Train steps ... :  15%|█▌        | 15215/100000 [4:41:29<13:44:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15216/100000 [4:41:30<13:44:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15217/100000 [4:41:30<13:45:06,  1.71it/s]
Train steps ... :  15%|█▌        | 15218/100000 [4:41:31<13:45:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15219/100000 [4:41:31<13:45:17,  1.71it/s]
Train steps ... :  15%|█▌        | 15220/100000 [4:41:32<13:44:58,  1.71it/s]
Train steps ... :  15%|█▌        | 15221/100000 [4:41:33<13:44:58,  1.71it/s]
Train steps ... :  15%|█▌        | 15222/100000 [4:41:33<13:45:21,  1.71it/s]
Train steps ... :  15%|█▌        | 15223/100000 [4:41:34<13:44:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15224/100000 [4:41:34<13:45:19,  1.71it/s]
Train steps ... :  15%|█▌        | 15225/100000 [4:41:35<13:46:34,  1.71it/s]Step... (15225 / 100000 | Loss: 0.9087995886802673, Learning Rate: 8.520100502512563e-05)
+
                                                                             
Step... (15225 / 100000 | Loss: 1.2180054187774658, Learning Rate: 8.520100502512563e-05)
+
Train steps ... :  15%|█▌        | 15225/100000 [4:41:35<13:46:34,  1.71it/s]
Train steps ... :  15%|█▌        | 15226/100000 [4:41:36<13:46:22,  1.71it/s]
Train steps ... :  15%|█▌        | 15227/100000 [4:41:36<13:45:13,  1.71it/s]
Train steps ... :  15%|█▌        | 15228/100000 [4:41:37<13:44:21,  1.71it/s]
Train steps ... :  15%|█▌        | 15229/100000 [4:41:37<13:44:48,  1.71it/s]
Train steps ... :  15%|█▌        | 15230/100000 [4:41:38<13:45:25,  1.71it/s]
Train steps ... :  15%|█▌        | 15231/100000 [4:41:38<13:44:46,  1.71it/s]
Train steps ... :  15%|█▌        | 15232/100000 [4:41:39<13:44:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15233/100000 [4:41:40<13:44:19,  1.71it/s]
Train steps ... :  15%|█▌        | 15234/100000 [4:41:40<13:44:41,  1.71it/s]
Train steps ... :  15%|█▌        | 15235/100000 [4:41:41<13:45:39,  1.71it/s]
Train steps ... :  15%|█▌        | 15236/100000 [4:41:41<13:45:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15237/100000 [4:41:42<13:45:53,  1.71it/s]
Train steps ... :  15%|█▌        | 15238/100000 [4:41:43<13:45:21,  1.71it/s]
Train steps ... :  15%|█▌        | 15239/100000 [4:41:43<13:44:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15240/100000 [4:41:44<13:45:10,  1.71it/s]
Train steps ... :  15%|█▌        | 15241/100000 [4:41:44<13:44:24,  1.71it/s]
Train steps ... :  15%|█▌        | 15242/100000 [4:41:45<13:45:06,  1.71it/s]
Train steps ... :  15%|█▌        | 15243/100000 [4:41:45<13:44:17,  1.71it/s]
Train steps ... :  15%|█▌        | 15244/100000 [4:41:46<13:43:54,  1.71it/s]
Train steps ... :  15%|█▌        | 15245/100000 [4:41:47<13:43:35,  1.72it/s]
Train steps ... :  15%|█▌        | 15246/100000 [4:41:47<13:43:25,  1.72it/s]
Train steps ... :  15%|█▌        | 15247/100000 [4:41:48<13:43:20,  1.72it/s]
Train steps ... :  15%|█▌        | 15248/100000 [4:41:48<13:45:25,  1.71it/s]
Train steps ... :  15%|█▌        | 15249/100000 [4:41:49<13:45:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15250/100000 [4:41:50<13:47:05,  1.71it/s]Step... (15250 / 100000 | Loss: 1.0793839693069458, Learning Rate: 8.517587939698493e-05)
+
                                                                             
Step... (15250 / 100000 | Loss: 1.0703275203704834, Learning Rate: 8.517587939698493e-05)
+
Train steps ... :  15%|█▌        | 15250/100000 [4:41:50<13:47:05,  1.71it/s]
Train steps ... :  15%|█▌        | 15251/100000 [4:41:50<13:46:17,  1.71it/s]
Train steps ... :  15%|█▌        | 15252/100000 [4:41:51<13:45:00,  1.71it/s]
Train steps ... :  15%|█▌        | 15253/100000 [4:41:51<13:44:17,  1.71it/s]
Train steps ... :  15%|█▌        | 15254/100000 [4:41:52<13:43:35,  1.71it/s]
Train steps ... :  15%|█▌        | 15255/100000 [4:41:52<13:44:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15256/100000 [4:41:53<13:44:13,  1.71it/s]
Train steps ... :  15%|█▌        | 15257/100000 [4:41:54<13:44:45,  1.71it/s]
Train steps ... :  15%|█▌        | 15258/100000 [4:41:54<13:44:57,  1.71it/s]
Train steps ... :  15%|█▌        | 15259/100000 [4:41:55<13:44:14,  1.71it/s]
Train steps ... :  15%|█▌        | 15260/100000 [4:41:55<13:44:03,  1.71it/s]
Train steps ... :  15%|█▌        | 15261/100000 [4:41:56<13:43:55,  1.71it/s]
Train steps ... :  15%|█▌        | 15262/100000 [4:41:57<13:43:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15263/100000 [4:41:57<13:43:22,  1.72it/s]
Train steps ... :  15%|█▌        | 15264/100000 [4:41:58<13:43:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15265/100000 [4:41:58<13:44:04,  1.71it/s]
Train steps ... :  15%|█▌        | 15266/100000 [4:41:59<13:45:03,  1.71it/s]
Train steps ... :  15%|█▌        | 15267/100000 [4:41:59<13:44:17,  1.71it/s]
Train steps ... :  15%|█▌        | 15268/100000 [4:42:00<13:43:39,  1.71it/s]
Train steps ... :  15%|█▌        | 15269/100000 [4:42:01<13:43:29,  1.71it/s]
Train steps ... :  15%|█▌        | 15270/100000 [4:42:01<13:43:53,  1.71it/s]
Train steps ... :  15%|█▌        | 15271/100000 [4:42:02<13:43:50,  1.71it/s]
Train steps ... :  15%|█▌        | 15272/100000 [4:42:02<13:43:05,  1.72it/s]
Train steps ... :  15%|█▌        | 15273/100000 [4:42:03<13:43:26,  1.71it/s]
Train steps ... :  15%|█▌        | 15274/100000 [4:42:04<13:43:00,  1.72it/s]
Train steps ... :  15%|█▌        | 15275/100000 [4:42:04<13:43:56,  1.71it/s]Step... (15275 / 100000 | Loss: 0.9928584098815918, Learning Rate: 8.515075376884423e-05)
+
                                                                             
Step... (15275 / 100000 | Loss: 1.2864174842834473, Learning Rate: 8.515075376884423e-05)
+
Train steps ... :  15%|█▌        | 15275/100000 [4:42:04<13:43:56,  1.71it/s]
Train steps ... :  15%|█▌        | 15276/100000 [4:42:05<13:44:31,  1.71it/s]
Train steps ... :  15%|█▌        | 15277/100000 [4:42:05<13:44:11,  1.71it/s]
Train steps ... :  15%|█▌        | 15278/100000 [4:42:06<13:44:31,  1.71it/s]
Train steps ... :  15%|█▌        | 15279/100000 [4:42:06<13:44:04,  1.71it/s]
Train steps ... :  15%|█▌        | 15280/100000 [4:42:07<13:44:25,  1.71it/s]
Train steps ... :  15%|█▌        | 15281/100000 [4:42:08<13:45:21,  1.71it/s]
Train steps ... :  15%|█▌        | 15282/100000 [4:42:08<13:44:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15283/100000 [4:42:09<13:44:11,  1.71it/s]
Train steps ... :  15%|█▌        | 15284/100000 [4:42:09<13:44:09,  1.71it/s]
Train steps ... :  15%|█▌        | 15285/100000 [4:42:10<13:42:57,  1.72it/s]
Train steps ... :  15%|█▌        | 15286/100000 [4:42:11<13:44:10,  1.71it/s]
Train steps ... :  15%|█▌        | 15287/100000 [4:42:11<13:43:45,  1.71it/s]
Train steps ... :  15%|█▌        | 15288/100000 [4:42:12<13:44:28,  1.71it/s]
Train steps ... :  15%|█▌        | 15289/100000 [4:42:12<13:45:03,  1.71it/s]
Train steps ... :  15%|█▌        | 15290/100000 [4:42:13<13:44:20,  1.71it/s]
Train steps ... :  15%|█▌        | 15291/100000 [4:42:13<13:44:06,  1.71it/s]
Train steps ... :  15%|█▌        | 15292/100000 [4:42:14<13:44:07,  1.71it/s]
Train steps ... :  15%|█▌        | 15293/100000 [4:42:15<13:44:56,  1.71it/s]
Train steps ... :  15%|█▌        | 15294/100000 [4:42:15<13:44:06,  1.71it/s]
Train steps ... :  15%|█▌        | 15295/100000 [4:42:16<13:43:54,  1.71it/s]
Train steps ... :  15%|█▌        | 15296/100000 [4:42:16<13:44:05,  1.71it/s]
Train steps ... :  15%|█▌        | 15297/100000 [4:42:17<13:43:43,  1.71it/s]
Train steps ... :  15%|█▌        | 15298/100000 [4:42:18<13:43:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15299/100000 [4:42:18<13:43:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15300/100000 [4:42:19<13:43:29,  1.71it/s]Step... (15300 / 100000 | Loss: 1.1571052074432373, Learning Rate: 8.512562814070352e-05)
+
                                                                             
Step... (15300 / 100000 | Loss: 0.7892410159111023, Learning Rate: 8.512562814070352e-05)
+
Train steps ... :  15%|█▌        | 15300/100000 [4:42:19<13:43:29,  1.71it/s]
Train steps ... :  15%|█▌        | 15301/100000 [4:42:19<13:43:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15302/100000 [4:42:20<13:44:16,  1.71it/s]
Train steps ... :  15%|█▌        | 15303/100000 [4:42:20<13:43:04,  1.72it/s]
Train steps ... :  15%|█▌        | 15304/100000 [4:42:21<13:43:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15305/100000 [4:42:22<13:43:33,  1.71it/s]
Train steps ... :  15%|█▌        | 15306/100000 [4:42:22<13:42:58,  1.72it/s]
Train steps ... :  15%|█▌        | 15307/100000 [4:42:23<13:42:53,  1.72it/s]
Train steps ... :  15%|█▌        | 15308/100000 [4:42:23<13:43:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15309/100000 [4:42:24<13:43:23,  1.71it/s]
Train steps ... :  15%|█▌        | 15310/100000 [4:42:25<13:43:41,  1.71it/s]
Train steps ... :  15%|█▌        | 15311/100000 [4:42:25<13:44:09,  1.71it/s]
Train steps ... :  15%|█▌        | 15312/100000 [4:42:26<13:43:38,  1.71it/s]
Train steps ... :  15%|█▌        | 15313/100000 [4:42:26<13:42:49,  1.72it/s]
Train steps ... :  15%|█▌        | 15314/100000 [4:42:27<13:43:47,  1.71it/s]
Train steps ... :  15%|█▌        | 15315/100000 [4:42:28<13:44:45,  1.71it/s]
Train steps ... :  15%|█▌        | 15316/100000 [4:42:28<13:45:19,  1.71it/s]
Train steps ... :  15%|█▌        | 15317/100000 [4:42:29<13:44:06,  1.71it/s]
Train steps ... :  15%|█▌        | 15318/100000 [4:42:29<13:43:46,  1.71it/s]
Train steps ... :  15%|█▌        | 15319/100000 [4:42:30<13:43:03,  1.71it/s]
Train steps ... :  15%|█▌        | 15320/100000 [4:42:30<13:43:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15321/100000 [4:42:31<13:43:08,  1.71it/s]
Train steps ... :  15%|█▌        | 15322/100000 [4:42:32<13:43:40,  1.71it/s]
Train steps ... :  15%|█▌        | 15323/100000 [4:42:32<13:43:07,  1.71it/s]
Train steps ... :  15%|█▌        | 15324/100000 [4:42:33<13:42:53,  1.72it/s]
Train steps ... :  15%|█▌        | 15325/100000 [4:42:33<13:42:51,  1.72it/s]Step... (15325 / 100000 | Loss: 1.2426793575286865, Learning Rate: 8.510050251256282e-05)
+
                                                                             
Step... (15325 / 100000 | Loss: 1.0741372108459473, Learning Rate: 8.510050251256282e-05)
+
Train steps ... :  15%|█▌        | 15325/100000 [4:42:34<13:42:51,  1.72it/s]
Train steps ... :  15%|█▌        | 15326/100000 [4:42:34<13:42:57,  1.71it/s]
Train steps ... :  15%|█▌        | 15327/100000 [4:42:35<13:42:34,  1.72it/s]
Train steps ... :  15%|█▌        | 15328/100000 [4:42:35<13:42:39,  1.72it/s]
Train steps ... :  15%|█▌        | 15329/100000 [4:42:36<13:43:21,  1.71it/s]
Train steps ... :  15%|█▌        | 15330/100000 [4:42:36<13:43:38,  1.71it/s]
Train steps ... :  15%|█▌        | 15331/100000 [4:42:37<13:44:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15332/100000 [4:42:37<13:44:05,  1.71it/s]
Train steps ... :  15%|█▌        | 15333/100000 [4:42:38<13:43:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15334/100000 [4:42:39<13:44:08,  1.71it/s]
Train steps ... :  15%|█▌        | 15335/100000 [4:42:39<13:43:59,  1.71it/s]
Train steps ... :  15%|█▌        | 15336/100000 [4:42:40<13:44:15,  1.71it/s]
Train steps ... :  15%|█▌        | 15337/100000 [4:42:40<13:43:41,  1.71it/s]
Train steps ... :  15%|█▌        | 15338/100000 [4:42:41<13:43:15,  1.71it/s]
Train steps ... :  15%|█▌        | 15339/100000 [4:42:42<13:43:27,  1.71it/s]
Train steps ... :  15%|█▌        | 15340/100000 [4:42:42<13:42:52,  1.71it/s]
Train steps ... :  15%|█▌        | 15341/100000 [4:42:43<13:43:03,  1.71it/s]
Train steps ... :  15%|█▌        | 15342/100000 [4:42:43<13:43:09,  1.71it/s]
Train steps ... :  15%|█▌        | 15343/100000 [4:42:44<13:43:47,  1.71it/s]
Train steps ... :  15%|█▌        | 15344/100000 [4:42:44<13:43:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15345/100000 [4:42:45<13:42:40,  1.72it/s]
Train steps ... :  15%|█▌        | 15346/100000 [4:42:46<13:42:36,  1.72it/s]
Train steps ... :  15%|█▌        | 15347/100000 [4:42:46<13:42:53,  1.71it/s]
Train steps ... :  15%|█▌        | 15348/100000 [4:42:47<13:43:39,  1.71it/s]
Train steps ... :  15%|█▌        | 15349/100000 [4:42:47<13:43:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15350/100000 [4:42:48<13:43:14,  1.71it/s]Step... (15350 / 100000 | Loss: 1.238072395324707, Learning Rate: 8.507537688442212e-05)
+
                                                                             
Step... (15350 / 100000 | Loss: 1.0012884140014648, Learning Rate: 8.507537688442212e-05)
+
Train steps ... :  15%|█▌        | 15350/100000 [4:42:48<13:43:14,  1.71it/s]
Train steps ... :  15%|█▌        | 15351/100000 [4:42:49<13:43:06,  1.71it/s]
Train steps ... :  15%|█▌        | 15352/100000 [4:42:49<13:43:19,  1.71it/s]
Train steps ... :  15%|█▌        | 15353/100000 [4:42:50<13:42:27,  1.72it/s]
Train steps ... :  15%|█▌        | 15354/100000 [4:42:50<13:43:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15355/100000 [4:42:51<13:43:32,  1.71it/s]
Train steps ... :  15%|█▌        | 15356/100000 [4:42:51<13:42:40,  1.71it/s]
Train steps ... :  15%|█▌        | 15357/100000 [4:42:52<13:42:19,  1.72it/s]
Train steps ... :  15%|█▌        | 15358/100000 [4:42:53<13:42:38,  1.71it/s]
Train steps ... :  15%|█▌        | 15359/100000 [4:42:53<13:42:45,  1.71it/s]
Train steps ... :  15%|█▌        | 15360/100000 [4:42:54<13:43:31,  1.71it/s]
Train steps ... :  15%|█▌        | 15361/100000 [4:42:54<13:42:48,  1.71it/s]
Train steps ... :  15%|█▌        | 15362/100000 [4:42:55<13:44:22,  1.71it/s]
Train steps ... :  15%|█▌        | 15363/100000 [4:42:56<13:44:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15364/100000 [4:42:56<13:43:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15365/100000 [4:42:57<13:43:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15366/100000 [4:42:57<13:42:25,  1.72it/s]
Train steps ... :  15%|█▌        | 15367/100000 [4:42:58<13:43:10,  1.71it/s]
Train steps ... :  15%|█▌        | 15368/100000 [4:42:58<13:42:58,  1.71it/s]
Train steps ... :  15%|█▌        | 15369/100000 [4:42:59<13:43:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15370/100000 [4:43:00<13:43:09,  1.71it/s]
Train steps ... :  15%|█▌        | 15371/100000 [4:43:00<13:42:41,  1.71it/s]
Train steps ... :  15%|█▌        | 15372/100000 [4:43:01<13:42:23,  1.72it/s]
Train steps ... :  15%|█▌        | 15373/100000 [4:43:01<13:41:56,  1.72it/s]
Train steps ... :  15%|█▌        | 15374/100000 [4:43:02<13:42:27,  1.71it/s]
Train steps ... :  15%|█▌        | 15375/100000 [4:43:03<13:42:08,  1.72it/s]Step... (15375 / 100000 | Loss: 1.0400135517120361, Learning Rate: 8.505025125628141e-05)
+
                                                                             
Step... (15375 / 100000 | Loss: 0.84708571434021, Learning Rate: 8.505025125628141e-05)
+
Train steps ... :  15%|█▌        | 15375/100000 [4:43:03<13:42:08,  1.72it/s]
Train steps ... :  15%|█▌        | 15376/100000 [4:43:03<13:42:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15377/100000 [4:43:04<13:42:19,  1.72it/s]
Train steps ... :  15%|█▌        | 15378/100000 [4:43:04<13:42:33,  1.71it/s]
Train steps ... :  15%|█▌        | 15379/100000 [4:43:05<13:42:28,  1.71it/s]
Train steps ... :  15%|█▌        | 15380/100000 [4:43:05<13:42:37,  1.71it/s]
Train steps ... :  15%|█▌        | 15381/100000 [4:43:06<13:42:15,  1.72it/s]
Train steps ... :  15%|█▌        | 15382/100000 [4:43:07<13:43:04,  1.71it/s]
Train steps ... :  15%|█▌        | 15383/100000 [4:43:07<13:42:41,  1.71it/s]
Train steps ... :  15%|█▌        | 15384/100000 [4:43:08<13:42:39,  1.71it/s]
Train steps ... :  15%|█▌        | 15385/100000 [4:43:08<13:42:53,  1.71it/s]
Train steps ... :  15%|█▌        | 15386/100000 [4:43:09<13:42:43,  1.71it/s]
Train steps ... :  15%|█▌        | 15387/100000 [4:43:10<13:43:56,  1.71it/s]
Train steps ... :  15%|█▌        | 15388/100000 [4:43:10<13:43:35,  1.71it/s]
Train steps ... :  15%|█▌        | 15389/100000 [4:43:11<13:43:24,  1.71it/s]
Train steps ... :  15%|█▌        | 15390/100000 [4:43:11<13:44:49,  1.71it/s]
Train steps ... :  15%|█▌        | 15391/100000 [4:43:12<13:43:52,  1.71it/s]
Train steps ... :  15%|█▌        | 15392/100000 [4:43:12<13:43:34,  1.71it/s]
Train steps ... :  15%|█▌        | 15393/100000 [4:43:13<13:43:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15394/100000 [4:43:14<13:42:58,  1.71it/s]
Train steps ... :  15%|█▌        | 15395/100000 [4:43:14<13:42:38,  1.71it/s]
Train steps ... :  15%|█▌        | 15396/100000 [4:43:15<13:43:35,  1.71it/s]
Train steps ... :  15%|█▌        | 15397/100000 [4:43:15<13:43:19,  1.71it/s]
Train steps ... :  15%|█▌        | 15398/100000 [4:43:16<13:42:40,  1.71it/s]
Train steps ... :  15%|█▌        | 15399/100000 [4:43:17<13:42:56,  1.71it/s]
Train steps ... :  15%|█▌        | 15400/100000 [4:43:17<13:43:30,  1.71it/s]Step... (15400 / 100000 | Loss: 0.8154097199440002, Learning Rate: 8.502512562814071e-05)
+
                                                                             
Step... (15400 / 100000 | Loss: 1.1604511737823486, Learning Rate: 8.502512562814071e-05)
+
Train steps ... :  15%|█▌        | 15400/100000 [4:43:17<13:43:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15401/100000 [4:43:18<13:43:43,  1.71it/s]
Train steps ... :  15%|█▌        | 15402/100000 [4:43:18<13:43:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15403/100000 [4:43:19<13:42:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15404/100000 [4:43:19<13:42:32,  1.71it/s]
Train steps ... :  15%|█▌        | 15405/100000 [4:43:20<13:42:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15406/100000 [4:43:21<13:42:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15407/100000 [4:43:21<13:42:43,  1.71it/s]
Train steps ... :  15%|█���        | 15408/100000 [4:43:22<13:43:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15409/100000 [4:43:22<13:43:14,  1.71it/s]
Train steps ... :  15%|█▌        | 15410/100000 [4:43:23<13:43:04,  1.71it/s]
Train steps ... :  15%|█▌        | 15411/100000 [4:43:24<13:42:06,  1.71it/s]
Train steps ... :  15%|█▌        | 15412/100000 [4:43:24<13:42:28,  1.71it/s]
Train steps ... :  15%|█▌        | 15413/100000 [4:43:25<13:43:57,  1.71it/s]
Train steps ... :  15%|█▌        | 15414/100000 [4:43:25<13:43:44,  1.71it/s]
Train steps ... :  15%|█▌        | 15415/100000 [4:43:26<13:43:38,  1.71it/s]
Train steps ... :  15%|█▌        | 15416/100000 [4:43:26<13:43:23,  1.71it/s]
Train steps ... :  15%|█▌        | 15417/100000 [4:43:27<13:42:54,  1.71it/s]
Train steps ... :  15%|█▌        | 15418/100000 [4:43:28<13:42:47,  1.71it/s]
Train steps ... :  15%|█▌        | 15419/100000 [4:43:28<13:43:40,  1.71it/s]
Train steps ... :  15%|█▌        | 15420/100000 [4:43:29<13:42:50,  1.71it/s]
Train steps ... :  15%|█▌        | 15421/100000 [4:43:29<13:42:34,  1.71it/s]
Train steps ... :  15%|█▌        | 15422/100000 [4:43:30<13:42:13,  1.71it/s]
Train steps ... :  15%|█▌        | 15423/100000 [4:43:31<13:42:39,  1.71it/s]
Train steps ... :  15%|█▌        | 15424/100000 [4:43:31<13:42:29,  1.71it/s]
Train steps ... :  15%|█▌        | 15425/100000 [4:43:32<13:42:34,  1.71it/s]Step... (15425 / 100000 | Loss: 0.7111440300941467, Learning Rate: 8.5e-05)
+
                                                                             
Step... (15425 / 100000 | Loss: 0.9703603982925415, Learning Rate: 8.5e-05)
+
Train steps ... :  15%|█▌        | 15425/100000 [4:43:32<13:42:34,  1.71it/s]
Train steps ... :  15%|█▌        | 15426/100000 [4:43:32<13:42:44,  1.71it/s]
Train steps ... :  15%|█▌        | 15427/100000 [4:43:33<13:41:57,  1.71it/s]
Train steps ... :  15%|█▌        | 15428/100000 [4:43:33<13:42:10,  1.71it/s]
Train steps ... :  15%|█▌        | 15429/100000 [4:43:34<13:41:54,  1.71it/s]
Train steps ... :  15%|█▌        | 15430/100000 [4:43:35<13:42:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15431/100000 [4:43:35<13:42:38,  1.71it/s]
Train steps ... :  15%|█▌        | 15432/100000 [4:43:36<13:42:05,  1.71it/s]
Train steps ... :  15%|█▌        | 15433/100000 [4:43:36<13:42:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15434/100000 [4:43:37<13:42:28,  1.71it/s]
Train steps ... :  15%|█▌        | 15435/100000 [4:43:38<13:42:28,  1.71it/s]
Train steps ... :  15%|█▌        | 15436/100000 [4:43:38<13:42:48,  1.71it/s]
Train steps ... :  15%|█▌        | 15437/100000 [4:43:39<13:42:02,  1.71it/s]
Train steps ... :  15%|█▌        | 15438/100000 [4:43:39<13:41:27,  1.72it/s]
Train steps ... :  15%|█▌        | 15439/100000 [4:43:40<13:42:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15440/100000 [4:43:40<13:42:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15441/100000 [4:43:41<13:43:15,  1.71it/s]
Train steps ... :  15%|█▌        | 15442/100000 [4:43:42<13:43:14,  1.71it/s]
Train steps ... :  15%|█▌        | 15443/100000 [4:43:42<13:42:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15444/100000 [4:43:43<13:43:23,  1.71it/s]
Train steps ... :  15%|█▌        | 15445/100000 [4:43:43<13:43:06,  1.71it/s]
Train steps ... :  15%|█▌        | 15446/100000 [4:43:44<13:44:04,  1.71it/s]
Train steps ... :  15%|█▌        | 15447/100000 [4:43:45<13:43:00,  1.71it/s]
Train steps ... :  15%|█▌        | 15448/100000 [4:43:45<13:42:42,  1.71it/s]
Train steps ... :  15%|█▌        | 15449/100000 [4:43:46<13:42:23,  1.71it/s]
Train steps ... :  15%|█▌        | 15450/100000 [4:43:46<13:42:01,  1.71it/s]Step... (15450 / 100000 | Loss: 1.220231294631958, Learning Rate: 8.49748743718593e-05)
+
                                                                             
Step... (15450 / 100000 | Loss: 1.2996951341629028, Learning Rate: 8.49748743718593e-05)
+
Train steps ... :  15%|█▌        | 15450/100000 [4:43:47<13:42:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15451/100000 [4:43:47<13:42:02,  1.71it/s]
Train steps ... :  15%|█▌        | 15452/100000 [4:43:47<13:41:27,  1.72it/s]
Train steps ... :  15%|█▌        | 15453/100000 [4:43:48<13:41:30,  1.72it/s]
Train steps ... :  15%|█▌        | 15454/100000 [4:43:49<13:42:23,  1.71it/s]
Train steps ... :  15%|█▌        | 15455/100000 [4:43:49<13:43:22,  1.71it/s]
Train steps ... :  15%|█▌        | 15456/100000 [4:43:50<13:43:15,  1.71it/s]
Train steps ... :  15%|█▌        | 15457/100000 [4:43:50<13:43:57,  1.71it/s]
Train steps ... :  15%|█▌        | 15458/100000 [4:43:51<13:42:53,  1.71it/s]
Train steps ... :  15%|█▌        | 15459/100000 [4:43:52<13:42:40,  1.71it/s]
Train steps ... :  15%|█▌        | 15460/100000 [4:43:52<13:42:55,  1.71it/s]
Train steps ... :  15%|█▌        | 15461/100000 [4:43:53<13:42:17,  1.71it/s]
Train steps ... :  15%|█▌        | 15462/100000 [4:43:53<13:42:57,  1.71it/s]
Train steps ... :  15%|█▌        | 15463/100000 [4:43:54<13:42:22,  1.71it/s]
Train steps ... :  15%|█▌        | 15464/100000 [4:43:54<13:41:54,  1.71it/s]
Train steps ... :  15%|█▌        | 15465/100000 [4:43:55<13:42:13,  1.71it/s]
Train steps ... :  15%|█▌        | 15466/100000 [4:43:56<13:42:14,  1.71it/s]
Train steps ... :  15%|█▌        | 15467/100000 [4:43:56<13:42:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15468/100000 [4:43:57<13:42:19,  1.71it/s]
Train steps ... :  15%|█▌        | 15469/100000 [4:43:57<13:42:44,  1.71it/s]
Train steps ... :  15%|█▌        | 15470/100000 [4:43:58<13:42:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15471/100000 [4:43:59<13:42:19,  1.71it/s]
Train steps ... :  15%|█▌        | 15472/100000 [4:43:59<13:42:46,  1.71it/s]
Train steps ... :  15%|█▌        | 15473/100000 [4:44:00<13:43:18,  1.71it/s]
Train steps ... :  15%|█▌        | 15474/100000 [4:44:00<13:43:17,  1.71it/s]
Train steps ... :  15%|█▌        | 15475/100000 [4:44:01<13:43:11,  1.71it/s]Step... (15475 / 100000 | Loss: 1.3712241649627686, Learning Rate: 8.49497487437186e-05)
+
                                                                             
Step... (15475 / 100000 | Loss: 1.5149173736572266, Learning Rate: 8.49497487437186e-05)
+
Train steps ... :  15%|█▌        | 15475/100000 [4:44:01<13:43:11,  1.71it/s]
Train steps ... :  15%|█▌        | 15476/100000 [4:44:01<13:42:52,  1.71it/s]
Train steps ... :  15%|█▌        | 15477/100000 [4:44:02<13:42:16,  1.71it/s]
Train steps ... :  15%|█▌        | 15478/100000 [4:44:03<13:42:02,  1.71it/s]
Train steps ... :  15%|█▌        | 15479/100000 [4:44:03<13:41:36,  1.71it/s]
Train steps ... :  15%|█▌        | 15480/100000 [4:44:04<13:40:53,  1.72it/s]
Train steps ... :  15%|█▌        | 15481/100000 [4:44:04<13:41:02,  1.72it/s]
Train steps ... :  15%|█▌        | 15482/100000 [4:44:05<13:41:10,  1.72it/s]
Train steps ... :  15%|█▌        | 15483/100000 [4:44:06<13:41:06,  1.72it/s]
Train steps ... :  15%|█▌        | 15484/100000 [4:44:06<13:41:59,  1.71it/s]
Train steps ... :  15%|█▌        | 15485/100000 [4:44:07<13:42:01,  1.71it/s]
Train steps ... :  15%|█▌        | 15486/100000 [4:44:07<13:42:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15487/100000 [4:44:08<13:42:50,  1.71it/s]
Train steps ... :  15%|█▌        | 15488/100000 [4:44:08<13:42:12,  1.71it/s]
Train steps ... :  15%|█▌        | 15489/100000 [4:44:09<13:41:55,  1.71it/s]
Train steps ... :  15%|█▌        | 15490/100000 [4:44:10<13:42:15,  1.71it/s]
Train steps ... :  15%|█▌        | 15491/100000 [4:44:10<13:44:41,  1.71it/s]
Train steps ... :  15%|█▌        | 15492/100000 [4:44:11<13:43:22,  1.71it/s]
Train steps ... :  15%|█▌        | 15493/100000 [4:44:11<13:43:41,  1.71it/s]
Train steps ... :  15%|█▌        | 15494/100000 [4:44:12<13:42:54,  1.71it/s]
Train steps ... :  15%|█▌        | 15495/100000 [4:44:13<13:43:06,  1.71it/s]
Train steps ... :  15%|█▌        | 15496/100000 [4:44:13<13:42:35,  1.71it/s]
Train steps ... :  15%|█▌        | 15497/100000 [4:44:14<13:42:30,  1.71it/s]
Train steps ... :  15%|█▌        | 15498/100000 [4:44:14<13:42:05,  1.71it/s]
Train steps ... :  15%|█▌        | 15499/100000 [4:44:15<13:41:49,  1.71it/s]
Train steps ... :  16%|█▌        | 15500/100000 [4:44:15<13:41:22,  1.71it/s]Step... (15500 / 100000 | Loss: 0.8567564487457275, Learning Rate: 8.49246231155779e-05)
+
                                                                             
Step... (15500 / 100000 | Loss: 0.9681174159049988, Learning Rate: 8.49246231155779e-05)
+
Train steps ... :  16%|█▌        | 15500/100000 [4:44:16<13:41:22,  1.71it/s]
Train steps ... :  16%|█▌        | 15501/100000 [4:44:16<13:41:47,  1.71it/s]
Train steps ... :  16%|█▌        | 15502/100000 [4:44:17<13:41:14,  1.71it/s]
Train steps ... :  16%|█▌        | 15503/100000 [4:44:17<13:41:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15504/100000 [4:44:18<13:42:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15505/100000 [4:44:18<13:41:26,  1.71it/s]
Train steps ... :  16%|█▌        | 15506/100000 [4:44:19<13:41:13,  1.71it/s]
Train steps ... :  16%|█▌        | 15507/100000 [4:44:20<13:41:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15508/100000 [4:44:20<13:42:51,  1.71it/s]
Train steps ... :  16%|█▌        | 15509/100000 [4:44:21<13:41:53,  1.71it/s]
Train steps ... :  16%|█▌        | 15510/100000 [4:44:21<13:41:37,  1.71it/s]
Train steps ... :  16%|█▌        | 15511/100000 [4:44:22<13:41:38,  1.71it/s]
Train steps ... :  16%|█▌        | 15512/100000 [4:44:22<13:40:30,  1.72it/s]
Train steps ... :  16%|█▌        | 15513/100000 [4:44:23<13:41:25,  1.71it/s]
Train steps ... :  16%|█▌        | 15514/100000 [4:44:24<13:41:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15515/100000 [4:44:24<13:42:36,  1.71it/s]
Train steps ... :  16%|█▌        | 15516/100000 [4:44:25<13:43:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15517/100000 [4:44:25<13:42:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15518/100000 [4:44:26<13:41:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15519/100000 [4:44:27<13:41:13,  1.71it/s]
Train steps ... :  16%|█▌        | 15520/100000 [4:44:27<13:41:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15521/100000 [4:44:28<13:41:38,  1.71it/s]
Train steps ... :  16%|█▌        | 15522/100000 [4:44:28<13:42:00,  1.71it/s]
Train steps ... :  16%|█▌        | 15523/100000 [4:44:29<13:41:53,  1.71it/s]
Train steps ... :  16%|█▌        | 15524/100000 [4:44:29<13:41:46,  1.71it/s]
Train steps ... :  16%|█▌        | 15525/100000 [4:44:30<13:41:37,  1.71it/s]Step... (15525 / 100000 | Loss: 0.8870557546615601, Learning Rate: 8.489949748743718e-05)
+
                                                                             
Step... (15525 / 100000 | Loss: 0.9983312487602234, Learning Rate: 8.489949748743718e-05)
+
Train steps ... :  16%|█▌        | 15525/100000 [4:44:30<13:41:37,  1.71it/s]
Train steps ... :  16%|█▌        | 15526/100000 [4:44:31<13:43:01,  1.71it/s]
Train steps ... :  16%|█▌        | 15527/100000 [4:44:31<13:42:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15528/100000 [4:44:32<13:42:21,  1.71it/s]
Train steps ... :  16%|█▌        | 15529/100000 [4:44:32<13:41:29,  1.71it/s]
Train steps ... :  16%|█▌        | 15530/100000 [4:44:33<13:41:20,  1.71it/s]
Train steps ... :  16%|█▌        | 15531/100000 [4:44:34<13:41:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15532/100000 [4:44:34<13:41:08,  1.71it/s]
Train steps ... :  16%|█▌        | 15533/100000 [4:44:35<13:41:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15534/100000 [4:44:35<13:41:26,  1.71it/s]
Train steps ... :  16%|█▌        | 15535/100000 [4:44:36<13:41:11,  1.71it/s]
Train steps ... :  16%|█▌        | 15536/100000 [4:44:36<13:41:42,  1.71it/s]
Train steps ... :  16%|█▌        | 15537/100000 [4:44:37<13:41:45,  1.71it/s]
Train steps ... :  16%|█▌        | 15538/100000 [4:44:38<13:40:40,  1.72it/s]
Train steps ... :  16%|█▌        | 15539/100000 [4:44:38<13:41:13,  1.71it/s]
Train steps ... :  16%|█▌        | 15540/100000 [4:44:39<13:42:04,  1.71it/s]
Train steps ... :  16%|█▌        | 15541/100000 [4:44:39<13:40:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15542/100000 [4:44:40<13:41:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15543/100000 [4:44:41<13:41:17,  1.71it/s]
Train steps ... :  16%|█▌        | 15544/100000 [4:44:41<13:41:26,  1.71it/s]
Train steps ... :  16%|█▌        | 15545/100000 [4:44:42<13:41:03,  1.71it/s]
Train steps ... :  16%|█▌        | 15546/100000 [4:44:42<13:41:47,  1.71it/s]
Train steps ... :  16%|█▌        | 15547/100000 [4:44:43<13:41:37,  1.71it/s]
Train steps ... :  16%|█▌        | 15548/100000 [4:44:43<13:40:51,  1.71it/s]
Train steps ... :  16%|█▌        | 15549/100000 [4:44:44<13:41:22,  1.71it/s]
Train steps ... :  16%|█▌        | 15550/100000 [4:44:45<13:41:13,  1.71it/s]Step... (15550 / 100000 | Loss: 1.466875672340393, Learning Rate: 8.487437185929649e-05)
+
                                                                             
Step... (15550 / 100000 | Loss: 1.4449710845947266, Learning Rate: 8.487437185929649e-05)
+
Train steps ... :  16%|█▌        | 15550/100000 [4:44:45<13:41:13,  1.71it/s]
Train steps ... :  16%|█▌        | 15551/100000 [4:44:45<13:41:12,  1.71it/s]
Train steps ... :  16%|█▌        | 15552/100000 [4:44:46<13:40:41,  1.71it/s]
Train steps ... :  16%|█▌        | 15553/100000 [4:44:46<13:40:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15554/100000 [4:44:47<13:40:49,  1.71it/s]
Train steps ... :  16%|█▌        | 15555/100000 [4:44:48<13:41:11,  1.71it/s]
Train steps ... :  16%|█▌        | 15556/100000 [4:44:48<13:40:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15557/100000 [4:44:49<13:40:30,  1.72it/s]
Train steps ... :  16%|█▌        | 15558/100000 [4:44:49<13:41:41,  1.71it/s]
Train steps ... :  16%|█▌        | 15559/100000 [4:44:50<13:42:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15560/100000 [4:44:50<13:41:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15561/100000 [4:44:51<13:41:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15562/100000 [4:44:52<13:41:25,  1.71it/s]
Train steps ... :  16%|█▌        | 15563/100000 [4:44:52<13:41:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15564/100000 [4:44:53<13:40:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15565/100000 [4:44:53<13:41:03,  1.71it/s]
Train steps ... :  16%|█▌        | 15566/100000 [4:44:54<13:40:53,  1.71it/s]
Train steps ... :  16%|█▌        | 15567/100000 [4:44:55<13:40:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15568/100000 [4:44:55<13:41:24,  1.71it/s]
Train steps ... :  16%|█▌        | 15569/100000 [4:44:56<13:41:55,  1.71it/s]
Train steps ... :  16%|█▌        | 15570/100000 [4:44:56<13:41:20,  1.71it/s]
Train steps ... :  16%|█▌        | 15571/100000 [4:44:57<13:41:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15572/100000 [4:44:57<13:42:04,  1.71it/s]
Train steps ... :  16%|█▌        | 15573/100000 [4:44:58<13:41:35,  1.71it/s]
Train steps ... :  16%|█▌        | 15574/100000 [4:44:59<13:42:19,  1.71it/s]
Train steps ... :  16%|█▌        | 15575/100000 [4:44:59<13:41:39,  1.71it/s]Step... (15575 / 100000 | Loss: 1.2589362859725952, Learning Rate: 8.484924623115579e-05)
+
                                                                             
Step... (15575 / 100000 | Loss: 1.0042884349822998, Learning Rate: 8.484924623115579e-05)
+
Train steps ... :  16%|█▌        | 15575/100000 [4:45:00<13:41:39,  1.71it/s]
Train steps ... :  16%|█▌        | 15576/100000 [4:45:00<13:43:09,  1.71it/s]
Train steps ... :  16%|█▌        | 15577/100000 [4:45:00<13:42:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15578/100000 [4:45:01<13:42:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15579/100000 [4:45:02<13:42:26,  1.71it/s]
Train steps ... :  16%|█▌        | 15580/100000 [4:45:02<13:43:02,  1.71it/s]
Train steps ... :  16%|█▌        | 15581/100000 [4:45:03<13:41:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15582/100000 [4:45:03<13:41:27,  1.71it/s]
Train steps ... :  16%|█▌        | 15583/100000 [4:45:04<13:42:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15584/100000 [4:45:05<13:41:26,  1.71it/s]
Train steps ... :  16%|█▌        | 15585/100000 [4:45:05<13:41:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15586/100000 [4:45:06<13:41:02,  1.71it/s]
Train steps ... :  16%|█▌        | 15587/100000 [4:45:06<13:41:02,  1.71it/s]
Train steps ... :  16%|█▌        | 15588/100000 [4:45:07<13:41:22,  1.71it/s]
Train steps ... :  16%|█▌        | 15589/100000 [4:45:07<13:41:11,  1.71it/s]
Train steps ... :  16%|█▌        | 15590/100000 [4:45:08<13:40:25,  1.71it/s]
Train steps ... :  16%|█▌        | 15591/100000 [4:45:09<13:40:33,  1.71it/s]
Train steps ... :  16%|█▌        | 15592/100000 [4:45:09<13:40:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15593/100000 [4:45:10<13:40:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15594/100000 [4:45:10<13:40:26,  1.71it/s]
Train steps ... :  16%|█▌        | 15595/100000 [4:45:11<13:40:15,  1.72it/s]
Train steps ... :  16%|█▌        | 15596/100000 [4:45:12<13:40:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15597/100000 [4:45:12<13:40:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15598/100000 [4:45:13<13:41:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15599/100000 [4:45:13<13:40:31,  1.71it/s]
Train steps ... :  16%|█▌        | 15600/100000 [4:45:14<13:40:24,  1.71it/s]Step... (15600 / 100000 | Loss: 1.241194248199463, Learning Rate: 8.482412060301508e-05)
+
                                                                             
Step... (15600 / 100000 | Loss: 0.8822963237762451, Learning Rate: 8.482412060301508e-05)
+
Train steps ... :  16%|█▌        | 15600/100000 [4:45:14<13:40:24,  1.71it/s]
Train steps ... :  16%|█▌        | 15601/100000 [4:45:14<13:41:12,  1.71it/s]
Train steps ... :  16%|█▌        | 15602/100000 [4:45:15<13:41:03,  1.71it/s]
Train steps ... :  16%|█▌        | 15603/100000 [4:45:16<13:41:10,  1.71it/s]
Train steps ... :  16%|█▌        | 15604/100000 [4:45:16<13:41:01,  1.71it/s]
Train steps ... :  16%|█▌        | 15605/100000 [4:45:17<13:40:46,  1.71it/s]
Train steps ... :  16%|█▌        | 15606/100000 [4:45:17<13:41:38,  1.71it/s]
Train steps ... :  16%|█▌        | 15607/100000 [4:45:18<13:40:55,  1.71it/s]
Train steps ... :  16%|█▌        | 15608/100000 [4:45:19<13:40:18,  1.71it/s]
Train steps ... :  16%|█▌        | 15609/100000 [4:45:19<13:40:37,  1.71it/s]
Train steps ... :  16%|█▌        | 15610/100000 [4:45:20<13:40:21,  1.71it/s]
Train steps ... :  16%|█▌        | 15611/100000 [4:45:20<13:40:08,  1.71it/s]
Train steps ... :  16%|█▌        | 15612/100000 [4:45:21<13:40:27,  1.71it/s]
Train steps ... :  16%|█▌        | 15613/100000 [4:45:21<13:40:07,  1.71it/s]
Train steps ... :  16%|█▌        | 15614/100000 [4:45:22<13:40:08,  1.71it/s]
Train steps ... :  16%|█▌        | 15615/100000 [4:45:23<13:41:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15616/100000 [4:45:23<13:41:20,  1.71it/s]
Train steps ... :  16%|█▌        | 15617/100000 [4:45:24<13:42:02,  1.71it/s]
Train steps ... :  16%|█▌        | 15618/100000 [4:45:24<13:41:38,  1.71it/s]
Train steps ... :  16%|█▌        | 15619/100000 [4:45:25<13:41:14,  1.71it/s]
Train steps ... :  16%|█▌        | 15620/100000 [4:45:26<13:41:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15621/100000 [4:45:26<13:41:38,  1.71it/s]
Train steps ... :  16%|█▌        | 15622/100000 [4:45:27<13:40:52,  1.71it/s]
Train steps ... :  16%|█▌        | 15623/100000 [4:45:27<13:40:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15624/100000 [4:45:28<13:41:33,  1.71it/s]
Train steps ... :  16%|█▌        | 15625/100000 [4:45:28<13:40:31,  1.71it/s]Step... (15625 / 100000 | Loss: 1.3214600086212158, Learning Rate: 8.479899497487438e-05)
+
                                                                             
Step... (15625 / 100000 | Loss: 1.0128319263458252, Learning Rate: 8.479899497487438e-05)
+
Train steps ... :  16%|█▌        | 15625/100000 [4:45:29<13:40:31,  1.71it/s]
Train steps ... :  16%|█▌        | 15626/100000 [4:45:29<13:41:35,  1.71it/s]
Train steps ... :  16%|█▌        | 15627/100000 [4:45:30<13:40:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15628/100000 [4:45:30<13:40:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15629/100000 [4:45:31<13:40:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15630/100000 [4:45:31<13:40:24,  1.71it/s]
Train steps ... :  16%|█▌        | 15631/100000 [4:45:32<13:40:14,  1.71it/s]
Train steps ... :  16%|█▌        | 15632/100000 [4:45:33<13:39:55,  1.71it/s]
Train steps ... :  16%|█▌        | 15633/100000 [4:45:33<13:40:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15634/100000 [4:45:34<13:39:52,  1.72it/s]
Train steps ... :  16%|█▌        | 15635/100000 [4:45:34<13:40:02,  1.71it/s]
Train steps ... :  16%|█▌        | 15636/100000 [4:45:35<13:40:49,  1.71it/s]
Train steps ... :  16%|█▌        | 15637/100000 [4:45:35<13:40:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15638/100000 [4:45:36<13:40:13,  1.71it/s]
Train steps ... :  16%|█▌        | 15639/100000 [4:45:37<13:40:29,  1.71it/s]
Train steps ... :  16%|█▌        | 15640/100000 [4:45:37<13:40:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15641/100000 [4:45:38<13:40:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15642/100000 [4:45:38<13:40:21,  1.71it/s]
Train steps ... :  16%|█▌        | 15643/100000 [4:45:39<13:40:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15644/100000 [4:45:40<13:40:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15645/100000 [4:45:40<13:42:12,  1.71it/s]
Train steps ... :  16%|█▌        | 15646/100000 [4:45:41<13:42:03,  1.71it/s]
Train steps ... :  16%|█▌        | 15647/100000 [4:45:41<13:41:12,  1.71it/s]
Train steps ... :  16%|█▌        | 15648/100000 [4:45:42<13:42:10,  1.71it/s]
Train steps ... :  16%|█▌        | 15649/100000 [4:45:42<13:41:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15650/100000 [4:45:43<13:41:09,  1.71it/s]Step... (15650 / 100000 | Loss: 1.4760446548461914, Learning Rate: 8.477386934673368e-05)
+
                                                                             
Step... (15650 / 100000 | Loss: 1.062575101852417, Learning Rate: 8.477386934673368e-05)
+
Train steps ... :  16%|█▌        | 15650/100000 [4:45:43<13:41:09,  1.71it/s]
Train steps ... :  16%|█▌        | 15651/100000 [4:45:44<13:41:02,  1.71it/s]
Train steps ... :  16%|█▌        | 15652/100000 [4:45:44<13:40:36,  1.71it/s]
Train steps ... :  16%|█▌        | 15653/100000 [4:45:45<13:40:52,  1.71it/s]
Train steps ... :  16%|█▌        | 15654/100000 [4:45:45<13:41:02,  1.71it/s]
Train steps ... :  16%|█▌        | 15655/100000 [4:45:46<13:40:38,  1.71it/s]
Train steps ... :  16%|█▌        | 15656/100000 [4:45:47<13:40:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15657/100000 [4:45:47<13:40:31,  1.71it/s]
Train steps ... :  16%|█▌        | 15658/100000 [4:45:48<13:41:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15659/100000 [4:45:48<13:41:14,  1.71it/s]
Train steps ... :  16%|█▌        | 15660/100000 [4:45:49<13:41:13,  1.71it/s]
Train steps ... :  16%|█▌        | 15661/100000 [4:45:49<13:40:39,  1.71it/s]
Train steps ... :  16%|█▌        | 15662/100000 [4:45:50<13:40:42,  1.71it/s]
Train steps ... :  16%|█▌        | 15663/100000 [4:45:51<13:40:08,  1.71it/s]
Train steps ... :  16%|█▌        | 15664/100000 [4:45:51<13:40:31,  1.71it/s]
Train steps ... :  16%|█▌        | 15665/100000 [4:45:52<13:40:14,  1.71it/s]
Train steps ... :  16%|█▌        | 15666/100000 [4:45:52<13:40:55,  1.71it/s]
Train steps ... :  16%|█▌        | 15667/100000 [4:45:53<13:40:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15668/100000 [4:45:54<13:40:47,  1.71it/s]
Train steps ... :  16%|█▌        | 15669/100000 [4:45:54<13:40:35,  1.71it/s]
Train steps ... :  16%|█▌        | 15670/100000 [4:45:55<13:41:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15671/100000 [4:45:55<13:40:21,  1.71it/s]
Train steps ... :  16%|█▌        | 15672/100000 [4:45:56<13:40:24,  1.71it/s]
Train steps ... :  16%|█▌        | 15673/100000 [4:45:56<13:40:01,  1.71it/s]
Train steps ... :  16%|█▌        | 15674/100000 [4:45:57<13:39:11,  1.72it/s]
Train steps ... :  16%|█▌        | 15675/100000 [4:45:58<13:40:35,  1.71it/s]Step... (15675 / 100000 | Loss: 1.0245189666748047, Learning Rate: 8.474874371859297e-05)
+
                                                                             
Step... (15675 / 100000 | Loss: 1.3461862802505493, Learning Rate: 8.474874371859297e-05)
+
Train steps ... :  16%|█▌        | 15675/100000 [4:45:58<13:40:35,  1.71it/s]
Train steps ... :  16%|█▌        | 15676/100000 [4:45:58<13:40:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15677/100000 [4:45:59<13:40:39,  1.71it/s]
Train steps ... :  16%|█▌        | 15678/100000 [4:45:59<13:39:47,  1.71it/s]
Train steps ... :  16%|█▌        | 15679/100000 [4:46:00<13:39:51,  1.71it/s]
Train steps ... :  16%|█▌        | 15680/100000 [4:46:01<13:39:49,  1.71it/s]
Train steps ... :  16%|█▌        | 15681/100000 [4:46:01<13:40:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15682/100000 [4:46:02<13:39:42,  1.71it/s]
Train steps ... :  16%|█▌        | 15683/100000 [4:46:02<13:39:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15684/100000 [4:46:03<13:40:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15685/100000 [4:46:03<13:40:08,  1.71it/s]
Train steps ... :  16%|█▌        | 15686/100000 [4:46:04<13:39:25,  1.71it/s]
Train steps ... :  16%|█▌        | 15687/100000 [4:46:05<13:39:42,  1.71it/s]
Train steps ... :  16%|█▌        | 15688/100000 [4:46:05<13:39:57,  1.71it/s]
Train steps ... :  16%|█▌        | 15689/100000 [4:46:06<13:39:42,  1.71it/s]
Train steps ... :  16%|█▌        | 15690/100000 [4:46:06<13:39:46,  1.71it/s]
Train steps ... :  16%|█▌        | 15691/100000 [4:46:07<13:39:58,  1.71it/s]
Train steps ... :  16%|█▌        | 15692/100000 [4:46:08<13:39:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15693/100000 [4:46:08<13:39:06,  1.72it/s]
Train steps ... :  16%|█▌        | 15694/100000 [4:46:09<13:39:09,  1.72it/s]
Train steps ... :  16%|█▌        | 15695/100000 [4:46:09<13:38:57,  1.72it/s]
Train steps ... :  16%|█▌        | 15696/100000 [4:46:10<13:39:18,  1.71it/s]
Train steps ... :  16%|█▌        | 15697/100000 [4:46:10<13:41:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15698/100000 [4:46:11<13:41:03,  1.71it/s]
Train steps ... :  16%|█▌        | 15699/100000 [4:46:12<13:43:35,  1.71it/s]
Train steps ... :  16%|█▌        | 15700/100000 [4:46:12<13:42:52,  1.71it/s]Step... (15700 / 100000 | Loss: 1.117264747619629, Learning Rate: 8.472361809045226e-05)
+
                                                                             
Step... (15700 / 100000 | Loss: 0.9669854044914246, Learning Rate: 8.472361809045226e-05)
+
Train steps ... :  16%|█▌        | 15700/100000 [4:46:13<13:42:52,  1.71it/s]
Train steps ... :  16%|█▌        | 15701/100000 [4:46:13<13:43:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15702/100000 [4:46:13<13:41:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15703/100000 [4:46:14<13:40:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15704/100000 [4:46:15<13:40:48,  1.71it/s]
Train steps ... :  16%|█▌        | 15705/100000 [4:46:15<13:40:27,  1.71it/s]
Train steps ... :  16%|█▌        | 15706/100000 [4:46:16<13:39:51,  1.71it/s]
Train steps ... :  16%|█▌        | 15707/100000 [4:46:16<13:40:47,  1.71it/s]
Train steps ... :  16%|█▌        | 15708/100000 [4:46:17<13:41:00,  1.71it/s]
Train steps ... :  16%|█▌        | 15709/100000 [4:46:17<13:41:19,  1.71it/s]
Train steps ... :  16%|█▌        | 15710/100000 [4:46:18<13:39:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15711/100000 [4:46:19<13:39:48,  1.71it/s]
Train steps ... :  16%|█▌        | 15712/100000 [4:46:19<13:39:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15713/100000 [4:46:20<13:40:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15714/100000 [4:46:20<13:39:45,  1.71it/s]
Train steps ... :  16%|█▌        | 15715/100000 [4:46:21<13:40:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15716/100000 [4:46:22<13:42:17,  1.71it/s]
Train steps ... :  16%|█▌        | 15717/100000 [4:46:22<13:41:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15718/100000 [4:46:23<13:41:53,  1.71it/s]
Train steps ... :  16%|█▌        | 15719/100000 [4:46:23<13:41:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15720/100000 [4:46:24<13:44:56,  1.70it/s]
Train steps ... :  16%|█▌        | 15721/100000 [4:46:24<13:41:38,  1.71it/s]
Train steps ... :  16%|█▌        | 15722/100000 [4:46:25<13:43:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15723/100000 [4:46:26<13:42:01,  1.71it/s]
Train steps ... :  16%|█▌        | 15724/100000 [4:46:26<13:41:21,  1.71it/s]
Train steps ... :  16%|█▌        | 15725/100000 [4:46:27<13:40:34,  1.71it/s]Step... (15725 / 100000 | Loss: 1.133278250694275, Learning Rate: 8.469849246231157e-05)
+
                                                                             
Step... (15725 / 100000 | Loss: 1.2293157577514648, Learning Rate: 8.469849246231157e-05)
+
Train steps ... :  16%|█▌        | 15725/100000 [4:46:27<13:40:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15726/100000 [4:46:27<13:40:13,  1.71it/s]
Train steps ... :  16%|█▌        | 15727/100000 [4:46:28<13:40:01,  1.71it/s]
Train steps ... :  16%|█▌        | 15728/100000 [4:46:29<13:39:21,  1.71it/s]
Train steps ... :  16%|█▌        | 15729/100000 [4:46:29<13:39:18,  1.71it/s]
Train steps ... :  16%|█▌        | 15730/100000 [4:46:30<13:39:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15731/100000 [4:46:30<13:39:43,  1.71it/s]
Train steps ... :  16%|█▌        | 15732/100000 [4:46:31<13:39:18,  1.71it/s]
Train steps ... :  16%|█▌        | 15733/100000 [4:46:32<13:39:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15734/100000 [4:46:32<13:40:19,  1.71it/s]
Train steps ... :  16%|█▌        | 15735/100000 [4:46:33<13:41:02,  1.71it/s]
Train steps ... :  16%|█▌        | 15736/100000 [4:46:33<13:41:14,  1.71it/s]
Train steps ... :  16%|█▌        | 15737/100000 [4:46:34<13:40:31,  1.71it/s]
Train steps ... :  16%|█▌        | 15738/100000 [4:46:34<13:39:03,  1.71it/s]
Train steps ... :  16%|█▌        | 15739/100000 [4:46:35<13:38:25,  1.72it/s]
Train steps ... :  16%|█▌        | 15740/100000 [4:46:36<13:38:23,  1.72it/s]
Train steps ... :  16%|█▌        | 15741/100000 [4:46:36<13:38:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15742/100000 [4:46:37<13:40:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15743/100000 [4:46:37<13:39:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15744/100000 [4:46:38<13:40:09,  1.71it/s]
Train steps ... :  16%|█▌        | 15745/100000 [4:46:39<13:39:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15746/100000 [4:46:39<13:39:39,  1.71it/s]
Train steps ... :  16%|█▌        | 15747/100000 [4:46:40<13:39:42,  1.71it/s]
Train steps ... :  16%|█▌        | 15748/100000 [4:46:40<13:40:38,  1.71it/s]
Train steps ... :  16%|█▌        | 15749/100000 [4:46:41<13:40:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15750/100000 [4:46:41<13:39:32,  1.71it/s]Step... (15750 / 100000 | Loss: 1.1687966585159302, Learning Rate: 8.467336683417085e-05)
+
                                                                             
Step... (15750 / 100000 | Loss: 0.8547934293746948, Learning Rate: 8.467336683417085e-05)
+
Train steps ... :  16%|█▌        | 15750/100000 [4:46:42<13:39:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15751/100000 [4:46:42<13:39:46,  1.71it/s]
Train steps ... :  16%|█▌        | 15752/100000 [4:46:43<13:40:49,  1.71it/s]
Train steps ... :  16%|█▌        | 15753/100000 [4:46:43<13:40:03,  1.71it/s]
Train steps ... :  16%|█▌        | 15754/100000 [4:46:44<13:39:57,  1.71it/s]
Train steps ... :  16%|█▌        | 15755/100000 [4:46:44<13:39:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15756/100000 [4:46:45<13:39:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15757/100000 [4:46:46<13:38:35,  1.72it/s]
Train steps ... :  16%|█▌        | 15758/100000 [4:46:46<13:39:09,  1.71it/s]
Train steps ... :  16%|█▌        | 15759/100000 [4:46:47<13:39:00,  1.71it/s]
Train steps ... :  16%|█▌        | 15760/100000 [4:46:47<13:39:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15761/100000 [4:46:48<13:40:08,  1.71it/s]
Train steps ... :  16%|█▌        | 15762/100000 [4:46:48<13:39:01,  1.71it/s]
Train steps ... :  16%|█▌        | 15763/100000 [4:46:49<13:39:15,  1.71it/s]
Train steps ... :  16%|█▌        | 15764/100000 [4:46:50<13:39:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15765/100000 [4:46:50<13:39:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15766/100000 [4:46:51<13:39:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15767/100000 [4:46:51<13:39:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15768/100000 [4:46:52<13:38:55,  1.71it/s]
Train steps ... :  16%|█▌        | 15769/100000 [4:46:53<13:39:41,  1.71it/s]
Train steps ... :  16%|█▌        | 15770/100000 [4:46:53<13:38:40,  1.71it/s]
Train steps ... :  16%|█▌        | 15771/100000 [4:46:54<13:39:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15772/100000 [4:46:54<13:39:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15773/100000 [4:46:55<13:39:48,  1.71it/s]
Train steps ... :  16%|█▌        | 15774/100000 [4:46:55<13:40:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15775/100000 [4:46:56<13:41:20,  1.71it/s]Step... (15775 / 100000 | Loss: 0.9263899326324463, Learning Rate: 8.464824120603016e-05)
+
                                                                             
Step... (15775 / 100000 | Loss: 0.874395489692688, Learning Rate: 8.464824120603016e-05)
+
Train steps ... :  16%|█▌        | 15775/100000 [4:46:56<13:41:20,  1.71it/s]
Train steps ... :  16%|█▌        | 15776/100000 [4:46:57<13:40:03,  1.71it/s]
Train steps ... :  16%|█▌        | 15777/100000 [4:46:57<13:41:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15778/100000 [4:46:58<13:40:43,  1.71it/s]
Train steps ... :  16%|█▌        | 15779/100000 [4:46:58<13:40:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15780/100000 [4:46:59<13:40:47,  1.71it/s]
Train steps ... :  16%|█▌        | 15781/100000 [4:47:00<13:40:01,  1.71it/s]
Train steps ... :  16%|█▌        | 15782/100000 [4:47:00<13:40:45,  1.71it/s]
Train steps ... :  16%|█▌        | 15783/100000 [4:47:01<13:40:08,  1.71it/s]
Train steps ... :  16%|█▌        | 15784/100000 [4:47:01<13:39:47,  1.71it/s]
Train steps ... :  16%|█▌        | 15785/100000 [4:47:02<13:39:29,  1.71it/s]
Train steps ... :  16%|█▌        | 15786/100000 [4:47:02<13:40:14,  1.71it/s]
Train steps ... :  16%|█▌        | 15787/100000 [4:47:03<13:40:14,  1.71it/s]
Train steps ... :  16%|█▌        | 15788/100000 [4:47:04<13:40:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15789/100000 [4:47:04<13:40:09,  1.71it/s]
Train steps ... :  16%|█▌        | 15790/100000 [4:47:05<13:39:53,  1.71it/s]
Train steps ... :  16%|█▌        | 15791/100000 [4:47:05<13:39:25,  1.71it/s]
Train steps ... :  16%|█▌        | 15792/100000 [4:47:06<13:39:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15793/100000 [4:47:07<13:39:46,  1.71it/s]
Train steps ... :  16%|█▌        | 15794/100000 [4:47:07<13:39:22,  1.71it/s]
Train steps ... :  16%|█▌        | 15795/100000 [4:47:08<13:39:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15796/100000 [4:47:08<13:39:00,  1.71it/s]
Train steps ... :  16%|█▌        | 15797/100000 [4:47:09<13:39:40,  1.71it/s]
Train steps ... :  16%|█▌        | 15798/100000 [4:47:09<13:39:31,  1.71it/s]
Train steps ... :  16%|█▌        | 15799/100000 [4:47:10<13:39:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15800/100000 [4:47:11<13:39:11,  1.71it/s]Step... (15800 / 100000 | Loss: 1.460836410522461, Learning Rate: 8.462311557788946e-05)
+
                                                                             
Step... (15800 / 100000 | Loss: 1.074571132659912, Learning Rate: 8.462311557788946e-05)
+
Train steps ... :  16%|█▌        | 15800/100000 [4:47:11<13:39:11,  1.71it/s]
Train steps ... :  16%|█▌        | 15801/100000 [4:47:11<13:39:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15802/100000 [4:47:12<13:39:25,  1.71it/s]
Train steps ... :  16%|█▌        | 15803/100000 [4:47:12<13:38:39,  1.71it/s]
Train steps ... :  16%|█▌        | 15804/100000 [4:47:13<13:39:11,  1.71it/s]
Train steps ... :  16%|█▌        | 15805/100000 [4:47:14<13:40:36,  1.71it/s]
Train steps ... :  16%|█▌        | 15806/100000 [4:47:14<13:40:07,  1.71it/s]
Train steps ... :  16%|█▌        | 15807/100000 [4:47:15<13:39:51,  1.71it/s]
Train steps ... :  16%|█▌        | 15808/100000 [4:47:15<13:38:55,  1.71it/s]
Train steps ... :  16%|█▌        | 15809/100000 [4:47:16<13:39:42,  1.71it/s]
Train steps ... :  16%|█▌        | 15810/100000 [4:47:16<13:38:54,  1.71it/s]
Train steps ... :  16%|█▌        | 15811/100000 [4:47:17<13:39:42,  1.71it/s]
Train steps ... :  16%|█▌        | 15812/100000 [4:47:18<13:39:08,  1.71it/s]
Train steps ... :  16%|█▌        | 15813/100000 [4:47:18<13:39:21,  1.71it/s]
Train steps ... :  16%|█▌        | 15814/100000 [4:47:19<13:39:57,  1.71it/s]
Train steps ... :  16%|█▌        | 15815/100000 [4:47:19<13:39:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15816/100000 [4:47:20<13:39:09,  1.71it/s]
Train steps ... :  16%|█▌        | 15817/100000 [4:47:21<13:39:39,  1.71it/s]
Train steps ... :  16%|█▌        | 15818/100000 [4:47:21<13:39:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15819/100000 [4:47:22<13:38:43,  1.71it/s]
Train steps ... :  16%|█▌        | 15820/100000 [4:47:22<13:38:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15821/100000 [4:47:23<13:39:43,  1.71it/s]
Train steps ... :  16%|█▌        | 15822/100000 [4:47:23<13:40:25,  1.71it/s]
Train steps ... :  16%|█▌        | 15823/100000 [4:47:24<13:40:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15824/100000 [4:47:25<13:41:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15825/100000 [4:47:25<13:38:42,  1.71it/s]Step... (15825 / 100000 | Loss: 1.5445630550384521, Learning Rate: 8.459798994974875e-05)
+
                                                                             
