diff --git "a/train.log" "b/train.log"
--- "a/train.log"
+++ "b/train.log"
@@ -19841,3 +19841,4231 @@ Eval results for step (20000 / 100000 | Eval Loss: 1.1917551755905151 | Eval wer
 
 60%|██████    | 3/5 [02:20<01:09, 34.72s/it]
 
 80%|████████  | 4/5 [02:20<00:21, 21.30s/it]
 
100%|██████████| 5/5 [02:21<00:00, 13.82s/it]
100%|██████████| 5/5 [02:21<00:00, 28.26s/it]
+
+
+
Evaluating eval...:   0%|          | 0/1900 [00:00<?, ?it/s]
+
+
Evaluating eval...:   0%|          | 1/1900 [00:03<1:47:46,  3.41s/it]
+
+
Evaluating eval...:   0%|          | 2/1900 [00:04<1:07:17,  2.13s/it]
+
+
Evaluating eval...:   0%|          | 3/1900 [00:05<55:24,  1.75s/it]  
+
+
Evaluating eval...:   0%|          | 4/1900 [00:07<48:49,  1.54s/it]
+
+
Evaluating eval...:   0%|          | 5/1900 [00:08<45:23,  1.44s/it]
+
+
Evaluating eval...:   0%|          | 6/1900 [00:09<42:24,  1.34s/it]
+
+
Evaluating eval...:   0%|          | 7/1900 [00:10<40:57,  1.30s/it]
+
+
Evaluating eval...:   0%|          | 8/1900 [00:11<39:40,  1.26s/it]
+
+
Evaluating eval...:   0%|          | 9/1900 [00:13<38:29,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 10/1900 [00:14<38:30,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 11/1900 [00:15<38:31,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 12/1900 [00:16<38:11,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 13/1900 [00:17<38:05,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 14/1900 [00:19<37:40,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 15/1900 [00:20<37:29,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 16/1900 [00:21<37:16,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 17/1900 [00:22<37:17,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 18/1900 [00:23<37:04,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 19/1900 [00:24<36:38,  1.17s/it]
+
+
Evaluating eval...:   1%|          | 20/1900 [00:26<36:49,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 21/1900 [00:27<37:22,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 22/1900 [00:28<37:13,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 23/1900 [00:29<36:47,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 24/1900 [00:30<37:05,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 25/1900 [00:32<36:35,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 26/1900 [00:33<36:18,  1.16s/it]
+
+
Evaluating eval...:   1%|▏         | 27/1900 [00:34<36:51,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 28/1900 [00:35<36:48,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 29/1900 [00:36<36:35,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 30/1900 [00:37<36:40,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 31/1900 [00:39<36:34,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 32/1900 [00:40<36:43,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 33/1900 [00:41<36:54,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 34/1900 [00:42<37:42,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 35/1900 [00:44<38:49,  1.25s/it]
+
+
Evaluating eval...:   2%|▏         | 36/1900 [00:45<39:15,  1.26s/it]
+
+
Evaluating eval...:   2%|▏         | 37/1900 [00:46<38:38,  1.24s/it]
+
+
Evaluating eval...:   2%|▏         | 38/1900 [00:47<37:50,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 39/1900 [00:48<37:28,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 40/1900 [00:50<37:13,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 41/1900 [00:51<36:46,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 42/1900 [00:52<38:21,  1.24s/it]
+
+
Evaluating eval...:   2%|▏         | 43/1900 [00:53<37:52,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 44/1900 [00:55<37:40,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 45/1900 [00:56<36:56,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 46/1900 [00:57<36:38,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 47/1900 [00:58<36:07,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 48/1900 [00:59<35:51,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 49/1900 [01:00<35:42,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 50/1900 [01:01<36:14,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 51/1900 [01:03<36:24,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 52/1900 [01:04<36:08,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 53/1900 [01:05<36:00,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 54/1900 [01:06<36:19,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 55/1900 [01:07<37:00,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 56/1900 [01:09<37:06,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 57/1900 [01:10<36:56,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 58/1900 [01:11<36:57,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 59/1900 [01:12<36:42,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 60/1900 [01:13<36:11,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 61/1900 [01:15<37:45,  1.23s/it]
+
+
Evaluating eval...:   3%|▎         | 62/1900 [01:16<37:08,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 63/1900 [01:17<36:48,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 64/1900 [01:18<36:36,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 65/1900 [01:19<36:11,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 66/1900 [01:21<36:00,  1.18s/it]
+
+
Evaluating eval...:   4%|▎         | 67/1900 [01:22<35:55,  1.18s/it]
+
+
Evaluating eval...:   4%|▎         | 68/1900 [01:23<38:37,  1.26s/it]
+
+
Evaluating eval...:   4%|▎         | 69/1900 [01:24<37:35,  1.23s/it]
+
+
Evaluating eval...:   4%|▎         | 70/1900 [01:26<37:44,  1.24s/it]
+
+
Evaluating eval...:   4%|▎         | 71/1900 [01:27<37:26,  1.23s/it]
+
+
Evaluating eval...:   4%|▍         | 72/1900 [01:28<37:29,  1.23s/it]
+
+
Evaluating eval...:   4%|▍         | 73/1900 [01:29<37:05,  1.22s/it]
+
+
Evaluating eval...:   4%|▍         | 74/1900 [01:30<36:47,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 75/1900 [01:32<36:17,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 76/1900 [01:33<36:11,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 77/1900 [01:34<36:11,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 78/1900 [01:35<36:06,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 79/1900 [01:36<36:10,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 80/1900 [01:38<36:01,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 81/1900 [01:39<35:47,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 82/1900 [01:40<36:38,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 83/1900 [01:41<37:25,  1.24s/it]
+
+
Evaluating eval...:   4%|▍         | 84/1900 [01:43<37:06,  1.23s/it]
+
+
Evaluating eval...:   4%|▍         | 85/1900 [01:44<36:42,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 86/1900 [01:45<35:54,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 87/1900 [01:46<36:10,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 88/1900 [01:47<35:57,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 89/1900 [01:49<37:50,  1.25s/it]
+
+
Evaluating eval...:   5%|▍         | 90/1900 [01:50<37:11,  1.23s/it]
+
+
Evaluating eval...:   5%|▍         | 91/1900 [01:51<37:11,  1.23s/it]
+
+
Evaluating eval...:   5%|▍         | 92/1900 [01:52<36:32,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 93/1900 [01:53<36:11,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 94/1900 [01:55<35:40,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 95/1900 [01:56<35:11,  1.17s/it]
+
+
Evaluating eval...:   5%|▌         | 96/1900 [01:57<36:18,  1.21s/it]
+
+
Evaluating eval...:   5%|▌         | 97/1900 [01:58<35:38,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 98/1900 [01:59<36:50,  1.23s/it]
+
+
Evaluating eval...:   5%|▌         | 99/1900 [02:01<36:32,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 100/1900 [02:02<36:15,  1.21s/it]
+
+
Evaluating eval...:   5%|▌         | 101/1900 [02:03<37:18,  1.24s/it]
+
+
Evaluating eval...:   5%|▌         | 102/1900 [02:04<37:32,  1.25s/it]
+
+
Evaluating eval...:   5%|▌         | 103/1900 [02:06<36:55,  1.23s/it]
+
+
Evaluating eval...:   5%|▌         | 104/1900 [02:07<36:24,  1.22s/it]
+
+
Evaluating eval...:   6%|▌         | 105/1900 [02:08<36:14,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 106/1900 [02:09<35:32,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 107/1900 [02:10<35:51,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 108/1900 [02:11<35:13,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 109/1900 [02:13<35:19,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 110/1900 [02:14<35:05,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 111/1900 [02:15<35:24,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 112/1900 [02:16<36:13,  1.22s/it]
+
+
Evaluating eval...:   6%|▌         | 113/1900 [02:17<35:44,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 114/1900 [02:19<35:17,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 115/1900 [02:20<35:05,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 116/1900 [02:21<34:46,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 117/1900 [02:22<34:57,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 118/1900 [02:23<35:12,  1.19s/it]
+
+
Evaluating eval...:   6%|▋         | 119/1900 [02:24<35:05,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 120/1900 [02:26<35:33,  1.20s/it]
+
+
Evaluating eval...:   6%|▋         | 121/1900 [02:27<35:03,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 122/1900 [02:28<35:04,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 123/1900 [02:29<35:00,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 124/1900 [02:30<35:13,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 125/1900 [02:32<35:09,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 126/1900 [02:33<35:38,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 127/1900 [02:34<35:41,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 128/1900 [02:35<35:20,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 129/1900 [02:36<35:05,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 130/1900 [02:38<34:53,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 131/1900 [02:39<34:56,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 132/1900 [02:40<35:23,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 133/1900 [02:41<34:46,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 134/1900 [02:42<35:01,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 135/1900 [02:44<35:28,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 136/1900 [02:45<36:03,  1.23s/it]
+
+
Evaluating eval...:   7%|▋         | 137/1900 [02:46<36:40,  1.25s/it]
+
+
Evaluating eval...:   7%|▋         | 138/1900 [02:47<36:13,  1.23s/it]
+
+
Evaluating eval...:   7%|▋         | 139/1900 [02:49<35:37,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 140/1900 [02:50<35:35,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 141/1900 [02:51<35:10,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 142/1900 [02:52<36:02,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 143/1900 [02:53<36:11,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 144/1900 [02:55<35:15,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 145/1900 [02:56<35:12,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 146/1900 [02:57<34:48,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 147/1900 [02:58<35:11,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 148/1900 [02:59<34:36,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 149/1900 [03:01<34:41,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 150/1900 [03:02<35:24,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 151/1900 [03:03<35:16,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 152/1900 [03:04<35:29,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 153/1900 [03:06<35:34,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 154/1900 [03:07<35:23,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 155/1900 [03:08<35:01,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 156/1900 [03:09<34:52,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 157/1900 [03:10<36:03,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 158/1900 [03:12<35:36,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 159/1900 [03:13<34:51,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 160/1900 [03:14<34:33,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 161/1900 [03:15<35:16,  1.22s/it]
+
+
Evaluating eval...:   9%|▊         | 162/1900 [03:16<34:44,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 163/1900 [03:17<34:11,  1.18s/it]
+
+
Evaluating eval...:   9%|▊         | 164/1900 [03:19<34:36,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 165/1900 [03:20<34:34,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 166/1900 [03:21<34:27,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 167/1900 [03:22<35:22,  1.22s/it]
+
+
Evaluating eval...:   9%|▉         | 168/1900 [03:24<34:40,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 169/1900 [03:25<34:24,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 170/1900 [03:26<34:17,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 171/1900 [03:27<34:08,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 172/1900 [03:28<34:26,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 173/1900 [03:29<34:26,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 174/1900 [03:31<34:33,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 175/1900 [03:32<33:59,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 176/1900 [03:33<33:34,  1.17s/it]
+
+
Evaluating eval...:   9%|▉         | 177/1900 [03:35<40:50,  1.42s/it]
+
+
Evaluating eval...:   9%|▉         | 178/1900 [03:36<39:02,  1.36s/it]
+
+
Evaluating eval...:   9%|▉         | 179/1900 [03:37<37:12,  1.30s/it]
+
+
Evaluating eval...:   9%|▉         | 180/1900 [03:39<36:15,  1.26s/it]
+
+
Evaluating eval...:  10%|▉         | 181/1900 [03:40<35:24,  1.24s/it]
+
+
Evaluating eval...:  10%|▉         | 182/1900 [03:41<35:59,  1.26s/it]
+
+
Evaluating eval...:  10%|▉         | 183/1900 [03:42<35:41,  1.25s/it]
+
+
Evaluating eval...:  10%|▉         | 184/1900 [03:43<34:52,  1.22s/it]
+
+
Evaluating eval...:  10%|▉         | 185/1900 [03:45<34:36,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 186/1900 [03:46<34:14,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 187/1900 [03:47<34:24,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 188/1900 [03:48<34:26,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 189/1900 [03:49<34:00,  1.19s/it]
+
+
Evaluating eval...:  10%|█         | 190/1900 [03:51<33:52,  1.19s/it]
+
+
Evaluating eval...:  10%|█         | 191/1900 [03:52<33:33,  1.18s/it]
+
+
Evaluating eval...:  10%|█         | 192/1900 [03:53<34:30,  1.21s/it]
+
+
Evaluating eval...:  10%|█         | 193/1900 [03:54<36:04,  1.27s/it]
+
+
Evaluating eval...:  10%|█         | 194/1900 [03:56<35:40,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 195/1900 [03:57<35:27,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 196/1900 [03:58<35:01,  1.23s/it]
+
+
Evaluating eval...:  10%|█         | 197/1900 [03:59<35:43,  1.26s/it]
+
+
Evaluating eval...:  10%|█         | 198/1900 [04:01<35:56,  1.27s/it]
+
+
Evaluating eval...:  10%|█         | 199/1900 [04:02<35:00,  1.23s/it]
+
+
Evaluating eval...:  11%|█         | 200/1900 [04:03<34:16,  1.21s/it]
+
+
Evaluating eval...:  11%|█         | 201/1900 [04:04<33:46,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 202/1900 [04:05<33:18,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 203/1900 [04:06<33:42,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 204/1900 [04:08<33:31,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 205/1900 [04:09<33:28,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 206/1900 [04:10<33:21,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 207/1900 [04:11<34:04,  1.21s/it]
+
+
Evaluating eval...:  11%|█         | 208/1900 [04:12<33:32,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 209/1900 [04:14<33:21,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 210/1900 [04:15<33:08,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 211/1900 [04:16<33:16,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 212/1900 [04:17<33:10,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 213/1900 [04:18<33:49,  1.20s/it]
+
+
Evaluating eval...:  11%|█▏        | 214/1900 [04:20<33:52,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 215/1900 [04:21<33:37,  1.20s/it]
+
+
Evaluating eval...:  11%|█▏        | 216/1900 [04:22<33:30,  1.19s/it]
+
+
Evaluating eval...:  11%|█▏        | 217/1900 [04:23<33:27,  1.19s/it]
+
+
Evaluating eval...:  11%|█▏        | 218/1900 [04:24<33:52,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 219/1900 [04:26<33:43,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 220/1900 [04:27<33:59,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 221/1900 [04:28<33:36,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 222/1900 [04:29<33:17,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 223/1900 [04:30<32:49,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 224/1900 [04:31<32:32,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 225/1900 [04:33<32:32,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 226/1900 [04:34<32:47,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 227/1900 [04:35<32:39,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 228/1900 [04:36<33:08,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 229/1900 [04:37<32:43,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 230/1900 [04:39<32:49,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 231/1900 [04:40<32:51,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 232/1900 [04:41<32:30,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 233/1900 [04:42<32:51,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 234/1900 [04:43<32:51,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 235/1900 [04:44<32:50,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 236/1900 [04:46<33:28,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 237/1900 [04:47<33:44,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 238/1900 [04:48<33:45,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 239/1900 [04:49<34:35,  1.25s/it]
+
+
Evaluating eval...:  13%|█▎        | 240/1900 [04:51<33:45,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 241/1900 [04:52<33:11,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 242/1900 [04:53<33:15,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 243/1900 [04:54<32:44,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 244/1900 [04:55<32:37,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 245/1900 [04:57<33:09,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 246/1900 [04:58<33:09,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 247/1900 [04:59<33:00,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 248/1900 [05:00<33:03,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 249/1900 [05:01<32:34,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 250/1900 [05:03<32:50,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 251/1900 [05:04<33:30,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 252/1900 [05:05<32:56,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 253/1900 [05:06<33:28,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 254/1900 [05:07<33:08,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 255/1900 [05:09<33:04,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 256/1900 [05:10<32:42,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 257/1900 [05:11<32:15,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 258/1900 [05:12<32:15,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 259/1900 [05:13<32:16,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 260/1900 [05:14<32:29,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 261/1900 [05:16<32:25,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 262/1900 [05:17<32:06,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 263/1900 [05:18<32:12,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 264/1900 [05:19<32:18,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 265/1900 [05:20<32:26,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 266/1900 [05:22<32:14,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 267/1900 [05:23<32:37,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 268/1900 [05:24<32:17,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 269/1900 [05:25<32:08,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 270/1900 [05:26<31:54,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 271/1900 [05:27<31:34,  1.16s/it]
+
+
Evaluating eval...:  14%|█▍        | 272/1900 [05:29<32:00,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 273/1900 [05:30<32:29,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 274/1900 [05:31<32:28,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 275/1900 [05:32<32:24,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 276/1900 [05:34<32:53,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 277/1900 [05:35<32:39,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 278/1900 [05:36<32:24,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 279/1900 [05:37<32:31,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 280/1900 [05:38<32:38,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 281/1900 [05:40<32:35,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 282/1900 [05:41<32:42,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 283/1900 [05:42<32:14,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 284/1900 [05:43<32:14,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 285/1900 [05:44<31:52,  1.18s/it]
+
+
Evaluating eval...:  15%|█▌        | 286/1900 [05:46<32:14,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 287/1900 [05:47<32:13,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 288/1900 [05:48<33:23,  1.24s/it]
+
+
Evaluating eval...:  15%|█▌        | 289/1900 [05:49<33:02,  1.23s/it]
+
+
Evaluating eval...:  15%|█▌        | 290/1900 [05:50<32:31,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 291/1900 [05:52<32:09,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 292/1900 [05:53<32:05,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 293/1900 [05:54<31:42,  1.18s/it]
+
+
Evaluating eval...:  15%|█▌        | 294/1900 [05:55<31:29,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 295/1900 [05:56<31:38,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 296/1900 [05:58<32:04,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 297/1900 [05:59<32:17,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 298/1900 [06:00<32:31,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 299/1900 [06:01<31:58,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 300/1900 [06:02<32:07,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 301/1900 [06:04<32:14,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 302/1900 [06:05<31:57,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 303/1900 [06:06<31:37,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 304/1900 [06:07<31:15,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 305/1900 [06:08<31:19,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 306/1900 [06:09<31:20,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 307/1900 [06:11<31:12,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 308/1900 [06:12<31:13,  1.18s/it]
+
+
Evaluating eval...:  16%|█▋        | 309/1900 [06:13<31:43,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 310/1900 [06:14<31:53,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 311/1900 [06:15<32:03,  1.21s/it]
+
+
Evaluating eval...:  16%|█▋        | 312/1900 [06:17<31:53,  1.21s/it]
+
+
Evaluating eval...:  16%|█▋        | 313/1900 [06:18<31:33,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 314/1900 [06:19<31:21,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 315/1900 [06:20<31:24,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 316/1900 [06:21<31:08,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 317/1900 [06:23<31:30,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 318/1900 [06:24<31:21,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 319/1900 [06:25<31:25,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 320/1900 [06:26<31:17,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 321/1900 [06:27<30:49,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 322/1900 [06:28<30:55,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 323/1900 [06:30<31:01,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 324/1900 [06:31<30:37,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 325/1900 [06:32<30:36,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 326/1900 [06:33<30:33,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 327/1900 [06:34<30:35,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 328/1900 [06:36<31:10,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 329/1900 [06:37<30:44,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 330/1900 [06:38<31:08,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 331/1900 [06:39<32:07,  1.23s/it]
+
+
Evaluating eval...:  17%|█▋        | 332/1900 [06:40<32:04,  1.23s/it]
+
+
Evaluating eval...:  18%|█▊        | 333/1900 [06:42<31:50,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 334/1900 [06:43<31:11,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 335/1900 [06:44<30:36,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 336/1900 [06:45<30:35,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 337/1900 [06:46<30:37,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 338/1900 [06:48<31:10,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 339/1900 [06:49<31:21,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 340/1900 [06:50<31:02,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 341/1900 [06:51<31:12,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 342/1900 [06:52<30:46,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 343/1900 [06:53<30:34,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 344/1900 [06:55<30:39,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 345/1900 [06:56<30:41,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 346/1900 [06:57<30:28,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 347/1900 [06:58<30:31,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 348/1900 [06:59<30:11,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 349/1900 [07:00<30:01,  1.16s/it]
+
+
Evaluating eval...:  18%|█▊        | 350/1900 [07:02<30:00,  1.16s/it]
+
+
Evaluating eval...:  18%|█▊        | 351/1900 [07:03<30:37,  1.19s/it]
+
+
Evaluating eval...:  19%|█▊        | 352/1900 [07:04<30:43,  1.19s/it]
+
+
Evaluating eval...:  19%|█▊        | 353/1900 [07:05<31:05,  1.21s/it]
+
+
Evaluating eval...:  19%|█▊        | 354/1900 [07:06<30:58,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 355/1900 [07:08<31:22,  1.22s/it]
+
+
Evaluating eval...:  19%|█▊        | 356/1900 [07:09<31:22,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 357/1900 [07:10<30:48,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 358/1900 [07:11<31:01,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 359/1900 [07:13<30:40,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 360/1900 [07:14<30:41,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 361/1900 [07:15<30:21,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 362/1900 [07:16<31:22,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 363/1900 [07:17<30:42,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 364/1900 [07:18<30:21,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 365/1900 [07:20<30:14,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 366/1900 [07:21<30:00,  1.17s/it]
+
+
Evaluating eval...:  19%|█▉        | 367/1900 [07:22<30:48,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 368/1900 [07:23<31:24,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 369/1900 [07:25<31:10,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 370/1900 [07:26<30:41,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 371/1900 [07:27<30:25,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 372/1900 [07:28<30:13,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 373/1900 [07:29<30:00,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 374/1900 [07:30<29:43,  1.17s/it]
+
+
Evaluating eval...:  20%|█▉        | 375/1900 [07:32<29:32,  1.16s/it]
+
+
Evaluating eval...:  20%|█▉        | 376/1900 [07:33<29:47,  1.17s/it]
+
+
Evaluating eval...:  20%|█▉        | 377/1900 [07:34<30:25,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 378/1900 [07:35<30:31,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 379/1900 [07:36<30:23,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 380/1900 [07:38<30:22,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 381/1900 [07:39<30:37,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 382/1900 [07:40<30:54,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 383/1900 [07:41<30:18,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 384/1900 [07:42<30:00,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 385/1900 [07:44<29:51,  1.18s/it]
+
+
Evaluating eval...:  20%|██        | 386/1900 [07:45<30:03,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 387/1900 [07:46<29:57,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 388/1900 [07:47<29:48,  1.18s/it]
+
+
Evaluating eval...:  20%|██        | 389/1900 [07:48<29:59,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 390/1900 [07:49<29:45,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 391/1900 [07:51<29:55,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 392/1900 [07:52<29:35,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 393/1900 [07:53<29:26,  1.17s/it]
+
+
Evaluating eval...:  21%|██        | 394/1900 [07:54<29:29,  1.17s/it]
+
+
Evaluating eval...:  21%|██        | 395/1900 [07:55<29:18,  1.17s/it]
+
+
Evaluating eval...:  21%|██        | 396/1900 [07:57<30:04,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 397/1900 [07:58<30:08,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 398/1900 [07:59<29:45,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 399/1900 [08:00<30:06,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 400/1900 [08:01<29:52,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 401/1900 [08:03<29:50,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 402/1900 [08:04<29:34,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 403/1900 [08:05<29:47,  1.19s/it]
+
+
Evaluating eval...:  21%|██▏       | 404/1900 [08:06<29:57,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 405/1900 [08:07<29:54,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 406/1900 [08:09<29:50,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 407/1900 [08:10<29:49,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 408/1900 [08:11<30:08,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 409/1900 [08:12<30:07,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 410/1900 [08:13<30:06,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 411/1900 [08:15<30:01,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 412/1900 [08:16<29:32,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 413/1900 [08:17<29:50,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 414/1900 [08:18<29:36,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 415/1900 [08:19<29:01,  1.17s/it]
+
+
Evaluating eval...:  22%|██▏       | 416/1900 [08:20<28:41,  1.16s/it]
+
+
Evaluating eval...:  22%|██▏       | 417/1900 [08:22<29:14,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 418/1900 [08:23<29:04,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 419/1900 [08:24<28:51,  1.17s/it]
+
+
Evaluating eval...:  22%|██▏       | 420/1900 [08:25<29:19,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 421/1900 [08:26<29:33,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 422/1900 [08:28<29:20,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 423/1900 [08:29<29:39,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 424/1900 [08:30<29:41,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 425/1900 [08:31<29:39,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 426/1900 [08:33<29:50,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 427/1900 [08:34<29:30,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 428/1900 [08:35<29:00,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 429/1900 [08:36<29:03,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 430/1900 [08:37<28:40,  1.17s/it]
+
+
Evaluating eval...:  23%|██▎       | 431/1900 [08:38<28:37,  1.17s/it]
+
+
Evaluating eval...:  23%|██▎       | 432/1900 [08:40<29:09,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 433/1900 [08:41<29:07,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 434/1900 [08:42<29:52,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 435/1900 [08:43<29:17,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 436/1900 [08:44<29:22,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 437/1900 [08:46<28:47,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 438/1900 [08:47<28:37,  1.17s/it]
+
+
Evaluating eval...:  23%|██▎       | 439/1900 [08:48<28:40,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 440/1900 [08:49<28:29,  1.17s/it]
+
+
Evaluating eval...:  23%|██▎       | 441/1900 [08:50<28:23,  1.17s/it]
+
+
Evaluating eval...:  23%|██▎       | 442/1900 [08:51<28:09,  1.16s/it]
+
+
Evaluating eval...:  23%|██▎       | 443/1900 [08:53<28:30,  1.17s/it]
+
+
Evaluating eval...:  23%|██▎       | 444/1900 [08:54<28:35,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 445/1900 [08:55<28:46,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 446/1900 [08:56<28:55,  1.19s/it]
+
+
Evaluating eval...:  24%|██▎       | 447/1900 [08:57<28:34,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 448/1900 [08:58<28:21,  1.17s/it]
+
+
Evaluating eval...:  24%|██▎       | 449/1900 [09:00<28:28,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 450/1900 [09:01<28:25,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 451/1900 [09:02<28:33,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 452/1900 [09:03<28:16,  1.17s/it]
+
+
Evaluating eval...:  24%|██▍       | 453/1900 [09:04<28:52,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 454/1900 [09:06<29:10,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 455/1900 [09:07<29:04,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 456/1900 [09:08<29:01,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 457/1900 [09:09<28:55,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 458/1900 [09:10<28:46,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 459/1900 [09:12<28:17,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 460/1900 [09:13<28:04,  1.17s/it]
+
+
Evaluating eval...:  24%|██▍       | 461/1900 [09:14<28:31,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 462/1900 [09:15<28:26,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 463/1900 [09:16<28:22,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 464/1900 [09:18<28:29,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 465/1900 [09:19<28:21,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 466/1900 [09:20<27:57,  1.17s/it]
+
+
Evaluating eval...:  25%|██▍       | 467/1900 [09:21<27:57,  1.17s/it]
+
+
Evaluating eval...:  25%|██▍       | 468/1900 [09:22<28:08,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 469/1900 [09:23<28:08,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 470/1900 [09:25<28:03,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 471/1900 [09:26<28:03,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 472/1900 [09:27<28:43,  1.21s/it]
+
+
Evaluating eval...:  25%|██▍       | 473/1900 [09:28<28:16,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 474/1900 [09:29<28:02,  1.18s/it]
+
+
Evaluating eval...:  25%|██▌       | 475/1900 [09:30<27:55,  1.18s/it]
+
+
Evaluating eval...:  25%|██▌       | 476/1900 [09:32<27:45,  1.17s/it]
+
+
Evaluating eval...:  25%|██▌       | 477/1900 [09:33<28:18,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 478/1900 [09:34<28:16,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 479/1900 [09:35<28:35,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 480/1900 [09:36<28:24,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 481/1900 [09:38<30:08,  1.27s/it]
+
+
Evaluating eval...:  25%|██▌       | 482/1900 [09:39<29:11,  1.23s/it]
+
+
Evaluating eval...:  25%|██▌       | 483/1900 [09:40<28:47,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 484/1900 [09:42<29:24,  1.25s/it]
+
+
Evaluating eval...:  26%|██▌       | 485/1900 [09:43<28:41,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 486/1900 [09:44<28:08,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 487/1900 [09:45<27:56,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 488/1900 [09:46<28:16,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 489/1900 [09:47<28:14,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 490/1900 [09:49<28:10,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 491/1900 [09:50<28:17,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 492/1900 [09:51<28:10,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 493/1900 [09:52<28:17,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 494/1900 [09:53<27:56,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 495/1900 [09:55<27:44,  1.18s/it]
+
+
Evaluating eval...:  26%|██▌       | 496/1900 [09:56<27:55,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 497/1900 [09:57<28:09,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 498/1900 [09:58<28:17,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 499/1900 [09:59<28:05,  1.20s/it]
+
+
Evaluating eval...:  26%|██▋       | 500/1900 [10:01<27:51,  1.19s/it]
+
+
Evaluating eval...:  26%|██▋       | 501/1900 [10:02<28:01,  1.20s/it]
+
+
Evaluating eval...:  26%|██▋       | 502/1900 [10:03<27:58,  1.20s/it]
+
+
Evaluating eval...:  26%|██▋       | 503/1900 [10:04<28:25,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 504/1900 [10:06<28:52,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 505/1900 [10:07<28:48,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 506/1900 [10:08<28:19,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 507/1900 [10:09<27:54,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 508/1900 [10:10<28:29,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 509/1900 [10:12<28:43,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 510/1900 [10:13<28:20,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 511/1900 [10:14<27:51,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 512/1900 [10:15<27:34,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 513/1900 [10:16<27:09,  1.17s/it]
+
+
Evaluating eval...:  27%|██▋       | 514/1900 [10:18<26:58,  1.17s/it]
+
+
Evaluating eval...:  27%|██▋       | 515/1900 [10:19<27:21,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 516/1900 [10:20<27:24,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 517/1900 [10:21<27:07,  1.18s/it]
+
+
Evaluating eval...:  27%|██▋       | 518/1900 [10:22<27:37,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 519/1900 [10:24<27:52,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 520/1900 [10:25<27:26,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 521/1900 [10:26<27:47,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 522/1900 [10:27<27:20,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 523/1900 [10:28<27:31,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 524/1900 [10:30<27:22,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 525/1900 [10:31<27:05,  1.18s/it]
+
+
Evaluating eval...:  28%|██▊       | 526/1900 [10:32<27:09,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 527/1900 [10:33<27:28,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 528/1900 [10:34<27:26,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 529/1900 [10:36<27:49,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 530/1900 [10:37<27:26,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 531/1900 [10:38<27:16,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 532/1900 [10:39<27:38,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 533/1900 [10:40<27:15,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 534/1900 [10:42<27:10,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 535/1900 [10:43<26:55,  1.18s/it]
+
+
Evaluating eval...:  28%|██▊       | 536/1900 [10:44<26:51,  1.18s/it]
+
+
Evaluating eval...:  28%|██▊       | 537/1900 [10:45<27:03,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 538/1900 [10:46<26:58,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 539/1900 [10:47<27:04,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 540/1900 [10:49<26:59,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 541/1900 [10:50<26:42,  1.18s/it]
+
+
Evaluating eval...:  29%|██▊       | 542/1900 [10:51<27:08,  1.20s/it]
+
+
Evaluating eval...:  29%|██▊       | 543/1900 [10:52<26:46,  1.18s/it]
+
+
Evaluating eval...:  29%|██▊       | 544/1900 [10:53<26:41,  1.18s/it]
+
+
Evaluating eval...:  29%|██▊       | 545/1900 [10:55<27:42,  1.23s/it]
+
+
Evaluating eval...:  29%|██▊       | 546/1900 [10:56<27:25,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 547/1900 [10:57<27:23,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 548/1900 [10:58<27:23,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 549/1900 [11:00<27:16,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 550/1900 [11:01<27:17,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 551/1900 [11:02<27:02,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 552/1900 [11:03<27:23,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 553/1900 [11:04<27:06,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 554/1900 [11:06<26:43,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 555/1900 [11:07<26:30,  1.18s/it]
+
+
Evaluating eval...:  29%|██▉       | 556/1900 [11:08<26:30,  1.18s/it]
+
+
Evaluating eval...:  29%|██▉       | 557/1900 [11:09<26:14,  1.17s/it]
+
+
Evaluating eval...:  29%|██▉       | 558/1900 [11:10<26:26,  1.18s/it]
+
+
Evaluating eval...:  29%|██▉       | 559/1900 [11:11<26:15,  1.18s/it]
+
+
Evaluating eval...:  29%|██▉       | 560/1900 [11:13<26:27,  1.18s/it]
+
+
Evaluating eval...:  30%|██▉       | 561/1900 [11:14<26:25,  1.18s/it]
+
+
Evaluating eval...:  30%|██▉       | 562/1900 [11:15<26:32,  1.19s/it]
+
+
Evaluating eval...:  30%|██▉       | 563/1900 [11:16<26:43,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 564/1900 [11:17<26:58,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 565/1900 [11:19<26:48,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 566/1900 [11:20<27:12,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 567/1900 [11:21<27:10,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 568/1900 [11:22<27:05,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 569/1900 [11:24<26:53,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 570/1900 [11:25<27:35,  1.25s/it]
+
+
Evaluating eval...:  30%|███       | 571/1900 [11:26<26:53,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 572/1900 [11:27<26:41,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 573/1900 [11:28<26:29,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 574/1900 [11:30<26:19,  1.19s/it]
+
+
Evaluating eval...:  30%|███       | 575/1900 [11:31<26:02,  1.18s/it]
+
+
Evaluating eval...:  30%|███       | 576/1900 [11:32<26:15,  1.19s/it]
+
+
Evaluating eval...:  30%|███       | 577/1900 [11:33<26:17,  1.19s/it]
+
+
Evaluating eval...:  30%|███       | 578/1900 [11:34<26:12,  1.19s/it]
+
+
Evaluating eval...:  30%|███       | 579/1900 [11:35<26:10,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 580/1900 [11:37<25:58,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 581/1900 [11:38<25:48,  1.17s/it]
+
+
Evaluating eval...:  31%|███       | 582/1900 [11:40<32:41,  1.49s/it]
+
+
Evaluating eval...:  31%|███       | 583/1900 [11:41<30:30,  1.39s/it]
+
+
Evaluating eval...:  31%|███       | 584/1900 [11:42<28:57,  1.32s/it]
+
+
Evaluating eval...:  31%|███       | 585/1900 [11:43<27:56,  1.28s/it]
+
+
Evaluating eval...:  31%|███       | 586/1900 [11:45<27:40,  1.26s/it]
+
+
Evaluating eval...:  31%|███       | 587/1900 [11:46<26:54,  1.23s/it]
+
+
Evaluating eval...:  31%|███       | 588/1900 [11:47<26:31,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 589/1900 [11:48<26:22,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 590/1900 [11:49<26:09,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 591/1900 [11:51<25:55,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 592/1900 [11:52<26:00,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 593/1900 [11:53<25:52,  1.19s/it]
+
+
Evaluating eval...:  31%|███▏      | 594/1900 [11:54<26:05,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 595/1900 [11:55<25:46,  1.18s/it]
+
+
Evaluating eval...:  31%|███▏      | 596/1900 [11:57<25:56,  1.19s/it]
+
+
Evaluating eval...:  31%|███▏      | 597/1900 [11:58<26:06,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 598/1900 [11:59<25:53,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 599/1900 [12:00<25:48,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 600/1900 [12:01<26:03,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 601/1900 [12:03<25:56,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 602/1900 [12:04<25:35,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 603/1900 [12:05<25:38,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 604/1900 [12:06<25:36,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 605/1900 [12:07<25:43,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 606/1900 [12:09<25:50,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 607/1900 [12:10<25:26,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 608/1900 [12:11<25:48,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 609/1900 [12:12<25:53,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 610/1900 [12:13<25:32,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 611/1900 [12:14<25:13,  1.17s/it]
+
+
Evaluating eval...:  32%|███▏      | 612/1900 [12:16<25:29,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 613/1900 [12:17<25:30,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 614/1900 [12:18<26:06,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 615/1900 [12:19<25:45,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 616/1900 [12:20<25:31,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 617/1900 [12:22<25:16,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 618/1900 [12:23<25:01,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 619/1900 [12:24<25:31,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 620/1900 [12:25<25:19,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 621/1900 [12:26<25:19,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 622/1900 [12:28<25:33,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 623/1900 [12:29<25:30,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 624/1900 [12:30<25:33,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 625/1900 [12:31<25:54,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 626/1900 [12:32<25:25,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 627/1900 [12:34<25:08,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 628/1900 [12:35<25:02,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 629/1900 [12:36<25:17,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 630/1900 [12:37<25:16,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 631/1900 [12:38<25:34,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 632/1900 [12:40<25:08,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 633/1900 [12:41<24:52,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 634/1900 [12:42<24:29,  1.16s/it]
+
+
Evaluating eval...:  33%|███▎      | 635/1900 [12:43<24:30,  1.16s/it]
+
+
Evaluating eval...:  33%|███▎      | 636/1900 [12:44<24:44,  1.17s/it]
+
+
Evaluating eval...:  34%|███▎      | 637/1900 [12:45<24:56,  1.19s/it]
+
+
Evaluating eval...:  34%|███▎      | 638/1900 [12:47<25:09,  1.20s/it]
+
+
Evaluating eval...:  34%|███▎      | 639/1900 [12:48<25:17,  1.20s/it]
+
+
Evaluating eval...:  34%|███▎      | 640/1900 [12:49<25:19,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 641/1900 [12:50<25:13,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 642/1900 [12:51<25:06,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 643/1900 [12:53<25:28,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 644/1900 [12:54<25:12,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 645/1900 [12:55<25:09,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 646/1900 [12:56<25:26,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 647/1900 [12:57<25:06,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 648/1900 [12:59<24:53,  1.19s/it]
+
+
Evaluating eval...:  34%|███▍      | 649/1900 [13:00<25:00,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 650/1900 [13:01<25:18,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 651/1900 [13:02<25:19,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 652/1900 [13:03<24:50,  1.19s/it]
+
+
Evaluating eval...:  34%|███▍      | 653/1900 [13:05<24:34,  1.18s/it]
+
+
Evaluating eval...:  34%|███▍      | 654/1900 [13:06<24:51,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 655/1900 [13:07<24:46,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 656/1900 [13:08<24:31,  1.18s/it]
+
+
Evaluating eval...:  35%|███▍      | 657/1900 [13:09<24:30,  1.18s/it]
+
+
Evaluating eval...:  35%|███▍      | 658/1900 [13:11<25:03,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 659/1900 [13:12<25:07,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 660/1900 [13:13<24:44,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 661/1900 [13:14<24:37,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 662/1900 [13:15<24:59,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 663/1900 [13:17<25:08,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 664/1900 [13:18<24:55,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 665/1900 [13:19<24:39,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 666/1900 [13:20<24:29,  1.19s/it]
+
+
Evaluating eval...:  35%|███▌      | 667/1900 [13:22<25:17,  1.23s/it]
+
+
Evaluating eval...:  35%|███▌      | 668/1900 [13:23<24:51,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 669/1900 [13:24<24:26,  1.19s/it]
+
+
Evaluating eval...:  35%|███▌      | 670/1900 [13:25<24:22,  1.19s/it]
+
+
Evaluating eval...:  35%|███▌      | 671/1900 [13:26<24:28,  1.19s/it]
+
+
Evaluating eval...:  35%|███▌      | 672/1900 [13:27<24:22,  1.19s/it]
+
+
Evaluating eval...:  35%|███▌      | 673/1900 [13:29<24:21,  1.19s/it]
+
+
Evaluating eval...:  35%|███▌      | 674/1900 [13:30<24:19,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 675/1900 [13:31<24:12,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 676/1900 [13:32<24:01,  1.18s/it]
+
+
Evaluating eval...:  36%|███▌      | 677/1900 [13:33<24:00,  1.18s/it]
+
+
Evaluating eval...:  36%|███▌      | 678/1900 [13:35<24:24,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 679/1900 [13:36<23:59,  1.18s/it]
+
+
Evaluating eval...:  36%|███▌      | 680/1900 [13:37<24:11,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 681/1900 [13:38<24:25,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 682/1900 [13:39<24:30,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 683/1900 [13:41<24:30,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 684/1900 [13:42<24:09,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 685/1900 [13:43<24:01,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 686/1900 [13:44<24:29,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 687/1900 [13:45<24:27,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 688/1900 [13:47<23:59,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 689/1900 [13:48<23:54,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 690/1900 [13:49<24:02,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 691/1900 [13:50<24:14,  1.20s/it]
+
+
Evaluating eval...:  36%|███▋      | 692/1900 [13:51<23:49,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 693/1900 [13:52<23:45,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 694/1900 [13:54<23:42,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 695/1900 [13:55<24:09,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 696/1900 [13:56<24:04,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 697/1900 [13:57<23:47,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 698/1900 [13:58<23:52,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 699/1900 [14:00<24:04,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 700/1900 [14:01<23:43,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 701/1900 [14:02<23:50,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 702/1900 [14:03<23:52,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 703/1900 [14:04<23:26,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 704/1900 [14:06<24:11,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 705/1900 [14:07<24:04,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 706/1900 [14:08<23:58,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 707/1900 [14:09<23:46,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 708/1900 [14:10<24:09,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 709/1900 [14:12<23:51,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 710/1900 [14:13<23:46,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 711/1900 [14:14<24:32,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 712/1900 [14:15<24:30,  1.24s/it]
+
+
Evaluating eval...:  38%|███▊      | 713/1900 [14:17<24:46,  1.25s/it]
+
+
Evaluating eval...:  38%|███▊      | 714/1900 [14:18<24:13,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 715/1900 [14:19<23:53,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 716/1900 [14:20<23:32,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 717/1900 [14:21<23:22,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 718/1900 [14:23<23:35,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 719/1900 [14:24<23:33,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 720/1900 [14:25<23:24,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 721/1900 [14:26<23:49,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 722/1900 [14:27<23:42,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 723/1900 [14:29<23:38,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 724/1900 [14:30<23:33,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 725/1900 [14:31<23:17,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 726/1900 [14:32<23:22,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 727/1900 [14:33<23:07,  1.18s/it]
+
+
Evaluating eval...:  38%|███▊      | 728/1900 [14:35<23:32,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 729/1900 [14:36<23:18,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 730/1900 [14:37<23:50,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 731/1900 [14:38<23:38,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 732/1900 [14:39<23:25,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 733/1900 [14:41<23:20,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 734/1900 [14:42<23:13,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 735/1900 [14:43<23:01,  1.19s/it]
+
+
Evaluating eval...:  39%|███▊      | 736/1900 [14:44<22:55,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 737/1900 [14:45<22:46,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 738/1900 [14:47<22:59,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 739/1900 [14:48<22:43,  1.17s/it]
+
+
Evaluating eval...:  39%|███▉      | 740/1900 [14:49<22:49,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 741/1900 [14:50<23:22,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 742/1900 [14:51<23:17,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 743/1900 [14:53<23:24,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 744/1900 [14:54<23:03,  1.20s/it]
+
+
Evaluating eval...:  39%|███▉      | 745/1900 [14:55<23:49,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 746/1900 [14:56<23:48,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 747/1900 [14:58<24:22,  1.27s/it]
+
+
Evaluating eval...:  39%|███▉      | 748/1900 [14:59<23:45,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 749/1900 [15:00<23:47,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 750/1900 [15:01<23:27,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 751/1900 [15:02<23:22,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 752/1900 [15:04<23:29,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 753/1900 [15:05<23:29,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 754/1900 [15:06<23:04,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 755/1900 [15:07<22:43,  1.19s/it]
+
+
Evaluating eval...:  40%|███▉      | 756/1900 [15:08<23:01,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 757/1900 [15:10<22:56,  1.20s/it]
+
+
Evaluating eval...:  40%|███▉      | 758/1900 [15:11<23:02,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 759/1900 [15:12<23:06,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 760/1900 [15:13<23:07,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 761/1900 [15:14<22:48,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 762/1900 [15:16<22:29,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 763/1900 [15:17<22:20,  1.18s/it]
+
+
Evaluating eval...:  40%|████      | 764/1900 [15:18<22:12,  1.17s/it]
+
+
Evaluating eval...:  40%|████      | 765/1900 [15:19<22:34,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 766/1900 [15:20<22:31,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 767/1900 [15:22<22:46,  1.21s/it]
+
+
Evaluating eval...:  40%|████      | 768/1900 [15:23<23:20,  1.24s/it]
+
+
Evaluating eval...:  40%|████      | 769/1900 [15:24<23:07,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 770/1900 [15:25<22:45,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 771/1900 [15:27<22:45,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 772/1900 [15:28<22:50,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 773/1900 [15:29<22:38,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 774/1900 [15:30<22:17,  1.19s/it]
+
+
Evaluating eval...:  41%|████      | 775/1900 [15:31<22:45,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 776/1900 [15:33<22:42,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 777/1900 [15:34<22:49,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 778/1900 [15:35<22:34,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 779/1900 [15:36<22:20,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 780/1900 [15:38<23:20,  1.25s/it]
+
+
Evaluating eval...:  41%|████      | 781/1900 [15:39<23:01,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 782/1900 [15:40<23:30,  1.26s/it]
+
+
Evaluating eval...:  41%|████      | 783/1900 [15:41<23:20,  1.25s/it]
+
+
Evaluating eval...:  41%|████▏     | 784/1900 [15:42<22:53,  1.23s/it]
+
+
Evaluating eval...:  41%|████▏     | 785/1900 [15:44<22:29,  1.21s/it]
+
+
Evaluating eval...:  41%|████▏     | 786/1900 [15:45<22:19,  1.20s/it]
+
+
Evaluating eval...:  41%|████▏     | 787/1900 [15:46<22:19,  1.20s/it]
+
+
Evaluating eval...:  41%|████▏     | 788/1900 [15:47<22:14,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 789/1900 [15:48<22:26,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 790/1900 [15:50<22:24,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 791/1900 [15:51<22:30,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 792/1900 [15:52<22:38,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 793/1900 [15:53<22:19,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 794/1900 [15:54<22:11,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 795/1900 [15:56<22:10,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 796/1900 [15:57<21:57,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 797/1900 [15:58<21:50,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 798/1900 [15:59<21:47,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 799/1900 [16:00<21:45,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 800/1900 [16:02<22:20,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 801/1900 [16:03<22:08,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 802/1900 [16:04<21:44,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 803/1900 [16:05<22:12,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 804/1900 [16:06<22:02,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 805/1900 [16:08<22:03,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 806/1900 [16:09<21:52,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 807/1900 [16:10<21:40,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 808/1900 [16:11<22:05,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 809/1900 [16:13<22:15,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 810/1900 [16:14<22:06,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 811/1900 [16:15<21:56,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 812/1900 [16:16<22:22,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 813/1900 [16:17<21:53,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 814/1900 [16:19<21:51,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 815/1900 [16:20<21:52,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 816/1900 [16:21<21:57,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 817/1900 [16:22<21:39,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 818/1900 [16:23<21:58,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 819/1900 [16:25<21:44,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 820/1900 [16:26<21:40,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 821/1900 [16:27<21:39,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 822/1900 [16:28<21:45,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 823/1900 [16:30<21:54,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 824/1900 [16:31<21:38,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 825/1900 [16:32<21:27,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 826/1900 [16:33<21:46,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 827/1900 [16:34<21:42,  1.21s/it]
+
+
Evaluating eval...:  44%|████▎     | 828/1900 [16:36<21:43,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 829/1900 [16:37<21:26,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 830/1900 [16:38<21:34,  1.21s/it]
+
+
Evaluating eval...:  44%|████▎     | 831/1900 [16:39<21:13,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 832/1900 [16:40<21:13,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 833/1900 [16:42<21:17,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 834/1900 [16:43<20:56,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 835/1900 [16:44<21:21,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 836/1900 [16:45<21:24,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 837/1900 [16:46<21:13,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 838/1900 [16:47<20:55,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 839/1900 [16:49<20:45,  1.17s/it]
+
+
Evaluating eval...:  44%|████▍     | 840/1900 [16:50<20:56,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 841/1900 [16:51<21:16,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 842/1900 [16:52<21:11,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 843/1900 [16:53<20:57,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 844/1900 [16:55<20:40,  1.17s/it]
+
+
Evaluating eval...:  44%|████▍     | 845/1900 [16:56<20:41,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 846/1900 [16:57<21:05,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 847/1900 [16:58<20:46,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 848/1900 [16:59<20:46,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 849/1900 [17:01<20:42,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 850/1900 [17:02<20:51,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 851/1900 [17:03<20:48,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 852/1900 [17:04<21:16,  1.22s/it]
+
+
Evaluating eval...:  45%|████▍     | 853/1900 [17:05<21:04,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 854/1900 [17:07<21:04,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 855/1900 [17:08<20:59,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 856/1900 [17:09<20:43,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 857/1900 [17:10<20:36,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 858/1900 [17:11<20:50,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 859/1900 [17:13<20:46,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 860/1900 [17:14<20:56,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 861/1900 [17:15<21:21,  1.23s/it]
+
+
Evaluating eval...:  45%|████▌     | 862/1900 [17:16<21:10,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 863/1900 [17:17<20:41,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 864/1900 [17:19<20:29,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 865/1900 [17:20<20:17,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 866/1900 [17:21<20:13,  1.17s/it]
+
+
Evaluating eval...:  46%|████▌     | 867/1900 [17:22<20:25,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 868/1900 [17:23<21:13,  1.23s/it]
+
+
Evaluating eval...:  46%|████▌     | 869/1900 [17:25<20:48,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 870/1900 [17:26<20:53,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 871/1900 [17:27<21:00,  1.23s/it]
+
+
Evaluating eval...:  46%|████▌     | 872/1900 [17:28<20:48,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 873/1900 [17:29<20:37,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 874/1900 [17:31<20:50,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 875/1900 [17:32<20:45,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 876/1900 [17:33<20:32,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 877/1900 [17:34<20:14,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 878/1900 [17:36<20:37,  1.21s/it]
+
+
Evaluating eval...:  46%|████▋     | 879/1900 [17:37<20:22,  1.20s/it]
+
+
Evaluating eval...:  46%|████▋     | 880/1900 [17:38<20:08,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 881/1900 [17:39<20:03,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 882/1900 [17:40<20:17,  1.20s/it]
+
+
Evaluating eval...:  46%|████▋     | 883/1900 [17:41<20:27,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 884/1900 [17:43<20:29,  1.21s/it]
+
+
Evaluating eval...:  47%|███��▋     | 885/1900 [17:44<20:12,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 886/1900 [17:45<19:58,  1.18s/it]
+
+
Evaluating eval...:  47%|████▋     | 887/1900 [17:46<20:02,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 888/1900 [17:47<20:07,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 889/1900 [17:49<20:06,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 890/1900 [17:50<19:56,  1.18s/it]
+
+
Evaluating eval...:  47%|████▋     | 891/1900 [17:51<20:17,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 892/1900 [17:52<20:22,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 893/1900 [17:53<20:29,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 894/1900 [17:55<20:05,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 895/1900 [17:56<20:06,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 896/1900 [17:57<20:04,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 897/1900 [17:58<19:56,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 898/1900 [18:00<20:42,  1.24s/it]
+
+
Evaluating eval...:  47%|████▋     | 899/1900 [18:01<20:16,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 900/1900 [18:02<20:21,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 901/1900 [18:03<20:03,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 902/1900 [18:04<20:20,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 903/1900 [18:06<20:14,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 904/1900 [18:07<20:04,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 905/1900 [18:08<19:52,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 906/1900 [18:09<20:16,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 907/1900 [18:11<20:30,  1.24s/it]
+
+
Evaluating eval...:  48%|████▊     | 908/1900 [18:12<20:08,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 909/1900 [18:13<20:05,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 910/1900 [18:14<19:59,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 911/1900 [18:15<20:07,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 912/1900 [18:17<19:52,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 913/1900 [18:18<19:44,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 914/1900 [18:19<19:41,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 915/1900 [18:20<20:05,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 916/1900 [18:21<19:48,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 917/1900 [18:22<19:32,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 918/1900 [18:24<19:38,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 919/1900 [18:25<19:47,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 920/1900 [18:26<19:39,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 921/1900 [18:27<19:25,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 922/1900 [18:28<19:20,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 923/1900 [18:30<19:49,  1.22s/it]
+
+
Evaluating eval...:  49%|████▊     | 924/1900 [18:31<19:23,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 925/1900 [18:32<19:42,  1.21s/it]
+
+
Evaluating eval...:  49%|████▊     | 926/1900 [18:33<19:28,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 927/1900 [18:34<19:12,  1.18s/it]
+
+
Evaluating eval...:  49%|████▉     | 928/1900 [18:36<19:41,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 929/1900 [18:37<19:19,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 930/1900 [18:38<19:02,  1.18s/it]
+
+
Evaluating eval...:  49%|████▉     | 931/1900 [18:39<19:15,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 932/1900 [18:41<19:34,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 933/1900 [18:42<19:35,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 934/1900 [18:43<19:19,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 935/1900 [18:44<19:31,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 936/1900 [18:46<20:14,  1.26s/it]
+
+
Evaluating eval...:  49%|████▉     | 937/1900 [18:47<19:57,  1.24s/it]
+
+
Evaluating eval...:  49%|████▉     | 938/1900 [18:48<19:43,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 939/1900 [18:49<19:35,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 940/1900 [18:50<19:39,  1.23s/it]
+
+
Evaluating eval...:  50%|████▉     | 941/1900 [18:52<19:33,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 942/1900 [18:53<19:56,  1.25s/it]
+
+
Evaluating eval...:  50%|████▉     | 943/1900 [18:54<19:34,  1.23s/it]
+
+
Evaluating eval...:  50%|████▉     | 944/1900 [18:55<19:15,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 945/1900 [18:56<18:57,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 946/1900 [18:58<18:55,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 947/1900 [18:59<19:08,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 948/1900 [19:00<19:03,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 949/1900 [19:01<19:12,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 950/1900 [19:02<19:05,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 951/1900 [19:04<19:32,  1.24s/it]
+
+
Evaluating eval...:  50%|█████     | 952/1900 [19:05<19:38,  1.24s/it]
+
+
Evaluating eval...:  50%|█████     | 953/1900 [19:06<19:13,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 954/1900 [19:07<18:53,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 955/1900 [19:09<18:52,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 956/1900 [19:10<18:42,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 957/1900 [19:11<18:32,  1.18s/it]