Step... (15825 / 100000 | Loss: 1.2437124252319336, Learning Rate: 8.459798994974875e-05)
+
Train steps ... :  16%|█▌        | 15825/100000 [4:47:26<13:38:42,  1.71it/s]
Train steps ... :  16%|█▌        | 15826/100000 [4:47:26<13:38:58,  1.71it/s]
Train steps ... :  16%|█▌        | 15827/100000 [4:47:26<13:38:31,  1.71it/s]
Train steps ... :  16%|█▌        | 15828/100000 [4:47:27<13:39:25,  1.71it/s]
Train steps ... :  16%|█▌        | 15829/100000 [4:47:28<13:38:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15830/100000 [4:47:28<13:38:51,  1.71it/s]
Train steps ... :  16%|█▌        | 15831/100000 [4:47:29<13:39:26,  1.71it/s]
Train steps ... :  16%|█▌        | 15832/100000 [4:47:29<13:39:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15833/100000 [4:47:30<13:38:51,  1.71it/s]
Train steps ... :  16%|█▌        | 15834/100000 [4:47:30<13:38:36,  1.71it/s]
Train steps ... :  16%|█▌        | 15835/100000 [4:47:31<13:39:57,  1.71it/s]
Train steps ... :  16%|█▌        | 15836/100000 [4:47:32<13:40:27,  1.71it/s]
Train steps ... :  16%|█▌        | 15837/100000 [4:47:32<13:39:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15838/100000 [4:47:33<13:40:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15839/100000 [4:47:33<13:39:19,  1.71it/s]
Train steps ... :  16%|█▌        | 15840/100000 [4:47:34<13:39:13,  1.71it/s]
Train steps ... :  16%|█▌        | 15841/100000 [4:47:35<13:39:38,  1.71it/s]
Train steps ... :  16%|█▌        | 15842/100000 [4:47:35<13:39:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15843/100000 [4:47:36<13:39:12,  1.71it/s]
Train steps ... :  16%|█▌        | 15844/100000 [4:47:36<13:38:51,  1.71it/s]
Train steps ... :  16%|█▌        | 15845/100000 [4:47:37<13:38:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15846/100000 [4:47:37<13:39:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15847/100000 [4:47:38<13:38:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15848/100000 [4:47:39<13:38:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15849/100000 [4:47:39<13:38:14,  1.71it/s]
Train steps ... :  16%|█▌        | 15850/100000 [4:47:40<13:39:10,  1.71it/s]Step... (15850 / 100000 | Loss: 1.4742166996002197, Learning Rate: 8.457286432160805e-05)
+
                                                                             
Step... (15850 / 100000 | Loss: 0.9632929563522339, Learning Rate: 8.457286432160805e-05)
+
Train steps ... :  16%|█▌        | 15850/100000 [4:47:40<13:39:10,  1.71it/s]
Train steps ... :  16%|█▌        | 15851/100000 [4:47:40<13:39:26,  1.71it/s]
Train steps ... :  16%|█▌        | 15852/100000 [4:47:41<13:39:04,  1.71it/s]
Train steps ... :  16%|█▌        | 15853/100000 [4:47:42<13:39:11,  1.71it/s]
Train steps ... :  16%|█▌        | 15854/100000 [4:47:42<13:38:53,  1.71it/s]
Train steps ... :  16%|█▌        | 15855/100000 [4:47:43<13:38:33,  1.71it/s]
Train steps ... :  16%|█▌        | 15856/100000 [4:47:43<13:39:17,  1.71it/s]
Train steps ... :  16%|█▌        | 15857/100000 [4:47:44<13:38:40,  1.71it/s]
Train steps ... :  16%|█▌        | 15858/100000 [4:47:45<13:38:43,  1.71it/s]
Train steps ... :  16%|█▌        | 15859/100000 [4:47:45<13:39:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15860/100000 [4:47:46<13:39:04,  1.71it/s]
Train steps ... :  16%|█▌        | 15861/100000 [4:47:46<13:39:01,  1.71it/s]
Train steps ... :  16%|█▌        | 15862/100000 [4:47:47<13:39:40,  1.71it/s]
Train steps ... :  16%|█▌        | 15863/100000 [4:47:47<13:39:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15864/100000 [4:47:48<13:39:07,  1.71it/s]
Train steps ... :  16%|█▌        | 15865/100000 [4:47:49<13:38:40,  1.71it/s]
Train steps ... :  16%|█▌        | 15866/100000 [4:47:49<13:38:55,  1.71it/s]
Train steps ... :  16%|█▌        | 15867/100000 [4:47:50<13:38:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15868/100000 [4:47:50<13:38:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15869/100000 [4:47:51<13:37:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15870/100000 [4:47:52<13:37:40,  1.71it/s]
Train steps ... :  16%|█▌        | 15871/100000 [4:47:52<13:37:59,  1.71it/s]
Train steps ... :  16%|█▌        | 15872/100000 [4:47:53<13:37:55,  1.71it/s]
Train steps ... :  16%|█▌        | 15873/100000 [4:47:53<13:38:41,  1.71it/s]
Train steps ... :  16%|█▌        | 15874/100000 [4:47:54<13:38:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15875/100000 [4:47:54<13:38:26,  1.71it/s]Step... (15875 / 100000 | Loss: 0.8951094150543213, Learning Rate: 8.454773869346733e-05)
+
                                                                             
Step... (15875 / 100000 | Loss: 1.030731201171875, Learning Rate: 8.454773869346733e-05)
+
Train steps ... :  16%|█▌        | 15875/100000 [4:47:55<13:38:26,  1.71it/s]
Train steps ... :  16%|█▌        | 15876/100000 [4:47:55<13:38:43,  1.71it/s]
Train steps ... :  16%|█▌        | 15877/100000 [4:47:56<13:38:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15878/100000 [4:47:56<13:38:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15879/100000 [4:47:57<13:38:26,  1.71it/s]
Train steps ... :  16%|█▌        | 15880/100000 [4:47:57<13:38:12,  1.71it/s]
Train steps ... :  16%|█▌        | 15881/100000 [4:47:58<13:38:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15882/100000 [4:47:59<13:38:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15883/100000 [4:47:59<13:39:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15884/100000 [4:48:00<13:41:10,  1.71it/s]
Train steps ... :  16%|█▌        | 15885/100000 [4:48:00<13:40:07,  1.71it/s]
Train steps ... :  16%|█▌        | 15886/100000 [4:48:01<13:40:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15887/100000 [4:48:01<13:39:17,  1.71it/s]
Train steps ... :  16%|█▌        | 15888/100000 [4:48:02<13:39:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15889/100000 [4:48:03<13:39:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15890/100000 [4:48:03<13:38:44,  1.71it/s]
Train steps ... :  16%|█��        | 15891/100000 [4:48:04<13:39:41,  1.71it/s]
Train steps ... :  16%|█▌        | 15892/100000 [4:48:04<13:40:01,  1.71it/s]
Train steps ... :  16%|█▌        | 15893/100000 [4:48:05<13:39:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15894/100000 [4:48:06<13:39:31,  1.71it/s]
Train steps ... :  16%|█▌        | 15895/100000 [4:48:06<13:39:51,  1.71it/s]
Train steps ... :  16%|█▌        | 15896/100000 [4:48:07<13:39:17,  1.71it/s]
Train steps ... :  16%|█▌        | 15897/100000 [4:48:07<13:38:17,  1.71it/s]
Train steps ... :  16%|█▌        | 15898/100000 [4:48:08<13:38:39,  1.71it/s]
Train steps ... :  16%|█▌        | 15899/100000 [4:48:08<13:38:10,  1.71it/s]
Train steps ... :  16%|█▌        | 15900/100000 [4:48:09<13:39:01,  1.71it/s]Step... (15900 / 100000 | Loss: 1.5292800664901733, Learning Rate: 8.452261306532664e-05)
+
                                                                             
Step... (15900 / 100000 | Loss: 1.1978480815887451, Learning Rate: 8.452261306532664e-05)
+
Train steps ... :  16%|█▌        | 15900/100000 [4:48:09<13:39:01,  1.71it/s]
Train steps ... :  16%|█▌        | 15901/100000 [4:48:10<13:38:58,  1.71it/s]
Train steps ... :  16%|█▌        | 15902/100000 [4:48:10<13:38:29,  1.71it/s]
Train steps ... :  16%|█▌        | 15903/100000 [4:48:11<13:38:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15904/100000 [4:48:11<13:38:02,  1.71it/s]
Train steps ... :  16%|█▌        | 15905/100000 [4:48:12<13:37:59,  1.71it/s]
Train steps ... :  16%|█▌        | 15906/100000 [4:48:13<13:37:46,  1.71it/s]
Train steps ... :  16%|█▌        | 15907/100000 [4:48:13<13:37:06,  1.72it/s]
Train steps ... :  16%|█▌        | 15908/100000 [4:48:14<13:37:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15909/100000 [4:48:14<13:37:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15910/100000 [4:48:15<13:38:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15911/100000 [4:48:15<13:37:59,  1.71it/s]
Train steps ... :  16%|█▌        | 15912/100000 [4:48:16<13:37:59,  1.71it/s]
Train steps ... :  16%|█▌        | 15913/100000 [4:48:17<13:38:48,  1.71it/s]
Train steps ... :  16%|█▌        | 15914/100000 [4:48:17<13:39:12,  1.71it/s]
Train steps ... :  16%|█▌        | 15915/100000 [4:48:18<13:39:25,  1.71it/s]
Train steps ... :  16%|█▌        | 15916/100000 [4:48:18<13:39:03,  1.71it/s]
Train steps ... :  16%|█▌        | 15917/100000 [4:48:19<13:38:18,  1.71it/s]
Train steps ... :  16%|█▌        | 15918/100000 [4:48:20<13:38:07,  1.71it/s]
Train steps ... :  16%|█▌        | 15919/100000 [4:48:20<13:38:19,  1.71it/s]
Train steps ... :  16%|█▌        | 15920/100000 [4:48:21<13:38:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15921/100000 [4:48:21<13:38:48,  1.71it/s]
Train steps ... :  16%|█▌        | 15922/100000 [4:48:22<13:38:12,  1.71it/s]
Train steps ... :  16%|█▌        | 15923/100000 [4:48:22<13:37:59,  1.71it/s]
Train steps ... :  16%|█▌        | 15924/100000 [4:48:23<13:37:57,  1.71it/s]
Train steps ... :  16%|█▌        | 15925/100000 [4:48:24<13:39:37,  1.71it/s]Step... (15925 / 100000 | Loss: 0.9045276641845703, Learning Rate: 8.449748743718592e-05)
+
                                                                             
Step... (15925 / 100000 | Loss: 0.9448001384735107, Learning Rate: 8.449748743718592e-05)
+
Train steps ... :  16%|█▌        | 15925/100000 [4:48:24<13:39:37,  1.71it/s]
Train steps ... :  16%|█▌        | 15926/100000 [4:48:24<13:38:39,  1.71it/s]
Train steps ... :  16%|█▌        | 15927/100000 [4:48:25<13:38:32,  1.71it/s]
Train steps ... :  16%|█▌        | 15928/100000 [4:48:25<13:39:05,  1.71it/s]
Train steps ... :  16%|█▌        | 15929/100000 [4:48:26<13:37:56,  1.71it/s]
Train steps ... :  16%|█▌        | 15930/100000 [4:48:27<13:37:46,  1.71it/s]
Train steps ... :  16%|█▌        | 15931/100000 [4:48:27<13:38:17,  1.71it/s]
Train steps ... :  16%|█▌        | 15932/100000 [4:48:28<13:38:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15933/100000 [4:48:28<13:37:51,  1.71it/s]
Train steps ... :  16%|█▌        | 15934/100000 [4:48:29<13:37:35,  1.71it/s]
Train steps ... :  16%|█▌        | 15935/100000 [4:48:29<13:37:22,  1.71it/s]
Train steps ... :  16%|█▌        | 15936/100000 [4:48:30<13:37:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15937/100000 [4:48:31<13:37:22,  1.71it/s]
Train steps ... :  16%|█▌        | 15938/100000 [4:48:31<13:37:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15939/100000 [4:48:32<13:37:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15940/100000 [4:48:32<13:37:36,  1.71it/s]
Train steps ... :  16%|█▌        | 15941/100000 [4:48:33<13:37:20,  1.71it/s]
Train steps ... :  16%|█▌        | 15942/100000 [4:48:34<13:37:25,  1.71it/s]
Train steps ... :  16%|█▌        | 15943/100000 [4:48:34<13:37:53,  1.71it/s]
Train steps ... :  16%|█▌        | 15944/100000 [4:48:35<13:37:46,  1.71it/s]
Train steps ... :  16%|█▌        | 15945/100000 [4:48:35<13:38:18,  1.71it/s]
Train steps ... :  16%|█▌        | 15946/100000 [4:48:36<13:38:35,  1.71it/s]
Train steps ... :  16%|█▌        | 15947/100000 [4:48:36<13:40:04,  1.71it/s]
Train steps ... :  16%|█▌        | 15948/100000 [4:48:37<13:37:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15949/100000 [4:48:38<13:39:07,  1.71it/s]
Train steps ... :  16%|█▌        | 15950/100000 [4:48:38<13:38:46,  1.71it/s]Step... (15950 / 100000 | Loss: 1.1064884662628174, Learning Rate: 8.447236180904524e-05)
+
                                                                             
Step... (15950 / 100000 | Loss: 1.6780591011047363, Learning Rate: 8.447236180904524e-05)
+
Train steps ... :  16%|█▌        | 15950/100000 [4:48:39<13:38:46,  1.71it/s]
Train steps ... :  16%|█▌        | 15951/100000 [4:48:39<13:38:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15952/100000 [4:48:39<13:38:17,  1.71it/s]
Train steps ... :  16%|█▌        | 15953/100000 [4:48:40<13:37:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15954/100000 [4:48:41<13:38:37,  1.71it/s]
Train steps ... :  16%|█▌        | 15955/100000 [4:48:41<13:37:59,  1.71it/s]
Train steps ... :  16%|█▌        | 15956/100000 [4:48:42<13:38:00,  1.71it/s]
Train steps ... :  16%|█▌        | 15957/100000 [4:48:42<13:37:59,  1.71it/s]
Train steps ... :  16%|█▌        | 15958/100000 [4:48:43<13:37:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15959/100000 [4:48:43<13:37:09,  1.71it/s]
Train steps ... :  16%|█▌        | 15960/100000 [4:48:44<13:36:57,  1.71it/s]
Train steps ... :  16%|█▌        | 15961/100000 [4:48:45<13:37:17,  1.71it/s]
Train steps ... :  16%|█▌        | 15962/100000 [4:48:45<13:38:20,  1.71it/s]
Train steps ... :  16%|█▌        | 15963/100000 [4:48:46<13:38:06,  1.71it/s]
Train steps ... :  16%|█▌        | 15964/100000 [4:48:46<13:37:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15965/100000 [4:48:47<13:37:37,  1.71it/s]
Train steps ... :  16%|█▌        | 15966/100000 [4:48:48<13:37:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15967/100000 [4:48:48<13:37:15,  1.71it/s]
Train steps ... :  16%|█▌        | 15968/100000 [4:48:49<13:37:04,  1.71it/s]
Train steps ... :  16%|█▌        | 15969/100000 [4:48:49<13:37:39,  1.71it/s]
Train steps ... :  16%|█▌        | 15970/100000 [4:48:50<13:37:33,  1.71it/s]
Train steps ... :  16%|█▌        | 15971/100000 [4:48:50<13:37:03,  1.71it/s]
Train steps ... :  16%|█▌        | 15972/100000 [4:48:51<13:37:40,  1.71it/s]
Train steps ... :  16%|█▌        | 15973/100000 [4:48:52<13:36:50,  1.71it/s]
Train steps ... :  16%|█▌        | 15974/100000 [4:48:52<13:37:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15975/100000 [4:48:53<13:37:33,  1.71it/s]Step... (15975 / 100000 | Loss: 0.9002241492271423, Learning Rate: 8.444723618090453e-05)
+
                                                                             
Step... (15975 / 100000 | Loss: 1.6666220426559448, Learning Rate: 8.444723618090453e-05)
+
Train steps ... :  16%|█▌        | 15975/100000 [4:48:53<13:37:33,  1.71it/s]
Train steps ... :  16%|█▌        | 15976/100000 [4:48:53<13:37:19,  1.71it/s]
Train steps ... :  16%|█▌        | 15977/100000 [4:48:54<13:38:29,  1.71it/s]
Train steps ... :  16%|█▌        | 15978/100000 [4:48:55<13:37:52,  1.71it/s]
Train steps ... :  16%|█▌        | 15979/100000 [4:48:55<13:39:28,  1.71it/s]
Train steps ... :  16%|█▌        | 15980/100000 [4:48:56<13:39:27,  1.71it/s]
Train steps ... :  16%|█▌        | 15981/100000 [4:48:56<13:39:11,  1.71it/s]
Train steps ... :  16%|█▌        | 15982/100000 [4:48:57<13:38:07,  1.71it/s]
Train steps ... :  16%|█▌        | 15983/100000 [4:48:58<13:37:45,  1.71it/s]
Train steps ... :  16%|█▌        | 15984/100000 [4:48:58<13:38:35,  1.71it/s]
Train steps ... :  16%|█▌        | 15985/100000 [4:48:59<13:37:52,  1.71it/s]
Train steps ... :  16%|█▌        | 15986/100000 [4:48:59<13:38:35,  1.71it/s]
Train steps ... :  16%|█▌        | 15987/100000 [4:49:00<13:39:02,  1.71it/s]
Train steps ... :  16%|█▌        | 15988/100000 [4:49:00<13:39:07,  1.71it/s]
Train steps ... :  16%|█▌        | 15989/100000 [4:49:01<13:38:12,  1.71it/s]
Train steps ... :  16%|█▌        | 15990/100000 [4:49:02<13:38:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15991/100000 [4:49:02<13:37:44,  1.71it/s]
Train steps ... :  16%|█▌        | 15992/100000 [4:49:03<13:37:30,  1.71it/s]
Train steps ... :  16%|█▌        | 15993/100000 [4:49:03<13:38:35,  1.71it/s]
Train steps ... :  16%|█▌        | 15994/100000 [4:49:04<13:37:34,  1.71it/s]
Train steps ... :  16%|█▌        | 15995/100000 [4:49:05<13:40:16,  1.71it/s]
Train steps ... :  16%|█▌        | 15996/100000 [4:49:05<13:37:07,  1.71it/s]
Train steps ... :  16%|█▌        | 15997/100000 [4:49:06<13:37:04,  1.71it/s]
Train steps ... :  16%|█▌        | 15998/100000 [4:49:06<13:38:23,  1.71it/s]
Train steps ... :  16%|█▌        | 15999/100000 [4:49:07<13:38:20,  1.71it/s]
Train steps ... :  16%|█▌        | 16000/100000 [4:49:07<13:38:35,  1.71it/s]Step... (16000 / 100000 | Loss: 1.3481184244155884, Learning Rate: 8.442211055276383e-05)
+
                                                                             
Step... (16000 / 100000 | Loss: 1.1225595474243164, Learning Rate: 8.442211055276383e-05)
+
Train steps ... :  16%|█▌        | 16000/100000 [4:49:08<13:38:35,  1.71it/s]
Train steps ... :  16%|█▌        | 16001/100000 [4:49:08<13:39:48,  1.71it/s]
Train steps ... :  16%|█▌        | 16002/100000 [4:49:09<13:37:46,  1.71it/s]
Train steps ... :  16%|█▌        | 16003/100000 [4:49:09<13:37:35,  1.71it/s]
Train steps ... :  16%|█▌        | 16004/100000 [4:49:10<13:37:38,  1.71it/s]
Train steps ... :  16%|█▌        | 16005/100000 [4:49:10<13:37:33,  1.71it/s]
Train steps ... :  16%|█▌        | 16006/100000 [4:49:11<13:36:54,  1.71it/s]
Train steps ... :  16%|█▌        | 16007/100000 [4:49:12<13:36:22,  1.71it/s]
Train steps ... :  16%|█▌        | 16008/100000 [4:49:12<13:36:36,  1.71it/s]
Train steps ... :  16%|█▌        | 16009/100000 [4:49:13<13:37:54,  1.71it/s]
Train steps ... :  16%|█▌        | 16010/100000 [4:49:13<13:38:20,  1.71it/s]
Train steps ... :  16%|█▌        | 16011/100000 [4:49:14<13:38:50,  1.71it/s]
Train steps ... :  16%|█▌        | 16012/100000 [4:49:14<13:38:55,  1.71it/s]
Train steps ... :  16%|█▌        | 16013/100000 [4:49:15<13:38:22,  1.71it/s]
Train steps ... :  16%|█▌        | 16014/100000 [4:49:16<13:38:06,  1.71it/s]
Train steps ... :  16%|█▌        | 16015/100000 [4:49:16<13:38:09,  1.71it/s]
Train steps ... :  16%|█▌        | 16016/100000 [4:49:17<13:37:43,  1.71it/s]
Train steps ... :  16%|█▌        | 16017/100000 [4:49:17<13:37:56,  1.71it/s]
Train steps ... :  16%|█▌        | 16018/100000 [4:49:18<13:37:35,  1.71it/s]
Train steps ... :  16%|█▌        | 16019/100000 [4:49:19<13:37:42,  1.71it/s]
Train steps ... :  16%|█▌        | 16020/100000 [4:49:19<13:37:20,  1.71it/s]
Train steps ... :  16%|█▌        | 16021/100000 [4:49:20<13:36:59,  1.71it/s]
Train steps ... :  16%|█▌        | 16022/100000 [4:49:20<13:36:40,  1.71it/s]
Train steps ... :  16%|█▌        | 16023/100000 [4:49:21<13:37:42,  1.71it/s]
Train steps ... :  16%|█▌        | 16024/100000 [4:49:21<13:37:01,  1.71it/s]
Train steps ... :  16%|█▌        | 16025/100000 [4:49:22<13:37:04,  1.71it/s]Step... (16025 / 100000 | Loss: 1.0708054304122925, Learning Rate: 8.439698492462313e-05)
+
                                                                             
Step... (16025 / 100000 | Loss: 1.2045308351516724, Learning Rate: 8.439698492462313e-05)
+
Train steps ... :  16%|█▌        | 16025/100000 [4:49:22<13:37:04,  1.71it/s]
Train steps ... :  16%|█▌        | 16026/100000 [4:49:23<13:37:30,  1.71it/s]
Train steps ... :  16%|█▌        | 16027/100000 [4:49:23<13:38:31,  1.71it/s]
Train steps ... :  16%|█▌        | 16028/100000 [4:49:24<13:39:48,  1.71it/s]
Train steps ... :  16%|█▌        | 16029/100000 [4:49:24<13:38:20,  1.71it/s]
Train steps ... :  16%|█▌        | 16030/100000 [4:49:25<13:37:46,  1.71it/s]
Train steps ... :  16%|█▌        | 16031/100000 [4:49:26<13:37:43,  1.71it/s]
Train steps ... :  16%|█▌        | 16032/100000 [4:49:26<13:37:20,  1.71it/s]
Train steps ... :  16%|█▌        | 16033/100000 [4:49:27<13:36:48,  1.71it/s]
Train steps ... :  16%|█▌        | 16034/100000 [4:49:27<13:36:24,  1.71it/s]
Train steps ... :  16%|█▌        | 16035/100000 [4:49:28<13:36:38,  1.71it/s]
Train steps ... :  16%|█▌        | 16036/100000 [4:49:28<13:37:09,  1.71it/s]
Train steps ... :  16%|█▌        | 16037/100000 [4:49:29<13:36:33,  1.71it/s]
Train steps ... :  16%|█▌        | 16038/100000 [4:49:30<13:36:37,  1.71it/s]
Train steps ... :  16%|█▌        | 16039/100000 [4:49:30<13:37:11,  1.71it/s]
Train steps ... :  16%|█▌        | 16040/100000 [4:49:31<13:36:53,  1.71it/s]
Train steps ... :  16%|█▌        | 16041/100000 [4:49:31<13:37:33,  1.71it/s]
Train steps ... :  16%|█▌        | 16042/100000 [4:49:32<13:37:18,  1.71it/s]
Train steps ... :  16%|█▌        | 16043/100000 [4:49:33<13:39:30,  1.71it/s]
Train steps ... :  16%|█▌        | 16044/100000 [4:49:33<13:39:00,  1.71it/s]
Train steps ... :  16%|█▌        | 16045/100000 [4:49:34<13:38:52,  1.71it/s]
Train steps ... :  16%|█▌        | 16046/100000 [4:49:34<13:37:54,  1.71it/s]
Train steps ... :  16%|█▌        | 16047/100000 [4:49:35<13:39:05,  1.71it/s]
Train steps ... :  16%|█▌        | 16048/100000 [4:49:35<13:38:19,  1.71it/s]
Train steps ... :  16%|█▌        | 16049/100000 [4:49:36<13:38:57,  1.71it/s]
Train steps ... :  16%|█▌        | 16050/100000 [4:49:37<13:38:21,  1.71it/s]Step... (16050 / 100000 | Loss: 1.1769311428070068, Learning Rate: 8.437185929648241e-05)
+
                                                                             
Step... (16050 / 100000 | Loss: 1.162201166152954, Learning Rate: 8.437185929648241e-05)
+
Train steps ... :  16%|█▌        | 16050/100000 [4:49:37<13:38:21,  1.71it/s]
Train steps ... :  16%|█▌        | 16051/100000 [4:49:37<13:39:41,  1.71it/s]
Train steps ... :  16%|█▌        | 16052/100000 [4:49:38<13:38:34,  1.71it/s]
Train steps ... :  16%|█▌        | 16053/100000 [4:49:38<13:38:40,  1.71it/s]
Train steps ... :  16%|█▌        | 16054/100000 [4:49:39<13:37:45,  1.71it/s]
Train steps ... :  16%|█▌        | 16055/100000 [4:49:40<13:37:21,  1.71it/s]
Train steps ... :  16%|█▌        | 16056/100000 [4:49:40<13:37:03,  1.71it/s]
Train steps ... :  16%|█▌        | 16057/100000 [4:49:41<13:36:08,  1.71it/s]
Train steps ... :  16%|█▌        | 16058/100000 [4:49:41<13:37:23,  1.71it/s]
Train steps ... :  16%|█▌        | 16059/100000 [4:49:42<13:37:33,  1.71it/s]
Train steps ... :  16%|█▌        | 16060/100000 [4:49:42<13:36:42,  1.71it/s]
Train steps ... :  16%|█▌        | 16061/100000 [4:49:43<13:37:07,  1.71it/s]
Train steps ... :  16%|█▌        | 16062/100000 [4:49:44<13:37:18,  1.71it/s]
Train steps ... :  16%|█▌        | 16063/100000 [4:49:44<13:36:45,  1.71it/s]
Train steps ... :  16%|█▌        | 16064/100000 [4:49:45<13:37:09,  1.71it/s]
Train steps ... :  16%|█▌        | 16065/100000 [4:49:45<13:38:09,  1.71it/s]
Train steps ... :  16%|█▌        | 16066/100000 [4:49:46<13:38:12,  1.71it/s]
Train steps ... :  16%|█▌        | 16067/100000 [4:49:47<13:38:20,  1.71it/s]
Train steps ... :  16%|█▌        | 16068/100000 [4:49:47<13:37:10,  1.71it/s]
Train steps ... :  16%|█▌        | 16069/100000 [4:49:48<13:37:52,  1.71it/s]
Train steps ... :  16%|█▌        | 16070/100000 [4:49:48<13:37:31,  1.71it/s]
Train steps ... :  16%|█▌        | 16071/100000 [4:49:49<13:36:46,  1.71it/s]
Train steps ... :  16%|█▌        | 16072/100000 [4:49:50<13:36:56,  1.71it/s]
Train steps ... :  16%|█▌        | 16073/100000 [4:49:50<13:37:37,  1.71it/s]
Train steps ... :  16%|█▌        | 16074/100000 [4:49:51<13:37:37,  1.71it/s]
Train steps ... :  16%|█▌        | 16075/100000 [4:49:51<13:39:12,  1.71it/s]Step... (16075 / 100000 | Loss: 1.1773827075958252, Learning Rate: 8.434673366834172e-05)
+
                                                                             
Step... (16075 / 100000 | Loss: 0.975871205329895, Learning Rate: 8.434673366834172e-05)
+
Train steps ... :  16%|█▌        | 16075/100000 [4:49:52<13:39:12,  1.71it/s]
Train steps ... :  16%|█▌        | 16076/100000 [4:49:52<13:39:09,  1.71it/s]
Train steps ... :  16%|█▌        | 16077/100000 [4:49:52<13:38:26,  1.71it/s]
Train steps ... :  16%|█▌        | 16078/100000 [4:49:53<13:37:18,  1.71it/s]
Train steps ... :  16%|█▌        | 16079/100000 [4:49:54<13:37:06,  1.71it/s]
Train steps ... :  16%|█▌        | 16080/100000 [4:49:54<13:37:52,  1.71it/s]
Train steps ... :  16%|█▌        | 16081/100000 [4:49:55<13:37:32,  1.71it/s]
Train steps ... :  16%|█▌        | 16082/100000 [4:49:55<13:36:44,  1.71it/s]
Train steps ... :  16%|█▌        | 16083/100000 [4:49:56<13:37:44,  1.71it/s]
Train steps ... :  16%|█▌        | 16084/100000 [4:49:57<13:37:09,  1.71it/s]
Train steps ... :  16%|█▌        | 16085/100000 [4:49:57<13:37:22,  1.71it/s]
Train steps ... :  16%|█▌        | 16086/100000 [4:49:58<13:37:05,  1.71it/s]
Train steps ... :  16%|█▌        | 16087/100000 [4:49:58<13:36:38,  1.71it/s]
Train steps ... :  16%|█▌        | 16088/100000 [4:49:59<13:36:42,  1.71it/s]
Train steps ... :  16%|█▌        | 16089/100000 [4:49:59<13:36:33,  1.71it/s]
Train steps ... :  16%|█▌        | 16090/100000 [4:50:00<13:37:04,  1.71it/s]
Train steps ... :  16%|█▌        | 16091/100000 [4:50:01<13:36:26,  1.71it/s]
Train steps ... :  16%|█▌        | 16092/100000 [4:50:01<13:36:21,  1.71it/s]
Train steps ... :  16%|█▌        | 16093/100000 [4:50:02<13:36:43,  1.71it/s]
Train steps ... :  16%|█▌        | 16094/100000 [4:50:02<13:36:49,  1.71it/s]
Train steps ... :  16%|█▌        | 16095/100000 [4:50:03<13:37:54,  1.71it/s]
Train steps ... :  16%|█▌        | 16096/100000 [4:50:04<13:36:34,  1.71it/s]
Train steps ... :  16%|█▌        | 16097/100000 [4:50:04<13:37:43,  1.71it/s]
Train steps ... :  16%|█▌        | 16098/100000 [4:50:05<13:37:05,  1.71it/s]
Train steps ... :  16%|█▌        | 16099/100000 [4:50:05<13:37:06,  1.71it/s]
Train steps ... :  16%|█▌        | 16100/100000 [4:50:06<13:36:56,  1.71it/s]Step... (16100 / 100000 | Loss: 1.1510990858078003, Learning Rate: 8.4321608040201e-05)
+
                                                                             
Step... (16100 / 100000 | Loss: 1.1188514232635498, Learning Rate: 8.4321608040201e-05)
+
Train steps ... :  16%|█▌        | 16100/100000 [4:50:06<13:36:56,  1.71it/s]
Train steps ... :  16%|█▌        | 16101/100000 [4:50:06<13:36:54,  1.71it/s]
Train steps ... :  16%|█▌        | 16102/100000 [4:50:07<13:36:44,  1.71it/s]
Train steps ... :  16%|█▌        | 16103/100000 [4:50:08<13:36:40,  1.71it/s]
Train steps ... :  16%|█▌        | 16104/100000 [4:50:08<13:36:38,  1.71it/s]
Train steps ... :  16%|█▌        | 16105/100000 [4:50:09<13:36:32,  1.71it/s]
Train steps ... :  16%|█▌        | 16106/100000 [4:50:09<13:36:53,  1.71it/s]
Train steps ... :  16%|█▌        | 16107/100000 [4:50:10<13:36:10,  1.71it/s]
Train steps ... :  16%|█▌        | 16108/100000 [4:50:11<13:36:31,  1.71it/s]
Train steps ... :  16%|█▌        | 16109/100000 [4:50:11<13:36:55,  1.71it/s]
Train steps ... :  16%|█▌        | 16110/100000 [4:50:12<13:37:05,  1.71it/s]
Train steps ... :  16%|█▌        | 16111/100000 [4:50:12<13:40:16,  1.70it/s]
Train steps ... :  16%|█▌        | 16112/100000 [4:50:13<13:39:16,  1.71it/s]
Train steps ... :  16%|█▌        | 16113/100000 [4:50:13<13:37:39,  1.71it/s]
Train steps ... :  16%|█▌        | 16114/100000 [4:50:14<13:36:59,  1.71it/s]
Train steps ... :  16%|█▌        | 16115/100000 [4:50:15<13:36:46,  1.71it/s]
Train steps ... :  16%|█▌        | 16116/100000 [4:50:15<13:36:38,  1.71it/s]
Train steps ... :  16%|█▌        | 16117/100000 [4:50:16<13:36:10,  1.71it/s]
Train steps ... :  16%|█▌        | 16118/100000 [4:50:16<13:36:49,  1.71it/s]
Train steps ... :  16%|█▌        | 16119/100000 [4:50:17<13:37:30,  1.71it/s]
Train steps ... :  16%|█▌        | 16120/100000 [4:50:18<13:36:50,  1.71it/s]
Train steps ... :  16%|█▌        | 16121/100000 [4:50:18<13:36:12,  1.71it/s]
Train steps ... :  16%|█▌        | 16122/100000 [4:50:19<13:36:06,  1.71it/s]
Train steps ... :  16%|█▌        | 16123/100000 [4:50:19<13:35:51,  1.71it/s]
Train steps ... :  16%|█▌        | 16124/100000 [4:50:20<13:36:25,  1.71it/s]
Train steps ... :  16%|█▌        | 16125/100000 [4:50:20<13:36:34,  1.71it/s]Step... (16125 / 100000 | Loss: 1.4859733581542969, Learning Rate: 8.429648241206031e-05)
+
                                                                             
Step... (16125 / 100000 | Loss: 1.2677266597747803, Learning Rate: 8.429648241206031e-05)
+
Train steps ... :  16%|█▌        | 16125/100000 [4:50:21<13:36:34,  1.71it/s]
Train steps ... :  16%|█▌        | 16126/100000 [4:50:21<13:36:49,  1.71it/s]
Train steps ... :  16%|█▌        | 16127/100000 [4:50:22<13:36:16,  1.71it/s]
Train steps ... :  16%|█▌        | 16128/100000 [4:50:22<13:36:21,  1.71it/s]
Train steps ... :  16%|█▌        | 16129/100000 [4:50:23<13:36:46,  1.71it/s]
Train steps ... :  16%|█▌        | 16130/100000 [4:50:23<13:37:07,  1.71it/s]
Train steps ... :  16%|█▌        | 16131/100000 [4:50:24<13:37:13,  1.71it/s]
Train steps ... :  16%|█▌        | 16132/100000 [4:50:25<13:37:10,  1.71it/s]
Train steps ... :  16%|█▌        | 16133/100000 [4:50:25<13:38:37,  1.71it/s]
Train steps ... :  16%|█▌        | 16134/100000 [4:50:26<13:36:00,  1.71it/s]
Train steps ... :  16%|█▌        | 16135/100000 [4:50:26<13:36:11,  1.71it/s]
Train steps ... :  16%|█▌        | 16136/100000 [4:50:27<13:35:57,  1.71it/s]
Train steps ... :  16%|█▌        | 16137/100000 [4:50:27<13:37:14,  1.71it/s]
Train steps ... :  16%|█▌        | 16138/100000 [4:50:28<13:36:49,  1.71it/s]
Train steps ... :  16%|█▌        | 16139/100000 [4:50:29<13:37:30,  1.71it/s]
Train steps ... :  16%|█▌        | 16140/100000 [4:50:29<13:36:43,  1.71it/s]
Train steps ... :  16%|█▌        | 16141/100000 [4:50:30<13:36:25,  1.71it/s]
Train steps ... :  16%|█▌        | 16142/100000 [4:50:30<13:36:47,  1.71it/s]
Train steps ... :  16%|█▌        | 16143/100000 [4:50:31<13:36:01,  1.71it/s]
Train steps ... :  16%|█▌        | 16144/100000 [4:50:32<13:36:14,  1.71it/s]
Train steps ... :  16%|█▌        | 16145/100000 [4:50:32<13:35:57,  1.71it/s]
Train steps ... :  16%|█▌        | 16146/100000 [4:50:33<13:35:55,  1.71it/s]
Train steps ... :  16%|█▌        | 16147/100000 [4:50:33<13:37:34,  1.71it/s]
Train steps ... :  16%|█▌        | 16148/100000 [4:50:34<13:38:09,  1.71it/s]
Train steps ... :  16%|█▌        | 16149/100000 [4:50:35<13:37:38,  1.71it/s]
Train steps ... :  16%|█▌        | 16150/100000 [4:50:35<13:37:27,  1.71it/s]Step... (16150 / 100000 | Loss: 1.011040449142456, Learning Rate: 8.42713567839196e-05)
+
                                                                             
Step... (16150 / 100000 | Loss: 0.9021272659301758, Learning Rate: 8.42713567839196e-05)
+
Train steps ... :  16%|█▌        | 16150/100000 [4:50:35<13:37:27,  1.71it/s]
Train steps ... :  16%|█▌        | 16151/100000 [4:50:36<13:38:09,  1.71it/s]
Train steps ... :  16%|█▌        | 16152/100000 [4:50:36<13:36:41,  1.71it/s]
Train steps ... :  16%|█▌        | 16153/100000 [4:50:37<13:36:42,  1.71it/s]
Train steps ... :  16%|█▌        | 16154/100000 [4:50:37<13:36:33,  1.71it/s]
Train steps ... :  16%|█▌        | 16155/100000 [4:50:38<13:36:10,  1.71it/s]
Train steps ... :  16%|█▌        | 16156/100000 [4:50:39<13:36:20,  1.71it/s]
Train steps ... :  16%|█▌        | 16157/100000 [4:50:39<13:35:52,  1.71it/s]
Train steps ... :  16%|█▌        | 16158/100000 [4:50:40<13:35:54,  1.71it/s]
Train steps ... :  16%|█▌        | 16159/100000 [4:50:40<13:36:36,  1.71it/s]
Train steps ... :  16%|█▌        | 16160/100000 [4:50:41<13:36:18,  1.71it/s]
Train steps ... :  16%|█▌        | 16161/100000 [4:50:42<13:36:35,  1.71it/s]
Train steps ... :  16%|█▌        | 16162/100000 [4:50:42<13:36:29,  1.71it/s]
Train steps ... :  16%|█▌        | 16163/100000 [4:50:43<13:36:37,  1.71it/s]
Train steps ... :  16%|█▌        | 16164/100000 [4:50:43<13:35:29,  1.71it/s]
Train steps ... :  16%|█▌        | 16165/100000 [4:50:44<13:35:55,  1.71it/s]
Train steps ... :  16%|█▌        | 16166/100000 [4:50:44<13:35:48,  1.71it/s]
Train steps ... :  16%|█▌        | 16167/100000 [4:50:45<13:35:48,  1.71it/s]
Train steps ... :  16%|█▌        | 16168/100000 [4:50:46<13:36:12,  1.71it/s]
Train steps ... :  16%|█▌        | 16169/100000 [4:50:46<13:37:29,  1.71it/s]
Train steps ... :  16%|█▌        | 16170/100000 [4:50:47<13:35:58,  1.71it/s]
Train steps ... :  16%|█▌        | 16171/100000 [4:50:47<13:37:09,  1.71it/s]
Train steps ... :  16%|█▌        | 16172/100000 [4:50:48<13:36:38,  1.71it/s]
Train steps ... :  16%|█▌        | 16173/100000 [4:50:49<13:36:33,  1.71it/s]
Train steps ... :  16%|█▌        | 16174/100000 [4:50:49<13:37:25,  1.71it/s]
Train steps ... :  16%|█▌        | 16175/100000 [4:50:50<13:37:19,  1.71it/s]Step... (16175 / 100000 | Loss: 1.177739143371582, Learning Rate: 8.42462311557789e-05)
+
                                                                             
Step... (16175 / 100000 | Loss: 1.1936192512512207, Learning Rate: 8.42462311557789e-05)
+
Train steps ... :  16%|█▌        | 16175/100000 [4:50:50<13:37:19,  1.71it/s]
Train steps ... :  16%|█▌        | 16176/100000 [4:50:50<13:37:16,  1.71it/s]
Train steps ... :  16%|█▌        | 16177/100000 [4:50:51<13:36:25,  1.71it/s]
Train steps ... :  16%|█▌        | 16178/100000 [4:50:51<13:36:17,  1.71it/s]
Train steps ... :  16%|█▌        | 16179/100000 [4:50:52<13:36:22,  1.71it/s]
Train steps ... :  16%|█▌        | 16180/100000 [4:50:53<13:35:47,  1.71it/s]
Train steps ... :  16%|█▌        | 16181/100000 [4:50:53<13:36:06,  1.71it/s]
Train steps ... :  16%|█▌        | 16182/100000 [4:50:54<13:37:27,  1.71it/s]
Train steps ... :  16%|█▌        | 16183/100000 [4:50:54<13:38:05,  1.71it/s]
Train steps ... :  16%|█▌        | 16184/100000 [4:50:55<13:37:07,  1.71it/s]
Train steps ... :  16%|█▌        | 16185/100000 [4:50:56<13:36:59,  1.71it/s]
Train steps ... :  16%|█▌        | 16186/100000 [4:50:56<13:37:51,  1.71it/s]
Train steps ... :  16%|█▌        | 16187/100000 [4:50:57<13:36:25,  1.71it/s]
Train steps ... :  16%|█▌        | 16188/100000 [4:50:57<13:37:08,  1.71it/s]
Train steps ... :  16%|█▌        | 16189/100000 [4:50:58<13:37:00,  1.71it/s]
Train steps ... :  16%|█▌        | 16190/100000 [4:50:58<13:36:37,  1.71it/s]
Train steps ... :  16%|█▌        | 16191/100000 [4:50:59<13:36:05,  1.71it/s]
Train steps ... :  16%|█▌        | 16192/100000 [4:51:00<13:35:53,  1.71it/s]
Train steps ... :  16%|█▌        | 16193/100000 [4:51:00<13:36:40,  1.71it/s]
Train steps ... :  16%|█▌        | 16194/100000 [4:51:01<13:36:24,  1.71it/s]
Train steps ... :  16%|█▌        | 16195/100000 [4:51:01<13:37:28,  1.71it/s]
Train steps ... :  16%|█▌        | 16196/100000 [4:51:02<13:36:57,  1.71it/s]
Train steps ... :  16%|█▌        | 16197/100000 [4:51:03<13:36:39,  1.71it/s]
Train steps ... :  16%|█▌        | 16198/100000 [4:51:03<13:35:53,  1.71it/s]
Train steps ... :  16%|█▌        | 16199/100000 [4:51:04<13:35:59,  1.71it/s]
Train steps ... :  16%|█▌        | 16200/100000 [4:51:04<13:35:48,  1.71it/s]Step... (16200 / 100000 | Loss: 1.3112244606018066, Learning Rate: 8.42211055276382e-05)
+
                                                                             
Step... (16200 / 100000 | Loss: 1.323207139968872, Learning Rate: 8.42211055276382e-05)
+
Train steps ... :  16%|█▌        | 16200/100000 [4:51:05<13:35:48,  1.71it/s]
Train steps ... :  16%|█▌        | 16201/100000 [4:51:05<13:37:35,  1.71it/s]
Train steps ... :  16%|█▌        | 16202/100000 [4:51:05<13:37:35,  1.71it/s]
Train steps ... :  16%|█▌        | 16203/100000 [4:51:06<13:38:14,  1.71it/s]
Train steps ... :  16%|█▌        | 16204/100000 [4:51:07<13:37:21,  1.71it/s]
Train steps ... :  16%|█▌        | 16205/100000 [4:51:07<13:36:33,  1.71it/s]
Train steps ... :  16%|█▌        | 16206/100000 [4:51:08<13:36:44,  1.71it/s]
Train steps ... :  16%|█▌        | 16207/100000 [4:51:08<13:36:15,  1.71it/s]
Train steps ... :  16%|█▌        | 16208/100000 [4:51:09<13:36:49,  1.71it/s]
Train steps ... :  16%|█▌        | 16209/100000 [4:51:10<13:36:38,  1.71it/s]
Train steps ... :  16%|█▌        | 16210/100000 [4:51:10<13:36:35,  1.71it/s]
Train steps ... :  16%|█▌        | 16211/100000 [4:51:11<13:37:27,  1.71it/s]
Train steps ... :  16%|█▌        | 16212/100000 [4:51:11<13:36:47,  1.71it/s]
Train steps ... :  16%|█▌        | 16213/100000 [4:51:12<13:35:54,  1.71it/s]
Train steps ... :  16%|█▌        | 16214/100000 [4:51:13<13:35:28,  1.71it/s]
Train steps ... :  16%|█▌        | 16215/100000 [4:51:13<13:35:04,  1.71it/s]
Train steps ... :  16%|█▌        | 16216/100000 [4:51:14<13:35:35,  1.71it/s]
Train steps ... :  16%|█▌        | 16217/100000 [4:51:14<13:36:41,  1.71it/s]
Train steps ... :  16%|█▌        | 16218/100000 [4:51:15<13:35:34,  1.71it/s]
Train steps ... :  16%|█▌        | 16219/100000 [4:51:15<13:37:26,  1.71it/s]
Train steps ... :  16%|█▌        | 16220/100000 [4:51:16<13:36:52,  1.71it/s]
Train steps ... :  16%|█▌        | 16221/100000 [4:51:17<13:36:35,  1.71it/s]
Train steps ... :  16%|█▌        | 16222/100000 [4:51:17<13:37:27,  1.71it/s]
Train steps ... :  16%|█▌        | 16223/100000 [4:51:18<13:36:47,  1.71it/s]
Train steps ... :  16%|█▌        | 16224/100000 [4:51:18<13:36:10,  1.71it/s]
Train steps ... :  16%|█▌        | 16225/100000 [4:51:19<13:36:44,  1.71it/s]Step... (16225 / 100000 | Loss: 1.0207452774047852, Learning Rate: 8.419597989949748e-05)
+
                                                                             
Step... (16225 / 100000 | Loss: 1.2684674263000488, Learning Rate: 8.419597989949748e-05)
+
Train steps ... :  16%|█▌        | 16225/100000 [4:51:19<13:36:44,  1.71it/s]
Train steps ... :  16%|█▌        | 16226/100000 [4:51:20<13:36:17,  1.71it/s]
Train steps ... :  16%|█▌        | 16227/100000 [4:51:20<13:37:08,  1.71it/s]
Train steps ... :  16%|█▌        | 16228/100000 [4:51:21<13:36:09,  1.71it/s]
Train steps ... :  16%|█▌        | 16229/100000 [4:51:21<13:36:07,  1.71it/s]
Train steps ... :  16%|█▌        | 16230/100000 [4:51:22<13:35:50,  1.71it/s]
Train steps ... :  16%|█▌        | 16231/100000 [4:51:22<13:35:54,  1.71it/s]
Train steps ... :  16%|█▌        | 16232/100000 [4:51:23<13:36:17,  1.71it/s]
Train steps ... :  16%|█▌        | 16233/100000 [4:51:24<13:35:42,  1.71it/s]
Train steps ... :  16%|█▌        | 16234/100000 [4:51:24<13:35:31,  1.71it/s]
Train steps ... :  16%|█▌        | 16235/100000 [4:51:25<13:37:19,  1.71it/s]
Train steps ... :  16%|█▌        | 16236/100000 [4:51:25<13:37:23,  1.71it/s]
Train steps ... :  16%|█▌        | 16237/100000 [4:51:26<13:36:51,  1.71it/s]
Train steps ... :  16%|█▌        | 16238/100000 [4:51:27<13:35:54,  1.71it/s]
Train steps ... :  16%|█▌        | 16239/100000 [4:51:27<13:35:30,  1.71it/s]
Train steps ... :  16%|█▌        | 16240/100000 [4:51:28<13:35:21,  1.71it/s]
Train steps ... :  16%|█▌        | 16241/100000 [4:51:28<13:35:57,  1.71it/s]
Train steps ... :  16%|█▌        | 16242/100000 [4:51:29<13:35:40,  1.71it/s]
Train steps ... :  16%|█▌        | 16243/100000 [4:51:29<13:35:10,  1.71it/s]
Train steps ... :  16%|█▌        | 16244/100000 [4:51:30<13:35:03,  1.71it/s]
Train steps ... :  16%|█▌        | 16245/100000 [4:51:31<13:34:45,  1.71it/s]
Train steps ... :  16%|█▌        | 16246/100000 [4:51:31<13:35:37,  1.71it/s]
Train steps ... :  16%|█▌        | 16247/100000 [4:51:32<13:35:05,  1.71it/s]
Train steps ... :  16%|█▌        | 16248/100000 [4:51:32<13:35:08,  1.71it/s]
Train steps ... :  16%|█▌        | 16249/100000 [4:51:33<13:35:11,  1.71it/s]
Train steps ... :  16%|█▋        | 16250/100000 [4:51:34<13:35:17,  1.71it/s]Step... (16250 / 100000 | Loss: 1.5268253087997437, Learning Rate: 8.41708542713568e-05)
+
                                                                             
Step... (16250 / 100000 | Loss: 1.2971134185791016, Learning Rate: 8.41708542713568e-05)
+
Train steps ... :  16%|█▋        | 16250/100000 [4:51:34<13:35:17,  1.71it/s]
Train steps ... :  16%|█▋        | 16251/100000 [4:51:34<13:36:24,  1.71it/s]
Train steps ... :  16%|█▋        | 16252/100000 [4:51:35<13:36:10,  1.71it/s]
Train steps ... :  16%|█▋        | 16253/100000 [4:51:35<13:35:58,  1.71it/s]
Train steps ... :  16%|█▋        | 16254/100000 [4:51:36<13:37:03,  1.71it/s]
Train steps ... :  16%|█▋        | 16255/100000 [4:51:36<13:36:25,  1.71it/s]
Train steps ... :  16%|█▋        | 16256/100000 [4:51:37<13:34:56,  1.71it/s]
Train steps ... :  16%|█▋        | 16257/100000 [4:51:38<13:34:44,  1.71it/s]
Train steps ... :  16%|█▋        | 16258/100000 [4:51:38<13:34:37,  1.71it/s]
Train steps ... :  16%|█▋        | 16259/100000 [4:51:39<13:37:07,  1.71it/s]
Train steps ... :  16%|█▋        | 16260/100000 [4:51:39<13:35:16,  1.71it/s]
Train steps ... :  16%|█▋        | 16261/100000 [4:51:40<13:35:03,  1.71it/s]
Train steps ... :  16%|█▋        | 16262/100000 [4:51:41<13:34:46,  1.71it/s]
Train steps ... :  16%|█▋        | 16263/100000 [4:51:41<13:34:40,  1.71it/s]
Train steps ... :  16%|█▋        | 16264/100000 [4:51:42<13:35:21,  1.71it/s]
Train steps ... :  16%|█▋        | 16265/100000 [4:51:42<13:35:05,  1.71it/s]
Train steps ... :  16%|█▋        | 16266/100000 [4:51:43<13:35:04,  1.71it/s]
Train steps ... :  16%|█▋        | 16267/100000 [4:51:43<13:35:40,  1.71it/s]
Train steps ... :  16%|█▋        | 16268/100000 [4:51:44<13:35:47,  1.71it/s]
Train steps ... :  16%|█▋        | 16269/100000 [4:51:45<13:35:28,  1.71it/s]
Train steps ... :  16%|█▋        | 16270/100000 [4:51:45<13:36:38,  1.71it/s]
Train steps ... :  16%|█▋        | 16271/100000 [4:51:46<13:37:08,  1.71it/s]
Train steps ... :  16%|█▋        | 16272/100000 [4:51:46<13:36:00,  1.71it/s]
Train steps ... :  16%|█▋        | 16273/100000 [4:51:47<13:36:24,  1.71it/s]
Train steps ... :  16%|█▋        | 16274/100000 [4:51:48<13:36:22,  1.71it/s]
Train steps ... :  16%|█▋        | 16275/100000 [4:51:48<13:37:17,  1.71it/s]Step... (16275 / 100000 | Loss: 1.203596830368042, Learning Rate: 8.414572864321608e-05)
+
                                                                             
Step... (16275 / 100000 | Loss: 1.3954229354858398, Learning Rate: 8.414572864321608e-05)
+
Train steps ... :  16%|█▋        | 16275/100000 [4:51:48<13:37:17,  1.71it/s]
Train steps ... :  16%|█▋        | 16276/100000 [4:51:49<13:36:45,  1.71it/s]
Train steps ... :  16%|█▋        | 16277/100000 [4:51:49<13:35:55,  1.71it/s]
Train steps ... :  16%|█▋        | 16278/100000 [4:51:50<13:36:28,  1.71it/s]
Train steps ... :  16%|█▋        | 16279/100000 [4:51:51<13:35:47,  1.71it/s]
Train steps ... :  16%|█▋        | 16280/100000 [4:51:51<13:35:41,  1.71it/s]
Train steps ... :  16%|█▋        | 16281/100000 [4:51:52<13:35:24,  1.71it/s]
Train steps ... :  16%|█▋        | 16282/100000 [4:51:52<13:36:01,  1.71it/s]
Train steps ... :  16%|█▋        | 16283/100000 [4:51:53<13:35:30,  1.71it/s]
Train steps ... :  16%|█▋        | 16284/100000 [4:51:53<13:35:51,  1.71it/s]
Train steps ... :  16%|█▋        | 16285/100000 [4:51:54<13:35:21,  1.71it/s]
Train steps ... :  16%|█▋        | 16286/100000 [4:51:55<13:36:40,  1.71it/s]
Train steps ... :  16%|█▋        | 16287/100000 [4:51:55<13:39:19,  1.70it/s]
Train steps ... :  16%|█▋        | 16288/100000 [4:51:56<13:36:34,  1.71it/s]
Train steps ... :  16%|█▋        | 16289/100000 [4:51:56<13:35:51,  1.71it/s]
Train steps ... :  16%|█▋        | 16290/100000 [4:51:57<13:35:33,  1.71it/s]
Train steps ... :  16%|█▋        | 16291/100000 [4:51:58<13:36:08,  1.71it/s]
Train steps ... :  16%|█▋        | 16292/100000 [4:51:58<13:35:13,  1.71it/s]
Train steps ... :  16%|█▋        | 16293/100000 [4:51:59<13:35:09,  1.71it/s]
Train steps ... :  16%|█▋        | 16294/100000 [4:51:59<13:36:08,  1.71it/s]
Train steps ... :  16%|█▋        | 16295/100000 [4:52:00<13:36:06,  1.71it/s]
Train steps ... :  16%|█▋        | 16296/100000 [4:52:00<13:35:59,  1.71it/s]
Train steps ... :  16%|█▋        | 16297/100000 [4:52:01<13:35:49,  1.71it/s]
Train steps ... :  16%|█▋        | 16298/100000 [4:52:02<13:35:27,  1.71it/s]
Train steps ... :  16%|█▋        | 16299/100000 [4:52:02<13:36:01,  1.71it/s]
Train steps ... :  16%|█▋        | 16300/100000 [4:52:03<13:36:02,  1.71it/s]Step... (16300 / 100000 | Loss: 0.8553887605667114, Learning Rate: 8.412060301507539e-05)
+
                                                                             
Step... (16300 / 100000 | Loss: 1.0437772274017334, Learning Rate: 8.412060301507539e-05)
+
Train steps ... :  16%|█▋        | 16300/100000 [4:52:03<13:36:02,  1.71it/s]
Train steps ... :  16%|█▋        | 16301/100000 [4:52:03<13:35:37,  1.71it/s]
Train steps ... :  16%|█▋        | 16302/100000 [4:52:04<13:35:51,  1.71it/s]
Train steps ... :  16%|█▋        | 16303/100000 [4:52:05<13:36:08,  1.71it/s]
Train steps ... :  16%|█▋        | 16304/100000 [4:52:05<13:35:21,  1.71it/s]
Train steps ... :  16%|█▋        | 16305/100000 [4:52:06<13:35:44,  1.71it/s]
Train steps ... :  16%|█▋        | 16306/100000 [4:52:06<13:35:18,  1.71it/s]
Train steps ... :  16%|█▋        | 16307/100000 [4:52:07<13:35:19,  1.71it/s]
Train steps ... :  16%|█▋        | 16308/100000 [4:52:07<13:35:33,  1.71it/s]
Train steps ... :  16%|█▋        | 16309/100000 [4:52:08<13:35:11,  1.71it/s]
Train steps ... :  16%|█▋        | 16310/100000 [4:52:09<13:35:00,  1.71it/s]
Train steps ... :  16%|█▋        | 16311/100000 [4:52:09<13:34:06,  1.71it/s]
Train steps ... :  16%|█▋        | 16312/100000 [4:52:10<13:34:13,  1.71it/s]
Train steps ... :  16%|█▋        | 16313/100000 [4:52:10<13:34:23,  1.71it/s]
Train steps ... :  16%|█▋        | 16314/100000 [4:52:11<13:34:33,  1.71it/s]
Train steps ... :  16%|█▋        | 16315/100000 [4:52:12<13:33:44,  1.71it/s]
Train steps ... :  16%|█▋        | 16316/100000 [4:52:12<13:34:11,  1.71it/s]
Train steps ... :  16%|█▋        | 16317/100000 [4:52:13<13:34:47,  1.71it/s]
Train steps ... :  16%|█▋        | 16318/100000 [4:52:13<13:35:01,  1.71it/s]
Train steps ... :  16%|█▋        | 16319/100000 [4:52:14<13:34:55,  1.71it/s]
Train steps ... :  16%|█▋        | 16320/100000 [4:52:14<13:35:02,  1.71it/s]
Train steps ... :  16%|█▋        | 16321/100000 [4:52:15<13:35:16,  1.71it/s]
Train steps ... :  16%|█▋        | 16322/100000 [4:52:16<13:34:49,  1.71it/s]
Train steps ... :  16%|█▋        | 16323/100000 [4:52:16<13:35:15,  1.71it/s]
Train steps ... :  16%|█▋        | 16324/100000 [4:52:17<13:34:59,  1.71it/s]
Train steps ... :  16%|█▋        | 16325/100000 [4:52:17<13:35:42,  1.71it/s]Step... (16325 / 100000 | Loss: 0.9928783178329468, Learning Rate: 8.409547738693467e-05)
+
                                                                             
Step... (16325 / 100000 | Loss: 1.3723698854446411, Learning Rate: 8.409547738693467e-05)
+
Train steps ... :  16%|█▋        | 16325/100000 [4:52:18<13:35:42,  1.71it/s]
Train steps ... :  16%|█▋        | 16326/100000 [4:52:18<13:35:19,  1.71it/s]
Train steps ... :  16%|█▋        | 16327/100000 [4:52:19<13:35:09,  1.71it/s]
Train steps ... :  16%|█▋        | 16328/100000 [4:52:19<13:34:39,  1.71it/s]
Train steps ... :  16%|█▋        | 16329/100000 [4:52:20<13:35:12,  1.71it/s]
Train steps ... :  16%|█▋        | 16330/100000 [4:52:20<13:35:43,  1.71it/s]
Train steps ... :  16%|█▋        | 16331/100000 [4:52:21<13:36:05,  1.71it/s]
Train steps ... :  16%|█▋        | 16332/100000 [4:52:21<13:37:02,  1.71it/s]
Train steps ... :  16%|█▋        | 16333/100000 [4:52:22<13:36:13,  1.71it/s]
Train steps ... :  16%|█▋        | 16334/100000 [4:52:23<13:37:06,  1.71it/s]
Train steps ... :  16%|█▋        | 16335/100000 [4:52:23<13:35:44,  1.71it/s]
Train steps ... :  16%|█▋        | 16336/100000 [4:52:24<13:35:09,  1.71it/s]
Train steps ... :  16%|█▋        | 16337/100000 [4:52:24<13:35:43,  1.71it/s]
Train steps ... :  16%|█▋        | 16338/100000 [4:52:25<13:37:03,  1.71it/s]
Train steps ... :  16%|█▋        | 16339/100000 [4:52:26<13:35:52,  1.71it/s]
Train steps ... :  16%|█▋        | 16340/100000 [4:52:26<13:35:04,  1.71it/s]
Train steps ... :  16%|█▋        | 16341/100000 [4:52:27<13:36:04,  1.71it/s]
Train steps ... :  16%|█▋        | 16342/100000 [4:52:27<13:35:43,  1.71it/s]
Train steps ... :  16%|█▋        | 16343/100000 [4:52:28<13:35:00,  1.71it/s]
Train steps ... :  16%|█▋        | 16344/100000 [4:52:29<13:34:35,  1.71it/s]
Train steps ... :  16%|█▋        | 16345/100000 [4:52:29<13:34:12,  1.71it/s]
Train steps ... :  16%|█▋        | 16346/100000 [4:52:30<13:34:04,  1.71it/s]
Train steps ... :  16%|█▋        | 16347/100000 [4:52:30<13:34:58,  1.71it/s]
Train steps ... :  16%|█▋        | 16348/100000 [4:52:31<13:34:52,  1.71it/s]
Train steps ... :  16%|█▋        | 16349/100000 [4:52:31<13:35:58,  1.71it/s]
Train steps ... :  16%|█▋        | 16350/100000 [4:52:32<13:35:05,  1.71it/s]Step... (16350 / 100000 | Loss: 1.7735686302185059, Learning Rate: 8.407035175879398e-05)
+
                                                                             
Step... (16350 / 100000 | Loss: 1.4647002220153809, Learning Rate: 8.407035175879398e-05)
+
Train steps ... :  16%|█▋        | 16350/100000 [4:52:32<13:35:05,  1.71it/s]
Train steps ... :  16%|█▋        | 16351/100000 [4:52:33<13:35:06,  1.71it/s]
Train steps ... :  16%|█▋        | 16352/100000 [4:52:33<13:34:34,  1.71it/s]
Train steps ... :  16%|█▋        | 16353/100000 [4:52:34<13:35:14,  1.71it/s]
Train steps ... :  16%|█▋        | 16354/100000 [4:52:34<13:34:36,  1.71it/s]
Train steps ... :  16%|█▋        | 16355/100000 [4:52:35<13:34:32,  1.71it/s]
Train steps ... :  16%|█▋        | 16356/100000 [4:52:36<13:34:58,  1.71it/s]
Train steps ... :  16%|█▋        | 16357/100000 [4:52:36<13:35:39,  1.71it/s]
Train steps ... :  16%|█▋        | 16358/100000 [4:52:37<13:35:32,  1.71it/s]
Train steps ... :  16%|█▋        | 16359/100000 [4:52:37<13:35:18,  1.71it/s]
Train steps ... :  16%|█▋        | 16360/100000 [4:52:38<13:35:02,  1.71it/s]
Train steps ... :  16%|█▋        | 16361/100000 [4:52:38<13:34:26,  1.71it/s]
Train steps ... :  16%|█▋        | 16362/100000 [4:52:39<13:34:49,  1.71it/s]
Train steps ... :  16%|█▋        | 16363/100000 [4:52:40<13:34:54,  1.71it/s]
Train steps ... :  16%|█▋        | 16364/100000 [4:52:40<13:34:52,  1.71it/s]
Train steps ... :  16%|█▋        | 16365/100000 [4:52:41<13:34:16,  1.71it/s]
Train steps ... :  16%|█▋        | 16366/100000 [4:52:41<13:35:15,  1.71it/s]
Train steps ... :  16%|█▋        | 16367/100000 [4:52:42<13:34:30,  1.71it/s]
Train steps ... :  16%|█▋        | 16368/100000 [4:52:43<13:34:24,  1.71it/s]
Train steps ... :  16%|█▋        | 16369/100000 [4:52:43<13:35:43,  1.71it/s]
Train steps ... :  16%|█▋        | 16370/100000 [4:52:44<13:34:25,  1.71it/s]
Train steps ... :  16%|█▋        | 16371/100000 [4:52:44<13:35:38,  1.71it/s]
Train steps ... :  16%|█▋        | 16372/100000 [4:52:45<13:35:56,  1.71it/s]
Train steps ... :  16%|█▋        | 16373/100000 [4:52:45<13:35:10,  1.71it/s]
Train steps ... :  16%|█▋        | 16374/100000 [4:52:46<13:35:05,  1.71it/s]
Train steps ... :  16%|█▋        | 16375/100000 [4:52:47<13:34:45,  1.71it/s]Step... (16375 / 100000 | Loss: 0.7434431910514832, Learning Rate: 8.404522613065326e-05)
+
                                                                             
Step... (16375 / 100000 | Loss: 1.9320542812347412, Learning Rate: 8.404522613065326e-05)
+
Train steps ... :  16%|█▋        | 16375/100000 [4:52:47<13:34:45,  1.71it/s]
Train steps ... :  16%|█▋        | 16376/100000 [4:52:47<13:36:16,  1.71it/s]
Train steps ... :  16%|█▋        | 16377/100000 [4:52:48<13:34:56,  1.71it/s]
Train steps ... :  16%|█▋        | 16378/100000 [4:52:48<13:35:17,  1.71it/s]
Train steps ... :  16%|█▋        | 16379/100000 [4:52:49<13:35:09,  1.71it/s]
Train steps ... :  16%|█▋        | 16380/100000 [4:52:50<13:34:25,  1.71it/s]
Train steps ... :  16%|█▋        | 16381/100000 [4:52:50<13:34:25,  1.71it/s]
Train steps ... :  16%|█▋        | 16382/100000 [4:52:51<13:33:51,  1.71it/s]
Train steps ... :  16%|█▋        | 16383/100000 [4:52:51<13:34:24,  1.71it/s]
Train steps ... :  16%|█▋        | 16384/100000 [4:52:52<13:34:46,  1.71it/s]
Train steps ... :  16%|█▋        | 16385/100000 [4:52:52<13:34:29,  1.71it/s]
Train steps ... :  16%|█▋        | 16386/100000 [4:52:53<13:34:13,  1.71it/s]
Train steps ... :  16%|█▋        | 16387/100000 [4:52:54<13:33:41,  1.71it/s]
Train steps ... :  16%|█▋        | 16388/100000 [4:52:54<13:34:53,  1.71it/s]
Train steps ... :  16%|█▋        | 16389/100000 [4:52:55<13:34:14,  1.71it/s]
Train steps ... :  16%|█▋        | 16390/100000 [4:52:55<13:34:34,  1.71it/s]
Train steps ... :  16%|█▋        | 16391/100000 [4:52:56<13:34:39,  1.71it/s]
Train steps ... :  16%|█▋        | 16392/100000 [4:52:57<13:34:23,  1.71it/s]
Train steps ... :  16%|█▋        | 16393/100000 [4:52:57<13:34:17,  1.71it/s]
Train steps ... :  16%|█▋        | 16394/100000 [4:52:58<13:35:04,  1.71it/s]
Train steps ... :  16%|█▋        | 16395/100000 [4:52:58<13:35:15,  1.71it/s]
Train steps ... :  16%|█▋        | 16396/100000 [4:52:59<13:35:01,  1.71it/s]
Train steps ... :  16%|█▋        | 16397/100000 [4:52:59<13:35:16,  1.71it/s]
Train steps ... :  16%|█▋        | 16398/100000 [4:53:00<13:35:13,  1.71it/s]
Train steps ... :  16%|█▋        | 16399/100000 [4:53:01<13:34:34,  1.71it/s]
Train steps ... :  16%|█▋        | 16400/100000 [4:53:01<13:34:01,  1.71it/s]Step... (16400 / 100000 | Loss: 1.0665363073349, Learning Rate: 8.402010050251256e-05)
+
                                                                             