+
+
Evaluating eval...:  50%|█████     | 958/1900 [19:12<18:44,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 959/1900 [19:13<18:37,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 960/1900 [19:14<18:34,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 961/1900 [19:16<19:13,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 962/1900 [19:17<18:59,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 963/1900 [19:18<19:20,  1.24s/it]
+
+
Evaluating eval...:  51%|█████     | 964/1900 [19:20<19:30,  1.25s/it]
+
+
Evaluating eval...:  51%|█████     | 965/1900 [19:21<19:17,  1.24s/it]
+
+
Evaluating eval...:  51%|█████     | 966/1900 [19:22<18:52,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 967/1900 [19:23<18:37,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 968/1900 [19:24<18:32,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 969/1900 [19:25<18:46,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 970/1900 [19:27<18:52,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 971/1900 [19:28<18:36,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 972/1900 [19:29<18:53,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 973/1900 [19:30<18:39,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 974/1900 [19:31<18:29,  1.20s/it]
+
+
Evaluating eval...:  51%|█████▏    | 975/1900 [19:33<18:47,  1.22s/it]
+
+
Evaluating eval...:  51%|█████▏    | 976/1900 [19:34<18:45,  1.22s/it]
+
+
Evaluating eval...:  51%|█████▏    | 977/1900 [19:35<18:25,  1.20s/it]
+
+
Evaluating eval...:  51%|█████▏    | 978/1900 [19:36<18:31,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 979/1900 [19:38<18:22,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 980/1900 [19:39<18:23,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 981/1900 [19:40<18:05,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 982/1900 [19:41<17:58,  1.17s/it]
+
+
Evaluating eval...:  52%|█████▏    | 983/1900 [19:42<18:11,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 984/1900 [19:43<18:10,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 985/1900 [19:45<18:02,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 986/1900 [19:46<17:55,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 987/1900 [19:47<17:53,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 988/1900 [19:48<17:50,  1.17s/it]
+
+
Evaluating eval...:  52%|█████▏    | 989/1900 [19:49<18:09,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 990/1900 [19:51<18:38,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 991/1900 [19:52<18:25,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 992/1900 [19:53<18:15,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 993/1900 [19:54<18:18,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 994/1900 [19:55<18:06,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 995/1900 [19:57<18:23,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 996/1900 [19:58<18:06,  1.20s/it]
+
+
Evaluating eval...:  52%|████���▏    | 997/1900 [19:59<17:57,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 998/1900 [20:00<17:57,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 999/1900 [20:01<17:54,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1000/1900 [20:03<17:46,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1001/1900 [20:04<17:41,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1002/1900 [20:05<17:48,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1003/1900 [20:06<18:08,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1004/1900 [20:07<18:13,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1005/1900 [20:09<17:53,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1006/1900 [20:10<17:56,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1007/1900 [20:11<17:50,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1008/1900 [20:12<17:37,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1009/1900 [20:13<17:33,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1010/1900 [20:15<17:39,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1011/1900 [20:16<17:31,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1012/1900 [20:17<17:59,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1013/1900 [20:18<17:44,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1014/1900 [20:19<17:57,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1015/1900 [20:21<17:44,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1016/1900 [20:22<18:13,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1017/1900 [20:23<18:13,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1018/1900 [20:24<18:08,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1019/1900 [20:26<18:24,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1020/1900 [20:27<18:14,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1021/1900 [20:28<18:02,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1022/1900 [20:29<18:01,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1023/1900 [20:31<18:03,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1024/1900 [20:32<17:53,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1025/1900 [20:33<17:33,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1026/1900 [20:34<17:40,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1027/1900 [20:35<17:39,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1028/1900 [20:37<17:27,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1029/1900 [20:38<17:21,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1030/1900 [20:39<17:15,  1.19s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1031/1900 [20:40<17:38,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1032/1900 [20:41<17:24,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1033/1900 [20:43<17:11,  1.19s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1034/1900 [20:44<17:49,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1035/1900 [20:45<17:35,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1036/1900 [20:46<17:34,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1037/1900 [20:47<17:26,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1038/1900 [20:49<17:19,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1039/1900 [20:50<17:24,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1040/1900 [20:51<17:16,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1041/1900 [20:52<17:21,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1042/1900 [20:54<17:29,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1043/1900 [20:55<17:17,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1044/1900 [20:56<17:14,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1045/1900 [20:57<16:59,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1046/1900 [20:58<16:57,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1047/1900 [20:59<16:49,  1.18s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1048/1900 [21:01<16:57,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1049/1900 [21:02<17:07,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1050/1900 [21:03<17:25,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1051/1900 [21:04<17:35,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1052/1900 [21:06<17:34,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1053/1900 [21:07<17:22,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1054/1900 [21:08<17:08,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1055/1900 [21:09<16:50,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1056/1900 [21:11<17:10,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1057/1900 [21:12<17:28,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1058/1900 [21:13<17:18,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1059/1900 [21:14<16:50,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1060/1900 [21:15<16:34,  1.18s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1061/1900 [21:17<16:37,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1062/1900 [21:18<16:32,  1.18s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1063/1900 [21:19<16:38,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1064/1900 [21:20<16:52,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1065/1900 [21:21<16:47,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1066/1900 [21:23<16:37,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1067/1900 [21:24<16:46,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1068/1900 [21:25<16:38,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1069/1900 [21:26<16:46,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1070/1900 [21:27<16:42,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1071/1900 [21:29<16:44,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1072/1900 [21:30<16:45,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1073/1900 [21:31<16:28,  1.19s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1074/1900 [21:32<16:32,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1075/1900 [21:33<16:36,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1076/1900 [21:35<16:44,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1077/1900 [21:36<16:40,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1078/1900 [21:37<16:20,  1.19s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1079/1900 [21:38<16:46,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1080/1900 [21:40<17:13,  1.26s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1081/1900 [21:41<17:05,  1.25s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1082/1900 [21:42<16:51,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1083/1900 [21:43<16:53,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1084/1900 [21:44<16:34,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1085/1900 [21:46<16:40,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1086/1900 [21:47<16:48,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1087/1900 [21:48<16:36,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1088/1900 [21:49<16:24,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1089/1900 [21:51<16:42,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1090/1900 [21:52<16:26,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1091/1900 [21:53<16:14,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1092/1900 [21:54<16:49,  1.25s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1093/1900 [21:56<16:30,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1094/1900 [21:57<16:22,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1095/1900 [21:58<16:20,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1096/1900 [21:59<16:02,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1097/1900 [22:00<15:54,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1098/1900 [22:02<16:14,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1099/1900 [22:03<16:14,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1100/1900 [22:04<16:07,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1101/1900 [22:05<16:00,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1102/1900 [22:06<15:53,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1103/1900 [22:08<16:14,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1104/1900 [22:09<15:56,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1105/1900 [22:10<16:26,  1.24s/it]
+
+
Evaluating eval...:  58%|███���█▊    | 1106/1900 [22:11<16:31,  1.25s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1107/1900 [22:13<16:28,  1.25s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1108/1900 [22:14<16:19,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1109/1900 [22:15<16:12,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1110/1900 [22:16<15:58,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1111/1900 [22:18<16:23,  1.25s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1112/1900 [22:19<16:10,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1113/1900 [22:20<16:10,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1114/1900 [22:21<16:02,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1115/1900 [22:22<16:01,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1116/1900 [22:24<15:59,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1117/1900 [22:25<15:51,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1118/1900 [22:26<15:38,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1119/1900 [22:27<15:51,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1120/1900 [22:28<15:46,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1121/1900 [22:30<15:49,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1122/1900 [22:31<15:34,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1123/1900 [22:32<15:35,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1124/1900 [22:33<15:34,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1125/1900 [22:34<15:30,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1126/1900 [22:36<15:24,  1.19s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1127/1900 [22:37<15:18,  1.19s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1128/1900 [22:38<15:31,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1129/1900 [22:39<15:32,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1130/1900 [22:40<15:22,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1131/1900 [22:42<15:22,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1132/1900 [22:43<15:29,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1133/1900 [22:44<15:29,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1134/1900 [22:45<15:22,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1135/1900 [22:47<15:44,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1136/1900 [22:48<15:28,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1137/1900 [22:49<15:18,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1138/1900 [22:50<15:32,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1139/1900 [22:51<15:32,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1140/1900 [22:53<15:36,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1141/1900 [22:54<15:46,  1.25s/it]
+
+
Evaluating eval...:  60%|██████    | 1142/1900 [22:55<15:25,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1143/1900 [22:56<15:18,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1144/1900 [22:58<15:19,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1145/1900 [22:59<15:25,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1146/1900 [23:00<15:40,  1.25s/it]
+
+
Evaluating eval...:  60%|██████    | 1147/1900 [23:01<15:56,  1.27s/it]
+
+
Evaluating eval...:  60%|██████    | 1148/1900 [23:03<15:48,  1.26s/it]
+
+
Evaluating eval...:  60%|██████    | 1149/1900 [23:04<15:24,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1150/1900 [23:05<15:32,  1.24s/it]
+
+
Evaluating eval...:  61%|██████    | 1151/1900 [23:06<15:17,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1152/1900 [23:07<15:05,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1153/1900 [23:09<15:20,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1154/1900 [23:10<15:10,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1155/1900 [23:11<15:05,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1156/1900 [23:12<14:49,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1157/1900 [23:13<14:53,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1158/1900 [23:15<15:02,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1159/1900 [23:16<14:50,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1160/1900 [23:17<14:57,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1161/1900 [23:18<14:59,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1162/1900 [23:20<14:46,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1163/1900 [23:21<14:49,  1.21s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1164/1900 [23:22<14:39,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1165/1900 [23:23<14:39,  1.20s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1166/1900 [23:24<14:52,  1.22s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1167/1900 [23:26<14:53,  1.22s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1168/1900 [23:27<14:47,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1169/1900 [23:28<14:44,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1170/1900 [23:29<14:47,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1171/1900 [23:30<14:51,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1172/1900 [23:32<14:55,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1173/1900 [23:33<14:45,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1174/1900 [23:34<14:34,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1175/1900 [23:35<14:57,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1176/1900 [23:37<15:03,  1.25s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1177/1900 [23:38<14:42,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1178/1900 [23:39<14:26,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1179/1900 [23:40<14:34,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1180/1900 [23:41<14:36,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1181/1900 [23:43<14:21,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1182/1900 [23:44<14:32,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1183/1900 [23:45<14:44,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1184/1900 [23:46<14:44,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1185/1900 [23:48<14:42,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1186/1900 [23:49<14:47,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1187/1900 [23:50<14:35,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1188/1900 [23:51<14:22,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1189/1900 [23:52<14:17,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1190/1900 [23:54<14:06,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1191/1900 [23:55<14:19,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1192/1900 [23:56<14:30,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1193/1900 [23:57<14:22,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1194/1900 [23:59<14:33,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1195/1900 [24:00<14:33,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1196/1900 [24:01<14:26,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1197/1900 [24:02<14:37,  1.25s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1198/1900 [24:04<14:28,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1199/1900 [24:05<14:37,  1.25s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1200/1900 [24:06<14:24,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1201/1900 [24:07<14:11,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1202/1900 [24:08<13:59,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1203/1900 [24:10<14:16,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1204/1900 [24:11<14:24,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1205/1900 [24:12<14:19,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1206/1900 [24:13<14:25,  1.25s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1207/1900 [24:15<14:11,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1208/1900 [24:16<14:10,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1209/1900 [24:17<13:56,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1210/1900 [24:18<14:07,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1211/1900 [24:20<14:11,  1.24s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1212/1900 [24:21<14:05,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1213/1900 [24:22<13:58,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1214/1900 [24:23<13:54,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1215/1900 [24:24<13:42,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1216/1900 [24:26<13:47,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1217/1900 [24:27<13:55,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1218/1900 [24:28<14:03,  1.24s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1219/1900 [24:29<13:51,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1220/1900 [24:30<13:48,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1221/1900 [24:32<13:39,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1222/1900 [24:33<13:32,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1223/1900 [24:34<13:31,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1224/1900 [24:35<13:27,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1225/1900 [24:36<13:37,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1226/1900 [24:38<13:33,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1227/1900 [24:39<13:28,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1228/1900 [24:40<13:24,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1229/1900 [24:41<13:17,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1230/1900 [24:42<13:23,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1231/1900 [24:44<13:25,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1232/1900 [24:45<13:22,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1233/1900 [24:46<13:18,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1234/1900 [24:47<13:19,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1235/1900 [24:49<13:35,  1.23s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1236/1900 [24:50<13:21,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1237/1900 [24:51<13:19,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1238/1900 [24:52<13:13,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1239/1900 [24:53<13:17,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1240/1900 [24:55<13:46,  1.25s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1241/1900 [24:56<13:30,  1.23s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1242/1900 [24:57<13:21,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1243/1900 [24:58<13:43,  1.25s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1244/1900 [25:00<13:24,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1245/1900 [25:01<13:11,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1246/1900 [25:02<13:21,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1247/1900 [25:03<13:13,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1248/1900 [25:04<13:02,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1249/1900 [25:06<13:08,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1250/1900 [25:07<13:02,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1251/1900 [25:08<12:52,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1252/1900 [25:09<12:49,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1253/1900 [25:10<12:59,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1254/1900 [25:12<13:03,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1255/1900 [25:13<13:17,  1.24s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1256/1900 [25:14<13:14,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1257/1900 [25:15<12:59,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1258/1900 [25:16<13:00,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1259/1900 [25:18<12:49,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1260/1900 [25:19<12:48,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1261/1900 [25:20<12:48,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1262/1900 [25:21<12:41,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1263/1900 [25:22<12:43,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1264/1900 [25:24<12:45,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1265/1900 [25:25<12:45,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1266/1900 [25:26<13:00,  1.23s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1267/1900 [25:27<12:50,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1268/1900 [25:29<12:52,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1269/1900 [25:30<12:57,  1.23s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1270/1900 [25:31<12:42,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1271/1900 [25:32<12:42,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1272/1900 [25:33<12:35,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1273/1900 [25:35<12:29,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1274/1900 [25:36<12:29,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1275/1900 [25:37<12:28,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1276/1900 [25:38<12:25,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1277/1900 [25:39<12:22,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1278/1900 [25:40<12:13,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1279/1900 [25:42<12:15,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1280/1900 [25:43<12:13,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1281/1900 [25:44<12:06,  1.17s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1282/1900 [25:45<12:04,  1.17s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1283/1900 [25:46<12:04,  1.17s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1284/1900 [25:48<12:10,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1285/1900 [25:49<12:14,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1286/1900 [25:50<12:15,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1287/1900 [25:51<12:34,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1288/1900 [25:53<12:33,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1289/1900 [25:54<12:22,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1290/1900 [25:55<12:14,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1291/1900 [25:56<12:05,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1292/1900 [25:57<12:09,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1293/1900 [25:58<12:15,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1294/1900 [26:00<12:15,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1295/1900 [26:01<12:09,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1296/1900 [26:02<12:15,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1297/1900 [26:03<12:00,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1298/1900 [26:05<12:05,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1299/1900 [26:06<12:12,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1300/1900 [26:07<12:21,  1.24s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1301/1900 [26:08<12:22,  1.24s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1302/1900 [26:09<12:12,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1303/1900 [26:11<12:07,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1304/1900 [26:12<12:01,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1305/1900 [26:13<11:50,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1306/1900 [26:14<11:51,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1307/1900 [26:15<11:45,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1308/1900 [26:17<11:42,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1309/1900 [26:18<11:41,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1310/1900 [26:19<11:41,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1311/1900 [26:20<11:53,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1312/1900 [26:21<11:48,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1313/1900 [26:23<11:45,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1314/1900 [26:24<11:34,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1315/1900 [26:25<11:32,  1.18s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1316/1900 [26:26<11:42,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1317/1900 [26:27<11:39,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1318/1900 [26:29<11:52,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1319/1900 [26:30<11:45,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1320/1900 [26:31<11:33,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1321/1900 [26:32<11:46,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1322/1900 [26:33<11:38,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1323/1900 [26:35<11:33,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1324/1900 [26:36<11:27,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1325/1900 [26:37<11:20,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1326/1900 [26:38<11:26,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1327/1900 [26:39<11:23,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1328/1900 [26:41<11:30,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1329/1900 [26:42<11:20,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1330/1900 [26:43<11:23,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1331/1900 [26:44<11:19,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1332/1900 [26:45<11:19,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1333/1900 [26:47<11:19,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1334/1900 [26:48<11:25,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1335/1900 [26:49<11:23,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1336/1900 [26:50<11:19,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1337/1900 [26:52<11:35,  1.24s/it]
+
+
Evaluating eval...:  70%|███████   | 1338/1900 [26:53<11:22,  1.22s/it]
+
+
Evaluating eval...:  70%|███████   | 1339/1900 [26:54<11:16,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1340/1900 [26:55<11:17,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1341/1900 [26:56<11:05,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1342/1900 [26:58<11:12,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1343/1900 [26:59<11:02,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1344/1900 [27:00<11:04,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1345/1900 [27:01<11:11,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1346/1900 [27:02<11:34,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1347/1900 [27:04<11:20,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1348/1900 [27:05<11:05,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1349/1900 [27:06<11:29,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1350/1900 [27:07<11:19,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1351/1900 [27:09<11:28,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1352/1900 [27:10<11:24,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1353/1900 [27:11<11:28,  1.26s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1354/1900 [27:12<11:22,  1.25s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1355/1900 [27:14<11:11,  1.23s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1356/1900 [27:15<11:15,  1.24s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1357/1900 [27:16<11:06,  1.23s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1358/1900 [27:17<10:56,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1359/1900 [27:18<10:58,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1360/1900 [27:20<10:51,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1361/1900 [27:21<10:53,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1362/1900 [27:22<10:42,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1363/1900 [27:23<10:53,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1364/1900 [27:24<10:45,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1365/1900 [27:26<10:38,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1366/1900 [27:27<10:34,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1367/1900 [27:28<10:34,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1368/1900 [27:29<10:38,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1369/1900 [27:30<10:39,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1370/1900 [27:32<10:38,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1371/1900 [27:33<10:41,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1372/1900 [27:34<10:31,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1373/1900 [27:35<10:26,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1374/1900 [27:36<10:23,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1375/1900 [27:38<10:29,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1376/1900 [27:39<10:26,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1377/1900 [27:40<10:28,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1378/1900 [27:41<10:18,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1379/1900 [27:42<10:17,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1380/1900 [27:44<10:21,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1381/1900 [27:45<10:22,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1382/1900 [27:46<10:24,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1383/1900 [27:47<10:24,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1384/1900 [27:48<10:18,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1385/1900 [27:50<10:15,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1386/1900 [27:51<10:17,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1387/1900 [27:52<10:08,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1388/1900 [27:53<10:05,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1389/1900 [27:54<10:04,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1390/1900 [27:56<10:25,  1.23s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1391/1900 [27:57<10:24,  1.23s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1392/1900 [27:58<10:18,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1393/1900 [27:59<10:13,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1394/1900 [28:01<10:22,  1.23s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1395/1900 [28:02<10:13,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1396/1900 [28:03<10:05,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1397/1900 [28:04<09:58,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1398/1900 [28:05<10:05,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1399/1900 [28:06<10:02,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1400/1900 [28:08<09:53,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1401/1900 [28:09<10:06,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1402/1900 [28:10<09:56,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1403/1900 [28:11<09:53,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1404/1900 [28:12<09:47,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1405/1900 [28:14<09:40,  1.17s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1406/1900 [28:15<09:43,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1407/1900 [28:16<09:47,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1408/1900 [28:17<09:57,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1409/1900 [28:18<09:50,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1410/1900 [28:20<09:47,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1411/1900 [28:21<09:45,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1412/1900 [28:22<09:46,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1413/1900 [28:23<09:45,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1414/1900 [28:24<09:42,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1415/1900 [28:26<09:42,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1416/1900 [28:27<09:36,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1417/1900 [28:28<09:39,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1418/1900 [28:29<09:31,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1419/1900 [28:30<09:46,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1420/1900 [28:32<09:41,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1421/1900 [28:33<09:35,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1422/1900 [28:34<09:45,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1423/1900 [28:35<09:39,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1424/1900 [28:36<09:37,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1425/1900 [28:38<09:34,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1426/1900 [28:39<09:32,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1427/1900 [28:40<09:31,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1428/1900 [28:41<09:40,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1429/1900 [28:43<09:35,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1430/1900 [28:44<09:28,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1431/1900 [28:45<09:33,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1432/1900 [28:46<09:58,  1.28s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1433/1900 [28:48<09:43,  1.25s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1434/1900 [28:49<09:36,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1435/1900 [28:50<09:28,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1436/1900 [28:51<09:25,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1437/1900 [28:52<09:19,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1438/1900 [28:54<09:11,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1439/1900 [28:55<09:08,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1440/1900 [28:56<09:12,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1441/1900 [28:57<09:09,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1442/1900 [28:58<09:14,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1443/1900 [29:00<09:20,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1444/1900 [29:01<09:13,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1445/1900 [29:02<09:06,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1446/1900 [29:03<09:04,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1447/1900 [29:04<08:58,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1448/1900 [29:06<08:58,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1449/1900 [29:07<08:57,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1450/1900 [29:08<09:08,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1451/1900 [29:09<09:07,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1452/1900 [29:10<08:57,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1453/1900 [29:12<08:57,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1454/1900 [29:13<09:09,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1455/1900 [29:14<09:02,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1456/1900 [29:15<09:07,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1457/1900 [29:17<09:00,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1458/1900 [29:18<08:58,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1459/1900 [29:19<08:50,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1460/1900 [29:20<08:43,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1461/1900 [29:21<08:42,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1462/1900 [29:22<08:41,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1463/1900 [29:24<08:38,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1464/1900 [29:25<08:43,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1465/1900 [29:26<08:39,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1466/1900 [29:27<08:45,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1467/1900 [29:28<08:38,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1468/1900 [29:30<08:49,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1469/1900 [29:31<08:46,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1470/1900 [29:32<08:37,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1471/1900 [29:33<08:38,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1472/1900 [29:35<08:31,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1473/1900 [29:36<08:30,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1474/1900 [29:37<08:29,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1475/1900 [29:38<08:31,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1476/1900 [29:39<08:30,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1477/1900 [29:41<08:28,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1478/1900 [29:42<08:28,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1479/1900 [29:43<08:39,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1480/1900 [29:44<08:30,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1481/1900 [29:45<08:28,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1482/1900 [29:47<08:23,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1483/1900 [29:48<08:17,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1484/1900 [29:49<08:17,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1485/1900 [29:50<08:25,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1486/1900 [29:51<08:19,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1487/1900 [29:53<08:23,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1488/1900 [29:54<08:12,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1489/1900 [29:55<08:07,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1490/1900 [29:56<08:08,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1491/1900 [29:57<08:01,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1492/1900 [29:59<08:04,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1493/1900 [30:00<08:10,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1494/1900 [30:01<08:03,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1495/1900 [30:02<08:00,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1496/1900 [30:03<07:54,  1.17s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1497/1900 [30:04<07:52,  1.17s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1498/1900 [30:06<07:59,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1499/1900 [30:07<07:58,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1500/1900 [30:08<07:58,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1501/1900 [30:09<07:54,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1502/1900 [30:10<07:52,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1503/1900 [30:12<07:50,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1504/1900 [30:13<07:45,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1505/1900 [30:14<07:45,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1506/1900 [30:15<07:51,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1507/1900 [30:16<07:46,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1508/1900 [30:18<07:50,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1509/1900 [30:19<07:52,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1510/1900 [30:20<07:49,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1511/1900 [30:21<07:48,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1512/1900 [30:23<07:55,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1513/1900 [30:24<07:53,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1514/1900 [30:25<07:48,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1515/1900 [30:26<07:52,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1516/1900 [30:27<07:53,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1517/1900 [30:29<07:44,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1518/1900 [30:30<07:36,  1.19s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1519/1900 [30:31<07:28,  1.18s/it]
+
+
Evaluating eval...:  80%|████████  | 1520/1900 [30:32<07:30,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1521/1900 [30:33<07:31,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1522/1900 [30:34<07:25,  1.18s/it]
+
+
Evaluating eval...:  80%|████████  | 1523/1900 [30:36<07:32,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1524/1900 [30:37<07:32,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1525/1900 [30:38<07:35,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1526/1900 [30:39<07:28,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1527/1900 [30:40<07:25,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1528/1900 [30:42<07:24,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1529/1900 [30:43<07:19,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1530/1900 [30:44<07:21,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1531/1900 [30:45<07:24,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1532/1900 [30:47<07:28,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1533/1900 [30:48<07:21,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1534/1900 [30:49<07:17,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1535/1900 [30:50<07:10,  1.18s/it]
+
+
Evaluating eval...:  81%|████████  | 1536/1900 [30:51<07:07,  1.17s/it]
+
+
Evaluating eval...:  81%|████████  | 1537/1900 [30:52<07:09,  1.18s/it]
+
+
Evaluating eval...:  81%|████████  | 1538/1900 [30:54<07:07,  1.18s/it]
+
+
Evaluating eval...:  81%|████████  | 1539/1900 [30:55<07:13,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1540/1900 [30:56<07:08,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1541/1900 [30:57<07:26,  1.24s/it]
+
+
Evaluating eval...:  81%|████████  | 1542/1900 [30:59<07:21,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1543/1900 [31:00<07:20,  1.23s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1544/1900 [31:01<07:14,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1545/1900 [31:02<07:08,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1546/1900 [31:03<07:07,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1547/1900 [31:05<07:10,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1548/1900 [31:06<07:07,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1549/1900 [31:07<06:58,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1550/1900 [31:08<07:03,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1551/1900 [31:09<07:04,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1552/1900 [31:11<06:56,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1553/1900 [31:12<06:54,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1554/1900 [31:13<06:52,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1555/1900 [31:14<06:51,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1556/1900 [31:15<07:02,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1557/1900 [31:17<06:59,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1558/1900 [31:18<07:03,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1559/1900 [31:19<07:02,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1560/1900 [31:20<06:52,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1561/1900 [31:22<06:54,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1562/1900 [31:23<06:59,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1563/1900 [31:24<06:55,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1564/1900 [31:25<06:47,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1565/1900 [31:26<06:43,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1566/1900 [31:28<06:44,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1567/1900 [31:29<06:41,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1568/1900 [31:30<07:07,  1.29s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1569/1900 [31:32<07:00,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1570/1900 [31:33<06:55,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1571/1900 [31:34<06:49,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1572/1900 [31:35<06:49,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1573/1900 [31:36<06:40,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1574/1900 [31:38<06:34,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1575/1900 [31:39<06:34,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1576/1900 [31:40<06:28,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1577/1900 [31:41<06:31,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1578/1900 [31:42<06:31,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1579/1900 [31:44<06:27,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1580/1900 [31:45<06:33,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1581/1900 [31:46<06:49,  1.28s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1582/1900 [31:48<06:46,  1.28s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1583/1900 [31:49<06:43,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1584/1900 [31:50<06:46,  1.29s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1585/1900 [31:51<06:41,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1586/1900 [31:53<06:34,  1.26s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1587/1900 [31:54<06:22,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1588/1900 [31:55<06:13,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1589/1900 [31:56<06:15,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1590/1900 [31:57<06:14,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1591/1900 [31:59<06:17,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1592/1900 [32:00<06:09,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1593/1900 [32:01<06:07,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1594/1900 [32:02<06:11,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1595/1900 [32:03<06:12,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1596/1900 [32:05<06:11,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1597/1900 [32:06<06:08,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1598/1900 [32:07<06:00,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1599/1900 [32:08<05:55,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1600/1900 [32:09<05:53,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1601/1900 [32:11<05:50,  1.17s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1602/1900 [32:12<05:50,  1.17s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1603/1900 [32:13<05:49,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1604/1900 [32:14<05:55,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1605/1900 [32:15<05:50,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1606/1900 [32:17<05:51,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1607/1900 [32:18<05:48,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1608/1900 [32:19<05:49,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1609/1900 [32:20<05:59,  1.24s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1610/1900 [32:21<05:55,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1611/1900 [32:23<05:48,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1612/1900 [32:24<05:44,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1613/1900 [32:25<05:38,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1614/1900 [32:26<05:40,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1615/1900 [32:27<05:40,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1616/1900 [32:28<05:36,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1617/1900 [32:30<05:40,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1618/1900 [32:31<05:42,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1619/1900 [32:32<05:41,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1620/1900 [32:33<05:40,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1621/1900 [32:35<05:36,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1622/1900 [32:36<05:29,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1623/1900 [32:37<05:29,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1624/1900 [32:38<05:24,  1.18s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1625/1900 [32:39<05:27,  1.19s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1626/1900 [32:41<05:32,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1627/1900 [32:42<05:32,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1628/1900 [32:43<05:31,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1629/1900 [32:44<05:26,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1630/1900 [32:45<05:25,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1631/1900 [32:47<05:33,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1632/1900 [32:48<05:28,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1633/1900 [32:49<05:26,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1634/1900 [32:50<05:22,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1635/1900 [32:51<05:17,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1636/1900 [32:53<05:19,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1637/1900 [32:54<05:20,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1638/1900 [32:55<05:13,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1639/1900 [32:56<05:15,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1640/1900 [32:58<05:16,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1641/1900 [32:59<05:13,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1642/1900 [33:00<05:11,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1643/1900 [33:01<05:10,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1644/1900 [33:02<05:04,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1645/1900 [33:03<04:59,  1.17s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1646/1900 [33:05<05:01,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1647/1900 [33:06<05:00,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1648/1900 [33:07<05:00,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1649/1900 [33:08<04:59,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1650/1900 [33:09<05:01,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1651/1900 [33:11<04:55,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1652/1900 [33:12<04:54,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1653/1900 [33:13<04:51,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1654/1900 [33:14<04:51,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1655/1900 [33:15<04:55,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1656/1900 [33:17<04:54,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1657/1900 [33:18<04:55,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1658/1900 [33:19<04:52,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1659/1900 [33:20<04:59,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1660/1900 [33:22<04:56,  1.23s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1661/1900 [33:23<04:53,  1.23s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1662/1900 [33:24<04:49,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1663/1900 [33:25<04:43,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1664/1900 [33:26<04:45,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1665/1900 [33:28<04:45,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1666/1900 [33:29<05:15,  1.35s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1667/1900 [33:31<05:08,  1.32s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1668/1900 [33:32<04:56,  1.28s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1669/1900 [33:33<04:52,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1670/1900 [33:34<04:52,  1.27s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1671/1900 [33:35<04:48,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1672/1900 [33:37<04:44,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1673/1900 [33:38<04:47,  1.27s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1674/1900 [33:39<04:42,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1675/1900 [33:40<04:38,  1.24s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1676/1900 [33:42<04:35,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1677/1900 [33:43<04:29,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1678/1900 [33:44<04:24,  1.19s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1679/1900 [33:45<04:24,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1680/1900 [33:46<04:25,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1681/1900 [33:48<04:24,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1682/1900 [33:49<04:22,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1683/1900 [33:50<04:24,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1684/1900 [33:51<04:20,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1685/1900 [33:52<04:15,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1686/1900 [33:54<04:14,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1687/1900 [33:55<04:16,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1688/1900 [33:56<04:15,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1689/1900 [33:57<04:12,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1690/1900 [33:58<04:09,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1691/1900 [34:00<04:13,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1692/1900 [34:01<04:10,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1693/1900 [34:02<04:10,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1694/1900 [34:03<04:11,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1695/1900 [34:04<04:09,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1696/1900 [34:06<04:05,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1697/1900 [34:07<04:07,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1698/1900 [34:08<04:07,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1699/1900 [34:09<04:01,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1700/1900 [34:11<04:01,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1701/1900 [34:12<04:05,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1702/1900 [34:13<04:05,  1.24s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1703/1900 [34:14<04:01,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1704/1900 [34:15<03:55,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1705/1900 [34:17<03:52,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1706/1900 [34:18<03:52,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1707/1900 [34:19<03:50,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1708/1900 [34:20<03:53,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1709/1900 [34:21<03:52,  1.22s/it]
+
+
Evaluating eval...:  90%|█████████ | 1710/1900 [34:23<03:50,  1.21s/it]
+
+
Evaluating eval...:  90%|█████████ | 1711/1900 [34:24<03:45,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1712/1900 [34:25<03:43,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1713/1900 [34:26<03:38,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1714/1900 [34:27<03:36,  1.16s/it]
+
+
Evaluating eval...:  90%|█████████ | 1715/1900 [34:29<03:38,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1716/1900 [34:30<03:36,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1717/1900 [34:31<03:51,  1.27s/it]
+
+
Evaluating eval...:  90%|█████████ | 1718/1900 [34:32<03:51,  1.27s/it]
+
+
Evaluating eval...:  90%|█████████ | 1719/1900 [34:34<03:45,  1.25s/it]
+
+
Evaluating eval...:  91%|█████████ | 1720/1900 [34:35<03:44,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1721/1900 [34:36<03:38,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1722/1900 [34:37<03:37,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1723/1900 [34:38<03:32,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1724/1900 [34:40<03:34,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1725/1900 [34:41<03:34,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1726/1900 [34:42<03:34,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1727/1900 [34:43<03:36,  1.25s/it]
+
+
Evaluating eval...:  91%|█████████ | 1728/1900 [34:45<03:30,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1729/1900 [34:46<03:26,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1730/1900 [34:47<03:29,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1731/1900 [34:48<03:25,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1732/1900 [34:49<03:23,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1733/1900 [34:51<03:23,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1734/1900 [34:52<03:21,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1735/1900 [34:53<03:19,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1736/1900 [34:54<03:20,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1737/1900 [34:56<03:18,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1738/1900 [34:57<03:15,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1739/1900 [34:58<03:16,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1740/1900 [34:59<03:13,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1741/1900 [35:00<03:14,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1742/1900 [35:02<03:10,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1743/1900 [35:03<03:08,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1744/1900 [35:04<03:06,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1745/1900 [35:05<03:03,  1.18s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1746/1900 [35:06<03:09,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1747/1900 [35:08<03:06,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1748/1900 [35:09<03:05,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1749/1900 [35:10<03:05,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1750/1900 [35:11<03:05,  1.24s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1751/1900 [35:13<03:03,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1752/1900 [35:14<03:01,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1753/1900 [35:15<02:57,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1754/1900 [35:16<02:56,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1755/1900 [35:17<02:58,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1756/1900 [35:19<02:56,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1757/1900 [35:20<02:59,  1.26s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1758/1900 [35:21<02:55,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1759/1900 [35:22<02:50,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1760/1900 [35:24<02:47,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1761/1900 [35:25<02:48,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1762/1900 [35:26<02:47,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1763/1900 [35:27<02:44,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1764/1900 [35:28<02:49,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1765/1900 [35:30<02:47,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1766/1900 [35:31<02:44,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1767/1900 [35:32<02:42,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1768/1900 [35:33<02:43,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1769/1900 [35:35<02:42,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1770/1900 [35:36<02:44,  1.26s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1771/1900 [35:37<02:40,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1772/1900 [35:38<02:36,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1773/1900 [35:40<02:36,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1774/1900 [35:41<02:33,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1775/1900 [35:42<02:32,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1776/1900 [35:43<02:31,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1777/1900 [35:44<02:28,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1778/1900 [35:46<02:26,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1779/1900 [35:47<02:23,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1780/1900 [35:48<02:21,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1781/1900 [35:49<02:19,  1.17s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1782/1900 [35:50<02:21,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1783/1900 [35:52<02:22,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1784/1900 [35:53<02:19,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1785/1900 [35:54<02:16,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1786/1900 [35:55<02:15,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1787/1900 [35:56<02:14,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1788/1900 [35:57<02:12,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1789/1900 [35:59<02:10,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1790/1900 [36:00<02:10,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1791/1900 [36:01<02:09,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1792/1900 [36:02<02:08,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1793/1900 [36:03<02:10,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1794/1900 [36:05<02:07,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1795/1900 [36:06<02:05,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1796/1900 [36:07<02:02,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1797/1900 [36:08<02:02,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1798/1900 [36:09<02:03,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1799/1900 [36:11<02:03,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1800/1900 [36:12<02:01,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1801/1900 [36:13<01:58,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1802/1900 [36:14<01:58,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1803/1900 [36:16<01:57,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1804/1900 [36:17<01:54,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1805/1900 [36:18<01:52,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1806/1900 [36:19<01:51,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1807/1900 [36:20<01:49,  1.17s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1808/1900 [36:21<01:47,  1.17s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1809/1900 [36:22<01:45,  1.16s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1810/1900 [36:24<01:46,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1811/1900 [36:25<01:46,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1812/1900 [36:26<01:44,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1813/1900 [36:27<01:43,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1814/1900 [36:28<01:42,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1815/1900 [36:30<01:40,  1.18s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1816/1900 [36:31<01:39,  1.18s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1817/1900 [36:32<01:41,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1818/1900 [36:33<01:39,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1819/1900 [36:35<01:37,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1820/1900 [36:36<01:36,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1821/1900 [36:37<01:35,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1822/1900 [36:38<01:34,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1823/1900 [36:39<01:32,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1824/1900 [36:40<01:30,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1825/1900 [36:42<01:30,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1826/1900 [36:43<01:29,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1827/1900 [36:44<01:29,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1828/1900 [36:45<01:28,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1829/1900 [36:47<01:30,  1.28s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1830/1900 [36:48<01:27,  1.25s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1831/1900 [36:49<01:24,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1832/1900 [36:50<01:21,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1833/1900 [36:52<01:19,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1834/1900 [36:53<01:19,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1835/1900 [36:54<01:18,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1836/1900 [36:55<01:17,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1837/1900 [36:56<01:18,  1.25s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1838/1900 [36:58<01:16,  1.24s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1839/1900 [36:59<01:14,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1840/1900 [37:00<01:14,  1.24s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1841/1900 [37:01<01:12,  1.23s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1842/1900 [37:03<01:09,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1843/1900 [37:04<01:07,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1844/1900 [37:05<01:06,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1845/1900 [37:06<01:05,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1846/1900 [37:07<01:04,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1847/1900 [37:09<01:03,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1848/1900 [37:10<01:03,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1849/1900 [37:11<01:02,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1850/1900 [37:12<01:00,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1851/1900 [37:13<00:59,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1852/1900 [37:15<00:57,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1853/1900 [37:16<00:56,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1854/1900 [37:17<00:54,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1855/1900 [37:18<00:55,  1.23s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1856/1900 [37:19<00:53,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1857/1900 [37:21<00:51,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1858/1900 [37:22<00:51,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1859/1900 [37:23<00:49,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1860/1900 [37:24<00:48,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1861/1900 [37:25<00:46,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1862/1900 [37:27<00:45,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1863/1900 [37:28<00:43,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1864/1900 [37:29<00:42,  1.18s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1865/1900 [37:30<00:41,  1.18s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1866/1900 [37:31<00:41,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1867/1900 [37:33<00:40,  1.23s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1868/1900 [37:34<00:38,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1869/1900 [37:35<00:38,  1.25s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1870/1900 [37:36<00:36,  1.23s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1871/1900 [37:38<00:36,  1.26s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1872/1900 [37:39<00:34,  1.25s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1873/1900 [37:40<00:33,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1874/1900 [37:41<00:31,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1875/1900 [37:43<00:30,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1876/1900 [37:44<00:29,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1877/1900 [37:45<00:28,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1878/1900 [37:46<00:26,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1879/1900 [37:47<00:25,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1880/1900 [37:49<00:23,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1881/1900 [37:50<00:22,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1882/1900 [37:51<00:21,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1883/1900 [37:52<00:21,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1884/1900 [37:54<00:19,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1885/1900 [37:55<00:18,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1886/1900 [37:56<00:17,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1887/1900 [37:57<00:15,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1888/1900 [37:58<00:14,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1889/1900 [37:59<00:13,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1890/1900 [38:01<00:11,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1891/1900 [38:02<00:10,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1892/1900 [38:03<00:09,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1893/1900 [38:04<00:08,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1894/1900 [38:05<00:07,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1895/1900 [38:07<00:05,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1896/1900 [38:08<00:04,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1897/1900 [38:09<00:03,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1898/1900 [38:10<00:02,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1899/1900 [38:11<00:01,  1.19s/it]
+
+
Evaluating eval...: 100%|██████████| 1900/1900 [38:13<00:00,  1.32s/it]
Evaluating eval...: 100%|██████████| 1900/1900 [38:13<00:00,  1.21s/it]
+Eval results for step (25000 / 100000 | Eval Loss: 1.1451153755187988 | Eval wer: 28.292255737160517 | Eval wer_ortho: 31.66972408170271 |)
+
                                                                             