Step... (16400 / 100000 | Loss: 1.1783721446990967, Learning Rate: 8.402010050251256e-05)
+
Train steps ... :  16%|█▋        | 16400/100000 [4:53:02<13:34:01,  1.71it/s]
Train steps ... :  16%|█▋        | 16401/100000 [4:53:02<13:34:45,  1.71it/s]
Train steps ... :  16%|█▋        | 16402/100000 [4:53:02<13:33:42,  1.71it/s]
Train steps ... :  16%|█▋        | 16403/100000 [4:53:03<13:34:42,  1.71it/s]
Train steps ... :  16%|█▋        | 16404/100000 [4:53:04<13:34:10,  1.71it/s]
Train steps ... :  16%|█▋        | 16405/100000 [4:53:04<13:34:20,  1.71it/s]
Train steps ... :  16%|█▋        | 16406/100000 [4:53:05<13:34:22,  1.71it/s]
Train steps ... :  16%|█▋        | 16407/100000 [4:53:05<13:33:59,  1.71it/s]
Train steps ... :  16%|█▋        | 16408/100000 [4:53:06<13:33:45,  1.71it/s]
Train steps ... :  16%|█▋        | 16409/100000 [4:53:07<13:33:42,  1.71it/s]
Train steps ... :  16%|█▋        | 16410/100000 [4:53:07<13:34:52,  1.71it/s]
Train steps ... :  16%|█▋        | 16411/100000 [4:53:08<13:34:53,  1.71it/s]
Train steps ... :  16%|█▋        | 16412/100000 [4:53:08<13:34:24,  1.71it/s]
Train steps ... :  16%|█▋        | 16413/100000 [4:53:09<13:34:10,  1.71it/s]
Train steps ... :  16%|█▋        | 16414/100000 [4:53:09<13:34:39,  1.71it/s]
Train steps ... :  16%|█▋        | 16415/100000 [4:53:10<13:35:01,  1.71it/s]
Train steps ... :  16%|█▋        | 16416/100000 [4:53:11<13:34:47,  1.71it/s]
Train steps ... :  16%|█▋        | 16417/100000 [4:53:11<13:34:49,  1.71it/s]
Train steps ... :  16%|█▋        | 16418/100000 [4:53:12<13:35:26,  1.71it/s]
Train steps ... :  16%|█▋        | 16419/100000 [4:53:12<13:34:56,  1.71it/s]
Train steps ... :  16%|█▋        | 16420/100000 [4:53:13<13:35:11,  1.71it/s]
Train steps ... :  16%|█▋        | 16421/100000 [4:53:14<13:34:45,  1.71it/s]
Train steps ... :  16%|█▋        | 16422/100000 [4:53:14<13:34:26,  1.71it/s]
Train steps ... :  16%|█▋        | 16423/100000 [4:53:15<13:34:38,  1.71it/s]
Train steps ... :  16%|█▋        | 16424/100000 [4:53:15<13:34:10,  1.71it/s]
Train steps ... :  16%|█▋        | 16425/100000 [4:53:16<13:34:06,  1.71it/s]Step... (16425 / 100000 | Loss: 0.9521584510803223, Learning Rate: 8.399497487437187e-05)
+
                                                                             
Step... (16425 / 100000 | Loss: 1.7918815612792969, Learning Rate: 8.399497487437187e-05)
+
Train steps ... :  16%|█▋        | 16425/100000 [4:53:16<13:34:06,  1.71it/s]
Train steps ... :  16%|█▋        | 16426/100000 [4:53:16<13:34:20,  1.71it/s]
Train steps ... :  16%|█▋        | 16427/100000 [4:53:17<13:34:34,  1.71it/s]
Train steps ... :  16%|█▋        | 16428/100000 [4:53:18<13:34:35,  1.71it/s]
Train steps ... :  16%|█▋        | 16429/100000 [4:53:18<13:34:51,  1.71it/s]
Train steps ... :  16%|█▋        | 16430/100000 [4:53:19<13:34:17,  1.71it/s]
Train steps ... :  16%|█▋        | 16431/100000 [4:53:19<13:34:09,  1.71it/s]
Train steps ... :  16%|█▋        | 16432/100000 [4:53:20<13:33:49,  1.71it/s]
Train steps ... :  16%|█▋        | 16433/100000 [4:53:21<13:33:15,  1.71it/s]
Train steps ... :  16%|█▋        | 16434/100000 [4:53:21<13:33:46,  1.71it/s]
Train steps ... :  16%|█▋        | 16435/100000 [4:53:22<13:34:19,  1.71it/s]
Train steps ... :  16%|█▋        | 16436/100000 [4:53:22<13:34:53,  1.71it/s]
Train steps ... :  16%|█▋        | 16437/100000 [4:53:23<13:33:54,  1.71it/s]
Train steps ... :  16%|█▋        | 16438/100000 [4:53:23<13:33:40,  1.71it/s]
Train steps ... :  16%|█▋        | 16439/100000 [4:53:24<13:33:13,  1.71it/s]
Train steps ... :  16%|█▋        | 16440/100000 [4:53:25<13:33:21,  1.71it/s]
Train steps ... :  16%|█▋        | 16441/100000 [4:53:25<13:33:07,  1.71it/s]
Train steps ... :  16%|█▋        | 16442/100000 [4:53:26<13:32:44,  1.71it/s]
Train steps ... :  16%|█▋        | 16443/100000 [4:53:26<13:33:32,  1.71it/s]
Train steps ... :  16%|█▋        | 16444/100000 [4:53:27<13:33:33,  1.71it/s]
Train steps ... :  16%|█▋        | 16445/100000 [4:53:28<13:33:16,  1.71it/s]
Train steps ... :  16%|█▋        | 16446/100000 [4:53:28<13:33:22,  1.71it/s]
Train steps ... :  16%|█▋        | 16447/100000 [4:53:29<13:34:47,  1.71it/s]
Train steps ... :  16%|█▋        | 16448/100000 [4:53:29<13:34:47,  1.71it/s]
Train steps ... :  16%|█▋        | 16449/100000 [4:53:30<13:35:07,  1.71it/s]
Train steps ... :  16%|█▋        | 16450/100000 [4:53:30<13:33:40,  1.71it/s]Step... (16450 / 100000 | Loss: 1.1475987434387207, Learning Rate: 8.396984924623115e-05)
+
                                                                             
Step... (16450 / 100000 | Loss: 0.7472834587097168, Learning Rate: 8.396984924623115e-05)
+
Train steps ... :  16%|█▋        | 16450/100000 [4:53:31<13:33:40,  1.71it/s]
Train steps ... :  16%|█▋        | 16451/100000 [4:53:31<13:38:08,  1.70it/s]
Train steps ... :  16%|█▋        | 16452/100000 [4:53:32<13:37:33,  1.70it/s]
Train steps ... :  16%|█▋        | 16453/100000 [4:53:32<13:36:16,  1.71it/s]
Train steps ... :  16%|█▋        | 16454/100000 [4:53:33<13:36:17,  1.71it/s]
Train steps ... :  16%|█▋        | 16455/100000 [4:53:33<13:35:34,  1.71it/s]
Train steps ... :  16%|█▋        | 16456/100000 [4:53:34<13:34:32,  1.71it/s]
Train steps ... :  16%|█▋        | 16457/100000 [4:53:35<13:34:59,  1.71it/s]
Train steps ... :  16%|█▋        | 16458/100000 [4:53:35<13:35:19,  1.71it/s]
Train steps ... :  16%|█▋        | 16459/100000 [4:53:36<13:38:51,  1.70it/s]
Train steps ... :  16%|█▋        | 16460/100000 [4:53:36<13:34:19,  1.71it/s]
Train steps ... :  16%|█▋        | 16461/100000 [4:53:37<13:33:36,  1.71it/s]
Train steps ... :  16%|█▋        | 16462/100000 [4:53:38<13:34:42,  1.71it/s]
Train steps ... :  16%|█▋        | 16463/100000 [4:53:38<13:34:06,  1.71it/s]
Train steps ... :  16%|█▋        | 16464/100000 [4:53:39<13:33:41,  1.71it/s]
Train steps ... :  16%|█▋        | 16465/100000 [4:53:39<13:32:59,  1.71it/s]
Train steps ... :  16%|█▋        | 16466/100000 [4:53:40<13:33:30,  1.71it/s]
Train steps ... :  16%|█▋        | 16467/100000 [4:53:40<13:33:09,  1.71it/s]
Train steps ... :  16%|█▋        | 16468/100000 [4:53:41<13:33:25,  1.71it/s]
Train steps ... :  16%|█▋        | 16469/100000 [4:53:42<13:33:26,  1.71it/s]
Train steps ... :  16%|█▋        | 16470/100000 [4:53:42<13:33:15,  1.71it/s]
Train steps ... :  16%|█▋        | 16471/100000 [4:53:43<13:32:54,  1.71it/s]
Train steps ... :  16%|█▋        | 16472/100000 [4:53:43<13:32:49,  1.71it/s]
Train steps ... :  16%|█▋        | 16473/100000 [4:53:44<13:33:42,  1.71it/s]
Train steps ... :  16%|█▋        | 16474/100000 [4:53:45<13:32:54,  1.71it/s]
Train steps ... :  16%|█▋        | 16475/100000 [4:53:45<13:33:59,  1.71it/s]Step... (16475 / 100000 | Loss: 1.200515627861023, Learning Rate: 8.394472361809046e-05)
+
                                                                             
Step... (16475 / 100000 | Loss: 1.0059130191802979, Learning Rate: 8.394472361809046e-05)
+
Train steps ... :  16%|█▋        | 16475/100000 [4:53:45<13:33:59,  1.71it/s]
Train steps ... :  16%|█▋        | 16476/100000 [4:53:46<13:34:31,  1.71it/s]
Train steps ... :  16%|█▋        | 16477/100000 [4:53:46<13:34:37,  1.71it/s]
Train steps ... :  16%|█▋        | 16478/100000 [4:53:47<13:34:22,  1.71it/s]
Train steps ... :  16%|█▋        | 16479/100000 [4:53:47<13:33:53,  1.71it/s]
Train steps ... :  16%|█▋        | 16480/100000 [4:53:48<13:33:47,  1.71it/s]
Train steps ... :  16%|█▋        | 16481/100000 [4:53:49<13:36:21,  1.71it/s]
Train steps ... :  16%|█▋        | 16482/100000 [4:53:49<13:33:12,  1.71it/s]
Train steps ... :  16%|█▋        | 16483/100000 [4:53:50<13:33:42,  1.71it/s]
Train steps ... :  16%|█▋        | 16484/100000 [4:53:50<13:32:37,  1.71it/s]
Train steps ... :  16%|█▋        | 16485/100000 [4:53:51<13:33:19,  1.71it/s]
Train steps ... :  16%|█▋        | 16486/100000 [4:53:52<13:33:28,  1.71it/s]
Train steps ... :  16%|█▋        | 16487/100000 [4:53:52<13:33:59,  1.71it/s]
Train steps ... :  16%|█▋        | 16488/100000 [4:53:53<13:34:16,  1.71it/s]
Train steps ... :  16%|█▋        | 16489/100000 [4:53:53<13:33:22,  1.71it/s]
Train steps ... :  16%|█▋        | 16490/100000 [4:53:54<13:33:01,  1.71it/s]
Train steps ... :  16%|█▋        | 16491/100000 [4:53:54<13:33:14,  1.71it/s]
Train steps ... :  16%|█▋        | 16492/100000 [4:53:55<13:34:29,  1.71it/s]
Train steps ... :  16%|█▋        | 16493/100000 [4:53:56<13:33:17,  1.71it/s]
Train steps ... :  16%|█▋        | 16494/100000 [4:53:56<13:33:56,  1.71it/s]
Train steps ... :  16%|█▋        | 16495/100000 [4:53:57<13:34:07,  1.71it/s]
Train steps ... :  16%|█▋        | 16496/100000 [4:53:57<13:34:02,  1.71it/s]
Train steps ... :  16%|█▋        | 16497/100000 [4:53:58<13:33:16,  1.71it/s]
Train steps ... :  16%|█▋        | 16498/100000 [4:53:59<13:33:42,  1.71it/s]
Train steps ... :  16%|█▋        | 16499/100000 [4:53:59<13:33:14,  1.71it/s]
Train steps ... :  16%|█▋        | 16500/100000 [4:54:00<13:33:09,  1.71it/s]Step... (16500 / 100000 | Loss: 1.1702682971954346, Learning Rate: 8.391959798994975e-05)
+
                                                                             
Step... (16500 / 100000 | Loss: 0.813420295715332, Learning Rate: 8.391959798994975e-05)
+
Train steps ... :  16%|█▋        | 16500/100000 [4:54:00<13:33:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16501/100000 [4:54:00<13:33:54,  1.71it/s]
Train steps ... :  17%|█▋        | 16502/100000 [4:54:01<13:32:53,  1.71it/s]
Train steps ... :  17%|█▋        | 16503/100000 [4:54:01<13:32:38,  1.71it/s]
Train steps ... :  17%|█▋        | 16504/100000 [4:54:02<13:31:48,  1.71it/s]
Train steps ... :  17%|█▋        | 16505/100000 [4:54:03<13:32:00,  1.71it/s]
Train steps ... :  17%|█▋        | 16506/100000 [4:54:03<13:33:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16507/100000 [4:54:04<13:33:41,  1.71it/s]
Train steps ... :  17%|█▋        | 16508/100000 [4:54:04<13:33:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16509/100000 [4:54:05<13:34:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16510/100000 [4:54:06<13:33:46,  1.71it/s]
Train steps ... :  17%|█▋        | 16511/100000 [4:54:06<13:33:30,  1.71it/s]
Train steps ... :  17%|█▋        | 16512/100000 [4:54:07<13:32:57,  1.71it/s]
Train steps ... :  17%|█▋        | 16513/100000 [4:54:07<13:32:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16514/100000 [4:54:08<13:33:24,  1.71it/s]
Train steps ... :  17%|█▋        | 16515/100000 [4:54:08<13:33:06,  1.71it/s]
Train steps ... :  17%|█▋        | 16516/100000 [4:54:09<13:33:04,  1.71it/s]
Train steps ... :  17%|█▋        | 16517/100000 [4:54:10<13:32:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16518/100000 [4:54:10<13:32:49,  1.71it/s]
Train steps ... :  17%|█▋        | 16519/100000 [4:54:11<13:32:41,  1.71it/s]
Train steps ... :  17%|█▋        | 16520/100000 [4:54:11<13:33:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16521/100000 [4:54:12<13:33:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16522/100000 [4:54:13<13:32:51,  1.71it/s]
Train steps ... :  17%|█▋        | 16523/100000 [4:54:13<13:33:04,  1.71it/s]
Train steps ... :  17%|█▋        | 16524/100000 [4:54:14<13:34:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16525/100000 [4:54:14<13:34:38,  1.71it/s]Step... (16525 / 100000 | Loss: 1.0044732093811035, Learning Rate: 8.389447236180906e-05)
+
                                                                             
Step... (16525 / 100000 | Loss: 1.199055790901184, Learning Rate: 8.389447236180906e-05)
+
Train steps ... :  17%|█▋        | 16525/100000 [4:54:15<13:34:38,  1.71it/s]
Train steps ... :  17%|█▋        | 16526/100000 [4:54:15<13:34:13,  1.71it/s]
Train steps ... :  17%|█▋        | 16527/100000 [4:54:16<13:34:00,  1.71it/s]
Train steps ... :  17%|█▋        | 16528/100000 [4:54:16<13:32:53,  1.71it/s]
Train steps ... :  17%|█▋        | 16529/100000 [4:54:17<13:32:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16530/100000 [4:54:17<13:32:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16531/100000 [4:54:18<13:32:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16532/100000 [4:54:18<13:32:33,  1.71it/s]
Train steps ... :  17%|█▋        | 16533/100000 [4:54:19<13:32:15,  1.71it/s]
Train steps ... :  17%|█▋        | 16534/100000 [4:54:20<13:32:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16535/100000 [4:54:20<13:32:34,  1.71it/s]
Train steps ... :  17%|█▋        | 16536/100000 [4:54:21<13:32:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16537/100000 [4:54:21<13:32:49,  1.71it/s]
Train steps ... :  17%|█▋        | 16538/100000 [4:54:22<13:32:21,  1.71it/s]
Train steps ... :  17%|█▋        | 16539/100000 [4:54:23<13:33:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16540/100000 [4:54:23<13:33:30,  1.71it/s]
Train steps ... :  17%|█▋        | 16541/100000 [4:54:24<13:33:11,  1.71it/s]
Train steps ... :  17%|█▋        | 16542/100000 [4:54:24<13:34:01,  1.71it/s]
Train steps ... :  17%|█▋        | 16543/100000 [4:54:25<13:33:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16544/100000 [4:54:25<13:33:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16545/100000 [4:54:26<13:33:17,  1.71it/s]
Train steps ... :  17%|█▋        | 16546/100000 [4:54:27<13:33:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16547/100000 [4:54:27<13:33:06,  1.71it/s]
Train steps ... :  17%|█▋        | 16548/100000 [4:54:28<13:32:45,  1.71it/s]
Train steps ... :  17%|█▋        | 16549/100000 [4:54:28<13:32:11,  1.71it/s]
Train steps ... :  17%|█▋        | 16550/100000 [4:54:29<13:33:25,  1.71it/s]Step... (16550 / 100000 | Loss: 0.7611103057861328, Learning Rate: 8.386934673366834e-05)
+
                                                                             
Step... (16550 / 100000 | Loss: 0.9956673383712769, Learning Rate: 8.386934673366834e-05)
+
Train steps ... :  17%|█▋        | 16550/100000 [4:54:29<13:33:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16551/100000 [4:54:30<13:33:15,  1.71it/s]
Train steps ... :  17%|█▋        | 16552/100000 [4:54:30<13:33:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16553/100000 [4:54:31<13:32:28,  1.71it/s]
Train steps ... :  17%|█▋        | 16554/100000 [4:54:31<13:32:35,  1.71it/s]
Train steps ... :  17%|█▋        | 16555/100000 [4:54:32<13:32:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16556/100000 [4:54:32<13:34:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16557/100000 [4:54:33<13:33:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16558/100000 [4:54:34<13:34:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16559/100000 [4:54:34<13:33:38,  1.71it/s]
Train steps ... :  17%|█▋        | 16560/100000 [4:54:35<13:32:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16561/100000 [4:54:35<13:32:52,  1.71it/s]
Train steps ... :  17%|█▋        | 16562/100000 [4:54:36<13:32:41,  1.71it/s]
Train steps ... :  17%|█▋        | 16563/100000 [4:54:37<13:33:15,  1.71it/s]
Train steps ... :  17%|█▋        | 16564/100000 [4:54:37<13:32:46,  1.71it/s]
Train steps ... :  17%|█▋        | 16565/100000 [4:54:38<13:33:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16566/100000 [4:54:38<13:33:01,  1.71it/s]
Train steps ... :  17%|█▋        | 16567/100000 [4:54:39<13:33:04,  1.71it/s]
Train steps ... :  17%|█▋        | 16568/100000 [4:54:39<13:33:12,  1.71it/s]
Train steps ... :  17%|█▋        | 16569/100000 [4:54:40<13:34:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16570/100000 [4:54:41<13:33:39,  1.71it/s]
Train steps ... :  17%|█▋        | 16571/100000 [4:54:41<13:32:55,  1.71it/s]
Train steps ... :  17%|█▋        | 16572/100000 [4:54:42<13:33:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16573/100000 [4:54:42<13:32:51,  1.71it/s]
Train steps ... :  17%|█▋        | 16574/100000 [4:54:43<13:32:24,  1.71it/s]
Train steps ... :  17%|█▋        | 16575/100000 [4:54:44<13:32:28,  1.71it/s]Step... (16575 / 100000 | Loss: 1.2315454483032227, Learning Rate: 8.384422110552764e-05)
+
                                                                             
Step... (16575 / 100000 | Loss: 0.9784159064292908, Learning Rate: 8.384422110552764e-05)
+
Train steps ... :  17%|█▋        | 16575/100000 [4:54:44<13:32:28,  1.71it/s]
Train steps ... :  17%|█▋        | 16576/100000 [4:54:44<13:32:45,  1.71it/s]
Train steps ... :  17%|█▋        | 16577/100000 [4:54:45<13:33:36,  1.71it/s]
Train steps ... :  17%|█▋        | 16578/100000 [4:54:45<13:32:39,  1.71it/s]
Train steps ... :  17%|█▋        | 16579/100000 [4:54:46<13:32:30,  1.71it/s]
Train steps ... :  17%|█▋        | 16580/100000 [4:54:46<13:33:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16581/100000 [4:54:47<13:32:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16582/100000 [4:54:48<13:34:41,  1.71it/s]
Train steps ... :  17%|█▋        | 16583/100000 [4:54:48<13:33:02,  1.71it/s]
Train steps ... :  17%|█▋        | 16584/100000 [4:54:49<13:32:36,  1.71it/s]
Train steps ... :  17%|█▋        | 16585/100000 [4:54:49<13:32:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16586/100000 [4:54:50<13:33:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16587/100000 [4:54:51<13:33:15,  1.71it/s]
Train steps ... :  17%|█▋        | 16588/100000 [4:54:51<13:32:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16589/100000 [4:54:52<13:32:45,  1.71it/s]
Train steps ... :  17%|█▋        | 16590/100000 [4:54:52<13:33:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16591/100000 [4:54:53<13:33:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16592/100000 [4:54:54<13:33:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16593/100000 [4:54:54<13:33:26,  1.71it/s]
Train steps ... :  17%|█▋        | 16594/100000 [4:54:55<13:32:48,  1.71it/s]
Train steps ... :  17%|█▋        | 16595/100000 [4:54:55<13:32:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16596/100000 [4:54:56<13:33:17,  1.71it/s]
Train steps ... :  17%|█▋        | 16597/100000 [4:54:56<13:32:11,  1.71it/s]
Train steps ... :  17%|█▋        | 16598/100000 [4:54:57<13:33:30,  1.71it/s]
Train steps ... :  17%|█▋        | 16599/100000 [4:54:58<13:32:37,  1.71it/s]
Train steps ... :  17%|█▋        | 16600/100000 [4:54:58<13:32:13,  1.71it/s]Step... (16600 / 100000 | Loss: 1.424290418624878, Learning Rate: 8.381909547738695e-05)
+
                                                                             
Step... (16600 / 100000 | Loss: 1.5382493734359741, Learning Rate: 8.381909547738695e-05)
+
Train steps ... :  17%|█▋        | 16600/100000 [4:54:59<13:32:13,  1.71it/s]
Train steps ... :  17%|█▋        | 16601/100000 [4:54:59<13:33:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16602/100000 [4:54:59<13:32:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16603/100000 [4:55:00<13:31:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16604/100000 [4:55:01<13:31:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16605/100000 [4:55:01<13:31:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16606/100000 [4:55:02<13:31:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16607/100000 [4:55:02<13:31:20,  1.71it/s]
Train steps ... :  17%|█▋        | 16608/100000 [4:55:03<13:31:02,  1.71it/s]
Train steps ... :  17%|█▋        | 16609/100000 [4:55:03<13:31:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16610/100000 [4:55:04<13:34:35,  1.71it/s]
Train steps ... :  17%|█▋        | 16611/100000 [4:55:05<13:31:24,  1.71it/s]
Train steps ... :  17%|█▋        | 16612/100000 [4:55:05<13:32:45,  1.71it/s]
Train steps ... :  17%|█▋        | 16613/100000 [4:55:06<13:32:46,  1.71it/s]
Train steps ... :  17%|█▋        | 16614/100000 [4:55:06<13:31:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16615/100000 [4:55:07<13:32:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16616/100000 [4:55:08<13:32:57,  1.71it/s]
Train steps ... :  17%|█▋        | 16617/100000 [4:55:08<13:33:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16618/100000 [4:55:09<13:33:16,  1.71it/s]
Train steps ... :  17%|█▋        | 16619/100000 [4:55:09<13:33:01,  1.71it/s]
Train steps ... :  17%|█▋        | 16620/100000 [4:55:10<13:33:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16621/100000 [4:55:10<13:32:15,  1.71it/s]
Train steps ... :  17%|█▋        | 16622/100000 [4:55:11<13:33:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16623/100000 [4:55:12<13:32:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16624/100000 [4:55:12<13:31:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16625/100000 [4:55:13<13:31:59,  1.71it/s]Step... (16625 / 100000 | Loss: 0.9607599973678589, Learning Rate: 8.379396984924623e-05)
+
                                                                             
Step... (16625 / 100000 | Loss: 1.033672571182251, Learning Rate: 8.379396984924623e-05)
+
Train steps ... :  17%|█▋        | 16625/100000 [4:55:13<13:31:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16626/100000 [4:55:13<13:32:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16627/100000 [4:55:14<13:31:50,  1.71it/s]
Train steps ... :  17%|█▋        | 16628/100000 [4:55:15<13:31:28,  1.71it/s]
Train steps ... :  17%|█▋        | 16629/100000 [4:55:15<13:31:50,  1.71it/s]
Train steps ... :  17%|█▋        | 16630/100000 [4:55:16<13:31:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16631/100000 [4:55:16<13:31:49,  1.71it/s]
Train steps ... :  17%|█▋        | 16632/100000 [4:55:17<13:31:23,  1.71it/s]
Train steps ... :  17%|█▋        | 16633/100000 [4:55:17<13:31:14,  1.71it/s]
Train steps ... :  17%|█▋        | 16634/100000 [4:55:18<13:31:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16635/100000 [4:55:19<13:33:35,  1.71it/s]
Train steps ... :  17%|█▋        | 16636/100000 [4:55:19<13:34:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16637/100000 [4:55:20<13:33:23,  1.71it/s]
Train steps ... :  17%|█▋        | 16638/100000 [4:55:20<13:33:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16639/100000 [4:55:21<13:31:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16640/100000 [4:55:22<13:32:33,  1.71it/s]
Train steps ... :  17%|█▋        | 16641/100000 [4:55:22<13:32:48,  1.71it/s]
Train steps ... :  17%|█▋        | 16642/100000 [4:55:23<13:32:17,  1.71it/s]
Train steps ... :  17%|█▋        | 16643/100000 [4:55:23<13:31:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16644/100000 [4:55:24<13:33:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16645/100000 [4:55:24<13:32:34,  1.71it/s]
Train steps ... :  17%|█▋        | 16646/100000 [4:55:25<13:32:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16647/100000 [4:55:26<13:31:51,  1.71it/s]
Train steps ... :  17%|█▋        | 16648/100000 [4:55:26<13:31:55,  1.71it/s]
Train steps ... :  17%|█▋        | 16649/100000 [4:55:27<13:31:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16650/100000 [4:55:27<13:31:18,  1.71it/s]Step... (16650 / 100000 | Loss: 0.9899942874908447, Learning Rate: 8.376884422110554e-05)
+
                                                                             
Step... (16650 / 100000 | Loss: 1.1058008670806885, Learning Rate: 8.376884422110554e-05)
+
Train steps ... :  17%|█▋        | 16650/100000 [4:55:28<13:31:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16651/100000 [4:55:28<13:32:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16652/100000 [4:55:29<13:32:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16653/100000 [4:55:29<13:32:15,  1.71it/s]
Train steps ... :  17%|█▋        | 16654/100000 [4:55:30<13:32:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16655/100000 [4:55:30<13:31:23,  1.71it/s]
Train steps ... :  17%|█▋        | 16656/100000 [4:55:31<13:31:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16657/100000 [4:55:32<13:31:39,  1.71it/s]
Train steps ... :  17%|█▋        | 16658/100000 [4:55:32<13:31:26,  1.71it/s]
Train steps ... :  17%|█▋        | 16659/100000 [4:55:33<13:31:33,  1.71it/s]
Train steps ... :  17%|█▋        | 16660/100000 [4:55:33<13:31:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16661/100000 [4:55:34<13:30:51,  1.71it/s]
Train steps ... :  17%|█▋        | 16662/100000 [4:55:34<13:31:33,  1.71it/s]
Train steps ... :  17%|█▋        | 16663/100000 [4:55:35<13:32:46,  1.71it/s]
Train steps ... :  17%|█▋        | 16664/100000 [4:55:36<13:32:06,  1.71it/s]
Train steps ... :  17%|█▋        | 16665/100000 [4:55:36<13:31:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16666/100000 [4:55:37<13:31:24,  1.71it/s]
Train steps ... :  17%|█▋        | 16667/100000 [4:55:37<13:31:23,  1.71it/s]
Train steps ... :  17%|█▋        | 16668/100000 [4:55:38<13:31:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16669/100000 [4:55:39<13:34:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16670/100000 [4:55:39<13:33:39,  1.71it/s]
Train steps ... :  17%|█▋        | 16671/100000 [4:55:40<13:33:12,  1.71it/s]
Train steps ... :  17%|█▋        | 16672/100000 [4:55:40<13:31:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16673/100000 [4:55:41<13:31:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16674/100000 [4:55:41<13:31:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16675/100000 [4:55:42<13:31:31,  1.71it/s]Step... (16675 / 100000 | Loss: 0.9304031133651733, Learning Rate: 8.374371859296482e-05)
+
                                                                             
Step... (16675 / 100000 | Loss: 1.0704652070999146, Learning Rate: 8.374371859296482e-05)
+
Train steps ... :  17%|█▋        | 16675/100000 [4:55:42<13:31:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16676/100000 [4:55:43<13:31:36,  1.71it/s]
Train steps ... :  17%|█▋        | 16677/100000 [4:55:43<13:31:20,  1.71it/s]
Train steps ... :  17%|█▋        | 16678/100000 [4:55:44<13:32:01,  1.71it/s]
Train steps ... :  17%|█▋        | 16679/100000 [4:55:44<13:32:23,  1.71it/s]
Train steps ... :  17%|█▋        | 16680/100000 [4:55:45<13:32:38,  1.71it/s]
Train steps ... :  17%|█▋        | 16681/100000 [4:55:46<13:32:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16682/100000 [4:55:46<13:32:02,  1.71it/s]
Train steps ... :  17%|█▋        | 16683/100000 [4:55:47<13:32:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16684/100000 [4:55:47<13:32:11,  1.71it/s]
Train steps ... :  17%|█▋        | 16685/100000 [4:55:48<13:31:55,  1.71it/s]
Train steps ... :  17%|█▋        | 16686/100000 [4:55:48<13:31:30,  1.71it/s]
Train steps ... :  17%|█▋        | 16687/100000 [4:55:49<13:31:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16688/100000 [4:55:50<13:31:20,  1.71it/s]
Train steps ... :  17%|█▋        | 16689/100000 [4:55:50<13:31:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16690/100000 [4:55:51<13:31:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16691/100000 [4:55:51<13:31:57,  1.71it/s]
Train steps ... :  17%|█▋        | 16692/100000 [4:55:52<13:32:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16693/100000 [4:55:53<13:31:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16694/100000 [4:55:53<13:31:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16695/100000 [4:55:54<13:31:41,  1.71it/s]
Train steps ... :  17%|█▋        | 16696/100000 [4:55:54<13:31:38,  1.71it/s]
Train steps ... :  17%|█▋        | 16697/100000 [4:55:55<13:32:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16698/100000 [4:55:55<13:32:05,  1.71it/s]
Train steps ... :  17%|█▋        | 16699/100000 [4:55:56<13:32:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16700/100000 [4:55:57<13:32:09,  1.71it/s]Step... (16700 / 100000 | Loss: 1.2563276290893555, Learning Rate: 8.371859296482413e-05)
+
                                                                             
Step... (16700 / 100000 | Loss: 1.1770789623260498, Learning Rate: 8.371859296482413e-05)
+
Train steps ... :  17%|█▋        | 16700/100000 [4:55:57<13:32:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16701/100000 [4:55:57<13:31:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16702/100000 [4:55:58<13:33:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16703/100000 [4:55:58<13:33:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16704/100000 [4:55:59<13:32:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16705/100000 [4:56:00<13:32:36,  1.71it/s]
Train steps ... :  17%|█▋        | 16706/100000 [4:56:00<13:31:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16707/100000 [4:56:01<13:31:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16708/100000 [4:56:01<13:31:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16709/100000 [4:56:02<13:30:57,  1.71it/s]
Train steps ... :  17%|█▋        | 16710/100000 [4:56:02<13:30:46,  1.71it/s]
Train steps ... :  17%|█▋        | 16711/100000 [4:56:03<13:31:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16712/100000 [4:56:04<13:30:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16713/100000 [4:56:04<13:31:28,  1.71it/s]
Train steps ... :  17%|█▋        | 16714/100000 [4:56:05<13:30:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16715/100000 [4:56:05<13:30:53,  1.71it/s]
Train steps ... :  17%|█▋        | 16716/100000 [4:56:06<13:31:41,  1.71it/s]
Train steps ... :  17%|█▋        | 16717/100000 [4:56:07<13:30:55,  1.71it/s]
Train steps ... :  17%|█▋        | 16718/100000 [4:56:07<13:30:39,  1.71it/s]
Train steps ... :  17%|█▋        | 16719/100000 [4:56:08<13:32:30,  1.71it/s]
Train steps ... :  17%|█▋        | 16720/100000 [4:56:08<13:30:20,  1.71it/s]
Train steps ... :  17%|█▋        | 16721/100000 [4:56:09<13:30:35,  1.71it/s]
Train steps ... :  17%|█▋        | 16722/100000 [4:56:10<13:30:35,  1.71it/s]
Train steps ... :  17%|█▋        | 16723/100000 [4:56:10<13:31:06,  1.71it/s]
Train steps ... :  17%|█▋        | 16724/100000 [4:56:11<13:30:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16725/100000 [4:56:11<13:30:24,  1.71it/s]Step... (16725 / 100000 | Loss: 1.3390309810638428, Learning Rate: 8.369346733668342e-05)
+
                                                                             
Step... (16725 / 100000 | Loss: 0.9830014705657959, Learning Rate: 8.369346733668342e-05)
+
Train steps ... :  17%|█▋        | 16725/100000 [4:56:12<13:30:24,  1.71it/s]
Train steps ... :  17%|█▋        | 16726/100000 [4:56:12<13:31:30,  1.71it/s]
Train steps ... :  17%|█▋        | 16727/100000 [4:56:12<13:30:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16728/100000 [4:56:13<13:30:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16729/100000 [4:56:14<13:30:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16730/100000 [4:56:14<13:30:50,  1.71it/s]
Train steps ... :  17%|█▋        | 16731/100000 [4:56:15<13:30:44,  1.71it/s]
Train steps ... :  17%|█▋        | 16732/100000 [4:56:15<13:32:45,  1.71it/s]
Train steps ... :  17%|█▋        | 16733/100000 [4:56:16<13:32:17,  1.71it/s]
Train steps ... :  17%|█▋        | 16734/100000 [4:56:17<13:31:46,  1.71it/s]
Train steps ... :  17%|█▋        | 16735/100000 [4:56:17<13:32:11,  1.71it/s]
Train steps ... :  17%|█▋        | 16736/100000 [4:56:18<13:32:22,  1.71it/s]
Train steps ... :  17%|█▋        | 16737/100000 [4:56:18<13:32:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16738/100000 [4:56:19<13:32:28,  1.71it/s]
Train steps ... :  17%|█▋        | 16739/100000 [4:56:19<13:31:50,  1.71it/s]
Train steps ... :  17%|█▋        | 16740/100000 [4:56:20<13:31:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16741/100000 [4:56:21<13:31:00,  1.71it/s]
Train steps ... :  17%|█▋        | 16742/100000 [4:56:21<13:31:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16743/100000 [4:56:22<13:31:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16744/100000 [4:56:22<13:31:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16745/100000 [4:56:23<13:30:37,  1.71it/s]
Train steps ... :  17%|█▋        | 16746/100000 [4:56:24<13:30:36,  1.71it/s]
Train steps ... :  17%|█▋        | 16747/100000 [4:56:24<13:30:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16748/100000 [4:56:25<13:30:54,  1.71it/s]
Train steps ... :  17%|█▋        | 16749/100000 [4:56:25<13:31:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16750/100000 [4:56:26<13:31:06,  1.71it/s]Step... (16750 / 100000 | Loss: 1.1742022037506104, Learning Rate: 8.366834170854271e-05)
+
                                                                             
Step... (16750 / 100000 | Loss: 1.3273146152496338, Learning Rate: 8.366834170854271e-05)
+
Train steps ... :  17%|█▋        | 16750/100000 [4:56:26<13:31:06,  1.71it/s]
Train steps ... :  17%|█▋        | 16751/100000 [4:56:26<13:31:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16752/100000 [4:56:27<13:31:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16753/100000 [4:56:28<13:31:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16754/100000 [4:56:28<13:30:51,  1.71it/s]
Train steps ... :  17%|█▋        | 16755/100000 [4:56:29<13:30:52,  1.71it/s]
Train steps ... :  17%|█▋        | 16756/100000 [4:56:29<13:30:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16757/100000 [4:56:30<13:31:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16758/100000 [4:56:31<13:31:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16759/100000 [4:56:31<13:31:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16760/100000 [4:56:32<13:30:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16761/100000 [4:56:32<13:30:50,  1.71it/s]
Train steps ... :  17%|█▋        | 16762/100000 [4:56:33<13:30:44,  1.71it/s]
Train steps ... :  17%|█▋        | 16763/100000 [4:56:33<13:30:53,  1.71it/s]
Train steps ... :  17%|█▋        | 16764/100000 [4:56:34<13:31:01,  1.71it/s]
Train steps ... :  17%|█▋        | 16765/100000 [4:56:35<13:31:56,  1.71it/s]
Train steps ... :  17%|█▋        | 16766/100000 [4:56:35<13:31:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16767/100000 [4:56:36<13:31:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16768/100000 [4:56:36<13:32:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16769/100000 [4:56:37<13:31:50,  1.71it/s]
Train steps ... :  17%|█▋        | 16770/100000 [4:56:38<13:31:48,  1.71it/s]
Train steps ... :  17%|█▋        | 16771/100000 [4:56:38<13:31:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16772/100000 [4:56:39<13:31:11,  1.71it/s]
Train steps ... :  17%|█▋        | 16773/100000 [4:56:39<13:30:33,  1.71it/s]
Train steps ... :  17%|█▋        | 16774/100000 [4:56:40<13:30:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16775/100000 [4:56:40<13:30:55,  1.71it/s]Step... (16775 / 100000 | Loss: 0.9947055578231812, Learning Rate: 8.364321608040201e-05)
+
                                                                             
Step... (16775 / 100000 | Loss: 1.0546071529388428, Learning Rate: 8.364321608040201e-05)
+
Train steps ... :  17%|█▋        | 16775/100000 [4:56:41<13:30:55,  1.71it/s]
Train steps ... :  17%|█▋        | 16776/100000 [4:56:41<13:31:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16777/100000 [4:56:42<13:30:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16778/100000 [4:56:42<13:30:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16779/100000 [4:56:43<13:30:38,  1.71it/s]
Train steps ... :  17%|█▋        | 16780/100000 [4:56:43<13:30:30,  1.71it/s]
Train steps ... :  17%|█▋        | 16781/100000 [4:56:44<13:31:02,  1.71it/s]
Train steps ... :  17%|█▋        | 16782/100000 [4:56:45<13:31:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16783/100000 [4:56:45<13:30:28,  1.71it/s]
Train steps ... :  17%|█▋        | 16784/100000 [4:56:46<13:30:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16785/100000 [4:56:46<13:29:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16786/100000 [4:56:47<13:29:34,  1.71it/s]
Train steps ... :  17%|█▋        | 16787/100000 [4:56:48<13:29:46,  1.71it/s]
Train steps ... :  17%|█▋        | 16788/100000 [4:56:48<13:29:57,  1.71it/s]
Train steps ... :  17%|█▋        | 16789/100000 [4:56:49<13:29:22,  1.71it/s]
Train steps ... :  17%|█▋        | 16790/100000 [4:56:49<13:30:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16791/100000 [4:56:50<13:30:30,  1.71it/s]
Train steps ... :  17%|█▋        | 16792/100000 [4:56:50<13:31:26,  1.71it/s]
Train steps ... :  17%|█▋        | 16793/100000 [4:56:51<13:30:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16794/100000 [4:56:52<13:30:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16795/100000 [4:56:52<13:31:06,  1.71it/s]
Train steps ... :  17%|█▋        | 16796/100000 [4:56:53<13:30:46,  1.71it/s]
Train steps ... :  17%|█▋        | 16797/100000 [4:56:53<13:30:26,  1.71it/s]
Train steps ... :  17%|█▋        | 16798/100000 [4:56:54<13:30:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16799/100000 [4:56:55<13:30:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16800/100000 [4:56:55<13:30:21,  1.71it/s]Step... (16800 / 100000 | Loss: 1.0963268280029297, Learning Rate: 8.36180904522613e-05)
+
                                                                             
Step... (16800 / 100000 | Loss: 0.8548029065132141, Learning Rate: 8.36180904522613e-05)
+
Train steps ... :  17%|█▋        | 16800/100000 [4:56:55<13:30:21,  1.71it/s]
Train steps ... :  17%|█▋        | 16801/100000 [4:56:56<13:32:01,  1.71it/s]
Train steps ... :  17%|█▋        | 16802/100000 [4:56:56<13:30:56,  1.71it/s]
Train steps ... :  17%|█▋        | 16803/100000 [4:56:57<13:30:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16804/100000 [4:56:57<13:30:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16805/100000 [4:56:58<13:29:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16806/100000 [4:56:59<13:30:39,  1.71it/s]
Train steps ... :  17%|█▋        | 16807/100000 [4:56:59<13:29:48,  1.71it/s]
Train steps ... :  17%|█▋        | 16808/100000 [4:57:00<13:29:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16809/100000 [4:57:00<13:29:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16810/100000 [4:57:01<13:29:56,  1.71it/s]
Train steps ... :  17%|█▋        | 16811/100000 [4:57:02<13:29:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16812/100000 [4:57:02<13:30:11,  1.71it/s]
Train steps ... :  17%|█▋        | 16813/100000 [4:57:03<13:30:20,  1.71it/s]
Train steps ... :  17%|█▋        | 16814/100000 [4:57:03<13:30:02,  1.71it/s]
Train steps ... :  17%|█▋        | 16815/100000 [4:57:04<13:29:35,  1.71it/s]
Train steps ... :  17%|█▋        | 16816/100000 [4:57:04<13:29:48,  1.71it/s]
Train steps ... :  17%|█▋        | 16817/100000 [4:57:05<13:29:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16818/100000 [4:57:06<13:29:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16819/100000 [4:57:06<13:31:15,  1.71it/s]
Train steps ... :  17%|█▋        | 16820/100000 [4:57:07<13:30:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16821/100000 [4:57:07<13:29:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16822/100000 [4:57:08<13:30:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16823/100000 [4:57:09<13:29:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16824/100000 [4:57:09<13:29:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16825/100000 [4:57:10<13:30:23,  1.71it/s]Step... (16825 / 100000 | Loss: 0.984415590763092, Learning Rate: 8.359296482412062e-05)
+
                                                                             
Step... (16825 / 100000 | Loss: 1.342130422592163, Learning Rate: 8.359296482412062e-05)
+
Train steps ... :  17%|█▋        | 16825/100000 [4:57:10<13:30:23,  1.71it/s]
Train steps ... :  17%|█▋        | 16826/100000 [4:57:10<13:30:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16827/100000 [4:57:11<13:29:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16828/100000 [4:57:11<13:29:24,  1.71it/s]
Train steps ... :  17%|█▋        | 16829/100000 [4:57:12<13:29:05,  1.71it/s]
Train steps ... :  17%|█▋        | 16830/100000 [4:57:13<13:30:02,  1.71it/s]
Train steps ... :  17%|█▋        | 16831/100000 [4:57:13<13:29:54,  1.71it/s]
Train steps ... :  17%|█▋        | 16832/100000 [4:57:14<13:31:00,  1.71it/s]
Train steps ... :  17%|█▋        | 16833/100000 [4:57:14<13:31:41,  1.71it/s]
Train steps ... :  17%|█▋        | 16834/100000 [4:57:15<13:29:01,  1.71it/s]
Train steps ... :  17%|█▋        | 16835/100000 [4:57:16<13:31:33,  1.71it/s]
Train steps ... :  17%|█▋        | 16836/100000 [4:57:16<13:31:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16837/100000 [4:57:17<13:30:44,  1.71it/s]
Train steps ... :  17%|█▋        | 16838/100000 [4:57:17<13:30:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16839/100000 [4:57:18<13:30:06,  1.71it/s]
Train steps ... :  17%|█▋        | 16840/100000 [4:57:18<13:31:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16841/100000 [4:57:19<13:30:34,  1.71it/s]
Train steps ... :  17%|█▋        | 16842/100000 [4:57:20<13:30:49,  1.71it/s]
Train steps ... :  17%|█▋        | 16843/100000 [4:57:20<13:30:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16844/100000 [4:57:21<13:29:46,  1.71it/s]
Train steps ... :  17%|█▋        | 16845/100000 [4:57:21<13:29:28,  1.71it/s]
Train steps ... :  17%|█▋        | 16846/100000 [4:57:22<13:29:48,  1.71it/s]
Train steps ... :  17%|█▋        | 16847/100000 [4:57:23<13:30:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16848/100000 [4:57:23<13:30:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16849/100000 [4:57:24<13:31:16,  1.71it/s]
Train steps ... :  17%|█▋        | 16850/100000 [4:57:24<13:33:13,  1.70it/s]Step... (16850 / 100000 | Loss: 1.354527235031128, Learning Rate: 8.35678391959799e-05)
+
                                                                             
Step... (16850 / 100000 | Loss: 1.0016508102416992, Learning Rate: 8.35678391959799e-05)
+
Train steps ... :  17%|█▋        | 16850/100000 [4:57:25<13:33:13,  1.70it/s]
Train steps ... :  17%|█▋        | 16851/100000 [4:57:25<13:32:17,  1.71it/s]
Train steps ... :  17%|█▋        | 16852/100000 [4:57:26<13:31:55,  1.71it/s]
Train steps ... :  17%|█▋        | 16853/100000 [4:57:26<13:30:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16854/100000 [4:57:27<13:30:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16855/100000 [4:57:27<13:29:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16856/100000 [4:57:28<13:29:26,  1.71it/s]
Train steps ... :  17%|█▋        | 16857/100000 [4:57:28<13:29:22,  1.71it/s]
Train steps ... :  17%|█▋        | 16858/100000 [4:57:29<13:29:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16859/100000 [4:57:30<13:30:11,  1.71it/s]
Train steps ... :  17%|█▋        | 16860/100000 [4:57:30<13:29:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16861/100000 [4:57:31<13:32:46,  1.70it/s]
Train steps ... :  17%|█▋        | 16862/100000 [4:57:31<13:30:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16863/100000 [4:57:32<13:29:00,  1.71it/s]
Train steps ... :  17%|█▋        | 16864/100000 [4:57:33<13:28:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16865/100000 [4:57:33<13:28:34,  1.71it/s]
Train steps ... :  17%|█▋        | 16866/100000 [4:57:34<13:29:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16867/100000 [4:57:34<13:30:44,  1.71it/s]
Train steps ... :  17%|█▋        | 16868/100000 [4:57:35<13:30:22,  1.71it/s]
Train steps ... :  17%|█▋        | 16869/100000 [4:57:35<13:31:55,  1.71it/s]
Train steps ... :  17%|█▋        | 16870/100000 [4:57:36<13:32:38,  1.70it/s]
Train steps ... :  17%|█▋        | 16871/100000 [4:57:37<13:29:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16872/100000 [4:57:37<13:29:41,  1.71it/s]
Train steps ... :  17%|█▋        | 16873/100000 [4:57:38<13:29:44,  1.71it/s]
Train steps ... :  17%|█▋        | 16874/100000 [4:57:38<13:28:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16875/100000 [4:57:39<13:30:25,  1.71it/s]Step... (16875 / 100000 | Loss: 1.1685185432434082, Learning Rate: 8.354271356783921e-05)
+
                                                                             
Step... (16875 / 100000 | Loss: 1.0982844829559326, Learning Rate: 8.354271356783921e-05)
+
Train steps ... :  17%|█▋        | 16875/100000 [4:57:39<13:30:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16876/100000 [4:57:40<13:29:32,  1.71it/s]
Train steps ... :  17%|█▋        | 16877/100000 [4:57:40<13:29:06,  1.71it/s]
Train steps ... :  17%|█▋        | 16878/100000 [4:57:41<13:29:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16879/100000 [4:57:41<13:29:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16880/100000 [4:57:42<13:29:24,  1.71it/s]
Train steps ... :  17%|█▋        | 16881/100000 [4:57:42<13:29:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16882/100000 [4:57:43<13:29:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16883/100000 [4:57:44<13:30:39,  1.71it/s]
Train steps ... :  17%|█▋        | 16884/100000 [4:57:44<13:30:17,  1.71it/s]
Train steps ... :  17%|█▋        | 16885/100000 [4:57:45<13:29:23,  1.71it/s]
Train steps ... :  17%|█▋        | 16886/100000 [4:57:45<13:30:06,  1.71it/s]
Train steps ... :  17%|█▋        | 16887/100000 [4:57:46<13:29:17,  1.71it/s]
Train steps ... :  17%|█▋        | 16888/100000 [4:57:47<13:28:56,  1.71it/s]
Train steps ... :  17%|█▋        | 16889/100000 [4:57:47<13:30:21,  1.71it/s]
Train steps ... :  17%|█▋        | 16890/100000 [4:57:48<13:29:22,  1.71it/s]
Train steps ... :  17%|█▋        | 16891/100000 [4:57:48<13:29:44,  1.71it/s]
Train steps ... :  17%|█▋        | 16892/100000 [4:57:49<13:29:34,  1.71it/s]
Train steps ... :  17%|█▋        | 16893/100000 [4:57:49<13:30:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16894/100000 [4:57:50<13:30:40,  1.71it/s]
Train steps ... :  17%|█▋        | 16895/100000 [4:57:51<13:30:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16896/100000 [4:57:51<13:29:44,  1.71it/s]
Train steps ... :  17%|█▋        | 16897/100000 [4:57:52<13:30:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16898/100000 [4:57:52<13:30:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16899/100000 [4:57:53<13:30:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16900/100000 [4:57:54<13:31:04,  1.71it/s]Step... (16900 / 100000 | Loss: 0.9721572399139404, Learning Rate: 8.351758793969849e-05)
+
                                                                             
Step... (16900 / 100000 | Loss: 1.1152946949005127, Learning Rate: 8.351758793969849e-05)
+
Train steps ... :  17%|█▋        | 16900/100000 [4:57:54<13:31:04,  1.71it/s]
Train steps ... :  17%|█▋        | 16901/100000 [4:57:54<13:30:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16902/100000 [4:57:55<13:30:50,  1.71it/s]
Train steps ... :  17%|█▋        | 16903/100000 [4:57:55<13:30:13,  1.71it/s]
Train steps ... :  17%|█▋        | 16904/100000 [4:57:56<13:30:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16905/100000 [4:57:56<13:30:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16906/100000 [4:57:57<13:29:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16907/100000 [4:57:58<13:30:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16908/100000 [4:57:58<13:30:02,  1.71it/s]
Train steps ... :  17%|█▋        | 16909/100000 [4:57:59<13:30:35,  1.71it/s]
Train steps ... :  17%|█▋        | 16910/100000 [4:57:59<13:30:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16911/100000 [4:58:00<13:31:00,  1.71it/s]
Train steps ... :  17%|█▋        | 16912/100000 [4:58:01<13:31:21,  1.71it/s]
Train steps ... :  17%|█▋        | 16913/100000 [4:58:01<13:30:49,  1.71it/s]
Train steps ... :  17%|█▋        | 16914/100000 [4:58:02<13:30:46,  1.71it/s]
Train steps ... :  17%|█▋        | 16915/100000 [4:58:02<13:30:28,  1.71it/s]
Train steps ... :  17%|█▋        | 16916/100000 [4:58:03<13:30:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16917/100000 [4:58:04<13:29:50,  1.71it/s]
Train steps ... :  17%|█▋        | 16918/100000 [4:58:04<13:29:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16919/100000 [4:58:05<13:30:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16920/100000 [4:58:05<13:33:08,  1.70it/s]
Train steps ... :  17%|█▋        | 16921/100000 [4:58:06<13:32:14,  1.70it/s]
Train steps ... :  17%|█▋        | 16922/100000 [4:58:06<13:31:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16923/100000 [4:58:07<13:30:10,  1.71it/s]
Train steps ... :  17%|█▋        | 16924/100000 [4:58:08<13:29:54,  1.71it/s]
Train steps ... :  17%|█▋        | 16925/100000 [4:58:08<13:29:26,  1.71it/s]Step... (16925 / 100000 | Loss: 1.5382013320922852, Learning Rate: 8.349246231155779e-05)
+
                                                                             
Step... (16925 / 100000 | Loss: 1.2882375717163086, Learning Rate: 8.349246231155779e-05)
+
Train steps ... :  17%|█▋        | 16925/100000 [4:58:09<13:29:26,  1.71it/s]
Train steps ... :  17%|█▋        | 16926/100000 [4:58:09<13:29:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16927/100000 [4:58:09<13:29:13,  1.71it/s]
Train steps ... :  17%|█▋        | 16928/100000 [4:58:10<13:29:12,  1.71it/s]
Train steps ... :  17%|█▋        | 16929/100000 [4:58:11<13:28:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16930/100000 [4:58:11<13:29:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16931/100000 [4:58:12<13:28:38,  1.71it/s]
Train steps ... :  17%|█▋        | 16932/100000 [4:58:12<13:28:16,  1.71it/s]
Train steps ... :  17%|█▋        | 16933/100000 [4:58:13<13:28:49,  1.71it/s]
Train steps ... :  17%|█▋        | 16934/100000 [4:58:13<13:28:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16935/100000 [4:58:14<13:28:33,  1.71it/s]
Train steps ... :  17%|█▋        | 16936/100000 [4:58:15<13:29:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16937/100000 [4:58:15<13:29:33,  1.71it/s]
Train steps ... :  17%|█▋        | 16938/100000 [4:58:16<13:29:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16939/100000 [4:58:16<13:29:21,  1.71it/s]
Train steps ... :  17%|█▋        | 16940/100000 [4:58:17<13:29:23,  1.71it/s]
Train steps ... :  17%|█▋        | 16941/100000 [4:58:18<13:30:15,  1.71it/s]
Train steps ... :  17%|█▋        | 16942/100000 [4:58:18<13:30:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16943/100000 [4:58:19<13:29:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16944/100000 [4:58:19<13:29:37,  1.71it/s]
Train steps ... :  17%|█▋        | 16945/100000 [4:58:20<13:29:03,  1.71it/s]
Train steps ... :  17%|█▋        | 16946/100000 [4:58:20<13:28:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16947/100000 [4:58:21<13:28:55,  1.71it/s]
Train steps ... :  17%|█▋        | 16948/100000 [4:58:22<13:28:55,  1.71it/s]
Train steps ... :  17%|█▋        | 16949/100000 [4:58:22<13:29:19,  1.71it/s]
Train steps ... :  17%|█▋        | 16950/100000 [4:58:23<13:29:08,  1.71it/s]Step... (16950 / 100000 | Loss: 1.2492033243179321, Learning Rate: 8.346733668341709e-05)
+
                                                                             
Step... (16950 / 100000 | Loss: 0.8794344663619995, Learning Rate: 8.346733668341709e-05)
+
Train steps ... :  17%|█▋        | 16950/100000 [4:58:23<13:29:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16951/100000 [4:58:23<13:29:56,  1.71it/s]
Train steps ... :  17%|█▋        | 16952/100000 [4:58:24<13:29:25,  1.71it/s]
Train steps ... :  17%|█▋        | 16953/100000 [4:58:25<13:29:39,  1.71it/s]
Train steps ... :  17%|█▋        | 16954/100000 [4:58:25<13:30:47,  1.71it/s]
Train steps ... :  17%|█▋        | 16955/100000 [4:58:26<13:31:53,  1.70it/s]
Train steps ... :  17%|█▋        | 16956/100000 [4:58:26<13:29:38,  1.71it/s]
Train steps ... :  17%|█▋        | 16957/100000 [4:58:27<13:31:26,  1.71it/s]
Train steps ... :  17%|█▋        | 16958/100000 [4:58:27<13:30:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16959/100000 [4:58:28<13:30:14,  1.71it/s]
Train steps ... :  17%|█▋        | 16960/100000 [4:58:29<13:29:31,  1.71it/s]
Train steps ... :  17%|█▋        | 16961/100000 [4:58:29<13:29:34,  1.71it/s]
Train steps ... :  17%|█▋        | 16962/100000 [4:58:30<13:28:36,  1.71it/s]
Train steps ... :  17%|█▋        | 16963/100000 [4:58:30<13:28:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16964/100000 [4:58:31<13:29:37,  1.71it/s]
Train steps ... :  17%|█▋        | 16965/100000 [4:58:32<13:28:22,  1.71it/s]
Train steps ... :  17%|█▋        | 16966/100000 [4:58:32<13:28:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16967/100000 [4:58:33<13:28:18,  1.71it/s]
Train steps ... :  17%|█▋        | 16968/100000 [4:58:33<13:27:56,  1.71it/s]
Train steps ... :  17%|█▋        | 16969/100000 [4:58:34<13:27:58,  1.71it/s]
Train steps ... :  17%|█▋        | 16970/100000 [4:58:35<13:28:15,  1.71it/s]
Train steps ... :  17%|█▋        | 16971/100000 [4:58:35<13:28:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16972/100000 [4:58:36<13:28:53,  1.71it/s]
Train steps ... :  17%|█▋        | 16973/100000 [4:58:36<13:28:42,  1.71it/s]
Train steps ... :  17%|█▋        | 16974/100000 [4:58:37<13:27:59,  1.71it/s]
Train steps ... :  17%|█▋        | 16975/100000 [4:58:37<13:29:27,  1.71it/s]Step... (16975 / 100000 | Loss: 1.3659436702728271, Learning Rate: 8.344221105527638e-05)
+
                                                                             
Step... (16975 / 100000 | Loss: 1.0415014028549194, Learning Rate: 8.344221105527638e-05)
+
Train steps ... :  17%|█▋        | 16975/100000 [4:58:38<13:29:27,  1.71it/s]
Train steps ... :  17%|█▋        | 16976/100000 [4:58:38<13:28:43,  1.71it/s]
Train steps ... :  17%|█▋        | 16977/100000 [4:58:39<13:27:51,  1.71it/s]
Train steps ... :  17%|█▋        | 16978/100000 [4:58:39<13:28:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16979/100000 [4:58:40<13:28:20,  1.71it/s]
Train steps ... :  17%|█▋        | 16980/100000 [4:58:40<13:28:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16981/100000 [4:58:41<13:29:01,  1.71it/s]
Train steps ... :  17%|█▋        | 16982/100000 [4:58:42<13:29:09,  1.71it/s]
Train steps ... :  17%|█▋        | 16983/100000 [4:58:42<13:29:41,  1.71it/s]
Train steps ... :  17%|█▋        | 16984/100000 [4:58:43<13:29:50,  1.71it/s]
Train steps ... :  17%|█▋        | 16985/100000 [4:58:43<13:30:16,  1.71it/s]
Train steps ... :  17%|█▋        | 16986/100000 [4:58:44<13:30:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16987/100000 [4:58:44<13:30:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16988/100000 [4:58:45<13:29:29,  1.71it/s]
Train steps ... :  17%|█▋        | 16989/100000 [4:58:46<13:29:07,  1.71it/s]
Train steps ... :  17%|█▋        | 16990/100000 [4:58:46<13:30:08,  1.71it/s]
Train steps ... :  17%|█▋        | 16991/100000 [4:58:47<13:28:53,  1.71it/s]
Train steps ... :  17%|█▋        | 16992/100000 [4:58:47<13:29:35,  1.71it/s]
Train steps ... :  17%|█▋        | 16993/100000 [4:58:48<13:29:22,  1.71it/s]
Train steps ... :  17%|█▋        | 16994/100000 [4:58:49<13:29:33,  1.71it/s]
Train steps ... :  17%|█▋        | 16995/100000 [4:58:49<13:30:17,  1.71it/s]
Train steps ... :  17%|█▋        | 16996/100000 [4:58:50<13:29:21,  1.71it/s]
Train steps ... :  17%|█▋        | 16997/100000 [4:58:50<13:28:21,  1.71it/s]
Train steps ... :  17%|█▋        | 16998/100000 [4:58:51<13:29:01,  1.71it/s]
Train steps ... :  17%|█▋        | 16999/100000 [4:58:51<13:28:28,  1.71it/s]
Train steps ... :  17%|█▋        | 17000/100000 [4:58:52<13:28:00,  1.71it/s]Step... (17000 / 100000 | Loss: 1.012488603591919, Learning Rate: 8.341708542713568e-05)
+
                                                                             
Step... (17000 / 100000 | Loss: 1.178044319152832, Learning Rate: 8.341708542713568e-05)
+
Train steps ... :  17%|█▋        | 17000/100000 [4:58:52<13:28:00,  1.71it/s]
Train steps ... :  17%|█▋        | 17001/100000 [4:58:53<13:29:00,  1.71it/s]
Train steps ... :  17%|█▋        | 17002/100000 [4:58:53<13:28:30,  1.71it/s]
Train steps ... :  17%|█▋        | 17003/100000 [4:58:54<13:28:33,  1.71it/s]
Train steps ... :  17%|█▋        | 17004/100000 [4:58:54<13:28:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17005/100000 [4:58:55<13:28:14,  1.71it/s]
Train steps ... :  17%|█▋        | 17006/100000 [4:58:56<13:29:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17007/100000 [4:58:56<13:28:08,  1.71it/s]
Train steps ... :  17%|█▋        | 17008/100000 [4:58:57<13:27:34,  1.71it/s]
Train steps ... :  17%|█▋        | 17009/100000 [4:58:57<13:27:37,  1.71it/s]
Train steps ... :  17%|█▋        | 17010/100000 [4:58:58<13:27:44,  1.71it/s]
Train steps ... :  17%|█▋        | 17011/100000 [4:58:58<13:27:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17012/100000 [4:58:59<13:27:35,  1.71it/s]
Train steps ... :  17%|█▋        | 17013/100000 [4:59:00<13:29:03,  1.71it/s]
Train steps ... :  17%|█▋        | 17014/100000 [4:59:00<13:29:34,  1.71it/s]
Train steps ... :  17%|█▋        | 17015/100000 [4:59:01<13:29:18,  1.71it/s]
Train steps ... :  17%|█▋        | 17016/100000 [4:59:01<13:29:05,  1.71it/s]
Train steps ... :  17%|█▋        | 17017/100000 [4:59:02<13:29:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17018/100000 [4:59:03<13:28:56,  1.71it/s]
Train steps ... :  17%|█▋        | 17019/100000 [4:59:03<13:29:02,  1.71it/s]
Train steps ... :  17%|█▋        | 17020/100000 [4:59:04<13:29:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17021/100000 [4:59:04<13:28:29,  1.71it/s]
Train steps ... :  17%|█▋        | 17022/100000 [4:59:05<13:28:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17023/100000 [4:59:05<13:28:41,  1.71it/s]
Train steps ... :  17%|█▋        | 17024/100000 [4:59:06<13:29:22,  1.71it/s]
Train steps ... :  17%|█▋        | 17025/100000 [4:59:07<13:28:39,  1.71it/s]Step... (17025 / 100000 | Loss: 1.2140940427780151, Learning Rate: 8.339195979899498e-05)
+
                                                                             
Step... (17025 / 100000 | Loss: 1.0205880403518677, Learning Rate: 8.339195979899498e-05)
+
Train steps ... :  17%|█▋        | 17025/100000 [4:59:07<13:28:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17026/100000 [4:59:07<13:29:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17027/100000 [4:59:08<13:29:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17028/100000 [4:59:08<13:29:36,  1.71it/s]
Train steps ... :  17%|█▋        | 17029/100000 [4:59:09<13:28:24,  1.71it/s]
Train steps ... :  17%|█▋        | 17030/100000 [4:59:10<13:27:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17031/100000 [4:59:10<13:27:06,  1.71it/s]
Train steps ... :  17%|█▋        | 17032/100000 [4:59:11<13:27:15,  1.71it/s]
Train steps ... :  17%|█▋        | 17033/100000 [4:59:11<13:27:41,  1.71it/s]
Train steps ... :  17%|█▋        | 17034/100000 [4:59:12<13:28:04,  1.71it/s]
Train steps ... :  17%|█▋        | 17035/100000 [4:59:13<13:27:52,  1.71it/s]
Train steps ... :  17%|█▋        | 17036/100000 [4:59:13<13:26:55,  1.71it/s]
Train steps ... :  17%|█▋        | 17037/100000 [4:59:14<13:27:09,  1.71it/s]
Train steps ... :  17%|█▋        | 17038/100000 [4:59:14<13:28:20,  1.71it/s]
Train steps ... :  17%|█▋        | 17039/100000 [4:59:15<13:29:26,  1.71it/s]
Train steps ... :  17%|█▋        | 17040/100000 [4:59:15<13:28:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17041/100000 [4:59:16<13:28:31,  1.71it/s]
Train steps ... :  17%|█▋        | 17042/100000 [4:59:17<13:27:41,  1.71it/s]
Train steps ... :  17%|█▋        | 17043/100000 [4:59:17<13:27:26,  1.71it/s]
Train steps ... :  17%|█▋        | 17044/100000 [4:59:18<13:27:12,  1.71it/s]
Train steps ... :  17%|█▋        | 17045/100000 [4:59:18<13:27:40,  1.71it/s]
Train steps ... :  17%|█▋        | 17046/100000 [4:59:19<13:27:29,  1.71it/s]
Train steps ... :  17%|█▋        | 17047/100000 [4:59:20<13:28:47,  1.71it/s]
Train steps ... :  17%|█▋        | 17048/100000 [4:59:20<13:27:12,  1.71it/s]
Train steps ... :  17%|█▋        | 17049/100000 [4:59:21<13:27:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17050/100000 [4:59:21<13:27:28,  1.71it/s]Step... (17050 / 100000 | Loss: 1.3049936294555664, Learning Rate: 8.336683417085429e-05)
+
                                                                             