Eval results for step (25000 / 100000 | Eval Loss: 1.1451153755187988 | Eval wer: 28.292255737160517 | Eval wer_ortho: 31.66972408170271 |)
+
Train steps ... :  25%|██▌       | 25000/100000 [7:41:22<12:14:29,  1.70it/s]
Train steps ... :  25%|██▌       | 25001/100000 [7:41:22<15837:55:24, 760.23s/it]
Train steps ... :  25%|██▌       | 25002/100000 [7:41:23<11090:03:02, 532.34s/it]
Train steps ... :  25%|██▌       | 25003/100000 [7:41:23<7766:34:20, 372.81s/it] 
Train steps ... :  25%|██▌       | 25004/100000 [7:41:24<5440:10:28, 261.14s/it]
Train steps ... :  25%|██▌       | 25005/100000 [7:41:25<3811:43:00, 182.97s/it]
Train steps ... :  25%|██▌       | 25006/100000 [7:41:25<2671:48:52, 128.26s/it]
Train steps ... :  25%|██▌       | 25007/100000 [7:41:26<1873:53:29, 89.96s/it] 
Train steps ... :  25%|██▌       | 25008/100000 [7:41:26<1315:22:17, 63.14s/it]
Train steps ... :  25%|██▌       | 25009/100000 [7:41:27<924:23:24, 44.38s/it] 
Train steps ... :  25%|██▌       | 25010/100000 [7:41:28<650:43:06, 31.24s/it]
Train steps ... :  25%|██▌       | 25011/100000 [7:41:28<459:08:19, 22.04s/it]
Train steps ... :  25%|██▌       | 25012/100000 [7:41:29<325:02:14, 15.60s/it]
Train steps ... :  25%|██▌       | 25013/100000 [7:41:29<231:10:43, 11.10s/it]
Train steps ... :  25%|██▌       | 25014/100000 [7:41:30<165:29:18,  7.94s/it]
Train steps ... :  25%|██▌       | 25015/100000 [7:41:30<119:28:54,  5.74s/it]
Train steps ... :  25%|██▌       | 25016/100000 [7:41:31<87:16:23,  4.19s/it] 
Train steps ... :  25%|██▌       | 25017/100000 [7:41:32<64:44:16,  3.11s/it]
Train steps ... :  25%|██▌       | 25018/100000 [7:41:32<48:57:51,  2.35s/it]
Train steps ... :  25%|██▌       | 25019/100000 [7:41:33<37:55:31,  1.82s/it]
Train steps ... :  25%|██▌       | 25020/100000 [7:41:33<30:12:21,  1.45s/it]
Train steps ... :  25%|██▌       | 25021/100000 [7:41:34<24:47:04,  1.19s/it]
Train steps ... :  25%|██▌       | 25022/100000 [7:41:35<20:59:50,  1.01s/it]
Train steps ... :  25%|██▌       | 25023/100000 [7:41:35<18:20:18,  1.14it/s]
Train steps ... :  25%|██▌       | 25024/100000 [7:41:36<16:29:54,  1.26it/s]
Train steps ... :  25%|██▌       | 25025/100000 [7:41:36<15:12:01,  1.37it/s]Step... (25025 / 100000 | Loss: 0.8828349113464355, Learning Rate: 7.535175879396985e-05)
+
                                                                             
Step... (25025 / 100000 | Loss: 0.883556604385376, Learning Rate: 7.535175879396985e-05)
+
Train steps ... :  25%|██▌       | 25025/100000 [7:41:37<15:12:01,  1.37it/s]
Train steps ... :  25%|██▌       | 25026/100000 [7:41:37<14:17:28,  1.46it/s]
Train steps ... :  25%|██▌       | 25027/100000 [7:41:37<13:39:07,  1.53it/s]
Train steps ... :  25%|██▌       | 25028/100000 [7:41:38<13:12:06,  1.58it/s]
Train steps ... :  25%|██▌       | 25029/100000 [7:41:39<12:52:47,  1.62it/s]
Train steps ... :  25%|██▌       | 25030/100000 [7:41:39<12:39:38,  1.64it/s]
Train steps ... :  25%|██▌       | 25031/100000 [7:41:40<12:31:41,  1.66it/s]
Train steps ... :  25%|██▌       | 25032/100000 [7:41:40<12:25:52,  1.68it/s]
Train steps ... :  25%|██▌       | 25033/100000 [7:41:41<12:20:15,  1.69it/s]
Train steps ... :  25%|██▌       | 25034/100000 [7:41:42<12:17:28,  1.69it/s]
Train steps ... :  25%|██▌       | 25035/100000 [7:41:42<12:14:40,  1.70it/s]
Train steps ... :  25%|██▌       | 25036/100000 [7:41:43<12:13:05,  1.70it/s]
Train steps ... :  25%|██▌       | 25037/100000 [7:41:43<12:12:03,  1.71it/s]
Train steps ... :  25%|██▌       | 25038/100000 [7:41:44<12:14:44,  1.70it/s]
Train steps ... :  25%|██▌       | 25039/100000 [7:41:44<12:13:18,  1.70it/s]
Train steps ... :  25%|██▌       | 25040/100000 [7:41:45<12:16:14,  1.70it/s]
Train steps ... :  25%|██▌       | 25041/100000 [7:41:46<12:13:15,  1.70it/s]
Train steps ... :  25%|██▌       | 25042/100000 [7:41:46<12:11:52,  1.71it/s]
Train steps ... :  25%|██▌       | 25043/100000 [7:41:47<12:11:46,  1.71it/s]
Train steps ... :  25%|██▌       | 25044/100000 [7:41:47<12:12:12,  1.71it/s]
Train steps ... :  25%|██▌       | 25045/100000 [7:41:48<12:11:02,  1.71it/s]
Train steps ... :  25%|██▌       | 25046/100000 [7:41:49<12:10:37,  1.71it/s]
Train steps ... :  25%|██▌       | 25047/100000 [7:41:49<12:09:56,  1.71it/s]
Train steps ... :  25%|██▌       | 25048/100000 [7:41:50<12:10:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25049/100000 [7:41:50<12:09:12,  1.71it/s]
Train steps ... :  25%|██▌       | 25050/100000 [7:41:51<12:09:37,  1.71it/s]Step... (25050 / 100000 | Loss: 0.8402733206748962, Learning Rate: 7.532663316582915e-05)
+
                                                                             
Step... (25050 / 100000 | Loss: 1.0256481170654297, Learning Rate: 7.532663316582915e-05)
+
Train steps ... :  25%|██▌       | 25050/100000 [7:41:51<12:09:37,  1.71it/s]
Train steps ... :  25%|██▌       | 25051/100000 [7:41:52<12:09:37,  1.71it/s]
Train steps ... :  25%|██▌       | 25052/100000 [7:41:52<12:09:12,  1.71it/s]
Train steps ... :  25%|██▌       | 25053/100000 [7:41:53<12:09:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25054/100000 [7:41:53<12:09:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25055/100000 [7:41:54<12:09:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25056/100000 [7:41:54<12:09:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25057/100000 [7:41:55<12:09:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25058/100000 [7:41:56<12:09:31,  1.71it/s]
Train steps ... :  25%|██▌       | 25059/100000 [7:41:56<12:09:19,  1.71it/s]
Train steps ... :  25%|██▌       | 25060/100000 [7:41:57<12:09:08,  1.71it/s]
Train steps ... :  25%|██▌       | 25061/100000 [7:41:57<12:09:13,  1.71it/s]
Train steps ... :  25%|██▌       | 25062/100000 [7:41:58<12:09:12,  1.71it/s]
Train steps ... :  25%|██▌       | 25063/100000 [7:41:59<12:08:35,  1.71it/s]
Train steps ... :  25%|██▌       | 25064/100000 [7:41:59<12:09:47,  1.71it/s]
Train steps ... :  25%|██▌       | 25065/100000 [7:42:00<12:10:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25066/100000 [7:42:00<12:09:55,  1.71it/s]
Train steps ... :  25%|██▌       | 25067/100000 [7:42:01<12:09:29,  1.71it/s]
Train steps ... :  25%|██▌       | 25068/100000 [7:42:01<12:09:21,  1.71it/s]
Train steps ... :  25%|██▌       | 25069/100000 [7:42:02<12:09:06,  1.71it/s]
Train steps ... :  25%|██▌       | 25070/100000 [7:42:03<12:09:21,  1.71it/s]
Train steps ... :  25%|██▌       | 25071/100000 [7:42:03<12:08:48,  1.71it/s]
Train steps ... :  25%|██▌       | 25072/100000 [7:42:04<12:08:10,  1.71it/s]
Train steps ... :  25%|██▌       | 25073/100000 [7:42:04<12:08:08,  1.72it/s]
Train steps ... :  25%|██▌       | 25074/100000 [7:42:05<12:08:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25075/100000 [7:42:06<12:08:30,  1.71it/s]Step... (25075 / 100000 | Loss: 1.0278446674346924, Learning Rate: 7.530150753768845e-05)
+
                                                                             
Step... (25075 / 100000 | Loss: 1.0137739181518555, Learning Rate: 7.530150753768845e-05)
+
Train steps ... :  25%|██▌       | 25075/100000 [7:42:06<12:08:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25076/100000 [7:42:06<12:08:50,  1.71it/s]
Train steps ... :  25%|██▌       | 25077/100000 [7:42:07<12:08:26,  1.71it/s]
Train steps ... :  25%|██▌       | 25078/100000 [7:42:07<12:09:47,  1.71it/s]
Train steps ... :  25%|██▌       | 25079/100000 [7:42:08<12:09:49,  1.71it/s]
Train steps ... :  25%|██▌       | 25080/100000 [7:42:08<12:09:29,  1.71it/s]
Train steps ... :  25%|██▌       | 25081/100000 [7:42:09<12:09:25,  1.71it/s]
Train steps ... :  25%|██▌       | 25082/100000 [7:42:10<12:09:02,  1.71it/s]
Train steps ... :  25%|██▌       | 25083/100000 [7:42:10<12:09:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25084/100000 [7:42:11<12:09:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25085/100000 [7:42:11<12:08:58,  1.71it/s]
Train steps ... :  25%|██▌       | 25086/100000 [7:42:12<12:09:07,  1.71it/s]
Train steps ... :  25%|██▌       | 25087/100000 [7:42:13<12:09:52,  1.71it/s]
Train steps ... :  25%|██▌       | 25088/100000 [7:42:13<12:09:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25089/100000 [7:42:14<12:08:24,  1.71it/s]
Train steps ... :  25%|██▌       | 25090/100000 [7:42:14<12:09:21,  1.71it/s]
Train steps ... :  25%|██▌       | 25091/100000 [7:42:15<12:08:55,  1.71it/s]
Train steps ... :  25%|██▌       | 25092/100000 [7:42:15<12:08:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25093/100000 [7:42:16<12:08:51,  1.71it/s]
Train steps ... :  25%|██▌       | 25094/100000 [7:42:17<12:10:00,  1.71it/s]
Train steps ... :  25%|██▌       | 25095/100000 [7:42:17<12:09:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25096/100000 [7:42:18<12:09:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25097/100000 [7:42:18<12:09:00,  1.71it/s]
Train steps ... :  25%|██▌       | 25098/100000 [7:42:19<12:09:13,  1.71it/s]
Train steps ... :  25%|██▌       | 25099/100000 [7:42:20<12:09:05,  1.71it/s]
Train steps ... :  25%|██▌       | 25100/100000 [7:42:20<12:09:30,  1.71it/s]Step... (25100 / 100000 | Loss: 0.9165620803833008, Learning Rate: 7.527638190954774e-05)
+
                                                                             
Step... (25100 / 100000 | Loss: 1.066927433013916, Learning Rate: 7.527638190954774e-05)
+
Train steps ... :  25%|██▌       | 25100/100000 [7:42:20<12:09:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25101/100000 [7:42:21<12:10:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25102/100000 [7:42:21<12:09:02,  1.71it/s]
Train steps ... :  25%|██▌       | 25103/100000 [7:42:22<12:10:15,  1.71it/s]
Train steps ... :  25%|██▌       | 25104/100000 [7:42:22<12:10:44,  1.71it/s]
Train steps ... :  25%|██▌       | 25105/100000 [7:42:23<12:11:52,  1.71it/s]
Train steps ... :  25%|██▌       | 25106/100000 [7:42:24<12:10:24,  1.71it/s]
Train steps ... :  25%|██▌       | 25107/100000 [7:42:24<12:09:20,  1.71it/s]
Train steps ... :  25%|██▌       | 25108/100000 [7:42:25<12:10:06,  1.71it/s]
Train steps ... :  25%|██▌       | 25109/100000 [7:42:25<12:09:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25110/100000 [7:42:26<12:09:04,  1.71it/s]
Train steps ... :  25%|██▌       | 25111/100000 [7:42:27<12:08:35,  1.71it/s]
Train steps ... :  25%|██▌       | 25112/100000 [7:42:27<12:08:52,  1.71it/s]
Train steps ... :  25%|██▌       | 25113/100000 [7:42:28<12:08:55,  1.71it/s]
Train steps ... :  25%|██▌       | 25114/100000 [7:42:28<12:08:49,  1.71it/s]
Train steps ... :  25%|██▌       | 25115/100000 [7:42:29<12:09:17,  1.71it/s]
Train steps ... :  25%|██▌       | 25116/100000 [7:42:29<12:10:21,  1.71it/s]
Train steps ... :  25%|██▌       | 25117/100000 [7:42:30<12:09:50,  1.71it/s]
Train steps ... :  25%|██▌       | 25118/100000 [7:42:31<12:09:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25119/100000 [7:42:31<12:10:05,  1.71it/s]
Train steps ... :  25%|██▌       | 25120/100000 [7:42:32<12:09:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25121/100000 [7:42:32<12:09:59,  1.71it/s]
Train steps ... :  25%|██▌       | 25122/100000 [7:42:33<12:10:16,  1.71it/s]
Train steps ... :  25%|██▌       | 25123/100000 [7:42:34<12:09:26,  1.71it/s]
Train steps ... :  25%|██▌       | 25124/100000 [7:42:34<12:09:26,  1.71it/s]
Train steps ... :  25%|██▌       | 25125/100000 [7:42:35<12:08:45,  1.71it/s]Step... (25125 / 100000 | Loss: 0.8815597295761108, Learning Rate: 7.525125628140704e-05)
+
                                                                             
Step... (25125 / 100000 | Loss: 1.031261920928955, Learning Rate: 7.525125628140704e-05)
+
Train steps ... :  25%|██▌       | 25125/100000 [7:42:35<12:08:45,  1.71it/s]
Train steps ... :  25%|██▌       | 25126/100000 [7:42:35<12:08:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25127/100000 [7:42:36<12:09:05,  1.71it/s]
Train steps ... :  25%|██▌       | 25128/100000 [7:42:37<12:09:56,  1.71it/s]
Train steps ... :  25%|██▌       | 25129/100000 [7:42:37<12:10:18,  1.71it/s]
Train steps ... :  25%|██▌       | 25130/100000 [7:42:38<12:09:54,  1.71it/s]
Train steps ... :  25%|██▌       | 25131/100000 [7:42:38<12:09:25,  1.71it/s]
Train steps ... :  25%|██▌       | 25132/100000 [7:42:39<12:08:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25133/100000 [7:42:39<12:08:54,  1.71it/s]
Train steps ... :  25%|██▌       | 25134/100000 [7:42:40<12:08:59,  1.71it/s]
Train steps ... :  25%|██▌       | 25135/100000 [7:42:41<12:08:39,  1.71it/s]
Train steps ... :  25%|██▌       | 25136/100000 [7:42:41<12:09:20,  1.71it/s]
Train steps ... :  25%|██▌       | 25137/100000 [7:42:42<12:09:02,  1.71it/s]
Train steps ... :  25%|██▌       | 25138/100000 [7:42:42<12:10:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25139/100000 [7:42:43<12:09:21,  1.71it/s]
Train steps ... :  25%|██▌       | 25140/100000 [7:42:44<12:09:37,  1.71it/s]
Train steps ... :  25%|██▌       | 25141/100000 [7:42:44<12:08:57,  1.71it/s]
Train steps ... :  25%|██▌       | 25142/100000 [7:42:45<12:08:32,  1.71it/s]
Train steps ... :  25%|██▌       | 25143/100000 [7:42:45<12:08:15,  1.71it/s]
Train steps ... :  25%|██▌       | 25144/100000 [7:42:46<12:09:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25145/100000 [7:42:46<12:08:44,  1.71it/s]
Train steps ... :  25%|██▌       | 25146/100000 [7:42:47<12:09:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25147/100000 [7:42:48<12:09:02,  1.71it/s]
Train steps ... :  25%|██▌       | 25148/100000 [7:42:48<12:09:03,  1.71it/s]
Train steps ... :  25%|██▌       | 25149/100000 [7:42:49<12:08:47,  1.71it/s]
Train steps ... :  25%|██▌       | 25150/100000 [7:42:49<12:09:38,  1.71it/s]Step... (25150 / 100000 | Loss: 0.7716541290283203, Learning Rate: 7.522613065326634e-05)
+
                                                                             
Step... (25150 / 100000 | Loss: 0.6709781289100647, Learning Rate: 7.522613065326634e-05)
+
Train steps ... :  25%|██▌       | 25150/100000 [7:42:50<12:09:38,  1.71it/s]
Train steps ... :  25%|██▌       | 25151/100000 [7:42:50<12:09:50,  1.71it/s]
Train steps ... :  25%|██▌       | 25152/100000 [7:42:51<12:10:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25153/100000 [7:42:51<12:09:42,  1.71it/s]
Train steps ... :  25%|██▌       | 25154/100000 [7:42:52<12:09:34,  1.71it/s]
Train steps ... :  25%|██▌       | 25155/100000 [7:42:52<12:09:42,  1.71it/s]
Train steps ... :  25%|██▌       | 25156/100000 [7:42:53<12:09:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25157/100000 [7:42:53<12:09:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25158/100000 [7:42:54<12:09:00,  1.71it/s]
Train steps ... :  25%|██▌       | 25159/100000 [7:42:55<12:08:58,  1.71it/s]
Train steps ... :  25%|██▌       | 25160/100000 [7:42:55<12:08:33,  1.71it/s]
Train steps ... :  25%|██▌       | 25161/100000 [7:42:56<12:08:44,  1.71it/s]
Train steps ... :  25%|██▌       | 25162/100000 [7:42:56<12:08:28,  1.71it/s]
Train steps ... :  25%|██▌       | 25163/100000 [7:42:57<12:09:47,  1.71it/s]
Train steps ... :  25%|██▌       | 25164/100000 [7:42:58<12:09:10,  1.71it/s]
Train steps ... :  25%|██▌       | 25165/100000 [7:42:58<12:09:00,  1.71it/s]
Train steps ... :  25%|██▌       | 25166/100000 [7:42:59<12:08:41,  1.71it/s]
Train steps ... :  25%|██▌       | 25167/100000 [7:42:59<12:08:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25168/100000 [7:43:00<12:09:06,  1.71it/s]
Train steps ... :  25%|██▌       | 25169/100000 [7:43:00<12:08:55,  1.71it/s]
Train steps ... :  25%|██▌       | 25170/100000 [7:43:01<12:09:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25171/100000 [7:43:02<12:08:58,  1.71it/s]
Train steps ... :  25%|██▌       | 25172/100000 [7:43:02<12:08:51,  1.71it/s]
Train steps ... :  25%|██▌       | 25173/100000 [7:43:03<12:09:34,  1.71it/s]
Train steps ... :  25%|██▌       | 25174/100000 [7:43:03<12:09:56,  1.71it/s]
Train steps ... :  25%|██▌       | 25175/100000 [7:43:04<12:09:01,  1.71it/s]Step... (25175 / 100000 | Loss: 0.891107439994812, Learning Rate: 7.520100502512563e-05)
+
                                                                             
Step... (25175 / 100000 | Loss: 0.6979004144668579, Learning Rate: 7.520100502512563e-05)
+
Train steps ... :  25%|██▌       | 25175/100000 [7:43:04<12:09:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25176/100000 [7:43:05<12:08:42,  1.71it/s]
Train steps ... :  25%|██▌       | 25177/100000 [7:43:05<12:08:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25178/100000 [7:43:06<12:08:51,  1.71it/s]
Train steps ... :  25%|██▌       | 25179/100000 [7:43:06<12:08:33,  1.71it/s]
Train steps ... :  25%|██▌       | 25180/100000 [7:43:07<12:09:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25181/100000 [7:43:07<12:08:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25182/100000 [7:43:08<12:09:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25183/100000 [7:43:09<12:09:06,  1.71it/s]
Train steps ... :  25%|██▌       | 25184/100000 [7:43:09<12:09:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25185/100000 [7:43:10<12:08:41,  1.71it/s]
Train steps ... :  25%|██▌       | 25186/100000 [7:43:10<12:09:36,  1.71it/s]
Train steps ... :  25%|██▌       | 25187/100000 [7:43:11<12:08:41,  1.71it/s]
Train steps ... :  25%|██▌       | 25188/100000 [7:43:12<12:08:36,  1.71it/s]
Train steps ... :  25%|██▌       | 25189/100000 [7:43:12<12:07:56,  1.71it/s]
Train steps ... :  25%|██▌       | 25190/100000 [7:43:13<12:08:09,  1.71it/s]
Train steps ... :  25%|█��▌       | 25191/100000 [7:43:13<12:08:38,  1.71it/s]
Train steps ... :  25%|██▌       | 25192/100000 [7:43:14<12:09:38,  1.71it/s]
Train steps ... :  25%|██▌       | 25193/100000 [7:43:14<12:09:58,  1.71it/s]
Train steps ... :  25%|██▌       | 25194/100000 [7:43:15<12:10:38,  1.71it/s]
Train steps ... :  25%|██▌       | 25195/100000 [7:43:16<12:09:50,  1.71it/s]
Train steps ... :  25%|██▌       | 25196/100000 [7:43:16<12:10:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25197/100000 [7:43:17<12:09:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25198/100000 [7:43:17<12:09:03,  1.71it/s]
Train steps ... :  25%|██▌       | 25199/100000 [7:43:18<12:09:19,  1.71it/s]
Train steps ... :  25%|██▌       | 25200/100000 [7:43:19<12:08:45,  1.71it/s]Step... (25200 / 100000 | Loss: 0.9535942673683167, Learning Rate: 7.517587939698493e-05)
+
                                                                             
Step... (25200 / 100000 | Loss: 1.0605634450912476, Learning Rate: 7.517587939698493e-05)
+
Train steps ... :  25%|██▌       | 25200/100000 [7:43:19<12:08:45,  1.71it/s]
Train steps ... :  25%|██▌       | 25201/100000 [7:43:19<12:09:24,  1.71it/s]
Train steps ... :  25%|██▌       | 25202/100000 [7:43:20<12:08:47,  1.71it/s]
Train steps ... :  25%|██▌       | 25203/100000 [7:43:20<12:08:12,  1.71it/s]
Train steps ... :  25%|██▌       | 25204/100000 [7:43:21<12:08:03,  1.71it/s]
Train steps ... :  25%|██▌       | 25205/100000 [7:43:22<12:07:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25206/100000 [7:43:22<12:08:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25207/100000 [7:43:23<12:07:41,  1.71it/s]
Train steps ... :  25%|██▌       | 25208/100000 [7:43:23<12:07:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25209/100000 [7:43:24<12:07:32,  1.71it/s]
Train steps ... :  25%|██▌       | 25210/100000 [7:43:24<12:09:19,  1.71it/s]
Train steps ... :  25%|██▌       | 25211/100000 [7:43:25<12:08:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25212/100000 [7:43:26<12:08:46,  1.71it/s]
Train steps ... :  25%|██▌       | 25213/100000 [7:43:26<12:07:38,  1.71it/s]
Train steps ... :  25%|██▌       | 25214/100000 [7:43:27<12:08:45,  1.71it/s]
Train steps ... :  25%|██▌       | 25215/100000 [7:43:27<12:08:24,  1.71it/s]
Train steps ... :  25%|██▌       | 25216/100000 [7:43:28<12:08:31,  1.71it/s]
Train steps ... :  25%|██▌       | 25217/100000 [7:43:29<12:08:49,  1.71it/s]
Train steps ... :  25%|██▌       | 25218/100000 [7:43:29<12:08:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25219/100000 [7:43:30<12:08:54,  1.71it/s]
Train steps ... :  25%|██▌       | 25220/100000 [7:43:30<12:08:56,  1.71it/s]
Train steps ... :  25%|██▌       | 25221/100000 [7:43:31<12:08:49,  1.71it/s]
Train steps ... :  25%|██▌       | 25222/100000 [7:43:31<12:09:16,  1.71it/s]
Train steps ... :  25%|██▌       | 25223/100000 [7:43:32<12:08:39,  1.71it/s]
Train steps ... :  25%|██▌       | 25224/100000 [7:43:33<12:08:36,  1.71it/s]
Train steps ... :  25%|██▌       | 25225/100000 [7:43:33<12:07:42,  1.71it/s]Step... (25225 / 100000 | Loss: 0.9199747443199158, Learning Rate: 7.515075376884423e-05)
+
                                                                             
Step... (25225 / 100000 | Loss: 1.4124269485473633, Learning Rate: 7.515075376884423e-05)
+
Train steps ... :  25%|██▌       | 25225/100000 [7:43:34<12:07:42,  1.71it/s]
Train steps ... :  25%|██▌       | 25226/100000 [7:43:34<12:08:39,  1.71it/s]
Train steps ... :  25%|██▌       | 25227/100000 [7:43:34<12:08:19,  1.71it/s]
Train steps ... :  25%|██▌       | 25228/100000 [7:43:35<12:08:16,  1.71it/s]
Train steps ... :  25%|██▌       | 25229/100000 [7:43:36<12:09:34,  1.71it/s]
Train steps ... :  25%|██▌       | 25230/100000 [7:43:36<12:08:50,  1.71it/s]
Train steps ... :  25%|██▌       | 25231/100000 [7:43:37<12:08:49,  1.71it/s]
Train steps ... :  25%|██▌       | 25232/100000 [7:43:37<12:08:24,  1.71it/s]
Train steps ... :  25%|██▌       | 25233/100000 [7:43:38<12:07:59,  1.71it/s]
Train steps ... :  25%|██▌       | 25234/100000 [7:43:38<12:12:37,  1.70it/s]
Train steps ... :  25%|██▌       | 25235/100000 [7:43:39<12:09:16,  1.71it/s]
Train steps ... :  25%|██▌       | 25236/100000 [7:43:40<12:12:08,  1.70it/s]
Train steps ... :  25%|██▌       | 25237/100000 [7:43:40<12:13:54,  1.70it/s]
Train steps ... :  25%|██▌       | 25238/100000 [7:43:41<12:12:20,  1.70it/s]
Train steps ... :  25%|██▌       | 25239/100000 [7:43:41<12:11:24,  1.70it/s]
Train steps ... :  25%|██▌       | 25240/100000 [7:43:42<12:10:15,  1.71it/s]
Train steps ... :  25%|██▌       | 25241/100000 [7:43:43<12:10:06,  1.71it/s]
Train steps ... :  25%|██▌       | 25242/100000 [7:43:43<12:09:33,  1.71it/s]
Train steps ... :  25%|██▌       | 25243/100000 [7:43:44<12:08:54,  1.71it/s]
Train steps ... :  25%|██▌       | 25244/100000 [7:43:44<12:08:21,  1.71it/s]
Train steps ... :  25%|██▌       | 25245/100000 [7:43:45<12:07:36,  1.71it/s]
Train steps ... :  25%|██▌       | 25246/100000 [7:43:46<12:07:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25247/100000 [7:43:46<12:08:05,  1.71it/s]
Train steps ... :  25%|██▌       | 25248/100000 [7:43:47<12:07:49,  1.71it/s]
Train steps ... :  25%|██▌       | 25249/100000 [7:43:47<12:07:50,  1.71it/s]
Train steps ... :  25%|██▌       | 25250/100000 [7:43:48<12:08:21,  1.71it/s]Step... (25250 / 100000 | Loss: 0.9301331043243408, Learning Rate: 7.512562814070352e-05)
+
                                                                             
Step... (25250 / 100000 | Loss: 1.197692632675171, Learning Rate: 7.512562814070352e-05)
+
Train steps ... :  25%|██▌       | 25250/100000 [7:43:48<12:08:21,  1.71it/s]
Train steps ... :  25%|██▌       | 25251/100000 [7:43:48<12:09:24,  1.71it/s]
Train steps ... :  25%|██▌       | 25252/100000 [7:43:49<12:08:48,  1.71it/s]
Train steps ... :  25%|██▌       | 25253/100000 [7:43:50<12:08:49,  1.71it/s]
Train steps ... :  25%|██▌       | 25254/100000 [7:43:50<12:09:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25255/100000 [7:43:51<12:08:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25256/100000 [7:43:51<12:08:32,  1.71it/s]
Train steps ... :  25%|██▌       | 25257/100000 [7:43:52<12:08:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25258/100000 [7:43:53<12:08:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25259/100000 [7:43:53<12:07:42,  1.71it/s]
Train steps ... :  25%|██▌       | 25260/100000 [7:43:54<12:07:37,  1.71it/s]
Train steps ... :  25%|██▌       | 25261/100000 [7:43:54<12:07:44,  1.71it/s]
Train steps ... :  25%|██▌       | 25262/100000 [7:43:55<12:08:00,  1.71it/s]
Train steps ... :  25%|██▌       | 25263/100000 [7:43:55<12:08:20,  1.71it/s]
Train steps ... :  25%|██▌       | 25264/100000 [7:43:56<12:08:17,  1.71it/s]
Train steps ... :  25%|██▌       | 25265/100000 [7:43:57<12:08:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25266/100000 [7:43:57<12:07:28,  1.71it/s]
Train steps ... :  25%|██▌       | 25267/100000 [7:43:58<12:10:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25268/100000 [7:43:58<12:10:25,  1.71it/s]
Train steps ... :  25%|██▌       | 25269/100000 [7:43:59<12:10:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25270/100000 [7:44:00<12:10:10,  1.71it/s]
Train steps ... :  25%|██▌       | 25271/100000 [7:44:00<12:10:05,  1.71it/s]
Train steps ... :  25%|██▌       | 25272/100000 [7:44:01<12:08:47,  1.71it/s]
Train steps ... :  25%|██▌       | 25273/100000 [7:44:01<12:08:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25274/100000 [7:44:02<12:09:17,  1.71it/s]
Train steps ... :  25%|██▌       | 25275/100000 [7:44:02<12:08:27,  1.71it/s]Step... (25275 / 100000 | Loss: 0.9984791874885559, Learning Rate: 7.510050251256282e-05)
+
                                                                             
Step... (25275 / 100000 | Loss: 1.1253730058670044, Learning Rate: 7.510050251256282e-05)
+
Train steps ... :  25%|██▌       | 25275/100000 [7:44:03<12:08:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25276/100000 [7:44:03<12:08:25,  1.71it/s]
Train steps ... :  25%|██▌       | 25277/100000 [7:44:04<12:08:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25278/100000 [7:44:04<12:08:35,  1.71it/s]
Train steps ... :  25%|██▌       | 25279/100000 [7:44:05<12:07:36,  1.71it/s]
Train steps ... :  25%|██▌       | 25280/100000 [7:44:05<12:08:05,  1.71it/s]
Train steps ... :  25%|██▌       | 25281/100000 [7:44:06<12:07:46,  1.71it/s]
Train steps ... :  25%|██▌       | 25282/100000 [7:44:07<12:07:57,  1.71it/s]
Train steps ... :  25%|██▌       | 25283/100000 [7:44:07<12:07:18,  1.71it/s]
Train steps ... :  25%|██▌       | 25284/100000 [7:44:08<12:07:39,  1.71it/s]
Train steps ... :  25%|██▌       | 25285/100000 [7:44:08<12:07:15,  1.71it/s]
Train steps ... :  25%|██▌       | 25286/100000 [7:44:09<12:07:45,  1.71it/s]
Train steps ... :  25%|██▌       | 25287/100000 [7:44:09<12:07:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25288/100000 [7:44:10<12:08:15,  1.71it/s]
Train steps ... :  25%|██▌       | 25289/100000 [7:44:11<12:08:48,  1.71it/s]
Train steps ... :  25%|██▌       | 25290/100000 [7:44:11<12:08:38,  1.71it/s]
Train steps ... :  25%|██▌       | 25291/100000 [7:44:12<12:08:13,  1.71it/s]
Train steps ... :  25%|██▌       | 25292/100000 [7:44:12<12:08:13,  1.71it/s]
Train steps ... :  25%|██▌       | 25293/100000 [7:44:13<12:08:56,  1.71it/s]
Train steps ... :  25%|██▌       | 25294/100000 [7:44:14<12:07:54,  1.71it/s]
Train steps ... :  25%|██▌       | 25295/100000 [7:44:14<12:07:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25296/100000 [7:44:15<12:07:25,  1.71it/s]
Train steps ... :  25%|██▌       | 25297/100000 [7:44:15<12:07:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25298/100000 [7:44:16<12:07:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25299/100000 [7:44:16<12:08:26,  1.71it/s]
Train steps ... :  25%|██▌       | 25300/100000 [7:44:17<12:08:30,  1.71it/s]Step... (25300 / 100000 | Loss: 0.8188943862915039, Learning Rate: 7.507537688442212e-05)
+
                                                                             
Step... (25300 / 100000 | Loss: 0.94456547498703, Learning Rate: 7.507537688442212e-05)
+
Train steps ... :  25%|██▌       | 25300/100000 [7:44:17<12:08:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25301/100000 [7:44:18<12:08:29,  1.71it/s]
Train steps ... :  25%|██▌       | 25302/100000 [7:44:18<12:09:06,  1.71it/s]
Train steps ... :  25%|██▌       | 25303/100000 [7:44:19<12:09:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25304/100000 [7:44:19<12:08:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25305/100000 [7:44:20<12:08:54,  1.71it/s]
Train steps ... :  25%|██▌       | 25306/100000 [7:44:21<12:08:02,  1.71it/s]
Train steps ... :  25%|██▌       | 25307/100000 [7:44:21<12:08:20,  1.71it/s]
Train steps ... :  25%|██▌       | 25308/100000 [7:44:22<12:07:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25309/100000 [7:44:22<12:08:15,  1.71it/s]
Train steps ... :  25%|██▌       | 25310/100000 [7:44:23<12:08:03,  1.71it/s]
Train steps ... :  25%|██▌       | 25311/100000 [7:44:24<12:07:05,  1.71it/s]
Train steps ... :  25%|██▌       | 25312/100000 [7:44:24<12:07:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25313/100000 [7:44:25<12:07:16,  1.71it/s]
Train steps ... :  25%|██▌       | 25314/100000 [7:44:25<12:07:19,  1.71it/s]
Train steps ... :  25%|██▌       | 25315/100000 [7:44:26<12:08:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25316/100000 [7:44:26<12:08:32,  1.71it/s]
Train steps ... :  25%|██▌       | 25317/100000 [7:44:27<12:08:16,  1.71it/s]
Train steps ... :  25%|██▌       | 25318/100000 [7:44:28<12:07:52,  1.71it/s]
Train steps ... :  25%|██▌       | 25319/100000 [7:44:28<12:08:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25320/100000 [7:44:29<12:08:20,  1.71it/s]
Train steps ... :  25%|██▌       | 25321/100000 [7:44:29<12:08:45,  1.71it/s]
Train steps ... :  25%|██▌       | 25322/100000 [7:44:30<12:08:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25323/100000 [7:44:31<12:08:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25324/100000 [7:44:31<12:08:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25325/100000 [7:44:32<12:08:11,  1.71it/s]Step... (25325 / 100000 | Loss: 0.9223517775535583, Learning Rate: 7.505025125628141e-05)
+
                                                                             
Step... (25325 / 100000 | Loss: 0.9665644764900208, Learning Rate: 7.505025125628141e-05)
+
Train steps ... :  25%|██▌       | 25325/100000 [7:44:32<12:08:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25326/100000 [7:44:32<12:07:53,  1.71it/s]
Train steps ... :  25%|██▌       | 25327/100000 [7:44:33<12:08:41,  1.71it/s]
Train steps ... :  25%|██▌       | 25328/100000 [7:44:33<12:08:04,  1.71it/s]
Train steps ... :  25%|██▌       | 25329/100000 [7:44:34<12:08:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25330/100000 [7:44:35<12:07:36,  1.71it/s]
Train steps ... :  25%|██▌       | 25331/100000 [7:44:35<12:07:32,  1.71it/s]
Train steps ... :  25%|██▌       | 25332/100000 [7:44:36<12:07:36,  1.71it/s]
Train steps ... :  25%|██▌       | 25333/100000 [7:44:36<12:07:54,  1.71it/s]
Train steps ... :  25%|██▌       | 25334/100000 [7:44:37<12:08:02,  1.71it/s]
Train steps ... :  25%|██▌       | 25335/100000 [7:44:38<12:07:35,  1.71it/s]
Train steps ... :  25%|██▌       | 25336/100000 [7:44:38<12:07:17,  1.71it/s]
Train steps ... :  25%|██▌       | 25337/100000 [7:44:39<12:06:52,  1.71it/s]
Train steps ... :  25%|██▌       | 25338/100000 [7:44:39<12:07:36,  1.71it/s]
Train steps ... :  25%|██▌       | 25339/100000 [7:44:40<12:08:20,  1.71it/s]
Train steps ... :  25%|██▌       | 25340/100000 [7:44:40<12:08:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25341/100000 [7:44:41<12:07:42,  1.71it/s]
Train steps ... :  25%|██▌       | 25342/100000 [7:44:42<12:07:24,  1.71it/s]
Train steps ... :  25%|██▌       | 25343/100000 [7:44:42<12:07:00,  1.71it/s]
Train steps ... :  25%|██▌       | 25344/100000 [7:44:43<12:07:03,  1.71it/s]
Train steps ... :  25%|██▌       | 25345/100000 [7:44:43<12:07:07,  1.71it/s]
Train steps ... :  25%|██▌       | 25346/100000 [7:44:44<12:06:41,  1.71it/s]
Train steps ... :  25%|██▌       | 25347/100000 [7:44:45<12:07:12,  1.71it/s]
Train steps ... :  25%|██▌       | 25348/100000 [7:44:45<12:07:37,  1.71it/s]
Train steps ... :  25%|██▌       | 25349/100000 [7:44:46<12:07:45,  1.71it/s]
Train steps ... :  25%|██▌       | 25350/100000 [7:44:46<12:07:14,  1.71it/s]Step... (25350 / 100000 | Loss: 0.9300516247749329, Learning Rate: 7.50251256281407e-05)
+
                                                                             
Step... (25350 / 100000 | Loss: 0.8713076114654541, Learning Rate: 7.50251256281407e-05)
+
Train steps ... :  25%|██▌       | 25350/100000 [7:44:47<12:07:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25351/100000 [7:44:47<12:06:58,  1.71it/s]
Train steps ... :  25%|██▌       | 25352/100000 [7:44:47<12:06:33,  1.71it/s]
Train steps ... :  25%|██▌       | 25353/100000 [7:44:48<12:06:44,  1.71it/s]
Train steps ... :  25%|██▌       | 25354/100000 [7:44:49<12:07:02,  1.71it/s]
Train steps ... :  25%|██▌       | 25355/100000 [7:44:49<12:07:10,  1.71it/s]
Train steps ... :  25%|██▌       | 25356/100000 [7:44:50<12:06:46,  1.71it/s]
Train steps ... :  25%|██▌       | 25357/100000 [7:44:50<12:07:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25358/100000 [7:44:51<12:07:41,  1.71it/s]
Train steps ... :  25%|██▌       | 25359/100000 [7:44:52<12:06:59,  1.71it/s]
Train steps ... :  25%|██▌       | 25360/100000 [7:44:52<12:07:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25361/100000 [7:44:53<12:07:12,  1.71it/s]
Train steps ... :  25%|██▌       | 25362/100000 [7:44:53<12:07:26,  1.71it/s]
Train steps ... :  25%|██▌       | 25363/100000 [7:44:54<12:07:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25364/100000 [7:44:55<12:07:46,  1.71it/s]
Train steps ... :  25%|██▌       | 25365/100000 [7:44:55<12:07:00,  1.71it/s]
Train steps ... :  25%|██▌       | 25366/100000 [7:44:56<12:06:55,  1.71it/s]
Train steps ... :  25%|██▌       | 25367/100000 [7:44:56<12:08:15,  1.71it/s]
Train steps ... :  25%|██▌       | 25368/100000 [7:44:57<12:07:34,  1.71it/s]
Train steps ... :  25%|██▌       | 25369/100000 [7:44:57<12:07:25,  1.71it/s]
Train steps ... :  25%|██▌       | 25370/100000 [7:44:58<12:07:10,  1.71it/s]
Train steps ... :  25%|██▌       | 25371/100000 [7:44:59<12:07:28,  1.71it/s]
Train steps ... :  25%|██▌       | 25372/100000 [7:44:59<12:06:52,  1.71it/s]
Train steps ... :  25%|██▌       | 25373/100000 [7:45:00<12:07:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25374/100000 [7:45:00<12:06:57,  1.71it/s]
Train steps ... :  25%|██▌       | 25375/100000 [7:45:01<12:07:17,  1.71it/s]Step... (25375 / 100000 | Loss: 0.8939588069915771, Learning Rate: 7.500000000000001e-05)
+
                                                                             
Step... (25375 / 100000 | Loss: 0.8124496936798096, Learning Rate: 7.500000000000001e-05)
+
Train steps ... :  25%|██▌       | 25375/100000 [7:45:01<12:07:17,  1.71it/s]
Train steps ... :  25%|██▌       | 25376/100000 [7:45:02<12:07:32,  1.71it/s]
Train steps ... :  25%|██▌       | 25377/100000 [7:45:02<12:07:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25378/100000 [7:45:03<12:07:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25379/100000 [7:45:03<12:07:16,  1.71it/s]
Train steps ... :  25%|██▌       | 25380/100000 [7:45:04<12:07:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25381/100000 [7:45:04<12:07:18,  1.71it/s]
Train steps ... :  25%|██▌       | 25382/100000 [7:45:05<12:08:24,  1.71it/s]
Train steps ... :  25%|██▌       | 25383/100000 [7:45:06<12:08:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25384/100000 [7:45:06<12:07:58,  1.71it/s]
Train steps ... :  25%|██▌       | 25385/100000 [7:45:07<12:07:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25386/100000 [7:45:07<12:07:13,  1.71it/s]
Train steps ... :  25%|██▌       | 25387/100000 [7:45:08<12:07:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25388/100000 [7:45:09<12:07:10,  1.71it/s]
Train steps ... :  25%|██▌       | 25389/100000 [7:45:09<12:07:46,  1.71it/s]
Train steps ... :  25%|██▌       | 25390/100000 [7:45:10<12:07:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25391/100000 [7:45:10<12:07:35,  1.71it/s]
Train steps ... :  25%|██▌       | 25392/100000 [7:45:11<12:06:47,  1.71it/s]
Train steps ... :  25%|██▌       | 25393/100000 [7:45:11<12:06:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25394/100000 [7:45:12<12:07:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25395/100000 [7:45:13<12:06:31,  1.71it/s]
Train steps ... :  25%|██▌       | 25396/100000 [7:45:13<12:06:49,  1.71it/s]
Train steps ... :  25%|██▌       | 25397/100000 [7:45:14<12:06:29,  1.71it/s]
Train steps ... :  25%|██▌       | 25398/100000 [7:45:14<12:06:18,  1.71it/s]
Train steps ... :  25%|██▌       | 25399/100000 [7:45:15<12:06:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25400/100000 [7:45:16<12:06:28,  1.71it/s]Step... (25400 / 100000 | Loss: 1.0804400444030762, Learning Rate: 7.49748743718593e-05)
+
                                                                             
Step... (25400 / 100000 | Loss: 1.1128497123718262, Learning Rate: 7.49748743718593e-05)
+
Train steps ... :  25%|██▌       | 25400/100000 [7:45:16<12:06:28,  1.71it/s]
Train steps ... :  25%|██▌       | 25401/100000 [7:45:16<12:06:26,  1.71it/s]
Train steps ... :  25%|██▌       | 25402/100000 [7:45:17<12:07:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25403/100000 [7:45:17<12:06:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25404/100000 [7:45:18<12:06:07,  1.71it/s]
Train steps ... :  25%|██▌       | 25405/100000 [7:45:18<12:06:09,  1.71it/s]
Train steps ... :  25%|██▌       | 25406/100000 [7:45:19<12:05:50,  1.71it/s]
Train steps ... :  25%|██▌       | 25407/100000 [7:45:20<12:06:58,  1.71it/s]
Train steps ... :  25%|██▌       | 25408/100000 [7:45:20<12:07:33,  1.71it/s]
Train steps ... :  25%|██▌       | 25409/100000 [7:45:21<12:07:17,  1.71it/s]
Train steps ... :  25%|██▌       | 25410/100000 [7:45:21<12:06:21,  1.71it/s]
Train steps ... :  25%|██▌       | 25411/100000 [7:45:22<12:05:55,  1.71it/s]
Train steps ... :  25%|██▌       | 25412/100000 [7:45:23<12:06:34,  1.71it/s]
Train steps ... :  25%|██▌       | 25413/100000 [7:45:23<12:06:20,  1.71it/s]
Train steps ... :  25%|██▌       | 25414/100000 [7:45:24<12:07:21,  1.71it/s]
Train steps ... :  25%|██▌       | 25415/100000 [7:45:24<12:06:45,  1.71it/s]
Train steps ... :  25%|██▌       | 25416/100000 [7:45:25<12:06:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25417/100000 [7:45:25<12:05:57,  1.71it/s]
Train steps ... :  25%|██▌       | 25418/100000 [7:45:26<12:06:39,  1.71it/s]
Train steps ... :  25%|██▌       | 25419/100000 [7:45:27<12:06:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25420/100000 [7:45:27<12:07:18,  1.71it/s]
Train steps ... :  25%|██▌       | 25421/100000 [7:45:28<12:06:48,  1.71it/s]
Train steps ... :  25%|██▌       | 25422/100000 [7:45:28<12:06:37,  1.71it/s]
Train steps ... :  25%|██▌       | 25423/100000 [7:45:29<12:07:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25424/100000 [7:45:30<12:07:38,  1.71it/s]
Train steps ... :  25%|██▌       | 25425/100000 [7:45:30<12:07:22,  1.71it/s]Step... (25425 / 100000 | Loss: 1.1141467094421387, Learning Rate: 7.49497487437186e-05)
+
                                                                             
Step... (25425 / 100000 | Loss: 1.412400484085083, Learning Rate: 7.49497487437186e-05)
+
Train steps ... :  25%|██▌       | 25425/100000 [7:45:31<12:07:22,  1.71it/s]
Train steps ... :  25%|██▌       | 25426/100000 [7:45:31<12:07:24,  1.71it/s]
Train steps ... :  25%|██▌       | 25427/100000 [7:45:31<12:07:15,  1.71it/s]
Train steps ... :  25%|██▌       | 25428/100000 [7:45:32<12:06:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25429/100000 [7:45:33<12:06:16,  1.71it/s]
Train steps ... :  25%|██▌       | 25430/100000 [7:45:33<12:06:29,  1.71it/s]
Train steps ... :  25%|██▌       | 25431/100000 [7:45:34<12:06:16,  1.71it/s]
Train steps ... :  25%|██▌       | 25432/100000 [7:45:34<12:06:25,  1.71it/s]
Train steps ... :  25%|██▌       | 25433/100000 [7:45:35<12:06:02,  1.71it/s]
Train steps ... :  25%|██▌       | 25434/100000 [7:45:35<12:06:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25435/100000 [7:45:36<12:05:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25436/100000 [7:45:37<12:06:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25437/100000 [7:45:37<12:06:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25438/100000 [7:45:38<12:06:31,  1.71it/s]
Train steps ... :  25%|██▌       | 25439/100000 [7:45:38<12:05:56,  1.71it/s]
Train steps ... :  25%|██▌       | 25440/100000 [7:45:39<12:05:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25441/100000 [7:45:40<12:05:05,  1.71it/s]
Train steps ... :  25%|██▌       | 25442/100000 [7:45:40<12:06:05,  1.71it/s]
Train steps ... :  25%|██▌       | 25443/100000 [7:45:41<12:05:58,  1.71it/s]
Train steps ... :  25%|██▌       | 25444/100000 [7:45:41<12:05:34,  1.71it/s]
Train steps ... :  25%|██▌       | 25445/100000 [7:45:42<12:05:32,  1.71it/s]
Train steps ... :  25%|██▌       | 25446/100000 [7:45:42<12:05:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25447/100000 [7:45:43<12:06:37,  1.71it/s]
Train steps ... :  25%|██▌       | 25448/100000 [7:45:44<12:07:07,  1.71it/s]
Train steps ... :  25%|██▌       | 25449/100000 [7:45:44<12:06:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25450/100000 [7:45:45<12:06:14,  1.71it/s]Step... (25450 / 100000 | Loss: 0.8909701108932495, Learning Rate: 7.49246231155779e-05)
+
                                                                             
Step... (25450 / 100000 | Loss: 1.0151431560516357, Learning Rate: 7.49246231155779e-05)
+
Train steps ... :  25%|██▌       | 25450/100000 [7:45:45<12:06:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25451/100000 [7:45:45<12:06:07,  1.71it/s]
Train steps ... :  25%|██▌       | 25452/100000 [7:45:46<12:07:04,  1.71it/s]
Train steps ... :  25%|██▌       | 25453/100000 [7:45:47<12:06:08,  1.71it/s]
Train steps ... :  25%|██▌       | 25454/100000 [7:45:47<12:06:35,  1.71it/s]
Train steps ... :  25%|██▌       | 25455/100000 [7:45:48<12:06:17,  1.71it/s]
Train steps ... :  25%|██▌       | 25456/100000 [7:45:48<12:06:33,  1.71it/s]
Train steps ... :  25%|██▌       | 25457/100000 [7:45:49<12:06:29,  1.71it/s]
Train steps ... :  25%|██▌       | 25458/100000 [7:45:49<12:05:40,  1.71it/s]
Train steps ... :  25%|██▌       | 25459/100000 [7:45:50<12:05:35,  1.71it/s]
Train steps ... :  25%|██▌       | 25460/100000 [7:45:51<12:06:21,  1.71it/s]
Train steps ... :  25%|██▌       | 25461/100000 [7:45:51<12:05:41,  1.71it/s]
Train steps ... :  25%|██▌       | 25462/100000 [7:45:52<12:05:44,  1.71it/s]
Train steps ... :  25%|██▌       | 25463/100000 [7:45:52<12:05:34,  1.71it/s]
Train steps ... :  25%|██▌       | 25464/100000 [7:45:53<12:05:32,  1.71it/s]
Train steps ... :  25%|██▌       | 25465/100000 [7:45:54<12:05:45,  1.71it/s]
Train steps ... :  25%|██▌       | 25466/100000 [7:45:54<12:05:32,  1.71it/s]
Train steps ... :  25%|██▌       | 25467/100000 [7:45:55<12:05:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25468/100000 [7:45:55<12:05:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25469/100000 [7:45:56<12:05:44,  1.71it/s]
Train steps ... :  25%|██▌       | 25470/100000 [7:45:56<12:06:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25471/100000 [7:45:57<12:05:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25472/100000 [7:45:58<12:05:27,  1.71it/s]
Train steps ... :  25%|██▌       | 25473/100000 [7:45:58<12:05:49,  1.71it/s]
Train steps ... :  25%|██▌       | 25474/100000 [7:45:59<12:05:35,  1.71it/s]
Train steps ... :  25%|██▌       | 25475/100000 [7:45:59<12:05:13,  1.71it/s]Step... (25475 / 100000 | Loss: 1.1903678178787231, Learning Rate: 7.48994974874372e-05)
+
                                                                             
Step... (25475 / 100000 | Loss: 1.29902982711792, Learning Rate: 7.48994974874372e-05)
+
Train steps ... :  25%|██▌       | 25475/100000 [7:46:00<12:05:13,  1.71it/s]
Train steps ... :  25%|██▌       | 25476/100000 [7:46:00<12:05:16,  1.71it/s]
Train steps ... :  25%|██▌       | 25477/100000 [7:46:01<12:05:53,  1.71it/s]
Train steps ... :  25%|██▌       | 25478/100000 [7:46:01<12:06:45,  1.71it/s]
Train steps ... :  25%|██▌       | 25479/100000 [7:46:02<12:06:44,  1.71it/s]
Train steps ... :  25%|██▌       | 25480/100000 [7:46:02<12:06:23,  1.71it/s]
Train steps ... :  25%|██▌       | 25481/100000 [7:46:03<12:05:59,  1.71it/s]
Train steps ... :  25%|██▌       | 25482/100000 [7:46:03<12:05:29,  1.71it/s]
Train steps ... :  25%|██▌       | 25483/100000 [7:46:04<12:05:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25484/100000 [7:46:05<12:05:07,  1.71it/s]
Train steps ... :  25%|██▌       | 25485/100000 [7:46:05<12:05:20,  1.71it/s]
Train steps ... :  25%|██▌       | 25486/100000 [7:46:06<12:05:43,  1.71it/s]
Train steps ... :  25%|██▌       | 25487/100000 [7:46:06<12:06:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25488/100000 [7:46:07<12:05:33,  1.71it/s]
Train steps ... :  25%|██▌       | 25489/100000 [7:46:08<12:06:30,  1.71it/s]
Train steps ... :  25%|██▌       | 25490/100000 [7:46:08<12:07:18,  1.71it/s]
Train steps ... :  25%|██▌       | 25491/100000 [7:46:09<12:07:14,  1.71it/s]
Train steps ... :  25%|██▌       | 25492/100000 [7:46:09<12:06:11,  1.71it/s]
Train steps ... :  25%|██▌       | 25493/100000 [7:46:10<12:06:13,  1.71it/s]
Train steps ... :  25%|██▌       | 25494/100000 [7:46:11<12:06:00,  1.71it/s]
Train steps ... :  25%|██▌       | 25495/100000 [7:46:11<12:06:01,  1.71it/s]
Train steps ... :  25%|██▌       | 25496/100000 [7:46:12<12:06:32,  1.71it/s]
Train steps ... :  25%|██▌       | 25497/100000 [7:46:12<12:05:48,  1.71it/s]
Train steps ... :  25%|██▌       | 25498/100000 [7:46:13<12:06:36,  1.71it/s]
Train steps ... :  25%|██▌       | 25499/100000 [7:46:13<12:06:38,  1.71it/s]
Train steps ... :  26%|██▌       | 25500/100000 [7:46:14<12:06:45,  1.71it/s]Step... (25500 / 100000 | Loss: 0.8462333679199219, Learning Rate: 7.487437185929649e-05)
+
                                                                             
Step... (25500 / 100000 | Loss: 1.1760681867599487, Learning Rate: 7.487437185929649e-05)
+
Train steps ... :  26%|██▌       | 25500/100000 [7:46:14<12:06:45,  1.71it/s]
Train steps ... :  26%|██▌       | 25501/100000 [7:46:15<12:05:58,  1.71it/s]
Train steps ... :  26%|██▌       | 25502/100000 [7:46:15<12:05:33,  1.71it/s]
Train steps ... :  26%|██▌       | 25503/100000 [7:46:16<12:04:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25504/100000 [7:46:16<12:05:35,  1.71it/s]
Train steps ... :  26%|██▌       | 25505/100000 [7:46:17<12:04:59,  1.71it/s]
Train steps ... :  26%|██▌       | 25506/100000 [7:46:18<12:05:46,  1.71it/s]
Train steps ... :  26%|██▌       | 25507/100000 [7:46:18<12:05:46,  1.71it/s]
Train steps ... :  26%|██▌       | 25508/100000 [7:46:19<12:05:22,  1.71it/s]
Train steps ... :  26%|██▌       | 25509/100000 [7:46:19<12:05:58,  1.71it/s]
Train steps ... :  26%|██▌       | 25510/100000 [7:46:20<12:05:37,  1.71it/s]
Train steps ... :  26%|██▌       | 25511/100000 [7:46:20<12:05:37,  1.71it/s]
Train steps ... :  26%|██▌       | 25512/100000 [7:46:21<12:05:45,  1.71it/s]
Train steps ... :  26%|██▌       | 25513/100000 [7:46:22<12:06:31,  1.71it/s]
Train steps ... :  26%|██▌       | 25514/100000 [7:46:22<12:07:26,  1.71it/s]
Train steps ... :  26%|██▌       | 25515/100000 [7:46:23<12:06:40,  1.71it/s]
Train steps ... :  26%|██▌       | 25516/100000 [7:46:23<12:06:57,  1.71it/s]
Train steps ... :  26%|██▌       | 25517/100000 [7:46:24<12:06:32,  1.71it/s]
Train steps ... :  26%|██▌       | 25518/100000 [7:46:25<12:05:51,  1.71it/s]
Train steps ... :  26%|██▌       | 25519/100000 [7:46:25<12:05:49,  1.71it/s]
Train steps ... :  26%|██▌       | 25520/100000 [7:46:26<12:06:46,  1.71it/s]
Train steps ... :  26%|██▌       | 25521/100000 [7:46:26<12:06:50,  1.71it/s]
Train steps ... :  26%|██▌       | 25522/100000 [7:46:27<12:06:09,  1.71it/s]
Train steps ... :  26%|██▌       | 25523/100000 [7:46:27<12:06:49,  1.71it/s]
Train steps ... :  26%|██▌       | 25524/100000 [7:46:28<12:06:59,  1.71it/s]
Train steps ... :  26%|██▌       | 25525/100000 [7:46:29<12:06:41,  1.71it/s]Step... (25525 / 100000 | Loss: 1.0046709775924683, Learning Rate: 7.484924623115577e-05)
+
                                                                             
Step... (25525 / 100000 | Loss: 0.9191486239433289, Learning Rate: 7.484924623115577e-05)
+
Train steps ... :  26%|██▌       | 25525/100000 [7:46:29<12:06:41,  1.71it/s]
Train steps ... :  26%|██▌       | 25526/100000 [7:46:29<12:07:04,  1.71it/s]
Train steps ... :  26%|██▌       | 25527/100000 [7:46:30<12:06:17,  1.71it/s]
Train steps ... :  26%|██▌       | 25528/100000 [7:46:30<12:06:28,  1.71it/s]
Train steps ... :  26%|██▌       | 25529/100000 [7:46:31<12:06:35,  1.71it/s]
Train steps ... :  26%|██▌       | 25530/100000 [7:46:32<12:06:08,  1.71it/s]
Train steps ... :  26%|██▌       | 25531/100000 [7:46:32<12:05:46,  1.71it/s]
Train steps ... :  26%|██▌       | 25532/100000 [7:46:33<12:05:24,  1.71it/s]
Train steps ... :  26%|██▌       | 25533/100000 [7:46:33<12:05:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25534/100000 [7:46:34<12:05:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25535/100000 [7:46:34<12:05:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25536/100000 [7:46:35<12:05:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25537/100000 [7:46:36<12:05:01,  1.71it/s]
Train steps ... :  26%|██▌       | 25538/100000 [7:46:36<12:05:38,  1.71it/s]
Train steps ... :  26%|██▌       | 25539/100000 [7:46:37<12:06:01,  1.71it/s]
Train steps ... :  26%|██▌       | 25540/100000 [7:46:37<12:05:17,  1.71it/s]
Train steps ... :  26%|██▌       | 25541/100000 [7:46:38<12:05:23,  1.71it/s]
Train steps ... :  26%|██▌       | 25542/100000 [7:46:39<12:05:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25543/100000 [7:46:39<12:05:22,  1.71it/s]
Train steps ... :  26%|██▌       | 25544/100000 [7:46:40<12:05:08,  1.71it/s]
Train steps ... :  26%|██▌       | 25545/100000 [7:46:40<12:04:45,  1.71it/s]
Train steps ... :  26%|██▌       | 25546/100000 [7:46:41<12:04:54,  1.71it/s]
Train steps ... :  26%|██▌       | 25547/100000 [7:46:41<12:05:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25548/100000 [7:46:42<12:04:17,  1.71it/s]
Train steps ... :  26%|██▌       | 25549/100000 [7:46:43<12:04:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25550/100000 [7:46:43<12:04:28,  1.71it/s]Step... (25550 / 100000 | Loss: 0.9884462356567383, Learning Rate: 7.482412060301508e-05)
+
                                                                             
Step... (25550 / 100000 | Loss: 0.9606744050979614, Learning Rate: 7.482412060301508e-05)
+
Train steps ... :  26%|██▌       | 25550/100000 [7:46:44<12:04:28,  1.71it/s]
Train steps ... :  26%|██▌       | 25551/100000 [7:46:44<12:05:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25552/100000 [7:46:44<12:05:04,  1.71it/s]
Train steps ... :  26%|██▌       | 25553/100000 [7:46:45<12:05:37,  1.71it/s]
Train steps ... :  26%|██▌       | 25554/100000 [7:46:46<12:06:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25555/100000 [7:46:46<12:05:26,  1.71it/s]
Train steps ... :  26%|██▌       | 25556/100000 [7:46:47<12:05:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25557/100000 [7:46:47<12:04:43,  1.71it/s]
Train steps ... :  26%|██▌       | 25558/100000 [7:46:48<12:04:47,  1.71it/s]
Train steps ... :  26%|██▌       | 25559/100000 [7:46:49<12:05:11,  1.71it/s]
Train steps ... :  26%|██▌       | 25560/100000 [7:46:49<12:04:57,  1.71it/s]
Train steps ... :  26%|██▌       | 25561/100000 [7:46:50<12:04:03,  1.71it/s]
Train steps ... :  26%|██▌       | 25562/100000 [7:46:50<12:04:30,  1.71it/s]
Train steps ... :  26%|██▌       | 25563/100000 [7:46:51<12:04:23,  1.71it/s]
Train steps ... :  26%|██▌       | 25564/100000 [7:46:51<12:04:33,  1.71it/s]
Train steps ... :  26%|██▌       | 25565/100000 [7:46:52<12:04:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25566/100000 [7:46:53<12:04:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25567/100000 [7:46:53<12:04:54,  1.71it/s]
Train steps ... :  26%|██▌       | 25568/100000 [7:46:54<12:04:40,  1.71it/s]
Train steps ... :  26%|██▌       | 25569/100000 [7:46:54<12:04:23,  1.71it/s]
Train steps ... :  26%|██▌       | 25570/100000 [7:46:55<12:05:49,  1.71it/s]
Train steps ... :  26%|██▌       | 25571/100000 [7:46:56<12:05:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25572/100000 [7:46:56<12:04:40,  1.71it/s]
Train steps ... :  26%|██▌       | 25573/100000 [7:46:57<12:05:07,  1.71it/s]
Train steps ... :  26%|██▌       | 25574/100000 [7:46:57<12:04:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25575/100000 [7:46:58<12:04:45,  1.71it/s]Step... (25575 / 100000 | Loss: 0.8169527053833008, Learning Rate: 7.479899497487437e-05)
+
                                                                             
Step... (25575 / 100000 | Loss: 1.2584600448608398, Learning Rate: 7.479899497487437e-05)
+
Train steps ... :  26%|██▌       | 25575/100000 [7:46:58<12:04:45,  1.71it/s]
Train steps ... :  26%|██▌       | 25576/100000 [7:46:58<12:05:44,  1.71it/s]
Train steps ... :  26%|██▌       | 25577/100000 [7:46:59<12:06:41,  1.71it/s]
Train steps ... :  26%|██▌       | 25578/100000 [7:47:00<12:05:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25579/100000 [7:47:00<12:05:24,  1.71it/s]
Train steps ... :  26%|██▌       | 25580/100000 [7:47:01<12:04:26,  1.71it/s]
Train steps ... :  26%|██▌       | 25581/100000 [7:47:01<12:05:32,  1.71it/s]
Train steps ... :  26%|██▌       | 25582/100000 [7:47:02<12:05:03,  1.71it/s]
Train steps ... :  26%|██▌       | 25583/100000 [7:47:03<12:04:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25584/100000 [7:47:03<12:04:47,  1.71it/s]
Train steps ... :  26%|██▌       | 25585/100000 [7:47:04<12:06:11,  1.71it/s]
Train steps ... :  26%|██▌       | 25586/100000 [7:47:04<12:05:54,  1.71it/s]
Train steps ... :  26%|██▌       | 25587/100000 [7:47:05<12:04:55,  1.71it/s]
Train steps ... :  26%|██▌       | 25588/100000 [7:47:05<12:04:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25589/100000 [7:47:06<12:03:41,  1.71it/s]
Train steps ... :  26%|██▌       | 25590/100000 [7:47:07<12:05:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25591/100000 [7:47:07<12:04:39,  1.71it/s]
Train steps ... :  26%|██▌       | 25592/100000 [7:47:08<12:06:15,  1.71it/s]
Train steps ... :  26%|██▌       | 25593/100000 [7:47:08<12:04:30,  1.71it/s]
Train steps ... :  26%|██▌       | 25594/100000 [7:47:09<12:04:20,  1.71it/s]
Train steps ... :  26%|██▌       | 25595/100000 [7:47:10<12:04:26,  1.71it/s]
Train steps ... :  26%|██▌       | 25596/100000 [7:47:10<12:03:55,  1.71it/s]
Train steps ... :  26%|██▌       | 25597/100000 [7:47:11<12:03:55,  1.71it/s]
Train steps ... :  26%|██▌       | 25598/100000 [7:47:11<12:03:44,  1.71it/s]
Train steps ... :  26%|██▌       | 25599/100000 [7:47:12<12:03:32,  1.71it/s]
Train steps ... :  26%|██▌       | 25600/100000 [7:47:12<12:03:49,  1.71it/s]Step... (25600 / 100000 | Loss: 1.0161813497543335, Learning Rate: 7.477386934673368e-05)
+
                                                                             
Step... (25600 / 100000 | Loss: 1.0964056253433228, Learning Rate: 7.477386934673368e-05)
+
Train steps ... :  26%|██▌       | 25600/100000 [7:47:13<12:03:49,  1.71it/s]
Train steps ... :  26%|██▌       | 25601/100000 [7:47:13<12:03:55,  1.71it/s]
Train steps ... :  26%|██▌       | 25602/100000 [7:47:14<12:06:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25603/100000 [7:47:14<12:05:28,  1.71it/s]
Train steps ... :  26%|██▌       | 25604/100000 [7:47:15<12:06:21,  1.71it/s]
Train steps ... :  26%|██▌       | 25605/100000 [7:47:15<12:05:20,  1.71it/s]
Train steps ... :  26%|██▌       | 25606/100000 [7:47:16<12:05:14,  1.71it/s]
Train steps ... :  26%|██▌       | 25607/100000 [7:47:17<12:05:14,  1.71it/s]
Train steps ... :  26%|██▌       | 25608/100000 [7:47:17<12:06:24,  1.71it/s]
Train steps ... :  26%|█���▌       | 25609/100000 [7:47:18<12:05:29,  1.71it/s]
Train steps ... :  26%|██▌       | 25610/100000 [7:47:18<12:06:01,  1.71it/s]
Train steps ... :  26%|██▌       | 25611/100000 [7:47:19<12:04:08,  1.71it/s]
Train steps ... :  26%|██▌       | 25612/100000 [7:47:19<12:04:01,  1.71it/s]
Train steps ... :  26%|██▌       | 25613/100000 [7:47:20<12:04:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25614/100000 [7:47:21<12:04:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25615/100000 [7:47:21<12:04:50,  1.71it/s]
Train steps ... :  26%|██▌       | 25616/100000 [7:47:22<12:04:54,  1.71it/s]
Train steps ... :  26%|██▌       | 25617/100000 [7:47:22<12:05:15,  1.71it/s]
Train steps ... :  26%|██▌       | 25618/100000 [7:47:23<12:06:21,  1.71it/s]
Train steps ... :  26%|██▌       | 25619/100000 [7:47:24<12:06:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25620/100000 [7:47:24<12:04:58,  1.71it/s]
Train steps ... :  26%|██▌       | 25621/100000 [7:47:25<12:04:39,  1.71it/s]
Train steps ... :  26%|██▌       | 25622/100000 [7:47:25<12:05:33,  1.71it/s]
Train steps ... :  26%|██▌       | 25623/100000 [7:47:26<12:07:39,  1.70it/s]
Train steps ... :  26%|██▌       | 25624/100000 [7:47:27<12:05:09,  1.71it/s]
Train steps ... :  26%|██▌       | 25625/100000 [7:47:27<12:05:10,  1.71it/s]Step... (25625 / 100000 | Loss: 0.8228912949562073, Learning Rate: 7.474874371859297e-05)
+
                                                                             
Step... (25625 / 100000 | Loss: 0.9528992176055908, Learning Rate: 7.474874371859297e-05)
+
Train steps ... :  26%|██▌       | 25625/100000 [7:47:27<12:05:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25626/100000 [7:47:28<12:05:51,  1.71it/s]
Train steps ... :  26%|██▌       | 25627/100000 [7:47:28<12:04:54,  1.71it/s]
Train steps ... :  26%|██▌       | 25628/100000 [7:47:29<12:05:47,  1.71it/s]
Train steps ... :  26%|██▌       | 25629/100000 [7:47:29<12:05:31,  1.71it/s]
Train steps ... :  26%|██▌       | 25630/100000 [7:47:30<12:05:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25631/100000 [7:47:31<12:05:58,  1.71it/s]
Train steps ... :  26%|██▌       | 25632/100000 [7:47:31<12:05:45,  1.71it/s]
Train steps ... :  26%|██▌       | 25633/100000 [7:47:32<12:04:44,  1.71it/s]
Train steps ... :  26%|██▌       | 25634/100000 [7:47:32<12:04:53,  1.71it/s]
Train steps ... :  26%|██▌       | 25635/100000 [7:47:33<12:04:36,  1.71it/s]
Train steps ... :  26%|██▌       | 25636/100000 [7:47:34<12:05:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25637/100000 [7:47:34<12:04:45,  1.71it/s]
Train steps ... :  26%|██▌       | 25638/100000 [7:47:35<12:05:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25639/100000 [7:47:35<12:04:16,  1.71it/s]
Train steps ... :  26%|██▌       | 25640/100000 [7:47:36<12:04:29,  1.71it/s]
Train steps ... :  26%|██▌       | 25641/100000 [7:47:36<12:04:50,  1.71it/s]
Train steps ... :  26%|██▌       | 25642/100000 [7:47:37<12:04:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25643/100000 [7:47:38<12:04:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25644/100000 [7:47:38<12:05:28,  1.71it/s]
Train steps ... :  26%|██▌       | 25645/100000 [7:47:39<12:05:51,  1.71it/s]
Train steps ... :  26%|██▌       | 25646/100000 [7:47:39<12:05:35,  1.71it/s]
Train steps ... :  26%|██▌       | 25647/100000 [7:47:40<12:07:47,  1.70it/s]
Train steps ... :  26%|██▌       | 25648/100000 [7:47:41<12:06:59,  1.70it/s]
Train steps ... :  26%|██▌       | 25649/100000 [7:47:41<12:07:54,  1.70it/s]
Train steps ... :  26%|██▌       | 25650/100000 [7:47:42<12:06:53,  1.70it/s]Step... (25650 / 100000 | Loss: 1.028343915939331, Learning Rate: 7.472361809045227e-05)
+
                                                                             
Step... (25650 / 100000 | Loss: 0.6823489665985107, Learning Rate: 7.472361809045227e-05)
+
Train steps ... :  26%|██▌       | 25650/100000 [7:47:42<12:06:53,  1.70it/s]
Train steps ... :  26%|██▌       | 25651/100000 [7:47:42<12:07:02,  1.70it/s]
Train steps ... :  26%|██▌       | 25652/100000 [7:47:43<12:07:04,  1.70it/s]
Train steps ... :  26%|██▌       | 25653/100000 [7:47:43<12:05:37,  1.71it/s]
Train steps ... :  26%|██▌       | 25654/100000 [7:47:44<12:05:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25655/100000 [7:47:45<12:04:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25656/100000 [7:47:45<12:06:42,  1.71it/s]
Train steps ... :  26%|██▌       | 25657/100000 [7:47:46<12:05:26,  1.71it/s]
Train steps ... :  26%|██▌       | 25658/100000 [7:47:46<12:05:39,  1.71it/s]
Train steps ... :  26%|██▌       | 25659/100000 [7:47:47<12:06:47,  1.70it/s]
Train steps ... :  26%|██▌       | 25660/100000 [7:47:48<12:05:54,  1.71it/s]
Train steps ... :  26%|██▌       | 25661/100000 [7:47:48<12:05:38,  1.71it/s]
Train steps ... :  26%|██▌       | 25662/100000 [7:47:49<12:07:15,  1.70it/s]
Train steps ... :  26%|██▌       | 25663/100000 [7:47:49<12:05:03,  1.71it/s]
Train steps ... :  26%|██▌       | 25664/100000 [7:47:50<12:04:34,  1.71it/s]
Train steps ... :  26%|██▌       | 25665/100000 [7:47:51<12:04:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25666/100000 [7:47:51<12:03:41,  1.71it/s]
Train steps ... :  26%|██▌       | 25667/100000 [7:47:52<12:03:39,  1.71it/s]
Train steps ... :  26%|██▌       | 25668/100000 [7:47:52<12:03:14,  1.71it/s]
Train steps ... :  26%|██▌       | 25669/100000 [7:47:53<12:03:28,  1.71it/s]
Train steps ... :  26%|██▌       | 25670/100000 [7:47:53<12:05:17,  1.71it/s]
Train steps ... :  26%|██▌       | 25671/100000 [7:47:54<12:05:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25672/100000 [7:47:55<12:05:14,  1.71it/s]
Train steps ... :  26%|██▌       | 25673/100000 [7:47:55<12:05:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25674/100000 [7:47:56<12:05:39,  1.71it/s]
Train steps ... :  26%|██▌       | 25675/100000 [7:47:56<12:05:10,  1.71it/s]Step... (25675 / 100000 | Loss: 1.1297683715820312, Learning Rate: 7.469849246231157e-05)
+
                                                                             