Step... (17050 / 100000 | Loss: 0.8690794706344604, Learning Rate: 8.336683417085429e-05)
+
Train steps ... :  17%|█▋        | 17050/100000 [4:59:22<13:27:28,  1.71it/s]
Train steps ... :  17%|█▋        | 17051/100000 [4:59:22<13:27:37,  1.71it/s]
Train steps ... :  17%|█▋        | 17052/100000 [4:59:22<13:26:55,  1.71it/s]
Train steps ... :  17%|█▋        | 17053/100000 [4:59:23<13:27:46,  1.71it/s]
Train steps ... :  17%|█▋        | 17054/100000 [4:59:24<13:29:18,  1.71it/s]
Train steps ... :  17%|█▋        | 17055/100000 [4:59:24<13:28:28,  1.71it/s]
Train steps ... :  17%|█▋        | 17056/100000 [4:59:25<13:27:56,  1.71it/s]
Train steps ... :  17%|█▋        | 17057/100000 [4:59:25<13:28:10,  1.71it/s]
Train steps ... :  17%|█▋        | 17058/100000 [4:59:26<13:28:22,  1.71it/s]
Train steps ... :  17%|█▋        | 17059/100000 [4:59:27<13:28:30,  1.71it/s]
Train steps ... :  17%|█▋        | 17060/100000 [4:59:27<13:29:34,  1.71it/s]
Train steps ... :  17%|█▋        | 17061/100000 [4:59:28<13:28:21,  1.71it/s]
Train steps ... :  17%|█▋        | 17062/100000 [4:59:28<13:28:31,  1.71it/s]
Train steps ... :  17%|█▋        | 17063/100000 [4:59:29<13:28:19,  1.71it/s]
Train steps ... :  17%|█▋        | 17064/100000 [4:59:29<13:28:16,  1.71it/s]
Train steps ... :  17%|█▋        | 17065/100000 [4:59:30<13:28:14,  1.71it/s]
Train steps ... :  17%|█▋        | 17066/100000 [4:59:31<13:27:57,  1.71it/s]
Train steps ... :  17%|█▋        | 17067/100000 [4:59:31<13:27:33,  1.71it/s]
Train steps ... :  17%|█▋        | 17068/100000 [4:59:32<13:27:21,  1.71it/s]
Train steps ... :  17%|█▋        | 17069/100000 [4:59:32<13:27:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17070/100000 [4:59:33<13:27:21,  1.71it/s]
Train steps ... :  17%|█▋        | 17071/100000 [4:59:34<13:27:06,  1.71it/s]
Train steps ... :  17%|█▋        | 17072/100000 [4:59:34<13:26:55,  1.71it/s]
Train steps ... :  17%|█▋        | 17073/100000 [4:59:35<13:26:53,  1.71it/s]
Train steps ... :  17%|█▋        | 17074/100000 [4:59:35<13:26:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17075/100000 [4:59:36<13:26:57,  1.71it/s]Step... (17075 / 100000 | Loss: 1.1178765296936035, Learning Rate: 8.334170854271357e-05)
+
                                                                             
Step... (17075 / 100000 | Loss: 0.9401446580886841, Learning Rate: 8.334170854271357e-05)
+
Train steps ... :  17%|█▋        | 17075/100000 [4:59:36<13:26:57,  1.71it/s]
Train steps ... :  17%|█▋        | 17076/100000 [4:59:36<13:28:53,  1.71it/s]
Train steps ... :  17%|█▋        | 17077/100000 [4:59:37<13:28:24,  1.71it/s]
Train steps ... :  17%|█▋        | 17078/100000 [4:59:38<13:28:24,  1.71it/s]
Train steps ... :  17%|█▋        | 17079/100000 [4:59:38<13:29:22,  1.71it/s]
Train steps ... :  17%|█▋        | 17080/100000 [4:59:39<13:28:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17081/100000 [4:59:39<13:27:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17082/100000 [4:59:40<13:26:26,  1.71it/s]
Train steps ... :  17%|█▋        | 17083/100000 [4:59:41<13:26:13,  1.71it/s]
Train steps ... :  17%|█▋        | 17084/100000 [4:59:41<13:26:57,  1.71it/s]
Train steps ... :  17%|█▋        | 17085/100000 [4:59:42<13:27:51,  1.71it/s]
Train steps ... :  17%|█▋        | 17086/100000 [4:59:42<13:27:14,  1.71it/s]
Train steps ... :  17%|█▋        | 17087/100000 [4:59:43<13:28:08,  1.71it/s]
Train steps ... :  17%|█▋        | 17088/100000 [4:59:43<13:28:45,  1.71it/s]
Train steps ... :  17%|█▋        | 17089/100000 [4:59:44<13:28:16,  1.71it/s]
Train steps ... :  17%|█▋        | 17090/100000 [4:59:46<19:20:26,  1.19it/s]
Train steps ... :  17%|█▋        | 17091/100000 [4:59:49<39:18:21,  1.71s/it]
Train steps ... :  17%|█▋        | 17092/100000 [4:59:50<31:31:51,  1.37s/it]
Train steps ... :  17%|█▋        | 17093/100000 [4:59:50<26:06:08,  1.13s/it]
Train steps ... :  17%|█▋        | 17094/100000 [4:59:51<22:20:27,  1.03it/s]
Train steps ... :  17%|█▋        | 17095/100000 [4:59:52<19:41:05,  1.17it/s]
Train steps ... :  17%|█▋        | 17096/100000 [4:59:52<17:48:49,  1.29it/s]
Train steps ... :  17%|█▋        | 17097/100000 [4:59:53<16:31:38,  1.39it/s]
Train steps ... :  17%|█▋        | 17098/100000 [4:59:53<15:36:48,  1.47it/s]
Train steps ... :  17%|█▋        | 17099/100000 [4:59:54<14:58:44,  1.54it/s]
Train steps ... :  17%|█▋        | 17100/100000 [4:59:55<14:31:26,  1.59it/s]Step... (17100 / 100000 | Loss: 0.6939107775688171, Learning Rate: 8.331658291457287e-05)
+
                                                                             
Step... (17100 / 100000 | Loss: 1.1672953367233276, Learning Rate: 8.331658291457287e-05)
+
Train steps ... :  17%|█▋        | 17100/100000 [4:59:55<14:31:26,  1.59it/s]
Train steps ... :  17%|█▋        | 17101/100000 [4:59:55<14:12:18,  1.62it/s]
Train steps ... :  17%|█▋        | 17102/100000 [4:59:56<13:59:15,  1.65it/s]
Train steps ... :  17%|█▋        | 17103/100000 [4:59:56<13:49:25,  1.67it/s]
Train steps ... :  17%|█▋        | 17104/100000 [4:59:57<13:42:41,  1.68it/s]
Train steps ... :  17%|█▋        | 17105/100000 [4:59:57<13:39:52,  1.69it/s]
Train steps ... :  17%|█▋        | 17106/100000 [4:59:58<13:35:30,  1.69it/s]
Train steps ... :  17%|█▋        | 17107/100000 [4:59:59<13:35:37,  1.69it/s]
Train steps ... :  17%|█▋        | 17108/100000 [4:59:59<13:33:18,  1.70it/s]
Train steps ... :  17%|█▋        | 17109/100000 [5:00:00<13:33:34,  1.70it/s]
Train steps ... :  17%|█▋        | 17110/100000 [5:00:00<13:30:50,  1.70it/s]
Train steps ... :  17%|█▋        | 17111/100000 [5:00:01<13:29:14,  1.71it/s]
Train steps ... :  17%|█▋        | 17112/100000 [5:00:02<13:30:04,  1.71it/s]
Train steps ... :  17%|█▋        | 17113/100000 [5:00:02<13:29:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17114/100000 [5:00:03<13:29:04,  1.71it/s]
Train steps ... :  17%|█▋        | 17115/100000 [5:00:03<13:28:43,  1.71it/s]
Train steps ... :  17%|█▋        | 17116/100000 [5:00:04<13:28:55,  1.71it/s]
Train steps ... :  17%|█▋        | 17117/100000 [5:00:04<13:28:47,  1.71it/s]
Train steps ... :  17%|█▋        | 17118/100000 [5:00:05<13:28:22,  1.71it/s]
Train steps ... :  17%|█▋        | 17119/100000 [5:00:06<13:27:43,  1.71it/s]
Train steps ... :  17%|█▋        | 17120/100000 [5:00:06<13:27:30,  1.71it/s]
Train steps ... :  17%|█▋        | 17121/100000 [5:00:07<13:27:53,  1.71it/s]
Train steps ... :  17%|█▋        | 17122/100000 [5:00:07<13:27:48,  1.71it/s]
Train steps ... :  17%|█▋        | 17123/100000 [5:00:08<13:27:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17124/100000 [5:00:09<13:28:05,  1.71it/s]
Train steps ... :  17%|█▋        | 17125/100000 [5:00:09<13:27:32,  1.71it/s]Step... (17125 / 100000 | Loss: 0.7180052995681763, Learning Rate: 8.329145728643216e-05)
+
                                                                             
Step... (17125 / 100000 | Loss: 0.8506487607955933, Learning Rate: 8.329145728643216e-05)
+
Train steps ... :  17%|█▋        | 17125/100000 [5:00:09<13:27:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17126/100000 [5:00:10<13:27:17,  1.71it/s]
Train steps ... :  17%|█▋        | 17127/100000 [5:00:10<13:26:55,  1.71it/s]
Train steps ... :  17%|█▋        | 17128/100000 [5:00:11<13:26:56,  1.71it/s]
Train steps ... :  17%|█▋        | 17129/100000 [5:00:11<13:26:35,  1.71it/s]
Train steps ... :  17%|█▋        | 17130/100000 [5:00:12<13:26:59,  1.71it/s]
Train steps ... :  17%|█▋        | 17131/100000 [5:00:13<13:26:49,  1.71it/s]
Train steps ... :  17%|█▋        | 17132/100000 [5:00:13<13:26:24,  1.71it/s]
Train steps ... :  17%|█▋        | 17133/100000 [5:00:14<13:25:51,  1.71it/s]
Train steps ... :  17%|█▋        | 17134/100000 [5:00:14<13:25:57,  1.71it/s]
Train steps ... :  17%|█▋        | 17135/100000 [5:00:15<13:26:46,  1.71it/s]
Train steps ... :  17%|█▋        | 17136/100000 [5:00:16<13:27:15,  1.71it/s]
Train steps ... :  17%|█▋        | 17137/100000 [5:00:16<13:27:13,  1.71it/s]
Train steps ... :  17%|█▋        | 17138/100000 [5:00:17<13:27:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17139/100000 [5:00:17<13:26:41,  1.71it/s]
Train steps ... :  17%|█▋        | 17140/100000 [5:00:18<13:27:08,  1.71it/s]
Train steps ... :  17%|█▋        | 17141/100000 [5:00:18<13:27:35,  1.71it/s]
Train steps ... :  17%|█▋        | 17142/100000 [5:00:19<13:27:36,  1.71it/s]
Train steps ... :  17%|█▋        | 17143/100000 [5:00:20<13:27:03,  1.71it/s]
Train steps ... :  17%|█▋        | 17144/100000 [5:00:20<13:26:56,  1.71it/s]
Train steps ... :  17%|█▋        | 17145/100000 [5:00:21<13:26:40,  1.71it/s]
Train steps ... :  17%|█▋        | 17146/100000 [5:00:21<13:27:35,  1.71it/s]
Train steps ... :  17%|█▋        | 17147/100000 [5:00:22<13:27:37,  1.71it/s]
Train steps ... :  17%|█▋        | 17148/100000 [5:00:23<13:27:26,  1.71it/s]
Train steps ... :  17%|█▋        | 17149/100000 [5:00:23<13:28:07,  1.71it/s]
Train steps ... :  17%|█▋        | 17150/100000 [5:00:24<13:27:42,  1.71it/s]Step... (17150 / 100000 | Loss: 1.179638147354126, Learning Rate: 8.326633165829146e-05)
+
                                                                             
Step... (17150 / 100000 | Loss: 1.5993138551712036, Learning Rate: 8.326633165829146e-05)
+
Train steps ... :  17%|█▋        | 17150/100000 [5:00:24<13:27:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17151/100000 [5:00:24<13:27:04,  1.71it/s]
Train steps ... :  17%|█▋        | 17152/100000 [5:00:25<13:26:43,  1.71it/s]
Train steps ... :  17%|█▋        | 17153/100000 [5:00:25<13:26:56,  1.71it/s]
Train steps ... :  17%|█▋        | 17154/100000 [5:00:26<13:26:38,  1.71it/s]
Train steps ... :  17%|█▋        | 17155/100000 [5:00:27<13:26:28,  1.71it/s]
Train steps ... :  17%|█▋        | 17156/100000 [5:00:27<13:26:30,  1.71it/s]
Train steps ... :  17%|█▋        | 17157/100000 [5:00:28<13:27:35,  1.71it/s]
Train steps ... :  17%|█▋        | 17158/100000 [5:00:28<13:26:55,  1.71it/s]
Train steps ... :  17%|█▋        | 17159/100000 [5:00:29<13:26:21,  1.71it/s]
Train steps ... :  17%|█▋        | 17160/100000 [5:00:30<13:26:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17161/100000 [5:00:30<13:26:34,  1.71it/s]
Train steps ... :  17%|█▋        | 17162/100000 [5:00:31<13:26:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17163/100000 [5:00:31<13:26:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17164/100000 [5:00:32<13:26:04,  1.71it/s]
Train steps ... :  17%|█▋        | 17165/100000 [5:00:33<13:25:58,  1.71it/s]
Train steps ... :  17%|█▋        | 17166/100000 [5:00:33<13:25:57,  1.71it/s]
Train steps ... :  17%|█▋        | 17167/100000 [5:00:34<13:25:55,  1.71it/s]
Train steps ... :  17%|█▋        | 17168/100000 [5:00:34<13:25:52,  1.71it/s]
Train steps ... :  17%|█▋        | 17169/100000 [5:00:35<13:27:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17170/100000 [5:00:35<13:26:30,  1.71it/s]
Train steps ... :  17%|█▋        | 17171/100000 [5:00:36<13:26:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17172/100000 [5:00:37<13:26:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17173/100000 [5:00:37<13:26:06,  1.71it/s]
Train steps ... :  17%|█▋        | 17174/100000 [5:00:38<13:26:50,  1.71it/s]
Train steps ... :  17%|█▋        | 17175/100000 [5:00:38<13:25:52,  1.71it/s]Step... (17175 / 100000 | Loss: 0.7841627597808838, Learning Rate: 8.324120603015076e-05)
+
                                                                             
Step... (17175 / 100000 | Loss: 1.1134527921676636, Learning Rate: 8.324120603015076e-05)
+
Train steps ... :  17%|█▋        | 17175/100000 [5:00:39<13:25:52,  1.71it/s]
Train steps ... :  17%|█▋        | 17176/100000 [5:00:39<13:26:02,  1.71it/s]
Train steps ... :  17%|█▋        | 17177/100000 [5:00:40<13:26:25,  1.71it/s]
Train steps ... :  17%|█▋        | 17178/100000 [5:00:40<13:26:06,  1.71it/s]
Train steps ... :  17%|█▋        | 17179/100000 [5:00:41<13:26:16,  1.71it/s]
Train steps ... :  17%|█▋        | 17180/100000 [5:00:41<13:26:00,  1.71it/s]
Train steps ... :  17%|█▋        | 17181/100000 [5:00:42<13:25:40,  1.71it/s]
Train steps ... :  17%|█▋        | 17182/100000 [5:00:42<13:26:03,  1.71it/s]
Train steps ... :  17%|█▋        | 17183/100000 [5:00:43<13:25:40,  1.71it/s]
Train steps ... :  17%|█▋        | 17184/100000 [5:00:44<13:26:03,  1.71it/s]
Train steps ... :  17%|█▋        | 17185/100000 [5:00:44<13:27:06,  1.71it/s]
Train steps ... :  17%|█▋        | 17186/100000 [5:00:45<13:26:21,  1.71it/s]
Train steps ... :  17%|█▋        | 17187/100000 [5:00:45<13:26:59,  1.71it/s]
Train steps ... :  17%|█▋        | 17188/100000 [5:00:46<13:27:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17189/100000 [5:00:47<13:26:33,  1.71it/s]
Train steps ... :  17%|█▋        | 17190/100000 [5:00:47<13:26:07,  1.71it/s]
Train steps ... :  17%|█▋        | 17191/100000 [5:00:48<13:25:51,  1.71it/s]
Train steps ... :  17%|█▋        | 17192/100000 [5:00:48<13:24:55,  1.71it/s]
Train steps ... :  17%|█▋        | 17193/100000 [5:00:49<13:26:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17194/100000 [5:00:49<13:26:24,  1.71it/s]
Train steps ... :  17%|█▋        | 17195/100000 [5:00:50<13:26:25,  1.71it/s]
Train steps ... :  17%|█▋        | 17196/100000 [5:00:51<13:26:58,  1.71it/s]
Train steps ... :  17%|█▋        | 17197/100000 [5:00:51<13:26:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17198/100000 [5:00:52<13:27:44,  1.71it/s]
Train steps ... :  17%|█▋        | 17199/100000 [5:00:52<13:26:34,  1.71it/s]
Train steps ... :  17%|█▋        | 17200/100000 [5:00:53<13:26:11,  1.71it/s]Step... (17200 / 100000 | Loss: 0.9112825989723206, Learning Rate: 8.321608040201005e-05)
+
                                                                             
Step... (17200 / 100000 | Loss: 1.0413813591003418, Learning Rate: 8.321608040201005e-05)
+
Train steps ... :  17%|█▋        | 17200/100000 [5:00:53<13:26:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17201/100000 [5:00:54<13:26:03,  1.71it/s]
Train steps ... :  17%|█▋        | 17202/100000 [5:00:54<13:27:02,  1.71it/s]
Train steps ... :  17%|█▋        | 17203/100000 [5:00:55<13:26:30,  1.71it/s]
Train steps ... :  17%|█▋        | 17204/100000 [5:00:55<13:27:30,  1.71it/s]
Train steps ... :  17%|█▋        | 17205/100000 [5:00:56<13:26:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17206/100000 [5:00:56<13:26:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17207/100000 [5:00:57<13:27:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17208/100000 [5:00:58<13:27:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17209/100000 [5:00:58<13:26:19,  1.71it/s]
Train steps ... :  17%|█▋        | 17210/100000 [5:00:59<13:26:10,  1.71it/s]
Train steps ... :  17%|█▋        | 17211/100000 [5:00:59<13:26:24,  1.71it/s]
Train steps ... :  17%|█▋        | 17212/100000 [5:01:00<13:26:06,  1.71it/s]
Train steps ... :  17%|█▋        | 17213/100000 [5:01:01<13:26:58,  1.71it/s]
Train steps ... :  17%|█▋        | 17214/100000 [5:01:01<13:26:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17215/100000 [5:01:02<13:26:20,  1.71it/s]
Train steps ... :  17%|█▋        | 17216/100000 [5:01:02<13:26:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17217/100000 [5:01:03<13:26:17,  1.71it/s]
Train steps ... :  17%|█▋        | 17218/100000 [5:01:03<13:26:13,  1.71it/s]
Train steps ... :  17%|█▋        | 17219/100000 [5:01:04<13:26:44,  1.71it/s]
Train steps ... :  17%|█▋        | 17220/100000 [5:01:05<13:26:38,  1.71it/s]
Train steps ... :  17%|█▋        | 17221/100000 [5:01:05<13:27:37,  1.71it/s]
Train steps ... :  17%|█▋        | 17222/100000 [5:01:06<13:27:12,  1.71it/s]
Train steps ... :  17%|█▋        | 17223/100000 [5:01:06<13:26:34,  1.71it/s]
Train steps ... :  17%|█▋        | 17224/100000 [5:01:07<13:25:46,  1.71it/s]
Train steps ... :  17%|█▋        | 17225/100000 [5:01:08<13:25:40,  1.71it/s]Step... (17225 / 100000 | Loss: 0.6309304237365723, Learning Rate: 8.319095477386936e-05)
+
                                                                             
Step... (17225 / 100000 | Loss: 1.2991697788238525, Learning Rate: 8.319095477386936e-05)
+
Train steps ... :  17%|█▋        | 17225/100000 [5:01:08<13:25:40,  1.71it/s]
Train steps ... :  17%|█▋        | 17226/100000 [5:01:08<13:26:18,  1.71it/s]
Train steps ... :  17%|█▋        | 17227/100000 [5:01:09<13:26:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17228/100000 [5:01:09<13:25:47,  1.71it/s]
Train steps ... :  17%|█▋        | 17229/100000 [5:01:10<13:26:21,  1.71it/s]
Train steps ... :  17%|█▋        | 17230/100000 [5:01:10<13:27:36,  1.71it/s]
Train steps ... :  17%|█▋        | 17231/100000 [5:01:11<13:26:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17232/100000 [5:01:12<13:25:47,  1.71it/s]
Train steps ... :  17%|█▋        | 17233/100000 [5:01:12<13:25:54,  1.71it/s]
Train steps ... :  17%|█▋        | 17234/100000 [5:01:13<13:25:17,  1.71it/s]
Train steps ... :  17%|█▋        | 17235/100000 [5:01:13<13:26:15,  1.71it/s]
Train steps ... :  17%|█▋        | 17236/100000 [5:01:14<13:25:41,  1.71it/s]
Train steps ... :  17%|█▋        | 17237/100000 [5:01:15<13:25:33,  1.71it/s]
Train steps ... :  17%|█▋        | 17238/100000 [5:01:15<13:26:29,  1.71it/s]
Train steps ... :  17%|█▋        | 17239/100000 [5:01:16<13:25:57,  1.71it/s]
Train steps ... :  17%|█▋        | 17240/100000 [5:01:16<13:26:07,  1.71it/s]
Train steps ... :  17%|█▋        | 17241/100000 [5:01:17<13:26:14,  1.71it/s]
Train steps ... :  17%|█▋        | 17242/100000 [5:01:18<13:26:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17243/100000 [5:01:18<13:26:20,  1.71it/s]
Train steps ... :  17%|█▋        | 17244/100000 [5:01:19<13:25:49,  1.71it/s]
Train steps ... :  17%|█▋        | 17245/100000 [5:01:19<13:25:46,  1.71it/s]
Train steps ... :  17%|█▋        | 17246/100000 [5:01:20<13:26:24,  1.71it/s]
Train steps ... :  17%|█▋        | 17247/100000 [5:01:20<13:26:20,  1.71it/s]
Train steps ... :  17%|█▋        | 17248/100000 [5:01:21<13:26:05,  1.71it/s]
Train steps ... :  17%|█▋        | 17249/100000 [5:01:22<13:25:48,  1.71it/s]
Train steps ... :  17%|█▋        | 17250/100000 [5:01:22<13:25:33,  1.71it/s]Step... (17250 / 100000 | Loss: 1.1256518363952637, Learning Rate: 8.316582914572865e-05)
+
                                                                             
Step... (17250 / 100000 | Loss: 1.3082032203674316, Learning Rate: 8.316582914572865e-05)
+
Train steps ... :  17%|█▋        | 17250/100000 [5:01:23<13:25:33,  1.71it/s]
Train steps ... :  17%|█▋        | 17251/100000 [5:01:23<13:26:15,  1.71it/s]
Train steps ... :  17%|█▋        | 17252/100000 [5:01:23<13:26:04,  1.71it/s]
Train steps ... :  17%|█▋        | 17253/100000 [5:01:24<13:25:41,  1.71it/s]
Train steps ... :  17%|█▋        | 17254/100000 [5:01:25<13:26:00,  1.71it/s]
Train steps ... :  17%|█▋        | 17255/100000 [5:01:25<13:25:37,  1.71it/s]
Train steps ... :  17%|█▋        | 17256/100000 [5:01:26<13:26:05,  1.71it/s]
Train steps ... :  17%|█▋        | 17257/100000 [5:01:26<13:26:02,  1.71it/s]
Train steps ... :  17%|█▋        | 17258/100000 [5:01:27<13:25:26,  1.71it/s]
Train steps ... :  17%|█▋        | 17259/100000 [5:01:27<13:25:13,  1.71it/s]
Train steps ... :  17%|█▋        | 17260/100000 [5:01:28<13:25:16,  1.71it/s]
Train steps ... :  17%|█▋        | 17261/100000 [5:01:29<13:25:12,  1.71it/s]
Train steps ... :  17%|█▋        | 17262/100000 [5:01:29<13:25:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17263/100000 [5:01:30<13:25:17,  1.71it/s]
Train steps ... :  17%|█▋        | 17264/100000 [5:01:30<13:25:26,  1.71it/s]
Train steps ... :  17%|█▋        | 17265/100000 [5:01:31<13:25:07,  1.71it/s]
Train steps ... :  17%|█▋        | 17266/100000 [5:01:32<13:25:13,  1.71it/s]
Train steps ... :  17%|█▋        | 17267/100000 [5:01:32<13:25:16,  1.71it/s]
Train steps ... :  17%|█▋        | 17268/100000 [5:01:33<13:24:56,  1.71it/s]
Train steps ... :  17%|█▋        | 17269/100000 [5:01:33<13:26:14,  1.71it/s]
Train steps ... :  17%|█▋        | 17270/100000 [5:01:34<13:25:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17271/100000 [5:01:34<13:25:31,  1.71it/s]
Train steps ... :  17%|█▋        | 17272/100000 [5:01:35<13:25:12,  1.71it/s]
Train steps ... :  17%|█▋        | 17273/100000 [5:01:36<13:25:13,  1.71it/s]
Train steps ... :  17%|█▋        | 17274/100000 [5:01:36<13:25:05,  1.71it/s]
Train steps ... :  17%|█▋        | 17275/100000 [5:01:37<13:24:44,  1.71it/s]Step... (17275 / 100000 | Loss: 1.3423879146575928, Learning Rate: 8.314070351758794e-05)
+
                                                                             
Step... (17275 / 100000 | Loss: 1.0955519676208496, Learning Rate: 8.314070351758794e-05)
+
Train steps ... :  17%|█▋        | 17275/100000 [5:01:37<13:24:44,  1.71it/s]
Train steps ... :  17%|█▋        | 17276/100000 [5:01:37<13:26:09,  1.71it/s]
Train steps ... :  17%|█▋        | 17277/100000 [5:01:38<13:26:17,  1.71it/s]
Train steps ... :  17%|█▋        | 17278/100000 [5:01:39<13:25:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17279/100000 [5:01:39<13:25:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17280/100000 [5:01:40<13:25:14,  1.71it/s]
Train steps ... :  17%|█▋        | 17281/100000 [5:01:40<13:24:45,  1.71it/s]
Train steps ... :  17%|█▋        | 17282/100000 [5:01:41<13:24:58,  1.71it/s]
Train steps ... :  17%|█▋        | 17283/100000 [5:01:41<13:25:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17284/100000 [5:01:42<13:24:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17285/100000 [5:01:43<13:24:25,  1.71it/s]
Train steps ... :  17%|█▋        | 17286/100000 [5:01:43<13:24:25,  1.71it/s]
Train steps ... :  17%|█▋        | 17287/100000 [5:01:44<13:24:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17288/100000 [5:01:44<13:24:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17289/100000 [5:01:45<13:24:54,  1.71it/s]
Train steps ... :  17%|█▋        | 17290/100000 [5:01:46<13:24:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17291/100000 [5:01:46<13:25:09,  1.71it/s]
Train steps ... :  17%|█▋        | 17292/100000 [5:01:47<13:25:03,  1.71it/s]
Train steps ... :  17%|█▋        | 17293/100000 [5:01:47<13:25:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17294/100000 [5:01:48<13:24:50,  1.71it/s]
Train steps ... :  17%|█▋        | 17295/100000 [5:01:48<13:24:50,  1.71it/s]
Train steps ... :  17%|█▋        | 17296/100000 [5:01:49<13:25:05,  1.71it/s]
Train steps ... :  17%|█▋        | 17297/100000 [5:01:50<13:24:50,  1.71it/s]
Train steps ... :  17%|█▋        | 17298/100000 [5:01:50<13:24:48,  1.71it/s]
Train steps ... :  17%|█▋        | 17299/100000 [5:01:51<13:24:52,  1.71it/s]
Train steps ... :  17%|█▋        | 17300/100000 [5:01:51<13:25:15,  1.71it/s]Step... (17300 / 100000 | Loss: 0.9588569402694702, Learning Rate: 8.311557788944724e-05)
+
                                                                             
Step... (17300 / 100000 | Loss: 0.8157744407653809, Learning Rate: 8.311557788944724e-05)
+
Train steps ... :  17%|█▋        | 17300/100000 [5:01:52<13:25:15,  1.71it/s]
Train steps ... :  17%|█▋        | 17301/100000 [5:01:52<13:25:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17302/100000 [5:01:53<13:25:20,  1.71it/s]
Train steps ... :  17%|█▋        | 17303/100000 [5:01:53<13:25:17,  1.71it/s]
Train steps ... :  17%|█▋        | 17304/100000 [5:01:54<13:25:02,  1.71it/s]
Train steps ... :  17%|█▋        | 17305/100000 [5:01:54<13:25:18,  1.71it/s]
Train steps ... :  17%|█▋        | 17306/100000 [5:01:55<13:25:59,  1.71it/s]
Train steps ... :  17%|█▋        | 17307/100000 [5:01:55<13:25:29,  1.71it/s]
Train steps ... :  17%|█▋        | 17308/100000 [5:01:56<13:26:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17309/100000 [5:01:57<13:25:22,  1.71it/s]
Train steps ... :  17%|█▋        | 17310/100000 [5:01:57<13:25:14,  1.71it/s]
Train steps ... :  17%|█▋        | 17311/100000 [5:01:58<13:25:05,  1.71it/s]
Train steps ... :  17%|█▋        | 17312/100000 [5:01:58<13:24:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17313/100000 [5:01:59<13:26:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17314/100000 [5:02:00<13:26:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17315/100000 [5:02:00<13:25:15,  1.71it/s]
Train steps ... :  17%|█▋        | 17316/100000 [5:02:01<13:25:15,  1.71it/s]
Train steps ... :  17%|█▋        | 17317/100000 [5:02:01<13:25:38,  1.71it/s]
Train steps ... :  17%|█▋        | 17318/100000 [5:02:02<13:25:14,  1.71it/s]
Train steps ... :  17%|█▋        | 17319/100000 [5:02:02<13:25:18,  1.71it/s]
Train steps ... :  17%|█▋        | 17320/100000 [5:02:03<13:26:37,  1.71it/s]
Train steps ... :  17%|█▋        | 17321/100000 [5:02:04<13:26:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17322/100000 [5:02:04<13:25:22,  1.71it/s]
Train steps ... :  17%|█▋        | 17323/100000 [5:02:05<13:25:15,  1.71it/s]
Train steps ... :  17%|█▋        | 17324/100000 [5:02:05<13:24:54,  1.71it/s]
Train steps ... :  17%|█▋        | 17325/100000 [5:02:06<13:24:55,  1.71it/s]Step... (17325 / 100000 | Loss: 1.2062623500823975, Learning Rate: 8.309045226130654e-05)
+
                                                                             
Step... (17325 / 100000 | Loss: 1.0438752174377441, Learning Rate: 8.309045226130654e-05)
+
Train steps ... :  17%|█▋        | 17325/100000 [5:02:06<13:24:55,  1.71it/s]
Train steps ... :  17%|█▋        | 17326/100000 [5:02:07<13:24:45,  1.71it/s]
Train steps ... :  17%|█▋        | 17327/100000 [5:02:07<13:24:36,  1.71it/s]
Train steps ... :  17%|█▋        | 17328/100000 [5:02:08<13:24:25,  1.71it/s]
Train steps ... :  17%|█▋        | 17329/100000 [5:02:08<13:24:20,  1.71it/s]
Train steps ... :  17%|█▋        | 17330/100000 [5:02:09<13:24:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17331/100000 [5:02:09<13:24:52,  1.71it/s]
Train steps ... :  17%|█▋        | 17332/100000 [5:02:10<13:24:17,  1.71it/s]
Train steps ... :  17%|█▋        | 17333/100000 [5:02:11<13:23:59,  1.71it/s]
Train steps ... :  17%|█▋        | 17334/100000 [5:02:11<13:24:20,  1.71it/s]
Train steps ... :  17%|█▋        | 17335/100000 [5:02:12<13:24:43,  1.71it/s]
Train steps ... :  17%|█▋        | 17336/100000 [5:02:12<13:25:31,  1.71it/s]
Train steps ... :  17%|█▋        | 17337/100000 [5:02:13<13:25:35,  1.71it/s]
Train steps ... :  17%|█▋        | 17338/100000 [5:02:14<13:25:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17339/100000 [5:02:14<13:25:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17340/100000 [5:02:15<13:25:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17341/100000 [5:02:15<13:25:13,  1.71it/s]
Train steps ... :  17%|█▋        | 17342/100000 [5:02:16<13:24:59,  1.71it/s]
Train steps ... :  17%|█▋        | 17343/100000 [5:02:17<13:24:47,  1.71it/s]
Train steps ... :  17%|█▋        | 17344/100000 [5:02:17<13:24:52,  1.71it/s]
Train steps ... :  17%|█▋        | 17345/100000 [5:02:18<13:25:25,  1.71it/s]
Train steps ... :  17%|█▋        | 17346/100000 [5:02:18<13:25:49,  1.71it/s]
Train steps ... :  17%|█▋        | 17347/100000 [5:02:19<13:26:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17348/100000 [5:02:19<13:25:58,  1.71it/s]
Train steps ... :  17%|█▋        | 17349/100000 [5:02:20<13:25:17,  1.71it/s]
Train steps ... :  17%|█▋        | 17350/100000 [5:02:21<13:25:02,  1.71it/s]Step... (17350 / 100000 | Loss: 1.1753745079040527, Learning Rate: 8.306532663316583e-05)
+
                                                                             
Step... (17350 / 100000 | Loss: 0.8404524922370911, Learning Rate: 8.306532663316583e-05)
+
Train steps ... :  17%|█▋        | 17350/100000 [5:02:21<13:25:02,  1.71it/s]
Train steps ... :  17%|█▋        | 17351/100000 [5:02:21<13:26:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17352/100000 [5:02:22<13:25:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17353/100000 [5:02:22<13:25:20,  1.71it/s]
Train steps ... :  17%|█▋        | 17354/100000 [5:02:23<13:25:21,  1.71it/s]
Train steps ... :  17%|█▋        | 17355/100000 [5:02:24<13:25:28,  1.71it/s]
Train steps ... :  17%|█▋        | 17356/100000 [5:02:24<13:25:47,  1.71it/s]
Train steps ... :  17%|█▋        | 17357/100000 [5:02:25<13:24:59,  1.71it/s]
Train steps ... :  17%|█▋        | 17358/100000 [5:02:25<13:25:31,  1.71it/s]
Train steps ... :  17%|█▋        | 17359/100000 [5:02:26<13:24:57,  1.71it/s]
Train steps ... :  17%|█▋        | 17360/100000 [5:02:26<13:25:51,  1.71it/s]
Train steps ... :  17%|█▋        | 17361/100000 [5:02:27<13:25:48,  1.71it/s]
Train steps ... :  17%|█▋        | 17362/100000 [5:02:28<13:24:56,  1.71it/s]
Train steps ... :  17%|█▋        | 17363/100000 [5:02:28<13:24:07,  1.71it/s]
Train steps ... :  17%|█▋        | 17364/100000 [5:02:29<13:24:26,  1.71it/s]
Train steps ... :  17%|█▋        | 17365/100000 [5:02:29<13:24:27,  1.71it/s]
Train steps ... :  17%|█▋        | 17366/100000 [5:02:30<13:23:50,  1.71it/s]
Train steps ... :  17%|█▋        | 17367/100000 [5:02:31<13:24:36,  1.71it/s]
Train steps ... :  17%|█▋        | 17368/100000 [5:02:31<13:24:37,  1.71it/s]
Train steps ... :  17%|█▋        | 17369/100000 [5:02:32<13:24:41,  1.71it/s]
Train steps ... :  17%|█▋        | 17370/100000 [5:02:32<13:24:29,  1.71it/s]
Train steps ... :  17%|█▋        | 17371/100000 [5:02:33<13:24:34,  1.71it/s]
Train steps ... :  17%|█▋        | 17372/100000 [5:02:33<13:24:05,  1.71it/s]
Train steps ... :  17%|█▋        | 17373/100000 [5:02:34<13:24:08,  1.71it/s]
Train steps ... :  17%|█▋        | 17374/100000 [5:02:35<13:24:25,  1.71it/s]
Train steps ... :  17%|█▋        | 17375/100000 [5:02:35<13:23:56,  1.71it/s]Step... (17375 / 100000 | Loss: 0.980818510055542, Learning Rate: 8.304020100502513e-05)
+
                                                                             
Step... (17375 / 100000 | Loss: 0.9465025067329407, Learning Rate: 8.304020100502513e-05)
+
Train steps ... :  17%|█▋        | 17375/100000 [5:02:36<13:23:56,  1.71it/s]
Train steps ... :  17%|█▋        | 17376/100000 [5:02:36<13:24:31,  1.71it/s]
Train steps ... :  17%|█▋        | 17377/100000 [5:02:36<13:24:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17378/100000 [5:02:37<13:24:19,  1.71it/s]
Train steps ... :  17%|█▋        | 17379/100000 [5:02:38<13:24:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17380/100000 [5:02:38<13:24:21,  1.71it/s]
Train steps ... :  17%|█▋        | 17381/100000 [5:02:39<13:24:06,  1.71it/s]
Train steps ... :  17%|█▋        | 17382/100000 [5:02:39<13:24:16,  1.71it/s]
Train steps ... :  17%|█▋        | 17383/100000 [5:02:40<13:23:30,  1.71it/s]
Train steps ... :  17%|█▋        | 17384/100000 [5:02:40<13:23:59,  1.71it/s]
Train steps ... :  17%|█▋        | 17385/100000 [5:02:41<13:24:48,  1.71it/s]
Train steps ... :  17%|█▋        | 17386/100000 [5:02:42<13:24:45,  1.71it/s]
Train steps ... :  17%|█▋        | 17387/100000 [5:02:42<13:24:00,  1.71it/s]
Train steps ... :  17%|█▋        | 17388/100000 [5:02:43<13:24:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17389/100000 [5:02:43<13:23:44,  1.71it/s]
Train steps ... :  17%|█▋        | 17390/100000 [5:02:44<13:24:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17391/100000 [5:02:45<13:24:07,  1.71it/s]
Train steps ... :  17%|█▋        | 17392/100000 [5:02:45<13:23:17,  1.71it/s]
Train steps ... :  17%|█▋        | 17393/100000 [5:02:46<13:23:33,  1.71it/s]
Train steps ... :  17%|█▋        | 17394/100000 [5:02:46<13:23:28,  1.71it/s]
Train steps ... :  17%|█▋        | 17395/100000 [5:02:47<13:24:19,  1.71it/s]
Train steps ... :  17%|█▋        | 17396/100000 [5:02:47<13:23:41,  1.71it/s]
Train steps ... :  17%|█▋        | 17397/100000 [5:02:48<13:23:48,  1.71it/s]
Train steps ... :  17%|█▋        | 17398/100000 [5:02:49<13:23:24,  1.71it/s]
Train steps ... :  17%|█▋        | 17399/100000 [5:02:49<13:23:40,  1.71it/s]
Train steps ... :  17%|█▋        | 17400/100000 [5:02:50<13:23:45,  1.71it/s]Step... (17400 / 100000 | Loss: 0.9851991534233093, Learning Rate: 8.301507537688443e-05)
+
                                                                             
Step... (17400 / 100000 | Loss: 1.2068687677383423, Learning Rate: 8.301507537688443e-05)
+
Train steps ... :  17%|█▋        | 17400/100000 [5:02:50<13:23:45,  1.71it/s]
Train steps ... :  17%|█▋        | 17401/100000 [5:02:50<13:24:17,  1.71it/s]
Train steps ... :  17%|█▋        | 17402/100000 [5:02:51<13:23:28,  1.71it/s]
Train steps ... :  17%|█▋        | 17403/100000 [5:02:52<13:23:14,  1.71it/s]
Train steps ... :  17%|█▋        | 17404/100000 [5:02:52<13:23:33,  1.71it/s]
Train steps ... :  17%|█▋        | 17405/100000 [5:02:53<13:24:31,  1.71it/s]
Train steps ... :  17%|█▋        | 17406/100000 [5:02:53<13:24:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17407/100000 [5:02:54<13:24:08,  1.71it/s]
Train steps ... :  17%|█▋        | 17408/100000 [5:02:54<13:24:24,  1.71it/s]
Train steps ... :  17%|█▋        | 17409/100000 [5:02:55<13:24:45,  1.71it/s]
Train steps ... :  17%|█▋        | 17410/100000 [5:02:56<13:25:33,  1.71it/s]
Train steps ... :  17%|█▋        | 17411/100000 [5:02:56<13:24:49,  1.71it/s]
Train steps ... :  17%|█▋        | 17412/100000 [5:02:57<13:24:39,  1.71it/s]
Train steps ... :  17%|█▋        | 17413/100000 [5:02:57<13:23:45,  1.71it/s]
Train steps ... :  17%|█▋        | 17414/100000 [5:02:58<13:24:56,  1.71it/s]
Train steps ... :  17%|█▋        | 17415/100000 [5:02:59<13:24:00,  1.71it/s]
Train steps ... :  17%|█▋        | 17416/100000 [5:02:59<13:24:21,  1.71it/s]
Train steps ... :  17%|█▋        | 17417/100000 [5:03:00<13:23:45,  1.71it/s]
Train steps ... :  17%|█▋        | 17418/100000 [5:03:00<13:23:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17419/100000 [5:03:01<13:24:08,  1.71it/s]
Train steps ... :  17%|█▋        | 17420/100000 [5:03:01<13:24:46,  1.71it/s]
Train steps ... :  17%|█▋        | 17421/100000 [5:03:02<13:24:12,  1.71it/s]
Train steps ... :  17%|█▋        | 17422/100000 [5:03:03<13:23:52,  1.71it/s]
Train steps ... :  17%|█▋        | 17423/100000 [5:03:03<13:23:59,  1.71it/s]
Train steps ... :  17%|█▋        | 17424/100000 [5:03:04<13:23:52,  1.71it/s]
Train steps ... :  17%|█▋        | 17425/100000 [5:03:04<13:24:06,  1.71it/s]Step... (17425 / 100000 | Loss: 1.0413219928741455, Learning Rate: 8.298994974874372e-05)
+
                                                                             
Step... (17425 / 100000 | Loss: 1.0588500499725342, Learning Rate: 8.298994974874372e-05)
+
Train steps ... :  17%|█▋        | 17425/100000 [5:03:05<13:24:06,  1.71it/s]
Train steps ... :  17%|█▋        | 17426/100000 [5:03:05<13:24:00,  1.71it/s]
Train steps ... :  17%|█▋        | 17427/100000 [5:03:06<13:24:24,  1.71it/s]
Train steps ... :  17%|█▋        | 17428/100000 [5:03:06<13:24:57,  1.71it/s]
Train steps ... :  17%|█▋        | 17429/100000 [5:03:07<13:24:27,  1.71it/s]
Train steps ... :  17%|█▋        | 17430/100000 [5:03:07<13:24:10,  1.71it/s]
Train steps ... :  17%|█▋        | 17431/100000 [5:03:08<13:23:36,  1.71it/s]
Train steps ... :  17%|█▋        | 17432/100000 [5:03:09<13:23:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17433/100000 [5:03:09<13:23:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17434/100000 [5:03:10<13:23:15,  1.71it/s]
Train steps ... :  17%|█▋        | 17435/100000 [5:03:10<13:25:09,  1.71it/s]
Train steps ... :  17%|█▋        | 17436/100000 [5:03:11<13:24:19,  1.71it/s]
Train steps ... :  17%|█▋        | 17437/100000 [5:03:11<13:25:04,  1.71it/s]
Train steps ... :  17%|█▋        | 17438/100000 [5:03:12<13:24:46,  1.71it/s]
Train steps ... :  17%|█▋        | 17439/100000 [5:03:13<13:24:15,  1.71it/s]
Train steps ... :  17%|█▋        | 17440/100000 [5:03:13<13:23:52,  1.71it/s]
Train steps ... :  17%|█▋        | 17441/100000 [5:03:14<13:24:18,  1.71it/s]
Train steps ... :  17%|█▋        | 17442/100000 [5:03:14<13:23:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17443/100000 [5:03:15<13:24:53,  1.71it/s]
Train steps ... :  17%|█▋        | 17444/100000 [5:03:16<13:24:02,  1.71it/s]
Train steps ... :  17%|█▋        | 17445/100000 [5:03:16<13:24:18,  1.71it/s]
Train steps ... :  17%|█▋        | 17446/100000 [5:03:17<13:23:52,  1.71it/s]
Train steps ... :  17%|█▋        | 17447/100000 [5:03:17<13:23:28,  1.71it/s]
Train steps ... :  17%|█▋        | 17448/100000 [5:03:18<13:23:38,  1.71it/s]
Train steps ... :  17%|█▋        | 17449/100000 [5:03:18<13:23:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17450/100000 [5:03:19<13:23:01,  1.71it/s]Step... (17450 / 100000 | Loss: 1.3541308641433716, Learning Rate: 8.296482412060302e-05)
+
                                                                             
Step... (17450 / 100000 | Loss: 1.0087649822235107, Learning Rate: 8.296482412060302e-05)
+
Train steps ... :  17%|█▋        | 17450/100000 [5:03:19<13:23:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17451/100000 [5:03:20<13:23:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17452/100000 [5:03:20<13:22:40,  1.71it/s]
Train steps ... :  17%|█▋        | 17453/100000 [5:03:21<13:22:33,  1.71it/s]
Train steps ... :  17%|█▋        | 17454/100000 [5:03:21<13:22:41,  1.71it/s]
Train steps ... :  17%|█▋        | 17455/100000 [5:03:22<13:23:00,  1.71it/s]
Train steps ... :  17%|█▋        | 17456/100000 [5:03:23<13:22:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17457/100000 [5:03:23<13:24:29,  1.71it/s]
Train steps ... :  17%|█▋        | 17458/100000 [5:03:24<13:24:12,  1.71it/s]
Train steps ... :  17%|█▋        | 17459/100000 [5:03:24<13:24:08,  1.71it/s]
Train steps ... :  17%|█▋        | 17460/100000 [5:03:25<13:24:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17461/100000 [5:03:25<13:24:38,  1.71it/s]
Train steps ... :  17%|█▋        | 17462/100000 [5:03:26<13:25:19,  1.71it/s]
Train steps ... :  17%|█▋        | 17463/100000 [5:03:27<13:25:32,  1.71it/s]
Train steps ... :  17%|█▋        | 17464/100000 [5:03:27<13:24:41,  1.71it/s]
Train steps ... :  17%|█▋        | 17465/100000 [5:03:28<13:23:54,  1.71it/s]
Train steps ... :  17%|█▋        | 17466/100000 [5:03:28<13:23:38,  1.71it/s]
Train steps ... :  17%|█▋        | 17467/100000 [5:03:29<13:23:34,  1.71it/s]
Train steps ... :  17%|█▋        | 17468/100000 [5:03:30<13:23:29,  1.71it/s]
Train steps ... :  17%|█▋        | 17469/100000 [5:03:30<13:23:30,  1.71it/s]
Train steps ... :  17%|█▋        | 17470/100000 [5:03:31<13:23:46,  1.71it/s]
Train steps ... :  17%|█▋        | 17471/100000 [5:03:31<13:23:31,  1.71it/s]
Train steps ... :  17%|█▋        | 17472/100000 [5:03:32<13:23:28,  1.71it/s]
Train steps ... :  17%|█▋        | 17473/100000 [5:03:32<13:23:27,  1.71it/s]
Train steps ... :  17%|█▋        | 17474/100000 [5:03:33<13:23:01,  1.71it/s]
Train steps ... :  17%|█▋        | 17475/100000 [5:03:34<13:23:25,  1.71it/s]Step... (17475 / 100000 | Loss: 1.1377465724945068, Learning Rate: 8.293969849246232e-05)
+
                                                                             
Step... (17475 / 100000 | Loss: 0.8870041966438293, Learning Rate: 8.293969849246232e-05)
+
Train steps ... :  17%|█▋        | 17475/100000 [5:03:34<13:23:25,  1.71it/s]
Train steps ... :  17%|█▋        | 17476/100000 [5:03:34<13:23:47,  1.71it/s]
Train steps ... :  17%|█▋        | 17477/100000 [5:03:35<13:23:58,  1.71it/s]
Train steps ... :  17%|█▋        | 17478/100000 [5:03:35<13:23:18,  1.71it/s]
Train steps ... :  17%|█▋        | 17479/100000 [5:03:36<13:24:33,  1.71it/s]
Train steps ... :  17%|█▋        | 17480/100000 [5:03:37<13:24:11,  1.71it/s]
Train steps ... :  17%|█▋        | 17481/100000 [5:03:37<13:24:34,  1.71it/s]
Train steps ... :  17%|█▋        | 17482/100000 [5:03:38<13:23:56,  1.71it/s]
Train steps ... :  17%|█▋        | 17483/100000 [5:03:38<13:23:44,  1.71it/s]
Train steps ... :  17%|█▋        | 17484/100000 [5:03:39<13:23:49,  1.71it/s]
Train steps ... :  17%|█▋        | 17485/100000 [5:03:39<13:23:26,  1.71it/s]
Train steps ... :  17%|█▋        | 17486/100000 [5:03:40<13:23:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17487/100000 [5:03:41<13:24:02,  1.71it/s]
Train steps ... :  17%|█▋        | 17488/100000 [5:03:41<13:24:16,  1.71it/s]
Train steps ... :  17%|█▋        | 17489/100000 [5:03:42<13:24:12,  1.71it/s]
Train steps ... :  17%|█▋        | 17490/100000 [5:03:42<13:24:42,  1.71it/s]
Train steps ... :  17%|█▋        | 17491/100000 [5:03:43<13:23:50,  1.71it/s]
Train steps ... :  17%|█▋        | 17492/100000 [5:03:44<13:24:08,  1.71it/s]
Train steps ... :  17%|█▋        | 17493/100000 [5:03:44<13:24:29,  1.71it/s]
Train steps ... :  17%|█▋        | 17494/100000 [5:03:45<13:24:23,  1.71it/s]
Train steps ... :  17%|█▋        | 17495/100000 [5:03:45<13:23:28,  1.71it/s]
Train steps ... :  17%|█▋        | 17496/100000 [5:03:46<13:24:16,  1.71it/s]
Train steps ... :  17%|█▋        | 17497/100000 [5:03:46<13:23:58,  1.71it/s]
Train steps ... :  17%|█▋        | 17498/100000 [5:03:47<13:23:21,  1.71it/s]
Train steps ... :  17%|█▋        | 17499/100000 [5:03:48<13:23:23,  1.71it/s]
Train steps ... :  18%|█▊        | 17500/100000 [5:03:48<13:23:32,  1.71it/s]Step... (17500 / 100000 | Loss: 1.1171549558639526, Learning Rate: 8.291457286432161e-05)
+
                                                                             
Step... (17500 / 100000 | Loss: 1.2328152656555176, Learning Rate: 8.291457286432161e-05)
+
Train steps ... :  18%|█▊        | 17500/100000 [5:03:49<13:23:32,  1.71it/s]
Train steps ... :  18%|█▊        | 17501/100000 [5:03:49<13:24:22,  1.71it/s]
Train steps ... :  18%|█▊        | 17502/100000 [5:03:49<13:24:49,  1.71it/s]
Train steps ... :  18%|█▊        | 17503/100000 [5:03:50<13:23:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17504/100000 [5:03:51<13:24:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17505/100000 [5:03:51<13:24:04,  1.71it/s]
Train steps ... :  18%|█▊        | 17506/100000 [5:03:52<13:25:00,  1.71it/s]
Train steps ... :  18%|█▊        | 17507/100000 [5:03:52<13:24:33,  1.71it/s]
Train steps ... :  18%|█▊        | 17508/100000 [5:03:53<13:24:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17509/100000 [5:03:54<13:23:35,  1.71it/s]
Train steps ... :  18%|█▊        | 17510/100000 [5:03:54<13:23:44,  1.71it/s]
Train steps ... :  18%|█▊        | 17511/100000 [5:03:55<13:23:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17512/100000 [5:03:55<13:22:43,  1.71it/s]
Train steps ... :  18%|█▊        | 17513/100000 [5:03:56<13:22:59,  1.71it/s]
Train steps ... :  18%|█▊        | 17514/100000 [5:03:56<13:22:33,  1.71it/s]
Train steps ... :  18%|█▊        | 17515/100000 [5:03:57<13:23:11,  1.71it/s]
Train steps ... :  18%|█▊        | 17516/100000 [5:03:58<13:23:03,  1.71it/s]
Train steps ... :  18%|█▊        | 17517/100000 [5:03:58<13:23:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17518/100000 [5:03:59<13:23:00,  1.71it/s]
Train steps ... :  18%|█▊        | 17519/100000 [5:03:59<13:23:21,  1.71it/s]
Train steps ... :  18%|█▊        | 17520/100000 [5:04:00<13:23:16,  1.71it/s]
Train steps ... :  18%|█▊        | 17521/100000 [5:04:01<13:23:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17522/100000 [5:04:01<13:23:43,  1.71it/s]
Train steps ... :  18%|█▊        | 17523/100000 [5:04:02<13:23:31,  1.71it/s]
Train steps ... :  18%|█▊        | 17524/100000 [5:04:02<13:23:58,  1.71it/s]
Train steps ... :  18%|█▊        | 17525/100000 [5:04:03<13:23:42,  1.71it/s]Step... (17525 / 100000 | Loss: 0.8946325778961182, Learning Rate: 8.288944723618091e-05)
+
                                                                             
Step... (17525 / 100000 | Loss: 1.1921049356460571, Learning Rate: 8.288944723618091e-05)
+
Train steps ... :  18%|█▊        | 17525/100000 [5:04:03<13:23:42,  1.71it/s]
Train steps ... :  18%|█▊        | 17526/100000 [5:04:03<13:23:20,  1.71it/s]
Train steps ... :  18%|█▊        | 17527/100000 [5:04:04<13:22:52,  1.71it/s]
Train steps ... :  18%|█▊        | 17528/100000 [5:04:05<13:22:57,  1.71it/s]
Train steps ... :  18%|█▊        | 17529/100000 [5:04:05<13:22:31,  1.71it/s]
Train steps ... :  18%|█▊        | 17530/100000 [5:04:06<13:22:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17531/100000 [5:04:06<13:22:56,  1.71it/s]
Train steps ... :  18%|█▊        | 17532/100000 [5:04:07<13:24:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17533/100000 [5:04:08<13:23:37,  1.71it/s]
Train steps ... :  18%|█▊        | 17534/100000 [5:04:08<13:23:32,  1.71it/s]
Train steps ... :  18%|█▊        | 17535/100000 [5:04:09<13:23:08,  1.71it/s]
Train steps ... :  18%|█▊        | 17536/100000 [5:04:09<13:23:39,  1.71it/s]
Train steps ... :  18%|█▊        | 17537/100000 [5:04:10<13:23:03,  1.71it/s]
Train steps ... :  18%|█▊        | 17538/100000 [5:04:10<13:23:16,  1.71it/s]
Train steps ... :  18%|█▊        | 17539/100000 [5:04:11<13:23:31,  1.71it/s]
Train steps ... :  18%|█▊        | 17540/100000 [5:04:12<13:23:49,  1.71it/s]
Train steps ... :  18%|█▊        | 17541/100000 [5:04:12<13:24:15,  1.71it/s]
Train steps ... :  18%|█▊        | 17542/100000 [5:04:13<13:23:20,  1.71it/s]
Train steps ... :  18%|█▊        | 17543/100000 [5:04:13<13:23:16,  1.71it/s]
Train steps ... :  18%|█▊        | 17544/100000 [5:04:14<13:22:51,  1.71it/s]
Train steps ... :  18%|█▊        | 17545/100000 [5:04:15<13:22:49,  1.71it/s]
Train steps ... :  18%|█▊        | 17546/100000 [5:04:15<13:23:00,  1.71it/s]
Train steps ... :  18%|█▊        | 17547/100000 [5:04:16<13:24:21,  1.71it/s]
Train steps ... :  18%|█▊        | 17548/100000 [5:04:16<13:24:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17549/100000 [5:04:17<13:23:14,  1.71it/s]
Train steps ... :  18%|█▊        | 17550/100000 [5:04:17<13:23:38,  1.71it/s]Step... (17550 / 100000 | Loss: 1.1784980297088623, Learning Rate: 8.28643216080402e-05)
+
                                                                             
Step... (17550 / 100000 | Loss: 1.2907445430755615, Learning Rate: 8.28643216080402e-05)
+
Train steps ... :  18%|█▊        | 17550/100000 [5:04:18<13:23:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17551/100000 [5:04:18<13:23:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17552/100000 [5:04:19<13:23:35,  1.71it/s]
Train steps ... :  18%|█▊        | 17553/100000 [5:04:19<13:24:21,  1.71it/s]
Train steps ... :  18%|█▊        | 17554/100000 [5:04:20<13:23:35,  1.71it/s]
Train steps ... :  18%|█▊        | 17555/100000 [5:04:20<13:23:58,  1.71it/s]
Train steps ... :  18%|█▊        | 17556/100000 [5:04:21<13:23:03,  1.71it/s]
Train steps ... :  18%|█▊        | 17557/100000 [5:04:22<13:22:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17558/100000 [5:04:22<13:22:50,  1.71it/s]
Train steps ... :  18%|█▊        | 17559/100000 [5:04:23<13:22:39,  1.71it/s]
Train steps ... :  18%|█▊        | 17560/100000 [5:04:23<13:22:49,  1.71it/s]
Train steps ... :  18%|█▊        | 17561/100000 [5:04:24<13:22:15,  1.71it/s]
Train steps ... :  18%|█▊        | 17562/100000 [5:04:24<13:23:00,  1.71it/s]
Train steps ... :  18%|█▊        | 17563/100000 [5:04:25<13:24:19,  1.71it/s]
Train steps ... :  18%|█▊        | 17564/100000 [5:04:26<13:23:39,  1.71it/s]
Train steps ... :  18%|█▊        | 17565/100000 [5:04:26<13:23:20,  1.71it/s]
Train steps ... :  18%|█▊        | 17566/100000 [5:04:27<13:23:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17567/100000 [5:04:27<13:23:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17568/100000 [5:04:28<13:23:04,  1.71it/s]
Train steps ... :  18%|█▊        | 17569/100000 [5:04:29<13:22:13,  1.71it/s]
Train steps ... :  18%|█▊        | 17570/100000 [5:04:29<13:22:43,  1.71it/s]
Train steps ... :  18%|█▊        | 17571/100000 [5:04:30<13:22:11,  1.71it/s]
Train steps ... :  18%|█▊        | 17572/100000 [5:04:30<13:22:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17573/100000 [5:04:31<13:22:44,  1.71it/s]
Train steps ... :  18%|█▊        | 17574/100000 [5:04:32<13:23:28,  1.71it/s]
Train steps ... :  18%|█▊        | 17575/100000 [5:04:32<13:23:08,  1.71it/s]Step... (17575 / 100000 | Loss: 0.8822317123413086, Learning Rate: 8.28391959798995e-05)
+
                                                                             
Step... (17575 / 100000 | Loss: 1.0176315307617188, Learning Rate: 8.28391959798995e-05)
+
Train steps ... :  18%|█▊        | 17575/100000 [5:04:32<13:23:08,  1.71it/s]
Train steps ... :  18%|█▊        | 17576/100000 [5:04:33<13:24:03,  1.71it/s]
Train steps ... :  18%|█▊        | 17577/100000 [5:04:33<13:23:10,  1.71it/s]
Train steps ... :  18%|█▊        | 17578/100000 [5:04:34<13:23:16,  1.71it/s]
Train steps ... :  18%|█▊        | 17579/100000 [5:04:34<13:24:14,  1.71it/s]
Train steps ... :  18%|█▊        | 17580/100000 [5:04:35<13:24:13,  1.71it/s]
Train steps ... :  18%|█▊        | 17581/100000 [5:04:36<13:23:33,  1.71it/s]
Train steps ... :  18%|█▊        | 17582/100000 [5:04:36<13:24:28,  1.71it/s]
Train steps ... :  18%|█▊        | 17583/100000 [5:04:37<13:24:01,  1.71it/s]
Train steps ... :  18%|█▊        | 17584/100000 [5:04:37<13:24:41,  1.71it/s]
Train steps ... :  18%|█▊        | 17585/100000 [5:04:38<13:23:37,  1.71it/s]
Train steps ... :  18%|█▊        | 17586/100000 [5:04:39<13:22:49,  1.71it/s]
Train steps ... :  18%|█▊        | 17587/100000 [5:04:39<13:23:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17588/100000 [5:04:40<13:23:21,  1.71it/s]
Train steps ... :  18%|█▊        | 17589/100000 [5:04:40<13:23:15,  1.71it/s]
Train steps ... :  18%|█▊        | 17590/100000 [5:04:41<13:24:54,  1.71it/s]
Train steps ... :  18%|█▊        | 17591/100000 [5:04:41<13:23:59,  1.71it/s]
Train steps ... :  18%|█▊        | 17592/100000 [5:04:42<13:24:48,  1.71it/s]
Train steps ... :  18%|█▊        | 17593/100000 [5:04:43<13:23:58,  1.71it/s]
Train steps ... :  18%|█▊        | 17594/100000 [5:04:43<13:23:18,  1.71it/s]
Train steps ... :  18%|█▊        | 17595/100000 [5:04:44<13:23:31,  1.71it/s]
Train steps ... :  18%|█▊        | 17596/100000 [5:04:44<13:22:58,  1.71it/s]
Train steps ... :  18%|█▊        | 17597/100000 [5:04:45<13:22:42,  1.71it/s]
Train steps ... :  18%|█▊        | 17598/100000 [5:04:46<13:22:26,  1.71it/s]
Train steps ... :  18%|█▊        | 17599/100000 [5:04:46<13:21:42,  1.71it/s]
Train steps ... :  18%|█▊        | 17600/100000 [5:04:47<13:22:19,  1.71it/s]Step... (17600 / 100000 | Loss: 0.7646717429161072, Learning Rate: 8.28140703517588e-05)
+
                                                                             
Step... (17600 / 100000 | Loss: 1.1075918674468994, Learning Rate: 8.28140703517588e-05)
+
Train steps ... :  18%|█▊        | 17600/100000 [5:04:47<13:22:19,  1.71it/s]
Train steps ... :  18%|���▊        | 17601/100000 [5:04:47<13:22:46,  1.71it/s]
Train steps ... :  18%|█▊        | 17602/100000 [5:04:48<13:23:26,  1.71it/s]
Train steps ... :  18%|█▊        | 17603/100000 [5:04:48<13:23:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17604/100000 [5:04:49<13:25:10,  1.71it/s]
Train steps ... :  18%|█▊        | 17605/100000 [5:04:50<13:24:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17606/100000 [5:04:50<13:24:57,  1.71it/s]
Train steps ... :  18%|█▊        | 17607/100000 [5:04:51<13:23:35,  1.71it/s]
Train steps ... :  18%|█▊        | 17608/100000 [5:04:51<13:23:22,  1.71it/s]
Train steps ... :  18%|█▊        | 17609/100000 [5:04:52<13:22:50,  1.71it/s]
Train steps ... :  18%|█▊        | 17610/100000 [5:04:53<13:23:08,  1.71it/s]
Train steps ... :  18%|█▊        | 17611/100000 [5:04:53<13:23:04,  1.71it/s]
Train steps ... :  18%|█▊        | 17612/100000 [5:04:54<13:23:06,  1.71it/s]
Train steps ... :  18%|█▊        | 17613/100000 [5:04:54<13:23:44,  1.71it/s]
Train steps ... :  18%|█▊        | 17614/100000 [5:04:55<13:22:45,  1.71it/s]
Train steps ... :  18%|█▊        | 17615/100000 [5:04:55<13:24:03,  1.71it/s]
Train steps ... :  18%|█▊        | 17616/100000 [5:04:56<13:23:25,  1.71it/s]
Train steps ... :  18%|█▊        | 17617/100000 [5:04:57<13:23:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17618/100000 [5:04:57<13:24:03,  1.71it/s]
Train steps ... :  18%|█▊        | 17619/100000 [5:04:58<13:24:29,  1.71it/s]
Train steps ... :  18%|█▊        | 17620/100000 [5:04:58<13:23:46,  1.71it/s]
Train steps ... :  18%|█▊        | 17621/100000 [5:04:59<13:23:42,  1.71it/s]
Train steps ... :  18%|█▊        | 17622/100000 [5:05:00<13:24:18,  1.71it/s]
Train steps ... :  18%|█▊        | 17623/100000 [5:05:00<13:23:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17624/100000 [5:05:01<13:23:44,  1.71it/s]
Train steps ... :  18%|█▊        | 17625/100000 [5:05:01<13:22:45,  1.71it/s]Step... (17625 / 100000 | Loss: 0.9605456590652466, Learning Rate: 8.27889447236181e-05)
+
                                                                             
Step... (17625 / 100000 | Loss: 1.0136756896972656, Learning Rate: 8.27889447236181e-05)
+
Train steps ... :  18%|█▊        | 17625/100000 [5:05:02<13:22:45,  1.71it/s]
Train steps ... :  18%|█▊        | 17626/100000 [5:05:02<13:23:42,  1.71it/s]
Train steps ... :  18%|█▊        | 17627/100000 [5:05:03<13:23:48,  1.71it/s]
Train steps ... :  18%|█▊        | 17628/100000 [5:05:03<13:23:39,  1.71it/s]
Train steps ... :  18%|█▊        | 17629/100000 [5:05:04<13:23:04,  1.71it/s]
Train steps ... :  18%|█▊        | 17630/100000 [5:05:04<13:22:57,  1.71it/s]
Train steps ... :  18%|█▊        | 17631/100000 [5:05:05<13:22:58,  1.71it/s]
Train steps ... :  18%|█▊        | 17632/100000 [5:05:05<13:23:41,  1.71it/s]
Train steps ... :  18%|█▊        | 17633/100000 [5:05:06<13:23:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17634/100000 [5:05:07<13:22:32,  1.71it/s]
Train steps ... :  18%|█▊        | 17635/100000 [5:05:07<13:22:54,  1.71it/s]
Train steps ... :  18%|█▊        | 17636/100000 [5:05:08<13:22:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17637/100000 [5:05:08<13:22:45,  1.71it/s]
Train steps ... :  18%|█▊        | 17638/100000 [5:05:09<13:22:54,  1.71it/s]
Train steps ... :  18%|█▊        | 17639/100000 [5:05:10<13:23:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17640/100000 [5:05:10<13:22:51,  1.71it/s]
Train steps ... :  18%|█▊        | 17641/100000 [5:05:11<13:22:29,  1.71it/s]
Train steps ... :  18%|█▊        | 17642/100000 [5:05:11<13:22:34,  1.71it/s]
Train steps ... :  18%|█▊        | 17643/100000 [5:05:12<13:22:46,  1.71it/s]
Train steps ... :  18%|█▊        | 17644/100000 [5:05:12<13:22:10,  1.71it/s]
Train steps ... :  18%|█▊        | 17645/100000 [5:05:13<13:21:51,  1.71it/s]
Train steps ... :  18%|█▊        | 17646/100000 [5:05:14<13:22:26,  1.71it/s]
Train steps ... :  18%|█▊        | 17647/100000 [5:05:14<13:22:10,  1.71it/s]
Train steps ... :  18%|█▊        | 17648/100000 [5:05:15<13:22:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17649/100000 [5:05:15<13:21:39,  1.71it/s]
Train steps ... :  18%|█▊        | 17650/100000 [5:05:16<13:22:15,  1.71it/s]Step... (17650 / 100000 | Loss: 1.2224628925323486, Learning Rate: 8.276381909547739e-05)
+
                                                                             