Step... (25675 / 100000 | Loss: 1.190453052520752, Learning Rate: 7.469849246231157e-05)
+
Train steps ... :  26%|██▌       | 25675/100000 [7:47:57<12:05:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25676/100000 [7:47:57<12:05:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25677/100000 [7:47:58<12:08:27,  1.70it/s]
Train steps ... :  26%|██▌       | 25678/100000 [7:47:58<12:07:16,  1.70it/s]
Train steps ... :  26%|██▌       | 25679/100000 [7:47:59<12:06:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25680/100000 [7:47:59<12:05:14,  1.71it/s]
Train steps ... :  26%|██▌       | 25681/100000 [7:48:00<12:05:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25682/100000 [7:48:00<12:04:12,  1.71it/s]
Train steps ... :  26%|██▌       | 25683/100000 [7:48:01<12:06:56,  1.70it/s]
Train steps ... :  26%|██▌       | 25684/100000 [7:48:02<12:06:49,  1.70it/s]
Train steps ... :  26%|██▌       | 25685/100000 [7:48:02<12:05:58,  1.71it/s]
Train steps ... :  26%|██▌       | 25686/100000 [7:48:03<12:06:27,  1.70it/s]
Train steps ... :  26%|██▌       | 25687/100000 [7:48:03<12:06:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25688/100000 [7:48:04<12:04:30,  1.71it/s]
Train steps ... :  26%|██▌       | 25689/100000 [7:48:05<12:05:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25690/100000 [7:48:05<12:04:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25691/100000 [7:48:06<12:04:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25692/100000 [7:48:06<12:05:14,  1.71it/s]
Train steps ... :  26%|██▌       | 25693/100000 [7:48:07<12:05:34,  1.71it/s]
Train steps ... :  26%|██▌       | 25694/100000 [7:48:08<12:05:43,  1.71it/s]
Train steps ... :  26%|██▌       | 25695/100000 [7:48:08<12:03:58,  1.71it/s]
Train steps ... :  26%|██▌       | 25696/100000 [7:48:09<12:05:03,  1.71it/s]
Train steps ... :  26%|██▌       | 25697/100000 [7:48:09<12:04:35,  1.71it/s]
Train steps ... :  26%|██▌       | 25698/100000 [7:48:10<12:04:54,  1.71it/s]
Train steps ... :  26%|██▌       | 25699/100000 [7:48:10<12:04:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25700/100000 [7:48:11<12:03:46,  1.71it/s]Step... (25700 / 100000 | Loss: 0.8867822885513306, Learning Rate: 7.467336683417085e-05)
+
                                                                             
Step... (25700 / 100000 | Loss: 0.8448630571365356, Learning Rate: 7.467336683417085e-05)
+
Train steps ... :  26%|██▌       | 25700/100000 [7:48:11<12:03:46,  1.71it/s]
Train steps ... :  26%|██▌       | 25701/100000 [7:48:12<12:04:04,  1.71it/s]
Train steps ... :  26%|██▌       | 25702/100000 [7:48:12<12:04:26,  1.71it/s]
Train steps ... :  26%|██▌       | 25703/100000 [7:48:13<12:05:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25704/100000 [7:48:13<12:04:35,  1.71it/s]
Train steps ... :  26%|██▌       | 25705/100000 [7:48:14<12:04:14,  1.71it/s]
Train steps ... :  26%|██▌       | 25706/100000 [7:48:15<12:03:58,  1.71it/s]
Train steps ... :  26%|██▌       | 25707/100000 [7:48:15<12:03:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25708/100000 [7:48:16<12:03:58,  1.71it/s]
Train steps ... :  26%|██▌       | 25709/100000 [7:48:16<12:04:35,  1.71it/s]
Train steps ... :  26%|██▌       | 25710/100000 [7:48:17<12:04:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25711/100000 [7:48:17<12:04:43,  1.71it/s]
Train steps ... :  26%|██▌       | 25712/100000 [7:48:18<12:04:31,  1.71it/s]
Train steps ... :  26%|██▌       | 25713/100000 [7:48:19<12:04:34,  1.71it/s]
Train steps ... :  26%|██▌       | 25714/100000 [7:48:19<12:03:55,  1.71it/s]
Train steps ... :  26%|██▌       | 25715/100000 [7:48:20<12:03:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25716/100000 [7:48:20<12:03:47,  1.71it/s]
Train steps ... :  26%|██▌       | 25717/100000 [7:48:21<12:03:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25718/100000 [7:48:22<12:04:24,  1.71it/s]
Train steps ... :  26%|██▌       | 25719/100000 [7:48:22<12:02:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25720/100000 [7:48:23<12:02:57,  1.71it/s]
Train steps ... :  26%|██▌       | 25721/100000 [7:48:23<12:03:20,  1.71it/s]
Train steps ... :  26%|██▌       | 25722/100000 [7:48:24<12:03:07,  1.71it/s]
Train steps ... :  26%|██▌       | 25723/100000 [7:48:24<12:03:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25724/100000 [7:48:25<12:02:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25725/100000 [7:48:26<12:03:11,  1.71it/s]Step... (25725 / 100000 | Loss: 0.7287053465843201, Learning Rate: 7.464824120603016e-05)
+
                                                                             
Step... (25725 / 100000 | Loss: 0.860363245010376, Learning Rate: 7.464824120603016e-05)
+
Train steps ... :  26%|██▌       | 25725/100000 [7:48:26<12:03:11,  1.71it/s]
Train steps ... :  26%|██▌       | 25726/100000 [7:48:26<12:03:23,  1.71it/s]
Train steps ... :  26%|██▌       | 25727/100000 [7:48:27<12:04:34,  1.71it/s]
Train steps ... :  26%|██▌       | 25728/100000 [7:48:27<12:04:22,  1.71it/s]
Train steps ... :  26%|██▌       | 25729/100000 [7:48:28<12:03:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25730/100000 [7:48:29<12:03:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25731/100000 [7:48:29<12:04:04,  1.71it/s]
Train steps ... :  26%|██▌       | 25732/100000 [7:48:30<12:03:03,  1.71it/s]
Train steps ... :  26%|██▌       | 25733/100000 [7:48:30<12:03:12,  1.71it/s]
Train steps ... :  26%|██▌       | 25734/100000 [7:48:31<12:02:44,  1.71it/s]
Train steps ... :  26%|██▌       | 25735/100000 [7:48:31<12:02:29,  1.71it/s]
Train steps ... :  26%|██▌       | 25736/100000 [7:48:32<12:04:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25737/100000 [7:48:33<12:02:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25738/100000 [7:48:33<12:03:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25739/100000 [7:48:34<12:01:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25740/100000 [7:48:34<12:02:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25741/100000 [7:48:35<12:02:55,  1.71it/s]
Train steps ... :  26%|██▌       | 25742/100000 [7:48:36<12:03:03,  1.71it/s]
Train steps ... :  26%|██▌       | 25743/100000 [7:48:36<12:02:31,  1.71it/s]
Train steps ... :  26%|██▌       | 25744/100000 [7:48:37<12:02:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25745/100000 [7:48:37<12:02:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25746/100000 [7:48:38<12:02:37,  1.71it/s]
Train steps ... :  26%|██▌       | 25747/100000 [7:48:38<12:03:08,  1.71it/s]
Train steps ... :  26%|██▌       | 25748/100000 [7:48:39<12:03:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25749/100000 [7:48:40<12:02:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25750/100000 [7:48:40<12:02:29,  1.71it/s]Step... (25750 / 100000 | Loss: 0.7799438238143921, Learning Rate: 7.462311557788944e-05)
+
                                                                             
Step... (25750 / 100000 | Loss: 1.014206051826477, Learning Rate: 7.462311557788944e-05)
+
Train steps ... :  26%|██▌       | 25750/100000 [7:48:41<12:02:29,  1.71it/s]
Train steps ... :  26%|██▌       | 25751/100000 [7:48:41<12:03:17,  1.71it/s]
Train steps ... :  26%|██▌       | 25752/100000 [7:48:41<12:04:07,  1.71it/s]
Train steps ... :  26%|██▌       | 25753/100000 [7:48:42<12:03:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25754/100000 [7:48:43<12:05:31,  1.71it/s]
Train steps ... :  26%|██▌       | 25755/100000 [7:48:43<12:04:11,  1.71it/s]
Train steps ... :  26%|██▌       | 25756/100000 [7:48:44<12:02:46,  1.71it/s]
Train steps ... :  26%|██▌       | 25757/100000 [7:48:44<12:04:12,  1.71it/s]
Train steps ... :  26%|██▌       | 25758/100000 [7:48:45<12:02:35,  1.71it/s]
Train steps ... :  26%|██▌       | 25759/100000 [7:48:45<12:02:32,  1.71it/s]
Train steps ... :  26%|██▌       | 25760/100000 [7:48:46<12:03:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25761/100000 [7:48:47<12:03:57,  1.71it/s]
Train steps ... :  26%|██▌       | 25762/100000 [7:48:47<12:03:25,  1.71it/s]
Train steps ... :  26%|██▌       | 25763/100000 [7:48:48<12:03:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25764/100000 [7:48:48<12:02:30,  1.71it/s]
Train steps ... :  26%|██▌       | 25765/100000 [7:48:49<12:03:12,  1.71it/s]
Train steps ... :  26%|██▌       | 25766/100000 [7:48:50<12:04:25,  1.71it/s]
Train steps ... :  26%|██▌       | 25767/100000 [7:48:50<12:04:26,  1.71it/s]
Train steps ... :  26%|██▌       | 25768/100000 [7:48:51<12:04:01,  1.71it/s]
Train steps ... :  26%|██▌       | 25769/100000 [7:48:51<12:03:44,  1.71it/s]
Train steps ... :  26%|██▌       | 25770/100000 [7:48:52<12:02:57,  1.71it/s]
Train steps ... :  26%|██▌       | 25771/100000 [7:48:53<12:02:59,  1.71it/s]
Train steps ... :  26%|██▌       | 25772/100000 [7:48:53<12:02:41,  1.71it/s]
Train steps ... :  26%|██▌       | 25773/100000 [7:48:54<12:02:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25774/100000 [7:48:54<12:01:59,  1.71it/s]
Train steps ... :  26%|██▌       | 25775/100000 [7:48:55<12:02:15,  1.71it/s]Step... (25775 / 100000 | Loss: 0.9267578721046448, Learning Rate: 7.459798994974875e-05)
+
                                                                             
Step... (25775 / 100000 | Loss: 0.9060577154159546, Learning Rate: 7.459798994974875e-05)
+
Train steps ... :  26%|██▌       | 25775/100000 [7:48:55<12:02:15,  1.71it/s]
Train steps ... :  26%|██▌       | 25776/100000 [7:48:55<12:03:28,  1.71it/s]
Train steps ... :  26%|██▌       | 25777/100000 [7:48:56<12:02:37,  1.71it/s]
Train steps ... :  26%|██▌       | 25778/100000 [7:48:57<12:02:20,  1.71it/s]
Train steps ... :  26%|██▌       | 25779/100000 [7:48:57<12:01:59,  1.71it/s]
Train steps ... :  26%|██▌       | 25780/100000 [7:48:58<12:01:44,  1.71it/s]
Train steps ... :  26%|██▌       | 25781/100000 [7:48:58<12:01:46,  1.71it/s]
Train steps ... :  26%|██▌       | 25782/100000 [7:48:59<12:02:05,  1.71it/s]
Train steps ... :  26%|██▌       | 25783/100000 [7:49:00<12:02:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25784/100000 [7:49:00<12:04:31,  1.71it/s]
Train steps ... :  26%|██▌       | 25785/100000 [7:49:01<12:03:25,  1.71it/s]
Train steps ... :  26%|██▌       | 25786/100000 [7:49:01<12:03:12,  1.71it/s]
Train steps ... :  26%|██▌       | 25787/100000 [7:49:02<12:03:38,  1.71it/s]
Train steps ... :  26%|██▌       | 25788/100000 [7:49:02<12:02:43,  1.71it/s]
Train steps ... :  26%|██▌       | 25789/100000 [7:49:03<12:03:25,  1.71it/s]
Train steps ... :  26%|██▌       | 25790/100000 [7:49:04<12:04:09,  1.71it/s]
Train steps ... :  26%|██▌       | 25791/100000 [7:49:04<12:04:09,  1.71it/s]
Train steps ... :  26%|██▌       | 25792/100000 [7:49:05<12:03:40,  1.71it/s]
Train steps ... :  26%|██▌       | 25793/100000 [7:49:05<12:04:07,  1.71it/s]
Train steps ... :  26%|██▌       | 25794/100000 [7:49:06<12:03:23,  1.71it/s]
Train steps ... :  26%|██▌       | 25795/100000 [7:49:07<12:03:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25796/100000 [7:49:07<12:02:44,  1.71it/s]
Train steps ... :  26%|██▌       | 25797/100000 [7:49:08<12:03:34,  1.71it/s]
Train steps ... :  26%|██▌       | 25798/100000 [7:49:08<12:03:08,  1.71it/s]
Train steps ... :  26%|██▌       | 25799/100000 [7:49:09<12:04:05,  1.71it/s]
Train steps ... :  26%|██▌       | 25800/100000 [7:49:09<12:04:20,  1.71it/s]Step... (25800 / 100000 | Loss: 0.9255344867706299, Learning Rate: 7.457286432160805e-05)
+
                                                                             
Step... (25800 / 100000 | Loss: 1.2467014789581299, Learning Rate: 7.457286432160805e-05)
+
Train steps ... :  26%|██▌       | 25800/100000 [7:49:10<12:04:20,  1.71it/s]
Train steps ... :  26%|██▌       | 25801/100000 [7:49:10<12:03:16,  1.71it/s]
Train steps ... :  26%|██▌       | 25802/100000 [7:49:11<12:03:30,  1.71it/s]
Train steps ... :  26%|██▌       | 25803/100000 [7:49:11<12:03:24,  1.71it/s]
Train steps ... :  26%|██▌       | 25804/100000 [7:49:12<12:04:50,  1.71it/s]
Train steps ... :  26%|██▌       | 25805/100000 [7:49:12<12:02:32,  1.71it/s]
Train steps ... :  26%|██▌       | 25806/100000 [7:49:13<12:02:49,  1.71it/s]
Train steps ... :  26%|██▌       | 25807/100000 [7:49:14<12:02:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25808/100000 [7:49:14<12:03:15,  1.71it/s]
Train steps ... :  26%|██▌       | 25809/100000 [7:49:15<12:02:16,  1.71it/s]
Train steps ... :  26%|██▌       | 25810/100000 [7:49:15<12:03:05,  1.71it/s]
Train steps ... :  26%|██▌       | 25811/100000 [7:49:16<12:02:29,  1.71it/s]
Train steps ... :  26%|██▌       | 25812/100000 [7:49:16<12:02:17,  1.71it/s]
Train steps ... :  26%|██▌       | 25813/100000 [7:49:17<12:02:14,  1.71it/s]
Train steps ... :  26%|██▌       | 25814/100000 [7:49:18<12:03:01,  1.71it/s]
Train steps ... :  26%|██▌       | 25815/100000 [7:49:18<12:03:29,  1.71it/s]
Train steps ... :  26%|██▌       | 25816/100000 [7:49:19<12:03:53,  1.71it/s]
Train steps ... :  26%|██▌       | 25817/100000 [7:49:19<12:02:55,  1.71it/s]
Train steps ... :  26%|██▌       | 25818/100000 [7:49:20<12:04:04,  1.71it/s]
Train steps ... :  26%|██▌       | 25819/100000 [7:49:21<12:04:49,  1.71it/s]
Train steps ... :  26%|█���▌       | 25820/100000 [7:49:21<12:03:50,  1.71it/s]
Train steps ... :  26%|██▌       | 25821/100000 [7:49:22<12:02:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25822/100000 [7:49:22<12:03:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25823/100000 [7:49:23<12:03:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25824/100000 [7:49:24<12:03:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25825/100000 [7:49:24<12:02:40,  1.71it/s]Step... (25825 / 100000 | Loss: 1.0256164073944092, Learning Rate: 7.454773869346735e-05)
+
                                                                             
Step... (25825 / 100000 | Loss: 0.8443363308906555, Learning Rate: 7.454773869346735e-05)
+
Train steps ... :  26%|██▌       | 25825/100000 [7:49:24<12:02:40,  1.71it/s]
Train steps ... :  26%|██▌       | 25826/100000 [7:49:25<12:03:26,  1.71it/s]
Train steps ... :  26%|██▌       | 25827/100000 [7:49:25<12:03:37,  1.71it/s]
Train steps ... :  26%|██▌       | 25828/100000 [7:49:26<12:03:06,  1.71it/s]
Train steps ... :  26%|██▌       | 25829/100000 [7:49:26<12:03:53,  1.71it/s]
Train steps ... :  26%|██▌       | 25830/100000 [7:49:27<12:04:15,  1.71it/s]
Train steps ... :  26%|██▌       | 25831/100000 [7:49:28<12:03:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25832/100000 [7:49:28<12:02:59,  1.71it/s]
Train steps ... :  26%|██▌       | 25833/100000 [7:49:29<12:03:39,  1.71it/s]
Train steps ... :  26%|██▌       | 25834/100000 [7:49:29<12:03:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25835/100000 [7:49:30<12:02:49,  1.71it/s]
Train steps ... :  26%|██▌       | 25836/100000 [7:49:31<12:03:17,  1.71it/s]
Train steps ... :  26%|██▌       | 25837/100000 [7:49:31<12:03:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25838/100000 [7:49:32<12:03:49,  1.71it/s]
Train steps ... :  26%|██▌       | 25839/100000 [7:49:32<12:02:57,  1.71it/s]
Train steps ... :  26%|██▌       | 25840/100000 [7:49:33<12:02:11,  1.71it/s]
Train steps ... :  26%|██▌       | 25841/100000 [7:49:33<12:01:49,  1.71it/s]
Train steps ... :  26%|██▌       | 25842/100000 [7:49:34<12:02:12,  1.71it/s]
Train steps ... :  26%|██▌       | 25843/100000 [7:49:35<12:01:51,  1.71it/s]
Train steps ... :  26%|██▌       | 25844/100000 [7:49:35<12:02:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25845/100000 [7:49:36<12:02:05,  1.71it/s]
Train steps ... :  26%|██▌       | 25846/100000 [7:49:36<12:02:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25847/100000 [7:49:37<12:02:01,  1.71it/s]
Train steps ... :  26%|██▌       | 25848/100000 [7:49:38<12:01:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25849/100000 [7:49:38<12:02:59,  1.71it/s]
Train steps ... :  26%|██▌       | 25850/100000 [7:49:39<12:03:17,  1.71it/s]Step... (25850 / 100000 | Loss: 0.8896986246109009, Learning Rate: 7.452261306532664e-05)
+
                                                                             
Step... (25850 / 100000 | Loss: 0.9091248512268066, Learning Rate: 7.452261306532664e-05)
+
Train steps ... :  26%|██▌       | 25850/100000 [7:49:39<12:03:17,  1.71it/s]
Train steps ... :  26%|██▌       | 25851/100000 [7:49:39<12:04:44,  1.71it/s]
Train steps ... :  26%|██▌       | 25852/100000 [7:49:40<12:04:44,  1.71it/s]
Train steps ... :  26%|██▌       | 25853/100000 [7:49:40<12:04:21,  1.71it/s]
Train steps ... :  26%|██▌       | 25854/100000 [7:49:41<12:03:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25855/100000 [7:49:42<12:03:23,  1.71it/s]
Train steps ... :  26%|██▌       | 25856/100000 [7:49:42<12:03:23,  1.71it/s]
Train steps ... :  26%|██▌       | 25857/100000 [7:49:43<12:04:07,  1.71it/s]
Train steps ... :  26%|██▌       | 25858/100000 [7:49:43<12:03:05,  1.71it/s]
Train steps ... :  26%|██▌       | 25859/100000 [7:49:44<12:03:36,  1.71it/s]
Train steps ... :  26%|██▌       | 25860/100000 [7:49:45<12:04:12,  1.71it/s]
Train steps ... :  26%|██▌       | 25861/100000 [7:49:45<12:02:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25862/100000 [7:49:46<12:02:42,  1.71it/s]
Train steps ... :  26%|██▌       | 25863/100000 [7:49:46<12:04:01,  1.71it/s]
Train steps ... :  26%|██▌       | 25864/100000 [7:49:47<12:04:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25865/100000 [7:49:48<12:04:54,  1.70it/s]
Train steps ... :  26%|██▌       | 25866/100000 [7:49:48<12:04:36,  1.71it/s]
Train steps ... :  26%|██▌       | 25867/100000 [7:49:49<12:04:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25868/100000 [7:49:49<12:03:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25869/100000 [7:49:50<12:02:46,  1.71it/s]
Train steps ... :  26%|██▌       | 25870/100000 [7:49:50<12:01:35,  1.71it/s]
Train steps ... :  26%|██▌       | 25871/100000 [7:49:51<12:01:50,  1.71it/s]
Train steps ... :  26%|██▌       | 25872/100000 [7:49:52<12:03:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25873/100000 [7:49:52<12:03:01,  1.71it/s]
Train steps ... :  26%|██▌       | 25874/100000 [7:49:53<12:03:07,  1.71it/s]
Train steps ... :  26%|██▌       | 25875/100000 [7:49:53<12:02:32,  1.71it/s]Step... (25875 / 100000 | Loss: 0.8202571868896484, Learning Rate: 7.449748743718593e-05)
+
                                                                             
Step... (25875 / 100000 | Loss: 0.9404691457748413, Learning Rate: 7.449748743718593e-05)
+
Train steps ... :  26%|██▌       | 25875/100000 [7:49:54<12:02:32,  1.71it/s]
Train steps ... :  26%|██▌       | 25876/100000 [7:49:54<12:02:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25877/100000 [7:49:55<12:02:13,  1.71it/s]
Train steps ... :  26%|██▌       | 25878/100000 [7:49:55<12:02:05,  1.71it/s]
Train steps ... :  26%|██▌       | 25879/100000 [7:49:56<12:03:23,  1.71it/s]
Train steps ... :  26%|██▌       | 25880/100000 [7:49:56<12:04:04,  1.71it/s]
Train steps ... :  26%|██▌       | 25881/100000 [7:49:57<12:04:38,  1.70it/s]
Train steps ... :  26%|██▌       | 25882/100000 [7:49:57<12:04:06,  1.71it/s]
Train steps ... :  26%|██▌       | 25883/100000 [7:49:58<12:04:48,  1.70it/s]
Train steps ... :  26%|██▌       | 25884/100000 [7:49:59<12:03:15,  1.71it/s]
Train steps ... :  26%|██▌       | 25885/100000 [7:49:59<12:02:33,  1.71it/s]
Train steps ... :  26%|██▌       | 25886/100000 [7:50:00<12:02:07,  1.71it/s]
Train steps ... :  26%|██▌       | 25887/100000 [7:50:00<12:03:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25888/100000 [7:50:01<12:02:54,  1.71it/s]
Train steps ... :  26%|██▌       | 25889/100000 [7:50:02<12:02:45,  1.71it/s]
Train steps ... :  26%|██▌       | 25890/100000 [7:50:02<12:02:04,  1.71it/s]
Train steps ... :  26%|██▌       | 25891/100000 [7:50:03<12:02:45,  1.71it/s]
Train steps ... :  26%|██▌       | 25892/100000 [7:50:03<12:03:21,  1.71it/s]
Train steps ... :  26%|██▌       | 25893/100000 [7:50:04<12:03:09,  1.71it/s]
Train steps ... :  26%|██▌       | 25894/100000 [7:50:04<12:02:40,  1.71it/s]
Train steps ... :  26%|██▌       | 25895/100000 [7:50:05<12:02:49,  1.71it/s]
Train steps ... :  26%|██▌       | 25896/100000 [7:50:06<12:04:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25897/100000 [7:50:06<12:03:25,  1.71it/s]
Train steps ... :  26%|██▌       | 25898/100000 [7:50:07<12:04:29,  1.70it/s]
Train steps ... :  26%|██▌       | 25899/100000 [7:50:07<12:03:40,  1.71it/s]
Train steps ... :  26%|██▌       | 25900/100000 [7:50:08<12:05:36,  1.70it/s]Step... (25900 / 100000 | Loss: 0.9383766651153564, Learning Rate: 7.447236180904524e-05)
+
                                                                             
Step... (25900 / 100000 | Loss: 1.0608782768249512, Learning Rate: 7.447236180904524e-05)
+
Train steps ... :  26%|██▌       | 25900/100000 [7:50:08<12:05:36,  1.70it/s]
Train steps ... :  26%|██▌       | 25901/100000 [7:50:09<12:03:37,  1.71it/s]
Train steps ... :  26%|██▌       | 25902/100000 [7:50:09<12:03:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25903/100000 [7:50:10<12:02:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25904/100000 [7:50:10<12:03:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25905/100000 [7:50:11<12:02:03,  1.71it/s]
Train steps ... :  26%|██▌       | 25906/100000 [7:50:12<12:03:34,  1.71it/s]
Train steps ... :  26%|██▌       | 25907/100000 [7:50:12<12:02:51,  1.71it/s]
Train steps ... :  26%|██▌       | 25908/100000 [7:50:13<12:03:40,  1.71it/s]
Train steps ... :  26%|██▌       | 25909/100000 [7:50:13<12:03:55,  1.71it/s]
Train steps ... :  26%|██▌       | 25910/100000 [7:50:14<12:02:41,  1.71it/s]
Train steps ... :  26%|██▌       | 25911/100000 [7:50:14<12:05:09,  1.70it/s]
Train steps ... :  26%|██▌       | 25912/100000 [7:50:15<12:01:58,  1.71it/s]
Train steps ... :  26%|██▌       | 25913/100000 [7:50:16<12:02:10,  1.71it/s]
Train steps ... :  26%|██▌       | 25914/100000 [7:50:16<12:01:47,  1.71it/s]
Train steps ... :  26%|██▌       | 25915/100000 [7:50:17<12:02:13,  1.71it/s]
Train steps ... :  26%|██▌       | 25916/100000 [7:50:17<12:02:59,  1.71it/s]
Train steps ... :  26%|██▌       | 25917/100000 [7:50:18<12:02:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25918/100000 [7:50:19<12:02:36,  1.71it/s]
Train steps ... :  26%|██▌       | 25919/100000 [7:50:19<12:02:00,  1.71it/s]
Train steps ... :  26%|██▌       | 25920/100000 [7:50:20<12:03:39,  1.71it/s]
Train steps ... :  26%|██▌       | 25921/100000 [7:50:20<12:01:47,  1.71it/s]
Train steps ... :  26%|██▌       | 25922/100000 [7:50:21<12:01:08,  1.71it/s]
Train steps ... :  26%|██▌       | 25923/100000 [7:50:21<12:01:20,  1.71it/s]
Train steps ... :  26%|██▌       | 25924/100000 [7:50:22<12:01:54,  1.71it/s]
Train steps ... :  26%|██▌       | 25925/100000 [7:50:23<12:02:40,  1.71it/s]Step... (25925 / 100000 | Loss: 1.1888598203659058, Learning Rate: 7.444723618090452e-05)
+
                                                                             
Step... (25925 / 100000 | Loss: 1.0429829359054565, Learning Rate: 7.444723618090452e-05)
+
Train steps ... :  26%|██▌       | 25925/100000 [7:50:23<12:02:40,  1.71it/s]
Train steps ... :  26%|██▌       | 25926/100000 [7:50:23<12:04:07,  1.70it/s]
Train steps ... :  26%|██▌       | 25927/100000 [7:50:24<12:01:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25928/100000 [7:50:24<12:02:57,  1.71it/s]
Train steps ... :  26%|██▌       | 25929/100000 [7:50:25<12:02:50,  1.71it/s]
Train steps ... :  26%|██▌       | 25930/100000 [7:50:26<12:03:31,  1.71it/s]
Train steps ... :  26%|██▌       | 25931/100000 [7:50:26<12:03:46,  1.71it/s]
Train steps ... :  26%|██▌       | 25932/100000 [7:50:27<12:03:40,  1.71it/s]
Train steps ... :  26%|██▌       | 25933/100000 [7:50:27<12:04:06,  1.70it/s]
Train steps ... :  26%|██▌       | 25934/100000 [7:50:28<12:03:25,  1.71it/s]
Train steps ... :  26%|██▌       | 25935/100000 [7:50:28<12:02:28,  1.71it/s]
Train steps ... :  26%|██▌       | 25936/100000 [7:50:29<12:04:12,  1.70it/s]
Train steps ... :  26%|██▌       | 25937/100000 [7:50:30<12:03:01,  1.71it/s]
Train steps ... :  26%|██▌       | 25938/100000 [7:50:30<12:02:59,  1.71it/s]
Train steps ... :  26%|██▌       | 25939/100000 [7:50:31<12:02:16,  1.71it/s]
Train steps ... :  26%|██▌       | 25940/100000 [7:50:31<12:04:03,  1.70it/s]
Train steps ... :  26%|██▌       | 25941/100000 [7:50:32<12:02:45,  1.71it/s]
Train steps ... :  26%|██▌       | 25942/100000 [7:50:33<12:03:03,  1.71it/s]
Train steps ... :  26%|██▌       | 25943/100000 [7:50:33<12:04:06,  1.70it/s]
Train steps ... :  26%|██▌       | 25944/100000 [7:50:34<12:03:28,  1.71it/s]
Train steps ... :  26%|██▌       | 25945/100000 [7:50:34<12:03:55,  1.70it/s]
Train steps ... :  26%|██▌       | 25946/100000 [7:50:35<12:05:30,  1.70it/s]
Train steps ... :  26%|██▌       | 25947/100000 [7:50:36<12:04:53,  1.70it/s]
Train steps ... :  26%|██▌       | 25948/100000 [7:50:36<12:05:00,  1.70it/s]
Train steps ... :  26%|██▌       | 25949/100000 [7:50:37<12:04:40,  1.70it/s]
Train steps ... :  26%|██▌       | 25950/100000 [7:50:37<12:03:33,  1.71it/s]Step... (25950 / 100000 | Loss: 1.2091995477676392, Learning Rate: 7.442211055276383e-05)
+
                                                                             
Step... (25950 / 100000 | Loss: 1.0680654048919678, Learning Rate: 7.442211055276383e-05)
+
Train steps ... :  26%|██▌       | 25950/100000 [7:50:38<12:03:33,  1.71it/s]
Train steps ... :  26%|██▌       | 25951/100000 [7:50:38<12:03:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25952/100000 [7:50:38<12:02:51,  1.71it/s]
Train steps ... :  26%|██▌       | 25953/100000 [7:50:39<12:03:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25954/100000 [7:50:40<12:01:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25955/100000 [7:50:40<12:02:13,  1.71it/s]
Train steps ... :  26%|██▌       | 25956/100000 [7:50:41<12:01:33,  1.71it/s]
Train steps ... :  26%|██▌       | 25957/100000 [7:50:41<12:03:11,  1.71it/s]
Train steps ... :  26%|██▌       | 25958/100000 [7:50:42<12:03:33,  1.71it/s]
Train steps ... :  26%|██▌       | 25959/100000 [7:50:43<12:02:31,  1.71it/s]
Train steps ... :  26%|██▌       | 25960/100000 [7:50:43<12:02:36,  1.71it/s]
Train steps ... :  26%|██▌       | 25961/100000 [7:50:44<12:02:50,  1.71it/s]
Train steps ... :  26%|██▌       | 25962/100000 [7:50:44<12:02:55,  1.71it/s]
Train steps ... :  26%|██▌       | 25963/100000 [7:50:45<12:01:56,  1.71it/s]
Train steps ... :  26%|██▌       | 25964/100000 [7:50:45<12:01:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25965/100000 [7:50:46<12:01:24,  1.71it/s]
Train steps ... :  26%|██▌       | 25966/100000 [7:50:47<12:01:53,  1.71it/s]
Train steps ... :  26%|██▌       | 25967/100000 [7:50:47<12:02:08,  1.71it/s]
Train steps ... :  26%|██▌       | 25968/100000 [7:50:48<12:02:15,  1.71it/s]
Train steps ... :  26%|██▌       | 25969/100000 [7:50:48<12:02:43,  1.71it/s]
Train steps ... :  26%|██▌       | 25970/100000 [7:50:49<12:05:28,  1.70it/s]
Train steps ... :  26%|██▌       | 25971/100000 [7:50:50<12:05:19,  1.70it/s]
Train steps ... :  26%|██▌       | 25972/100000 [7:50:50<12:05:03,  1.70it/s]
Train steps ... :  26%|██▌       | 25973/100000 [7:50:51<12:04:56,  1.70it/s]
Train steps ... :  26%|██▌       | 25974/100000 [7:50:51<12:03:59,  1.70it/s]
Train steps ... :  26%|██▌       | 25975/100000 [7:50:52<12:04:48,  1.70it/s]Step... (25975 / 100000 | Loss: 1.2053704261779785, Learning Rate: 7.439698492462311e-05)
+
                                                                             
Step... (25975 / 100000 | Loss: 0.8758577108383179, Learning Rate: 7.439698492462311e-05)
+
Train steps ... :  26%|██▌       | 25975/100000 [7:50:52<12:04:48,  1.70it/s]
Train steps ... :  26%|██▌       | 25976/100000 [7:50:53<12:02:34,  1.71it/s]
Train steps ... :  26%|██▌       | 25977/100000 [7:50:53<12:02:53,  1.71it/s]
Train steps ... :  26%|██▌       | 25978/100000 [7:50:54<12:03:32,  1.71it/s]
Train steps ... :  26%|██▌       | 25979/100000 [7:50:54<12:00:49,  1.71it/s]
Train steps ... :  26%|██▌       | 25980/100000 [7:50:55<12:00:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25981/100000 [7:50:55<12:00:27,  1.71it/s]
Train steps ... :  26%|██▌       | 25982/100000 [7:50:56<12:00:52,  1.71it/s]
Train steps ... :  26%|██▌       | 25983/100000 [7:50:57<12:01:47,  1.71it/s]
Train steps ... :  26%|██▌       | 25984/100000 [7:50:57<12:01:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25985/100000 [7:50:58<12:01:20,  1.71it/s]
Train steps ... :  26%|██▌       | 25986/100000 [7:50:58<12:02:15,  1.71it/s]
Train steps ... :  26%|██▌       | 25987/100000 [7:50:59<12:03:19,  1.71it/s]
Train steps ... :  26%|██▌       | 25988/100000 [7:51:00<12:02:46,  1.71it/s]
Train steps ... :  26%|██▌       | 25989/100000 [7:51:00<12:02:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25990/100000 [7:51:01<12:02:22,  1.71it/s]
Train steps ... :  26%|██▌       | 25991/100000 [7:51:01<12:01:43,  1.71it/s]
Train steps ... :  26%|██▌       | 25992/100000 [7:51:02<12:00:48,  1.71it/s]
Train steps ... :  26%|██▌       | 25993/100000 [7:51:02<12:00:18,  1.71it/s]
Train steps ... :  26%|██▌       | 25994/100000 [7:51:03<12:00:13,  1.71it/s]
Train steps ... :  26%|██▌       | 25995/100000 [7:51:04<12:02:02,  1.71it/s]
Train steps ... :  26%|██▌       | 25996/100000 [7:51:04<12:01:31,  1.71it/s]
Train steps ... :  26%|██▌       | 25997/100000 [7:51:05<12:00:50,  1.71it/s]
Train steps ... :  26%|██▌       | 25998/100000 [7:51:05<12:01:05,  1.71it/s]
Train steps ... :  26%|██▌       | 25999/100000 [7:51:06<12:00:41,  1.71it/s]
Train steps ... :  26%|██▌       | 26000/100000 [7:51:07<12:01:43,  1.71it/s]Step... (26000 / 100000 | Loss: 0.9182013273239136, Learning Rate: 7.437185929648241e-05)
+
                                                                             
Step... (26000 / 100000 | Loss: 1.6334666013717651, Learning Rate: 7.437185929648241e-05)
+
Train steps ... :  26%|██▌       | 26000/100000 [7:51:07<12:01:43,  1.71it/s]
Train steps ... :  26%|██▌       | 26001/100000 [7:51:07<12:01:38,  1.71it/s]
Train steps ... :  26%|██▌       | 26002/100000 [7:51:08<12:01:20,  1.71it/s]
Train steps ... :  26%|██▌       | 26003/100000 [7:51:08<12:01:17,  1.71it/s]
Train steps ... :  26%|██▌       | 26004/100000 [7:51:09<12:00:46,  1.71it/s]
Train steps ... :  26%|██▌       | 26005/100000 [7:51:09<12:02:26,  1.71it/s]
Train steps ... :  26%|██▌       | 26006/100000 [7:51:10<12:03:43,  1.70it/s]
Train steps ... :  26%|██▌       | 26007/100000 [7:51:11<12:02:59,  1.71it/s]
Train steps ... :  26%|██▌       | 26008/100000 [7:51:11<12:01:45,  1.71it/s]
Train steps ... :  26%|██▌       | 26009/100000 [7:51:12<12:02:36,  1.71it/s]
Train steps ... :  26%|██▌       | 26010/100000 [7:51:12<12:02:30,  1.71it/s]
Train steps ... :  26%|██▌       | 26011/100000 [7:51:13<12:01:35,  1.71it/s]
Train steps ... :  26%|██▌       | 26012/100000 [7:51:14<12:00:24,  1.71it/s]
Train steps ... :  26%|██▌       | 26013/100000 [7:51:14<12:02:29,  1.71it/s]
Train steps ... :  26%|██▌       | 26014/100000 [7:51:15<12:00:56,  1.71it/s]
Train steps ... :  26%|██▌       | 26015/100000 [7:51:15<12:01:28,  1.71it/s]
Train steps ... :  26%|██▌       | 26016/100000 [7:51:16<12:01:32,  1.71it/s]
Train steps ... :  26%|██▌       | 26017/100000 [7:51:17<12:02:18,  1.71it/s]
Train steps ... :  26%|██▌       | 26018/100000 [7:51:17<12:02:40,  1.71it/s]
Train steps ... :  26%|██▌       | 26019/100000 [7:51:18<12:02:04,  1.71it/s]
Train steps ... :  26%|██▌       | 26020/100000 [7:51:18<12:02:21,  1.71it/s]
Train steps ... :  26%|██▌       | 26021/100000 [7:51:19<12:01:26,  1.71it/s]
Train steps ... :  26%|██▌       | 26022/100000 [7:51:19<12:00:28,  1.71it/s]
Train steps ... :  26%|██▌       | 26023/100000 [7:51:20<12:00:35,  1.71it/s]
Train steps ... :  26%|██▌       | 26024/100000 [7:51:21<12:02:12,  1.71it/s]
Train steps ... :  26%|██▌       | 26025/100000 [7:51:21<12:01:05,  1.71it/s]Step... (26025 / 100000 | Loss: 1.276475191116333, Learning Rate: 7.434673366834172e-05)
+
                                                                             
Step... (26025 / 100000 | Loss: 1.14516282081604, Learning Rate: 7.434673366834172e-05)
+
Train steps ... :  26%|██▌       | 26025/100000 [7:51:22<12:01:05,  1.71it/s]
Train steps ... :  26%|██▌       | 26026/100000 [7:51:22<12:01:55,  1.71it/s]
Train steps ... :  26%|██▌       | 26027/100000 [7:51:22<12:02:57,  1.71it/s]
Train steps ... :  26%|██▌       | 26028/100000 [7:51:23<12:02:40,  1.71it/s]
Train steps ... :  26%|██▌       | 26029/100000 [7:51:24<12:04:14,  1.70it/s]
Train steps ... :  26%|██▌       | 26030/100000 [7:51:24<12:03:09,  1.70it/s]
Train steps ... :  26%|██▌       | 26031/100000 [7:51:25<12:04:47,  1.70it/s]
Train steps ... :  26%|██▌       | 26032/100000 [7:51:25<12:03:18,  1.70it/s]
Train steps ... :  26%|██▌       | 26033/100000 [7:51:26<12:01:35,  1.71it/s]
Train steps ... :  26%|██▌       | 26034/100000 [7:51:26<12:00:54,  1.71it/s]
Train steps ... :  26%|██▌       | 26035/100000 [7:51:27<12:01:02,  1.71it/s]
Train steps ... :  26%|██▌       | 26036/100000 [7:51:28<12:00:32,  1.71it/s]
Train steps ... :  26%|██▌       | 26037/100000 [7:51:28<12:02:11,  1.71it/s]
Train steps ... :  26%|██▌       | 26038/100000 [7:51:29<12:00:27,  1.71it/s]
Train steps ... :  26%|██▌       | 26039/100000 [7:51:29<11:59:45,  1.71it/s]
Train steps ... :  26%|██▌       | 26040/100000 [7:51:30<11:59:48,  1.71it/s]
Train steps ... :  26%|██▌       | 26041/100000 [7:51:31<12:00:28,  1.71it/s]
Train steps ... :  26%|██▌       | 26042/100000 [7:51:31<12:00:08,  1.71it/s]
Train steps ... :  26%|██▌       | 26043/100000 [7:51:32<11:59:46,  1.71it/s]
Train steps ... :  26%|██▌       | 26044/100000 [7:51:32<11:59:50,  1.71it/s]
Train steps ... :  26%|██▌       | 26045/100000 [7:51:33<12:00:41,  1.71it/s]
Train steps ... :  26%|██▌       | 26046/100000 [7:51:33<12:01:56,  1.71it/s]
Train steps ... :  26%|██▌       | 26047/100000 [7:51:34<12:02:19,  1.71it/s]
Train steps ... :  26%|██▌       | 26048/100000 [7:51:35<12:01:39,  1.71it/s]
Train steps ... :  26%|██▌       | 26049/100000 [7:51:35<12:00:23,  1.71it/s]
Train steps ... :  26%|██▌       | 26050/100000 [7:51:36<12:01:01,  1.71it/s]Step... (26050 / 100000 | Loss: 0.9188627004623413, Learning Rate: 7.4321608040201e-05)
+
                                                                             
Step... (26050 / 100000 | Loss: 0.6909140348434448, Learning Rate: 7.4321608040201e-05)
+
Train steps ... :  26%|██▌       | 26050/100000 [7:51:36<12:01:01,  1.71it/s]
Train steps ... :  26%|██▌       | 26051/100000 [7:51:36<12:01:15,  1.71it/s]
Train steps ... :  26%|██▌       | 26052/100000 [7:51:37<12:01:43,  1.71it/s]
Train steps ... :  26%|██▌       | 26053/100000 [7:51:38<12:04:42,  1.70it/s]
Train steps ... :  26%|██▌       | 26054/100000 [7:51:38<12:02:36,  1.71it/s]
Train steps ... :  26%|██▌       | 26055/100000 [7:51:39<12:02:43,  1.71it/s]
Train steps ... :  26%|██▌       | 26056/100000 [7:51:39<12:01:52,  1.71it/s]
Train steps ... :  26%|██▌       | 26057/100000 [7:51:40<12:01:58,  1.71it/s]
Train steps ... :  26%|██▌       | 26058/100000 [7:51:41<12:01:49,  1.71it/s]
Train steps ... :  26%|██▌       | 26059/100000 [7:51:41<12:01:27,  1.71it/s]
Train steps ... :  26%|██▌       | 26060/100000 [7:51:42<12:01:20,  1.71it/s]
Train steps ... :  26%|██▌       | 26061/100000 [7:51:42<12:01:24,  1.71it/s]
Train steps ... :  26%|██▌       | 26062/100000 [7:51:43<12:01:38,  1.71it/s]
Train steps ... :  26%|██▌       | 26063/100000 [7:51:43<12:02:00,  1.71it/s]
Train steps ... :  26%|██▌       | 26064/100000 [7:51:44<12:01:23,  1.71it/s]
Train steps ... :  26%|██▌       | 26065/100000 [7:51:45<12:02:44,  1.70it/s]
Train steps ... :  26%|██▌       | 26066/100000 [7:51:45<12:02:52,  1.70it/s]
Train steps ... :  26%|██▌       | 26067/100000 [7:51:46<12:01:50,  1.71it/s]
Train steps ... :  26%|██▌       | 26068/100000 [7:51:46<12:01:10,  1.71it/s]
Train steps ... :  26%|██▌       | 26069/100000 [7:51:47<12:01:56,  1.71it/s]
Train steps ... :  26%|██▌       | 26070/100000 [7:51:48<12:00:55,  1.71it/s]
Train steps ... :  26%|██▌       | 26071/100000 [7:51:48<12:00:25,  1.71it/s]
Train steps ... :  26%|██▌       | 26072/100000 [7:51:49<12:02:12,  1.71it/s]
Train steps ... :  26%|██▌       | 26073/100000 [7:51:49<12:02:03,  1.71it/s]
Train steps ... :  26%|██▌       | 26074/100000 [7:51:50<12:01:35,  1.71it/s]
Train steps ... :  26%|██▌       | 26075/100000 [7:51:50<12:02:11,  1.71it/s]Step... (26075 / 100000 | Loss: 1.0324485301971436, Learning Rate: 7.429648241206031e-05)
+
                                                                             
Step... (26075 / 100000 | Loss: 0.9771898984909058, Learning Rate: 7.429648241206031e-05)
+
Train steps ... :  26%|██▌       | 26075/100000 [7:51:51<12:02:11,  1.71it/s]
Train steps ... :  26%|██▌       | 26076/100000 [7:51:51<12:01:56,  1.71it/s]
Train steps ... :  26%|██▌       | 26077/100000 [7:51:52<12:02:43,  1.70it/s]
Train steps ... :  26%|██▌       | 26078/100000 [7:51:52<12:01:49,  1.71it/s]
Train steps ... :  26%|██▌       | 26079/100000 [7:51:53<12:01:11,  1.71it/s]
Train steps ... :  26%|██▌       | 26080/100000 [7:51:53<12:01:01,  1.71it/s]
Train steps ... :  26%|██▌       | 26081/100000 [7:51:54<12:02:17,  1.71it/s]
Train steps ... :  26%|██▌       | 26082/100000 [7:51:55<12:01:35,  1.71it/s]
Train steps ... :  26%|██▌       | 26083/100000 [7:51:55<12:02:21,  1.71it/s]
Train steps ... :  26%|██▌       | 26084/100000 [7:51:56<12:03:54,  1.70it/s]
Train steps ... :  26%|██▌       | 26085/100000 [7:51:56<12:03:50,  1.70it/s]
Train steps ... :  26%|██▌       | 26086/100000 [7:51:57<12:03:29,  1.70it/s]
Train steps ... :  26%|██▌       | 26087/100000 [7:51:58<12:03:46,  1.70it/s]
Train steps ... :  26%|██▌       | 26088/100000 [7:51:58<12:01:54,  1.71it/s]
Train steps ... :  26%|██▌       | 26089/100000 [7:51:59<12:00:57,  1.71it/s]
Train steps ... :  26%|██▌       | 26090/100000 [7:51:59<12:03:44,  1.70it/s]
Train steps ... :  26%|██▌       | 26091/100000 [7:52:00<12:00:16,  1.71it/s]
Train steps ... :  26%|██▌       | 26092/100000 [7:52:00<12:00:00,  1.71it/s]
Train steps ... :  26%|██▌       | 26093/100000 [7:52:01<12:01:21,  1.71it/s]
Train steps ... :  26%|██▌       | 26094/100000 [7:52:02<12:01:01,  1.71it/s]
Train steps ... :  26%|██▌       | 26095/100000 [7:52:02<12:00:47,  1.71it/s]
Train steps ... :  26%|██▌       | 26096/100000 [7:52:03<12:00:08,  1.71it/s]
Train steps ... :  26%|██▌       | 26097/100000 [7:52:03<12:00:35,  1.71it/s]
Train steps ... :  26%|██▌       | 26098/100000 [7:52:04<12:00:45,  1.71it/s]
Train steps ... :  26%|██▌       | 26099/100000 [7:52:05<11:59:52,  1.71it/s]
Train steps ... :  26%|██▌       | 26100/100000 [7:52:05<12:01:03,  1.71it/s]Step... (26100 / 100000 | Loss: 0.9088196754455566, Learning Rate: 7.42713567839196e-05)
+
                                                                             
Step... (26100 / 100000 | Loss: 1.0262949466705322, Learning Rate: 7.42713567839196e-05)
+
Train steps ... :  26%|██▌       | 26100/100000 [7:52:05<12:01:03,  1.71it/s]
Train steps ... :  26%|██▌       | 26101/100000 [7:52:06<12:01:45,  1.71it/s]
Train steps ... :  26%|██▌       | 26102/100000 [7:52:06<12:00:42,  1.71it/s]
Train steps ... :  26%|██▌       | 26103/100000 [7:52:07<12:00:25,  1.71it/s]
Train steps ... :  26%|██▌       | 26104/100000 [7:52:07<12:02:55,  1.70it/s]
Train steps ... :  26%|██▌       | 26105/100000 [7:52:08<11:59:40,  1.71it/s]
Train steps ... :  26%|██▌       | 26106/100000 [7:52:09<12:00:09,  1.71it/s]
Train steps ... :  26%|██▌       | 26107/100000 [7:52:09<12:00:59,  1.71it/s]
Train steps ... :  26%|██▌       | 26108/100000 [7:52:10<12:00:24,  1.71it/s]
Train steps ... :  26%|██▌       | 26109/100000 [7:52:10<12:00:13,  1.71it/s]
Train steps ... :  26%|██▌       | 26110/100000 [7:52:11<12:00:06,  1.71it/s]
Train steps ... :  26%|██▌       | 26111/100000 [7:52:12<12:00:34,  1.71it/s]
Train steps ... :  26%|██▌       | 26112/100000 [7:52:12<12:01:21,  1.71it/s]
Train steps ... :  26%|██▌       | 26113/100000 [7:52:13<12:00:39,  1.71it/s]
Train steps ... :  26%|██▌       | 26114/100000 [7:52:13<12:00:42,  1.71it/s]
Train steps ... :  26%|██▌       | 26115/100000 [7:52:14<12:01:07,  1.71it/s]
Train steps ... :  26%|██▌       | 26116/100000 [7:52:14<12:00:41,  1.71it/s]
Train steps ... :  26%|██▌       | 26117/100000 [7:52:15<12:00:01,  1.71it/s]
Train steps ... :  26%|██▌       | 26118/100000 [7:52:16<12:00:32,  1.71it/s]
Train steps ... :  26%|██▌       | 26119/100000 [7:52:16<12:01:07,  1.71it/s]
Train steps ... :  26%|██▌       | 26120/100000 [7:52:17<12:01:49,  1.71it/s]
Train steps ... :  26%|██▌       | 26121/100000 [7:52:17<12:00:32,  1.71it/s]
Train steps ... :  26%|██▌       | 26122/100000 [7:52:18<12:00:55,  1.71it/s]
Train steps ... :  26%|██▌       | 26123/100000 [7:52:19<12:00:29,  1.71it/s]
Train steps ... :  26%|██▌       | 26124/100000 [7:52:19<12:00:42,  1.71it/s]
Train steps ... :  26%|██▌       | 26125/100000 [7:52:20<11:59:30,  1.71it/s]Step... (26125 / 100000 | Loss: 1.2516119480133057, Learning Rate: 7.42462311557789e-05)
+
                                                                             
Step... (26125 / 100000 | Loss: 1.0457873344421387, Learning Rate: 7.42462311557789e-05)
+
Train steps ... :  26%|██▌       | 26125/100000 [7:52:20<11:59:30,  1.71it/s]
Train steps ... :  26%|██▌       | 26126/100000 [7:52:20<12:00:46,  1.71it/s]
Train steps ... :  26%|██▌       | 26127/100000 [7:52:21<12:00:31,  1.71it/s]
Train steps ... :  26%|██▌       | 26128/100000 [7:52:21<11:59:26,  1.71it/s]
Train steps ... :  26%|██▌       | 26129/100000 [7:52:22<11:59:28,  1.71it/s]
Train steps ... :  26%|██▌       | 26130/100000 [7:52:23<11:59:43,  1.71it/s]
Train steps ... :  26%|██▌       | 26131/100000 [7:52:23<11:59:03,  1.71it/s]
Train steps ... :  26%|██▌       | 26132/100000 [7:52:24<11:58:52,  1.71it/s]
Train steps ... :  26%|██▌       | 26133/100000 [7:52:24<11:59:21,  1.71it/s]
Train steps ... :  26%|██▌       | 26134/100000 [7:52:25<11:59:15,  1.71it/s]
Train steps ... :  26%|██▌       | 26135/100000 [7:52:26<11:59:33,  1.71it/s]
Train steps ... :  26%|██▌       | 26136/100000 [7:52:26<12:00:34,  1.71it/s]
Train steps ... :  26%|██▌       | 26137/100000 [7:52:27<12:01:08,  1.71it/s]
Train steps ... :  26%|██▌       | 26138/100000 [7:52:27<12:00:18,  1.71it/s]
Train steps ... :  26%|██▌       | 26139/100000 [7:52:28<11:59:55,  1.71it/s]
Train steps ... :  26%|██▌       | 26140/100000 [7:52:29<11:59:25,  1.71it/s]
Train steps ... :  26%|██▌       | 26141/100000 [7:52:29<12:00:00,  1.71it/s]
Train steps ... :  26%|██▌       | 26142/100000 [7:52:30<11:59:45,  1.71it/s]
Train steps ... :  26%|██▌       | 26143/100000 [7:52:30<12:00:25,  1.71it/s]
Train steps ... :  26%|██▌       | 26144/100000 [7:52:31<12:00:18,  1.71it/s]
Train steps ... :  26%|██▌       | 26145/100000 [7:52:31<11:59:52,  1.71it/s]
Train steps ... :  26%|██▌       | 26146/100000 [7:52:32<11:59:27,  1.71it/s]
Train steps ... :  26%|██▌       | 26147/100000 [7:52:33<11:59:36,  1.71it/s]
Train steps ... :  26%|██▌       | 26148/100000 [7:52:33<11:59:09,  1.71it/s]
Train steps ... :  26%|██▌       | 26149/100000 [7:52:34<11:58:50,  1.71it/s]
Train steps ... :  26%|██▌       | 26150/100000 [7:52:34<11:59:02,  1.71it/s]Step... (26150 / 100000 | Loss: 0.7127915024757385, Learning Rate: 7.422110552763819e-05)
+
                                                                             
Step... (26150 / 100000 | Loss: 0.8352352380752563, Learning Rate: 7.422110552763819e-05)
+
Train steps ... :  26%|██▌       | 26150/100000 [7:52:35<11:59:02,  1.71it/s]
Train steps ... :  26%|██▌       | 26151/100000 [7:52:35<12:00:31,  1.71it/s]
Train steps ... :  26%|██▌       | 26152/100000 [7:52:36<11:59:41,  1.71it/s]
Train steps ... :  26%|██▌       | 26153/100000 [7:52:36<11:59:10,  1.71it/s]
Train steps ... :  26%|██▌       | 26154/100000 [7:52:37<11:59:38,  1.71it/s]
Train steps ... :  26%|██▌       | 26155/100000 [7:52:37<11:58:39,  1.71it/s]
Train steps ... :  26%|██▌       | 26156/100000 [7:52:38<11:59:18,  1.71it/s]
Train steps ... :  26%|██▌       | 26157/100000 [7:52:38<11:59:50,  1.71it/s]
Train steps ... :  26%|██▌       | 26158/100000 [7:52:39<11:59:23,  1.71it/s]
Train steps ... :  26%|██▌       | 26159/100000 [7:52:40<11:59:48,  1.71it/s]
Train steps ... :  26%|██▌       | 26160/100000 [7:52:40<11:59:35,  1.71it/s]
Train steps ... :  26%|██▌       | 26161/100000 [7:52:41<11:58:56,  1.71it/s]
Train steps ... :  26%|██▌       | 26162/100000 [7:52:41<11:58:49,  1.71it/s]
Train steps ... :  26%|██▌       | 26163/100000 [7:52:42<11:58:50,  1.71it/s]
Train steps ... :  26%|██▌       | 26164/100000 [7:52:43<11:59:18,  1.71it/s]
Train steps ... :  26%|██▌       | 26165/100000 [7:52:43<11:59:58,  1.71it/s]
Train steps ... :  26%|██▌       | 26166/100000 [7:52:44<12:01:43,  1.71it/s]
Train steps ... :  26%|██▌       | 26167/100000 [7:52:44<11:58:55,  1.71it/s]
Train steps ... :  26%|██▌       | 26168/100000 [7:52:45<11:59:24,  1.71it/s]
Train steps ... :  26%|██▌       | 26169/100000 [7:52:45<11:59:53,  1.71it/s]
Train steps ... :  26%|██▌       | 26170/100000 [7:52:46<11:59:17,  1.71it/s]
Train steps ... :  26%|██▌       | 26171/100000 [7:52:47<11:59:30,  1.71it/s]
Train steps ... :  26%|██▌       | 26172/100000 [7:52:47<11:59:14,  1.71it/s]
Train steps ... :  26%|██▌       | 26173/100000 [7:52:48<11:58:23,  1.71it/s]
Train steps ... :  26%|██▌       | 26174/100000 [7:52:48<11:58:35,  1.71it/s]
Train steps ... :  26%|██▌       | 26175/100000 [7:52:49<11:58:14,  1.71it/s]Step... (26175 / 100000 | Loss: 1.0155048370361328, Learning Rate: 7.419597989949749e-05)
+
                                                                             
Step... (26175 / 100000 | Loss: 1.5087125301361084, Learning Rate: 7.419597989949749e-05)
+
Train steps ... :  26%|██▌       | 26175/100000 [7:52:49<11:58:14,  1.71it/s]
Train steps ... :  26%|██▌       | 26176/100000 [7:52:50<11:58:16,  1.71it/s]
Train steps ... :  26%|██▌       | 26177/100000 [7:52:50<11:58:51,  1.71it/s]
Train steps ... :  26%|██▌       | 26178/100000 [7:52:51<11:59:19,  1.71it/s]
Train steps ... :  26%|██▌       | 26179/100000 [7:52:51<11:58:43,  1.71it/s]
Train steps ... :  26%|██▌       | 26180/100000 [7:52:52<11:58:36,  1.71it/s]
Train steps ... :  26%|██▌       | 26181/100000 [7:52:52<11:58:47,  1.71it/s]
Train steps ... :  26%|██▌       | 26182/100000 [7:52:53<11:58:26,  1.71it/s]
Train steps ... :  26%|██▌       | 26183/100000 [7:52:54<11:58:57,  1.71it/s]
Train steps ... :  26%|██▌       | 26184/100000 [7:52:54<11:59:17,  1.71it/s]
Train steps ... :  26%|██▌       | 26185/100000 [7:52:55<11:59:13,  1.71it/s]
Train steps ... :  26%|██▌       | 26186/100000 [7:52:55<11:59:20,  1.71it/s]
Train steps ... :  26%|██▌       | 26187/100000 [7:52:56<11:59:00,  1.71it/s]
Train steps ... :  26%|██▌       | 26188/100000 [7:52:57<11:59:46,  1.71it/s]
Train steps ... :  26%|██▌       | 26189/100000 [7:52:57<11:59:11,  1.71it/s]
Train steps ... :  26%|██▌       | 26190/100000 [7:52:58<11:59:53,  1.71it/s]
Train steps ... :  26%|██▌       | 26191/100000 [7:52:58<12:00:48,  1.71it/s]
Train steps ... :  26%|██▌       | 26192/100000 [7:52:59<11:59:52,  1.71it/s]
Train steps ... :  26%|██▌       | 26193/100000 [7:52:59<12:00:23,  1.71it/s]
Train steps ... :  26%|██▌       | 26194/100000 [7:53:00<12:00:40,  1.71it/s]
Train steps ... :  26%|██▌       | 26195/100000 [7:53:01<11:59:29,  1.71it/s]
Train steps ... :  26%|██▌       | 26196/100000 [7:53:01<11:59:03,  1.71it/s]
Train steps ... :  26%|██▌       | 26197/100000 [7:53:02<11:58:19,  1.71it/s]
Train steps ... :  26%|██▌       | 26198/100000 [7:53:02<11:58:25,  1.71it/s]
Train steps ... :  26%|██▌       | 26199/100000 [7:53:03<11:59:00,  1.71it/s]
Train steps ... :  26%|██▌       | 26200/100000 [7:53:04<11:58:36,  1.71it/s]Step... (26200 / 100000 | Loss: 0.8087785243988037, Learning Rate: 7.417085427135678e-05)
+
                                                                             
Step... (26200 / 100000 | Loss: 1.3135626316070557, Learning Rate: 7.417085427135678e-05)
+
Train steps ... :  26%|██▌       | 26200/100000 [7:53:04<11:58:36,  1.71it/s]
Train steps ... :  26%|██▌       | 26201/100000 [7:53:04<11:59:12,  1.71it/s]
Train steps ... :  26%|██▌       | 26202/100000 [7:53:05<11:58:26,  1.71it/s]
Train steps ... :  26%|██▌       | 26203/100000 [7:53:05<11:58:50,  1.71it/s]
Train steps ... :  26%|██▌       | 26204/100000 [7:53:06<11:58:38,  1.71it/s]
Train steps ... :  26%|██▌       | 26205/100000 [7:53:07<11:59:43,  1.71it/s]
Train steps ... :  26%|██▌       | 26206/100000 [7:53:07<11:59:30,  1.71it/s]
Train steps ... :  26%|██▌       | 26207/100000 [7:53:08<11:59:04,  1.71it/s]
Train steps ... :  26%|██▌       | 26208/100000 [7:53:08<11:59:04,  1.71it/s]
Train steps ... :  26%|██▌       | 26209/100000 [7:53:09<11:58:51,  1.71it/s]
Train steps ... :  26%|██▌       | 26210/100000 [7:53:09<11:58:14,  1.71it/s]
Train steps ... :  26%|██▌       | 26211/100000 [7:53:10<11:58:11,  1.71it/s]
Train steps ... :  26%|██▌       | 26212/100000 [7:53:11<11:58:33,  1.71it/s]
Train steps ... :  26%|██▌       | 26213/100000 [7:53:11<12:00:33,  1.71it/s]
Train steps ... :  26%|██▌       | 26214/100000 [7:53:12<11:59:58,  1.71it/s]
Train steps ... :  26%|██▌       | 26215/100000 [7:53:12<11:59:37,  1.71it/s]
Train steps ... :  26%|██▌       | 26216/100000 [7:53:13<11:59:35,  1.71it/s]
Train steps ... :  26%|██▌       | 26217/100000 [7:53:14<11:59:04,  1.71it/s]
Train steps ... :  26%|██▌       | 26218/100000 [7:53:14<11:58:08,  1.71it/s]
Train steps ... :  26%|██▌       | 26219/100000 [7:53:15<11:57:54,  1.71it/s]
Train steps ... :  26%|██▌       | 26220/100000 [7:53:15<11:57:45,  1.71it/s]
Train steps ... :  26%|██▌       | 26221/100000 [7:53:16<11:58:04,  1.71it/s]
Train steps ... :  26%|██▌       | 26222/100000 [7:53:16<11:59:03,  1.71it/s]
Train steps ... :  26%|██▌       | 26223/100000 [7:53:17<11:58:54,  1.71it/s]
Train steps ... :  26%|██▌       | 26224/100000 [7:53:18<11:59:03,  1.71it/s]
Train steps ... :  26%|██▌       | 26225/100000 [7:53:18<11:57:56,  1.71it/s]Step... (26225 / 100000 | Loss: 1.1599173545837402, Learning Rate: 7.414572864321608e-05)
+
                                                                             
Step... (26225 / 100000 | Loss: 1.0583524703979492, Learning Rate: 7.414572864321608e-05)
+
Train steps ... :  26%|██▌       | 26225/100000 [7:53:19<11:57:56,  1.71it/s]
Train steps ... :  26%|██▌       | 26226/100000 [7:53:19<11:58:26,  1.71it/s]
Train steps ... :  26%|██▌       | 26227/100000 [7:53:19<11:58:02,  1.71it/s]
Train steps ... :  26%|██▌       | 26228/100000 [7:53:20<11:58:21,  1.71it/s]
Train steps ... :  26%|██▌       | 26229/100000 [7:53:21<11:57:47,  1.71it/s]
Train steps ... :  26%|██▌       | 26230/100000 [7:53:21<11:58:13,  1.71it/s]
Train steps ... :  26%|██▌       | 26231/100000 [7:53:22<11:58:10,  1.71it/s]
Train steps ... :  26%|██▌       | 26232/100000 [7:53:22<11:58:03,  1.71it/s]
Train steps ... :  26%|██▌       | 26233/100000 [7:53:23<11:57:31,  1.71it/s]
Train steps ... :  26%|██▌       | 26234/100000 [7:53:23<11:57:43,  1.71it/s]
Train steps ... :  26%|██▌       | 26235/100000 [7:53:24<11:58:26,  1.71it/s]
Train steps ... :  26%|██▌       | 26236/100000 [7:53:25<11:57:46,  1.71it/s]
Train steps ... :  26%|██▌       | 26237/100000 [7:53:25<11:58:03,  1.71it/s]
Train steps ... :  26%|██▌       | 26238/100000 [7:53:26<11:58:04,  1.71it/s]
Train steps ... :  26%|██▌       | 26239/100000 [7:53:26<11:57:45,  1.71it/s]
Train steps ... :  26%|██▌       | 26240/100000 [7:53:27<12:00:10,  1.71it/s]
Train steps ... :  26%|██▌       | 26241/100000 [7:53:28<12:00:13,  1.71it/s]
Train steps ... :  26%|██▌       | 26242/100000 [7:53:28<11:58:58,  1.71it/s]
Train steps ... :  26%|██▌       | 26243/100000 [7:53:29<11:59:50,  1.71it/s]
Train steps ... :  26%|██▌       | 26244/100000 [7:53:29<11:59:40,  1.71it/s]
Train steps ... :  26%|██▌       | 26245/100000 [7:53:30<11:58:49,  1.71it/s]
Train steps ... :  26%|██▌       | 26246/100000 [7:53:30<11:59:00,  1.71it/s]
Train steps ... :  26%|██▌       | 26247/100000 [7:53:31<11:58:30,  1.71it/s]
Train steps ... :  26%|██▌       | 26248/100000 [7:53:32<11:58:25,  1.71it/s]
Train steps ... :  26%|██▌       | 26249/100000 [7:53:32<11:57:32,  1.71it/s]
Train steps ... :  26%|██▋       | 26250/100000 [7:53:33<11:57:48,  1.71it/s]Step... (26250 / 100000 | Loss: 0.8342490792274475, Learning Rate: 7.412060301507539e-05)
+
                                                                             
Step... (26250 / 100000 | Loss: 1.153395652770996, Learning Rate: 7.412060301507539e-05)
+
Train steps ... :  26%|██▋       | 26250/100000 [7:53:33<11:57:48,  1.71it/s]
Train steps ... :  26%|██▋       | 26251/100000 [7:53:33<11:59:06,  1.71it/s]
Train steps ... :  26%|██▋       | 26252/100000 [7:53:34<11:59:40,  1.71it/s]
Train steps ... :  26%|██▋       | 26253/100000 [7:53:35<11:59:41,  1.71it/s]
Train steps ... :  26%|██▋       | 26254/100000 [7:53:35<11:58:44,  1.71it/s]
Train steps ... :  26%|██▋       | 26255/100000 [7:53:36<11:58:15,  1.71it/s]
Train steps ... :  26%|██▋       | 26256/100000 [7:53:36<11:59:01,  1.71it/s]
Train steps ... :  26%|██▋       | 26257/100000 [7:53:37<12:00:24,  1.71it/s]
Train steps ... :  26%|██▋       | 26258/100000 [7:53:37<12:00:13,  1.71it/s]
Train steps ... :  26%|██▋       | 26259/100000 [7:53:38<11:59:37,  1.71it/s]
Train steps ... :  26%|██▋       | 26260/100000 [7:53:39<12:00:34,  1.71it/s]
Train steps ... :  26%|██▋       | 26261/100000 [7:53:39<11:58:38,  1.71it/s]
Train steps ... :  26%|██▋       | 26262/100000 [7:53:40<11:58:13,  1.71it/s]
Train steps ... :  26%|██▋       | 26263/100000 [7:53:40<11:58:07,  1.71it/s]
Train steps ... :  26%|██▋       | 26264/100000 [7:53:41<11:58:06,  1.71it/s]
Train steps ... :  26%|██▋       | 26265/100000 [7:53:42<11:57:43,  1.71it/s]
Train steps ... :  26%|██▋       | 26266/100000 [7:53:42<11:58:10,  1.71it/s]
Train steps ... :  26%|██▋       | 26267/100000 [7:53:43<11:57:54,  1.71it/s]
Train steps ... :  26%|██▋       | 26268/100000 [7:53:43<11:58:43,  1.71it/s]
Train steps ... :  26%|██▋       | 26269/100000 [7:53:44<11:58:38,  1.71it/s]
Train steps ... :  26%|██▋       | 26270/100000 [7:53:45<11:58:43,  1.71it/s]
Train steps ... :  26%|██▋       | 26271/100000 [7:53:45<11:58:01,  1.71it/s]
Train steps ... :  26%|██▋       | 26272/100000 [7:53:46<11:57:22,  1.71it/s]
Train steps ... :  26%|██▋       | 26273/100000 [7:53:46<11:57:49,  1.71it/s]
Train steps ... :  26%|██▋       | 26274/100000 [7:53:47<11:56:56,  1.71it/s]
Train steps ... :  26%|██▋       | 26275/100000 [7:53:47<11:59:08,  1.71it/s]Step... (26275 / 100000 | Loss: 1.2366409301757812, Learning Rate: 7.409547738693467e-05)
+
                                                                             
Step... (26275 / 100000 | Loss: 0.9172029495239258, Learning Rate: 7.409547738693467e-05)
+
Train steps ... :  26%|██▋       | 26275/100000 [7:53:48<11:59:08,  1.71it/s]
Train steps ... :  26%|██▋       | 26276/100000 [7:53:48<11:58:17,  1.71it/s]
Train steps ... :  26%|██▋       | 26277/100000 [7:53:49<11:58:10,  1.71it/s]
Train steps ... :  26%|██▋       | 26278/100000 [7:53:49<11:58:00,  1.71it/s]
Train steps ... :  26%|██▋       | 26279/100000 [7:53:50<11:58:02,  1.71it/s]
Train steps ... :  26%|██▋       | 26280/100000 [7:53:50<11:59:08,  1.71it/s]
Train steps ... :  26%|██▋       | 26281/100000 [7:53:51<11:59:23,  1.71it/s]
Train steps ... :  26%|██▋       | 26282/100000 [7:53:52<11:58:36,  1.71it/s]
Train steps ... :  26%|██▋       | 26283/100000 [7:53:52<11:57:55,  1.71it/s]
Train steps ... :  26%|██▋       | 26284/100000 [7:53:53<11:57:58,  1.71it/s]
Train steps ... :  26%|██▋       | 26285/100000 [7:53:53<11:57:29,  1.71it/s]
Train steps ... :  26%|██▋       | 26286/100000 [7:53:54<11:57:33,  1.71it/s]
Train steps ... :  26%|██▋       | 26287/100000 [7:53:54<11:57:12,  1.71it/s]
Train steps ... :  26%|██▋       | 26288/100000 [7:53:55<11:57:24,  1.71it/s]
Train steps ... :  26%|██▋       | 26289/100000 [7:53:56<11:57:23,  1.71it/s]
Train steps ... :  26%|██▋       | 26290/100000 [7:53:56<11:57:13,  1.71it/s]
Train steps ... :  26%|██▋       | 26291/100000 [7:53:57<11:58:51,  1.71it/s]
Train steps ... :  26%|██▋       | 26292/100000 [7:53:57<11:56:11,  1.72it/s]
Train steps ... :  26%|██▋       | 26293/100000 [7:53:58<11:56:25,  1.71it/s]
Train steps ... :  26%|██▋       | 26294/100000 [7:53:59<11:56:27,  1.71it/s]
Train steps ... :  26%|██▋       | 26295/100000 [7:53:59<11:56:24,  1.71it/s]
Train steps ... :  26%|██▋       | 26296/100000 [7:54:00<11:56:29,  1.71it/s]
Train steps ... :  26%|██▋       | 26297/100000 [7:54:00<11:56:16,  1.71it/s]
Train steps ... :  26%|██▋       | 26298/100000 [7:54:01<11:56:11,  1.72it/s]
Train steps ... :  26%|██▋       | 26299/100000 [7:54:01<11:56:29,  1.71it/s]
Train steps ... :  26%|██▋       | 26300/100000 [7:54:02<11:56:51,  1.71it/s]Step... (26300 / 100000 | Loss: 0.8716118335723877, Learning Rate: 7.407035175879398e-05)
+
                                                                             
Step... (26300 / 100000 | Loss: 1.039184331893921, Learning Rate: 7.407035175879398e-05)
+
Train steps ... :  26%|██▋       | 26300/100000 [7:54:02<11:56:51,  1.71it/s]
Train steps ... :  26%|██▋       | 26301/100000 [7:54:03<11:57:09,  1.71it/s]
Train steps ... :  26%|██▋       | 26302/100000 [7:54:03<11:57:00,  1.71it/s]
Train steps ... :  26%|██▋       | 26303/100000 [7:54:04<11:56:56,  1.71it/s]
Train steps ... :  26%|██▋       | 26304/100000 [7:54:04<11:57:06,  1.71it/s]
Train steps ... :  26%|██▋       | 26305/100000 [7:54:05<11:57:40,  1.71it/s]
Train steps ... :  26%|██▋       | 26306/100000 [7:54:06<11:57:31,  1.71it/s]
Train steps ... :  26%|██▋       | 26307/100000 [7:54:06<11:57:09,  1.71it/s]
Train steps ... :  26%|██▋       | 26308/100000 [7:54:07<11:58:03,  1.71it/s]
Train steps ... :  26%|██▋       | 26309/100000 [7:54:07<11:57:57,  1.71it/s]
Train steps ... :  26%|██▋       | 26310/100000 [7:54:08<11:57:58,  1.71it/s]
Train steps ... :  26%|██▋       | 26311/100000 [7:54:08<11:58:05,  1.71it/s]
Train steps ... :  26%|██▋       | 26312/100000 [7:54:09<11:57:30,  1.71it/s]
Train steps ... :  26%|██▋       | 26313/100000 [7:54:10<11:56:52,  1.71it/s]
Train steps ... :  26%|██▋       | 26314/100000 [7:54:10<11:57:20,  1.71it/s]
Train steps ... :  26%|██▋       | 26315/100000 [7:54:11<11:56:48,  1.71it/s]
Train steps ... :  26%|██▋       | 26316/100000 [7:54:11<11:57:04,  1.71it/s]
Train steps ... :  26%|██▋       | 26317/100000 [7:54:12<11:56:37,  1.71it/s]
Train steps ... :  26%|██▋       | 26318/100000 [7:54:13<11:58:00,  1.71it/s]
Train steps ... :  26%|██▋       | 26319/100000 [7:54:13<11:57:36,  1.71it/s]
Train steps ... :  26%|██▋       | 26320/100000 [7:54:14<11:58:00,  1.71it/s]
Train steps ... :  26%|██▋       | 26321/100000 [7:54:14<11:58:32,  1.71it/s]
Train steps ... :  26%|██▋       | 26322/100000 [7:54:15<11:57:31,  1.71it/s]
Train steps ... :  26%|██▋       | 26323/100000 [7:54:15<11:58:26,  1.71it/s]
Train steps ... :  26%|██▋       | 26324/100000 [7:54:16<11:57:42,  1.71it/s]
Train steps ... :  26%|██▋       | 26325/100000 [7:54:17<11:58:11,  1.71it/s]Step... (26325 / 100000 | Loss: 0.6965480446815491, Learning Rate: 7.404522613065327e-05)
+
                                                                             
Step... (26325 / 100000 | Loss: 0.9285296201705933, Learning Rate: 7.404522613065327e-05)
+
Train steps ... :  26%|██▋       | 26325/100000 [7:54:17<11:58:11,  1.71it/s]
Train steps ... :  26%|██▋       | 26326/100000 [7:54:17<11:59:44,  1.71it/s]
Train steps ... :  26%|██▋       | 26327/100000 [7:54:18<11:58:43,  1.71it/s]
Train steps ... :  26%|██▋       | 26328/100000 [7:54:18<11:58:37,  1.71it/s]
Train steps ... :  26%|██▋       | 26329/100000 [7:54:19<11:58:53,  1.71it/s]
Train steps ... :  26%|██▋       | 26330/100000 [7:54:20<11:57:59,  1.71it/s]
Train steps ... :  26%|██▋       | 26331/100000 [7:54:20<11:57:53,  1.71it/s]
Train steps ... :  26%|██▋       | 26332/100000 [7:54:21<11:57:46,  1.71it/s]
Train steps ... :  26%|██▋       | 26333/100000 [7:54:21<11:57:05,  1.71it/s]
Train steps ... :  26%|██▋       | 26334/100000 [7:54:22<11:57:37,  1.71it/s]
Train steps ... :  26%|██▋       | 26335/100000 [7:54:22<11:57:56,  1.71it/s]
Train steps ... :  26%|██▋       | 26336/100000 [7:54:23<11:57:40,  1.71it/s]
Train steps ... :  26%|██▋       | 26337/100000 [7:54:24<11:57:31,  1.71it/s]
Train steps ... :  26%|██▋       | 26338/100000 [7:54:24<11:58:04,  1.71it/s]
Train steps ... :  26%|██▋       | 26339/100000 [7:54:25<11:57:32,  1.71it/s]
Train steps ... :  26%|██▋       | 26340/100000 [7:54:25<11:57:31,  1.71it/s]
Train steps ... :  26%|██▋       | 26341/100000 [7:54:26<11:56:43,  1.71it/s]
Train steps ... :  26%|██▋       | 26342/100000 [7:54:27<11:56:47,  1.71it/s]
Train steps ... :  26%|██▋       | 26343/100000 [7:54:27<11:57:11,  1.71it/s]
Train steps ... :  26%|██▋       | 26344/100000 [7:54:28<11:57:01,  1.71it/s]
Train steps ... :  26%|██▋       | 26345/100000 [7:54:28<11:57:15,  1.71it/s]
Train steps ... :  26%|██▋       | 26346/100000 [7:54:29<11:57:10,  1.71it/s]
Train steps ... :  26%|██▋       | 26347/100000 [7:54:30<11:57:21,  1.71it/s]
Train steps ... :  26%|██▋       | 26348/100000 [7:54:30<11:56:48,  1.71it/s]
Train steps ... :  26%|██▋       | 26349/100000 [7:54:31<11:56:43,  1.71it/s]
Train steps ... :  26%|██▋       | 26350/100000 [7:54:31<11:57:08,  1.71it/s]Step... (26350 / 100000 | Loss: 1.037508249282837, Learning Rate: 7.402010050251256e-05)
+
                                                                             
Step... (26350 / 100000 | Loss: 0.6795042753219604, Learning Rate: 7.402010050251256e-05)
+
Train steps ... :  26%|██▋       | 26350/100000 [7:54:32<11:57:08,  1.71it/s]
Train steps ... :  26%|██▋       | 26351/100000 [7:54:32<11:57:40,  1.71it/s]
Train steps ... :  26%|██▋       | 26352/100000 [7:54:32<11:57:55,  1.71it/s]
Train steps ... :  26%|██▋       | 26353/100000 [7:54:33<11:57:04,  1.71it/s]
Train steps ... :  26%|██▋       | 26354/100000 [7:54:34<11:56:50,  1.71it/s]
Train steps ... :  26%|██▋       | 26355/100000 [7:54:34<11:56:56,  1.71it/s]
Train steps ... :  26%|██▋       | 26356/100000 [7:54:35<11:56:56,  1.71it/s]
Train steps ... :  26%|██▋       | 26357/100000 [7:54:35<11:56:46,  1.71it/s]
Train steps ... :  26%|██▋       | 26358/100000 [7:54:36<11:56:57,  1.71it/s]
Train steps ... :  26%|██▋       | 26359/100000 [7:54:37<11:57:12,  1.71it/s]
Train steps ... :  26%|██▋       | 26360/100000 [7:54:37<11:57:18,  1.71it/s]
Train steps ... :  26%|██▋       | 26361/100000 [7:54:38<11:56:30,  1.71it/s]
Train steps ... :  26%|██▋       | 26362/100000 [7:54:38<11:56:08,  1.71it/s]
Train steps ... :  26%|██▋       | 26363/100000 [7:54:39<11:56:26,  1.71it/s]
Train steps ... :  26%|██▋       | 26364/100000 [7:54:39<11:56:45,  1.71it/s]
Train steps ... :  26%|██▋       | 26365/100000 [7:54:40<11:56:21,  1.71it/s]
Train steps ... :  26%|██▋       | 26366/100000 [7:54:41<11:55:54,  1.71it/s]
Train steps ... :  26%|██▋       | 26367/100000 [7:54:41<11:56:51,  1.71it/s]
Train steps ... :  26%|██▋       | 26368/100000 [7:54:42<11:56:12,  1.71it/s]
Train steps ... :  26%|██▋       | 26369/100000 [7:54:42<11:56:46,  1.71it/s]
Train steps ... :  26%|██▋       | 26370/100000 [7:54:43<11:56:47,  1.71it/s]
Train steps ... :  26%|██▋       | 26371/100000 [7:54:44<11:56:14,  1.71it/s]
Train steps ... :  26%|██▋       | 26372/100000 [7:54:44<11:56:20,  1.71it/s]
Train steps ... :  26%|██▋       | 26373/100000 [7:54:45<11:56:13,  1.71it/s]
Train steps ... :  26%|██▋       | 26374/100000 [7:54:45<11:56:42,  1.71it/s]
Train steps ... :  26%|██▋       | 26375/100000 [7:54:46<11:57:31,  1.71it/s]Step... (26375 / 100000 | Loss: 1.1335909366607666, Learning Rate: 7.399497487437186e-05)
+
                                                                             