Step... (17650 / 100000 | Loss: 1.120872974395752, Learning Rate: 8.276381909547739e-05)
+
Train steps ... :  18%|█▊        | 17650/100000 [5:05:16<13:22:15,  1.71it/s]
Train steps ... :  18%|█▊        | 17651/100000 [5:05:17<13:22:02,  1.71it/s]
Train steps ... :  18%|█▊        | 17652/100000 [5:05:17<13:22:34,  1.71it/s]
Train steps ... :  18%|█▊        | 17653/100000 [5:05:18<13:21:52,  1.71it/s]
Train steps ... :  18%|█▊        | 17654/100000 [5:05:18<13:21:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17655/100000 [5:05:19<13:21:17,  1.71it/s]
Train steps ... :  18%|█▊        | 17656/100000 [5:05:19<13:21:23,  1.71it/s]
Train steps ... :  18%|█▊        | 17657/100000 [5:05:20<13:21:34,  1.71it/s]
Train steps ... :  18%|█▊        | 17658/100000 [5:05:21<13:21:34,  1.71it/s]
Train steps ... :  18%|█▊        | 17659/100000 [5:05:21<13:21:52,  1.71it/s]
Train steps ... :  18%|█▊        | 17660/100000 [5:05:22<13:21:23,  1.71it/s]
Train steps ... :  18%|█▊        | 17661/100000 [5:05:22<13:21:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17662/100000 [5:05:23<13:21:48,  1.71it/s]
Train steps ... :  18%|█▊        | 17663/100000 [5:05:24<13:22:36,  1.71it/s]
Train steps ... :  18%|█▊        | 17664/100000 [5:05:24<13:21:42,  1.71it/s]
Train steps ... :  18%|█▊        | 17665/100000 [5:05:25<13:22:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17666/100000 [5:05:25<13:22:16,  1.71it/s]
Train steps ... :  18%|█▊        | 17667/100000 [5:05:26<13:21:40,  1.71it/s]
Train steps ... :  18%|█▊        | 17668/100000 [5:05:26<13:21:57,  1.71it/s]
Train steps ... :  18%|█▊        | 17669/100000 [5:05:27<13:22:24,  1.71it/s]
Train steps ... :  18%|█▊        | 17670/100000 [5:05:28<13:23:44,  1.71it/s]
Train steps ... :  18%|█▊        | 17671/100000 [5:05:28<13:22:52,  1.71it/s]
Train steps ... :  18%|█▊        | 17672/100000 [5:05:29<13:22:53,  1.71it/s]
Train steps ... :  18%|█▊        | 17673/100000 [5:05:29<13:22:44,  1.71it/s]
Train steps ... :  18%|█▊        | 17674/100000 [5:05:30<13:23:25,  1.71it/s]
Train steps ... :  18%|█▊        | 17675/100000 [5:05:31<13:23:52,  1.71it/s]Step... (17675 / 100000 | Loss: 1.1470081806182861, Learning Rate: 8.273869346733669e-05)
+
                                                                             
Step... (17675 / 100000 | Loss: 1.3995187282562256, Learning Rate: 8.273869346733669e-05)
+
Train steps ... :  18%|█▊        | 17675/100000 [5:05:31<13:23:52,  1.71it/s]
Train steps ... :  18%|█▊        | 17676/100000 [5:05:31<13:23:01,  1.71it/s]
Train steps ... :  18%|█▊        | 17677/100000 [5:05:32<13:22:16,  1.71it/s]
Train steps ... :  18%|█▊        | 17678/100000 [5:05:32<13:22:35,  1.71it/s]
Train steps ... :  18%|█▊        | 17679/100000 [5:05:33<13:22:32,  1.71it/s]
Train steps ... :  18%|█▊        | 17680/100000 [5:05:34<13:24:58,  1.70it/s]
Train steps ... :  18%|█▊        | 17681/100000 [5:05:34<13:24:13,  1.71it/s]
Train steps ... :  18%|█▊        | 17682/100000 [5:05:35<13:23:22,  1.71it/s]
Train steps ... :  18%|█▊        | 17683/100000 [5:05:35<13:23:36,  1.71it/s]
Train steps ... :  18%|█▊        | 17684/100000 [5:05:36<13:22:19,  1.71it/s]
Train steps ... :  18%|█▊        | 17685/100000 [5:05:36<13:20:16,  1.71it/s]
Train steps ... :  18%|█▊        | 17686/100000 [5:05:37<13:18:26,  1.72it/s]
Train steps ... :  18%|█▊        | 17687/100000 [5:05:38<13:17:00,  1.72it/s]
Train steps ... :  18%|█▊        | 17688/100000 [5:05:38<13:16:10,  1.72it/s]
Train steps ... :  18%|█▊        | 17689/100000 [5:05:39<13:16:32,  1.72it/s]
Train steps ... :  18%|█▊        | 17690/100000 [5:05:39<13:16:44,  1.72it/s]
Train steps ... :  18%|█▊        | 17691/100000 [5:05:40<13:16:13,  1.72it/s]
Train steps ... :  18%|█▊        | 17692/100000 [5:05:40<13:17:12,  1.72it/s]
Train steps ... :  18%|█▊        | 17693/100000 [5:05:41<13:16:18,  1.72it/s]
Train steps ... :  18%|█▊        | 17694/100000 [5:05:42<13:18:09,  1.72it/s]
Train steps ... :  18%|█▊        | 17695/100000 [5:05:42<13:18:02,  1.72it/s]
Train steps ... :  18%|█▊        | 17696/100000 [5:05:43<13:20:14,  1.71it/s]
Train steps ... :  18%|█▊        | 17697/100000 [5:05:43<13:19:01,  1.72it/s]
Train steps ... :  18%|█▊        | 17698/100000 [5:05:44<13:18:42,  1.72it/s]
Train steps ... :  18%|█▊        | 17699/100000 [5:05:45<13:18:34,  1.72it/s]
Train steps ... :  18%|█▊        | 17700/100000 [5:05:45<13:19:10,  1.72it/s]Step... (17700 / 100000 | Loss: 1.1765178442001343, Learning Rate: 8.271356783919599e-05)
+
                                                                             
Step... (17700 / 100000 | Loss: 0.9555251598358154, Learning Rate: 8.271356783919599e-05)
+
Train steps ... :  18%|█▊        | 17700/100000 [5:05:45<13:19:10,  1.72it/s]
Train steps ... :  18%|█▊        | 17701/100000 [5:05:46<13:19:29,  1.72it/s]
Train steps ... :  18%|█▊        | 17702/100000 [5:05:46<13:19:26,  1.72it/s]
Train steps ... :  18%|█▊        | 17703/100000 [5:05:47<13:19:11,  1.72it/s]
Train steps ... :  18%|█▊        | 17704/100000 [5:05:47<13:20:40,  1.71it/s]
Train steps ... :  18%|█▊        | 17705/100000 [5:05:48<13:19:15,  1.72it/s]
Train steps ... :  18%|█▊        | 17706/100000 [5:05:49<13:19:20,  1.72it/s]
Train steps ... :  18%|█▊        | 17707/100000 [5:05:49<13:19:25,  1.72it/s]
Train steps ... :  18%|█▊        | 17708/100000 [5:05:50<13:20:22,  1.71it/s]
Train steps ... :  18%|█▊        | 17709/100000 [5:05:50<13:21:35,  1.71it/s]
Train steps ... :  18%|█▊        | 17710/100000 [5:05:51<13:21:42,  1.71it/s]
Train steps ... :  18%|█▊        | 17711/100000 [5:05:52<13:20:45,  1.71it/s]
Train steps ... :  18%|█▊        | 17712/100000 [5:05:52<13:20:06,  1.71it/s]
Train steps ... :  18%|█▊        | 17713/100000 [5:05:53<13:20:03,  1.71it/s]
Train steps ... :  18%|█▊        | 17714/100000 [5:05:53<13:20:59,  1.71it/s]
Train steps ... :  18%|█▊        | 17715/100000 [5:05:54<13:21:53,  1.71it/s]
Train steps ... :  18%|█▊        | 17716/100000 [5:05:54<13:21:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17717/100000 [5:05:55<13:22:15,  1.71it/s]
Train steps ... :  18%|█▊        | 17718/100000 [5:05:56<13:21:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17719/100000 [5:05:56<13:20:41,  1.71it/s]
Train steps ... :  18%|█▊        | 17720/100000 [5:05:57<13:20:23,  1.71it/s]
Train steps ... :  18%|█▊        | 17721/100000 [5:05:57<13:21:01,  1.71it/s]
Train steps ... :  18%|█▊        | 17722/100000 [5:05:58<13:20:28,  1.71it/s]
Train steps ... :  18%|█▊        | 17723/100000 [5:05:59<13:21:25,  1.71it/s]
Train steps ... :  18%|█▊        | 17724/100000 [5:05:59<13:21:34,  1.71it/s]
Train steps ... :  18%|█▊        | 17725/100000 [5:06:00<13:20:58,  1.71it/s]Step... (17725 / 100000 | Loss: 1.467637062072754, Learning Rate: 8.268844221105528e-05)
+
                                                                             
Step... (17725 / 100000 | Loss: 1.3457361459732056, Learning Rate: 8.268844221105528e-05)
+
Train steps ... :  18%|█▊        | 17725/100000 [5:06:00<13:20:58,  1.71it/s]
Train steps ... :  18%|█▊        | 17726/100000 [5:06:00<13:20:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17727/100000 [5:06:01<13:22:24,  1.71it/s]
Train steps ... :  18%|█▊        | 17728/100000 [5:06:02<13:20:35,  1.71it/s]
Train steps ... :  18%|█▊        | 17729/100000 [5:06:02<13:20:33,  1.71it/s]
Train steps ... :  18%|█▊        | 17730/100000 [5:06:03<13:21:01,  1.71it/s]
Train steps ... :  18%|█▊        | 17731/100000 [5:06:03<13:20:40,  1.71it/s]
Train steps ... :  18%|█▊        | 17732/100000 [5:06:04<13:20:43,  1.71it/s]
Train steps ... :  18%|█▊        | 17733/100000 [5:06:04<13:19:49,  1.71it/s]
Train steps ... :  18%|█▊        | 17734/100000 [5:06:05<13:20:49,  1.71it/s]
Train steps ... :  18%|█▊        | 17735/100000 [5:06:06<13:20:50,  1.71it/s]
Train steps ... :  18%|█▊        | 17736/100000 [5:06:06<13:20:55,  1.71it/s]
Train steps ... :  18%|█▊        | 17737/100000 [5:06:07<13:21:03,  1.71it/s]
Train steps ... :  18%|█▊        | 17738/100000 [5:06:07<13:20:35,  1.71it/s]
Train steps ... :  18%|█▊        | 17739/100000 [5:06:08<13:20:19,  1.71it/s]
Train steps ... :  18%|█▊        | 17740/100000 [5:06:09<13:20:51,  1.71it/s]
Train steps ... :  18%|█▊        | 17741/100000 [5:06:09<13:23:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17742/100000 [5:06:10<13:20:48,  1.71it/s]
Train steps ... :  18%|█▊        | 17743/100000 [5:06:10<13:20:39,  1.71it/s]
Train steps ... :  18%|█▊        | 17744/100000 [5:06:11<13:20:45,  1.71it/s]
Train steps ... :  18%|█▊        | 17745/100000 [5:06:11<13:22:00,  1.71it/s]
Train steps ... :  18%|█▊        | 17746/100000 [5:06:12<13:23:21,  1.71it/s]
Train steps ... :  18%|█▊        | 17747/100000 [5:06:13<13:21:50,  1.71it/s]
Train steps ... :  18%|█▊        | 17748/100000 [5:06:13<13:21:26,  1.71it/s]
Train steps ... :  18%|█▊        | 17749/100000 [5:06:14<13:21:30,  1.71it/s]
Train steps ... :  18%|█▊        | 17750/100000 [5:06:14<13:21:46,  1.71it/s]Step... (17750 / 100000 | Loss: 1.32315993309021, Learning Rate: 8.266331658291458e-05)
+
                                                                             
Step... (17750 / 100000 | Loss: 1.350563645362854, Learning Rate: 8.266331658291458e-05)
+
Train steps ... :  18%|█▊        | 17750/100000 [5:06:15<13:21:46,  1.71it/s]
Train steps ... :  18%|█▊        | 17751/100000 [5:06:15<13:22:37,  1.71it/s]
Train steps ... :  18%|█▊        | 17752/100000 [5:06:16<13:21:58,  1.71it/s]
Train steps ... :  18%|█▊        | 17753/100000 [5:06:16<13:21:43,  1.71it/s]
Train steps ... :  18%|█▊        | 17754/100000 [5:06:17<13:21:58,  1.71it/s]
Train steps ... :  18%|█▊        | 17755/100000 [5:06:17<13:22:39,  1.71it/s]
Train steps ... :  18%|█▊        | 17756/100000 [5:06:18<13:22:12,  1.71it/s]
Train steps ... :  18%|█▊        | 17757/100000 [5:06:18<13:22:29,  1.71it/s]
Train steps ... :  18%|█▊        | 17758/100000 [5:06:19<13:22:52,  1.71it/s]
Train steps ... :  18%|█▊        | 17759/100000 [5:06:20<13:22:13,  1.71it/s]
Train steps ... :  18%|█▊        | 17760/100000 [5:06:20<13:21:49,  1.71it/s]
Train steps ... :  18%|█▊        | 17761/100000 [5:06:21<13:21:20,  1.71it/s]
Train steps ... :  18%|█▊        | 17762/100000 [5:06:21<13:20:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17763/100000 [5:06:22<13:22:11,  1.71it/s]
Train steps ... :  18%|█▊        | 17764/100000 [5:06:23<13:22:04,  1.71it/s]
Train steps ... :  18%|█▊        | 17765/100000 [5:06:23<13:21:18,  1.71it/s]
Train steps ... :  18%|█▊        | 17766/100000 [5:06:24<13:21:02,  1.71it/s]
Train steps ... :  18%|█▊        | 17767/100000 [5:06:24<13:20:55,  1.71it/s]
Train steps ... :  18%|█▊        | 17768/100000 [5:06:25<13:22:13,  1.71it/s]
Train steps ... :  18%|█▊        | 17769/100000 [5:06:25<13:21:31,  1.71it/s]
Train steps ... :  18%|█▊        | 17770/100000 [5:06:26<13:23:57,  1.70it/s]
Train steps ... :  18%|█▊        | 17771/100000 [5:06:27<13:22:22,  1.71it/s]
Train steps ... :  18%|█▊        | 17772/100000 [5:06:27<13:22:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17773/100000 [5:06:28<13:21:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17774/100000 [5:06:28<13:21:11,  1.71it/s]
Train steps ... :  18%|█▊        | 17775/100000 [5:06:29<13:21:05,  1.71it/s]Step... (17775 / 100000 | Loss: 1.094716191291809, Learning Rate: 8.263819095477387e-05)
+
                                                                             
Step... (17775 / 100000 | Loss: 1.0025670528411865, Learning Rate: 8.263819095477387e-05)
+
Train steps ... :  18%|█▊        | 17775/100000 [5:06:29<13:21:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17776/100000 [5:06:30<13:21:21,  1.71it/s]
Train steps ... :  18%|█▊        | 17777/100000 [5:06:30<13:21:16,  1.71it/s]
Train steps ... :  18%|█▊        | 17778/100000 [5:06:31<13:20:58,  1.71it/s]
Train steps ... :  18%|█▊        | 17779/100000 [5:06:31<13:21:45,  1.71it/s]
Train steps ... :  18%|█▊        | 17780/100000 [5:06:32<13:20:48,  1.71it/s]
Train steps ... :  18%|█▊        | 17781/100000 [5:06:32<13:20:54,  1.71it/s]
Train steps ... :  18%|█▊        | 17782/100000 [5:06:33<13:20:15,  1.71it/s]
Train steps ... :  18%|█▊        | 17783/100000 [5:06:34<13:20:44,  1.71it/s]
Train steps ... :  18%|█▊        | 17784/100000 [5:06:34<13:22:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17785/100000 [5:06:35<13:21:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17786/100000 [5:06:35<13:21:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17787/100000 [5:06:36<13:20:24,  1.71it/s]
Train steps ... :  18%|█▊        | 17788/100000 [5:06:37<13:22:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17789/100000 [5:06:37<13:20:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17790/100000 [5:06:38<13:20:01,  1.71it/s]
Train steps ... :  18%|█▊        | 17791/100000 [5:06:38<13:20:17,  1.71it/s]
Train steps ... :  18%|█▊        | 17792/100000 [5:06:39<13:20:17,  1.71it/s]
Train steps ... :  18%|█▊        | 17793/100000 [5:06:40<13:20:32,  1.71it/s]
Train steps ... :  18%|█▊        | 17794/100000 [5:06:40<13:20:19,  1.71it/s]
Train steps ... :  18%|█▊        | 17795/100000 [5:06:41<13:20:33,  1.71it/s]
Train steps ... :  18%|█▊        | 17796/100000 [5:06:41<13:19:48,  1.71it/s]
Train steps ... :  18%|█▊        | 17797/100000 [5:06:42<13:20:55,  1.71it/s]
Train steps ... :  18%|█▊        | 17798/100000 [5:06:42<13:20:26,  1.71it/s]
Train steps ... :  18%|█▊        | 17799/100000 [5:06:43<13:20:15,  1.71it/s]
Train steps ... :  18%|█▊        | 17800/100000 [5:06:44<13:20:00,  1.71it/s]Step... (17800 / 100000 | Loss: 0.8450510501861572, Learning Rate: 8.261306532663317e-05)
+
                                                                             
Step... (17800 / 100000 | Loss: 0.9484798908233643, Learning Rate: 8.261306532663317e-05)
+
Train steps ... :  18%|█▊        | 17800/100000 [5:06:44<13:20:00,  1.71it/s]
Train steps ... :  18%|█▊        | 17801/100000 [5:06:44<13:19:54,  1.71it/s]
Train steps ... :  18%|█▊        | 17802/100000 [5:06:45<13:20:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17803/100000 [5:06:45<13:19:43,  1.71it/s]
Train steps ... :  18%|█▊        | 17804/100000 [5:06:46<13:20:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17805/100000 [5:06:47<13:20:39,  1.71it/s]
Train steps ... :  18%|█▊        | 17806/100000 [5:06:47<13:21:13,  1.71it/s]
Train steps ... :  18%|█▊        | 17807/100000 [5:06:48<13:20:50,  1.71it/s]
Train steps ... :  18%|█▊        | 17808/100000 [5:06:48<13:21:51,  1.71it/s]
Train steps ... :  18%|█▊        | 17809/100000 [5:06:49<13:20:26,  1.71it/s]
Train steps ... :  18%|█▊        | 17810/100000 [5:06:49<13:21:18,  1.71it/s]
Train steps ... :  18%|█▊        | 17811/100000 [5:06:50<13:21:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17812/100000 [5:06:51<13:21:41,  1.71it/s]
Train steps ... :  18%|█▊        | 17813/100000 [5:06:51<13:21:36,  1.71it/s]
Train steps ... :  18%|█▊        | 17814/100000 [5:06:52<13:21:23,  1.71it/s]
Train steps ... :  18%|█▊        | 17815/100000 [5:06:52<13:23:26,  1.70it/s]
Train steps ... :  18%|█▊        | 17816/100000 [5:06:53<13:21:01,  1.71it/s]
Train steps ... :  18%|█▊        | 17817/100000 [5:06:54<13:20:57,  1.71it/s]
Train steps ... :  18%|█▊        | 17818/100000 [5:06:54<13:22:46,  1.71it/s]
Train steps ... :  18%|█▊        | 17819/100000 [5:06:55<13:21:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17820/100000 [5:06:55<13:21:15,  1.71it/s]
Train steps ... :  18%|█▊        | 17821/100000 [5:06:56<13:20:54,  1.71it/s]
Train steps ... :  18%|█▊        | 17822/100000 [5:06:56<13:21:19,  1.71it/s]
Train steps ... :  18%|█▊        | 17823/100000 [5:06:57<13:20:40,  1.71it/s]
Train steps ... :  18%|█▊        | 17824/100000 [5:06:58<13:20:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17825/100000 [5:06:58<13:22:20,  1.71it/s]Step... (17825 / 100000 | Loss: 0.8818867206573486, Learning Rate: 8.258793969849247e-05)
+
                                                                             
Step... (17825 / 100000 | Loss: 0.6979104280471802, Learning Rate: 8.258793969849247e-05)
+
Train steps ... :  18%|█▊        | 17825/100000 [5:06:59<13:22:20,  1.71it/s]
Train steps ... :  18%|█▊        | 17826/100000 [5:06:59<13:21:00,  1.71it/s]
Train steps ... :  18%|█▊        | 17827/100000 [5:06:59<13:20:21,  1.71it/s]
Train steps ... :  18%|█▊        | 17828/100000 [5:07:00<13:22:11,  1.71it/s]
Train steps ... :  18%|█▊        | 17829/100000 [5:07:01<13:20:27,  1.71it/s]
Train steps ... :  18%|█▊        | 17830/100000 [5:07:01<13:19:37,  1.71it/s]
Train steps ... :  18%|█▊        | 17831/100000 [5:07:02<13:22:40,  1.71it/s]
Train steps ... :  18%|█▊        | 17832/100000 [5:07:02<13:20:52,  1.71it/s]
Train steps ... :  18%|█▊        | 17833/100000 [5:07:03<13:20:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17834/100000 [5:07:03<13:19:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17835/100000 [5:07:04<13:20:32,  1.71it/s]
Train steps ... :  18%|█▊        | 17836/100000 [5:07:05<13:21:01,  1.71it/s]
Train steps ... :  18%|█▊        | 17837/100000 [5:07:05<13:20:36,  1.71it/s]
Train steps ... :  18%|█▊        | 17838/100000 [5:07:06<13:21:01,  1.71it/s]
Train steps ... :  18%|█▊        | 17839/100000 [5:07:06<13:20:06,  1.71it/s]
Train steps ... :  18%|█▊        | 17840/100000 [5:07:07<13:19:54,  1.71it/s]
Train steps ... :  18%|█▊        | 17841/100000 [5:07:08<13:19:51,  1.71it/s]
Train steps ... :  18%|█▊        | 17842/100000 [5:07:08<13:21:17,  1.71it/s]
Train steps ... :  18%|█▊        | 17843/100000 [5:07:09<13:20:31,  1.71it/s]
Train steps ... :  18%|█▊        | 17844/100000 [5:07:09<13:20:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17845/100000 [5:07:10<13:21:10,  1.71it/s]
Train steps ... :  18%|█▊        | 17846/100000 [5:07:10<13:19:41,  1.71it/s]
Train steps ... :  18%|█▊        | 17847/100000 [5:07:11<13:19:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17848/100000 [5:07:12<13:19:28,  1.71it/s]
Train steps ... :  18%|█▊        | 17849/100000 [5:07:12<13:20:06,  1.71it/s]
Train steps ... :  18%|█▊        | 17850/100000 [5:07:13<13:20:02,  1.71it/s]Step... (17850 / 100000 | Loss: 1.0097582340240479, Learning Rate: 8.256281407035176e-05)
+
                                                                             
Step... (17850 / 100000 | Loss: 0.8678888082504272, Learning Rate: 8.256281407035176e-05)
+
Train steps ... :  18%|█▊        | 17850/100000 [5:07:13<13:20:02,  1.71it/s]
Train steps ... :  18%|█▊        | 17851/100000 [5:07:13<13:20:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17852/100000 [5:07:14<13:20:48,  1.71it/s]
Train steps ... :  18%|█▊        | 17853/100000 [5:07:15<13:20:49,  1.71it/s]
Train steps ... :  18%|█▊        | 17854/100000 [5:07:15<13:19:59,  1.71it/s]
Train steps ... :  18%|█▊        | 17855/100000 [5:07:16<13:20:14,  1.71it/s]
Train steps ... :  18%|█▊        | 17856/100000 [5:07:16<13:20:35,  1.71it/s]
Train steps ... :  18%|█▊        | 17857/100000 [5:07:17<13:19:26,  1.71it/s]
Train steps ... :  18%|█▊        | 17858/100000 [5:07:18<13:19:42,  1.71it/s]
Train steps ... :  18%|█▊        | 17859/100000 [5:07:18<13:20:18,  1.71it/s]
Train steps ... :  18%|█▊        | 17860/100000 [5:07:19<13:20:37,  1.71it/s]
Train steps ... :  18%|█▊        | 17861/100000 [5:07:19<13:20:10,  1.71it/s]
Train steps ... :  18%|█▊        | 17862/100000 [5:07:20<13:20:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17863/100000 [5:07:20<13:21:24,  1.71it/s]
Train steps ... :  18%|█▊        | 17864/100000 [5:07:21<13:21:30,  1.71it/s]
Train steps ... :  18%|█▊        | 17865/100000 [5:07:22<13:21:02,  1.71it/s]
Train steps ... :  18%|█▊        | 17866/100000 [5:07:22<13:22:01,  1.71it/s]
Train steps ... :  18%|█▊        | 17867/100000 [5:07:23<13:21:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17868/100000 [5:07:23<13:20:10,  1.71it/s]
Train steps ... :  18%|█▊        | 17869/100000 [5:07:24<13:20:41,  1.71it/s]
Train steps ... :  18%|█▊        | 17870/100000 [5:07:25<13:21:21,  1.71it/s]
Train steps ... :  18%|█▊        | 17871/100000 [5:07:25<13:21:25,  1.71it/s]
Train steps ... :  18%|█▊        | 17872/100000 [5:07:26<13:21:17,  1.71it/s]
Train steps ... :  18%|█▊        | 17873/100000 [5:07:26<13:22:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17874/100000 [5:07:27<13:20:13,  1.71it/s]
Train steps ... :  18%|█▊        | 17875/100000 [5:07:27<13:20:06,  1.71it/s]Step... (17875 / 100000 | Loss: 0.7808749675750732, Learning Rate: 8.253768844221106e-05)
+
                                                                             
Step... (17875 / 100000 | Loss: 1.268415093421936, Learning Rate: 8.253768844221106e-05)
+
Train steps ... :  18%|█▊        | 17875/100000 [5:07:28<13:20:06,  1.71it/s]
Train steps ... :  18%|█▊        | 17876/100000 [5:07:28<13:21:50,  1.71it/s]
Train steps ... :  18%|█▊        | 17877/100000 [5:07:29<13:20:50,  1.71it/s]
Train steps ... :  18%|█▊        | 17878/100000 [5:07:29<13:21:18,  1.71it/s]
Train steps ... :  18%|█▊        | 17879/100000 [5:07:30<13:20:48,  1.71it/s]
Train steps ... :  18%|█▊        | 17880/100000 [5:07:30<13:20:54,  1.71it/s]
Train steps ... :  18%|█▊        | 17881/100000 [5:07:31<13:20:03,  1.71it/s]
Train steps ... :  18%|█▊        | 17882/100000 [5:07:32<13:20:17,  1.71it/s]
Train steps ... :  18%|█▊        | 17883/100000 [5:07:32<13:19:58,  1.71it/s]
Train steps ... :  18%|█▊        | 17884/100000 [5:07:33<13:20:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17885/100000 [5:07:33<13:20:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17886/100000 [5:07:34<13:21:27,  1.71it/s]
Train steps ... :  18%|█▊        | 17887/100000 [5:07:34<13:20:14,  1.71it/s]
Train steps ... :  18%|█▊        | 17888/100000 [5:07:35<13:20:00,  1.71it/s]
Train steps ... :  18%|█▊        | 17889/100000 [5:07:36<13:21:33,  1.71it/s]
Train steps ... :  18%|█▊        | 17890/100000 [5:07:36<13:19:18,  1.71it/s]
Train steps ... :  18%|█▊        | 17891/100000 [5:07:37<13:19:42,  1.71it/s]
Train steps ... :  18%|█▊        | 17892/100000 [5:07:37<13:20:30,  1.71it/s]
Train steps ... :  18%|█▊        | 17893/100000 [5:07:38<13:21:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17894/100000 [5:07:39<13:19:26,  1.71it/s]
Train steps ... :  18%|█▊        | 17895/100000 [5:07:39<13:19:27,  1.71it/s]
Train steps ... :  18%|█▊        | 17896/100000 [5:07:40<13:21:56,  1.71it/s]
Train steps ... :  18%|█▊        | 17897/100000 [5:07:40<13:19:15,  1.71it/s]
Train steps ... :  18%|█▊        | 17898/100000 [5:07:41<13:18:57,  1.71it/s]
Train steps ... :  18%|█▊        | 17899/100000 [5:07:41<13:18:36,  1.71it/s]
Train steps ... :  18%|█▊        | 17900/100000 [5:07:42<13:20:12,  1.71it/s]Step... (17900 / 100000 | Loss: 0.8665341138839722, Learning Rate: 8.251256281407036e-05)
+
                                                                             
Step... (17900 / 100000 | Loss: 1.1810933351516724, Learning Rate: 8.251256281407036e-05)
+
Train steps ... :  18%|█▊        | 17900/100000 [5:07:42<13:20:12,  1.71it/s]
Train steps ... :  18%|█▊        | 17901/100000 [5:07:43<13:19:52,  1.71it/s]
Train steps ... :  18%|█▊        | 17902/100000 [5:07:43<13:18:48,  1.71it/s]
Train steps ... :  18%|█▊        | 17903/100000 [5:07:44<13:19:25,  1.71it/s]
Train steps ... :  18%|█▊        | 17904/100000 [5:07:44<13:20:14,  1.71it/s]
Train steps ... :  18%|█▊        | 17905/100000 [5:07:45<13:20:04,  1.71it/s]
Train steps ... :  18%|█▊        | 17906/100000 [5:07:46<13:19:45,  1.71it/s]
Train steps ... :  18%|█▊        | 17907/100000 [5:07:46<13:20:10,  1.71it/s]
Train steps ... :  18%|█▊        | 17908/100000 [5:07:47<13:20:25,  1.71it/s]
Train steps ... :  18%|█▊        | 17909/100000 [5:07:47<13:19:50,  1.71it/s]
Train steps ... :  18%|█▊        | 17910/100000 [5:07:48<13:22:09,  1.71it/s]
Train steps ... :  18%|█▊        | 17911/100000 [5:07:49<13:19:47,  1.71it/s]
Train steps ... :  18%|█▊        | 17912/100000 [5:07:49<13:20:38,  1.71it/s]
Train steps ... :  18%|█▊        | 17913/100000 [5:07:50<13:19:54,  1.71it/s]
Train steps ... :  18%|█▊        | 17914/100000 [5:07:50<13:20:28,  1.71it/s]
Train steps ... :  18%|█▊        | 17915/100000 [5:07:51<13:20:21,  1.71it/s]
Train steps ... :  18%|█▊        | 17916/100000 [5:07:51<13:19:40,  1.71it/s]
Train steps ... :  18%|█▊        | 17917/100000 [5:07:52<13:19:41,  1.71it/s]
Train steps ... :  18%|█▊        | 17918/100000 [5:07:53<13:19:07,  1.71it/s]
Train steps ... :  18%|█▊        | 17919/100000 [5:07:53<13:19:51,  1.71it/s]
Train steps ... :  18%|█▊        | 17920/100000 [5:07:54<13:19:50,  1.71it/s]
Train steps ... :  18%|█▊        | 17921/100000 [5:07:54<13:20:16,  1.71it/s]
Train steps ... :  18%|█▊        | 17922/100000 [5:07:55<13:19:56,  1.71it/s]
Train steps ... :  18%|█▊        | 17923/100000 [5:07:56<13:19:59,  1.71it/s]
Train steps ... :  18%|█▊        | 17924/100000 [5:07:56<13:20:55,  1.71it/s]
Train steps ... :  18%|█▊        | 17925/100000 [5:07:57<13:19:23,  1.71it/s]Step... (17925 / 100000 | Loss: 1.260741114616394, Learning Rate: 8.248743718592965e-05)
+
                                                                             
Step... (17925 / 100000 | Loss: 0.966032862663269, Learning Rate: 8.248743718592965e-05)
+
Train steps ... :  18%|█▊        | 17925/100000 [5:07:57<13:19:23,  1.71it/s]
Train steps ... :  18%|█▊        | 17926/100000 [5:07:57<13:19:28,  1.71it/s]
Train steps ... :  18%|█▊        | 17927/100000 [5:07:58<13:19:19,  1.71it/s]
Train steps ... :  18%|█▊        | 17928/100000 [5:07:58<13:19:29,  1.71it/s]
Train steps ... :  18%|█▊        | 17929/100000 [5:07:59<13:19:14,  1.71it/s]
Train steps ... :  18%|█▊        | 17930/100000 [5:08:00<13:19:02,  1.71it/s]
Train steps ... :  18%|█▊        | 17931/100000 [5:08:00<13:20:04,  1.71it/s]
Train steps ... :  18%|█▊        | 17932/100000 [5:08:01<13:20:27,  1.71it/s]
Train steps ... :  18%|█▊        | 17933/100000 [5:08:01<13:19:50,  1.71it/s]
Train steps ... :  18%|█▊        | 17934/100000 [5:08:02<13:20:13,  1.71it/s]
Train steps ... :  18%|█▊        | 17935/100000 [5:08:03<13:20:18,  1.71it/s]
Train steps ... :  18%|█▊        | 17936/100000 [5:08:03<13:20:25,  1.71it/s]
Train steps ... :  18%|█▊        | 17937/100000 [5:08:04<13:18:56,  1.71it/s]
Train steps ... :  18%|█▊        | 17938/100000 [5:08:04<13:19:26,  1.71it/s]
Train steps ... :  18%|█▊        | 17939/100000 [5:08:05<13:20:14,  1.71it/s]
Train steps ... :  18%|█▊        | 17940/100000 [5:08:05<13:21:22,  1.71it/s]
Train steps ... :  18%|█▊        | 17941/100000 [5:08:06<13:19:12,  1.71it/s]
Train steps ... :  18%|█▊        | 17942/100000 [5:08:07<13:18:33,  1.71it/s]
Train steps ... :  18%|█▊        | 17943/100000 [5:08:07<13:19:44,  1.71it/s]
Train steps ... :  18%|█▊        | 17944/100000 [5:08:08<13:19:29,  1.71it/s]
Train steps ... :  18%|█▊        | 17945/100000 [5:08:08<13:21:39,  1.71it/s]
Train steps ... :  18%|█▊        | 17946/100000 [5:08:09<13:20:33,  1.71it/s]
Train steps ... :  18%|█▊        | 17947/100000 [5:08:10<13:20:02,  1.71it/s]
Train steps ... :  18%|█▊        | 17948/100000 [5:08:10<13:19:45,  1.71it/s]
Train steps ... :  18%|█▊        | 17949/100000 [5:08:11<13:20:00,  1.71it/s]
Train steps ... :  18%|█▊        | 17950/100000 [5:08:11<13:20:10,  1.71it/s]Step... (17950 / 100000 | Loss: 0.8578602075576782, Learning Rate: 8.246231155778895e-05)
+
                                                                             
Step... (17950 / 100000 | Loss: 0.7631610035896301, Learning Rate: 8.246231155778895e-05)
+
Train steps ... :  18%|█▊        | 17950/100000 [5:08:12<13:20:10,  1.71it/s]
Train steps ... :  18%|█▊        | 17951/100000 [5:08:12<13:20:05,  1.71it/s]
Train steps ... :  18%|█▊        | 17952/100000 [5:08:12<13:20:59,  1.71it/s]
Train steps ... :  18%|█▊        | 17953/100000 [5:08:13<13:20:45,  1.71it/s]
Train steps ... :  18%|█▊        | 17954/100000 [5:08:14<13:20:28,  1.71it/s]
Train steps ... :  18%|█▊        | 17955/100000 [5:08:14<13:20:22,  1.71it/s]
Train steps ... :  18%|█▊        | 17956/100000 [5:08:15<13:20:36,  1.71it/s]
Train steps ... :  18%|█▊        | 17957/100000 [5:08:15<13:19:30,  1.71it/s]
Train steps ... :  18%|█▊        | 17958/100000 [5:08:16<13:19:24,  1.71it/s]
Train steps ... :  18%|█▊        | 17959/100000 [5:08:17<13:19:40,  1.71it/s]
Train steps ... :  18%|█▊        | 17960/100000 [5:08:17<13:21:31,  1.71it/s]
Train steps ... :  18%|█▊        | 17961/100000 [5:08:18<13:21:03,  1.71it/s]
Train steps ... :  18%|█▊        | 17962/100000 [5:08:18<13:20:43,  1.71it/s]
Train steps ... :  18%|█▊        | 17963/100000 [5:08:19<13:20:20,  1.71it/s]
Train steps ... :  18%|█▊        | 17964/100000 [5:08:20<13:20:46,  1.71it/s]
Train steps ... :  18%|█▊        | 17965/100000 [5:08:20<13:20:17,  1.71it/s]
Train steps ... :  18%|█▊        | 17966/100000 [5:08:21<13:20:37,  1.71it/s]
Train steps ... :  18%|█▊        | 17967/100000 [5:08:21<13:19:57,  1.71it/s]
Train steps ... :  18%|█▊        | 17968/100000 [5:08:22<13:21:46,  1.71it/s]
Train steps ... :  18%|█▊        | 17969/100000 [5:08:22<13:19:14,  1.71it/s]
Train steps ... :  18%|█▊        | 17970/100000 [5:08:23<13:22:54,  1.70it/s]
Train steps ... :  18%|█▊        | 17971/100000 [5:08:24<13:18:45,  1.71it/s]
Train steps ... :  18%|█▊        | 17972/100000 [5:08:24<13:19:56,  1.71it/s]
Train steps ... :  18%|█▊        | 17973/100000 [5:08:25<13:18:44,  1.71it/s]
Train steps ... :  18%|█▊        | 17974/100000 [5:08:25<13:20:06,  1.71it/s]
Train steps ... :  18%|█▊        | 17975/100000 [5:08:26<13:19:08,  1.71it/s]Step... (17975 / 100000 | Loss: 1.014901876449585, Learning Rate: 8.243718592964825e-05)
+
                                                                             
Step... (17975 / 100000 | Loss: 0.8177669048309326, Learning Rate: 8.243718592964825e-05)
+
Train steps ... :  18%|█▊        | 17975/100000 [5:08:26<13:19:08,  1.71it/s]
Train steps ... :  18%|█▊        | 17976/100000 [5:08:27<13:20:28,  1.71it/s]
Train steps ... :  18%|█▊        | 17977/100000 [5:08:27<13:21:48,  1.70it/s]
Train steps ... :  18%|█▊        | 17978/100000 [5:08:28<13:20:59,  1.71it/s]
Train steps ... :  18%|█▊        | 17979/100000 [5:08:28<13:20:06,  1.71it/s]
Train steps ... :  18%|█▊        | 17980/100000 [5:08:29<13:19:26,  1.71it/s]
Train steps ... :  18%|█▊        | 17981/100000 [5:08:29<13:19:27,  1.71it/s]
Train steps ... :  18%|█▊        | 17982/100000 [5:08:30<13:18:25,  1.71it/s]
Train steps ... :  18%|█▊        | 17983/100000 [5:08:31<13:19:52,  1.71it/s]
Train steps ... :  18%|█▊        | 17984/100000 [5:08:31<13:19:21,  1.71it/s]
Train steps ... :  18%|█▊        | 17985/100000 [5:08:32<13:18:17,  1.71it/s]
Train steps ... :  18%|█▊        | 17986/100000 [5:08:32<13:19:33,  1.71it/s]
Train steps ... :  18%|█▊        | 17987/100000 [5:08:33<13:21:15,  1.71it/s]
Train steps ... :  18%|█▊        | 17988/100000 [5:08:34<13:21:52,  1.70it/s]
Train steps ... :  18%|█▊        | 17989/100000 [5:08:34<13:20:51,  1.71it/s]
Train steps ... :  18%|█▊        | 17990/100000 [5:08:35<13:19:37,  1.71it/s]
Train steps ... :  18%|█▊        | 17991/100000 [5:08:35<13:21:29,  1.71it/s]
Train steps ... :  18%|█▊        | 17992/100000 [5:08:36<13:19:14,  1.71it/s]
Train steps ... :  18%|█▊        | 17993/100000 [5:08:36<13:19:59,  1.71it/s]
Train steps ... :  18%|█▊        | 17994/100000 [5:08:37<13:20:41,  1.71it/s]
Train steps ... :  18%|█▊        | 17995/100000 [5:08:38<13:19:56,  1.71it/s]
Train steps ... :  18%|█▊        | 17996/100000 [5:08:38<13:19:28,  1.71it/s]
Train steps ... :  18%|█▊        | 17997/100000 [5:08:39<13:19:27,  1.71it/s]
Train steps ... :  18%|█▊        | 17998/100000 [5:08:39<13:18:32,  1.71it/s]
Train steps ... :  18%|█▊        | 17999/100000 [5:08:40<13:21:32,  1.71it/s]
Train steps ... :  18%|█▊        | 18000/100000 [5:08:41<13:18:24,  1.71it/s]Step... (18000 / 100000 | Loss: 0.8652462959289551, Learning Rate: 8.241206030150754e-05)
+
                                                                             
Step... (18000 / 100000 | Loss: 1.274351954460144, Learning Rate: 8.241206030150754e-05)
+
Train steps ... :  18%|█▊        | 18000/100000 [5:08:41<13:18:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18001/100000 [5:08:41<13:18:56,  1.71it/s]
Train steps ... :  18%|█▊        | 18002/100000 [5:08:42<13:18:26,  1.71it/s]
Train steps ... :  18%|█▊        | 18003/100000 [5:08:42<13:18:33,  1.71it/s]
Train steps ... :  18%|█▊        | 18004/100000 [5:08:43<13:18:40,  1.71it/s]
Train steps ... :  18%|█▊        | 18005/100000 [5:08:44<13:18:28,  1.71it/s]
Train steps ... :  18%|█▊        | 18006/100000 [5:08:44<13:18:43,  1.71it/s]
Train steps ... :  18%|█▊        | 18007/100000 [5:08:45<13:18:42,  1.71it/s]
Train steps ... :  18%|█▊        | 18008/100000 [5:08:45<13:18:09,  1.71it/s]
Train steps ... :  18%|█▊        | 18009/100000 [5:08:46<13:19:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18010/100000 [5:08:46<13:18:48,  1.71it/s]
Train steps ... :  18%|█▊        | 18011/100000 [5:08:47<13:18:35,  1.71it/s]
Train steps ... :  18%|█▊        | 18012/100000 [5:08:48<13:17:38,  1.71it/s]
Train steps ... :  18%|█▊        | 18013/100000 [5:08:48<13:18:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18014/100000 [5:08:49<13:19:25,  1.71it/s]
Train steps ... :  18%|█▊        | 18015/100000 [5:08:49<13:20:03,  1.71it/s]
Train steps ... :  18%|█▊        | 18016/100000 [5:08:50<13:19:20,  1.71it/s]
Train steps ... :  18%|█▊        | 18017/100000 [5:08:51<13:19:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18018/100000 [5:08:51<13:18:41,  1.71it/s]
Train steps ... :  18%|█▊        | 18019/100000 [5:08:52<13:19:49,  1.71it/s]
Train steps ... :  18%|█▊        | 18020/100000 [5:08:52<13:19:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18021/100000 [5:08:53<13:18:50,  1.71it/s]
Train steps ... :  18%|█▊        | 18022/100000 [5:08:53<13:19:27,  1.71it/s]
Train steps ... :  18%|█▊        | 18023/100000 [5:08:54<13:19:29,  1.71it/s]
Train steps ... :  18%|█▊        | 18024/100000 [5:08:55<13:19:09,  1.71it/s]
Train steps ... :  18%|█▊        | 18025/100000 [5:08:55<13:18:31,  1.71it/s]Step... (18025 / 100000 | Loss: 0.8926382064819336, Learning Rate: 8.238693467336683e-05)
+
                                                                             
Step... (18025 / 100000 | Loss: 1.1256916522979736, Learning Rate: 8.238693467336683e-05)
+
Train steps ... :  18%|█▊        | 18025/100000 [5:08:56<13:18:31,  1.71it/s]
Train steps ... :  18%|█▊        | 18026/100000 [5:08:56<13:18:35,  1.71it/s]
Train steps ... :  18%|█▊        | 18027/100000 [5:08:56<13:19:50,  1.71it/s]
Train steps ... :  18%|█▊        | 18028/100000 [5:08:57<13:18:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18029/100000 [5:08:58<13:18:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18030/100000 [5:08:58<13:18:58,  1.71it/s]
Train steps ... :  18%|█▊        | 18031/100000 [5:08:59<13:20:35,  1.71it/s]
Train steps ... :  18%|█▊        | 18032/100000 [5:08:59<13:19:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18033/100000 [5:09:00<13:20:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18034/100000 [5:09:00<13:19:51,  1.71it/s]
Train steps ... :  18%|█▊        | 18035/100000 [5:09:01<13:19:46,  1.71it/s]
Train steps ... :  18%|█▊        | 18036/100000 [5:09:02<13:19:45,  1.71it/s]
Train steps ... :  18%|█▊        | 18037/100000 [5:09:02<13:19:36,  1.71it/s]
Train steps ... :  18%|█▊        | 18038/100000 [5:09:03<13:20:30,  1.71it/s]
Train steps ... :  18%|█▊        | 18039/100000 [5:09:03<13:19:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18040/100000 [5:09:04<13:23:47,  1.70it/s]
Train steps ... :  18%|█▊        | 18041/100000 [5:09:05<13:23:18,  1.70it/s]
Train steps ... :  18%|█▊        | 18042/100000 [5:09:05<13:23:21,  1.70it/s]
Train steps ... :  18%|█▊        | 18043/100000 [5:09:06<13:23:08,  1.70it/s]
Train steps ... :  18%|█▊        | 18044/100000 [5:09:06<13:24:47,  1.70it/s]
Train steps ... :  18%|█▊        | 18045/100000 [5:09:07<13:22:51,  1.70it/s]
Train steps ... :  18%|█▊        | 18046/100000 [5:09:08<13:25:20,  1.70it/s]
Train steps ... :  18%|█▊        | 18047/100000 [5:09:08<13:25:08,  1.70it/s]
Train steps ... :  18%|█▊        | 18048/100000 [5:09:09<13:22:35,  1.70it/s]
Train steps ... :  18%|█▊        | 18049/100000 [5:09:09<13:22:58,  1.70it/s]
Train steps ... :  18%|█▊        | 18050/100000 [5:09:10<13:20:37,  1.71it/s]Step... (18050 / 100000 | Loss: 0.9670225381851196, Learning Rate: 8.236180904522614e-05)
+
                                                                             
Step... (18050 / 100000 | Loss: 1.1553174257278442, Learning Rate: 8.236180904522614e-05)
+
Train steps ... :  18%|█▊        | 18050/100000 [5:09:10<13:20:37,  1.71it/s]
Train steps ... :  18%|█▊        | 18051/100000 [5:09:10<13:24:13,  1.70it/s]
Train steps ... :  18%|█▊        | 18052/100000 [5:09:11<13:21:20,  1.70it/s]
Train steps ... :  18%|█▊        | 18053/100000 [5:09:12<13:22:32,  1.70it/s]
Train steps ... :  18%|█▊        | 18054/100000 [5:09:12<13:19:51,  1.71it/s]
Train steps ... :  18%|█▊        | 18055/100000 [5:09:13<13:20:19,  1.71it/s]
Train steps ... :  18%|█▊        | 18056/100000 [5:09:13<13:20:27,  1.71it/s]
Train steps ... :  18%|█▊        | 18057/100000 [5:09:14<13:21:29,  1.70it/s]
Train steps ... :  18%|█▊        | 18058/100000 [5:09:15<13:22:08,  1.70it/s]
Train steps ... :  18%|█▊        | 18059/100000 [5:09:15<13:23:33,  1.70it/s]
Train steps ... :  18%|█▊        | 18060/100000 [5:09:16<13:19:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18061/100000 [5:09:16<13:22:57,  1.70it/s]
Train steps ... :  18%|█▊        | 18062/100000 [5:09:17<13:20:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18063/100000 [5:09:17<13:18:22,  1.71it/s]
Train steps ... :  18%|█▊        | 18064/100000 [5:09:18<13:20:50,  1.71it/s]
Train steps ... :  18%|█▊        | 18065/100000 [5:09:19<13:20:42,  1.71it/s]
Train steps ... :  18%|█▊        | 18066/100000 [5:09:19<13:20:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18067/100000 [5:09:20<13:19:41,  1.71it/s]
Train steps ... :  18%|█▊        | 18068/100000 [5:09:20<13:19:19,  1.71it/s]
Train steps ... :  18%|█▊        | 18069/100000 [5:09:21<13:20:07,  1.71it/s]
Train steps ... :  18%|█▊        | 18070/100000 [5:09:22<13:21:20,  1.70it/s]
Train steps ... :  18%|█▊        | 18071/100000 [5:09:22<13:19:57,  1.71it/s]
Train steps ... :  18%|█▊        | 18072/100000 [5:09:23<13:20:58,  1.70it/s]
Train steps ... :  18%|█▊        | 18073/100000 [5:09:23<13:19:20,  1.71it/s]
Train steps ... :  18%|█▊        | 18074/100000 [5:09:24<13:20:12,  1.71it/s]
Train steps ... :  18%|█▊        | 18075/100000 [5:09:25<13:20:25,  1.71it/s]Step... (18075 / 100000 | Loss: 1.4467816352844238, Learning Rate: 8.233668341708543e-05)
+
                                                                             
Step... (18075 / 100000 | Loss: 0.9392261505126953, Learning Rate: 8.233668341708543e-05)
+
Train steps ... :  18%|█▊        | 18075/100000 [5:09:25<13:20:25,  1.71it/s]
Train steps ... :  18%|█▊        | 18076/100000 [5:09:25<13:20:01,  1.71it/s]
Train steps ... :  18%|█▊        | 18077/100000 [5:09:26<13:20:11,  1.71it/s]
Train steps ... :  18%|█▊        | 18078/100000 [5:09:26<13:20:07,  1.71it/s]
Train steps ... :  18%|█▊        | 18079/100000 [5:09:27<13:18:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18080/100000 [5:09:27<13:19:13,  1.71it/s]
Train steps ... :  18%|█▊        | 18081/100000 [5:09:28<13:19:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18082/100000 [5:09:29<13:18:22,  1.71it/s]
Train steps ... :  18%|█▊        | 18083/100000 [5:09:29<13:19:26,  1.71it/s]
Train steps ... :  18%|█▊        | 18084/100000 [5:09:30<13:19:26,  1.71it/s]
Train steps ... :  18%|█▊        | 18085/100000 [5:09:30<13:19:17,  1.71it/s]
Train steps ... :  18%|█▊        | 18086/100000 [5:09:31<13:19:30,  1.71it/s]
Train steps ... :  18%|█▊        | 18087/100000 [5:09:32<13:19:15,  1.71it/s]
Train steps ... :  18%|█▊        | 18088/100000 [5:09:32<13:18:37,  1.71it/s]
Train steps ... :  18%|█▊        | 18089/100000 [5:09:33<13:18:50,  1.71it/s]
Train steps ... :  18%|█▊        | 18090/100000 [5:09:33<13:18:05,  1.71it/s]
Train steps ... :  18%|█▊        | 18091/100000 [5:09:34<13:18:19,  1.71it/s]
Train steps ... :  18%|█▊        | 18092/100000 [5:09:34<13:17:46,  1.71it/s]
Train steps ... :  18%|█▊        | 18093/100000 [5:09:35<13:18:04,  1.71it/s]
Train steps ... :  18%|█▊        | 18094/100000 [5:09:36<13:18:46,  1.71it/s]
Train steps ... :  18%|█▊        | 18095/100000 [5:09:36<13:17:52,  1.71it/s]
Train steps ... :  18%|█▊        | 18096/100000 [5:09:37<13:18:06,  1.71it/s]
Train steps ... :  18%|█▊        | 18097/100000 [5:09:37<13:18:00,  1.71it/s]
Train steps ... :  18%|█▊        | 18098/100000 [5:09:38<13:17:42,  1.71it/s]
Train steps ... :  18%|█▊        | 18099/100000 [5:09:39<13:17:12,  1.71it/s]
Train steps ... :  18%|█▊        | 18100/100000 [5:09:39<13:17:01,  1.71it/s]Step... (18100 / 100000 | Loss: 0.956849217414856, Learning Rate: 8.231155778894473e-05)
+
                                                                             
Step... (18100 / 100000 | Loss: 1.390987753868103, Learning Rate: 8.231155778894473e-05)
+
Train steps ... :  18%|█▊        | 18100/100000 [5:09:39<13:17:01,  1.71it/s]
Train steps ... :  18%|█▊        | 18101/100000 [5:09:40<13:17:05,  1.71it/s]
Train steps ... :  18%|█▊        | 18102/100000 [5:09:40<13:19:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18103/100000 [5:09:41<13:17:40,  1.71it/s]
Train steps ... :  18%|█▊        | 18104/100000 [5:09:41<13:17:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18105/100000 [5:09:42<13:17:42,  1.71it/s]
Train steps ... :  18%|█▊        | 18106/100000 [5:09:43<13:18:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18107/100000 [5:09:43<13:18:02,  1.71it/s]
Train steps ... :  18%|█▊        | 18108/100000 [5:09:44<13:18:44,  1.71it/s]
Train steps ... :  18%|█▊        | 18109/100000 [5:09:44<13:19:01,  1.71it/s]
Train steps ... :  18%|█▊        | 18110/100000 [5:09:45<13:21:36,  1.70it/s]
Train steps ... :  18%|█▊        | 18111/100000 [5:09:46<13:19:22,  1.71it/s]
Train steps ... :  18%|█▊        | 18112/100000 [5:09:46<13:19:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18113/100000 [5:09:47<13:18:49,  1.71it/s]
Train steps ... :  18%|█▊        | 18114/100000 [5:09:47<13:19:17,  1.71it/s]
Train steps ... :  18%|█▊        | 18115/100000 [5:09:48<13:18:56,  1.71it/s]
Train steps ... :  18%|█▊        | 18116/100000 [5:09:49<13:19:17,  1.71it/s]
Train steps ... :  18%|█▊        | 18117/100000 [5:09:49<13:18:56,  1.71it/s]
Train steps ... :  18%|█▊        | 18118/100000 [5:09:50<13:18:38,  1.71it/s]
Train steps ... :  18%|█▊        | 18119/100000 [5:09:50<13:18:37,  1.71it/s]
Train steps ... :  18%|█▊        | 18120/100000 [5:09:51<13:17:49,  1.71it/s]
Train steps ... :  18%|█▊        | 18121/100000 [5:09:51<13:17:30,  1.71it/s]
Train steps ... :  18%|█▊        | 18122/100000 [5:09:52<13:17:05,  1.71it/s]
Train steps ... :  18%|█▊        | 18123/100000 [5:09:53<13:17:06,  1.71it/s]
Train steps ... :  18%|█▊        | 18124/100000 [5:09:53<13:17:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18125/100000 [5:09:54<13:17:40,  1.71it/s]Step... (18125 / 100000 | Loss: 0.9114012718200684, Learning Rate: 8.228643216080403e-05)
+
                                                                             
Step... (18125 / 100000 | Loss: 1.1172066926956177, Learning Rate: 8.228643216080403e-05)
+
Train steps ... :  18%|█▊        | 18125/100000 [5:09:54<13:17:40,  1.71it/s]
Train steps ... :  18%|█▊        | 18126/100000 [5:09:54<13:18:01,  1.71it/s]
Train steps ... :  18%|█▊        | 18127/100000 [5:09:55<13:17:32,  1.71it/s]
Train steps ... :  18%|█▊        | 18128/100000 [5:09:56<13:18:48,  1.71it/s]
Train steps ... :  18%|█▊        | 18129/100000 [5:09:56<13:18:25,  1.71it/s]
Train steps ... :  18%|█▊        | 18130/100000 [5:09:57<13:18:21,  1.71it/s]
Train steps ... :  18%|█▊        | 18131/100000 [5:09:57<13:17:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18132/100000 [5:09:58<13:19:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18133/100000 [5:09:58<13:18:36,  1.71it/s]
Train steps ... :  18%|█▊        | 18134/100000 [5:09:59<13:18:32,  1.71it/s]
Train steps ... :  18%|█▊        | 18135/100000 [5:10:00<13:17:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18136/100000 [5:10:00<13:17:36,  1.71it/s]
Train steps ... :  18%|█▊        | 18137/100000 [5:10:01<13:18:50,  1.71it/s]
Train steps ... :  18%|█▊        | 18138/100000 [5:10:01<13:20:03,  1.71it/s]
Train steps ... :  18%|█▊        | 18139/100000 [5:10:02<13:17:53,  1.71it/s]
Train steps ... :  18%|█▊        | 18140/100000 [5:10:03<13:18:03,  1.71it/s]
Train steps ... :  18%|█▊        | 18141/100000 [5:10:03<13:17:37,  1.71it/s]
Train steps ... :  18%|█▊        | 18142/100000 [5:10:04<13:17:12,  1.71it/s]
Train steps ... :  18%|█▊        | 18143/100000 [5:10:04<13:16:32,  1.71it/s]
Train steps ... :  18%|█▊        | 18144/100000 [5:10:05<13:16:44,  1.71it/s]
Train steps ... :  18%|█▊        | 18145/100000 [5:10:05<13:18:46,  1.71it/s]
Train steps ... :  18%|█▊        | 18146/100000 [5:10:06<13:19:20,  1.71it/s]
Train steps ... :  18%|█▊        | 18147/100000 [5:10:07<13:19:30,  1.71it/s]
Train steps ... :  18%|█▊        | 18148/100000 [5:10:07<13:18:17,  1.71it/s]
Train steps ... :  18%|█▊        | 18149/100000 [5:10:08<13:18:46,  1.71it/s]
Train steps ... :  18%|█▊        | 18150/100000 [5:10:08<13:18:19,  1.71it/s]Step... (18150 / 100000 | Loss: 0.9851399660110474, Learning Rate: 8.226130653266332e-05)
+
                                                                             
Step... (18150 / 100000 | Loss: 1.3511831760406494, Learning Rate: 8.226130653266332e-05)
+
Train steps ... :  18%|█▊        | 18150/100000 [5:10:09<13:18:19,  1.71it/s]
Train steps ... :  18%|█▊        | 18151/100000 [5:10:09<13:19:23,  1.71it/s]
Train steps ... :  18%|█▊        | 18152/100000 [5:10:10<13:18:41,  1.71it/s]
Train steps ... :  18%|█▊        | 18153/100000 [5:10:10<13:18:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18154/100000 [5:10:11<13:17:36,  1.71it/s]
Train steps ... :  18%|█▊        | 18155/100000 [5:10:11<13:18:12,  1.71it/s]
Train steps ... :  18%|█▊        | 18156/100000 [5:10:12<13:17:40,  1.71it/s]
Train steps ... :  18%|█▊        | 18157/100000 [5:10:12<13:17:05,  1.71it/s]
Train steps ... :  18%|█▊        | 18158/100000 [5:10:13<13:16:51,  1.71it/s]
Train steps ... :  18%|█▊        | 18159/100000 [5:10:14<13:17:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18160/100000 [5:10:14<13:17:21,  1.71it/s]
Train steps ... :  18%|█▊        | 18161/100000 [5:10:15<13:17:16,  1.71it/s]
Train steps ... :  18%|█▊        | 18162/100000 [5:10:15<13:17:56,  1.71it/s]
Train steps ... :  18%|█▊        | 18163/100000 [5:10:16<13:17:11,  1.71it/s]
Train steps ... :  18%|█▊        | 18164/100000 [5:10:17<13:17:05,  1.71it/s]
Train steps ... :  18%|█▊        | 18165/100000 [5:10:17<13:18:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18166/100000 [5:10:18<13:18:15,  1.71it/s]
Train steps ... :  18%|█▊        | 18167/100000 [5:10:18<13:18:44,  1.71it/s]
Train steps ... :  18%|█▊        | 18168/100000 [5:10:19<13:20:12,  1.70it/s]
Train steps ... :  18%|█▊        | 18169/100000 [5:10:20<13:19:16,  1.71it/s]
Train steps ... :  18%|█▊        | 18170/100000 [5:10:20<13:18:44,  1.71it/s]
Train steps ... :  18%|█▊        | 18171/100000 [5:10:21<13:18:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18172/100000 [5:10:21<13:18:15,  1.71it/s]
Train steps ... :  18%|█▊        | 18173/100000 [5:10:22<13:18:09,  1.71it/s]
Train steps ... :  18%|█▊        | 18174/100000 [5:10:22<13:18:10,  1.71it/s]
Train steps ... :  18%|█▊        | 18175/100000 [5:10:23<13:18:59,  1.71it/s]Step... (18175 / 100000 | Loss: 1.1986992359161377, Learning Rate: 8.223618090452262e-05)
+
                                                                             
Step... (18175 / 100000 | Loss: 0.8395127654075623, Learning Rate: 8.223618090452262e-05)
+
Train steps ... :  18%|█▊        | 18175/100000 [5:10:23<13:18:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18176/100000 [5:10:24<13:18:32,  1.71it/s]
Train steps ... :  18%|█▊        | 18177/100000 [5:10:24<13:18:05,  1.71it/s]
Train steps ... :  18%|█▊        | 18178/100000 [5:10:25<13:19:06,  1.71it/s]
Train steps ... :  18%|█▊        | 18179/100000 [5:10:25<13:19:21,  1.71it/s]
Train steps ... :  18%|█▊        | 18180/100000 [5:10:26<13:18:57,  1.71it/s]
Train steps ... :  18%|█▊        | 18181/100000 [5:10:27<13:20:52,  1.70it/s]
Train steps ... :  18%|█▊        | 18182/100000 [5:10:27<13:19:51,  1.70it/s]
Train steps ... :  18%|█▊        | 18183/100000 [5:10:28<13:20:13,  1.70it/s]
Train steps ... :  18%|█▊        | 18184/100000 [5:10:28<13:18:52,  1.71it/s]
Train steps ... :  18%|█▊        | 18185/100000 [5:10:29<13:19:38,  1.71it/s]
Train steps ... :  18%|█▊        | 18186/100000 [5:10:29<13:19:07,  1.71it/s]
Train steps ... :  18%|█▊        | 18187/100000 [5:10:30<13:21:23,  1.70it/s]
Train steps ... :  18%|█▊        | 18188/100000 [5:10:31<13:18:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18189/100000 [5:10:31<13:18:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18190/100000 [5:10:32<13:17:32,  1.71it/s]
Train steps ... :  18%|█▊        | 18191/100000 [5:10:32<13:21:04,  1.70it/s]
Train steps ... :  18%|█▊        | 18192/100000 [5:10:33<13:19:41,  1.70it/s]
Train steps ... :  18%|█▊        | 18193/100000 [5:10:34<13:20:05,  1.70it/s]
Train steps ... :  18%|█▊        | 18194/100000 [5:10:34<13:18:57,  1.71it/s]
Train steps ... :  18%|█▊        | 18195/100000 [5:10:35<13:19:09,  1.71it/s]
Train steps ... :  18%|█▊        | 18196/100000 [5:10:35<13:19:55,  1.70it/s]
Train steps ... :  18%|█▊        | 18197/100000 [5:10:36<13:19:12,  1.71it/s]
Train steps ... :  18%|█▊        | 18198/100000 [5:10:37<13:19:32,  1.71it/s]
Train steps ... :  18%|█▊        | 18199/100000 [5:10:37<13:18:33,  1.71it/s]
Train steps ... :  18%|█▊        | 18200/100000 [5:10:38<13:19:31,  1.71it/s]Step... (18200 / 100000 | Loss: 1.1384066343307495, Learning Rate: 8.22110552763819e-05)
+
                                                                             
Step... (18200 / 100000 | Loss: 0.9872628450393677, Learning Rate: 8.22110552763819e-05)
+
Train steps ... :  18%|█▊        | 18200/100000 [5:10:38<13:19:31,  1.71it/s]
Train steps ... :  18%|█▊        | 18201/100000 [5:10:38<13:19:01,  1.71it/s]
Train steps ... :  18%|█▊        | 18202/100000 [5:10:39<13:18:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18203/100000 [5:10:39<13:21:27,  1.70it/s]
Train steps ... :  18%|█▊        | 18204/100000 [5:10:40<13:20:05,  1.70it/s]
Train steps ... :  18%|█▊        | 18205/100000 [5:10:41<13:18:52,  1.71it/s]
Train steps ... :  18%|█▊        | 18206/100000 [5:10:41<13:19:11,  1.71it/s]
Train steps ... :  18%|█▊        | 18207/100000 [5:10:42<13:19:59,  1.70it/s]
Train steps ... :  18%|█▊        | 18208/100000 [5:10:42<13:16:33,  1.71it/s]
Train steps ... :  18%|█▊        | 18209/100000 [5:10:43<13:17:22,  1.71it/s]
Train steps ... :  18%|█▊        | 18210/100000 [5:10:44<13:17:06,  1.71it/s]
Train steps ... :  18%|█▊        | 18211/100000 [5:10:44<13:16:57,  1.71it/s]
Train steps ... :  18%|█▊        | 18212/100000 [5:10:45<13:17:10,  1.71it/s]
Train steps ... :  18%|█▊        | 18213/100000 [5:10:45<13:17:35,  1.71it/s]
Train steps ... :  18%|█▊        | 18214/100000 [5:10:46<13:17:09,  1.71it/s]
Train steps ... :  18%|█▊        | 18215/100000 [5:10:46<13:17:34,  1.71it/s]
Train steps ... :  18%|█▊        | 18216/100000 [5:10:47<13:17:09,  1.71it/s]
Train steps ... :  18%|█▊        | 18217/100000 [5:10:48<13:16:34,  1.71it/s]
Train steps ... :  18%|█▊        | 18218/100000 [5:10:48<13:16:12,  1.71it/s]
Train steps ... :  18%|█▊        | 18219/100000 [5:10:49<13:16:52,  1.71it/s]
Train steps ... :  18%|█▊        | 18220/100000 [5:10:49<13:16:22,  1.71it/s]
Train steps ... :  18%|█▊        | 18221/100000 [5:10:50<13:17:20,  1.71it/s]
Train steps ... :  18%|█▊        | 18222/100000 [5:10:51<13:16:44,  1.71it/s]
Train steps ... :  18%|█▊        | 18223/100000 [5:10:51<13:16:12,  1.71it/s]
Train steps ... :  18%|█▊        | 18224/100000 [5:10:52<13:16:35,  1.71it/s]
Train steps ... :  18%|█▊        | 18225/100000 [5:10:52<13:15:55,  1.71it/s]Step... (18225 / 100000 | Loss: 0.9814021587371826, Learning Rate: 8.218592964824121e-05)
+
                                                                             
Step... (18225 / 100000 | Loss: 1.5004335641860962, Learning Rate: 8.218592964824121e-05)
+
Train steps ... :  18%|█▊        | 18225/100000 [5:10:53<13:15:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18226/100000 [5:10:53<13:17:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18227/100000 [5:10:53<13:18:03,  1.71it/s]
Train steps ... :  18%|█▊        | 18228/100000 [5:10:54<13:17:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18229/100000 [5:10:55<13:16:43,  1.71it/s]
Train steps ... :  18%|█▊        | 18230/100000 [5:10:55<13:16:29,  1.71it/s]
Train steps ... :  18%|█▊        | 18231/100000 [5:10:56<13:17:33,  1.71it/s]
Train steps ... :  18%|█▊        | 18232/100000 [5:10:56<13:17:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18233/100000 [5:10:57<13:17:51,  1.71it/s]
Train steps ... :  18%|█▊        | 18234/100000 [5:10:58<13:17:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18235/100000 [5:10:58<13:17:41,  1.71it/s]
Train steps ... :  18%|█▊        | 18236/100000 [5:10:59<13:17:16,  1.71it/s]
Train steps ... :  18%|█▊        | 18237/100000 [5:10:59<13:17:14,  1.71it/s]
Train steps ... :  18%|█▊        | 18238/100000 [5:11:00<13:17:51,  1.71it/s]
Train steps ... :  18%|█▊        | 18239/100000 [5:11:01<13:16:47,  1.71it/s]
Train steps ... :  18%|█▊        | 18240/100000 [5:11:01<13:16:15,  1.71it/s]
Train steps ... :  18%|█▊        | 18241/100000 [5:11:02<13:16:10,  1.71it/s]
Train steps ... :  18%|█▊        | 18242/100000 [5:11:02<13:15:51,  1.71it/s]
Train steps ... :  18%|█▊        | 18243/100000 [5:11:03<13:15:34,  1.71it/s]
Train steps ... :  18%|█▊        | 18244/100000 [5:11:03<13:17:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18245/100000 [5:11:04<13:16:54,  1.71it/s]
Train steps ... :  18%|█▊        | 18246/100000 [5:11:05<13:16:26,  1.71it/s]
Train steps ... :  18%|█▊        | 18247/100000 [5:11:05<13:16:33,  1.71it/s]
Train steps ... :  18%|█▊        | 18248/100000 [5:11:06<13:16:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18249/100000 [5:11:06<13:17:01,  1.71it/s]
Train steps ... :  18%|█▊        | 18250/100000 [5:11:07<13:16:20,  1.71it/s]Step... (18250 / 100000 | Loss: 1.2734272480010986, Learning Rate: 8.21608040201005e-05)
+
                                                                             
Step... (18250 / 100000 | Loss: 0.8540000915527344, Learning Rate: 8.21608040201005e-05)
+
Train steps ... :  18%|█▊        | 18250/100000 [5:11:07<13:16:20,  1.71it/s]
Train steps ... :  18%|█▊        | 18251/100000 [5:11:08<13:16:49,  1.71it/s]
Train steps ... :  18%|█▊        | 18252/100000 [5:11:08<13:16:42,  1.71it/s]
Train steps ... :  18%|█▊        | 18253/100000 [5:11:09<13:16:23,  1.71it/s]
Train steps ... :  18%|█▊        | 18254/100000 [5:11:09<13:16:34,  1.71it/s]
Train steps ... :  18%|█▊        | 18255/100000 [5:11:10<13:16:53,  1.71it/s]
Train steps ... :  18%|█▊        | 18256/100000 [5:11:10<13:16:28,  1.71it/s]
Train steps ... :  18%|█▊        | 18257/100000 [5:11:11<13:17:10,  1.71it/s]
Train steps ... :  18%|█▊        | 18258/100000 [5:11:12<13:18:00,  1.71it/s]
Train steps ... :  18%|█▊        | 18259/100000 [5:11:12<13:17:06,  1.71it/s]
Train steps ... :  18%|█▊        | 18260/100000 [5:11:13<13:16:21,  1.71it/s]
Train steps ... :  18%|█▊        | 18261/100000 [5:11:13<13:17:03,  1.71it/s]
Train steps ... :  18%|█▊        | 18262/100000 [5:11:14<13:15:56,  1.71it/s]
Train steps ... :  18%|█▊        | 18263/100000 [5:11:15<13:16:04,  1.71it/s]
Train steps ... :  18%|█▊        | 18264/100000 [5:11:15<13:15:58,  1.71it/s]
Train steps ... :  18%|█▊        | 18265/100000 [5:11:16<13:15:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18266/100000 [5:11:16<13:15:30,  1.71it/s]
Train steps ... :  18%|█▊        | 18267/100000 [5:11:17<13:16:57,  1.71it/s]
Train steps ... :  18%|█▊        | 18268/100000 [5:11:17<13:15:57,  1.71it/s]
Train steps ... :  18%|█▊        | 18269/100000 [5:11:18<13:16:04,  1.71it/s]
Train steps ... :  18%|█▊        | 18270/100000 [5:11:19<13:16:41,  1.71it/s]
Train steps ... :  18%|█▊        | 18271/100000 [5:11:19<13:16:13,  1.71it/s]
Train steps ... :  18%|█▊        | 18272/100000 [5:11:20<13:16:44,  1.71it/s]
Train steps ... :  18%|█▊        | 18273/100000 [5:11:20<13:16:58,  1.71it/s]
Train steps ... :  18%|█▊        | 18274/100000 [5:11:21<13:16:23,  1.71it/s]
Train steps ... :  18%|█▊        | 18275/100000 [5:11:22<13:15:49,  1.71it/s]Step... (18275 / 100000 | Loss: 1.043967843055725, Learning Rate: 8.213567839195981e-05)
+
                                                                             
Step... (18275 / 100000 | Loss: 1.2347556352615356, Learning Rate: 8.213567839195981e-05)
+
Train steps ... :  18%|█▊        | 18275/100000 [5:11:22<13:15:49,  1.71it/s]
Train steps ... :  18%|█▊        | 18276/100000 [5:11:22<13:16:14,  1.71it/s]
Train steps ... :  18%|█▊        | 18277/100000 [5:11:23<13:16:20,  1.71it/s]
Train steps ... :  18%|█▊        | 18278/100000 [5:11:23<13:16:15,  1.71it/s]
Train steps ... :  18%|█▊        | 18279/100000 [5:11:24<13:15:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18280/100000 [5:11:24<13:15:49,  1.71it/s]
Train steps ... :  18%|█▊        | 18281/100000 [5:11:25<13:16:14,  1.71it/s]
Train steps ... :  18%|█▊        | 18282/100000 [5:11:26<13:16:07,  1.71it/s]
Train steps ... :  18%|█▊        | 18283/100000 [5:11:26<13:16:10,  1.71it/s]
Train steps ... :  18%|█▊        | 18284/100000 [5:11:27<13:15:42,  1.71it/s]
Train steps ... :  18%|█▊        | 18285/100000 [5:11:27<13:15:16,  1.71it/s]
Train steps ... :  18%|█▊        | 18286/100000 [5:11:28<13:15:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18287/100000 [5:11:29<13:15:15,  1.71it/s]
Train steps ... :  18%|█▊        | 18288/100000 [5:11:29<13:14:57,  1.71it/s]
Train steps ... :  18%|█▊        | 18289/100000 [5:11:30<13:14:45,  1.71it/s]
Train steps ... :  18%|█▊        | 18290/100000 [5:11:30<13:15:27,  1.71it/s]
Train steps ... :  18%|█▊        | 18291/100000 [5:11:31<13:15:53,  1.71it/s]
Train steps ... :  18%|█▊        | 18292/100000 [5:11:31<13:15:38,  1.71it/s]
Train steps ... :  18%|█▊        | 18293/100000 [5:11:32<13:15:54,  1.71it/s]
Train steps ... :  18%|█▊        | 18294/100000 [5:11:33<13:16:25,  1.71it/s]
Train steps ... :  18%|█▊        | 18295/100000 [5:11:33<13:15:44,  1.71it/s]
Train steps ... :  18%|█▊        | 18296/100000 [5:11:34<13:16:06,  1.71it/s]
Train steps ... :  18%|█▊        | 18297/100000 [5:11:34<13:15:37,  1.71it/s]
Train steps ... :  18%|█▊        | 18298/100000 [5:11:35<13:15:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18299/100000 [5:11:36<13:16:22,  1.71it/s]
Train steps ... :  18%|��▊        | 18300/100000 [5:11:36<13:16:07,  1.71it/s]Step... (18300 / 100000 | Loss: 0.865938663482666, Learning Rate: 8.21105527638191e-05)
+
                                                                             
Step... (18300 / 100000 | Loss: 0.9948369860649109, Learning Rate: 8.21105527638191e-05)
+
Train steps ... :  18%|█▊        | 18300/100000 [5:11:36<13:16:07,  1.71it/s]
Train steps ... :  18%|█▊        | 18301/100000 [5:11:37<13:15:56,  1.71it/s]
Train steps ... :  18%|█▊        | 18302/100000 [5:11:37<13:16:54,  1.71it/s]
Train steps ... :  18%|█▊        | 18303/100000 [5:11:38<13:16:46,  1.71it/s]
Train steps ... :  18%|█▊        | 18304/100000 [5:11:39<13:16:42,  1.71it/s]
Train steps ... :  18%|█▊        | 18305/100000 [5:11:39<13:16:54,  1.71it/s]
Train steps ... :  18%|█▊        | 18306/100000 [5:11:40<13:18:04,  1.71it/s]
Train steps ... :  18%|█▊        | 18307/100000 [5:11:40<13:18:04,  1.71it/s]
Train steps ... :  18%|█▊        | 18308/100000 [5:11:41<13:16:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18309/100000 [5:11:41<13:16:33,  1.71it/s]
Train steps ... :  18%|█▊        | 18310/100000 [5:11:42<13:15:49,  1.71it/s]
Train steps ... :  18%|█▊        | 18311/100000 [5:11:43<13:16:23,  1.71it/s]
Train steps ... :  18%|█▊        | 18312/100000 [5:11:43<13:16:33,  1.71it/s]
Train steps ... :  18%|█▊        | 18313/100000 [5:11:44<13:16:44,  1.71it/s]
Train steps ... :  18%|█▊        | 18314/100000 [5:11:44<13:16:34,  1.71it/s]
Train steps ... :  18%|█▊        | 18315/100000 [5:11:45<13:15:54,  1.71it/s]
Train steps ... :  18%|█▊        | 18316/100000 [5:11:46<13:15:33,  1.71it/s]
Train steps ... :  18%|█▊        | 18317/100000 [5:11:46<13:16:35,  1.71it/s]
Train steps ... :  18%|█▊        | 18318/100000 [5:11:47<13:16:10,  1.71it/s]
Train steps ... :  18%|█▊        | 18319/100000 [5:11:47<13:17:03,  1.71it/s]
Train steps ... :  18%|█▊        | 18320/100000 [5:11:48<13:15:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18321/100000 [5:11:48<13:15:37,  1.71it/s]
Train steps ... :  18%|█▊        | 18322/100000 [5:11:49<13:14:45,  1.71it/s]
Train steps ... :  18%|█▊        | 18323/100000 [5:11:50<13:14:58,  1.71it/s]
Train steps ... :  18%|█▊        | 18324/100000 [5:11:50<13:14:51,  1.71it/s]
Train steps ... :  18%|█▊        | 18325/100000 [5:11:51<13:14:49,  1.71it/s]Step... (18325 / 100000 | Loss: 1.0059181451797485, Learning Rate: 8.20854271356784e-05)
+
                                                                             
Step... (18325 / 100000 | Loss: 0.8935027122497559, Learning Rate: 8.20854271356784e-05)
+
Train steps ... :  18%|█▊        | 18325/100000 [5:11:51<13:14:49,  1.71it/s]
Train steps ... :  18%|█▊        | 18326/100000 [5:11:51<13:15:00,  1.71it/s]
Train steps ... :  18%|█▊        | 18327/100000 [5:11:52<13:15:47,  1.71it/s]
Train steps ... :  18%|█▊        | 18328/100000 [5:11:53<13:16:45,  1.71it/s]
Train steps ... :  18%|█▊        | 18329/100000 [5:11:53<13:15:52,  1.71it/s]
Train steps ... :  18%|█▊        | 18330/100000 [5:11:54<13:16:17,  1.71it/s]
Train steps ... :  18%|█▊        | 18331/100000 [5:11:54<13:15:09,  1.71it/s]
Train steps ... :  18%|█▊        | 18332/100000 [5:11:55<13:14:50,  1.71it/s]
Train steps ... :  18%|█▊        | 18333/100000 [5:11:55<13:14:35,  1.71it/s]
Train steps ... :  18%|█▊        | 18334/100000 [5:11:56<13:14:53,  1.71it/s]
Train steps ... :  18%|█▊        | 18335/100000 [5:11:57<13:14:51,  1.71it/s]
Train steps ... :  18%|█▊        | 18336/100000 [5:11:57<13:14:45,  1.71it/s]
Train steps ... :  18%|█▊        | 18337/100000 [5:11:58<13:16:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18338/100000 [5:11:58<13:15:49,  1.71it/s]
Train steps ... :  18%|█▊        | 18339/100000 [5:11:59<13:17:23,  1.71it/s]
Train steps ... :  18%|█▊        | 18340/100000 [5:12:00<13:14:58,  1.71it/s]
Train steps ... :  18%|█▊        | 18341/100000 [5:12:00<13:15:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18342/100000 [5:12:01<13:14:40,  1.71it/s]
Train steps ... :  18%|█▊        | 18343/100000 [5:12:01<13:14:54,  1.71it/s]
Train steps ... :  18%|█▊        | 18344/100000 [5:12:02<13:15:05,  1.71it/s]
Train steps ... :  18%|█▊        | 18345/100000 [5:12:02<13:15:23,  1.71it/s]
Train steps ... :  18%|█▊        | 18346/100000 [5:12:03<13:14:35,  1.71it/s]
Train steps ... :  18%|█▊        | 18347/100000 [5:12:04<13:15:14,  1.71it/s]
Train steps ... :  18%|█▊        | 18348/100000 [5:12:04<13:15:40,  1.71it/s]
Train steps ... :  18%|█▊        | 18349/100000 [5:12:05<13:15:28,  1.71it/s]
Train steps ... :  18%|█▊        | 18350/100000 [5:12:05<13:15:30,  1.71it/s]Step... (18350 / 100000 | Loss: 0.8760055899620056, Learning Rate: 8.20603015075377e-05)
+
                                                                             
Step... (18350 / 100000 | Loss: 1.4406296014785767, Learning Rate: 8.20603015075377e-05)
+
Train steps ... :  18%|█▊        | 18350/100000 [5:12:06<13:15:30,  1.71it/s]
Train steps ... :  18%|█▊        | 18351/100000 [5:12:06<13:16:01,  1.71it/s]
Train steps ... :  18%|█▊        | 18352/100000 [5:12:07<13:16:02,  1.71it/s]
Train steps ... :  18%|█▊        | 18353/100000 [5:12:07<13:16:50,  1.71it/s]
Train steps ... :  18%|█▊        | 18354/100000 [5:12:08<13:16:22,  1.71it/s]
Train steps ... :  18%|█▊        | 18355/100000 [5:12:08<13:18:27,  1.70it/s]
Train steps ... :  18%|█▊        | 18356/100000 [5:12:09<13:17:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18357/100000 [5:12:10<13:16:56,  1.71it/s]
Train steps ... :  18%|█▊        | 18358/100000 [5:12:10<13:19:42,  1.70it/s]
Train steps ... :  18%|█▊        | 18359/100000 [5:12:11<13:18:27,  1.70it/s]
Train steps ... :  18%|█▊        | 18360/100000 [5:12:11<13:18:50,  1.70it/s]
Train steps ... :  18%|█▊        | 18361/100000 [5:12:12<13:17:42,  1.71it/s]
Train steps ... :  18%|█▊        | 18362/100000 [5:12:12<13:16:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18363/100000 [5:12:13<13:16:35,  1.71it/s]
Train steps ... :  18%|█▊        | 18364/100000 [5:12:14<13:15:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18365/100000 [5:12:14<13:16:11,  1.71it/s]
Train steps ... :  18%|█▊        | 18366/100000 [5:12:15<13:15:53,  1.71it/s]
Train steps ... :  18%|█▊        | 18367/100000 [5:12:15<13:17:00,  1.71it/s]
Train steps ... :  18%|█▊        | 18368/100000 [5:12:16<13:15:48,  1.71it/s]
Train steps ... :  18%|█▊        | 18369/100000 [5:12:17<13:16:43,  1.71it/s]
Train steps ... :  18%|█▊        | 18370/100000 [5:12:17<13:15:46,  1.71it/s]
Train steps ... :  18%|█▊        | 18371/100000 [5:12:18<13:18:51,  1.70it/s]
Train steps ... :  18%|█▊        | 18372/100000 [5:12:18<13:18:20,  1.70it/s]
Train steps ... :  18%|█▊        | 18373/100000 [5:12:19<13:16:51,  1.71it/s]
Train steps ... :  18%|█▊        | 18374/100000 [5:12:19<13:15:56,  1.71it/s]
Train steps ... :  18%|█▊        | 18375/100000 [5:12:20<13:15:34,  1.71it/s]Step... (18375 / 100000 | Loss: 1.319899320602417, Learning Rate: 8.203517587939698e-05)
+
                                                                             
Step... (18375 / 100000 | Loss: 1.1618525981903076, Learning Rate: 8.203517587939698e-05)
+
Train steps ... :  18%|█▊        | 18375/100000 [5:12:20<13:15:34,  1.71it/s]
Train steps ... :  18%|█▊        | 18376/100000 [5:12:21<13:15:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18377/100000 [5:12:21<13:14:54,  1.71it/s]
Train steps ... :  18%|█▊        | 18378/100000 [5:12:22<13:15:41,  1.71it/s]
Train steps ... :  18%|█▊        | 18379/100000 [5:12:22<13:15:22,  1.71it/s]
Train steps ... :  18%|█▊        | 18380/100000 [5:12:23<13:15:58,  1.71it/s]
Train steps ... :  18%|█▊        | 18381/100000 [5:12:24<13:16:34,  1.71it/s]
Train steps ... :  18%|█▊        | 18382/100000 [5:12:24<13:16:43,  1.71it/s]
Train steps ... :  18%|█▊        | 18383/100000 [5:12:25<13:16:38,  1.71it/s]
Train steps ... :  18%|█▊        | 18384/100000 [5:12:25<13:15:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18385/100000 [5:12:26<13:17:15,  1.71it/s]
Train steps ... :  18%|█▊        | 18386/100000 [5:12:26<13:16:31,  1.71it/s]
Train steps ... :  18%|█▊        | 18387/100000 [5:12:27<13:15:47,  1.71it/s]
Train steps ... :  18%|█▊        | 18388/100000 [5:12:28<13:16:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18389/100000 [5:12:28<13:15:11,  1.71it/s]
Train steps ... :  18%|█▊        | 18390/100000 [5:12:29<13:15:01,  1.71it/s]
Train steps ... :  18%|█▊        | 18391/100000 [5:12:29<13:14:58,  1.71it/s]
Train steps ... :  18%|█▊        | 18392/100000 [5:12:30<13:14:26,  1.71it/s]
Train steps ... :  18%|█▊        | 18393/100000 [5:12:31<13:15:11,  1.71it/s]
Train steps ... :  18%|█▊        | 18394/100000 [5:12:31<13:14:41,  1.71it/s]
Train steps ... :  18%|█▊        | 18395/100000 [5:12:32<13:14:47,  1.71it/s]
Train steps ... :  18%|█▊        | 18396/100000 [5:12:32<13:14:27,  1.71it/s]
Train steps ... :  18%|█▊        | 18397/100000 [5:12:33<13:14:23,  1.71it/s]
Train steps ... :  18%|█▊        | 18398/100000 [5:12:33<13:13:48,  1.71it/s]
Train steps ... :  18%|█▊        | 18399/100000 [5:12:34<13:14:06,  1.71it/s]
Train steps ... :  18%|█▊        | 18400/100000 [5:12:35<13:14:03,  1.71it/s]Step... (18400 / 100000 | Loss: 0.9748672246932983, Learning Rate: 8.201005025125629e-05)
+
                                                                             
Step... (18400 / 100000 | Loss: 0.8482012152671814, Learning Rate: 8.201005025125629e-05)
+
Train steps ... :  18%|█▊        | 18400/100000 [5:12:35<13:14:03,  1.71it/s]
Train steps ... :  18%|█▊        | 18401/100000 [5:12:35<13:14:44,  1.71it/s]
Train steps ... :  18%|█▊        | 18402/100000 [5:12:36<13:15:03,  1.71it/s]
Train steps ... :  18%|█▊        | 18403/100000 [5:12:36<13:14:46,  1.71it/s]
Train steps ... :  18%|█▊        | 18404/100000 [5:12:37<13:14:58,  1.71it/s]
Train steps ... :  18%|█▊        | 18405/100000 [5:12:38<13:14:37,  1.71it/s]
Train steps ... :  18%|█▊        | 18406/100000 [5:12:38<13:14:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18407/100000 [5:12:39<13:14:31,  1.71it/s]
Train steps ... :  18%|█▊        | 18408/100000 [5:12:39<13:14:43,  1.71it/s]
Train steps ... :  18%|█▊        | 18409/100000 [5:12:40<13:14:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18410/100000 [5:12:41<13:13:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18411/100000 [5:12:41<13:14:10,  1.71it/s]
Train steps ... :  18%|█▊        | 18412/100000 [5:12:42<13:14:23,  1.71it/s]
Train steps ... :  18%|█▊        | 18413/100000 [5:12:42<13:15:40,  1.71it/s]
Train steps ... :  18%|█▊        | 18414/100000 [5:12:43<13:14:27,  1.71it/s]
Train steps ... :  18%|█▊        | 18415/100000 [5:12:43<13:16:38,  1.71it/s]
Train steps ... :  18%|█▊        | 18416/100000 [5:12:44<13:13:43,  1.71it/s]
Train steps ... :  18%|█▊        | 18417/100000 [5:12:45<13:15:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18418/100000 [5:12:45<13:15:16,  1.71it/s]
Train steps ... :  18%|█▊        | 18419/100000 [5:12:46<13:16:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18420/100000 [5:12:46<13:16:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18421/100000 [5:12:47<13:14:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18422/100000 [5:12:48<13:15:47,  1.71it/s]
Train steps ... :  18%|█▊        | 18423/100000 [5:12:48<13:14:50,  1.71it/s]
Train steps ... :  18%|█▊        | 18424/100000 [5:12:49<13:14:54,  1.71it/s]
Train steps ... :  18%|█▊        | 18425/100000 [5:12:49<13:14:27,  1.71it/s]Step... (18425 / 100000 | Loss: 1.0421478748321533, Learning Rate: 8.198492462311557e-05)
+
                                                                             
Step... (18425 / 100000 | Loss: 0.9450874328613281, Learning Rate: 8.198492462311557e-05)
+
Train steps ... :  18%|█▊        | 18425/100000 [5:12:50<13:14:27,  1.71it/s]
Train steps ... :  18%|█▊        | 18426/100000 [5:12:50<13:15:20,  1.71it/s]
Train steps ... :  18%|█▊        | 18427/100000 [5:12:50<13:13:49,  1.71it/s]
Train steps ... :  18%|█▊        | 18428/100000 [5:12:51<13:15:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18429/100000 [5:12:52<13:15:11,  1.71it/s]
Train steps ... :  18%|█▊        | 18430/100000 [5:12:52<13:15:58,  1.71it/s]
Train steps ... :  18%|█▊        | 18431/100000 [5:12:53<13:16:46,  1.71it/s]
Train steps ... :  18%|█▊        | 18432/100000 [5:12:53<13:16:22,  1.71it/s]
Train steps ... :  18%|█▊        | 18433/100000 [5:12:54<13:16:50,  1.71it/s]
Train steps ... :  18%|█▊        | 18434/100000 [5:12:55<13:16:36,  1.71it/s]
Train steps ... :  18%|█▊        | 18435/100000 [5:12:55<13:17:19,  1.70it/s]
Train steps ... :  18%|█▊        | 18436/100000 [5:12:56<13:16:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18437/100000 [5:12:56<13:14:39,  1.71it/s]
Train steps ... :  18%|█▊        | 18438/100000 [5:12:57<13:14:48,  1.71it/s]
Train steps ... :  18%|█▊        | 18439/100000 [5:12:57<13:14:24,  1.71it/s]
Train steps ... :  18%|█▊        | 18440/100000 [5:12:58<13:14:48,  1.71it/s]
Train steps ... :  18%|█▊        | 18441/100000 [5:12:59<13:14:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18442/100000 [5:12:59<13:14:07,  1.71it/s]
Train steps ... :  18%|█▊        | 18443/100000 [5:13:00<13:15:41,  1.71it/s]
Train steps ... :  18%|█▊        | 18444/100000 [5:13:00<13:14:37,  1.71it/s]
Train steps ... :  18%|█▊        | 18445/100000 [5:13:01<13:14:12,  1.71it/s]
Train steps ... :  18%|█▊        | 18446/100000 [5:13:02<13:14:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18447/100000 [5:13:02<13:13:58,  1.71it/s]
Train steps ... :  18%|█▊        | 18448/100000 [5:13:03<13:15:00,  1.71it/s]
Train steps ... :  18%|█▊        | 18449/100000 [5:13:03<13:14:43,  1.71it/s]
Train steps ... :  18%|█▊        | 18450/100000 [5:13:04<13:15:40,  1.71it/s]Step... (18450 / 100000 | Loss: 0.9743820428848267, Learning Rate: 8.195979899497488e-05)
+
                                                                             
Step... (18450 / 100000 | Loss: 1.013811469078064, Learning Rate: 8.195979899497488e-05)
+
Train steps ... :  18%|█▊        | 18450/100000 [5:13:04<13:15:40,  1.71it/s]
Train steps ... :  18%|█▊        | 18451/100000 [5:13:04<13:16:07,  1.71it/s]
Train steps ... :  18%|█▊        | 18452/100000 [5:13:05<13:18:39,  1.70it/s]
Train steps ... :  18%|█▊        | 18453/100000 [5:13:06<13:16:32,  1.71it/s]
Train steps ... :  18%|█▊        | 18454/100000 [5:13:06<13:15:18,  1.71it/s]
Train steps ... :  18%|█▊        | 18455/100000 [5:13:07<13:16:27,  1.71it/s]
Train steps ... :  18%|█▊        | 18456/100000 [5:13:07<13:15:26,  1.71it/s]
Train steps ... :  18%|█▊        | 18457/100000 [5:13:08<13:19:21,  1.70it/s]
Train steps ... :  18%|█▊        | 18458/100000 [5:13:09<13:15:43,  1.71it/s]
Train steps ... :  18%|█▊        | 18459/100000 [5:13:09<13:16:47,  1.71it/s]
Train steps ... :  18%|█▊        | 18460/100000 [5:13:10<13:15:15,  1.71it/s]
Train steps ... :  18%|█▊        | 18461/100000 [5:13:10<13:17:57,  1.70it/s]
Train steps ... :  18%|█▊        | 18462/100000 [5:13:11<13:16:28,  1.71it/s]
Train steps ... :  18%|█▊        | 18463/100000 [5:13:12<13:17:17,  1.70it/s]
Train steps ... :  18%|█▊        | 18464/100000 [5:13:12<13:18:05,  1.70it/s]
Train steps ... :  18%|█▊        | 18465/100000 [5:13:13<13:16:22,  1.71it/s]
Train steps ... :  18%|█▊        | 18466/100000 [5:13:13<13:16:47,  1.71it/s]
Train steps ... :  18%|█▊        | 18467/100000 [5:13:14<13:15:28,  1.71it/s]
Train steps ... :  18%|█▊        | 18468/100000 [5:13:14<13:16:01,  1.71it/s]
Train steps ... :  18%|█▊        | 18469/100000 [5:13:15<13:16:12,  1.71it/s]
Train steps ... :  18%|█▊        | 18470/100000 [5:13:16<13:15:31,  1.71it/s]
Train steps ... :  18%|█▊        | 18471/100000 [5:13:16<13:14:15,  1.71it/s]
Train steps ... :  18%|█▊        | 18472/100000 [5:13:17<13:14:31,  1.71it/s]
Train steps ... :  18%|█▊        | 18473/100000 [5:13:17<13:14:56,  1.71it/s]
Train steps ... :  18%|█▊        | 18474/100000 [5:13:18<13:15:08,  1.71it/s]
Train steps ... :  18%|█▊        | 18475/100000 [5:13:19<13:15:32,  1.71it/s]Step... (18475 / 100000 | Loss: 1.6625087261199951, Learning Rate: 8.193467336683417e-05)
+
                                                                             
Step... (18475 / 100000 | Loss: 1.2227907180786133, Learning Rate: 8.193467336683417e-05)
+
Train steps ... :  18%|█▊        | 18475/100000 [5:13:19<13:15:32,  1.71it/s]
Train steps ... :  18%|█▊        | 18476/100000 [5:13:19<13:14:48,  1.71it/s]
Train steps ... :  18%|█▊        | 18477/100000 [5:13:20<13:14:10,  1.71it/s]
Train steps ... :  18%|█▊        | 18478/100000 [5:13:20<13:13:46,  1.71it/s]
Train steps ... :  18%|█▊        | 18479/100000 [5:13:21<13:13:48,  1.71it/s]
Train steps ... :  18%|█▊        | 18480/100000 [5:13:21<13:14:00,  1.71it/s]
Train steps ... :  18%|█▊        | 18481/100000 [5:13:22<13:14:45,  1.71it/s]
Train steps ... :  18%|█▊        | 18482/100000 [5:13:23<13:14:01,  1.71it/s]
Train steps ... :  18%|█▊        | 18483/100000 [5:13:23<13:13:45,  1.71it/s]
Train steps ... :  18%|█▊        | 18484/100000 [5:13:24<13:14:09,  1.71it/s]
Train steps ... :  18%|█▊        | 18485/100000 [5:13:24<13:14:09,  1.71it/s]
Train steps ... :  18%|█▊        | 18486/100000 [5:13:25<13:14:43,  1.71it/s]
Train steps ... :  18%|█▊        | 18487/100000 [5:13:26<13:14:55,  1.71it/s]
Train steps ... :  18%|█▊        | 18488/100000 [5:13:26<13:13:59,  1.71it/s]
Train steps ... :  18%|█▊        | 18489/100000 [5:13:27<13:16:21,  1.71it/s]
Train steps ... :  18%|█▊        | 18490/100000 [5:13:27<13:15:31,  1.71it/s]
Train steps ... :  18%|█▊        | 18491/100000 [5:13:28<13:14:29,  1.71it/s]
Train steps ... :  18%|█▊        | 18492/100000 [5:13:28<13:14:30,  1.71it/s]
Train steps ... :  18%|█▊        | 18493/100000 [5:13:29<13:14:36,  1.71it/s]
Train steps ... :  18%|█▊        | 18494/100000 [5:13:30<13:15:17,  1.71it/s]
Train steps ... :  18%|█▊        | 18495/100000 [5:13:30<13:17:13,  1.70it/s]
Train steps ... :  18%|█▊        | 18496/100000 [5:13:31<13:17:07,  1.70it/s]
Train steps ... :  18%|█▊        | 18497/100000 [5:13:31<13:19:32,  1.70it/s]
Train steps ... :  18%|█▊        | 18498/100000 [5:13:32<13:18:04,  1.70it/s]
Train steps ... :  18%|█▊        | 18499/100000 [5:13:33<13:16:04,  1.71it/s]
Train steps ... :  18%|█▊        | 18500/100000 [5:13:33<13:16:17,  1.71it/s]Step... (18500 / 100000 | Loss: 0.8948959112167358, Learning Rate: 8.190954773869348e-05)
+
                                                                             
Step... (18500 / 100000 | Loss: 0.9522907733917236, Learning Rate: 8.190954773869348e-05)
+
Train steps ... :  18%|█▊        | 18500/100000 [5:13:34<13:16:17,  1.71it/s]
Train steps ... :  19%|█▊        | 18501/100000 [5:13:34<13:15:58,  1.71it/s]
Train steps ... :  19%|█▊        | 18502/100000 [5:13:34<13:16:29,  1.71it/s]
Train steps ... :  19%|█▊        | 18503/100000 [5:13:35<13:16:10,  1.71it/s]
Train steps ... :  19%|█▊        | 18504/100000 [5:13:36<13:15:28,  1.71it/s]
Train steps ... :  19%|█▊        | 18505/100000 [5:13:36<13:14:55,  1.71it/s]
Train steps ... :  19%|█▊        | 18506/100000 [5:13:37<13:14:35,  1.71it/s]
Train steps ... :  19%|█▊        | 18507/100000 [5:13:37<13:17:03,  1.70it/s]
Train steps ... :  19%|█▊        | 18508/100000 [5:13:38<13:15:56,  1.71it/s]
Train steps ... :  19%|█▊        | 18509/100000 [5:13:38<13:15:55,  1.71it/s]
Train steps ... :  19%|█▊        | 18510/100000 [5:13:39<13:15:31,  1.71it/s]
Train steps ... :  19%|█▊        | 18511/100000 [5:13:40<13:17:43,  1.70it/s]
Train steps ... :  19%|█▊        | 18512/100000 [5:13:40<13:15:47,  1.71it/s]
Train steps ... :  19%|█▊        | 18513/100000 [5:13:41<13:13:38,  1.71it/s]
Train steps ... :  19%|█▊        | 18514/100000 [5:13:41<13:14:33,  1.71it/s]
Train steps ... :  19%|█▊        | 18515/100000 [5:13:42<13:15:50,  1.71it/s]
Train steps ... :  19%|█▊        | 18516/100000 [5:13:43<13:15:30,  1.71it/s]
Train steps ... :  19%|█▊        | 18517/100000 [5:13:43<13:14:42,  1.71it/s]
Train steps ... :  19%|█▊        | 18518/100000 [5:13:44<13:14:00,  1.71it/s]
Train steps ... :  19%|█▊        | 18519/100000 [5:13:44<13:13:57,  1.71it/s]
Train steps ... :  19%|█▊        | 18520/100000 [5:13:45<13:14:08,  1.71it/s]
Train steps ... :  19%|█▊        | 18521/100000 [5:13:45<13:14:53,  1.71it/s]
Train steps ... :  19%|█▊        | 18522/100000 [5:13:46<13:15:20,  1.71it/s]
Train steps ... :  19%|█▊        | 18523/100000 [5:13:47<13:16:53,  1.70it/s]
Train steps ... :  19%|█▊        | 18524/100000 [5:13:47<13:15:50,  1.71it/s]
Train steps ... :  19%|█▊        | 18525/100000 [5:13:48<13:16:04,  1.71it/s]Step... (18525 / 100000 | Loss: 0.9238152503967285, Learning Rate: 8.188442211055277e-05)
+
                                                                             
Step... (18525 / 100000 | Loss: 1.2166975736618042, Learning Rate: 8.188442211055277e-05)
+
Train steps ... :  19%|█▊        | 18525/100000 [5:13:48<13:16:04,  1.71it/s]
Train steps ... :  19%|█▊        | 18526/100000 [5:13:48<13:15:53,  1.71it/s]
Train steps ... :  19%|█▊        | 18527/100000 [5:13:49<13:16:45,  1.70it/s]
Train steps ... :  19%|█▊        | 18528/100000 [5:13:50<13:14:05,  1.71it/s]
Train steps ... :  19%|█▊        | 18529/100000 [5:13:50<13:16:52,  1.70it/s]
Train steps ... :  19%|█▊        | 18530/100000 [5:13:51<13:16:15,  1.71it/s]
Train steps ... :  19%|█▊        | 18531/100000 [5:13:51<13:15:34,  1.71it/s]
Train steps ... :  19%|█▊        | 18532/100000 [5:13:52<13:15:02,  1.71it/s]
Train steps ... :  19%|█▊        | 18533/100000 [5:13:53<13:14:16,  1.71it/s]
Train steps ... :  19%|█▊        | 18534/100000 [5:13:53<13:13:59,  1.71it/s]
Train steps ... :  19%|█▊        | 18535/100000 [5:13:54<13:14:15,  1.71it/s]
Train steps ... :  19%|█▊        | 18536/100000 [5:13:54<13:14:13,  1.71it/s]
Train steps ... :  19%|█▊        | 18537/100000 [5:13:55<13:15:11,  1.71it/s]
Train steps ... :  19%|█▊        | 18538/100000 [5:13:55<13:15:17,  1.71it/s]
Train steps ... :  19%|█▊        | 18539/100000 [5:13:56<13:17:12,  1.70it/s]
Train steps ... :  19%|█▊        | 18540/100000 [5:13:57<13:14:54,  1.71it/s]
Train steps ... :  19%|█▊        | 18541/100000 [5:13:57<13:14:40,  1.71it/s]
Train steps ... :  19%|█▊        | 18542/100000 [5:13:58<13:16:08,  1.71it/s]
Train steps ... :  19%|█▊        | 18543/100000 [5:13:58<13:14:30,  1.71it/s]
Train steps ... :  19%|█▊        | 18544/100000 [5:13:59<13:13:40,  1.71it/s]
Train steps ... :  19%|█▊        | 18545/100000 [5:14:00<13:13:48,  1.71it/s]
Train steps ... :  19%|█▊        | 18546/100000 [5:14:00<13:14:24,  1.71it/s]
Train steps ... :  19%|█▊        | 18547/100000 [5:14:01<13:14:34,  1.71it/s]
Train steps ... :  19%|█▊        | 18548/100000 [5:14:01<13:13:33,  1.71it/s]
Train steps ... :  19%|█▊        | 18549/100000 [5:14:02<13:14:02,  1.71it/s]
Train steps ... :  19%|█▊        | 18550/100000 [5:14:02<13:13:17,  1.71it/s]Step... (18550 / 100000 | Loss: 1.0160831212997437, Learning Rate: 8.185929648241206e-05)
+
                                                                             
Step... (18550 / 100000 | Loss: 1.276834487915039, Learning Rate: 8.185929648241206e-05)
+
Train steps ... :  19%|█▊        | 18550/100000 [5:14:03<13:13:17,  1.71it/s]
Train steps ... :  19%|█▊        | 18551/100000 [5:14:03<13:12:58,  1.71it/s]
Train steps ... :  19%|█▊        | 18552/100000 [5:14:04<13:12:47,  1.71it/s]
Train steps ... :  19%|█▊        | 18553/100000 [5:14:04<13:12:48,  1.71it/s]
Train steps ... :  19%|█▊        | 18554/100000 [5:14:05<13:12:43,  1.71it/s]
Train steps ... :  19%|█▊        | 18555/100000 [5:14:05<13:15:40,  1.71it/s]
Train steps ... :  19%|█▊        | 18556/100000 [5:14:06<13:14:50,  1.71it/s]
Train steps ... :  19%|█▊        | 18557/100000 [5:14:07<13:15:19,  1.71it/s]
Train steps ... :  19%|█▊        | 18558/100000 [5:14:07<13:14:44,  1.71it/s]
Train steps ... :  19%|█▊        | 18559/100000 [5:14:08<13:18:48,  1.70it/s]
Train steps ... :  19%|█▊        | 18560/100000 [5:14:08<13:19:15,  1.70it/s]
Train steps ... :  19%|█▊        | 18561/100000 [5:14:09<13:17:12,  1.70it/s]
Train steps ... :  19%|█▊        | 18562/100000 [5:14:10<13:15:40,  1.71it/s]
Train steps ... :  19%|█▊        | 18563/100000 [5:14:10<13:14:06,  1.71it/s]
Train steps ... :  19%|█▊        | 18564/100000 [5:14:11<13:13:55,  1.71it/s]
Train steps ... :  19%|█▊        | 18565/100000 [5:14:11<13:13:49,  1.71it/s]
Train steps ... :  19%|█▊        | 18566/100000 [5:14:12<13:14:51,  1.71it/s]
Train steps ... :  19%|█▊        | 18567/100000 [5:14:12<13:14:10,  1.71it/s]
Train steps ... :  19%|█▊        | 18568/100000 [5:14:13<13:14:39,  1.71it/s]
Train steps ... :  19%|█▊        | 18569/100000 [5:14:14<13:14:11,  1.71it/s]
Train steps ... :  19%|█▊        | 18570/100000 [5:14:14<13:14:06,  1.71it/s]
Train steps ... :  19%|█▊        | 18571/100000 [5:14:15<13:14:39,  1.71it/s]
Train steps ... :  19%|█▊        | 18572/100000 [5:14:15<13:13:50,  1.71it/s]
Train steps ... :  19%|█▊        | 18573/100000 [5:14:16<13:14:36,  1.71it/s]
Train steps ... :  19%|█▊        | 18574/100000 [5:14:17<13:14:25,  1.71it/s]
Train steps ... :  19%|█▊        | 18575/100000 [5:14:17<13:14:28,  1.71it/s]Step... (18575 / 100000 | Loss: 0.933459997177124, Learning Rate: 8.183417085427137e-05)
+
                                                                             
Step... (18575 / 100000 | Loss: 0.9583403468132019, Learning Rate: 8.183417085427137e-05)
+
Train steps ... :  19%|█▊        | 18575/100000 [5:14:17<13:14:28,  1.71it/s]
Train steps ... :  19%|█▊        | 18576/100000 [5:14:18<13:13:14,  1.71it/s]
Train steps ... :  19%|█▊        | 18577/100000 [5:14:18<13:13:02,  1.71it/s]
Train steps ... :  19%|█▊        | 18578/100000 [5:14:19<13:12:50,  1.71it/s]
Train steps ... :  19%|█▊        | 18579/100000 [5:14:19<13:12:33,  1.71it/s]
Train steps ... :  19%|█▊        | 18580/100000 [5:14:20<13:12:51,  1.71it/s]
Train steps ... :  19%|█▊        | 18581/100000 [5:14:21<13:13:04,  1.71it/s]
Train steps ... :  19%|█▊        | 18582/100000 [5:14:21<13:12:33,  1.71it/s]
Train steps ... :  19%|█▊        | 18583/100000 [5:14:22<13:12:25,  1.71it/s]
Train steps ... :  19%|█▊        | 18584/100000 [5:14:22<13:12:07,  1.71it/s]
Train steps ... :  19%|█▊        | 18585/100000 [5:14:23<13:11:58,  1.71it/s]
Train steps ... :  19%|█▊        | 18586/100000 [5:14:24<13:11:34,  1.71it/s]
Train steps ... :  19%|█▊        | 18587/100000 [5:14:24<13:12:37,  1.71it/s]
Train steps ... :  19%|█▊        | 18588/100000 [5:14:25<13:12:34,  1.71it/s]
Train steps ... :  19%|█▊        | 18589/100000 [5:14:25<13:13:15,  1.71it/s]
Train steps ... :  19%|█▊        | 18590/100000 [5:14:26<13:13:07,  1.71it/s]
Train steps ... :  19%|█▊        | 18591/100000 [5:14:26<13:12:57,  1.71it/s]
Train steps ... :  19%|█▊        | 18592/100000 [5:14:27<13:13:19,  1.71it/s]
Train steps ... :  19%|█▊        | 18593/100000 [5:14:28<13:13:46,  1.71it/s]
Train steps ... :  19%|█▊        | 18594/100000 [5:14:28<13:13:25,  1.71it/s]
Train steps ... :  19%|█▊        | 18595/100000 [5:14:29<13:13:38,  1.71it/s]
Train steps ... :  19%|█▊        | 18596/100000 [5:14:29<13:13:06,  1.71it/s]
Train steps ... :  19%|█▊        | 18597/100000 [5:14:30<13:12:54,  1.71it/s]
Train steps ... :  19%|█▊        | 18598/100000 [5:14:31<13:12:45,  1.71it/s]
Train steps ... :  19%|█▊        | 18599/100000 [5:14:31<13:12:59,  1.71it/s]
Train steps ... :  19%|█▊        | 18600/100000 [5:14:32<13:12:17,  1.71it/s]Step... (18600 / 100000 | Loss: 0.9203124046325684, Learning Rate: 8.180904522613065e-05)
+
                                                                             
Step... (18600 / 100000 | Loss: 0.9366077184677124, Learning Rate: 8.180904522613065e-05)
+
Train steps ... :  19%|█▊        | 18600/100000 [5:14:32<13:12:17,  1.71it/s]
Train steps ... :  19%|█▊        | 18601/100000 [5:14:32<13:12:23,  1.71it/s]
Train steps ... :  19%|█▊        | 18602/100000 [5:14:33<13:11:52,  1.71it/s]
Train steps ... :  19%|█▊        | 18603/100000 [5:14:33<13:12:44,  1.71it/s]
Train steps ... :  19%|█▊        | 18604/100000 [5:14:34<13:12:39,  1.71it/s]
Train steps ... :  19%|█▊        | 18605/100000 [5:14:35<13:12:45,  1.71it/s]
Train steps ... :  19%|█▊        | 18606/100000 [5:14:35<13:12:23,  1.71it/s]
Train steps ... :  19%|█▊        | 18607/100000 [5:14:36<13:11:56,  1.71it/s]
Train steps ... :  19%|█▊        | 18608/100000 [5:14:36<13:11:42,  1.71it/s]
Train steps ... :  19%|█▊        | 18609/100000 [5:14:37<13:12:08,  1.71it/s]
Train steps ... :  19%|█▊        | 18610/100000 [5:14:38<13:12:39,  1.71it/s]
Train steps ... :  19%|█▊        | 18611/100000 [5:14:38<13:12:49,  1.71it/s]
Train steps ... :  19%|█▊        | 18612/100000 [5:14:39<13:13:21,  1.71it/s]
Train steps ... :  19%|█▊        | 18613/100000 [5:14:39<13:13:50,  1.71it/s]
Train steps ... :  19%|█▊        | 18614/100000 [5:14:40<13:14:35,  1.71it/s]
Train steps ... :  19%|█▊        | 18615/100000 [5:14:40<13:15:09,  1.71it/s]
Train steps ... :  19%|█▊        | 18616/100000 [5:14:41<13:14:57,  1.71it/s]
Train steps ... :  19%|█▊        | 18617/100000 [5:14:42<13:15:25,  1.71it/s]
Train steps ... :  19%|█▊        | 18618/100000 [5:14:42<13:16:27,  1.70it/s]
Train steps ... :  19%|█▊        | 18619/100000 [5:14:43<13:15:02,  1.71it/s]
Train steps ... :  19%|█▊        | 18620/100000 [5:14:43<13:15:12,  1.71it/s]
Train steps ... :  19%|█▊        | 18621/100000 [5:14:44<13:13:10,  1.71it/s]
Train steps ... :  19%|█▊        | 18622/100000 [5:14:45<13:13:56,  1.71it/s]
Train steps ... :  19%|█▊        | 18623/100000 [5:14:45<13:14:48,  1.71it/s]
Train steps ... :  19%|█▊        | 18624/100000 [5:14:46<13:14:29,  1.71it/s]
Train steps ... :  19%|█▊        | 18625/100000 [5:14:46<13:12:48,  1.71it/s]Step... (18625 / 100000 | Loss: 1.0094003677368164, Learning Rate: 8.178391959798996e-05)
+
                                                                             
Step... (18625 / 100000 | Loss: 0.8212896585464478, Learning Rate: 8.178391959798996e-05)
+
Train steps ... :  19%|█▊        | 18625/100000 [5:14:47<13:12:48,  1.71it/s]
Train steps ... :  19%|█▊        | 18626/100000 [5:14:47<13:12:38,  1.71it/s]
Train steps ... :  19%|█▊        | 18627/100000 [5:14:48<13:12:42,  1.71it/s]
Train steps ... :  19%|█▊        | 18628/100000 [5:14:48<13:13:08,  1.71it/s]
Train steps ... :  19%|█▊        | 18629/100000 [5:14:49<13:13:09,  1.71it/s]
Train steps ... :  19%|█▊        | 18630/100000 [5:14:49<13:13:24,  1.71it/s]
Train steps ... :  19%|█▊        | 18631/100000 [5:14:50<13:13:46,  1.71it/s]
Train steps ... :  19%|█▊        | 18632/100000 [5:14:50<13:12:59,  1.71it/s]
Train steps ... :  19%|█▊        | 18633/100000 [5:14:51<13:15:17,  1.71it/s]
Train steps ... :  19%|█▊        | 18634/100000 [5:14:52<13:14:09,  1.71it/s]
Train steps ... :  19%|█▊        | 18635/100000 [5:14:52<13:13:02,  1.71it/s]
Train steps ... :  19%|█▊        | 18636/100000 [5:14:53<13:13:39,  1.71it/s]
Train steps ... :  19%|█▊        | 18637/100000 [5:14:53<13:13:46,  1.71it/s]
Train steps ... :  19%|█▊        | 18638/100000 [5:14:54<13:13:26,  1.71it/s]
Train steps ... :  19%|█▊        | 18639/100000 [5:14:55<13:13:22,  1.71it/s]
Train steps ... :  19%|█▊        | 18640/100000 [5:14:55<13:12:56,  1.71it/s]
Train steps ... :  19%|█▊        | 18641/100000 [5:14:56<13:12:34,  1.71it/s]
Train steps ... :  19%|█▊        | 18642/100000 [5:14:56<13:12:33,  1.71it/s]
Train steps ... :  19%|█▊        | 18643/100000 [5:14:57<13:13:09,  1.71it/s]
Train steps ... :  19%|█▊        | 18644/100000 [5:14:57<13:13:24,  1.71it/s]
Train steps ... :  19%|█▊        | 18645/100000 [5:14:58<13:13:07,  1.71it/s]
Train steps ... :  19%|█▊        | 18646/100000 [5:14:59<13:12:59,  1.71it/s]
Train steps ... :  19%|█▊        | 18647/100000 [5:14:59<13:13:48,  1.71it/s]
Train steps ... :  19%|█▊        | 18648/100000 [5:15:00<13:13:03,  1.71it/s]
Train steps ... :  19%|█▊        | 18649/100000 [5:15:00<13:12:30,  1.71it/s]
Train steps ... :  19%|█▊        | 18650/100000 [5:15:01<13:12:09,  1.71it/s]Step... (18650 / 100000 | Loss: 0.8910712003707886, Learning Rate: 8.175879396984924e-05)
+
                                                                             
Step... (18650 / 100000 | Loss: 0.7611311674118042, Learning Rate: 8.175879396984924e-05)
+
Train steps ... :  19%|█▊        | 18650/100000 [5:15:01<13:12:09,  1.71it/s]
Train steps ... :  19%|█▊        | 18651/100000 [5:15:02<13:12:05,  1.71it/s]
Train steps ... :  19%|█▊        | 18652/100000 [5:15:02<13:12:16,  1.71it/s]
Train steps ... :  19%|█▊        | 18653/100000 [5:15:03<13:11:35,  1.71it/s]
Train steps ... :  19%|█▊        | 18654/100000 [5:15:03<13:12:06,  1.71it/s]
Train steps ... :  19%|█▊        | 18655/100000 [5:15:04<13:11:28,  1.71it/s]
Train steps ... :  19%|█▊        | 18656/100000 [5:15:04<13:11:17,  1.71it/s]
Train steps ... :  19%|█▊        | 18657/100000 [5:15:05<13:13:00,  1.71it/s]
Train steps ... :  19%|█▊        | 18658/100000 [5:15:06<13:12:37,  1.71it/s]
Train steps ... :  19%|█▊        | 18659/100000 [5:15:06<13:12:31,  1.71it/s]
Train steps ... :  19%|█▊        | 18660/100000 [5:15:07<13:12:13,  1.71it/s]
Train steps ... :  19%|█▊        | 18661/100000 [5:15:07<13:12:00,  1.71it/s]
Train steps ... :  19%|█▊        | 18662/100000 [5:15:08<13:11:55,  1.71it/s]
Train steps ... :  19%|█▊        | 18663/100000 [5:15:09<13:11:52,  1.71it/s]
Train steps ... :  19%|█▊        | 18664/100000 [5:15:09<13:11:56,  1.71it/s]
Train steps ... :  19%|█▊        | 18665/100000 [5:15:10<13:13:10,  1.71it/s]
Train steps ... :  19%|█▊        | 18666/100000 [5:15:10<13:12:53,  1.71it/s]
Train steps ... :  19%|█▊        | 18667/100000 [5:15:11<13:13:37,  1.71it/s]
Train steps ... :  19%|█▊        | 18668/100000 [5:15:11<13:12:34,  1.71it/s]
Train steps ... :  19%|█▊        | 18669/100000 [5:15:12<13:12:14,  1.71it/s]
Train steps ... :  19%|█▊        | 18670/100000 [5:15:13<13:12:06,  1.71it/s]
Train steps ... :  19%|█▊        | 18671/100000 [5:15:13<13:12:00,  1.71it/s]
Train steps ... :  19%|█▊        | 18672/100000 [5:15:14<13:11:29,  1.71it/s]
Train steps ... :  19%|█▊        | 18673/100000 [5:15:14<13:11:10,  1.71it/s]
Train steps ... :  19%|█▊        | 18674/100000 [5:15:15<13:11:09,  1.71it/s]
Train steps ... :  19%|█▊        | 18675/100000 [5:15:16<13:11:51,  1.71it/s]Step... (18675 / 100000 | Loss: 0.9673024415969849, Learning Rate: 8.173366834170855e-05)
+
                                                                             
Step... (18675 / 100000 | Loss: 0.9532004594802856, Learning Rate: 8.173366834170855e-05)
+
Train steps ... :  19%|█▊        | 18675/100000 [5:15:16<13:11:51,  1.71it/s]
Train steps ... :  19%|█▊        | 18676/100000 [5:15:16<13:12:32,  1.71it/s]
Train steps ... :  19%|█▊        | 18677/100000 [5:15:17<13:12:30,  1.71it/s]
Train steps ... :  19%|█▊        | 18678/100000 [5:15:17<13:11:59,  1.71it/s]
Train steps ... :  19%|█▊        | 18679/100000 [5:15:18<13:11:59,  1.71it/s]
Train steps ... :  19%|█▊        | 18680/100000 [5:15:18<13:11:15,  1.71it/s]
Train steps ... :  19%|█▊        | 18681/100000 [5:15:19<13:11:31,  1.71it/s]
Train steps ... :  19%|█▊        | 18682/100000 [5:15:20<13:12:31,  1.71it/s]
Train steps ... :  19%|█▊        | 18683/100000 [5:15:20<13:11:38,  1.71it/s]
Train steps ... :  19%|█▊        | 18684/100000 [5:15:21<13:12:13,  1.71it/s]
Train steps ... :  19%|█▊        | 18685/100000 [5:15:21<13:13:51,  1.71it/s]
Train steps ... :  19%|█▊        | 18686/100000 [5:15:22<13:11:19,  1.71it/s]
Train steps ... :  19%|█▊        | 18687/100000 [5:15:23<13:12:27,  1.71it/s]
Train steps ... :  19%|█▊        | 18688/100000 [5:15:23<13:12:25,  1.71it/s]
Train steps ... :  19%|█▊        | 18689/100000 [5:15:24<13:11:58,  1.71it/s]
Train steps ... :  19%|█▊        | 18690/100000 [5:15:24<13:11:48,  1.71it/s]
Train steps ... :  19%|█▊        | 18691/100000 [5:15:25<13:12:06,  1.71it/s]
Train steps ... :  19%|█▊        | 18692/100000 [5:15:26<13:12:05,  1.71it/s]
Train steps ... :  19%|█▊        | 18693/100000 [5:15:26<13:12:20,  1.71it/s]
Train steps ... :  19%|█▊        | 18694/100000 [5:15:27<13:12:03,  1.71it/s]
Train steps ... :  19%|█▊        | 18695/100000 [5:15:27<13:11:33,  1.71it/s]
Train steps ... :  19%|█▊        | 18696/100000 [5:15:28<13:11:08,  1.71it/s]
Train steps ... :  19%|█▊        | 18697/100000 [5:15:28<13:10:55,  1.71it/s]
Train steps ... :  19%|█▊        | 18698/100000 [5:15:29<13:11:14,  1.71it/s]
Train steps ... :  19%|█▊        | 18699/100000 [5:15:30<13:12:14,  1.71it/s]
Train steps ... :  19%|█▊        | 18700/100000 [5:15:30<13:12:07,  1.71it/s]Step... (18700 / 100000 | Loss: 1.3843127489089966, Learning Rate: 8.170854271356785e-05)
+
                                                                             
Step... (18700 / 100000 | Loss: 0.8437381982803345, Learning Rate: 8.170854271356785e-05)
+
Train steps ... :  19%|█▊        | 18700/100000 [5:15:31<13:12:07,  1.71it/s]
Train steps ... :  19%|█▊        | 18701/100000 [5:15:31<13:11:41,  1.71it/s]
Train steps ... :  19%|█▊        | 18702/100000 [5:15:31<13:11:10,  1.71it/s]
Train steps ... :  19%|█▊        | 18703/100000 [5:15:32<13:11:17,  1.71it/s]
Train steps ... :  19%|█▊        | 18704/100000 [5:15:33<13:11:03,  1.71it/s]
Train steps ... :  19%|█▊        | 18705/100000 [5:15:33<13:11:16,  1.71it/s]
Train steps ... :  19%|█▊        | 18706/100000 [5:15:34<13:11:13,  1.71it/s]
Train steps ... :  19%|█▊        | 18707/100000 [5:15:34<13:11:40,  1.71it/s]
Train steps ... :  19%|█▊        | 18708/100000 [5:15:35<13:11:45,  1.71it/s]
Train steps ... :  19%|█▊        | 18709/100000 [5:15:35<13:11:55,  1.71it/s]
Train steps ... :  19%|█▊        | 18710/100000 [5:15:36<13:11:06,  1.71it/s]
Train steps ... :  19%|█▊        | 18711/100000 [5:15:37<13:11:11,  1.71it/s]
Train steps ... :  19%|█▊        | 18712/100000 [5:15:37<13:11:00,  1.71it/s]
Train steps ... :  19%|█▊        | 18713/100000 [5:15:38<13:12:34,  1.71it/s]
Train steps ... :  19%|█▊        | 18714/100000 [5:15:38<13:12:26,  1.71it/s]
Train steps ... :  19%|█▊        | 18715/100000 [5:15:39<13:11:44,  1.71it/s]
Train steps ... :  19%|█▊        | 18716/100000 [5:15:40<13:11:29,  1.71it/s]
Train steps ... :  19%|█▊        | 18717/100000 [5:15:40<13:10:49,  1.71it/s]
Train steps ... :  19%|█▊        | 18718/100000 [5:15:41<13:10:52,  1.71it/s]
Train steps ... :  19%|█▊        | 18719/100000 [5:15:41<13:10:35,  1.71it/s]
Train steps ... :  19%|█▊        | 18720/100000 [5:15:42<13:12:05,  1.71it/s]
Train steps ... :  19%|█▊        | 18721/100000 [5:15:42<13:11:08,  1.71it/s]
Train steps ... :  19%|█▊        | 18722/100000 [5:15:43<13:11:10,  1.71it/s]
Train steps ... :  19%|█▊        | 18723/100000 [5:15:44<13:11:15,  1.71it/s]
Train steps ... :  19%|█▊        | 18724/100000 [5:15:44<13:11:03,  1.71it/s]
Train steps ... :  19%|█▊        | 18725/100000 [5:15:45<13:10:49,  1.71it/s]Step... (18725 / 100000 | Loss: 0.9809591770172119, Learning Rate: 8.168341708542713e-05)
+
                                                                             
Step... (18725 / 100000 | Loss: 0.9563585519790649, Learning Rate: 8.168341708542713e-05)
+
Train steps ... :  19%|█▊        | 18725/100000 [5:15:45<13:10:49,  1.71it/s]
Train steps ... :  19%|█▊        | 18726/100000 [5:15:45<13:12:02,  1.71it/s]
Train steps ... :  19%|█▊        | 18727/100000 [5:15:46<13:12:13,  1.71it/s]
Train steps ... :  19%|█▊        | 18728/100000 [5:15:47<13:11:11,  1.71it/s]
Train steps ... :  19%|█▊        | 18729/100000 [5:15:47<13:10:30,  1.71it/s]
Train steps ... :  19%|█▊        | 18730/100000 [5:15:48<13:10:50,  1.71it/s]
Train steps ... :  19%|█▊        | 18731/100000 [5:15:48<13:10:36,  1.71it/s]
Train steps ... :  19%|█▊        | 18732/100000 [5:15:49<13:10:09,  1.71it/s]
Train steps ... :  19%|█▊        | 18733/100000 [5:15:49<13:10:24,  1.71it/s]
Train steps ... :  19%|█▊        | 18734/100000 [5:15:50<13:10:30,  1.71it/s]
Train steps ... :  19%|█▊        | 18735/100000 [5:15:51<13:10:33,  1.71it/s]
Train steps ... :  19%|█▊        | 18736/100000 [5:15:51<13:10:53,  1.71it/s]
Train steps ... :  19%|█▊        | 18737/100000 [5:15:52<13:10:06,  1.71it/s]
Train steps ... :  19%|█▊        | 18738/100000 [5:15:52<13:10:25,  1.71it/s]
Train steps ... :  19%|█▊        | 18739/100000 [5:15:53<13:11:09,  1.71it/s]
Train steps ... :  19%|█▊        | 18740/100000 [5:15:54<13:10:35,  1.71it/s]
Train steps ... :  19%|█▊        | 18741/100000 [5:15:54<13:10:44,  1.71it/s]
Train steps ... :  19%|█▊        | 18742/100000 [5:15:55<13:10:17,  1.71it/s]
Train steps ... :  19%|█▊        | 18743/100000 [5:15:55<13:10:21,  1.71it/s]
Train steps ... :  19%|█▊        | 18744/100000 [5:15:56<13:09:56,  1.71it/s]
Train steps ... :  19%|█▊        | 18745/100000 [5:15:56<13:09:56,  1.71it/s]
Train steps ... :  19%|█▊        | 18746/100000 [5:15:57<13:10:35,  1.71it/s]
Train steps ... :  19%|█▊        | 18747/100000 [5:15:58<13:10:35,  1.71it/s]
Train steps ... :  19%|█▊        | 18748/100000 [5:15:58<13:10:40,  1.71it/s]
Train steps ... :  19%|█▊        | 18749/100000 [5:15:59<13:10:36,  1.71it/s]
Train steps ... :  19%|█▉        | 18750/100000 [5:15:59<13:10:19,  1.71it/s]Step... (18750 / 100000 | Loss: 1.0472784042358398, Learning Rate: 8.165829145728644e-05)
+
                                                                             
Step... (18750 / 100000 | Loss: 1.2323956489562988, Learning Rate: 8.165829145728644e-05)
+
Train steps ... :  19%|█▉        | 18750/100000 [5:16:00<13:10:19,  1.71it/s]
Train steps ... :  19%|█▉        | 18751/100000 [5:16:00<13:10:44,  1.71it/s]
Train steps ... :  19%|█▉        | 18752/100000 [5:16:01<13:10:27,  1.71it/s]
Train steps ... :  19%|█▉        | 18753/100000 [5:16:01<13:11:18,  1.71it/s]
Train steps ... :  19%|█▉        | 18754/100000 [5:16:02<13:10:23,  1.71it/s]
Train steps ... :  19%|█▉        | 18755/100000 [5:16:02<13:11:04,  1.71it/s]
Train steps ... :  19%|█▉        | 18756/100000 [5:16:03<13:10:58,  1.71it/s]
Train steps ... :  19%|█▉        | 18757/100000 [5:16:03<13:10:20,  1.71it/s]
Train steps ... :  19%|█▉        | 18758/100000 [5:16:04<13:10:55,  1.71it/s]
Train steps ... :  19%|█▉        | 18759/100000 [5:16:05<13:11:26,  1.71it/s]
Train steps ... :  19%|█▉        | 18760/100000 [5:16:05<13:10:59,  1.71it/s]
Train steps ... :  19%|█▉        | 18761/100000 [5:16:06<13:11:15,  1.71it/s]
Train steps ... :  19%|█▉        | 18762/100000 [5:16:06<13:10:27,  1.71it/s]
Train steps ... :  19%|█▉        | 18763/100000 [5:16:07<13:11:32,  1.71it/s]
Train steps ... :  19%|█▉        | 18764/100000 [5:16:08<13:11:42,  1.71it/s]
Train steps ... :  19%|█▉        | 18765/100000 [5:16:08<13:11:05,  1.71it/s]
Train steps ... :  19%|█▉        | 18766/100000 [5:16:09<13:10:39,  1.71it/s]
Train steps ... :  19%|█▉        | 18767/100000 [5:16:09<13:11:06,  1.71it/s]
Train steps ... :  19%|█▉        | 18768/100000 [5:16:10<13:10:39,  1.71it/s]
Train steps ... :  19%|█▉        | 18769/100000 [5:16:10<13:10:12,  1.71it/s]
Train steps ... :  19%|█▉        | 18770/100000 [5:16:11<13:10:49,  1.71it/s]
Train steps ... :  19%|█▉        | 18771/100000 [5:16:12<13:10:17,  1.71it/s]
Train steps ... :  19%|█▉        | 18772/100000 [5:16:12<13:10:28,  1.71it/s]
Train steps ... :  19%|█▉        | 18773/100000 [5:16:13<13:09:52,  1.71it/s]
Train steps ... :  19%|█▉        | 18774/100000 [5:16:13<13:09:34,  1.71it/s]
Train steps ... :  19%|█▉        | 18775/100000 [5:16:14<13:09:48,  1.71it/s]Step... (18775 / 100000 | Loss: 1.0046274662017822, Learning Rate: 8.163316582914573e-05)
+
                                                                             