Step... (26375 / 100000 | Loss: 1.0541571378707886, Learning Rate: 7.399497487437186e-05)
+
Train steps ... :  26%|██▋       | 26375/100000 [7:54:46<11:57:31,  1.71it/s]
Train steps ... :  26%|██▋       | 26376/100000 [7:54:46<11:57:23,  1.71it/s]
Train steps ... :  26%|██▋       | 26377/100000 [7:54:47<11:58:04,  1.71it/s]
Train steps ... :  26%|██▋       | 26378/100000 [7:54:48<11:57:23,  1.71it/s]
Train steps ... :  26%|██▋       | 26379/100000 [7:54:48<11:56:56,  1.71it/s]
Train steps ... :  26%|██▋       | 26380/100000 [7:54:49<11:56:50,  1.71it/s]
Train steps ... :  26%|██▋       | 26381/100000 [7:54:49<11:56:54,  1.71it/s]
Train steps ... :  26%|██▋       | 26382/100000 [7:54:50<11:56:57,  1.71it/s]
Train steps ... :  26%|██▋       | 26383/100000 [7:54:51<11:57:13,  1.71it/s]
Train steps ... :  26%|██▋       | 26384/100000 [7:54:51<11:56:28,  1.71it/s]
Train steps ... :  26%|██▋       | 26385/100000 [7:54:52<11:56:30,  1.71it/s]
Train steps ... :  26%|██▋       | 26386/100000 [7:54:52<11:57:24,  1.71it/s]
Train steps ... :  26%|██▋       | 26387/100000 [7:54:53<11:57:11,  1.71it/s]
Train steps ... :  26%|██▋       | 26388/100000 [7:54:53<11:57:07,  1.71it/s]
Train steps ... :  26%|██▋       | 26389/100000 [7:54:54<11:56:35,  1.71it/s]
Train steps ... :  26%|██▋       | 26390/100000 [7:54:55<11:56:53,  1.71it/s]
Train steps ... :  26%|██▋       | 26391/100000 [7:54:55<11:56:53,  1.71it/s]
Train steps ... :  26%|██▋       | 26392/100000 [7:54:56<11:57:06,  1.71it/s]
Train steps ... :  26%|██▋       | 26393/100000 [7:54:56<11:56:39,  1.71it/s]
Train steps ... :  26%|██▋       | 26394/100000 [7:54:57<11:57:23,  1.71it/s]
Train steps ... :  26%|██▋       | 26395/100000 [7:54:58<11:56:36,  1.71it/s]
Train steps ... :  26%|██▋       | 26396/100000 [7:54:58<11:56:03,  1.71it/s]
Train steps ... :  26%|██▋       | 26397/100000 [7:54:59<11:56:33,  1.71it/s]
Train steps ... :  26%|██▋       | 26398/100000 [7:54:59<11:56:10,  1.71it/s]
Train steps ... :  26%|██▋       | 26399/100000 [7:55:00<11:55:55,  1.71it/s]
Train steps ... :  26%|██▋       | 26400/100000 [7:55:00<11:56:44,  1.71it/s]Step... (26400 / 100000 | Loss: 1.1869382858276367, Learning Rate: 7.396984924623115e-05)
+
                                                                             
Step... (26400 / 100000 | Loss: 0.8842419385910034, Learning Rate: 7.396984924623115e-05)
+
Train steps ... :  26%|██▋       | 26400/100000 [7:55:01<11:56:44,  1.71it/s]
Train steps ... :  26%|██▋       | 26401/100000 [7:55:01<11:56:53,  1.71it/s]
Train steps ... :  26%|██▋       | 26402/100000 [7:55:02<11:56:03,  1.71it/s]
Train steps ... :  26%|██▋       | 26403/100000 [7:55:02<11:56:41,  1.71it/s]
Train steps ... :  26%|██▋       | 26404/100000 [7:55:03<11:55:07,  1.72it/s]
Train steps ... :  26%|██▋       | 26405/100000 [7:55:03<11:55:15,  1.71it/s]
Train steps ... :  26%|██▋       | 26406/100000 [7:55:04<11:56:31,  1.71it/s]
Train steps ... :  26%|██▋       | 26407/100000 [7:55:05<11:56:03,  1.71it/s]
Train steps ... :  26%|██▋       | 26408/100000 [7:55:05<11:56:19,  1.71it/s]
Train steps ... :  26%|██▋       | 26409/100000 [7:55:06<11:56:52,  1.71it/s]
Train steps ... :  26%|██▋       | 26410/100000 [7:55:06<11:56:25,  1.71it/s]
Train steps ... :  26%|██▋       | 26411/100000 [7:55:07<11:56:42,  1.71it/s]
Train steps ... :  26%|██▋       | 26412/100000 [7:55:07<11:56:50,  1.71it/s]
Train steps ... :  26%|██▋       | 26413/100000 [7:55:08<11:57:05,  1.71it/s]
Train steps ... :  26%|██▋       | 26414/100000 [7:55:09<11:56:46,  1.71it/s]
Train steps ... :  26%|██▋       | 26415/100000 [7:55:09<11:56:10,  1.71it/s]
Train steps ... :  26%|██▋       | 26416/100000 [7:55:10<11:56:56,  1.71it/s]
Train steps ... :  26%|██▋       | 26417/100000 [7:55:10<11:56:50,  1.71it/s]
Train steps ... :  26%|██▋       | 26418/100000 [7:55:11<11:57:17,  1.71it/s]
Train steps ... :  26%|██▋       | 26419/100000 [7:55:12<11:57:28,  1.71it/s]
Train steps ... :  26%|██▋       | 26420/100000 [7:55:12<11:56:25,  1.71it/s]
Train steps ... :  26%|██▋       | 26421/100000 [7:55:13<11:56:20,  1.71it/s]
Train steps ... :  26%|██▋       | 26422/100000 [7:55:13<11:56:16,  1.71it/s]
Train steps ... :  26%|██▋       | 26423/100000 [7:55:14<11:56:06,  1.71it/s]
Train steps ... :  26%|██▋       | 26424/100000 [7:55:14<11:55:52,  1.71it/s]
Train steps ... :  26%|██▋       | 26425/100000 [7:55:15<11:55:41,  1.71it/s]Step... (26425 / 100000 | Loss: 0.7855684757232666, Learning Rate: 7.394472361809047e-05)
+
                                                                             
Step... (26425 / 100000 | Loss: 0.7936699390411377, Learning Rate: 7.394472361809047e-05)
+
Train steps ... :  26%|██▋       | 26425/100000 [7:55:15<11:55:41,  1.71it/s]
Train steps ... :  26%|██▋       | 26426/100000 [7:55:16<11:56:22,  1.71it/s]
Train steps ... :  26%|██▋       | 26427/100000 [7:55:16<11:56:28,  1.71it/s]
Train steps ... :  26%|██▋       | 26428/100000 [7:55:17<11:56:00,  1.71it/s]
Train steps ... :  26%|██▋       | 26429/100000 [7:55:17<11:55:53,  1.71it/s]
Train steps ... :  26%|██▋       | 26430/100000 [7:55:18<11:55:23,  1.71it/s]
Train steps ... :  26%|██▋       | 26431/100000 [7:55:19<11:56:34,  1.71it/s]
Train steps ... :  26%|██▋       | 26432/100000 [7:55:19<11:55:52,  1.71it/s]
Train steps ... :  26%|██▋       | 26433/100000 [7:55:20<11:55:26,  1.71it/s]
Train steps ... :  26%|██▋       | 26434/100000 [7:55:20<11:55:33,  1.71it/s]
Train steps ... :  26%|██▋       | 26435/100000 [7:55:21<11:55:57,  1.71it/s]
Train steps ... :  26%|██▋       | 26436/100000 [7:55:21<11:56:24,  1.71it/s]
Train steps ... :  26%|██▋       | 26437/100000 [7:55:22<11:56:30,  1.71it/s]
Train steps ... :  26%|██▋       | 26438/100000 [7:55:23<11:56:50,  1.71it/s]
Train steps ... :  26%|██▋       | 26439/100000 [7:55:23<11:55:56,  1.71it/s]
Train steps ... :  26%|██▋       | 26440/100000 [7:55:24<11:55:38,  1.71it/s]
Train steps ... :  26%|██▋       | 26441/100000 [7:55:24<11:55:54,  1.71it/s]
Train steps ... :  26%|██▋       | 26442/100000 [7:55:25<11:56:03,  1.71it/s]
Train steps ... :  26%|██▋       | 26443/100000 [7:55:26<11:55:48,  1.71it/s]
Train steps ... :  26%|██▋       | 26444/100000 [7:55:26<11:55:32,  1.71it/s]
Train steps ... :  26%|██▋       | 26445/100000 [7:55:27<11:55:07,  1.71it/s]
Train steps ... :  26%|██▋       | 26446/100000 [7:55:27<11:54:53,  1.71it/s]
Train steps ... :  26%|██▋       | 26447/100000 [7:55:28<11:54:54,  1.71it/s]
Train steps ... :  26%|██▋       | 26448/100000 [7:55:28<11:55:09,  1.71it/s]
Train steps ... :  26%|██▋       | 26449/100000 [7:55:29<11:55:53,  1.71it/s]
Train steps ... :  26%|██▋       | 26450/100000 [7:55:30<11:56:13,  1.71it/s]Step... (26450 / 100000 | Loss: 1.2464828491210938, Learning Rate: 7.391959798994975e-05)
+
                                                                             
Step... (26450 / 100000 | Loss: 1.1577763557434082, Learning Rate: 7.391959798994975e-05)
+
Train steps ... :  26%|██▋       | 26450/100000 [7:55:30<11:56:13,  1.71it/s]
Train steps ... :  26%|██▋       | 26451/100000 [7:55:30<11:56:28,  1.71it/s]
Train steps ... :  26%|██▋       | 26452/100000 [7:55:31<11:55:37,  1.71it/s]
Train steps ... :  26%|██▋       | 26453/100000 [7:55:31<11:55:41,  1.71it/s]
Train steps ... :  26%|██▋       | 26454/100000 [7:55:32<11:55:45,  1.71it/s]
Train steps ... :  26%|██▋       | 26455/100000 [7:55:33<11:56:02,  1.71it/s]
Train steps ... :  26%|██▋       | 26456/100000 [7:55:33<11:55:25,  1.71it/s]
Train steps ... :  26%|██▋       | 26457/100000 [7:55:34<11:56:15,  1.71it/s]
Train steps ... :  26%|██▋       | 26458/100000 [7:55:34<11:55:48,  1.71it/s]
Train steps ... :  26%|██▋       | 26459/100000 [7:55:35<11:56:45,  1.71it/s]
Train steps ... :  26%|██▋       | 26460/100000 [7:55:36<11:56:24,  1.71it/s]
Train steps ... :  26%|██▋       | 26461/100000 [7:55:36<11:56:06,  1.71it/s]
Train steps ... :  26%|██▋       | 26462/100000 [7:55:37<11:58:04,  1.71it/s]
Train steps ... :  26%|██▋       | 26463/100000 [7:55:37<11:56:29,  1.71it/s]
Train steps ... :  26%|██▋       | 26464/100000 [7:55:38<11:55:37,  1.71it/s]
Train steps ... :  26%|██▋       | 26465/100000 [7:55:38<11:55:07,  1.71it/s]
Train steps ... :  26%|██▋       | 26466/100000 [7:55:39<11:55:41,  1.71it/s]
Train steps ... :  26%|██▋       | 26467/100000 [7:55:40<11:55:12,  1.71it/s]
Train steps ... :  26%|██▋       | 26468/100000 [7:55:40<11:55:29,  1.71it/s]
Train steps ... :  26%|██▋       | 26469/100000 [7:55:41<11:55:30,  1.71it/s]
Train steps ... :  26%|██▋       | 26470/100000 [7:55:41<11:56:50,  1.71it/s]
Train steps ... :  26%|██▋       | 26471/100000 [7:55:42<11:56:46,  1.71it/s]
Train steps ... :  26%|██▋       | 26472/100000 [7:55:43<11:57:11,  1.71it/s]
Train steps ... :  26%|██▋       | 26473/100000 [7:55:43<11:56:12,  1.71it/s]
Train steps ... :  26%|██▋       | 26474/100000 [7:55:44<11:56:15,  1.71it/s]
Train steps ... :  26%|██▋       | 26475/100000 [7:55:44<11:56:08,  1.71it/s]Step... (26475 / 100000 | Loss: 0.923504650592804, Learning Rate: 7.389447236180906e-05)
+
                                                                             
Step... (26475 / 100000 | Loss: 0.8901864886283875, Learning Rate: 7.389447236180906e-05)
+
Train steps ... :  26%|██▋       | 26475/100000 [7:55:45<11:56:08,  1.71it/s]
Train steps ... :  26%|██▋       | 26476/100000 [7:55:45<11:56:25,  1.71it/s]
Train steps ... :  26%|██▋       | 26477/100000 [7:55:45<11:55:23,  1.71it/s]
Train steps ... :  26%|██▋       | 26478/100000 [7:55:46<11:55:22,  1.71it/s]
Train steps ... :  26%|██▋       | 26479/100000 [7:55:47<11:55:10,  1.71it/s]
Train steps ... :  26%|██▋       | 26480/100000 [7:55:47<11:55:48,  1.71it/s]
Train steps ... :  26%|██▋       | 26481/100000 [7:55:48<11:55:03,  1.71it/s]
Train steps ... :  26%|██▋       | 26482/100000 [7:55:48<11:55:53,  1.71it/s]
Train steps ... :  26%|██▋       | 26483/100000 [7:55:49<11:55:57,  1.71it/s]
Train steps ... :  26%|██▋       | 26484/100000 [7:55:50<11:55:42,  1.71it/s]
Train steps ... :  26%|██▋       | 26485/100000 [7:55:50<11:55:50,  1.71it/s]
Train steps ... :  26%|██▋       | 26486/100000 [7:55:51<11:56:14,  1.71it/s]
Train steps ... :  26%|██▋       | 26487/100000 [7:55:51<11:55:48,  1.71it/s]
Train steps ... :  26%|██▋       | 26488/100000 [7:55:52<11:55:38,  1.71it/s]
Train steps ... :  26%|██▋       | 26489/100000 [7:55:52<11:56:28,  1.71it/s]
Train steps ... :  26%|██▋       | 26490/100000 [7:55:53<11:56:05,  1.71it/s]
Train steps ... :  26%|██▋       | 26491/100000 [7:55:54<11:55:52,  1.71it/s]
Train steps ... :  26%|██▋       | 26492/100000 [7:55:54<11:56:26,  1.71it/s]
Train steps ... :  26%|██▋       | 26493/100000 [7:55:55<11:55:51,  1.71it/s]
Train steps ... :  26%|██▋       | 26494/100000 [7:55:55<11:55:35,  1.71it/s]
Train steps ... :  26%|██▋       | 26495/100000 [7:55:56<11:55:22,  1.71it/s]
Train steps ... :  26%|██▋       | 26496/100000 [7:55:57<11:55:09,  1.71it/s]
Train steps ... :  26%|██▋       | 26497/100000 [7:55:57<11:55:42,  1.71it/s]
Train steps ... :  26%|██▋       | 26498/100000 [7:55:58<11:55:12,  1.71it/s]
Train steps ... :  26%|██▋       | 26499/100000 [7:55:58<11:54:42,  1.71it/s]
Train steps ... :  26%|██▋       | 26500/100000 [7:55:59<11:54:52,  1.71it/s]Step... (26500 / 100000 | Loss: 1.0783226490020752, Learning Rate: 7.386934673366834e-05)
+
                                                                             
Step... (26500 / 100000 | Loss: 0.7595709562301636, Learning Rate: 7.386934673366834e-05)
+
Train steps ... :  26%|██▋       | 26500/100000 [7:55:59<11:54:52,  1.71it/s]
Train steps ... :  27%|██▋       | 26501/100000 [7:55:59<11:55:18,  1.71it/s]
Train steps ... :  27%|██▋       | 26502/100000 [7:56:00<11:54:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26503/100000 [7:56:01<11:55:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26504/100000 [7:56:01<11:55:07,  1.71it/s]
Train steps ... :  27%|██▋       | 26505/100000 [7:56:02<11:55:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26506/100000 [7:56:02<11:54:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26507/100000 [7:56:03<11:55:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26508/100000 [7:56:04<11:56:28,  1.71it/s]
Train steps ... :  27%|██▋       | 26509/100000 [7:56:04<11:55:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26510/100000 [7:56:05<11:56:30,  1.71it/s]
Train steps ... :  27%|██▋       | 26511/100000 [7:56:05<11:57:11,  1.71it/s]
Train steps ... :  27%|██▋       | 26512/100000 [7:56:06<11:57:12,  1.71it/s]
Train steps ... :  27%|██▋       | 26513/100000 [7:56:06<11:56:42,  1.71it/s]
Train steps ... :  27%|██▋       | 26514/100000 [7:56:07<11:56:25,  1.71it/s]
Train steps ... :  27%|██▋       | 26515/100000 [7:56:08<11:56:22,  1.71it/s]
Train steps ... :  27%|██▋       | 26516/100000 [7:56:08<11:55:57,  1.71it/s]
Train steps ... :  27%|██▋       | 26517/100000 [7:56:09<11:56:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26518/100000 [7:56:09<11:55:39,  1.71it/s]
Train steps ... :  27%|██▋       | 26519/100000 [7:56:10<11:55:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26520/100000 [7:56:11<11:55:54,  1.71it/s]
Train steps ... :  27%|██▋       | 26521/100000 [7:56:11<11:55:30,  1.71it/s]
Train steps ... :  27%|██▋       | 26522/100000 [7:56:12<11:55:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26523/100000 [7:56:12<11:54:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26524/100000 [7:56:13<11:55:02,  1.71it/s]
Train steps ... :  27%|██▋       | 26525/100000 [7:56:13<11:55:13,  1.71it/s]Step... (26525 / 100000 | Loss: 0.9303649663925171, Learning Rate: 7.384422110552764e-05)
+
                                                                             
Step... (26525 / 100000 | Loss: 0.9677947759628296, Learning Rate: 7.384422110552764e-05)
+
Train steps ... :  27%|██▋       | 26525/100000 [7:56:14<11:55:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26526/100000 [7:56:14<11:55:25,  1.71it/s]
Train steps ... :  27%|██▋       | 26527/100000 [7:56:15<11:55:04,  1.71it/s]
Train steps ... :  27%|██▋       | 26528/100000 [7:56:15<11:54:47,  1.71it/s]
Train steps ... :  27%|██▋       | 26529/100000 [7:56:16<11:54:58,  1.71it/s]
Train steps ... :  27%|██▋       | 26530/100000 [7:56:16<11:55:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26531/100000 [7:56:17<11:55:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26532/100000 [7:56:18<11:56:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26533/100000 [7:56:18<11:55:55,  1.71it/s]
Train steps ... :  27%|██▋       | 26534/100000 [7:56:19<11:56:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26535/100000 [7:56:19<11:55:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26536/100000 [7:56:20<11:55:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26537/100000 [7:56:20<11:56:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26538/100000 [7:56:21<11:55:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26539/100000 [7:56:22<11:55:36,  1.71it/s]
Train steps ... :  27%|██▋       | 26540/100000 [7:56:22<11:55:27,  1.71it/s]
Train steps ... :  27%|██▋       | 26541/100000 [7:56:23<11:55:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26542/100000 [7:56:23<11:55:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26543/100000 [7:56:24<11:55:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26544/100000 [7:56:25<11:57:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26545/100000 [7:56:25<11:56:36,  1.71it/s]
Train steps ... :  27%|██▋       | 26546/100000 [7:56:26<11:57:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26547/100000 [7:56:26<11:57:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26548/100000 [7:56:27<11:56:51,  1.71it/s]
Train steps ... :  27%|██▋       | 26549/100000 [7:56:28<11:57:54,  1.71it/s]
Train steps ... :  27%|██▋       | 26550/100000 [7:56:28<11:55:30,  1.71it/s]Step... (26550 / 100000 | Loss: 0.9635831117630005, Learning Rate: 7.381909547738693e-05)
+
                                                                             
Step... (26550 / 100000 | Loss: 0.8975105285644531, Learning Rate: 7.381909547738693e-05)
+
Train steps ... :  27%|██▋       | 26550/100000 [7:56:28<11:55:30,  1.71it/s]
Train steps ... :  27%|██▋       | 26551/100000 [7:56:29<11:56:09,  1.71it/s]
Train steps ... :  27%|██▋       | 26552/100000 [7:56:29<11:56:42,  1.71it/s]
Train steps ... :  27%|██▋       | 26553/100000 [7:56:30<11:55:58,  1.71it/s]
Train steps ... :  27%|██▋       | 26554/100000 [7:56:30<11:55:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26555/100000 [7:56:31<11:56:10,  1.71it/s]
Train steps ... :  27%|██▋       | 26556/100000 [7:56:32<11:55:47,  1.71it/s]
Train steps ... :  27%|██▋       | 26557/100000 [7:56:32<11:56:04,  1.71it/s]
Train steps ... :  27%|██▋       | 26558/100000 [7:56:33<11:55:21,  1.71it/s]
Train steps ... :  27%|██▋       | 26559/100000 [7:56:33<11:55:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26560/100000 [7:56:34<11:55:47,  1.71it/s]
Train steps ... :  27%|██▋       | 26561/100000 [7:56:35<11:55:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26562/100000 [7:56:35<11:56:10,  1.71it/s]
Train steps ... :  27%|██▋       | 26563/100000 [7:56:36<11:56:17,  1.71it/s]
Train steps ... :  27%|██▋       | 26564/100000 [7:56:36<11:56:17,  1.71it/s]
Train steps ... :  27%|██▋       | 26565/100000 [7:56:37<11:55:28,  1.71it/s]
Train steps ... :  27%|██▋       | 26566/100000 [7:56:37<11:56:30,  1.71it/s]
Train steps ... :  27%|██▋       | 26567/100000 [7:56:38<11:57:04,  1.71it/s]
Train steps ... :  27%|██▋       | 26568/100000 [7:56:39<11:55:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26569/100000 [7:56:39<11:55:10,  1.71it/s]
Train steps ... :  27%|██▋       | 26570/100000 [7:56:40<11:55:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26571/100000 [7:56:40<11:55:17,  1.71it/s]
Train steps ... :  27%|██▋       | 26572/100000 [7:56:41<11:54:51,  1.71it/s]
Train steps ... :  27%|██▋       | 26573/100000 [7:56:42<11:55:22,  1.71it/s]
Train steps ... :  27%|██▋       | 26574/100000 [7:56:42<11:54:59,  1.71it/s]
Train steps ... :  27%|██▋       | 26575/100000 [7:56:43<11:55:31,  1.71it/s]Step... (26575 / 100000 | Loss: 1.1762491464614868, Learning Rate: 7.379396984924623e-05)
+
                                                                             
Step... (26575 / 100000 | Loss: 1.0966051816940308, Learning Rate: 7.379396984924623e-05)
+
Train steps ... :  27%|██▋       | 26575/100000 [7:56:43<11:55:31,  1.71it/s]
Train steps ... :  27%|██▋       | 26576/100000 [7:56:43<11:56:37,  1.71it/s]
Train steps ... :  27%|██▋       | 26577/100000 [7:56:44<11:56:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26578/100000 [7:56:44<11:55:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26579/100000 [7:56:45<11:55:35,  1.71it/s]
Train steps ... :  27%|██▋       | 26580/100000 [7:56:46<11:55:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26581/100000 [7:56:46<11:55:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26582/100000 [7:56:47<11:55:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26583/100000 [7:56:47<11:54:57,  1.71it/s]
Train steps ... :  27%|██▋       | 26584/100000 [7:56:48<11:55:43,  1.71it/s]
Train steps ... :  27%|██▋       | 26585/100000 [7:56:49<11:55:49,  1.71it/s]
Train steps ... :  27%|██▋       | 26586/100000 [7:56:49<11:55:23,  1.71it/s]
Train steps ... :  27%|██▋       | 26587/100000 [7:56:50<11:55:18,  1.71it/s]
Train steps ... :  27%|██▋       | 26588/100000 [7:56:50<11:55:24,  1.71it/s]
Train steps ... :  27%|██▋       | 26589/100000 [7:56:51<11:54:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26590/100000 [7:56:51<11:54:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26591/100000 [7:56:52<11:54:51,  1.71it/s]
Train steps ... :  27%|██▋       | 26592/100000 [7:56:53<11:55:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26593/100000 [7:56:53<11:55:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26594/100000 [7:56:54<11:55:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26595/100000 [7:56:54<11:55:17,  1.71it/s]
Train steps ... :  27%|██▋       | 26596/100000 [7:56:55<11:54:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26597/100000 [7:56:56<11:55:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26598/100000 [7:56:56<11:55:01,  1.71it/s]
Train steps ... :  27%|██▋       | 26599/100000 [7:56:57<11:54:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26600/100000 [7:56:57<11:54:43,  1.71it/s]Step... (26600 / 100000 | Loss: 0.7248786687850952, Learning Rate: 7.376884422110553e-05)
+
                                                                             
Step... (26600 / 100000 | Loss: 0.7817364931106567, Learning Rate: 7.376884422110553e-05)
+
Train steps ... :  27%|██▋       | 26600/100000 [7:56:58<11:54:43,  1.71it/s]
Train steps ... :  27%|██▋       | 26601/100000 [7:56:58<11:54:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26602/100000 [7:56:59<11:54:07,  1.71it/s]
Train steps ... :  27%|██���       | 26603/100000 [7:56:59<11:54:04,  1.71it/s]
Train steps ... :  27%|██▋       | 26604/100000 [7:57:00<11:53:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26605/100000 [7:57:00<11:53:58,  1.71it/s]
Train steps ... :  27%|██▋       | 26606/100000 [7:57:01<11:54:51,  1.71it/s]
Train steps ... :  27%|██▋       | 26607/100000 [7:57:01<11:54:21,  1.71it/s]
Train steps ... :  27%|██▋       | 26608/100000 [7:57:02<11:55:18,  1.71it/s]
Train steps ... :  27%|██▋       | 26609/100000 [7:57:03<11:54:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26610/100000 [7:57:03<11:54:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26611/100000 [7:57:04<11:53:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26612/100000 [7:57:04<11:53:47,  1.71it/s]
Train steps ... :  27%|██▋       | 26613/100000 [7:57:05<11:53:37,  1.71it/s]
Train steps ... :  27%|██▋       | 26614/100000 [7:57:06<11:53:28,  1.71it/s]
Train steps ... :  27%|██▋       | 26615/100000 [7:57:06<11:53:39,  1.71it/s]
Train steps ... :  27%|██▋       | 26616/100000 [7:57:07<11:54:31,  1.71it/s]
Train steps ... :  27%|██▋       | 26617/100000 [7:57:07<11:53:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26618/100000 [7:57:08<11:54:03,  1.71it/s]
Train steps ... :  27%|██▋       | 26619/100000 [7:57:08<11:54:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26620/100000 [7:57:09<11:54:30,  1.71it/s]
Train steps ... :  27%|██▋       | 26621/100000 [7:57:10<11:55:09,  1.71it/s]
Train steps ... :  27%|██▋       | 26622/100000 [7:57:10<11:54:59,  1.71it/s]
Train steps ... :  27%|██▋       | 26623/100000 [7:57:11<11:54:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26624/100000 [7:57:11<11:54:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26625/100000 [7:57:12<11:54:11,  1.71it/s]Step... (26625 / 100000 | Loss: 1.2109205722808838, Learning Rate: 7.374371859296482e-05)
+
                                                                             
Step... (26625 / 100000 | Loss: 1.0306432247161865, Learning Rate: 7.374371859296482e-05)
+
Train steps ... :  27%|██▋       | 26625/100000 [7:57:12<11:54:11,  1.71it/s]
Train steps ... :  27%|██▋       | 26626/100000 [7:57:13<11:54:36,  1.71it/s]
Train steps ... :  27%|██▋       | 26627/100000 [7:57:13<11:54:55,  1.71it/s]
Train steps ... :  27%|██▋       | 26628/100000 [7:57:14<11:54:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26629/100000 [7:57:14<11:53:17,  1.71it/s]
Train steps ... :  27%|██▋       | 26630/100000 [7:57:15<11:54:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26631/100000 [7:57:15<11:54:50,  1.71it/s]
Train steps ... :  27%|██▋       | 26632/100000 [7:57:16<11:54:02,  1.71it/s]
Train steps ... :  27%|██▋       | 26633/100000 [7:57:17<11:53:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26634/100000 [7:57:17<11:53:50,  1.71it/s]
Train steps ... :  27%|██▋       | 26635/100000 [7:57:18<11:53:59,  1.71it/s]
Train steps ... :  27%|██▋       | 26636/100000 [7:57:18<11:54:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26637/100000 [7:57:19<11:55:00,  1.71it/s]
Train steps ... :  27%|██▋       | 26638/100000 [7:57:20<11:55:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26639/100000 [7:57:20<11:55:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26640/100000 [7:57:21<11:55:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26641/100000 [7:57:21<11:54:42,  1.71it/s]
Train steps ... :  27%|██▋       | 26642/100000 [7:57:22<11:55:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26643/100000 [7:57:22<11:55:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26644/100000 [7:57:23<11:55:14,  1.71it/s]
Train steps ... :  27%|██▋       | 26645/100000 [7:57:24<11:55:24,  1.71it/s]
Train steps ... :  27%|██▋       | 26646/100000 [7:57:24<11:55:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26647/100000 [7:57:25<11:55:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26648/100000 [7:57:25<11:55:07,  1.71it/s]
Train steps ... :  27%|██▋       | 26649/100000 [7:57:26<11:54:44,  1.71it/s]
Train steps ... :  27%|██▋       | 26650/100000 [7:57:27<11:54:10,  1.71it/s]Step... (26650 / 100000 | Loss: 0.8804242610931396, Learning Rate: 7.371859296482413e-05)
+
                                                                             
Step... (26650 / 100000 | Loss: 1.0567024946212769, Learning Rate: 7.371859296482413e-05)
+
Train steps ... :  27%|██▋       | 26650/100000 [7:57:27<11:54:10,  1.71it/s]
Train steps ... :  27%|██▋       | 26651/100000 [7:57:27<11:55:10,  1.71it/s]
Train steps ... :  27%|██▋       | 26652/100000 [7:57:28<11:55:12,  1.71it/s]
Train steps ... :  27%|██▋       | 26653/100000 [7:57:28<11:55:09,  1.71it/s]
Train steps ... :  27%|██▋       | 26654/100000 [7:57:29<11:54:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26655/100000 [7:57:29<11:54:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26656/100000 [7:57:30<11:54:27,  1.71it/s]
Train steps ... :  27%|██▋       | 26657/100000 [7:57:31<11:53:49,  1.71it/s]
Train steps ... :  27%|██▋       | 26658/100000 [7:57:31<11:54:42,  1.71it/s]
Train steps ... :  27%|██▋       | 26659/100000 [7:57:32<11:54:03,  1.71it/s]
Train steps ... :  27%|██▋       | 26660/100000 [7:57:32<11:53:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26661/100000 [7:57:33<11:54:22,  1.71it/s]
Train steps ... :  27%|██▋       | 26662/100000 [7:57:34<11:54:18,  1.71it/s]
Train steps ... :  27%|██▋       | 26663/100000 [7:57:34<11:53:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26664/100000 [7:57:35<11:53:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26665/100000 [7:57:35<11:53:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26666/100000 [7:57:36<11:54:02,  1.71it/s]
Train steps ... :  27%|██▋       | 26667/100000 [7:57:36<11:53:46,  1.71it/s]
Train steps ... :  27%|██▋       | 26668/100000 [7:57:37<11:54:27,  1.71it/s]
Train steps ... :  27%|██▋       | 26669/100000 [7:57:38<11:53:46,  1.71it/s]
Train steps ... :  27%|██▋       | 26670/100000 [7:57:38<11:55:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26671/100000 [7:57:39<11:55:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26672/100000 [7:57:39<11:55:28,  1.71it/s]
Train steps ... :  27%|██▋       | 26673/100000 [7:57:40<11:54:48,  1.71it/s]
Train steps ... :  27%|██▋       | 26674/100000 [7:57:41<11:55:10,  1.71it/s]
Train steps ... :  27%|██▋       | 26675/100000 [7:57:41<11:56:12,  1.71it/s]Step... (26675 / 100000 | Loss: 1.2138949632644653, Learning Rate: 7.369346733668342e-05)
+
                                                                             
Step... (26675 / 100000 | Loss: 1.1219971179962158, Learning Rate: 7.369346733668342e-05)
+
Train steps ... :  27%|██▋       | 26675/100000 [7:57:42<11:56:12,  1.71it/s]
Train steps ... :  27%|██▋       | 26676/100000 [7:57:42<11:55:18,  1.71it/s]
Train steps ... :  27%|██▋       | 26677/100000 [7:57:42<11:55:18,  1.71it/s]
Train steps ... :  27%|██▋       | 26678/100000 [7:57:43<11:55:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26679/100000 [7:57:44<11:54:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26680/100000 [7:57:44<11:54:21,  1.71it/s]
Train steps ... :  27%|██▋       | 26681/100000 [7:57:45<11:55:48,  1.71it/s]
Train steps ... :  27%|██▋       | 26682/100000 [7:57:45<11:55:54,  1.71it/s]
Train steps ... :  27%|██▋       | 26683/100000 [7:57:46<11:54:51,  1.71it/s]
Train steps ... :  27%|██▋       | 26684/100000 [7:57:46<11:54:27,  1.71it/s]
Train steps ... :  27%|██▋       | 26685/100000 [7:57:47<11:54:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26686/100000 [7:57:48<11:54:21,  1.71it/s]
Train steps ... :  27%|██▋       | 26687/100000 [7:57:48<11:53:42,  1.71it/s]
Train steps ... :  27%|██▋       | 26688/100000 [7:57:49<11:53:28,  1.71it/s]
Train steps ... :  27%|██▋       | 26689/100000 [7:57:49<11:53:00,  1.71it/s]
Train steps ... :  27%|██▋       | 26690/100000 [7:57:50<11:53:12,  1.71it/s]
Train steps ... :  27%|██▋       | 26691/100000 [7:57:51<11:52:37,  1.71it/s]
Train steps ... :  27%|██▋       | 26692/100000 [7:57:51<11:53:58,  1.71it/s]
Train steps ... :  27%|██▋       | 26693/100000 [7:57:52<11:53:50,  1.71it/s]
Train steps ... :  27%|██▋       | 26694/100000 [7:57:52<11:54:12,  1.71it/s]
Train steps ... :  27%|██▋       | 26695/100000 [7:57:53<11:54:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26696/100000 [7:57:53<11:54:08,  1.71it/s]
Train steps ... :  27%|██▋       | 26697/100000 [7:57:54<11:53:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26698/100000 [7:57:55<11:53:37,  1.71it/s]
Train steps ... :  27%|██▋       | 26699/100000 [7:57:55<11:54:11,  1.71it/s]
Train steps ... :  27%|██▋       | 26700/100000 [7:57:56<11:53:50,  1.71it/s]Step... (26700 / 100000 | Loss: 0.9066104888916016, Learning Rate: 7.366834170854271e-05)
+
                                                                             
Step... (26700 / 100000 | Loss: 0.9009419679641724, Learning Rate: 7.366834170854271e-05)
+
Train steps ... :  27%|██▋       | 26700/100000 [7:57:56<11:53:50,  1.71it/s]
Train steps ... :  27%|██▋       | 26701/100000 [7:57:56<11:53:46,  1.71it/s]
Train steps ... :  27%|██▋       | 26702/100000 [7:57:57<11:53:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26703/100000 [7:57:58<11:53:52,  1.71it/s]
Train steps ... :  27%|██▋       | 26704/100000 [7:57:58<11:54:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26705/100000 [7:57:59<11:53:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26706/100000 [7:57:59<11:53:55,  1.71it/s]
Train steps ... :  27%|██▋       | 26707/100000 [7:58:00<11:53:51,  1.71it/s]
Train steps ... :  27%|██▋       | 26708/100000 [7:58:00<11:53:35,  1.71it/s]
Train steps ... :  27%|██▋       | 26709/100000 [7:58:01<11:53:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26710/100000 [7:58:02<11:53:52,  1.71it/s]
Train steps ... :  27%|██▋       | 26711/100000 [7:58:02<11:53:44,  1.71it/s]
Train steps ... :  27%|██▋       | 26712/100000 [7:58:03<11:53:23,  1.71it/s]
Train steps ... :  27%|██▋       | 26713/100000 [7:58:03<11:53:04,  1.71it/s]
Train steps ... :  27%|██▋       | 26714/100000 [7:58:04<11:53:30,  1.71it/s]
Train steps ... :  27%|██▋       | 26715/100000 [7:58:05<11:53:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26716/100000 [7:58:05<11:53:38,  1.71it/s]
Train steps ... :  27%|██▋       | 26717/100000 [7:58:06<11:53:11,  1.71it/s]
Train steps ... :  27%|██▋       | 26718/100000 [7:58:06<11:54:07,  1.71it/s]
Train steps ... :  27%|██▋       | 26719/100000 [7:58:07<11:53:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26720/100000 [7:58:07<11:53:03,  1.71it/s]
Train steps ... :  27%|██▋       | 26721/100000 [7:58:08<11:52:20,  1.71it/s]
Train steps ... :  27%|██▋       | 26722/100000 [7:58:09<11:52:36,  1.71it/s]
Train steps ... :  27%|██▋       | 26723/100000 [7:58:09<11:53:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26724/100000 [7:58:10<11:52:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26725/100000 [7:58:10<11:52:42,  1.71it/s]Step... (26725 / 100000 | Loss: 1.307746410369873, Learning Rate: 7.364321608040201e-05)
+
                                                                             
Step... (26725 / 100000 | Loss: 1.0464626550674438, Learning Rate: 7.364321608040201e-05)
+
Train steps ... :  27%|██▋       | 26725/100000 [7:58:11<11:52:42,  1.71it/s]
Train steps ... :  27%|██▋       | 26726/100000 [7:58:11<11:53:54,  1.71it/s]
Train steps ... :  27%|██▋       | 26727/100000 [7:58:12<11:53:48,  1.71it/s]
Train steps ... :  27%|██▋       | 26728/100000 [7:58:12<11:53:03,  1.71it/s]
Train steps ... :  27%|██▋       | 26729/100000 [7:58:13<11:52:59,  1.71it/s]
Train steps ... :  27%|██▋       | 26730/100000 [7:58:13<11:53:02,  1.71it/s]
Train steps ... :  27%|██▋       | 26731/100000 [7:58:14<11:53:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26732/100000 [7:58:14<11:55:17,  1.71it/s]
Train steps ... :  27%|██▋       | 26733/100000 [7:58:15<11:54:07,  1.71it/s]
Train steps ... :  27%|██▋       | 26734/100000 [7:58:16<11:54:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26735/100000 [7:58:16<11:55:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26736/100000 [7:58:17<11:55:04,  1.71it/s]
Train steps ... :  27%|██▋       | 26737/100000 [7:58:17<11:54:38,  1.71it/s]
Train steps ... :  27%|██▋       | 26738/100000 [7:58:18<11:54:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26739/100000 [7:58:19<11:55:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26740/100000 [7:58:19<11:54:49,  1.71it/s]
Train steps ... :  27%|██▋       | 26741/100000 [7:58:20<11:53:52,  1.71it/s]
Train steps ... :  27%|██▋       | 26742/100000 [7:58:20<11:53:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26743/100000 [7:58:21<11:54:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26744/100000 [7:58:22<11:54:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26745/100000 [7:58:22<11:53:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26746/100000 [7:58:23<11:53:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26747/100000 [7:58:23<11:53:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26748/100000 [7:58:24<11:52:50,  1.71it/s]
Train steps ... :  27%|██▋       | 26749/100000 [7:58:24<11:52:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26750/100000 [7:58:25<11:52:49,  1.71it/s]Step... (26750 / 100000 | Loss: 0.7203659415245056, Learning Rate: 7.361809045226131e-05)
+
                                                                             
Step... (26750 / 100000 | Loss: 1.0473980903625488, Learning Rate: 7.361809045226131e-05)
+
Train steps ... :  27%|██▋       | 26750/100000 [7:58:25<11:52:49,  1.71it/s]
Train steps ... :  27%|██▋       | 26751/100000 [7:58:26<11:53:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26752/100000 [7:58:26<11:54:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26753/100000 [7:58:27<11:55:01,  1.71it/s]
Train steps ... :  27%|██▋       | 26754/100000 [7:58:27<11:54:17,  1.71it/s]
Train steps ... :  27%|██▋       | 26755/100000 [7:58:28<11:54:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26756/100000 [7:58:29<11:54:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26757/100000 [7:58:29<11:53:51,  1.71it/s]
Train steps ... :  27%|██▋       | 26758/100000 [7:58:30<11:54:08,  1.71it/s]
Train steps ... :  27%|██▋       | 26759/100000 [7:58:30<11:53:25,  1.71it/s]
Train steps ... :  27%|██▋       | 26760/100000 [7:58:31<11:52:55,  1.71it/s]
Train steps ... :  27%|██▋       | 26761/100000 [7:58:31<11:53:44,  1.71it/s]
Train steps ... :  27%|██▋       | 26762/100000 [7:58:32<11:53:25,  1.71it/s]
Train steps ... :  27%|██▋       | 26763/100000 [7:58:33<11:53:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26764/100000 [7:58:33<11:54:02,  1.71it/s]
Train steps ... :  27%|██▋       | 26765/100000 [7:58:34<11:53:18,  1.71it/s]
Train steps ... :  27%|██▋       | 26766/100000 [7:58:34<11:52:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26767/100000 [7:58:35<11:53:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26768/100000 [7:58:36<11:52:47,  1.71it/s]
Train steps ... :  27%|██▋       | 26769/100000 [7:58:36<11:53:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26770/100000 [7:58:37<11:53:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26771/100000 [7:58:37<11:52:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26772/100000 [7:58:38<11:52:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26773/100000 [7:58:38<11:53:48,  1.71it/s]
Train steps ... :  27%|██▋       | 26774/100000 [7:58:39<11:53:11,  1.71it/s]
Train steps ... :  27%|██▋       | 26775/100000 [7:58:40<11:53:44,  1.71it/s]Step... (26775 / 100000 | Loss: 0.699982762336731, Learning Rate: 7.35929648241206e-05)
+
                                                                             