Step... (18775 / 100000 | Loss: 1.0671155452728271, Learning Rate: 8.163316582914573e-05)
+
Train steps ... :  19%|█▉        | 18775/100000 [5:16:14<13:09:48,  1.71it/s]
Train steps ... :  19%|█▉        | 18776/100000 [5:16:15<13:10:26,  1.71it/s]
Train steps ... :  19%|█▉        | 18777/100000 [5:16:15<13:10:51,  1.71it/s]
Train steps ... :  19%|█▉        | 18778/100000 [5:16:16<13:10:50,  1.71it/s]
Train steps ... :  19%|█▉        | 18779/100000 [5:16:16<13:10:45,  1.71it/s]
Train steps ... :  19%|█▉        | 18780/100000 [5:16:17<13:10:00,  1.71it/s]
Train steps ... :  19%|█▉        | 18781/100000 [5:16:17<13:10:04,  1.71it/s]
Train steps ... :  19%|█▉        | 18782/100000 [5:16:18<13:10:05,  1.71it/s]
Train steps ... :  19%|█▉        | 18783/100000 [5:16:19<13:09:55,  1.71it/s]
Train steps ... :  19%|█▉        | 18784/100000 [5:16:19<13:09:41,  1.71it/s]
Train steps ... :  19%|█▉        | 18785/100000 [5:16:20<13:09:58,  1.71it/s]
Train steps ... :  19%|█▉        | 18786/100000 [5:16:20<13:10:04,  1.71it/s]
Train steps ... :  19%|█▉        | 18787/100000 [5:16:21<13:10:10,  1.71it/s]
Train steps ... :  19%|█▉        | 18788/100000 [5:16:22<13:10:04,  1.71it/s]
Train steps ... :  19%|█▉        | 18789/100000 [5:16:22<13:10:26,  1.71it/s]
Train steps ... :  19%|█▉        | 18790/100000 [5:16:23<13:10:35,  1.71it/s]
Train steps ... :  19%|█▉        | 18791/100000 [5:16:23<13:10:20,  1.71it/s]
Train steps ... :  19%|█▉        | 18792/100000 [5:16:24<13:10:21,  1.71it/s]
Train steps ... :  19%|█▉        | 18793/100000 [5:16:24<13:09:57,  1.71it/s]
Train steps ... :  19%|█▉        | 18794/100000 [5:16:25<13:09:48,  1.71it/s]
Train steps ... :  19%|█▉        | 18795/100000 [5:16:26<13:10:28,  1.71it/s]
Train steps ... :  19%|█▉        | 18796/100000 [5:16:26<13:10:40,  1.71it/s]
Train steps ... :  19%|█▉        | 18797/100000 [5:16:27<13:10:23,  1.71it/s]
Train steps ... :  19%|█▉        | 18798/100000 [5:16:27<13:11:06,  1.71it/s]
Train steps ... :  19%|█▉        | 18799/100000 [5:16:28<13:11:21,  1.71it/s]
Train steps ... :  19%|█▉        | 18800/100000 [5:16:29<13:10:21,  1.71it/s]Step... (18800 / 100000 | Loss: 1.197373628616333, Learning Rate: 8.160804020100504e-05)
+
                                                                             
Step... (18800 / 100000 | Loss: 1.4808199405670166, Learning Rate: 8.160804020100504e-05)
+
Train steps ... :  19%|█▉        | 18800/100000 [5:16:29<13:10:21,  1.71it/s]
Train steps ... :  19%|█▉        | 18801/100000 [5:16:29<13:10:12,  1.71it/s]
Train steps ... :  19%|█▉        | 18802/100000 [5:16:30<13:10:41,  1.71it/s]
Train steps ... :  19%|█▉        | 18803/100000 [5:16:30<13:10:17,  1.71it/s]
Train steps ... :  19%|█▉        | 18804/100000 [5:16:31<13:10:27,  1.71it/s]
Train steps ... :  19%|█▉        | 18805/100000 [5:16:31<13:09:58,  1.71it/s]
Train steps ... :  19%|█▉        | 18806/100000 [5:16:32<13:10:05,  1.71it/s]
Train steps ... :  19%|█▉        | 18807/100000 [5:16:33<13:10:14,  1.71it/s]
Train steps ... :  19%|█▉        | 18808/100000 [5:16:33<13:09:46,  1.71it/s]
Train steps ... :  19%|█▉        | 18809/100000 [5:16:34<13:09:23,  1.71it/s]
Train steps ... :  19%|█▉        | 18810/100000 [5:16:34<13:09:51,  1.71it/s]
Train steps ... :  19%|█▉        | 18811/100000 [5:16:35<13:10:04,  1.71it/s]
Train steps ... :  19%|█▉        | 18812/100000 [5:16:36<13:10:05,  1.71it/s]
Train steps ... :  19%|█▉        | 18813/100000 [5:16:36<13:10:37,  1.71it/s]
Train steps ... :  19%|█▉        | 18814/100000 [5:16:37<13:12:09,  1.71it/s]
Train steps ... :  19%|█▉        | 18815/100000 [5:16:37<13:11:09,  1.71it/s]
Train steps ... :  19%|█▉        | 18816/100000 [5:16:38<13:10:27,  1.71it/s]
Train steps ... :  19%|█▉        | 18817/100000 [5:16:39<13:10:46,  1.71it/s]
Train steps ... :  19%|█▉        | 18818/100000 [5:16:39<13:10:56,  1.71it/s]
Train steps ... :  19%|█▉        | 18819/100000 [5:16:40<13:10:41,  1.71it/s]
Train steps ... :  19%|█▉        | 18820/100000 [5:16:40<13:10:05,  1.71it/s]
Train steps ... :  19%|█▉        | 18821/100000 [5:16:41<13:10:05,  1.71it/s]
Train steps ... :  19%|█▉        | 18822/100000 [5:16:41<13:10:28,  1.71it/s]
Train steps ... :  19%|█▉        | 18823/100000 [5:16:42<13:10:29,  1.71it/s]
Train steps ... :  19%|█▉        | 18824/100000 [5:16:43<13:10:30,  1.71it/s]
Train steps ... :  19%|█▉        | 18825/100000 [5:16:43<13:09:37,  1.71it/s]Step... (18825 / 100000 | Loss: 1.0680372714996338, Learning Rate: 8.158291457286432e-05)
+
                                                                             
Step... (18825 / 100000 | Loss: 1.1611844301223755, Learning Rate: 8.158291457286432e-05)
+
Train steps ... :  19%|█▉        | 18825/100000 [5:16:44<13:09:37,  1.71it/s]
Train steps ... :  19%|█▉        | 18826/100000 [5:16:44<13:09:54,  1.71it/s]
Train steps ... :  19%|█▉        | 18827/100000 [5:16:44<13:09:53,  1.71it/s]
Train steps ... :  19%|█▉        | 18828/100000 [5:16:45<13:09:21,  1.71it/s]
Train steps ... :  19%|█▉        | 18829/100000 [5:16:46<13:09:27,  1.71it/s]
Train steps ... :  19%|█▉        | 18830/100000 [5:16:46<13:10:53,  1.71it/s]
Train steps ... :  19%|█▉        | 18831/100000 [5:16:47<13:10:30,  1.71it/s]
Train steps ... :  19%|█▉        | 18832/100000 [5:16:47<13:10:15,  1.71it/s]
Train steps ... :  19%|█▉        | 18833/100000 [5:16:48<13:10:17,  1.71it/s]
Train steps ... :  19%|█▉        | 18834/100000 [5:16:48<13:10:01,  1.71it/s]
Train steps ... :  19%|█▉        | 18835/100000 [5:16:49<13:09:56,  1.71it/s]
Train steps ... :  19%|█▉        | 18836/100000 [5:16:50<13:09:45,  1.71it/s]
Train steps ... :  19%|█▉        | 18837/100000 [5:16:50<13:09:26,  1.71it/s]
Train steps ... :  19%|█▉        | 18838/100000 [5:16:51<13:09:13,  1.71it/s]
Train steps ... :  19%|█▉        | 18839/100000 [5:16:51<13:09:28,  1.71it/s]
Train steps ... :  19%|█▉        | 18840/100000 [5:16:52<13:09:17,  1.71it/s]
Train steps ... :  19%|█▉        | 18841/100000 [5:16:53<13:09:46,  1.71it/s]
Train steps ... :  19%|█▉        | 18842/100000 [5:16:53<13:09:48,  1.71it/s]
Train steps ... :  19%|█▉        | 18843/100000 [5:16:54<13:10:52,  1.71it/s]
Train steps ... :  19%|█▉        | 18844/100000 [5:16:54<13:10:50,  1.71it/s]
Train steps ... :  19%|█▉        | 18845/100000 [5:16:55<13:10:57,  1.71it/s]
Train steps ... :  19%|█▉        | 18846/100000 [5:16:55<13:11:36,  1.71it/s]
Train steps ... :  19%|█▉        | 18847/100000 [5:16:56<13:10:31,  1.71it/s]
Train steps ... :  19%|█▉        | 18848/100000 [5:16:57<13:10:00,  1.71it/s]
Train steps ... :  19%|█▉        | 18849/100000 [5:16:57<13:09:50,  1.71it/s]
Train steps ... :  19%|█▉        | 18850/100000 [5:16:58<13:09:40,  1.71it/s]Step... (18850 / 100000 | Loss: 0.70177161693573, Learning Rate: 8.155778894472363e-05)
+
                                                                             
Step... (18850 / 100000 | Loss: 0.9327646493911743, Learning Rate: 8.155778894472363e-05)
+
Train steps ... :  19%|█▉        | 18850/100000 [5:16:58<13:09:40,  1.71it/s]
Train steps ... :  19%|█▉        | 18851/100000 [5:16:58<13:10:14,  1.71it/s]
Train steps ... :  19%|█▉        | 18852/100000 [5:16:59<13:10:56,  1.71it/s]
Train steps ... :  19%|█▉        | 18853/100000 [5:17:00<13:10:32,  1.71it/s]
Train steps ... :  19%|█▉        | 18854/100000 [5:17:00<13:10:00,  1.71it/s]
Train steps ... :  19%|█▉        | 18855/100000 [5:17:01<13:10:17,  1.71it/s]
Train steps ... :  19%|█▉        | 18856/100000 [5:17:01<13:10:39,  1.71it/s]
Train steps ... :  19%|█▉        | 18857/100000 [5:17:02<13:11:09,  1.71it/s]
Train steps ... :  19%|█▉        | 18858/100000 [5:17:02<13:10:46,  1.71it/s]
Train steps ... :  19%|█▉        | 18859/100000 [5:17:03<13:09:54,  1.71it/s]
Train steps ... :  19%|█▉        | 18860/100000 [5:17:04<13:09:57,  1.71it/s]
Train steps ... :  19%|█▉        | 18861/100000 [5:17:04<13:10:19,  1.71it/s]
Train steps ... :  19%|█▉        | 18862/100000 [5:17:05<13:11:12,  1.71it/s]
Train steps ... :  19%|█▉        | 18863/100000 [5:17:05<13:10:36,  1.71it/s]
Train steps ... :  19%|█▉        | 18864/100000 [5:17:06<13:10:19,  1.71it/s]
Train steps ... :  19%|█▉        | 18865/100000 [5:17:07<13:11:41,  1.71it/s]
Train steps ... :  19%|█▉        | 18866/100000 [5:17:07<13:11:13,  1.71it/s]
Train steps ... :  19%|█▉        | 18867/100000 [5:17:08<13:11:19,  1.71it/s]
Train steps ... :  19%|█▉        | 18868/100000 [5:17:08<13:10:45,  1.71it/s]
Train steps ... :  19%|█▉        | 18869/100000 [5:17:09<13:10:04,  1.71it/s]
Train steps ... :  19%|█▉        | 18870/100000 [5:17:09<13:09:36,  1.71it/s]
Train steps ... :  19%|█▉        | 18871/100000 [5:17:10<13:09:07,  1.71it/s]
Train steps ... :  19%|█▉        | 18872/100000 [5:17:11<13:08:54,  1.71it/s]
Train steps ... :  19%|█▉        | 18873/100000 [5:17:11<13:09:02,  1.71it/s]
Train steps ... :  19%|█▉        | 18874/100000 [5:17:12<13:09:18,  1.71it/s]
Train steps ... :  19%|█▉        | 18875/100000 [5:17:12<13:09:37,  1.71it/s]Step... (18875 / 100000 | Loss: 1.1192060708999634, Learning Rate: 8.153266331658291e-05)
+
                                                                             
Step... (18875 / 100000 | Loss: 1.276786208152771, Learning Rate: 8.153266331658291e-05)
+
Train steps ... :  19%|█▉        | 18875/100000 [5:17:13<13:09:37,  1.71it/s]
Train steps ... :  19%|█▉        | 18876/100000 [5:17:13<13:09:56,  1.71it/s]
Train steps ... :  19%|█▉        | 18877/100000 [5:17:14<13:09:24,  1.71it/s]
Train steps ... :  19%|█▉        | 18878/100000 [5:17:14<13:09:05,  1.71it/s]
Train steps ... :  19%|█▉        | 18879/100000 [5:17:15<13:09:28,  1.71it/s]
Train steps ... :  19%|█▉        | 18880/100000 [5:17:15<13:09:05,  1.71it/s]
Train steps ... :  19%|█▉        | 18881/100000 [5:17:16<13:09:13,  1.71it/s]
Train steps ... :  19%|█▉        | 18882/100000 [5:17:16<13:09:42,  1.71it/s]
Train steps ... :  19%|█▉        | 18883/100000 [5:17:17<13:09:48,  1.71it/s]
Train steps ... :  19%|█▉        | 18884/100000 [5:17:18<13:09:37,  1.71it/s]
Train steps ... :  19%|█▉        | 18885/100000 [5:17:18<13:09:03,  1.71it/s]
Train steps ... :  19%|█▉        | 18886/100000 [5:17:19<13:08:47,  1.71it/s]
Train steps ... :  19%|█▉        | 18887/100000 [5:17:19<13:09:01,  1.71it/s]
Train steps ... :  19%|█▉        | 18888/100000 [5:17:20<13:10:15,  1.71it/s]
Train steps ... :  19%|█▉        | 18889/100000 [5:17:21<13:10:10,  1.71it/s]
Train steps ... :  19%|█▉        | 18890/100000 [5:17:21<13:09:17,  1.71it/s]
Train steps ... :  19%|█▉        | 18891/100000 [5:17:22<13:09:02,  1.71it/s]
Train steps ... :  19%|█▉        | 18892/100000 [5:17:22<13:10:08,  1.71it/s]
Train steps ... :  19%|█▉        | 18893/100000 [5:17:23<13:11:04,  1.71it/s]
Train steps ... :  19%|█▉        | 18894/100000 [5:17:23<13:10:56,  1.71it/s]
Train steps ... :  19%|█▉        | 18895/100000 [5:17:24<13:10:21,  1.71it/s]
Train steps ... :  19%|█▉        | 18896/100000 [5:17:25<13:09:58,  1.71it/s]
Train steps ... :  19%|█▉        | 18897/100000 [5:17:25<13:10:08,  1.71it/s]
Train steps ... :  19%|█▉        | 18898/100000 [5:17:26<13:10:11,  1.71it/s]
Train steps ... :  19%|█▉        | 18899/100000 [5:17:26<13:09:37,  1.71it/s]
Train steps ... :  19%|█▉        | 18900/100000 [5:17:27<13:09:58,  1.71it/s]Step... (18900 / 100000 | Loss: 1.0308113098144531, Learning Rate: 8.150753768844221e-05)
+
                                                                             
Step... (18900 / 100000 | Loss: 1.120597004890442, Learning Rate: 8.150753768844221e-05)
+
Train steps ... :  19%|█▉        | 18900/100000 [5:17:27<13:09:58,  1.71it/s]
Train steps ... :  19%|█▉        | 18901/100000 [5:17:28<13:09:43,  1.71it/s]
Train steps ... :  19%|█▉        | 18902/100000 [5:17:28<13:09:12,  1.71it/s]
Train steps ... :  19%|█▉        | 18903/100000 [5:17:29<13:09:13,  1.71it/s]
Train steps ... :  19%|█▉        | 18904/100000 [5:17:29<13:09:24,  1.71it/s]
Train steps ... :  19%|█▉        | 18905/100000 [5:17:30<13:10:11,  1.71it/s]
Train steps ... :  19%|█▉        | 18906/100000 [5:17:31<13:09:33,  1.71it/s]
Train steps ... :  19%|█▉        | 18907/100000 [5:17:31<13:10:24,  1.71it/s]
Train steps ... :  19%|█▉        | 18908/100000 [5:17:32<13:10:35,  1.71it/s]
Train steps ... :  19%|█▉        | 18909/100000 [5:17:32<13:10:34,  1.71it/s]
Train steps ... :  19%|█▉        | 18910/100000 [5:17:33<13:10:51,  1.71it/s]
Train steps ... :  19%|█▉        | 18911/100000 [5:17:33<13:10:16,  1.71it/s]
Train steps ... :  19%|█▉        | 18912/100000 [5:17:34<13:09:43,  1.71it/s]
Train steps ... :  19%|█▉        | 18913/100000 [5:17:35<13:10:10,  1.71it/s]
Train steps ... :  19%|█▉        | 18914/100000 [5:17:35<13:11:00,  1.71it/s]
Train steps ... :  19%|█▉        | 18915/100000 [5:17:36<13:10:35,  1.71it/s]
Train steps ... :  19%|█▉        | 18916/100000 [5:17:36<13:10:19,  1.71it/s]
Train steps ... :  19%|█▉        | 18917/100000 [5:17:37<13:09:55,  1.71it/s]
Train steps ... :  19%|█▉        | 18918/100000 [5:17:38<13:09:38,  1.71it/s]
Train steps ... :  19%|█▉        | 18919/100000 [5:17:38<13:09:45,  1.71it/s]
Train steps ... :  19%|█▉        | 18920/100000 [5:17:39<13:09:10,  1.71it/s]
Train steps ... :  19%|█▉        | 18921/100000 [5:17:39<13:08:39,  1.71it/s]
Train steps ... :  19%|█▉        | 18922/100000 [5:17:40<13:08:56,  1.71it/s]
Train steps ... :  19%|█▉        | 18923/100000 [5:17:40<13:09:43,  1.71it/s]
Train steps ... :  19%|█▉        | 18924/100000 [5:17:41<13:09:11,  1.71it/s]
Train steps ... :  19%|█▉        | 18925/100000 [5:17:42<13:09:36,  1.71it/s]Step... (18925 / 100000 | Loss: 1.1638991832733154, Learning Rate: 8.148241206030152e-05)
+
                                                                             
Step... (18925 / 100000 | Loss: 0.979714572429657, Learning Rate: 8.148241206030152e-05)
+
Train steps ... :  19%|█▉        | 18925/100000 [5:17:42<13:09:36,  1.71it/s]
Train steps ... :  19%|█▉        | 18926/100000 [5:17:42<13:09:12,  1.71it/s]
Train steps ... :  19%|█▉        | 18927/100000 [5:17:43<13:10:17,  1.71it/s]
Train steps ... :  19%|█▉        | 18928/100000 [5:17:43<13:09:22,  1.71it/s]
Train steps ... :  19%|█▉        | 18929/100000 [5:17:44<13:10:06,  1.71it/s]
Train steps ... :  19%|█▉        | 18930/100000 [5:17:45<13:10:23,  1.71it/s]
Train steps ... :  19%|█▉        | 18931/100000 [5:17:45<13:10:28,  1.71it/s]
Train steps ... :  19%|█▉        | 18932/100000 [5:17:46<13:11:06,  1.71it/s]
Train steps ... :  19%|█▉        | 18933/100000 [5:17:46<13:10:42,  1.71it/s]
Train steps ... :  19%|█▉        | 18934/100000 [5:17:47<13:09:50,  1.71it/s]
Train steps ... :  19%|█▉        | 18935/100000 [5:17:47<13:09:20,  1.71it/s]
Train steps ... :  19%|█▉        | 18936/100000 [5:17:48<13:09:38,  1.71it/s]
Train steps ... :  19%|█▉        | 18937/100000 [5:17:49<13:10:40,  1.71it/s]
Train steps ... :  19%|█▉        | 18938/100000 [5:17:49<13:09:49,  1.71it/s]
Train steps ... :  19%|█▉        | 18939/100000 [5:17:50<13:09:50,  1.71it/s]
Train steps ... :  19%|█▉        | 18940/100000 [5:17:50<13:09:36,  1.71it/s]
Train steps ... :  19%|█▉        | 18941/100000 [5:17:51<13:09:29,  1.71it/s]
Train steps ... :  19%|█▉        | 18942/100000 [5:17:52<13:09:10,  1.71it/s]
Train steps ... :  19%|█▉        | 18943/100000 [5:17:52<13:09:38,  1.71it/s]
Train steps ... :  19%|█▉        | 18944/100000 [5:17:53<13:09:11,  1.71it/s]
Train steps ... :  19%|█▉        | 18945/100000 [5:17:53<13:09:00,  1.71it/s]
Train steps ... :  19%|█▉        | 18946/100000 [5:17:54<13:09:18,  1.71it/s]
Train steps ... :  19%|█▉        | 18947/100000 [5:17:54<13:08:50,  1.71it/s]
Train steps ... :  19%|█▉        | 18948/100000 [5:17:55<13:09:41,  1.71it/s]
Train steps ... :  19%|█▉        | 18949/100000 [5:17:56<13:08:58,  1.71it/s]
Train steps ... :  19%|█▉        | 18950/100000 [5:17:56<13:08:58,  1.71it/s]Step... (18950 / 100000 | Loss: 0.7572318315505981, Learning Rate: 8.14572864321608e-05)
+
                                                                             
Step... (18950 / 100000 | Loss: 0.7997657060623169, Learning Rate: 8.14572864321608e-05)
+
Train steps ... :  19%|█▉        | 18950/100000 [5:17:57<13:08:58,  1.71it/s]
Train steps ... :  19%|█▉        | 18951/100000 [5:17:57<13:09:13,  1.71it/s]
Train steps ... :  19%|█▉        | 18952/100000 [5:17:57<13:09:07,  1.71it/s]
Train steps ... :  19%|█▉        | 18953/100000 [5:17:58<13:08:55,  1.71it/s]
Train steps ... :  19%|█▉        | 18954/100000 [5:17:59<13:10:00,  1.71it/s]
Train steps ... :  19%|█▉        | 18955/100000 [5:17:59<13:09:15,  1.71it/s]
Train steps ... :  19%|█▉        | 18956/100000 [5:18:00<13:09:22,  1.71it/s]
Train steps ... :  19%|█▉        | 18957/100000 [5:18:00<13:09:29,  1.71it/s]
Train steps ... :  19%|█▉        | 18958/100000 [5:18:01<13:09:17,  1.71it/s]
Train steps ... :  19%|█▉        | 18959/100000 [5:18:01<13:08:38,  1.71it/s]
Train steps ... :  19%|█▉        | 18960/100000 [5:18:02<13:09:07,  1.71it/s]
Train steps ... :  19%|█▉        | 18961/100000 [5:18:03<13:08:54,  1.71it/s]
Train steps ... :  19%|█▉        | 18962/100000 [5:18:03<13:09:15,  1.71it/s]
Train steps ... :  19%|█▉        | 18963/100000 [5:18:04<13:08:23,  1.71it/s]
Train steps ... :  19%|█▉        | 18964/100000 [5:18:04<13:08:32,  1.71it/s]
Train steps ... :  19%|█▉        | 18965/100000 [5:18:05<13:08:27,  1.71it/s]
Train steps ... :  19%|█▉        | 18966/100000 [5:18:06<13:09:22,  1.71it/s]
Train steps ... :  19%|█▉        | 18967/100000 [5:18:06<13:08:54,  1.71it/s]
Train steps ... :  19%|█▉        | 18968/100000 [5:18:07<13:08:51,  1.71it/s]
Train steps ... :  19%|█▉        | 18969/100000 [5:18:07<13:08:54,  1.71it/s]
Train steps ... :  19%|█▉        | 18970/100000 [5:18:08<13:08:26,  1.71it/s]
Train steps ... :  19%|█▉        | 18971/100000 [5:18:08<13:08:48,  1.71it/s]
Train steps ... :  19%|█▉        | 18972/100000 [5:18:09<13:09:43,  1.71it/s]
Train steps ... :  19%|█▉        | 18973/100000 [5:18:10<13:08:44,  1.71it/s]
Train steps ... :  19%|█▉        | 18974/100000 [5:18:10<13:08:38,  1.71it/s]
Train steps ... :  19%|█▉        | 18975/100000 [5:18:11<13:08:39,  1.71it/s]Step... (18975 / 100000 | Loss: 1.3090815544128418, Learning Rate: 8.143216080402011e-05)
+
                                                                             
Step... (18975 / 100000 | Loss: 0.8175194263458252, Learning Rate: 8.143216080402011e-05)
+
Train steps ... :  19%|█▉        | 18975/100000 [5:18:11<13:08:39,  1.71it/s]
Train steps ... :  19%|█▉        | 18976/100000 [5:18:11<13:08:43,  1.71it/s]
Train steps ... :  19%|█▉        | 18977/100000 [5:18:12<13:09:51,  1.71it/s]
Train steps ... :  19%|█▉        | 18978/100000 [5:18:13<13:09:01,  1.71it/s]
Train steps ... :  19%|█▉        | 18979/100000 [5:18:13<13:09:25,  1.71it/s]
Train steps ... :  19%|█▉        | 18980/100000 [5:18:14<13:09:21,  1.71it/s]
Train steps ... :  19%|█▉        | 18981/100000 [5:18:14<13:09:14,  1.71it/s]
Train steps ... :  19%|█▉        | 18982/100000 [5:18:15<13:08:35,  1.71it/s]
Train steps ... :  19%|█▉        | 18983/100000 [5:18:16<13:09:54,  1.71it/s]
Train steps ... :  19%|█▉        | 18984/100000 [5:18:16<13:11:47,  1.71it/s]
Train steps ... :  19%|█▉        | 18985/100000 [5:18:17<13:10:07,  1.71it/s]
Train steps ... :  19%|█▉        | 18986/100000 [5:18:17<13:09:45,  1.71it/s]
Train steps ... :  19%|█▉        | 18987/100000 [5:18:18<13:08:34,  1.71it/s]
Train steps ... :  19%|█▉        | 18988/100000 [5:18:18<13:08:32,  1.71it/s]
Train steps ... :  19%|█▉        | 18989/100000 [5:18:19<13:09:59,  1.71it/s]
Train steps ... :  19%|█▉        | 18990/100000 [5:18:20<13:10:09,  1.71it/s]
Train steps ... :  19%|█▉        | 18991/100000 [5:18:20<13:10:00,  1.71it/s]
Train steps ... :  19%|█▉        | 18992/100000 [5:18:21<13:09:36,  1.71it/s]
Train steps ... :  19%|█▉        | 18993/100000 [5:18:21<13:09:30,  1.71it/s]
Train steps ... :  19%|█▉        | 18994/100000 [5:18:22<13:09:12,  1.71it/s]
Train steps ... :  19%|█▉        | 18995/100000 [5:18:23<13:08:41,  1.71it/s]
Train steps ... :  19%|█▉        | 18996/100000 [5:18:23<13:08:33,  1.71it/s]
Train steps ... :  19%|█▉        | 18997/100000 [5:18:24<13:08:33,  1.71it/s]
Train steps ... :  19%|█▉        | 18998/100000 [5:18:24<13:08:47,  1.71it/s]
Train steps ... :  19%|█▉        | 18999/100000 [5:18:25<13:08:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19000/100000 [5:18:25<13:09:14,  1.71it/s]Step... (19000 / 100000 | Loss: 0.8914295434951782, Learning Rate: 8.14070351758794e-05)
+
                                                                             
Step... (19000 / 100000 | Loss: 0.8605281114578247, Learning Rate: 8.14070351758794e-05)
+
Train steps ... :  19%|█▉        | 19000/100000 [5:18:26<13:09:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19001/100000 [5:18:26<13:09:11,  1.71it/s]
Train steps ... :  19%|█▉        | 19002/100000 [5:18:27<13:09:24,  1.71it/s]
Train steps ... :  19%|█▉        | 19003/100000 [5:18:27<13:10:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19004/100000 [5:18:28<13:10:18,  1.71it/s]
Train steps ... :  19%|█▉        | 19005/100000 [5:18:28<13:09:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19006/100000 [5:18:29<13:09:19,  1.71it/s]
Train steps ... :  19%|█▉        | 19007/100000 [5:18:30<13:08:18,  1.71it/s]
Train steps ... :  19%|█▉        | 19008/100000 [5:18:30<13:08:19,  1.71it/s]
Train steps ... :  19%|█▉        | 19009/100000 [5:18:31<13:08:46,  1.71it/s]
Train steps ... :  19%|█▉        | 19010/100000 [5:18:31<13:09:04,  1.71it/s]
Train steps ... :  19%|█▉        | 19011/100000 [5:18:32<13:08:36,  1.71it/s]
Train steps ... :  19%|█▉        | 19012/100000 [5:18:32<13:07:54,  1.71it/s]
Train steps ... :  19%|█▉        | 19013/100000 [5:18:33<13:08:45,  1.71it/s]
Train steps ... :  19%|█▉        | 19014/100000 [5:18:34<13:08:06,  1.71it/s]
Train steps ... :  19%|█▉        | 19015/100000 [5:18:34<13:08:00,  1.71it/s]
Train steps ... :  19%|█▉        | 19016/100000 [5:18:35<13:07:54,  1.71it/s]
Train steps ... :  19%|█▉        | 19017/100000 [5:18:35<13:08:24,  1.71it/s]
Train steps ... :  19%|█▉        | 19018/100000 [5:18:36<13:07:48,  1.71it/s]
Train steps ... :  19%|█▉        | 19019/100000 [5:18:37<13:07:44,  1.71it/s]
Train steps ... :  19%|█▉        | 19020/100000 [5:18:37<13:08:41,  1.71it/s]
Train steps ... :  19%|█▉        | 19021/100000 [5:18:38<13:08:25,  1.71it/s]
Train steps ... :  19%|█▉        | 19022/100000 [5:18:38<13:07:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19023/100000 [5:18:39<13:08:11,  1.71it/s]
Train steps ... :  19%|█▉        | 19024/100000 [5:18:39<13:09:08,  1.71it/s]
Train steps ... :  19%|█▉        | 19025/100000 [5:18:40<13:08:39,  1.71it/s]Step... (19025 / 100000 | Loss: 0.9960285425186157, Learning Rate: 8.13819095477387e-05)
+
                                                                             
Step... (19025 / 100000 | Loss: 0.9104254245758057, Learning Rate: 8.13819095477387e-05)
+
Train steps ... :  19%|█▉        | 19025/100000 [5:18:40<13:08:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19026/100000 [5:18:41<13:08:55,  1.71it/s]
Train steps ... :  19%|█▉        | 19027/100000 [5:18:41<13:08:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19028/100000 [5:18:42<13:09:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19029/100000 [5:18:42<13:09:05,  1.71it/s]
Train steps ... :  19%|█▉        | 19030/100000 [5:18:43<13:09:40,  1.71it/s]
Train steps ... :  19%|█▉        | 19031/100000 [5:18:44<13:09:21,  1.71it/s]
Train steps ... :  19%|█▉        | 19032/100000 [5:18:44<13:09:51,  1.71it/s]
Train steps ... :  19%|█▉        | 19033/100000 [5:18:45<13:09:11,  1.71it/s]
Train steps ... :  19%|█▉        | 19034/100000 [5:18:45<13:08:41,  1.71it/s]
Train steps ... :  19%|█▉        | 19035/100000 [5:18:46<13:08:40,  1.71it/s]
Train steps ... :  19%|█▉        | 19036/100000 [5:18:46<13:08:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19037/100000 [5:18:47<13:08:54,  1.71it/s]
Train steps ... :  19%|█▉        | 19038/100000 [5:18:48<13:08:19,  1.71it/s]
Train steps ... :  19%|█▉        | 19039/100000 [5:18:48<13:08:18,  1.71it/s]
Train steps ... :  19%|█▉        | 19040/100000 [5:18:49<13:09:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19041/100000 [5:18:49<13:09:05,  1.71it/s]
Train steps ... :  19%|█▉        | 19042/100000 [5:18:50<13:09:18,  1.71it/s]
Train steps ... :  19%|█▉        | 19043/100000 [5:18:51<13:09:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19044/100000 [5:18:51<13:08:47,  1.71it/s]
Train steps ... :  19%|█▉        | 19045/100000 [5:18:52<13:09:19,  1.71it/s]
Train steps ... :  19%|█▉        | 19046/100000 [5:18:52<13:08:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19047/100000 [5:18:53<13:08:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19048/100000 [5:18:53<13:08:11,  1.71it/s]
Train steps ... :  19%|█▉        | 19049/100000 [5:18:54<13:09:27,  1.71it/s]
Train steps ... :  19%|█▉        | 19050/100000 [5:18:55<13:09:26,  1.71it/s]Step... (19050 / 100000 | Loss: 1.2495661973953247, Learning Rate: 8.135678391959799e-05)
+
                                                                             
Step... (19050 / 100000 | Loss: 0.9427721500396729, Learning Rate: 8.135678391959799e-05)
+
Train steps ... :  19%|█▉        | 19050/100000 [5:18:55<13:09:26,  1.71it/s]
Train steps ... :  19%|█▉        | 19051/100000 [5:18:55<13:09:08,  1.71it/s]
Train steps ... :  19%|█▉        | 19052/100000 [5:18:56<13:08:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19053/100000 [5:18:56<13:08:25,  1.71it/s]
Train steps ... :  19%|█▉        | 19054/100000 [5:18:57<13:08:11,  1.71it/s]
Train steps ... :  19%|█▉        | 19055/100000 [5:18:58<13:10:11,  1.71it/s]
Train steps ... :  19%|█▉        | 19056/100000 [5:18:58<13:09:36,  1.71it/s]
Train steps ... :  19%|█▉        | 19057/100000 [5:18:59<13:09:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19058/100000 [5:18:59<13:08:16,  1.71it/s]
Train steps ... :  19%|█▉        | 19059/100000 [5:19:00<13:08:46,  1.71it/s]
Train steps ... :  19%|█▉        | 19060/100000 [5:19:01<13:09:20,  1.71it/s]
Train steps ... :  19%|█▉        | 19061/100000 [5:19:01<13:08:38,  1.71it/s]
Train steps ... :  19%|█▉        | 19062/100000 [5:19:02<13:08:41,  1.71it/s]
Train steps ... :  19%|█▉        | 19063/100000 [5:19:02<13:09:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19064/100000 [5:19:03<13:08:33,  1.71it/s]
Train steps ... :  19%|█▉        | 19065/100000 [5:19:03<13:09:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19066/100000 [5:19:04<13:08:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19067/100000 [5:19:05<13:09:02,  1.71it/s]
Train steps ... :  19%|█▉        | 19068/100000 [5:19:05<13:09:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19069/100000 [5:19:06<13:09:23,  1.71it/s]
Train steps ... :  19%|█▉        | 19070/100000 [5:19:06<13:09:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19071/100000 [5:19:07<13:07:57,  1.71it/s]
Train steps ... :  19%|█▉        | 19072/100000 [5:19:08<13:07:31,  1.71it/s]
Train steps ... :  19%|█▉        | 19073/100000 [5:19:08<13:07:32,  1.71it/s]
Train steps ... :  19%|█▉        | 19074/100000 [5:19:09<13:08:02,  1.71it/s]
Train steps ... :  19%|█▉        | 19075/100000 [5:19:09<13:07:54,  1.71it/s]Step... (19075 / 100000 | Loss: 1.0694267749786377, Learning Rate: 8.133165829145729e-05)
+
                                                                             
Step... (19075 / 100000 | Loss: 1.0152225494384766, Learning Rate: 8.133165829145729e-05)
+
Train steps ... :  19%|█▉        | 19075/100000 [5:19:10<13:07:54,  1.71it/s]
Train steps ... :  19%|█▉        | 19076/100000 [5:19:10<13:08:02,  1.71it/s]
Train steps ... :  19%|█▉        | 19077/100000 [5:19:10<13:07:35,  1.71it/s]
Train steps ... :  19%|█▉        | 19078/100000 [5:19:11<13:08:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19079/100000 [5:19:12<13:08:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19080/100000 [5:19:12<13:08:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19081/100000 [5:19:13<13:07:19,  1.71it/s]
Train steps ... :  19%|█▉        | 19082/100000 [5:19:13<13:07:29,  1.71it/s]
Train steps ... :  19%|█▉        | 19083/100000 [5:19:14<13:07:27,  1.71it/s]
Train steps ... :  19%|█▉        | 19084/100000 [5:19:15<13:07:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19085/100000 [5:19:15<13:08:10,  1.71it/s]
Train steps ... :  19%|█▉        | 19086/100000 [5:19:16<13:09:20,  1.71it/s]
Train steps ... :  19%|█▉        | 19087/100000 [5:19:16<13:08:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19088/100000 [5:19:17<13:09:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19089/100000 [5:19:17<13:09:06,  1.71it/s]
Train steps ... :  19%|█▉        | 19090/100000 [5:19:18<13:08:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19091/100000 [5:19:19<13:08:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19092/100000 [5:19:19<13:08:38,  1.71it/s]
Train steps ... :  19%|█▉        | 19093/100000 [5:19:20<13:08:05,  1.71it/s]
Train steps ... :  19%|█▉        | 19094/100000 [5:19:20<13:08:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19095/100000 [5:19:21<13:07:45,  1.71it/s]
Train steps ... :  19%|█▉        | 19096/100000 [5:19:22<13:07:03,  1.71it/s]
Train steps ... :  19%|█▉        | 19097/100000 [5:19:22<13:08:05,  1.71it/s]
Train steps ... :  19%|█▉        | 19098/100000 [5:19:23<13:07:33,  1.71it/s]
Train steps ... :  19%|█▉        | 19099/100000 [5:19:23<13:07:29,  1.71it/s]
Train steps ... :  19%|█▉        | 19100/100000 [5:19:24<13:07:58,  1.71it/s]Step... (19100 / 100000 | Loss: 0.6937959790229797, Learning Rate: 8.130653266331658e-05)
+
                                                                             
Step... (19100 / 100000 | Loss: 0.7153791785240173, Learning Rate: 8.130653266331658e-05)
+
Train steps ... :  19%|█▉        | 19100/100000 [5:19:24<13:07:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19101/100000 [5:19:24<13:07:27,  1.71it/s]
Train steps ... :  19%|█▉        | 19102/100000 [5:19:25<13:07:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19103/100000 [5:19:26<13:07:54,  1.71it/s]
Train steps ... :  19%|█▉        | 19104/100000 [5:19:26<13:07:10,  1.71it/s]
Train steps ... :  19%|█▉        | 19105/100000 [5:19:27<13:08:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19106/100000 [5:19:27<13:07:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19107/100000 [5:19:28<13:07:45,  1.71it/s]
Train steps ... :  19%|█▉        | 19108/100000 [5:19:29<13:07:57,  1.71it/s]
Train steps ... :  19%|█▉        | 19109/100000 [5:19:29<13:07:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19110/100000 [5:19:30<13:07:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19111/100000 [5:19:30<13:07:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19112/100000 [5:19:31<13:07:06,  1.71it/s]
Train steps ... :  19%|█▉        | 19113/100000 [5:19:31<13:06:55,  1.71it/s]
Train steps ... :  19%|█▉        | 19114/100000 [5:19:32<13:09:19,  1.71it/s]
Train steps ... :  19%|█▉        | 19115/100000 [5:19:33<13:08:26,  1.71it/s]
Train steps ... :  19%|█▉        | 19116/100000 [5:19:33<13:08:38,  1.71it/s]
Train steps ... :  19%|█▉        | 19117/100000 [5:19:34<13:08:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19118/100000 [5:19:34<13:08:48,  1.71it/s]
Train steps ... :  19%|█▉        | 19119/100000 [5:19:35<13:08:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19120/100000 [5:19:36<13:08:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19121/100000 [5:19:36<13:08:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19122/100000 [5:19:37<13:08:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19123/100000 [5:19:37<13:08:30,  1.71it/s]
Train steps ... :  19%|█▉        | 19124/100000 [5:19:38<13:07:24,  1.71it/s]
Train steps ... :  19%|█▉        | 19125/100000 [5:19:39<13:07:23,  1.71it/s]Step... (19125 / 100000 | Loss: 0.7712568044662476, Learning Rate: 8.128140703517588e-05)
+
                                                                             
Step... (19125 / 100000 | Loss: 0.8666174411773682, Learning Rate: 8.128140703517588e-05)
+
Train steps ... :  19%|█▉        | 19125/100000 [5:19:39<13:07:23,  1.71it/s]
Train steps ... :  19%|█▉        | 19126/100000 [5:19:39<13:08:31,  1.71it/s]
Train steps ... :  19%|█▉        | 19127/100000 [5:19:40<13:08:07,  1.71it/s]
Train steps ... :  19%|█▉        | 19128/100000 [5:19:40<13:08:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19129/100000 [5:19:41<13:08:59,  1.71it/s]
Train steps ... :  19%|█▉        | 19130/100000 [5:19:41<13:08:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19131/100000 [5:19:42<13:08:46,  1.71it/s]
Train steps ... :  19%|█▉        | 19132/100000 [5:19:43<13:08:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19133/100000 [5:19:43<13:08:13,  1.71it/s]
Train steps ... :  19%|█▉        | 19134/100000 [5:19:44<13:08:07,  1.71it/s]
Train steps ... :  19%|█▉        | 19135/100000 [5:19:44<13:07:30,  1.71it/s]
Train steps ... :  19%|█▉        | 19136/100000 [5:19:45<13:07:59,  1.71it/s]
Train steps ... :  19%|█▉        | 19137/100000 [5:19:46<13:08:38,  1.71it/s]
Train steps ... :  19%|█▉        | 19138/100000 [5:19:46<13:07:42,  1.71it/s]
Train steps ... :  19%|█▉        | 19139/100000 [5:19:47<13:07:25,  1.71it/s]
Train steps ... :  19%|█▉        | 19140/100000 [5:19:47<13:08:36,  1.71it/s]
Train steps ... :  19%|█▉        | 19141/100000 [5:19:48<13:09:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19142/100000 [5:19:48<13:08:48,  1.71it/s]
Train steps ... :  19%|█▉        | 19143/100000 [5:19:49<13:07:50,  1.71it/s]
Train steps ... :  19%|█▉        | 19144/100000 [5:19:50<13:06:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19145/100000 [5:19:50<13:07:29,  1.71it/s]
Train steps ... :  19%|█▉        | 19146/100000 [5:19:51<13:07:21,  1.71it/s]
Train steps ... :  19%|█▉        | 19147/100000 [5:19:51<13:07:29,  1.71it/s]
Train steps ... :  19%|█▉        | 19148/100000 [5:19:52<13:06:55,  1.71it/s]
Train steps ... :  19%|█▉        | 19149/100000 [5:19:53<13:07:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19150/100000 [5:19:53<13:07:06,  1.71it/s]Step... (19150 / 100000 | Loss: 0.8931464552879333, Learning Rate: 8.125628140703519e-05)
+
                                                                             
Step... (19150 / 100000 | Loss: 0.9123995304107666, Learning Rate: 8.125628140703519e-05)
+
Train steps ... :  19%|█▉        | 19150/100000 [5:19:53<13:07:06,  1.71it/s]
Train steps ... :  19%|█▉        | 19151/100000 [5:19:54<13:08:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19152/100000 [5:19:54<13:07:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19153/100000 [5:19:55<13:08:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19154/100000 [5:19:55<13:07:32,  1.71it/s]
Train steps ... :  19%|█▉        | 19155/100000 [5:19:56<13:07:51,  1.71it/s]
Train steps ... :  19%|█▉        | 19156/100000 [5:19:57<13:07:45,  1.71it/s]
Train steps ... :  19%|█▉        | 19157/100000 [5:19:57<13:08:02,  1.71it/s]
Train steps ... :  19%|█▉        | 19158/100000 [5:19:58<13:10:35,  1.70it/s]
Train steps ... :  19%|█▉        | 19159/100000 [5:19:58<13:09:02,  1.71it/s]
Train steps ... :  19%|█▉        | 19160/100000 [5:19:59<13:08:35,  1.71it/s]
Train steps ... :  19%|█▉        | 19161/100000 [5:20:00<13:09:07,  1.71it/s]
Train steps ... :  19%|█▉        | 19162/100000 [5:20:00<13:07:41,  1.71it/s]
Train steps ... :  19%|█▉        | 19163/100000 [5:20:01<13:07:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19164/100000 [5:20:01<13:09:20,  1.71it/s]
Train steps ... :  19%|█▉        | 19165/100000 [5:20:02<13:11:13,  1.70it/s]
Train steps ... :  19%|█▉        | 19166/100000 [5:20:02<13:08:45,  1.71it/s]
Train steps ... :  19%|█▉        | 19167/100000 [5:20:03<13:08:21,  1.71it/s]
Train steps ... :  19%|█▉        | 19168/100000 [5:20:04<13:09:06,  1.71it/s]
Train steps ... :  19%|█▉        | 19169/100000 [5:20:04<13:08:02,  1.71it/s]
Train steps ... :  19%|█▉        | 19170/100000 [5:20:05<13:07:20,  1.71it/s]
Train steps ... :  19%|█▉        | 19171/100000 [5:20:05<13:07:04,  1.71it/s]
Train steps ... :  19%|█▉        | 19172/100000 [5:20:06<13:09:21,  1.71it/s]
Train steps ... :  19%|█▉        | 19173/100000 [5:20:07<13:07:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19174/100000 [5:20:07<13:06:42,  1.71it/s]
Train steps ... :  19%|█▉        | 19175/100000 [5:20:08<13:06:58,  1.71it/s]Step... (19175 / 100000 | Loss: 0.9808655977249146, Learning Rate: 8.123115577889447e-05)
+
                                                                             
Step... (19175 / 100000 | Loss: 1.0284366607666016, Learning Rate: 8.123115577889447e-05)
+
Train steps ... :  19%|█▉        | 19175/100000 [5:20:08<13:06:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19176/100000 [5:20:08<13:09:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19177/100000 [5:20:09<13:09:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19178/100000 [5:20:10<13:08:37,  1.71it/s]
Train steps ... :  19%|█▉        | 19179/100000 [5:20:10<13:08:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19180/100000 [5:20:11<13:08:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19181/100000 [5:20:11<13:07:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19182/100000 [5:20:12<13:08:01,  1.71it/s]
Train steps ... :  19%|█▉        | 19183/100000 [5:20:12<13:08:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19184/100000 [5:20:13<13:07:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19185/100000 [5:20:14<13:07:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19186/100000 [5:20:14<13:06:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19187/100000 [5:20:15<13:06:56,  1.71it/s]
Train steps ... :  19%|█▉        | 19188/100000 [5:20:15<13:06:37,  1.71it/s]
Train steps ... :  19%|█▉        | 19189/100000 [5:20:16<13:06:50,  1.71it/s]
Train steps ... :  19%|█▉        | 19190/100000 [5:20:17<13:07:26,  1.71it/s]
Train steps ... :  19%|█▉        | 19191/100000 [5:20:17<13:06:55,  1.71it/s]
Train steps ... :  19%|█▉        | 19192/100000 [5:20:18<13:06:44,  1.71it/s]
Train steps ... :  19%|█▉        | 19193/100000 [5:20:18<13:07:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19194/100000 [5:20:19<13:07:25,  1.71it/s]
Train steps ... :  19%|█▉        | 19195/100000 [5:20:19<13:06:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19196/100000 [5:20:20<13:07:08,  1.71it/s]
Train steps ... :  19%|█▉        | 19197/100000 [5:20:21<13:06:59,  1.71it/s]
Train steps ... :  19%|█▉        | 19198/100000 [5:20:21<13:06:35,  1.71it/s]
Train steps ... :  19%|█▉        | 19199/100000 [5:20:22<13:06:00,  1.71it/s]
Train steps ... :  19%|█▉        | 19200/100000 [5:20:22<13:06:11,  1.71it/s]Step... (19200 / 100000 | Loss: 1.327913761138916, Learning Rate: 8.120603015075378e-05)
+
                                                                             
Step... (19200 / 100000 | Loss: 1.0077916383743286, Learning Rate: 8.120603015075378e-05)
+
Train steps ... :  19%|█▉        | 19200/100000 [5:20:23<13:06:11,  1.71it/s]
Train steps ... :  19%|█▉        | 19201/100000 [5:20:23<13:07:43,  1.71it/s]
Train steps ... :  19%|█▉        | 19202/100000 [5:20:24<13:07:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19203/100000 [5:20:24<13:07:59,  1.71it/s]
Train steps ... :  19%|█▉        | 19204/100000 [5:20:25<13:07:07,  1.71it/s]
Train steps ... :  19%|█▉        | 19205/100000 [5:20:25<13:06:36,  1.71it/s]
Train steps ... :  19%|█▉        | 19206/100000 [5:20:26<13:07:17,  1.71it/s]
Train steps ... :  19%|���▉        | 19207/100000 [5:20:26<13:06:41,  1.71it/s]
Train steps ... :  19%|█▉        | 19208/100000 [5:20:27<13:07:42,  1.71it/s]
Train steps ... :  19%|█▉        | 19209/100000 [5:20:28<13:07:36,  1.71it/s]
Train steps ... :  19%|█▉        | 19210/100000 [5:20:28<13:07:03,  1.71it/s]
Train steps ... :  19%|█▉        | 19211/100000 [5:20:29<13:06:37,  1.71it/s]
Train steps ... :  19%|█▉        | 19212/100000 [5:20:29<13:06:35,  1.71it/s]
Train steps ... :  19%|█▉        | 19213/100000 [5:20:30<13:06:31,  1.71it/s]
Train steps ... :  19%|█▉        | 19214/100000 [5:20:31<13:06:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19215/100000 [5:20:31<13:06:42,  1.71it/s]
Train steps ... :  19%|█▉        | 19216/100000 [5:20:32<13:06:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19217/100000 [5:20:32<13:07:00,  1.71it/s]
Train steps ... :  19%|█▉        | 19218/100000 [5:20:33<13:06:31,  1.71it/s]
Train steps ... :  19%|█▉        | 19219/100000 [5:20:33<13:06:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19220/100000 [5:20:34<13:07:06,  1.71it/s]
Train steps ... :  19%|█▉        | 19221/100000 [5:20:35<13:07:16,  1.71it/s]
Train steps ... :  19%|█▉        | 19222/100000 [5:20:35<13:06:19,  1.71it/s]
Train steps ... :  19%|█▉        | 19223/100000 [5:20:36<13:06:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19224/100000 [5:20:36<13:07:23,  1.71it/s]
Train steps ... :  19%|█▉        | 19225/100000 [5:20:37<13:07:14,  1.71it/s]Step... (19225 / 100000 | Loss: 1.1729958057403564, Learning Rate: 8.118090452261307e-05)
+
                                                                             
Step... (19225 / 100000 | Loss: 1.2497252225875854, Learning Rate: 8.118090452261307e-05)
+
Train steps ... :  19%|█▉        | 19225/100000 [5:20:37<13:07:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19226/100000 [5:20:38<13:07:34,  1.71it/s]
Train steps ... :  19%|█▉        | 19227/100000 [5:20:38<13:06:56,  1.71it/s]
Train steps ... :  19%|█▉        | 19228/100000 [5:20:39<13:06:56,  1.71it/s]
Train steps ... :  19%|█▉        | 19229/100000 [5:20:39<13:06:21,  1.71it/s]
Train steps ... :  19%|█▉        | 19230/100000 [5:20:40<13:07:21,  1.71it/s]
Train steps ... :  19%|█▉        | 19231/100000 [5:20:40<13:07:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19232/100000 [5:20:41<13:07:08,  1.71it/s]
Train steps ... :  19%|█▉        | 19233/100000 [5:20:42<13:07:23,  1.71it/s]
Train steps ... :  19%|█▉        | 19234/100000 [5:20:42<13:07:51,  1.71it/s]
Train steps ... :  19%|█▉        | 19235/100000 [5:20:43<13:07:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19236/100000 [5:20:43<13:07:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19237/100000 [5:20:44<13:07:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19238/100000 [5:20:45<13:08:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19239/100000 [5:20:45<13:08:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19240/100000 [5:20:46<13:08:16,  1.71it/s]
Train steps ... :  19%|█▉        | 19241/100000 [5:20:46<13:07:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19242/100000 [5:20:47<13:07:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19243/100000 [5:20:48<13:07:38,  1.71it/s]
Train steps ... :  19%|█▉        | 19244/100000 [5:20:48<13:07:23,  1.71it/s]
Train steps ... :  19%|█▉        | 19245/100000 [5:20:49<13:10:07,  1.70it/s]
Train steps ... :  19%|█▉        | 19246/100000 [5:20:49<13:09:28,  1.70it/s]
Train steps ... :  19%|█▉        | 19247/100000 [5:20:50<13:10:06,  1.70it/s]
Train steps ... :  19%|█▉        | 19248/100000 [5:20:50<13:08:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19249/100000 [5:20:51<13:08:50,  1.71it/s]
Train steps ... :  19%|█▉        | 19250/100000 [5:20:52<13:09:20,  1.71it/s]Step... (19250 / 100000 | Loss: 1.0582466125488281, Learning Rate: 8.115577889447236e-05)
+
                                                                             
Step... (19250 / 100000 | Loss: 1.0960144996643066, Learning Rate: 8.115577889447236e-05)
+
Train steps ... :  19%|█▉        | 19250/100000 [5:20:52<13:09:20,  1.71it/s]
Train steps ... :  19%|█▉        | 19251/100000 [5:20:52<13:07:56,  1.71it/s]
Train steps ... :  19%|█▉        | 19252/100000 [5:20:53<13:08:21,  1.71it/s]
Train steps ... :  19%|█▉        | 19253/100000 [5:20:53<13:10:08,  1.70it/s]
Train steps ... :  19%|█▉        | 19254/100000 [5:20:54<13:09:02,  1.71it/s]
Train steps ... :  19%|█▉        | 19255/100000 [5:20:55<13:08:46,  1.71it/s]
Train steps ... :  19%|█▉        | 19256/100000 [5:20:55<13:08:08,  1.71it/s]
Train steps ... :  19%|█▉        | 19257/100000 [5:20:56<13:09:31,  1.70it/s]
Train steps ... :  19%|█▉        | 19258/100000 [5:20:56<13:10:08,  1.70it/s]
Train steps ... :  19%|█▉        | 19259/100000 [5:20:57<13:08:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19260/100000 [5:20:57<13:08:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19261/100000 [5:20:58<13:07:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19262/100000 [5:20:59<13:08:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19263/100000 [5:20:59<13:06:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19264/100000 [5:21:00<13:06:42,  1.71it/s]
Train steps ... :  19%|█▉        | 19265/100000 [5:21:00<13:10:33,  1.70it/s]
Train steps ... :  19%|█▉        | 19266/100000 [5:21:01<13:08:35,  1.71it/s]
Train steps ... :  19%|█▉        | 19267/100000 [5:21:02<13:07:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19268/100000 [5:21:02<13:09:30,  1.70it/s]
Train steps ... :  19%|█▉        | 19269/100000 [5:21:03<13:08:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19270/100000 [5:21:03<13:09:03,  1.71it/s]
Train steps ... :  19%|█▉        | 19271/100000 [5:21:04<13:07:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19272/100000 [5:21:05<13:08:13,  1.71it/s]
Train steps ... :  19%|█▉        | 19273/100000 [5:21:05<13:07:21,  1.71it/s]
Train steps ... :  19%|█▉        | 19274/100000 [5:21:06<13:08:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19275/100000 [5:21:06<13:07:53,  1.71it/s]Step... (19275 / 100000 | Loss: 0.9191663265228271, Learning Rate: 8.113065326633166e-05)
+
                                                                             
Step... (19275 / 100000 | Loss: 1.4400660991668701, Learning Rate: 8.113065326633166e-05)
+
Train steps ... :  19%|█▉        | 19275/100000 [5:21:07<13:07:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19276/100000 [5:21:07<13:07:47,  1.71it/s]
Train steps ... :  19%|█▉        | 19277/100000 [5:21:07<13:07:06,  1.71it/s]
Train steps ... :  19%|█▉        | 19278/100000 [5:21:08<13:06:56,  1.71it/s]
Train steps ... :  19%|█▉        | 19279/100000 [5:21:09<13:06:30,  1.71it/s]
Train steps ... :  19%|█▉        | 19280/100000 [5:21:09<13:06:38,  1.71it/s]
Train steps ... :  19%|█▉        | 19281/100000 [5:21:10<13:06:46,  1.71it/s]
Train steps ... :  19%|█▉        | 19282/100000 [5:21:10<13:06:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19283/100000 [5:21:11<13:06:16,  1.71it/s]
Train steps ... :  19%|█▉        | 19284/100000 [5:21:12<13:06:24,  1.71it/s]
Train steps ... :  19%|█▉        | 19285/100000 [5:21:12<13:07:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19286/100000 [5:21:13<13:07:50,  1.71it/s]
Train steps ... :  19%|█▉        | 19287/100000 [5:21:13<13:07:07,  1.71it/s]
Train steps ... :  19%|█▉        | 19288/100000 [5:21:14<13:07:36,  1.71it/s]
Train steps ... :  19%|█▉        | 19289/100000 [5:21:14<13:07:34,  1.71it/s]
Train steps ... :  19%|█▉        | 19290/100000 [5:21:15<13:06:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19291/100000 [5:21:16<13:07:19,  1.71it/s]
Train steps ... :  19%|█▉        | 19292/100000 [5:21:16<13:07:35,  1.71it/s]
Train steps ... :  19%|█▉        | 19293/100000 [5:21:17<13:07:26,  1.71it/s]
Train steps ... :  19%|█▉        | 19294/100000 [5:21:17<13:07:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19295/100000 [5:21:18<13:07:08,  1.71it/s]
Train steps ... :  19%|█▉        | 19296/100000 [5:21:19<13:06:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19297/100000 [5:21:19<13:07:11,  1.71it/s]
Train steps ... :  19%|█▉        | 19298/100000 [5:21:20<13:07:46,  1.71it/s]
Train steps ... :  19%|█▉        | 19299/100000 [5:21:20<13:10:39,  1.70it/s]
Train steps ... :  19%|█▉        | 19300/100000 [5:21:21<13:08:55,  1.70it/s]Step... (19300 / 100000 | Loss: 0.9582332968711853, Learning Rate: 8.110552763819096e-05)
+
                                                                             
Step... (19300 / 100000 | Loss: 0.7617912888526917, Learning Rate: 8.110552763819096e-05)
+
Train steps ... :  19%|█▉        | 19300/100000 [5:21:21<13:08:55,  1.70it/s]
Train steps ... :  19%|█▉        | 19301/100000 [5:21:21<13:08:54,  1.70it/s]
Train steps ... :  19%|█▉        | 19302/100000 [5:21:22<13:09:04,  1.70it/s]
Train steps ... :  19%|█▉        | 19303/100000 [5:21:23<13:08:31,  1.71it/s]
Train steps ... :  19%|█▉        | 19304/100000 [5:21:23<13:09:09,  1.70it/s]
Train steps ... :  19%|█▉        | 19305/100000 [5:21:24<13:08:40,  1.71it/s]
Train steps ... :  19%|█▉        | 19306/100000 [5:21:24<13:07:42,  1.71it/s]
Train steps ... :  19%|█▉        | 19307/100000 [5:21:25<13:09:47,  1.70it/s]
Train steps ... :  19%|█▉        | 19308/100000 [5:21:26<13:09:23,  1.70it/s]
Train steps ... :  19%|█▉        | 19309/100000 [5:21:26<13:06:40,  1.71it/s]
Train steps ... :  19%|█▉        | 19310/100000 [5:21:27<13:10:13,  1.70it/s]
Train steps ... :  19%|█▉        | 19311/100000 [5:21:27<13:08:51,  1.70it/s]
Train steps ... :  19%|█▉        | 19312/100000 [5:21:28<13:09:06,  1.70it/s]
Train steps ... :  19%|█▉        | 19313/100000 [5:21:29<13:08:16,  1.71it/s]
Train steps ... :  19%|█▉        | 19314/100000 [5:21:29<13:08:00,  1.71it/s]
Train steps ... :  19%|█▉        | 19315/100000 [5:21:30<13:07:38,  1.71it/s]
Train steps ... :  19%|█▉        | 19316/100000 [5:21:30<13:09:17,  1.70it/s]
Train steps ... :  19%|█▉        | 19317/100000 [5:21:31<13:07:32,  1.71it/s]
Train steps ... :  19%|█▉        | 19318/100000 [5:21:31<13:08:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19319/100000 [5:21:32<13:08:21,  1.71it/s]
Train steps ... :  19%|█▉        | 19320/100000 [5:21:33<13:05:37,  1.71it/s]
Train steps ... :  19%|█▉        | 19321/100000 [5:21:33<13:07:54,  1.71it/s]
Train steps ... :  19%|█▉        | 19322/100000 [5:21:34<13:07:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19323/100000 [5:21:34<13:07:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19324/100000 [5:21:35<13:08:56,  1.70it/s]
Train steps ... :  19%|█▉        | 19325/100000 [5:21:36<13:06:48,  1.71it/s]Step... (19325 / 100000 | Loss: 1.3371336460113525, Learning Rate: 8.108040201005027e-05)
+
                                                                             
Step... (19325 / 100000 | Loss: 0.7661670446395874, Learning Rate: 8.108040201005027e-05)
+
Train steps ... :  19%|█▉        | 19325/100000 [5:21:36<13:06:48,  1.71it/s]
Train steps ... :  19%|█▉        | 19326/100000 [5:21:36<13:08:49,  1.70it/s]
Train steps ... :  19%|█▉        | 19327/100000 [5:21:37<13:07:13,  1.71it/s]
Train steps ... :  19%|█▉        | 19328/100000 [5:21:37<13:07:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19329/100000 [5:21:38<13:07:08,  1.71it/s]
Train steps ... :  19%|█▉        | 19330/100000 [5:21:38<13:07:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19331/100000 [5:21:39<13:07:16,  1.71it/s]
Train steps ... :  19%|█▉        | 19332/100000 [5:21:40<13:07:23,  1.71it/s]
Train steps ... :  19%|█▉        | 19333/100000 [5:21:40<13:06:20,  1.71it/s]
Train steps ... :  19%|█▉        | 19334/100000 [5:21:41<13:07:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19335/100000 [5:21:41<13:06:32,  1.71it/s]
Train steps ... :  19%|█▉        | 19336/100000 [5:21:42<13:06:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19337/100000 [5:21:43<13:07:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19338/100000 [5:21:43<13:07:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19339/100000 [5:21:44<13:06:48,  1.71it/s]
Train steps ... :  19%|█▉        | 19340/100000 [5:21:44<13:06:32,  1.71it/s]
Train steps ... :  19%|█▉        | 19341/100000 [5:21:45<13:08:05,  1.71it/s]
Train steps ... :  19%|█▉        | 19342/100000 [5:21:46<13:08:06,  1.71it/s]
Train steps ... :  19%|█▉        | 19343/100000 [5:21:46<13:07:19,  1.71it/s]
Train steps ... :  19%|█▉        | 19344/100000 [5:21:47<13:07:35,  1.71it/s]
Train steps ... :  19%|█▉        | 19345/100000 [5:21:47<13:07:34,  1.71it/s]
Train steps ... :  19%|█▉        | 19346/100000 [5:21:48<13:06:01,  1.71it/s]
Train steps ... :  19%|█▉        | 19347/100000 [5:21:48<13:06:44,  1.71it/s]
Train steps ... :  19%|█▉        | 19348/100000 [5:21:49<13:07:11,  1.71it/s]
Train steps ... :  19%|█▉        | 19349/100000 [5:21:50<13:07:41,  1.71it/s]
Train steps ... :  19%|█▉        | 19350/100000 [5:21:50<13:09:41,  1.70it/s]Step... (19350 / 100000 | Loss: 1.4476128816604614, Learning Rate: 8.105527638190955e-05)
+
                                                                             
Step... (19350 / 100000 | Loss: 0.8597778677940369, Learning Rate: 8.105527638190955e-05)
+
Train steps ... :  19%|█▉        | 19350/100000 [5:21:51<13:09:41,  1.70it/s]
Train steps ... :  19%|█▉        | 19351/100000 [5:21:51<13:08:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19352/100000 [5:21:51<13:08:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19353/100000 [5:21:52<13:11:58,  1.70it/s]
Train steps ... :  19%|█▉        | 19354/100000 [5:21:53<13:07:44,  1.71it/s]
Train steps ... :  19%|█▉        | 19355/100000 [5:21:53<13:07:40,  1.71it/s]
Train steps ... :  19%|█▉        | 19356/100000 [5:21:54<13:06:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19357/100000 [5:21:54<13:07:34,  1.71it/s]
Train steps ... :  19%|█▉        | 19358/100000 [5:21:55<13:06:34,  1.71it/s]
Train steps ... :  19%|█▉        | 19359/100000 [5:21:55<13:05:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19360/100000 [5:21:56<13:07:13,  1.71it/s]
Train steps ... :  19%|█▉        | 19361/100000 [5:21:57<13:07:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19362/100000 [5:21:57<13:06:26,  1.71it/s]
Train steps ... :  19%|█▉        | 19363/100000 [5:21:58<13:06:47,  1.71it/s]
Train steps ... :  19%|█▉        | 19364/100000 [5:21:58<13:07:02,  1.71it/s]
Train steps ... :  19%|█▉        | 19365/100000 [5:21:59<13:06:44,  1.71it/s]
Train steps ... :  19%|█▉        | 19366/100000 [5:22:00<13:06:56,  1.71it/s]
Train steps ... :  19%|█▉        | 19367/100000 [5:22:00<13:06:08,  1.71it/s]
Train steps ... :  19%|█▉        | 19368/100000 [5:22:01<13:05:41,  1.71it/s]
Train steps ... :  19%|█▉        | 19369/100000 [5:22:01<13:06:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19370/100000 [5:22:02<13:07:10,  1.71it/s]
Train steps ... :  19%|█▉        | 19371/100000 [5:22:02<13:06:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19372/100000 [5:22:03<13:07:00,  1.71it/s]
Train steps ... :  19%|█▉        | 19373/100000 [5:22:04<13:07:18,  1.71it/s]
Train steps ... :  19%|█▉        | 19374/100000 [5:22:04<13:06:34,  1.71it/s]
Train steps ... :  19%|█▉        | 19375/100000 [5:22:05<13:05:15,  1.71it/s]Step... (19375 / 100000 | Loss: 0.9385749101638794, Learning Rate: 8.103015075376886e-05)
+
                                                                             
Step... (19375 / 100000 | Loss: 0.9629145264625549, Learning Rate: 8.103015075376886e-05)
+
Train steps ... :  19%|█▉        | 19375/100000 [5:22:05<13:05:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19376/100000 [5:22:05<13:05:33,  1.71it/s]
Train steps ... :  19%|█▉        | 19377/100000 [5:22:06<13:05:42,  1.71it/s]
Train steps ... :  19%|█▉        | 19378/100000 [5:22:07<13:05:13,  1.71it/s]
Train steps ... :  19%|█▉        | 19379/100000 [5:22:07<13:05:11,  1.71it/s]
Train steps ... :  19%|█▉        | 19380/100000 [5:22:08<13:04:50,  1.71it/s]
Train steps ... :  19%|█▉        | 19381/100000 [5:22:08<13:05:16,  1.71it/s]
Train steps ... :  19%|█▉        | 19382/100000 [5:22:09<13:05:32,  1.71it/s]
Train steps ... :  19%|█▉        | 19383/100000 [5:22:10<13:05:46,  1.71it/s]
Train steps ... :  19%|█▉        | 19384/100000 [5:22:10<13:06:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19385/100000 [5:22:11<13:04:54,  1.71it/s]
Train steps ... :  19%|█▉        | 19386/100000 [5:22:11<13:04:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19387/100000 [5:22:12<13:05:40,  1.71it/s]
Train steps ... :  19%|█▉        | 19388/100000 [5:22:12<13:04:38,  1.71it/s]
Train steps ... :  19%|█▉        | 19389/100000 [5:22:13<13:05:08,  1.71it/s]
Train steps ... :  19%|█▉        | 19390/100000 [5:22:14<13:05:50,  1.71it/s]
Train steps ... :  19%|█▉        | 19391/100000 [5:22:14<13:06:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19392/100000 [5:22:15<13:05:42,  1.71it/s]
Train steps ... :  19%|█▉        | 19393/100000 [5:22:15<13:06:37,  1.71it/s]
Train steps ... :  19%|█▉        | 19394/100000 [5:22:16<13:05:25,  1.71it/s]
Train steps ... :  19%|█▉        | 19395/100000 [5:22:17<13:05:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19396/100000 [5:22:17<13:04:51,  1.71it/s]
Train steps ... :  19%|█▉        | 19397/100000 [5:22:18<13:04:44,  1.71it/s]
Train steps ... :  19%|█▉        | 19398/100000 [5:22:18<13:05:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19399/100000 [5:22:19<13:06:01,  1.71it/s]
Train steps ... :  19%|█▉        | 19400/100000 [5:22:19<13:05:52,  1.71it/s]Step... (19400 / 100000 | Loss: 1.0174789428710938, Learning Rate: 8.100502512562814e-05)
+
                                                                             
Step... (19400 / 100000 | Loss: 0.8507622480392456, Learning Rate: 8.100502512562814e-05)
+
Train steps ... :  19%|█▉        | 19400/100000 [5:22:20<13:05:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19401/100000 [5:22:20<13:05:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19402/100000 [5:22:21<13:05:27,  1.71it/s]
Train steps ... :  19%|█▉        | 19403/100000 [5:22:21<13:05:40,  1.71it/s]
Train steps ... :  19%|█▉        | 19404/100000 [5:22:22<13:05:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19405/100000 [5:22:22<13:05:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19406/100000 [5:22:23<13:05:16,  1.71it/s]
Train steps ... :  19%|█▉        | 19407/100000 [5:22:24<13:05:42,  1.71it/s]
Train steps ... :  19%|█▉        | 19408/100000 [5:22:24<13:05:38,  1.71it/s]
Train steps ... :  19%|█▉        | 19409/100000 [5:22:25<13:06:00,  1.71it/s]
Train steps ... :  19%|█▉        | 19410/100000 [5:22:25<13:04:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19411/100000 [5:22:26<13:04:26,  1.71it/s]
Train steps ... :  19%|█▉        | 19412/100000 [5:22:26<13:04:14,  1.71it/s]
Train steps ... :  19%|█▉        | 19413/100000 [5:22:27<13:04:06,  1.71it/s]
Train steps ... :  19%|█▉        | 19414/100000 [5:22:28<13:04:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19415/100000 [5:22:28<13:04:43,  1.71it/s]
Train steps ... :  19%|█▉        | 19416/100000 [5:22:29<13:04:30,  1.71it/s]
Train steps ... :  19%|█▉        | 19417/100000 [5:22:29<13:04:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19418/100000 [5:22:30<13:05:05,  1.71it/s]
Train steps ... :  19%|█▉        | 19419/100000 [5:22:31<13:05:25,  1.71it/s]
Train steps ... :  19%|█▉        | 19420/100000 [5:22:31<13:04:49,  1.71it/s]
Train steps ... :  19%|█▉        | 19421/100000 [5:22:32<13:05:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19422/100000 [5:22:32<13:04:40,  1.71it/s]
Train steps ... :  19%|█▉        | 19423/100000 [5:22:33<13:04:34,  1.71it/s]
Train steps ... :  19%|█▉        | 19424/100000 [5:22:33<13:05:00,  1.71it/s]
Train steps ... :  19%|█▉        | 19425/100000 [5:22:34<13:04:17,  1.71it/s]Step... (19425 / 100000 | Loss: 0.7245700359344482, Learning Rate: 8.097989949748744e-05)
+
                                                                             
Step... (19425 / 100000 | Loss: 1.2260510921478271, Learning Rate: 8.097989949748744e-05)
+
Train steps ... :  19%|█▉        | 19425/100000 [5:22:34<13:04:17,  1.71it/s]
Train steps ... :  19%|█▉        | 19426/100000 [5:22:35<13:06:13,  1.71it/s]
Train steps ... :  19%|█▉        | 19427/100000 [5:22:35<13:04:42,  1.71it/s]
Train steps ... :  19%|█▉        | 19428/100000 [5:22:36<13:04:27,  1.71it/s]
Train steps ... :  19%|█▉        | 19429/100000 [5:22:36<13:04:07,  1.71it/s]
Train steps ... :  19%|█▉        | 19430/100000 [5:22:37<13:03:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19431/100000 [5:22:38<13:03:43,  1.71it/s]
Train steps ... :  19%|█▉        | 19432/100000 [5:22:38<13:04:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19433/100000 [5:22:39<13:04:23,  1.71it/s]
Train steps ... :  19%|█▉        | 19434/100000 [5:22:39<13:04:31,  1.71it/s]
Train steps ... :  19%|█▉        | 19435/100000 [5:22:40<13:03:59,  1.71it/s]
Train steps ... :  19%|█▉        | 19436/100000 [5:22:40<13:03:50,  1.71it/s]
Train steps ... :  19%|█▉        | 19437/100000 [5:22:41<13:04:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19438/100000 [5:22:42<13:04:44,  1.71it/s]
Train steps ... :  19%|█▉        | 19439/100000 [5:22:42<13:04:08,  1.71it/s]
Train steps ... :  19%|█▉        | 19440/100000 [5:22:43<13:04:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19441/100000 [5:22:43<13:04:32,  1.71it/s]
Train steps ... :  19%|█▉        | 19442/100000 [5:22:44<13:05:00,  1.71it/s]
Train steps ... :  19%|█▉        | 19443/100000 [5:22:45<13:04:55,  1.71it/s]
Train steps ... :  19%|█▉        | 19444/100000 [5:22:45<13:05:09,  1.71it/s]
Train steps ... :  19%|█▉        | 19445/100000 [5:22:46<13:06:20,  1.71it/s]
Train steps ... :  19%|█▉        | 19446/100000 [5:22:46<13:06:27,  1.71it/s]
Train steps ... :  19%|█▉        | 19447/100000 [5:22:47<13:06:35,  1.71it/s]
Train steps ... :  19%|█▉        | 19448/100000 [5:22:48<13:08:02,  1.70it/s]
Train steps ... :  19%|█▉        | 19449/100000 [5:22:48<13:05:03,  1.71it/s]
Train steps ... :  19%|█▉        | 19450/100000 [5:22:49<13:05:16,  1.71it/s]Step... (19450 / 100000 | Loss: 1.0622899532318115, Learning Rate: 8.095477386934673e-05)
+
                                                                             
Step... (19450 / 100000 | Loss: 1.1459966897964478, Learning Rate: 8.095477386934673e-05)
+
Train steps ... :  19%|█▉        | 19450/100000 [5:22:49<13:05:16,  1.71it/s]
Train steps ... :  19%|█▉        | 19451/100000 [5:22:49<13:05:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19452/100000 [5:22:50<13:05:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19453/100000 [5:22:50<13:05:30,  1.71it/s]
Train steps ... :  19%|█▉        | 19454/100000 [5:22:51<13:06:41,  1.71it/s]
Train steps ... :  19%|█▉        | 19455/100000 [5:22:52<13:05:36,  1.71it/s]
Train steps ... :  19%|█▉        | 19456/100000 [5:22:52<13:04:51,  1.71it/s]
Train steps ... :  19%|█▉        | 19457/100000 [5:22:53<13:04:43,  1.71it/s]
Train steps ... :  19%|█▉        | 19458/100000 [5:22:53<13:04:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19459/100000 [5:22:54<13:04:24,  1.71it/s]
Train steps ... :  19%|█▉        | 19460/100000 [5:22:55<13:03:52,  1.71it/s]
Train steps ... :  19%|█▉        | 19461/100000 [5:22:55<13:03:41,  1.71it/s]
Train steps ... :  19%|█▉        | 19462/100000 [5:22:56<13:04:51,  1.71it/s]
Train steps ... :  19%|█▉        | 19463/100000 [5:22:56<13:05:12,  1.71it/s]
Train steps ... :  19%|█▉        | 19464/100000 [5:22:57<13:04:47,  1.71it/s]
Train steps ... :  19%|█▉        | 19465/100000 [5:22:57<13:05:38,  1.71it/s]
Train steps ... :  19%|█▉        | 19466/100000 [5:22:58<13:05:05,  1.71it/s]
Train steps ... :  19%|█▉        | 19467/100000 [5:22:59<13:04:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19468/100000 [5:22:59<13:04:37,  1.71it/s]
Train steps ... :  19%|█▉        | 19469/100000 [5:23:00<13:04:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19470/100000 [5:23:00<13:05:01,  1.71it/s]
Train steps ... :  19%|█▉        | 19471/100000 [5:23:01<13:04:51,  1.71it/s]
Train steps ... :  19%|█▉        | 19472/100000 [5:23:02<13:05:03,  1.71it/s]
Train steps ... :  19%|█▉        | 19473/100000 [5:23:02<13:04:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19474/100000 [5:23:03<13:03:53,  1.71it/s]
Train steps ... :  19%|█▉        | 19475/100000 [5:23:03<13:03:32,  1.71it/s]Step... (19475 / 100000 | Loss: 0.9301275014877319, Learning Rate: 8.092964824120603e-05)
+
                                                                             
Step... (19475 / 100000 | Loss: 1.1604645252227783, Learning Rate: 8.092964824120603e-05)
+
Train steps ... :  19%|█▉        | 19475/100000 [5:23:04<13:03:32,  1.71it/s]
Train steps ... :  19%|█▉        | 19476/100000 [5:23:04<13:04:58,  1.71it/s]
Train steps ... :  19%|█▉        | 19477/100000 [5:23:04<13:04:44,  1.71it/s]
Train steps ... :  19%|█▉        | 19478/100000 [5:23:05<13:04:43,  1.71it/s]
Train steps ... :  19%|█▉        | 19479/100000 [5:23:06<13:04:15,  1.71it/s]
Train steps ... :  19%|█▉        | 19480/100000 [5:23:06<13:04:22,  1.71it/s]
Train steps ... :  19%|█▉        | 19481/100000 [5:23:07<13:05:48,  1.71it/s]
Train steps ... :  19%|█▉        | 19482/100000 [5:23:07<13:05:03,  1.71it/s]
Train steps ... :  19%|█▉        | 19483/100000 [5:23:08<13:04:21,  1.71it/s]
Train steps ... :  19%|█▉        | 19484/100000 [5:23:09<13:03:37,  1.71it/s]
Train steps ... :  19%|█▉        | 19485/100000 [5:23:09<13:03:31,  1.71it/s]
Train steps ... :  19%|█▉        | 19486/100000 [5:23:10<13:03:33,  1.71it/s]
Train steps ... :  19%|█▉        | 19487/100000 [5:23:10<13:03:37,  1.71it/s]
Train steps ... :  19%|█▉        | 19488/100000 [5:23:11<13:03:39,  1.71it/s]
Train steps ... :  19%|█▉        | 19489/100000 [5:23:11<13:03:47,  1.71it/s]
Train steps ... :  19%|█▉        | 19490/100000 [5:23:12<13:04:50,  1.71it/s]
Train steps ... :  19%|█▉        | 19491/100000 [5:23:13<13:05:02,  1.71it/s]
Train steps ... :  19%|█▉        | 19492/100000 [5:23:13<13:04:04,  1.71it/s]
Train steps ... :  19%|█▉        | 19493/100000 [5:23:14<13:05:35,  1.71it/s]
Train steps ... :  19%|█▉        | 19494/100000 [5:23:14<13:03:48,  1.71it/s]
Train steps ... :  19%|█▉        | 19495/100000 [5:23:15<13:03:27,  1.71it/s]
Train steps ... :  19%|█▉        | 19496/100000 [5:23:16<13:05:28,  1.71it/s]
Train steps ... :  19%|█▉        | 19497/100000 [5:23:16<13:03:43,  1.71it/s]
Train steps ... :  19%|█▉        | 19498/100000 [5:23:17<13:05:35,  1.71it/s]
Train steps ... :  19%|█▉        | 19499/100000 [5:23:17<13:04:38,  1.71it/s]
Train steps ... :  20%|█▉        | 19500/100000 [5:23:18<13:04:03,  1.71it/s]Step... (19500 / 100000 | Loss: 0.9320699572563171, Learning Rate: 8.090452261306533e-05)
+
                                                                             
Step... (19500 / 100000 | Loss: 1.0571296215057373, Learning Rate: 8.090452261306533e-05)
+
Train steps ... :  20%|█▉        | 19500/100000 [5:23:18<13:04:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19501/100000 [5:23:19<13:06:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19502/100000 [5:23:19<13:05:18,  1.71it/s]
Train steps ... :  20%|█▉        | 19503/100000 [5:23:20<13:04:28,  1.71it/s]
Train steps ... :  20%|█▉        | 19504/100000 [5:23:20<13:04:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19505/100000 [5:23:21<13:04:40,  1.71it/s]
Train steps ... :  20%|█▉        | 19506/100000 [5:23:21<13:04:25,  1.71it/s]
Train steps ... :  20%|█▉        | 19507/100000 [5:23:22<13:04:29,  1.71it/s]
Train steps ... :  20%|█▉        | 19508/100000 [5:23:23<13:04:05,  1.71it/s]
Train steps ... :  20%|█▉        | 19509/100000 [5:23:23<13:03:57,  1.71it/s]
Train steps ... :  20%|█▉        | 19510/100000 [5:23:24<13:03:43,  1.71it/s]
Train steps ... :  20%|█▉        | 19511/100000 [5:23:24<13:04:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19512/100000 [5:23:25<13:04:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19513/100000 [5:23:26<13:05:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19514/100000 [5:23:26<13:05:02,  1.71it/s]
Train steps ... :  20%|█▉        | 19515/100000 [5:23:27<13:06:17,  1.71it/s]
Train steps ... :  20%|█▉        | 19516/100000 [5:23:27<13:05:15,  1.71it/s]
Train steps ... :  20%|█▉        | 19517/100000 [5:23:28<13:05:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19518/100000 [5:23:28<13:04:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19519/100000 [5:23:29<13:04:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19520/100000 [5:23:30<13:03:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19521/100000 [5:23:30<13:04:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19522/100000 [5:23:31<13:04:46,  1.71it/s]
Train steps ... :  20%|█▉        | 19523/100000 [5:23:31<13:04:07,  1.71it/s]
Train steps ... :  20%|█▉        | 19524/100000 [5:23:32<13:05:13,  1.71it/s]
Train steps ... :  20%|█▉        | 19525/100000 [5:23:33<13:04:28,  1.71it/s]Step... (19525 / 100000 | Loss: 1.2557547092437744, Learning Rate: 8.087939698492462e-05)
+
                                                                             
Step... (19525 / 100000 | Loss: 0.9165252447128296, Learning Rate: 8.087939698492462e-05)
+
Train steps ... :  20%|█▉        | 19525/100000 [5:23:33<13:04:28,  1.71it/s]
Train steps ... :  20%|█▉        | 19526/100000 [5:23:33<13:04:05,  1.71it/s]
Train steps ... :  20%|█▉        | 19527/100000 [5:23:34<13:03:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19528/100000 [5:23:34<13:03:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19529/100000 [5:23:35<13:05:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19530/100000 [5:23:35<13:03:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19531/100000 [5:23:36<13:03:32,  1.71it/s]
Train steps ... :  20%|█▉        | 19532/100000 [5:23:37<13:03:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19533/100000 [5:23:37<13:03:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19534/100000 [5:23:38<13:04:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19535/100000 [5:23:38<13:03:49,  1.71it/s]
Train steps ... :  20%|█▉        | 19536/100000 [5:23:39<13:03:26,  1.71it/s]
Train steps ... :  20%|█▉        | 19537/100000 [5:23:40<13:03:56,  1.71it/s]
Train steps ... :  20%|█▉        | 19538/100000 [5:23:40<13:04:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19539/100000 [5:23:41<13:04:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19540/100000 [5:23:41<13:03:41,  1.71it/s]
Train steps ... :  20%|█▉        | 19541/100000 [5:23:42<13:03:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19542/100000 [5:23:42<13:04:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19543/100000 [5:23:43<13:04:10,  1.71it/s]
Train steps ... :  20%|█▉        | 19544/100000 [5:23:44<13:05:15,  1.71it/s]
Train steps ... :  20%|█▉        | 19545/100000 [5:23:44<13:04:02,  1.71it/s]
Train steps ... :  20%|█▉        | 19546/100000 [5:23:45<13:03:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19547/100000 [5:23:45<13:04:04,  1.71it/s]
Train steps ... :  20%|█▉        | 19548/100000 [5:23:46<13:04:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19549/100000 [5:23:47<13:04:07,  1.71it/s]
Train steps ... :  20%|█▉        | 19550/100000 [5:23:47<13:03:50,  1.71it/s]Step... (19550 / 100000 | Loss: 0.8931140899658203, Learning Rate: 8.085427135678393e-05)
+
                                                                             
Step... (19550 / 100000 | Loss: 1.3851748704910278, Learning Rate: 8.085427135678393e-05)
+
Train steps ... :  20%|█▉        | 19550/100000 [5:23:47<13:03:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19551/100000 [5:23:48<13:04:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19552/100000 [5:23:48<13:04:39,  1.71it/s]
Train steps ... :  20%|█▉        | 19553/100000 [5:23:49<13:03:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19554/100000 [5:23:49<13:04:26,  1.71it/s]
Train steps ... :  20%|█▉        | 19555/100000 [5:23:50<13:03:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19556/100000 [5:23:51<13:04:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19557/100000 [5:23:51<13:03:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19558/100000 [5:23:52<13:03:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19559/100000 [5:23:52<13:03:01,  1.71it/s]
Train steps ... :  20%|█▉        | 19560/100000 [5:23:53<13:03:05,  1.71it/s]
Train steps ... :  20%|█▉        | 19561/100000 [5:23:54<13:02:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19562/100000 [5:23:54<13:02:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19563/100000 [5:23:55<13:03:02,  1.71it/s]
Train steps ... :  20%|█▉        | 19564/100000 [5:23:55<13:03:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19565/100000 [5:23:56<13:04:15,  1.71it/s]
Train steps ... :  20%|█▉        | 19566/100000 [5:23:57<13:04:41,  1.71it/s]
Train steps ... :  20%|█▉        | 19567/100000 [5:23:57<13:03:46,  1.71it/s]
Train steps ... :  20%|█▉        | 19568/100000 [5:23:58<13:03:13,  1.71it/s]
Train steps ... :  20%|█▉        | 19569/100000 [5:23:58<13:04:54,  1.71it/s]
Train steps ... :  20%|█▉        | 19570/100000 [5:23:59<13:04:07,  1.71it/s]
Train steps ... :  20%|█▉        | 19571/100000 [5:23:59<13:03:33,  1.71it/s]
Train steps ... :  20%|█▉        | 19572/100000 [5:24:00<13:03:38,  1.71it/s]
Train steps ... :  20%|█▉        | 19573/100000 [5:24:01<13:03:49,  1.71it/s]
Train steps ... :  20%|█▉        | 19574/100000 [5:24:01<13:03:06,  1.71it/s]
Train steps ... :  20%|█▉        | 19575/100000 [5:24:02<13:03:17,  1.71it/s]Step... (19575 / 100000 | Loss: 0.7308351993560791, Learning Rate: 8.082914572864322e-05)
+
                                                                             
Step... (19575 / 100000 | Loss: 0.8489357829093933, Learning Rate: 8.082914572864322e-05)
+
Train steps ... :  20%|█▉        | 19575/100000 [5:24:02<13:03:17,  1.71it/s]
Train steps ... :  20%|█▉        | 19576/100000 [5:24:02<13:03:53,  1.71it/s]
Train steps ... :  20%|█▉        | 19577/100000 [5:24:03<13:04:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19578/100000 [5:24:04<13:03:40,  1.71it/s]
Train steps ... :  20%|█▉        | 19579/100000 [5:24:04<13:03:18,  1.71it/s]
Train steps ... :  20%|█▉        | 19580/100000 [5:24:05<13:04:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19581/100000 [5:24:05<13:03:33,  1.71it/s]
Train steps ... :  20%|█▉        | 19582/100000 [5:24:06<13:03:34,  1.71it/s]
Train steps ... :  20%|█▉        | 19583/100000 [5:24:06<13:03:34,  1.71it/s]
Train steps ... :  20%|█▉        | 19584/100000 [5:24:07<13:03:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19585/100000 [5:24:08<13:03:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19586/100000 [5:24:08<13:03:33,  1.71it/s]
Train steps ... :  20%|█▉        | 19587/100000 [5:24:09<13:04:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19588/100000 [5:24:09<13:03:12,  1.71it/s]
Train steps ... :  20%|█▉        | 19589/100000 [5:24:10<13:03:05,  1.71it/s]
Train steps ... :  20%|█▉        | 19590/100000 [5:24:11<13:03:29,  1.71it/s]
Train steps ... :  20%|█▉        | 19591/100000 [5:24:11<13:02:33,  1.71it/s]
Train steps ... :  20%|█▉        | 19592/100000 [5:24:12<13:02:36,  1.71it/s]
Train steps ... :  20%|█▉        | 19593/100000 [5:24:12<13:02:40,  1.71it/s]
Train steps ... :  20%|█▉        | 19594/100000 [5:24:13<13:02:28,  1.71it/s]
Train steps ... :  20%|█▉        | 19595/100000 [5:24:13<13:02:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19596/100000 [5:24:14<13:02:32,  1.71it/s]
Train steps ... :  20%|█▉        | 19597/100000 [5:24:15<13:02:29,  1.71it/s]
Train steps ... :  20%|█▉        | 19598/100000 [5:24:15<13:02:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19599/100000 [5:24:16<13:02:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19600/100000 [5:24:16<13:02:32,  1.71it/s]Step... (19600 / 100000 | Loss: 0.8195221424102783, Learning Rate: 8.080402010050251e-05)
+
                                                                             
Step... (19600 / 100000 | Loss: 1.0495973825454712, Learning Rate: 8.080402010050251e-05)
+
Train steps ... :  20%|█▉        | 19600/100000 [5:24:17<13:02:32,  1.71it/s]
Train steps ... :  20%|█▉        | 19601/100000 [5:24:17<13:03:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19602/100000 [5:24:18<13:03:06,  1.71it/s]
Train steps ... :  20%|█▉        | 19603/100000 [5:24:18<13:03:51,  1.71it/s]
Train steps ... :  20%|█▉        | 19604/100000 [5:24:19<13:05:11,  1.71it/s]
Train steps ... :  20%|█▉        | 19605/100000 [5:24:19<13:05:21,  1.71it/s]
Train steps ... :  20%|█▉        | 19606/100000 [5:24:20<13:04:36,  1.71it/s]
Train steps ... :  20%|█▉        | 19607/100000 [5:24:20<13:04:37,  1.71it/s]
Train steps ... :  20%|█▉        | 19608/100000 [5:24:21<13:04:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19609/100000 [5:24:22<13:04:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19610/100000 [5:24:22<13:03:04,  1.71it/s]
Train steps ... :  20%|█▉        | 19611/100000 [5:24:23<13:02:56,  1.71it/s]
Train steps ... :  20%|█▉        | 19612/100000 [5:24:23<13:03:33,  1.71it/s]
Train steps ... :  20%|█▉        | 19613/100000 [5:24:24<13:02:32,  1.71it/s]
Train steps ... :  20%|█▉        | 19614/100000 [5:24:25<13:03:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19615/100000 [5:24:25<13:03:06,  1.71it/s]
Train steps ... :  20%|█▉        | 19616/100000 [5:24:26<13:03:59,  1.71it/s]
Train steps ... :  20%|█▉        | 19617/100000 [5:24:26<13:03:18,  1.71it/s]
Train steps ... :  20%|█▉        | 19618/100000 [5:24:27<13:02:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19619/100000 [5:24:27<13:02:38,  1.71it/s]
Train steps ... :  20%|█▉        | 19620/100000 [5:24:28<13:03:57,  1.71it/s]
Train steps ... :  20%|█▉        | 19621/100000 [5:24:29<13:03:15,  1.71it/s]
Train steps ... :  20%|█▉        | 19622/100000 [5:24:29<13:02:55,  1.71it/s]
Train steps ... :  20%|█▉        | 19623/100000 [5:24:30<13:03:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19624/100000 [5:24:30<13:02:34,  1.71it/s]
Train steps ... :  20%|█▉        | 19625/100000 [5:24:31<13:03:26,  1.71it/s]Step... (19625 / 100000 | Loss: 1.1255896091461182, Learning Rate: 8.077889447236181e-05)
+
                                                                             
Step... (19625 / 100000 | Loss: 1.0797451734542847, Learning Rate: 8.077889447236181e-05)
+
Train steps ... :  20%|█▉        | 19625/100000 [5:24:31<13:03:26,  1.71it/s]
Train steps ... :  20%|█▉        | 19626/100000 [5:24:32<13:04:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19627/100000 [5:24:32<13:03:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19628/100000 [5:24:33<13:02:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19629/100000 [5:24:33<13:03:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19630/100000 [5:24:34<13:03:26,  1.71it/s]
Train steps ... :  20%|█▉        | 19631/100000 [5:24:35<13:03:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19632/100000 [5:24:35<13:02:36,  1.71it/s]
Train steps ... :  20%|█▉        | 19633/100000 [5:24:36<13:03:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19634/100000 [5:24:36<13:02:45,  1.71it/s]
Train steps ... :  20%|█▉        | 19635/100000 [5:24:37<13:02:57,  1.71it/s]
Train steps ... :  20%|█▉        | 19636/100000 [5:24:37<13:02:35,  1.71it/s]
Train steps ... :  20%|█▉        | 19637/100000 [5:24:38<13:01:57,  1.71it/s]
Train steps ... :  20%|█▉        | 19638/100000 [5:24:39<13:02:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19639/100000 [5:24:39<13:02:07,  1.71it/s]
Train steps ... :  20%|█▉        | 19640/100000 [5:24:40<13:03:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19641/100000 [5:24:40<13:03:17,  1.71it/s]
Train steps ... :  20%|█▉        | 19642/100000 [5:24:41<13:02:59,  1.71it/s]
Train steps ... :  20%|█▉        | 19643/100000 [5:24:42<13:02:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19644/100000 [5:24:42<13:02:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19645/100000 [5:24:43<13:01:37,  1.71it/s]
Train steps ... :  20%|█▉        | 19646/100000 [5:24:43<13:02:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19647/100000 [5:24:44<13:01:24,  1.71it/s]
Train steps ... :  20%|█▉        | 19648/100000 [5:24:44<13:01:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19649/100000 [5:24:45<13:02:24,  1.71it/s]
Train steps ... :  20%|█▉        | 19650/100000 [5:24:46<13:01:02,  1.71it/s]Step... (19650 / 100000 | Loss: 1.2739043235778809, Learning Rate: 8.075376884422111e-05)
+
                                                                             
Step... (19650 / 100000 | Loss: 1.0105977058410645, Learning Rate: 8.075376884422111e-05)
+
Train steps ... :  20%|█▉        | 19650/100000 [5:24:46<13:01:02,  1.71it/s]
Train steps ... :  20%|█▉        | 19651/100000 [5:24:46<13:01:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19652/100000 [5:24:47<13:02:04,  1.71it/s]
Train steps ... :  20%|█▉        | 19653/100000 [5:24:47<13:02:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19654/100000 [5:24:48<13:02:41,  1.71it/s]
Train steps ... :  20%|█▉        | 19655/100000 [5:24:49<13:02:18,  1.71it/s]
Train steps ... :  20%|█▉        | 19656/100000 [5:24:49<13:02:48,  1.71it/s]
Train steps ... :  20%|█▉        | 19657/100000 [5:24:50<13:02:30,  1.71it/s]
Train steps ... :  20%|█▉        | 19658/100000 [5:24:50<13:02:01,  1.71it/s]
Train steps ... :  20%|█▉        | 19659/100000 [5:24:51<13:01:12,  1.71it/s]
Train steps ... :  20%|█▉        | 19660/100000 [5:24:51<13:02:42,  1.71it/s]
Train steps ... :  20%|█▉        | 19661/100000 [5:24:52<13:02:30,  1.71it/s]
Train steps ... :  20%|█▉        | 19662/100000 [5:24:53<13:02:13,  1.71it/s]
Train steps ... :  20%|█▉        | 19663/100000 [5:24:53<13:01:42,  1.71it/s]
Train steps ... :  20%|█▉        | 19664/100000 [5:24:54<13:01:25,  1.71it/s]
Train steps ... :  20%|█▉        | 19665/100000 [5:24:54<13:01:56,  1.71it/s]
Train steps ... :  20%|█▉        | 19666/100000 [5:24:55<13:02:11,  1.71it/s]
Train steps ... :  20%|█▉        | 19667/100000 [5:24:56<13:01:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19668/100000 [5:24:56<13:02:46,  1.71it/s]
Train steps ... :  20%|█▉        | 19669/100000 [5:24:57<13:02:10,  1.71it/s]
Train steps ... :  20%|█▉        | 19670/100000 [5:24:57<13:03:25,  1.71it/s]
Train steps ... :  20%|█▉        | 19671/100000 [5:24:58<13:02:32,  1.71it/s]
Train steps ... :  20%|█▉        | 19672/100000 [5:24:58<13:02:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19673/100000 [5:24:59<13:01:33,  1.71it/s]
Train steps ... :  20%|█▉        | 19674/100000 [5:25:00<13:03:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19675/100000 [5:25:00<13:03:51,  1.71it/s]Step... (19675 / 100000 | Loss: 1.0589349269866943, Learning Rate: 8.07286432160804e-05)
+
                                                                             
Step... (19675 / 100000 | Loss: 1.706545352935791, Learning Rate: 8.07286432160804e-05)
+
Train steps ... :  20%|█▉        | 19675/100000 [5:25:01<13:03:51,  1.71it/s]
Train steps ... :  20%|█▉        | 19676/100000 [5:25:01<13:03:40,  1.71it/s]
Train steps ... :  20%|█▉        | 19677/100000 [5:25:01<13:02:48,  1.71it/s]
Train steps ... :  20%|█▉        | 19678/100000 [5:25:02<13:02:53,  1.71it/s]
Train steps ... :  20%|█▉        | 19679/100000 [5:25:03<13:02:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19680/100000 [5:25:03<13:01:30,  1.71it/s]
Train steps ... :  20%|█▉        | 19681/100000 [5:25:04<13:01:59,  1.71it/s]
Train steps ... :  20%|█▉        | 19682/100000 [5:25:04<13:03:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19683/100000 [5:25:05<13:02:25,  1.71it/s]
Train steps ... :  20%|█▉        | 19684/100000 [5:25:05<13:02:13,  1.71it/s]
Train steps ... :  20%|█▉        | 19685/100000 [5:25:06<13:02:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19686/100000 [5:25:07<13:03:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19687/100000 [5:25:07<13:02:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19688/100000 [5:25:08<13:02:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19689/100000 [5:25:08<13:02:49,  1.71it/s]
Train steps ... :  20%|█▉        | 19690/100000 [5:25:09<13:02:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19691/100000 [5:25:10<13:02:25,  1.71it/s]
Train steps ... :  20%|█▉        | 19692/100000 [5:25:10<13:03:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19693/100000 [5:25:11<13:02:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19694/100000 [5:25:11<13:05:01,  1.70it/s]
Train steps ... :  20%|█▉        | 19695/100000 [5:25:12<13:02:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19696/100000 [5:25:12<13:01:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19697/100000 [5:25:13<13:02:26,  1.71it/s]
Train steps ... :  20%|█▉        | 19698/100000 [5:25:14<13:01:51,  1.71it/s]
Train steps ... :  20%|█▉        | 19699/100000 [5:25:14<13:01:25,  1.71it/s]
Train steps ... :  20%|█▉        | 19700/100000 [5:25:15<13:01:14,  1.71it/s]Step... (19700 / 100000 | Loss: 1.1543116569519043, Learning Rate: 8.07035175879397e-05)
+
                                                                             
Step... (19700 / 100000 | Loss: 1.3920842409133911, Learning Rate: 8.07035175879397e-05)
+
Train steps ... :  20%|█▉        | 19700/100000 [5:25:15<13:01:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19701/100000 [5:25:15<13:01:55,  1.71it/s]
Train steps ... :  20%|█▉        | 19702/100000 [5:25:16<13:02:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19703/100000 [5:25:17<13:02:11,  1.71it/s]
Train steps ... :  20%|█▉        | 19704/100000 [5:25:17<13:01:46,  1.71it/s]
Train steps ... :  20%|█▉        | 19705/100000 [5:25:18<13:01:15,  1.71it/s]
Train steps ... :  20%|█▉        | 19706/100000 [5:25:18<13:02:39,  1.71it/s]
Train steps ... :  20%|█▉        | 19707/100000 [5:25:19<13:01:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19708/100000 [5:25:20<13:02:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19709/100000 [5:25:20<13:02:15,  1.71it/s]
Train steps ... :  20%|█▉        | 19710/100000 [5:25:21<13:02:33,  1.71it/s]
Train steps ... :  20%|█▉        | 19711/100000 [5:25:21<13:01:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19712/100000 [5:25:22<13:01:49,  1.71it/s]
Train steps ... :  20%|█▉        | 19713/100000 [5:25:22<13:02:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19714/100000 [5:25:23<13:02:11,  1.71it/s]
Train steps ... :  20%|█▉        | 19715/100000 [5:25:24<13:01:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19716/100000 [5:25:24<13:02:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19717/100000 [5:25:25<13:02:42,  1.71it/s]
Train steps ... :  20%|█▉        | 19718/100000 [5:25:25<13:02:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19719/100000 [5:25:26<13:02:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19720/100000 [5:25:27<13:03:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19721/100000 [5:25:27<13:02:54,  1.71it/s]
Train steps ... :  20%|█▉        | 19722/100000 [5:25:28<13:03:43,  1.71it/s]
Train steps ... :  20%|█▉        | 19723/100000 [5:25:28<13:04:05,  1.71it/s]
Train steps ... :  20%|█▉        | 19724/100000 [5:25:29<13:02:56,  1.71it/s]
Train steps ... :  20%|█▉        | 19725/100000 [5:25:29<13:02:50,  1.71it/s]Step... (19725 / 100000 | Loss: 0.8170976638793945, Learning Rate: 8.0678391959799e-05)
+
                                                                             
Step... (19725 / 100000 | Loss: 0.981975793838501, Learning Rate: 8.0678391959799e-05)
+
Train steps ... :  20%|█▉        | 19725/100000 [5:25:30<13:02:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19726/100000 [5:25:30<13:03:28,  1.71it/s]
Train steps ... :  20%|█▉        | 19727/100000 [5:25:31<13:02:43,  1.71it/s]
Train steps ... :  20%|█▉        | 19728/100000 [5:25:31<13:02:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19729/100000 [5:25:32<13:02:06,  1.71it/s]
Train steps ... :  20%|█▉        | 19730/100000 [5:25:32<13:02:19,  1.71it/s]
Train steps ... :  20%|█▉        | 19731/100000 [5:25:33<13:01:43,  1.71it/s]
Train steps ... :  20%|█▉        | 19732/100000 [5:25:34<13:02:32,  1.71it/s]
Train steps ... :  20%|█▉        | 19733/100000 [5:25:34<13:02:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19734/100000 [5:25:35<13:01:29,  1.71it/s]
Train steps ... :  20%|█▉        | 19735/100000 [5:25:35<13:02:54,  1.71it/s]
Train steps ... :  20%|█▉        | 19736/100000 [5:25:36<13:01:01,  1.71it/s]
Train steps ... :  20%|█▉        | 19737/100000 [5:25:36<13:02:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19738/100000 [5:25:37<13:01:15,  1.71it/s]
Train steps ... :  20%|█▉        | 19739/100000 [5:25:38<13:01:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19740/100000 [5:25:38<13:01:25,  1.71it/s]
Train steps ... :  20%|█▉        | 19741/100000 [5:25:39<13:01:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19742/100000 [5:25:39<13:01:40,  1.71it/s]
Train steps ... :  20%|█▉        | 19743/100000 [5:25:40<13:01:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19744/100000 [5:25:41<13:01:19,  1.71it/s]
Train steps ... :  20%|█▉        | 19745/100000 [5:25:41<13:02:39,  1.71it/s]
Train steps ... :  20%|█▉        | 19746/100000 [5:25:42<13:02:26,  1.71it/s]
Train steps ... :  20%|█▉        | 19747/100000 [5:25:42<13:01:57,  1.71it/s]
Train steps ... :  20%|█▉        | 19748/100000 [5:25:43<13:02:51,  1.71it/s]
Train steps ... :  20%|█▉        | 19749/100000 [5:25:43<13:03:00,  1.71it/s]
Train steps ... :  20%|█▉        | 19750/100000 [5:25:44<13:00:24,  1.71it/s]Step... (19750 / 100000 | Loss: 1.5189909934997559, Learning Rate: 8.06532663316583e-05)
+
                                                                             
Step... (19750 / 100000 | Loss: 1.0422416925430298, Learning Rate: 8.06532663316583e-05)
+
Train steps ... :  20%|█▉        | 19750/100000 [5:25:44<13:00:24,  1.71it/s]
Train steps ... :  20%|█▉        | 19751/100000 [5:25:45<13:00:41,  1.71it/s]
Train steps ... :  20%|█▉        | 19752/100000 [5:25:45<13:00:34,  1.71it/s]
Train steps ... :  20%|█▉        | 19753/100000 [5:25:46<13:00:59,  1.71it/s]
Train steps ... :  20%|█▉        | 19754/100000 [5:25:46<13:01:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19755/100000 [5:25:47<13:01:19,  1.71it/s]
Train steps ... :  20%|█▉        | 19756/100000 [5:25:48<13:01:53,  1.71it/s]
Train steps ... :  20%|█▉        | 19757/100000 [5:25:48<13:01:35,  1.71it/s]
Train steps ... :  20%|█▉        | 19758/100000 [5:25:49<13:01:11,  1.71it/s]
Train steps ... :  20%|█▉        | 19759/100000 [5:25:49<13:00:40,  1.71it/s]
Train steps ... :  20%|█▉        | 19760/100000 [5:25:50<13:00:54,  1.71it/s]
Train steps ... :  20%|█▉        | 19761/100000 [5:25:50<13:00:37,  1.71it/s]
Train steps ... :  20%|█▉        | 19762/100000 [5:25:51<13:00:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19763/100000 [5:25:52<13:01:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19764/100000 [5:25:52<13:01:13,  1.71it/s]
Train steps ... :  20%|█▉        | 19765/100000 [5:25:53<13:00:55,  1.71it/s]
Train steps ... :  20%|█▉        | 19766/100000 [5:25:53<13:01:48,  1.71it/s]
Train steps ... :  20%|█▉        | 19767/100000 [5:25:54<13:01:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19768/100000 [5:25:55<13:00:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19769/100000 [5:25:55<13:01:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19770/100000 [5:25:56<13:00:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19771/100000 [5:25:56<13:00:39,  1.71it/s]
Train steps ... :  20%|█▉        | 19772/100000 [5:25:57<13:00:38,  1.71it/s]
Train steps ... :  20%|█▉        | 19773/100000 [5:25:57<13:00:53,  1.71it/s]
Train steps ... :  20%|█▉        | 19774/100000 [5:25:58<13:01:01,  1.71it/s]
Train steps ... :  20%|█▉        | 19775/100000 [5:25:59<13:00:52,  1.71it/s]Step... (19775 / 100000 | Loss: 1.1432294845581055, Learning Rate: 8.062814070351759e-05)
+
                                                                             
Step... (19775 / 100000 | Loss: 0.9627625942230225, Learning Rate: 8.062814070351759e-05)
+
Train steps ... :  20%|█▉        | 19775/100000 [5:25:59<13:00:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19776/100000 [5:25:59<13:01:31,  1.71it/s]
Train steps ... :  20%|█▉        | 19777/100000 [5:26:00<13:00:57,  1.71it/s]
Train steps ... :  20%|█▉        | 19778/100000 [5:26:00<13:01:13,  1.71it/s]
Train steps ... :  20%|█▉        | 19779/100000 [5:26:01<13:00:57,  1.71it/s]
Train steps ... :  20%|█▉        | 19780/100000 [5:26:02<13:01:26,  1.71it/s]
Train steps ... :  20%|█▉        | 19781/100000 [5:26:02<13:00:46,  1.71it/s]
Train steps ... :  20%|█▉        | 19782/100000 [5:26:03<13:00:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19783/100000 [5:26:03<13:00:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19784/100000 [5:26:04<13:01:18,  1.71it/s]
Train steps ... :  20%|█▉        | 19785/100000 [5:26:05<13:00:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19786/100000 [5:26:05<13:00:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19787/100000 [5:26:06<13:01:31,  1.71it/s]
Train steps ... :  20%|█▉        | 19788/100000 [5:26:06<13:01:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19789/100000 [5:26:07<13:01:02,  1.71it/s]
Train steps ... :  20%|█▉        | 19790/100000 [5:26:07<13:01:42,  1.71it/s]
Train steps ... :  20%|█▉        | 19791/100000 [5:26:08<13:01:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19792/100000 [5:26:09<13:02:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19793/100000 [5:26:09<13:01:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19794/100000 [5:26:10<13:01:12,  1.71it/s]
Train steps ... :  20%|█▉        | 19795/100000 [5:26:10<13:02:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19796/100000 [5:26:11<13:01:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19797/100000 [5:26:12<13:01:15,  1.71it/s]
Train steps ... :  20%|█▉        | 19798/100000 [5:26:12<13:01:12,  1.71it/s]
Train steps ... :  20%|█▉        | 19799/100000 [5:26:13<13:01:02,  1.71it/s]
Train steps ... :  20%|█▉        | 19800/100000 [5:26:13<13:00:33,  1.71it/s]Step... (19800 / 100000 | Loss: 1.031435489654541, Learning Rate: 8.060301507537689e-05)
+
                                                                             
Step... (19800 / 100000 | Loss: 0.8555871248245239, Learning Rate: 8.060301507537689e-05)
+
Train steps ... :  20%|█▉        | 19800/100000 [5:26:14<13:00:33,  1.71it/s]
Train steps ... :  20%|█▉        | 19801/100000 [5:26:14<13:00:55,  1.71it/s]
Train steps ... :  20%|█▉        | 19802/100000 [5:26:14<13:00:30,  1.71it/s]
Train steps ... :  20%|█▉        | 19803/100000 [5:26:15<13:00:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19804/100000 [5:26:16<13:01:19,  1.71it/s]
Train steps ... :  20%|█▉        | 19805/100000 [5:26:16<13:01:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19806/100000 [5:26:17<13:01:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19807/100000 [5:26:17<13:01:11,  1.71it/s]
Train steps ... :  20%|█▉        | 19808/100000 [5:26:18<13:00:40,  1.71it/s]
Train steps ... :  20%|█▉        | 19809/100000 [5:26:19<13:01:02,  1.71it/s]
Train steps ... :  20%|█▉        | 19810/100000 [5:26:19<13:00:36,  1.71it/s]
Train steps ... :  20%|█▉        | 19811/100000 [5:26:20<13:00:41,  1.71it/s]
Train steps ... :  20%|█▉        | 19812/100000 [5:26:20<13:00:56,  1.71it/s]
Train steps ... :  20%|█▉        | 19813/100000 [5:26:21<13:00:54,  1.71it/s]
Train steps ... :  20%|█▉        | 19814/100000 [5:26:21<13:01:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19815/100000 [5:26:22<13:00:31,  1.71it/s]
Train steps ... :  20%|█▉        | 19816/100000 [5:26:23<13:00:36,  1.71it/s]
Train steps ... :  20%|█▉        | 19817/100000 [5:26:23<13:01:55,  1.71it/s]
Train steps ... :  20%|█▉        | 19818/100000 [5:26:24<13:00:34,  1.71it/s]
Train steps ... :  20%|█▉        | 19819/100000 [5:26:24<13:00:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19820/100000 [5:26:25<13:00:12,  1.71it/s]
Train steps ... :  20%|█▉        | 19821/100000 [5:26:26<13:00:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19822/100000 [5:26:26<12:59:51,  1.71it/s]
Train steps ... :  20%|█▉        | 19823/100000 [5:26:27<12:59:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19824/100000 [5:26:27<13:00:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19825/100000 [5:26:28<13:00:06,  1.71it/s]Step... (19825 / 100000 | Loss: 0.8647386431694031, Learning Rate: 8.057788944723618e-05)
+
                                                                             
Step... (19825 / 100000 | Loss: 0.9438706040382385, Learning Rate: 8.057788944723618e-05)
+
Train steps ... :  20%|█▉        | 19825/100000 [5:26:28<13:00:06,  1.71it/s]
Train steps ... :  20%|█▉        | 19826/100000 [5:26:28<12:59:59,  1.71it/s]
Train steps ... :  20%|█▉        | 19827/100000 [5:26:29<12:59:35,  1.71it/s]
Train steps ... :  20%|█▉        | 19828/100000 [5:26:30<13:00:11,  1.71it/s]
Train steps ... :  20%|█▉        | 19829/100000 [5:26:30<12:59:42,  1.71it/s]
Train steps ... :  20%|█▉        | 19830/100000 [5:26:31<13:00:11,  1.71it/s]
Train steps ... :  20%|█▉        | 19831/100000 [5:26:31<13:00:29,  1.71it/s]
Train steps ... :  20%|█▉        | 19832/100000 [5:26:32<13:00:04,  1.71it/s]
Train steps ... :  20%|█▉        | 19833/100000 [5:26:33<13:00:34,  1.71it/s]
Train steps ... :  20%|█▉        | 19834/100000 [5:26:33<13:00:34,  1.71it/s]
Train steps ... :  20%|█▉        | 19835/100000 [5:26:34<13:00:57,  1.71it/s]
Train steps ... :  20%|█▉        | 19836/100000 [5:26:34<13:01:40,  1.71it/s]
Train steps ... :  20%|█▉        | 19837/100000 [5:26:35<13:02:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19838/100000 [5:26:35<13:01:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19839/100000 [5:26:36<13:02:12,  1.71it/s]
Train steps ... :  20%|█▉        | 19840/100000 [5:26:37<13:01:53,  1.71it/s]
Train steps ... :  20%|█▉        | 19841/100000 [5:26:37<13:01:05,  1.71it/s]
Train steps ... :  20%|█▉        | 19842/100000 [5:26:38<13:00:31,  1.71it/s]
Train steps ... :  20%|█▉        | 19843/100000 [5:26:38<13:00:26,  1.71it/s]
Train steps ... :  20%|█▉        | 19844/100000 [5:26:39<13:00:25,  1.71it/s]
Train steps ... :  20%|█▉        | 19845/100000 [5:26:40<13:00:30,  1.71it/s]
Train steps ... :  20%|█▉        | 19846/100000 [5:26:40<13:00:39,  1.71it/s]
Train steps ... :  20%|█▉        | 19847/100000 [5:26:41<13:00:25,  1.71it/s]
Train steps ... :  20%|█▉        | 19848/100000 [5:26:41<13:00:10,  1.71it/s]
Train steps ... :  20%|█▉        | 19849/100000 [5:26:42<13:01:02,  1.71it/s]
Train steps ... :  20%|█▉        | 19850/100000 [5:26:42<13:00:39,  1.71it/s]Step... (19850 / 100000 | Loss: 1.2362726926803589, Learning Rate: 8.055276381909548e-05)
+
                                                                             
Step... (19850 / 100000 | Loss: 1.294892430305481, Learning Rate: 8.055276381909548e-05)
+
Train steps ... :  20%|█▉        | 19850/100000 [5:26:43<13:00:39,  1.71it/s]
Train steps ... :  20%|█▉        | 19851/100000 [5:26:43<13:00:33,  1.71it/s]
Train steps ... :  20%|█▉        | 19852/100000 [5:26:44<12:59:43,  1.71it/s]
Train steps ... :  20%|█▉        | 19853/100000 [5:26:44<12:59:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19854/100000 [5:26:45<13:00:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19855/100000 [5:26:45<13:00:21,  1.71it/s]
Train steps ... :  20%|█▉        | 19856/100000 [5:26:46<13:00:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19857/100000 [5:26:47<13:00:13,  1.71it/s]
Train steps ... :  20%|█▉        | 19858/100000 [5:26:47<13:00:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19859/100000 [5:26:48<12:59:42,  1.71it/s]
Train steps ... :  20%|█▉        | 19860/100000 [5:26:48<13:00:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19861/100000 [5:26:49<13:01:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19862/100000 [5:26:49<13:00:53,  1.71it/s]
Train steps ... :  20%|█▉        | 19863/100000 [5:26:50<13:01:15,  1.71it/s]
Train steps ... :  20%|█▉        | 19864/100000 [5:26:51<13:00:45,  1.71it/s]
Train steps ... :  20%|█▉        | 19865/100000 [5:26:51<13:00:31,  1.71it/s]
Train steps ... :  20%|█▉        | 19866/100000 [5:26:52<13:00:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19867/100000 [5:26:52<13:00:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19868/100000 [5:26:53<12:59:11,  1.71it/s]
Train steps ... :  20%|█▉        | 19869/100000 [5:26:54<12:59:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19870/100000 [5:26:54<12:59:57,  1.71it/s]
Train steps ... :  20%|█▉        | 19871/100000 [5:26:55<13:00:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19872/100000 [5:26:55<12:59:59,  1.71it/s]
Train steps ... :  20%|█▉        | 19873/100000 [5:26:56<12:59:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19874/100000 [5:26:57<13:00:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19875/100000 [5:26:57<12:59:41,  1.71it/s]Step... (19875 / 100000 | Loss: 0.9999058246612549, Learning Rate: 8.052763819095478e-05)
+
                                                                             
Step... (19875 / 100000 | Loss: 1.1360853910446167, Learning Rate: 8.052763819095478e-05)
+
Train steps ... :  20%|█▉        | 19875/100000 [5:26:57<12:59:41,  1.71it/s]
Train steps ... :  20%|█▉        | 19876/100000 [5:26:58<13:00:15,  1.71it/s]
Train steps ... :  20%|█▉        | 19877/100000 [5:26:58<12:59:55,  1.71it/s]
Train steps ... :  20%|█▉        | 19878/100000 [5:26:59<12:59:45,  1.71it/s]
Train steps ... :  20%|█▉        | 19879/100000 [5:26:59<12:59:59,  1.71it/s]
Train steps ... :  20%|█▉        | 19880/100000 [5:27:00<13:00:10,  1.71it/s]
Train steps ... :  20%|█▉        | 19881/100000 [5:27:01<12:59:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19882/100000 [5:27:01<13:00:07,  1.71it/s]
Train steps ... :  20%|█▉        | 19883/100000 [5:27:02<13:00:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19884/100000 [5:27:02<13:00:00,  1.71it/s]
Train steps ... :  20%|█▉        | 19885/100000 [5:27:03<13:00:01,  1.71it/s]
Train steps ... :  20%|█▉        | 19886/100000 [5:27:04<12:59:43,  1.71it/s]
Train steps ... :  20%|█▉        | 19887/100000 [5:27:04<13:00:39,  1.71it/s]
Train steps ... :  20%|█▉        | 19888/100000 [5:27:05<13:00:28,  1.71it/s]
Train steps ... :  20%|█▉        | 19889/100000 [5:27:05<12:59:29,  1.71it/s]
Train steps ... :  20%|█▉        | 19890/100000 [5:27:06<13:00:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19891/100000 [5:27:06<13:00:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19892/100000 [5:27:07<12:59:35,  1.71it/s]
Train steps ... :  20%|█▉        | 19893/100000 [5:27:08<12:59:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19894/100000 [5:27:08<13:00:41,  1.71it/s]
Train steps ... :  20%|█▉        | 19895/100000 [5:27:09<13:00:30,  1.71it/s]
Train steps ... :  20%|█▉        | 19896/100000 [5:27:09<13:00:12,  1.71it/s]
Train steps ... :  20%|█▉        | 19897/100000 [5:27:10<13:00:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19898/100000 [5:27:11<13:00:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19899/100000 [5:27:11<13:00:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19900/100000 [5:27:12<13:00:21,  1.71it/s]Step... (19900 / 100000 | Loss: 1.0188177824020386, Learning Rate: 8.050251256281407e-05)
+
                                                                             
Step... (19900 / 100000 | Loss: 0.8684961795806885, Learning Rate: 8.050251256281407e-05)
+
Train steps ... :  20%|█▉        | 19900/100000 [5:27:12<13:00:21,  1.71it/s]
Train steps ... :  20%|█▉        | 19901/100000 [5:27:12<13:00:26,  1.71it/s]
Train steps ... :  20%|█▉        | 19902/100000 [5:27:13<13:00:13,  1.71it/s]
Train steps ... :  20%|█▉        | 19903/100000 [5:27:13<13:00:11,  1.71it/s]
Train steps ... :  20%|█▉        | 19904/100000 [5:27:14<13:00:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19905/100000 [5:27:15<13:00:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19906/100000 [5:27:15<13:00:10,  1.71it/s]
Train steps ... :  20%|█▉        | 19907/100000 [5:27:16<13:00:57,  1.71it/s]
Train steps ... :  20%|█▉        | 19908/100000 [5:27:16<13:00:13,  1.71it/s]
Train steps ... :  20%|█▉        | 19909/100000 [5:27:17<13:00:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19910/100000 [5:27:18<13:01:31,  1.71it/s]
Train steps ... :  20%|█▉        | 19911/100000 [5:27:18<13:02:01,  1.71it/s]
Train steps ... :  20%|█▉        | 19912/100000 [5:27:19<13:01:43,  1.71it/s]
Train steps ... :  20%|█▉        | 19913/100000 [5:27:19<13:00:46,  1.71it/s]
Train steps ... :  20%|█▉        | 19914/100000 [5:27:20<13:00:29,  1.71it/s]
Train steps ... :  20%|█▉        | 19915/100000 [5:27:20<13:00:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19916/100000 [5:27:21<13:01:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19917/100000 [5:27:22<13:01:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19918/100000 [5:27:22<13:01:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19919/100000 [5:27:23<13:00:10,  1.71it/s]
Train steps ... :  20%|█▉        | 19920/100000 [5:27:23<13:00:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19921/100000 [5:27:24<12:59:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19922/100000 [5:27:25<12:59:56,  1.71it/s]
Train steps ... :  20%|█▉        | 19923/100000 [5:27:25<12:59:45,  1.71it/s]
Train steps ... :  20%|█▉        | 19924/100000 [5:27:26<13:00:34,  1.71it/s]
Train steps ... :  20%|█▉        | 19925/100000 [5:27:26<12:59:51,  1.71it/s]Step... (19925 / 100000 | Loss: 1.0757298469543457, Learning Rate: 8.047738693467337e-05)
+
                                                                             
Step... (19925 / 100000 | Loss: 0.9375120401382446, Learning Rate: 8.047738693467337e-05)
+
Train steps ... :  20%|█▉        | 19925/100000 [5:27:27<12:59:51,  1.71it/s]
Train steps ... :  20%|█▉        | 19926/100000 [5:27:27<12:59:43,  1.71it/s]
Train steps ... :  20%|█▉        | 19927/100000 [5:27:27<12:58:56,  1.71it/s]
Train steps ... :  20%|█▉        | 19928/100000 [5:27:28<12:58:55,  1.71it/s]
Train steps ... :  20%|█▉        | 19929/100000 [5:27:29<12:59:40,  1.71it/s]
Train steps ... :  20%|█▉        | 19930/100000 [5:27:29<13:00:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19931/100000 [5:27:30<13:01:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19932/100000 [5:27:30<13:01:39,  1.71it/s]
Train steps ... :  20%|█▉        | 19933/100000 [5:27:31<13:00:52,  1.71it/s]
Train steps ... :  20%|█▉        | 19934/100000 [5:27:32<13:02:02,  1.71it/s]
Train steps ... :  20%|█▉        | 19935/100000 [5:27:32<13:02:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19936/100000 [5:27:33<13:04:57,  1.70it/s]
Train steps ... :  20%|█▉        | 19937/100000 [5:27:33<13:03:26,  1.70it/s]
Train steps ... :  20%|█▉        | 19938/100000 [5:27:34<13:03:17,  1.70it/s]
Train steps ... :  20%|█▉        | 19939/100000 [5:27:35<13:01:05,  1.71it/s]
Train steps ... :  20%|█▉        | 19940/100000 [5:27:35<13:00:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19941/100000 [5:27:36<13:01:36,  1.71it/s]
Train steps ... :  20%|█▉        | 19942/100000 [5:27:36<13:00:45,  1.71it/s]
Train steps ... :  20%|█▉        | 19943/100000 [5:27:37<13:00:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19944/100000 [5:27:37<13:02:44,  1.70it/s]
Train steps ... :  20%|█▉        | 19945/100000 [5:27:38<13:02:03,  1.71it/s]
Train steps ... :  20%|█▉        | 19946/100000 [5:27:39<13:01:38,  1.71it/s]
Train steps ... :  20%|█▉        | 19947/100000 [5:27:39<13:00:48,  1.71it/s]
Train steps ... :  20%|█▉        | 19948/100000 [5:27:40<13:01:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19949/100000 [5:27:40<13:00:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19950/100000 [5:27:41<13:00:47,  1.71it/s]Step... (19950 / 100000 | Loss: 0.7004914283752441, Learning Rate: 8.045226130653267e-05)
+
                                                                             
Step... (19950 / 100000 | Loss: 1.1973614692687988, Learning Rate: 8.045226130653267e-05)
+
Train steps ... :  20%|█▉        | 19950/100000 [5:27:41<13:00:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19951/100000 [5:27:42<12:59:19,  1.71it/s]
Train steps ... :  20%|█▉        | 19952/100000 [5:27:42<12:58:34,  1.71it/s]
Train steps ... :  20%|█▉        | 19953/100000 [5:27:43<12:59:04,  1.71it/s]
Train steps ... :  20%|█▉        | 19954/100000 [5:27:43<12:58:28,  1.71it/s]
Train steps ... :  20%|█▉        | 19955/100000 [5:27:44<12:58:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19956/100000 [5:27:44<12:59:29,  1.71it/s]
Train steps ... :  20%|█▉        | 19957/100000 [5:27:45<12:59:43,  1.71it/s]
Train steps ... :  20%|█▉        | 19958/100000 [5:27:46<12:59:43,  1.71it/s]
Train steps ... :  20%|█▉        | 19959/100000 [5:27:46<13:01:02,  1.71it/s]
Train steps ... :  20%|█▉        | 19960/100000 [5:27:47<13:01:07,  1.71it/s]
Train steps ... :  20%|█▉        | 19961/100000 [5:27:47<13:00:28,  1.71it/s]
Train steps ... :  20%|█▉        | 19962/100000 [5:27:48<13:00:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19963/100000 [5:27:49<12:59:38,  1.71it/s]
Train steps ... :  20%|█▉        | 19964/100000 [5:27:49<12:59:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19965/100000 [5:27:50<12:59:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19966/100000 [5:27:50<12:59:16,  1.71it/s]
Train steps ... :  20%|█▉        | 19967/100000 [5:27:51<12:59:09,  1.71it/s]
Train steps ... :  20%|█▉        | 19968/100000 [5:27:51<12:58:32,  1.71it/s]
Train steps ... :  20%|█▉        | 19969/100000 [5:27:52<12:57:58,  1.71it/s]
Train steps ... :  20%|█▉        | 19970/100000 [5:27:53<12:58:50,  1.71it/s]
Train steps ... :  20%|█▉        | 19971/100000 [5:27:53<12:58:41,  1.71it/s]
Train steps ... :  20%|█▉        | 19972/100000 [5:27:54<12:58:48,  1.71it/s]
Train steps ... :  20%|█▉        | 19973/100000 [5:27:54<13:00:36,  1.71it/s]
Train steps ... :  20%|█▉        | 19974/100000 [5:27:55<12:59:10,  1.71it/s]
Train steps ... :  20%|█▉        | 19975/100000 [5:27:56<12:59:26,  1.71it/s]Step... (19975 / 100000 | Loss: 1.1748496294021606, Learning Rate: 8.042713567839196e-05)
+
                                                                             
Step... (19975 / 100000 | Loss: 1.0039215087890625, Learning Rate: 8.042713567839196e-05)
+
Train steps ... :  20%|█▉        | 19975/100000 [5:27:56<12:59:26,  1.71it/s]
Train steps ... :  20%|█▉        | 19976/100000 [5:27:56<12:59:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19977/100000 [5:27:57<12:59:31,  1.71it/s]
Train steps ... :  20%|█▉        | 19978/100000 [5:27:57<12:59:33,  1.71it/s]
Train steps ... :  20%|█▉        | 19979/100000 [5:27:58<12:58:44,  1.71it/s]
Train steps ... :  20%|█▉        | 19980/100000 [5:27:58<12:58:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19981/100000 [5:27:59<12:58:07,  1.71it/s]
Train steps ... :  20%|█▉        | 19982/100000 [5:28:00<12:58:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19983/100000 [5:28:00<12:59:54,  1.71it/s]
Train steps ... :  20%|█▉        | 19984/100000 [5:28:01<12:59:34,  1.71it/s]
Train steps ... :  20%|█▉        | 19985/100000 [5:28:01<12:59:38,  1.71it/s]
Train steps ... :  20%|█▉        | 19986/100000 [5:28:02<12:59:27,  1.71it/s]
Train steps ... :  20%|█▉        | 19987/100000 [5:28:03<12:58:48,  1.71it/s]
Train steps ... :  20%|█▉        | 19988/100000 [5:28:03<12:59:19,  1.71it/s]
Train steps ... :  20%|█▉        | 19989/100000 [5:28:04<12:58:30,  1.71it/s]
Train steps ... :  20%|█▉        | 19990/100000 [5:28:04<12:58:36,  1.71it/s]
Train steps ... :  20%|█▉        | 19991/100000 [5:28:05<12:59:14,  1.71it/s]
Train steps ... :  20%|█▉        | 19992/100000 [5:28:05<13:01:08,  1.71it/s]
Train steps ... :  20%|█▉        | 19993/100000 [5:28:06<13:01:20,  1.71it/s]
Train steps ... :  20%|█▉        | 19994/100000 [5:28:07<12:59:47,  1.71it/s]
Train steps ... :  20%|█▉        | 19995/100000 [5:28:07<13:00:13,  1.71it/s]
Train steps ... :  20%|█▉        | 19996/100000 [5:28:08<12:59:22,  1.71it/s]
Train steps ... :  20%|█▉        | 19997/100000 [5:28:08<12:59:35,  1.71it/s]
Train steps ... :  20%|█▉        | 19998/100000 [5:28:09<12:59:23,  1.71it/s]
Train steps ... :  20%|█▉        | 19999/100000 [5:28:10<12:58:22,  1.71it/s]
Train steps ... :  20%|██        | 20000/100000 [5:28:10<12:58:39,  1.71it/s]Step... (20000 / 100000 | Loss: 1.204679250717163, Learning Rate: 8.040201005025126e-05)
+
                                                                             
Step... (20000 / 100000 | Loss: 1.310227394104004, Learning Rate: 8.040201005025126e-05)
+
Train steps ... :  20%|██        | 20000/100000 [5:28:11<12:58:39,  1.71it/s]06/17/2024 21:22:37 - INFO - accelerate.accelerator - Saving current state to ./checkpoint-20000-epoch-1
+06/17/2024 21:22:37 - 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
+06/17/2024 21:22:40 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-20000-epoch-1/model.safetensors
+06/17/2024 21:22:40 - 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
+06/17/2024 21:22:44 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-20000-epoch-1/model_1.safetensors
+06/17/2024 21:22:45 - INFO - accelerate.checkpointing - Optimizer state saved in checkpoint-20000-epoch-1/optimizer.bin
+06/17/2024 21:22:45 - INFO - accelerate.checkpointing - Scheduler state saved in checkpoint-20000-epoch-1/scheduler.bin
+06/17/2024 21:22:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in checkpoint-20000-epoch-1/sampler.bin
+06/17/2024 21:22:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in checkpoint-20000-epoch-1/sampler_1.bin
+06/17/2024 21:22:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 2 saved in checkpoint-20000-epoch-1/sampler_2.bin
+06/17/2024 21:22:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 3 saved in checkpoint-20000-epoch-1/sampler_3.bin
+06/17/2024 21:22:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 4 saved in checkpoint-20000-epoch-1/sampler_4.bin
+06/17/2024 21:22:45 - INFO - accelerate.checkpointing - Random states saved in checkpoint-20000-epoch-1/random_states_0.pkl
+
+
  0%|          | 0/5 [00:00<?, ?it/s]
+
 20%|██        | 1/5 [01:44<06:59, 104.92s/it]
+
 40%|████      | 2/5 [02:18<03:09, 63.08s/it] 
+
 60%|██████    | 3/5 [02:19<01:09, 34.56s/it]
+
 80%|████████  | 4/5 [02:19<00:21, 21.17s/it]
+
100%|██████████| 5/5 [02:20<00:00, 13.75s/it]
100%|██████████| 5/5 [02:20<00:00, 28.11s/it]