Step... (26775 / 100000 | Loss: 0.9358566999435425, Learning Rate: 7.35929648241206e-05)
+
Train steps ... :  27%|██▋       | 26775/100000 [7:58:40<11:53:44,  1.71it/s]
Train steps ... :  27%|██▋       | 26776/100000 [7:58:40<11:53:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26777/100000 [7:58:41<11:52:49,  1.71it/s]
Train steps ... :  27%|██▋       | 26778/100000 [7:58:41<11:53:21,  1.71it/s]
Train steps ... :  27%|██▋       | 26779/100000 [7:58:42<11:53:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26780/100000 [7:58:43<11:53:20,  1.71it/s]
Train steps ... :  27%|██▋       | 26781/100000 [7:58:43<11:53:36,  1.71it/s]
Train steps ... :  27%|██▋       | 26782/100000 [7:58:44<11:52:55,  1.71it/s]
Train steps ... :  27%|██▋       | 26783/100000 [7:58:44<11:53:20,  1.71it/s]
Train steps ... :  27%|██▋       | 26784/100000 [7:58:45<11:55:03,  1.71it/s]
Train steps ... :  27%|██▋       | 26785/100000 [7:58:45<11:54:59,  1.71it/s]
Train steps ... :  27%|██▋       | 26786/100000 [7:58:46<11:53:47,  1.71it/s]
Train steps ... :  27%|██▋       | 26787/100000 [7:58:47<11:53:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26788/100000 [7:58:47<11:53:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26789/100000 [7:58:48<11:53:28,  1.71it/s]
Train steps ... :  27%|██▋       | 26790/100000 [7:58:48<11:52:57,  1.71it/s]
Train steps ... :  27%|██▋       | 26791/100000 [7:58:49<11:53:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26792/100000 [7:58:50<11:54:03,  1.71it/s]
Train steps ... :  27%|██▋       | 26793/100000 [7:58:50<11:52:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26794/100000 [7:58:51<11:52:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26795/100000 [7:58:51<11:53:37,  1.71it/s]
Train steps ... :  27%|██▋       | 26796/100000 [7:58:52<11:52:39,  1.71it/s]
Train steps ... :  27%|██▋       | 26797/100000 [7:58:52<11:52:35,  1.71it/s]
Train steps ... :  27%|██▋       | 26798/100000 [7:58:53<11:53:27,  1.71it/s]
Train steps ... :  27%|██▋       | 26799/100000 [7:58:54<11:53:02,  1.71it/s]
Train steps ... :  27%|██▋       | 26800/100000 [7:58:54<11:54:05,  1.71it/s]Step... (26800 / 100000 | Loss: 0.9942542314529419, Learning Rate: 7.35678391959799e-05)
+
                                                                             
Step... (26800 / 100000 | Loss: 0.9965482950210571, Learning Rate: 7.35678391959799e-05)
+
Train steps ... :  27%|██▋       | 26800/100000 [7:58:55<11:54:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26801/100000 [7:58:55<11:53:08,  1.71it/s]
Train steps ... :  27%|██▋       | 26802/100000 [7:58:55<11:52:35,  1.71it/s]
Train steps ... :  27%|██▋       | 26803/100000 [7:58:56<11:52:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26804/100000 [7:58:57<11:52:12,  1.71it/s]
Train steps ... :  27%|██▋       | 26805/100000 [7:58:57<11:52:07,  1.71it/s]
Train steps ... :  27%|██▋       | 26806/100000 [7:58:58<11:53:09,  1.71it/s]
Train steps ... :  27%|██▋       | 26807/100000 [7:58:58<11:52:37,  1.71it/s]
Train steps ... :  27%|██▋       | 26808/100000 [7:58:59<11:52:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26809/100000 [7:58:59<11:53:21,  1.71it/s]
Train steps ... :  27%|██▋       | 26810/100000 [7:59:00<11:52:58,  1.71it/s]
Train steps ... :  27%|██▋       | 26811/100000 [7:59:01<11:53:02,  1.71it/s]
Train steps ... :  27%|██▋       | 26812/100000 [7:59:01<11:52:55,  1.71it/s]
Train steps ... :  27%|██▋       | 26813/100000 [7:59:02<11:52:43,  1.71it/s]
Train steps ... :  27%|██▋       | 26814/100000 [7:59:02<11:52:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26815/100000 [7:59:03<11:53:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26816/100000 [7:59:04<11:52:58,  1.71it/s]
Train steps ... :  27%|██▋       | 26817/100000 [7:59:04<11:52:59,  1.71it/s]
Train steps ... :  27%|██▋       | 26818/100000 [7:59:05<11:52:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26819/100000 [7:59:05<11:52:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26820/100000 [7:59:06<11:52:48,  1.71it/s]
Train steps ... :  27%|██▋       | 26821/100000 [7:59:07<11:53:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26822/100000 [7:59:07<11:52:37,  1.71it/s]
Train steps ... :  27%|██▋       | 26823/100000 [7:59:08<11:53:10,  1.71it/s]
Train steps ... :  27%|██▋       | 26824/100000 [7:59:08<11:53:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26825/100000 [7:59:09<11:52:45,  1.71it/s]Step... (26825 / 100000 | Loss: 0.9262043833732605, Learning Rate: 7.35427135678392e-05)
+
                                                                             
Step... (26825 / 100000 | Loss: 0.9801734685897827, Learning Rate: 7.35427135678392e-05)
+
Train steps ... :  27%|██▋       | 26825/100000 [7:59:09<11:52:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26826/100000 [7:59:09<11:53:39,  1.71it/s]
Train steps ... :  27%|██▋       | 26827/100000 [7:59:10<11:52:51,  1.71it/s]
Train steps ... :  27%|██▋       | 26828/100000 [7:59:11<11:52:37,  1.71it/s]
Train steps ... :  27%|██▋       | 26829/100000 [7:59:11<11:52:28,  1.71it/s]
Train steps ... :  27%|██▋       | 26830/100000 [7:59:12<11:52:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26831/100000 [7:59:12<11:52:33,  1.71it/s]
Train steps ... :  27%|██▋       | 26832/100000 [7:59:13<11:52:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26833/100000 [7:59:14<11:53:54,  1.71it/s]
Train steps ... :  27%|██▋       | 26834/100000 [7:59:14<11:53:08,  1.71it/s]
Train steps ... :  27%|██▋       | 26835/100000 [7:59:15<11:53:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26836/100000 [7:59:15<11:52:48,  1.71it/s]
Train steps ... :  27%|██▋       | 26837/100000 [7:59:16<11:52:37,  1.71it/s]
Train steps ... :  27%|██▋       | 26838/100000 [7:59:16<11:52:23,  1.71it/s]
Train steps ... :  27%|██▋       | 26839/100000 [7:59:17<11:52:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26840/100000 [7:59:18<11:52:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26841/100000 [7:59:18<11:52:46,  1.71it/s]
Train steps ... :  27%|██▋       | 26842/100000 [7:59:19<11:52:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26843/100000 [7:59:19<11:53:00,  1.71it/s]
Train steps ... :  27%|██▋       | 26844/100000 [7:59:20<11:53:08,  1.71it/s]
Train steps ... :  27%|██▋       | 26845/100000 [7:59:21<11:52:44,  1.71it/s]
Train steps ... :  27%|██▋       | 26846/100000 [7:59:21<11:52:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26847/100000 [7:59:22<11:52:31,  1.71it/s]
Train steps ... :  27%|██▋       | 26848/100000 [7:59:22<11:52:14,  1.71it/s]
Train steps ... :  27%|██▋       | 26849/100000 [7:59:23<11:52:37,  1.71it/s]
Train steps ... :  27%|██▋       | 26850/100000 [7:59:23<11:52:16,  1.71it/s]Step... (26850 / 100000 | Loss: 0.9878298044204712, Learning Rate: 7.35175879396985e-05)
+
                                                                             
Step... (26850 / 100000 | Loss: 1.2553155422210693, Learning Rate: 7.35175879396985e-05)
+
Train steps ... :  27%|██▋       | 26850/100000 [7:59:24<11:52:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26851/100000 [7:59:24<11:53:07,  1.71it/s]
Train steps ... :  27%|██▋       | 26852/100000 [7:59:25<11:52:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26853/100000 [7:59:25<11:52:38,  1.71it/s]
Train steps ... :  27%|██▋       | 26854/100000 [7:59:26<11:52:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26855/100000 [7:59:26<11:52:09,  1.71it/s]
Train steps ... :  27%|██▋       | 26856/100000 [7:59:27<11:53:14,  1.71it/s]
Train steps ... :  27%|██▋       | 26857/100000 [7:59:28<11:53:01,  1.71it/s]
Train steps ... :  27%|██▋       | 26858/100000 [7:59:28<11:53:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26859/100000 [7:59:29<11:53:23,  1.71it/s]
Train steps ... :  27%|██▋       | 26860/100000 [7:59:29<11:52:48,  1.71it/s]
Train steps ... :  27%|██▋       | 26861/100000 [7:59:30<11:52:49,  1.71it/s]
Train steps ... :  27%|██▋       | 26862/100000 [7:59:30<11:52:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26863/100000 [7:59:31<11:51:57,  1.71it/s]
Train steps ... :  27%|██▋       | 26864/100000 [7:59:32<11:51:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26865/100000 [7:59:32<11:51:22,  1.71it/s]
Train steps ... :  27%|██▋       | 26866/100000 [7:59:33<11:51:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26867/100000 [7:59:33<11:51:14,  1.71it/s]
Train steps ... :  27%|██▋       | 26868/100000 [7:59:34<11:51:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26869/100000 [7:59:35<11:51:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26870/100000 [7:59:35<11:51:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26871/100000 [7:59:36<11:52:04,  1.71it/s]
Train steps ... :  27%|██▋       | 26872/100000 [7:59:36<11:52:48,  1.71it/s]
Train steps ... :  27%|██▋       | 26873/100000 [7:59:37<11:53:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26874/100000 [7:59:37<11:52:51,  1.71it/s]
Train steps ... :  27%|██▋       | 26875/100000 [7:59:38<11:52:54,  1.71it/s]Step... (26875 / 100000 | Loss: 1.056031584739685, Learning Rate: 7.349246231155779e-05)
+
                                                                             
Step... (26875 / 100000 | Loss: 1.0398555994033813, Learning Rate: 7.349246231155779e-05)
+
Train steps ... :  27%|██▋       | 26875/100000 [7:59:38<11:52:54,  1.71it/s]
Train steps ... :  27%|██▋       | 26876/100000 [7:59:39<11:53:11,  1.71it/s]
Train steps ... :  27%|██▋       | 26877/100000 [7:59:39<11:52:27,  1.71it/s]
Train steps ... :  27%|██▋       | 26878/100000 [7:59:40<11:52:07,  1.71it/s]
Train steps ... :  27%|██▋       | 26879/100000 [7:59:40<11:52:08,  1.71it/s]
Train steps ... :  27%|██▋       | 26880/100000 [7:59:41<11:51:22,  1.71it/s]
Train steps ... :  27%|██▋       | 26881/100000 [7:59:42<11:52:23,  1.71it/s]
Train steps ... :  27%|██▋       | 26882/100000 [7:59:42<11:51:59,  1.71it/s]
Train steps ... :  27%|██▋       | 26883/100000 [7:59:43<11:53:00,  1.71it/s]
Train steps ... :  27%|██▋       | 26884/100000 [7:59:43<11:52:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26885/100000 [7:59:44<11:52:03,  1.71it/s]
Train steps ... :  27%|██▋       | 26886/100000 [7:59:45<11:51:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26887/100000 [7:59:45<11:51:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26888/100000 [7:59:46<11:51:47,  1.71it/s]
Train steps ... :  27%|██▋       | 26889/100000 [7:59:46<11:52:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26890/100000 [7:59:47<11:51:42,  1.71it/s]
Train steps ... :  27%|██▋       | 26891/100000 [7:59:47<11:51:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26892/100000 [7:59:48<11:53:11,  1.71it/s]
Train steps ... :  27%|██▋       | 26893/100000 [7:59:49<11:52:07,  1.71it/s]
Train steps ... :  27%|██▋       | 26894/100000 [7:59:49<11:52:24,  1.71it/s]
Train steps ... :  27%|██▋       | 26895/100000 [7:59:50<11:52:39,  1.71it/s]
Train steps ... :  27%|██▋       | 26896/100000 [7:59:50<11:52:08,  1.71it/s]
Train steps ... :  27%|██▋       | 26897/100000 [7:59:51<11:52:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26898/100000 [7:59:52<11:51:49,  1.71it/s]
Train steps ... :  27%|██▋       | 26899/100000 [7:59:52<11:51:58,  1.71it/s]
Train steps ... :  27%|██▋       | 26900/100000 [7:59:53<11:52:00,  1.71it/s]Step... (26900 / 100000 | Loss: 0.7596563100814819, Learning Rate: 7.346733668341709e-05)
+
                                                                             
Step... (26900 / 100000 | Loss: 0.8172039985656738, Learning Rate: 7.346733668341709e-05)
+
Train steps ... :  27%|██▋       | 26900/100000 [7:59:53<11:52:00,  1.71it/s]
Train steps ... :  27%|██▋       | 26901/100000 [7:59:53<11:51:46,  1.71it/s]
Train steps ... :  27%|██▋       | 26902/100000 [7:59:54<11:52:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26903/100000 [7:59:54<11:51:59,  1.71it/s]
Train steps ... :  27%|██▋       | 26904/100000 [7:59:55<11:51:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26905/100000 [7:59:56<11:51:25,  1.71it/s]
Train steps ... :  27%|██▋       | 26906/100000 [7:59:56<11:51:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26907/100000 [7:59:57<11:51:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26908/100000 [7:59:57<11:52:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26909/100000 [7:59:58<11:51:58,  1.71it/s]
Train steps ... :  27%|██▋       | 26910/100000 [7:59:59<11:52:25,  1.71it/s]
Train steps ... :  27%|██▋       | 26911/100000 [7:59:59<11:51:50,  1.71it/s]
Train steps ... :  27%|██▋       | 26912/100000 [8:00:00<11:51:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26913/100000 [8:00:00<11:51:15,  1.71it/s]
Train steps ... :  27%|██▋       | 26914/100000 [8:00:01<11:52:11,  1.71it/s]
Train steps ... :  27%|██▋       | 26915/100000 [8:00:01<11:52:12,  1.71it/s]
Train steps ... :  27%|██▋       | 26916/100000 [8:00:02<11:51:59,  1.71it/s]
Train steps ... :  27%|██▋       | 26917/100000 [8:00:03<11:52:21,  1.71it/s]
Train steps ... :  27%|██▋       | 26918/100000 [8:00:03<11:53:27,  1.71it/s]
Train steps ... :  27%|██▋       | 26919/100000 [8:00:04<11:53:39,  1.71it/s]
Train steps ... :  27%|██▋       | 26920/100000 [8:00:04<11:52:39,  1.71it/s]
Train steps ... :  27%|██▋       | 26921/100000 [8:00:05<11:53:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26922/100000 [8:00:06<11:52:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26923/100000 [8:00:06<11:51:49,  1.71it/s]
Train steps ... :  27%|██▋       | 26924/100000 [8:00:07<11:52:35,  1.71it/s]
Train steps ... :  27%|██▋       | 26925/100000 [8:00:07<11:52:44,  1.71it/s]Step... (26925 / 100000 | Loss: 1.0686652660369873, Learning Rate: 7.344221105527638e-05)
+
                                                                             
Step... (26925 / 100000 | Loss: 0.9445255994796753, Learning Rate: 7.344221105527638e-05)
+
Train steps ... :  27%|██▋       | 26925/100000 [8:00:08<11:52:44,  1.71it/s]
Train steps ... :  27%|██▋       | 26926/100000 [8:00:08<11:52:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26927/100000 [8:00:08<11:52:04,  1.71it/s]
Train steps ... :  27%|██▋       | 26928/100000 [8:00:09<11:51:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26929/100000 [8:00:10<11:50:45,  1.71it/s]
Train steps ... :  27%|██▋       | 26930/100000 [8:00:10<11:50:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26931/100000 [8:00:11<11:50:46,  1.71it/s]
Train steps ... :  27%|██▋       | 26932/100000 [8:00:11<11:50:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26933/100000 [8:00:12<11:50:42,  1.71it/s]
Train steps ... :  27%|██▋       | 26934/100000 [8:00:13<11:50:27,  1.71it/s]
Train steps ... :  27%|██▋       | 26935/100000 [8:00:13<11:50:47,  1.71it/s]
Train steps ... :  27%|██▋       | 26936/100000 [8:00:14<11:50:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26937/100000 [8:00:14<11:51:02,  1.71it/s]
Train steps ... :  27%|██▋       | 26938/100000 [8:00:15<11:51:25,  1.71it/s]
Train steps ... :  27%|██▋       | 26939/100000 [8:00:15<11:50:52,  1.71it/s]
Train steps ... :  27%|██▋       | 26940/100000 [8:00:16<11:51:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26941/100000 [8:00:17<11:50:47,  1.71it/s]
Train steps ... :  27%|██▋       | 26942/100000 [8:00:17<11:51:17,  1.71it/s]
Train steps ... :  27%|██▋       | 26943/100000 [8:00:18<11:50:41,  1.71it/s]
Train steps ... :  27%|██▋       | 26944/100000 [8:00:18<11:51:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26945/100000 [8:00:19<11:51:21,  1.71it/s]
Train steps ... :  27%|██▋       | 26946/100000 [8:00:20<11:51:57,  1.71it/s]
Train steps ... :  27%|██▋       | 26947/100000 [8:00:20<11:51:27,  1.71it/s]
Train steps ... :  27%|██▋       | 26948/100000 [8:00:21<11:51:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26949/100000 [8:00:21<11:52:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26950/100000 [8:00:22<11:52:13,  1.71it/s]Step... (26950 / 100000 | Loss: 1.1498357057571411, Learning Rate: 7.341708542713568e-05)
+
                                                                             
Step... (26950 / 100000 | Loss: 1.1321616172790527, Learning Rate: 7.341708542713568e-05)
+
Train steps ... :  27%|██▋       | 26950/100000 [8:00:22<11:52:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26951/100000 [8:00:22<11:52:09,  1.71it/s]
Train steps ... :  27%|██▋       | 26952/100000 [8:00:23<11:51:27,  1.71it/s]
Train steps ... :  27%|██▋       | 26953/100000 [8:00:24<11:51:52,  1.71it/s]
Train steps ... :  27%|██▋       | 26954/100000 [8:00:24<11:51:03,  1.71it/s]
Train steps ... :  27%|██▋       | 26955/100000 [8:00:25<11:51:05,  1.71it/s]
Train steps ... :  27%|██▋       | 26956/100000 [8:00:25<11:51:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26957/100000 [8:00:26<11:50:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26958/100000 [8:00:27<11:50:33,  1.71it/s]
Train steps ... :  27%|██▋       | 26959/100000 [8:00:27<11:50:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26960/100000 [8:00:28<11:51:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26961/100000 [8:00:28<11:51:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26962/100000 [8:00:29<11:51:43,  1.71it/s]
Train steps ... :  27%|██▋       | 26963/100000 [8:00:29<11:51:06,  1.71it/s]
Train steps ... :  27%|██▋       | 26964/100000 [8:00:30<11:50:59,  1.71it/s]
Train steps ... :  27%|██▋       | 26965/100000 [8:00:31<11:50:56,  1.71it/s]
Train steps ... :  27%|██▋       | 26966/100000 [8:00:31<11:51:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26967/100000 [8:00:32<11:51:24,  1.71it/s]
Train steps ... :  27%|██▋       | 26968/100000 [8:00:32<11:51:35,  1.71it/s]
Train steps ... :  27%|██▋       | 26969/100000 [8:00:33<11:51:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26970/100000 [8:00:34<11:51:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26971/100000 [8:00:34<11:51:13,  1.71it/s]
Train steps ... :  27%|██▋       | 26972/100000 [8:00:35<11:51:09,  1.71it/s]
Train steps ... :  27%|██▋       | 26973/100000 [8:00:35<11:50:44,  1.71it/s]
Train steps ... :  27%|██▋       | 26974/100000 [8:00:36<11:50:26,  1.71it/s]
Train steps ... :  27%|██▋       | 26975/100000 [8:00:37<11:51:19,  1.71it/s]Step... (26975 / 100000 | Loss: 1.0625227689743042, Learning Rate: 7.339195979899498e-05)
+
                                                                             
Step... (26975 / 100000 | Loss: 0.9003986120223999, Learning Rate: 7.339195979899498e-05)
+
Train steps ... :  27%|██▋       | 26975/100000 [8:00:37<11:51:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26976/100000 [8:00:37<11:51:04,  1.71it/s]
Train steps ... :  27%|██▋       | 26977/100000 [8:00:38<11:50:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26978/100000 [8:00:38<11:50:23,  1.71it/s]
Train steps ... :  27%|██▋       | 26979/100000 [8:00:39<11:49:55,  1.71it/s]
Train steps ... :  27%|██▋       | 26980/100000 [8:00:39<11:50:02,  1.71it/s]
Train steps ... :  27%|██▋       | 26981/100000 [8:00:40<11:50:39,  1.71it/s]
Train steps ... :  27%|██▋       | 26982/100000 [8:00:41<11:51:16,  1.71it/s]
Train steps ... :  27%|██▋       | 26983/100000 [8:00:41<11:51:40,  1.71it/s]
Train steps ... :  27%|██▋       | 26984/100000 [8:00:42<11:52:02,  1.71it/s]
Train steps ... :  27%|██▋       | 26985/100000 [8:00:42<11:52:14,  1.71it/s]
Train steps ... :  27%|██▋       | 26986/100000 [8:00:43<11:51:38,  1.71it/s]
Train steps ... :  27%|██▋       | 26987/100000 [8:00:44<11:52:01,  1.71it/s]
Train steps ... :  27%|██▋       | 26988/100000 [8:00:44<11:51:03,  1.71it/s]
Train steps ... :  27%|██▋       | 26989/100000 [8:00:45<11:51:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26990/100000 [8:00:45<11:50:34,  1.71it/s]
Train steps ... :  27%|██▋       | 26991/100000 [8:00:46<11:51:24,  1.71it/s]
Train steps ... :  27%|██▋       | 26992/100000 [8:00:46<11:51:33,  1.71it/s]
Train steps ... :  27%|██▋       | 26993/100000 [8:00:47<11:51:32,  1.71it/s]
Train steps ... :  27%|██▋       | 26994/100000 [8:00:48<11:51:53,  1.71it/s]
Train steps ... :  27%|██▋       | 26995/100000 [8:00:48<11:51:19,  1.71it/s]
Train steps ... :  27%|██▋       | 26996/100000 [8:00:49<11:51:04,  1.71it/s]
Train steps ... :  27%|██▋       | 26997/100000 [8:00:49<11:50:29,  1.71it/s]
Train steps ... :  27%|██▋       | 26998/100000 [8:00:50<11:50:21,  1.71it/s]
Train steps ... :  27%|██▋       | 26999/100000 [8:00:51<11:51:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27000/100000 [8:00:51<11:50:43,  1.71it/s]Step... (27000 / 100000 | Loss: 1.063808798789978, Learning Rate: 7.336683417085427e-05)
+
                                                                             
Step... (27000 / 100000 | Loss: 1.4601353406906128, Learning Rate: 7.336683417085427e-05)
+
Train steps ... :  27%|██▋       | 27000/100000 [8:00:51<11:50:43,  1.71it/s]
Train steps ... :  27%|██▋       | 27001/100000 [8:00:52<11:50:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27002/100000 [8:00:52<11:50:16,  1.71it/s]
Train steps ... :  27%|██▋       | 27003/100000 [8:00:53<11:50:10,  1.71it/s]
Train steps ... :  27%|██▋       | 27004/100000 [8:00:53<11:50:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27005/100000 [8:00:54<11:50:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27006/100000 [8:00:55<11:51:08,  1.71it/s]
Train steps ... :  27%|██▋       | 27007/100000 [8:00:55<11:50:36,  1.71it/s]
Train steps ... :  27%|██▋       | 27008/100000 [8:00:56<11:50:48,  1.71it/s]
Train steps ... :  27%|██▋       | 27009/100000 [8:00:56<11:51:07,  1.71it/s]
Train steps ... :  27%|██▋       | 27010/100000 [8:00:57<11:50:32,  1.71it/s]
Train steps ... :  27%|██▋       | 27011/100000 [8:00:58<11:49:54,  1.71it/s]
Train steps ... :  27%|██▋       | 27012/100000 [8:00:58<11:51:01,  1.71it/s]
Train steps ... :  27%|██▋       | 27013/100000 [8:00:59<11:50:41,  1.71it/s]
Train steps ... :  27%|██▋       | 27014/100000 [8:00:59<11:50:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27015/100000 [8:01:00<11:51:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27016/100000 [8:01:00<11:51:38,  1.71it/s]
Train steps ... :  27%|██▋       | 27017/100000 [8:01:01<11:51:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27018/100000 [8:01:02<11:50:25,  1.71it/s]
Train steps ... :  27%|██▋       | 27019/100000 [8:01:02<11:51:25,  1.71it/s]
Train steps ... :  27%|██▋       | 27020/100000 [8:01:03<11:51:34,  1.71it/s]
Train steps ... :  27%|██▋       | 27021/100000 [8:01:03<11:51:05,  1.71it/s]
Train steps ... :  27%|██▋       | 27022/100000 [8:01:04<11:51:30,  1.71it/s]
Train steps ... :  27%|██▋       | 27023/100000 [8:01:05<11:51:50,  1.71it/s]
Train steps ... :  27%|██▋       | 27024/100000 [8:01:05<11:51:06,  1.71it/s]
Train steps ... :  27%|██▋       | 27025/100000 [8:01:06<11:50:54,  1.71it/s]Step... (27025 / 100000 | Loss: 0.8731588125228882, Learning Rate: 7.334170854271357e-05)
+
                                                                             
Step... (27025 / 100000 | Loss: 0.9877845048904419, Learning Rate: 7.334170854271357e-05)
+
Train steps ... :  27%|██▋       | 27025/100000 [8:01:06<11:50:54,  1.71it/s]
Train steps ... :  27%|██▋       | 27026/100000 [8:01:06<11:50:58,  1.71it/s]
Train steps ... :  27%|██▋       | 27027/100000 [8:01:07<11:50:49,  1.71it/s]
Train steps ... :  27%|██▋       | 27028/100000 [8:01:07<11:51:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27029/100000 [8:01:08<11:51:40,  1.71it/s]
Train steps ... :  27%|██▋       | 27030/100000 [8:01:09<11:51:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27031/100000 [8:01:09<11:51:24,  1.71it/s]
Train steps ... :  27%|██▋       | 27032/100000 [8:01:10<11:51:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27033/100000 [8:01:10<11:51:06,  1.71it/s]
Train steps ... :  27%|██▋       | 27034/100000 [8:01:11<11:50:44,  1.71it/s]
Train steps ... :  27%|██▋       | 27035/100000 [8:01:12<11:50:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27036/100000 [8:01:12<11:50:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27037/100000 [8:01:13<11:49:49,  1.71it/s]
Train steps ... :  27%|██▋       | 27038/100000 [8:01:13<11:50:56,  1.71it/s]
Train steps ... :  27%|██▋       | 27039/100000 [8:01:14<11:50:30,  1.71it/s]
Train steps ... :  27%|██▋       | 27040/100000 [8:01:14<11:50:34,  1.71it/s]
Train steps ... :  27%|██▋       | 27041/100000 [8:01:15<11:50:07,  1.71it/s]
Train steps ... :  27%|██▋       | 27042/100000 [8:01:16<11:50:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27043/100000 [8:01:16<11:50:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27044/100000 [8:01:17<11:50:04,  1.71it/s]
Train steps ... :  27%|██▋       | 27045/100000 [8:01:17<11:50:10,  1.71it/s]
Train steps ... :  27%|██▋       | 27046/100000 [8:01:18<11:50:21,  1.71it/s]
Train steps ... :  27%|██▋       | 27047/100000 [8:01:19<11:51:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27048/100000 [8:01:19<11:50:57,  1.71it/s]
Train steps ... :  27%|██▋       | 27049/100000 [8:01:20<11:50:08,  1.71it/s]
Train steps ... :  27%|██▋       | 27050/100000 [8:01:20<11:50:26,  1.71it/s]Step... (27050 / 100000 | Loss: 0.9411298036575317, Learning Rate: 7.331658291457287e-05)
+
                                                                             
Step... (27050 / 100000 | Loss: 1.206018090248108, Learning Rate: 7.331658291457287e-05)
+
Train steps ... :  27%|██▋       | 27050/100000 [8:01:21<11:50:26,  1.71it/s]
Train steps ... :  27%|██▋       | 27051/100000 [8:01:21<11:50:12,  1.71it/s]
Train steps ... :  27%|██▋       | 27052/100000 [8:01:22<11:50:14,  1.71it/s]
Train steps ... :  27%|██▋       | 27053/100000 [8:01:22<11:49:34,  1.71it/s]
Train steps ... :  27%|██▋       | 27054/100000 [8:01:23<11:49:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27055/100000 [8:01:23<11:49:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27056/100000 [8:01:24<11:50:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27057/100000 [8:01:24<11:49:44,  1.71it/s]
Train steps ... :  27%|██▋       | 27058/100000 [8:01:25<11:50:34,  1.71it/s]
Train steps ... :  27%|██▋       | 27059/100000 [8:01:26<11:50:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27060/100000 [8:01:26<11:50:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27061/100000 [8:01:27<11:50:26,  1.71it/s]
Train steps ... :  27%|██▋       | 27062/100000 [8:01:27<11:51:47,  1.71it/s]
Train steps ... :  27%|██▋       | 27063/100000 [8:01:28<11:50:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27064/100000 [8:01:29<11:50:50,  1.71it/s]
Train steps ... :  27%|██▋       | 27065/100000 [8:01:29<11:51:07,  1.71it/s]
Train steps ... :  27%|██▋       | 27066/100000 [8:01:30<11:51:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27067/100000 [8:01:30<11:51:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27068/100000 [8:01:31<11:52:38,  1.71it/s]
Train steps ... :  27%|██▋       | 27069/100000 [8:01:31<11:51:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27070/100000 [8:01:32<11:50:36,  1.71it/s]
Train steps ... :  27%|██▋       | 27071/100000 [8:01:33<11:49:49,  1.71it/s]
Train steps ... :  27%|██▋       | 27072/100000 [8:01:33<11:50:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27073/100000 [8:01:34<11:50:31,  1.71it/s]
Train steps ... :  27%|██▋       | 27074/100000 [8:01:34<11:49:43,  1.71it/s]
Train steps ... :  27%|██▋       | 27075/100000 [8:01:35<11:49:42,  1.71it/s]Step... (27075 / 100000 | Loss: 1.227996587753296, Learning Rate: 7.329145728643216e-05)
+
                                                                             
Step... (27075 / 100000 | Loss: 1.3905539512634277, Learning Rate: 7.329145728643216e-05)
+
Train steps ... :  27%|██▋       | 27075/100000 [8:01:35<11:49:42,  1.71it/s]
Train steps ... :  27%|██▋       | 27076/100000 [8:01:36<11:49:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27077/100000 [8:01:36<11:49:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27078/100000 [8:01:37<11:50:24,  1.71it/s]
Train steps ... :  27%|██▋       | 27079/100000 [8:01:37<11:50:27,  1.71it/s]
Train steps ... :  27%|██▋       | 27080/100000 [8:01:38<11:50:59,  1.71it/s]
Train steps ... :  27%|██▋       | 27081/100000 [8:01:38<11:50:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27082/100000 [8:01:39<11:50:42,  1.71it/s]
Train steps ... :  27%|██▋       | 27083/100000 [8:01:40<11:51:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27084/100000 [8:01:40<11:50:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27085/100000 [8:01:41<11:50:24,  1.71it/s]
Train steps ... :  27%|██▋       | 27086/100000 [8:01:41<11:51:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27087/100000 [8:01:42<11:50:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27088/100000 [8:01:43<11:50:05,  1.71it/s]
Train steps ... :  27%|██▋       | 27089/100000 [8:01:43<11:50:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27090/100000 [8:01:44<11:50:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27091/100000 [8:01:44<11:49:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27092/100000 [8:01:45<11:50:15,  1.71it/s]
Train steps ... :  27%|██▋       | 27093/100000 [8:01:45<11:50:56,  1.71it/s]
Train steps ... :  27%|██▋       | 27094/100000 [8:01:46<11:50:45,  1.71it/s]
Train steps ... :  27%|██▋       | 27095/100000 [8:01:47<11:50:46,  1.71it/s]
Train steps ... :  27%|██▋       | 27096/100000 [8:01:47<11:51:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27097/100000 [8:01:48<11:51:11,  1.71it/s]
Train steps ... :  27%|██▋       | 27098/100000 [8:01:48<11:51:17,  1.71it/s]
Train steps ... :  27%|██▋       | 27099/100000 [8:01:49<11:50:50,  1.71it/s]
Train steps ... :  27%|██▋       | 27100/100000 [8:01:50<11:50:05,  1.71it/s]Step... (27100 / 100000 | Loss: 1.4708576202392578, Learning Rate: 7.326633165829146e-05)
+
                                                                             
Step... (27100 / 100000 | Loss: 0.7924158573150635, Learning Rate: 7.326633165829146e-05)
+
Train steps ... :  27%|██▋       | 27100/100000 [8:01:50<11:50:05,  1.71it/s]
Train steps ... :  27%|██▋       | 27101/100000 [8:01:50<11:50:49,  1.71it/s]
Train steps ... :  27%|██▋       | 27102/100000 [8:01:51<11:51:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27103/100000 [8:01:51<11:50:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27104/100000 [8:01:52<11:50:34,  1.71it/s]
Train steps ... :  27%|██▋       | 27105/100000 [8:01:52<11:49:53,  1.71it/s]
Train steps ... :  27%|██▋       | 27106/100000 [8:01:53<11:49:31,  1.71it/s]
Train steps ... :  27%|██▋       | 27107/100000 [8:01:54<11:49:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27108/100000 [8:01:54<11:49:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27109/100000 [8:01:55<11:49:43,  1.71it/s]
Train steps ... :  27%|██▋       | 27110/100000 [8:01:55<11:49:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27111/100000 [8:01:56<11:50:11,  1.71it/s]
Train steps ... :  27%|██▋       | 27112/100000 [8:01:57<11:49:48,  1.71it/s]
Train steps ... :  27%|██▋       | 27113/100000 [8:01:57<11:50:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27114/100000 [8:01:58<11:50:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27115/100000 [8:01:58<11:50:15,  1.71it/s]
Train steps ... :  27%|██▋       | 27116/100000 [8:01:59<11:50:40,  1.71it/s]
Train steps ... :  27%|██▋       | 27117/100000 [8:02:00<11:50:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27118/100000 [8:02:00<11:51:12,  1.71it/s]
Train steps ... :  27%|██▋       | 27119/100000 [8:02:01<11:50:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27120/100000 [8:02:01<11:50:06,  1.71it/s]
Train steps ... :  27%|██▋       | 27121/100000 [8:02:02<11:50:32,  1.71it/s]
Train steps ... :  27%|██▋       | 27122/100000 [8:02:02<11:49:48,  1.71it/s]
Train steps ... :  27%|██▋       | 27123/100000 [8:02:03<11:49:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27124/100000 [8:02:04<11:50:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27125/100000 [8:02:04<11:49:46,  1.71it/s]Step... (27125 / 100000 | Loss: 0.7525397539138794, Learning Rate: 7.324120603015076e-05)
+
                                                                             
Step... (27125 / 100000 | Loss: 1.3071061372756958, Learning Rate: 7.324120603015076e-05)
+
Train steps ... :  27%|██▋       | 27125/100000 [8:02:05<11:49:46,  1.71it/s]
Train steps ... :  27%|██▋       | 27126/100000 [8:02:05<11:50:04,  1.71it/s]
Train steps ... :  27%|██▋       | 27127/100000 [8:02:05<11:50:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27128/100000 [8:02:06<11:50:10,  1.71it/s]
Train steps ... :  27%|██▋       | 27129/100000 [8:02:07<11:50:47,  1.71it/s]
Train steps ... :  27%|██▋       | 27130/100000 [8:02:07<11:49:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27131/100000 [8:02:08<11:50:42,  1.71it/s]
Train steps ... :  27%|██▋       | 27132/100000 [8:02:08<11:50:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27133/100000 [8:02:09<11:50:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27134/100000 [8:02:09<11:50:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27135/100000 [8:02:10<11:51:30,  1.71it/s]
Train steps ... :  27%|██▋       | 27136/100000 [8:02:11<11:51:17,  1.71it/s]
Train steps ... :  27%|██▋       | 27137/100000 [8:02:11<11:50:30,  1.71it/s]
Train steps ... :  27%|██▋       | 27138/100000 [8:02:12<11:50:59,  1.71it/s]
Train steps ... :  27%|██▋       | 27139/100000 [8:02:12<11:50:21,  1.71it/s]
Train steps ... :  27%|██▋       | 27140/100000 [8:02:13<11:50:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27141/100000 [8:02:14<11:50:22,  1.71it/s]
Train steps ... :  27%|██▋       | 27142/100000 [8:02:14<11:50:27,  1.71it/s]
Train steps ... :  27%|██▋       | 27143/100000 [8:02:15<11:50:16,  1.71it/s]
Train steps ... :  27%|██▋       | 27144/100000 [8:02:15<11:51:15,  1.71it/s]
Train steps ... :  27%|██▋       | 27145/100000 [8:02:16<11:50:28,  1.71it/s]
Train steps ... :  27%|██▋       | 27146/100000 [8:02:16<11:50:24,  1.71it/s]
Train steps ... :  27%|██▋       | 27147/100000 [8:02:17<11:49:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27148/100000 [8:02:18<11:49:29,  1.71it/s]
Train steps ... :  27%|██▋       | 27149/100000 [8:02:18<11:52:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27150/100000 [8:02:19<11:49:04,  1.71it/s]Step... (27150 / 100000 | Loss: 1.1269872188568115, Learning Rate: 7.321608040201005e-05)
+
                                                                             
Step... (27150 / 100000 | Loss: 0.8812083005905151, Learning Rate: 7.321608040201005e-05)
+
Train steps ... :  27%|██▋       | 27150/100000 [8:02:19<11:49:04,  1.71it/s]
Train steps ... :  27%|██▋       | 27151/100000 [8:02:19<11:49:57,  1.71it/s]
Train steps ... :  27%|██▋       | 27152/100000 [8:02:20<11:50:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27153/100000 [8:02:21<11:50:15,  1.71it/s]
Train steps ... :  27%|██▋       | 27154/100000 [8:02:21<11:50:14,  1.71it/s]
Train steps ... :  27%|██▋       | 27155/100000 [8:02:22<11:49:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27156/100000 [8:02:22<11:50:48,  1.71it/s]
Train steps ... :  27%|██▋       | 27157/100000 [8:02:23<11:50:47,  1.71it/s]
Train steps ... :  27%|██▋       | 27158/100000 [8:02:23<11:50:27,  1.71it/s]
Train steps ... :  27%|██▋       | 27159/100000 [8:02:24<11:50:06,  1.71it/s]
Train steps ... :  27%|██▋       | 27160/100000 [8:02:25<11:49:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27161/100000 [8:02:25<11:49:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27162/100000 [8:02:26<11:49:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27163/100000 [8:02:26<11:49:18,  1.71it/s]
Train steps ... :  27%|██▋       | 27164/100000 [8:02:27<11:48:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27165/100000 [8:02:28<11:49:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27166/100000 [8:02:28<11:48:58,  1.71it/s]
Train steps ... :  27%|██▋       | 27167/100000 [8:02:29<11:49:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27168/100000 [8:02:29<11:49:42,  1.71it/s]
Train steps ... :  27%|██▋       | 27169/100000 [8:02:30<11:49:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27170/100000 [8:02:31<11:49:34,  1.71it/s]
Train steps ... :  27%|██▋       | 27171/100000 [8:02:31<11:49:27,  1.71it/s]
Train steps ... :  27%|██▋       | 27172/100000 [8:02:32<11:49:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27173/100000 [8:02:32<11:49:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27174/100000 [8:02:33<11:48:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27175/100000 [8:02:33<11:49:14,  1.71it/s]Step... (27175 / 100000 | Loss: 0.8548939824104309, Learning Rate: 7.319095477386935e-05)
+
                                                                             
Step... (27175 / 100000 | Loss: 0.9293388724327087, Learning Rate: 7.319095477386935e-05)
+
Train steps ... :  27%|██▋       | 27175/100000 [8:02:34<11:49:14,  1.71it/s]
Train steps ... :  27%|██▋       | 27176/100000 [8:02:34<11:49:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27177/100000 [8:02:35<11:49:03,  1.71it/s]
Train steps ... :  27%|██▋       | 27178/100000 [8:02:35<11:49:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27179/100000 [8:02:36<11:50:00,  1.71it/s]
Train steps ... :  27%|██▋       | 27180/100000 [8:02:36<11:49:06,  1.71it/s]
Train steps ... :  27%|██▋       | 27181/100000 [8:02:37<11:49:45,  1.71it/s]
Train steps ... :  27%|██▋       | 27182/100000 [8:02:38<11:49:36,  1.71it/s]
Train steps ... :  27%|██▋       | 27183/100000 [8:02:38<11:49:26,  1.71it/s]
Train steps ... :  27%|██▋       | 27184/100000 [8:02:39<11:49:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27185/100000 [8:02:39<11:49:10,  1.71it/s]
Train steps ... :  27%|██▋       | 27186/100000 [8:02:40<11:48:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27187/100000 [8:02:40<11:49:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27188/100000 [8:02:41<11:50:16,  1.71it/s]
Train steps ... :  27%|██▋       | 27189/100000 [8:02:42<11:51:06,  1.71it/s]
Train steps ... :  27%|██▋       | 27190/100000 [8:02:42<11:50:03,  1.71it/s]
Train steps ... :  27%|██▋       | 27191/100000 [8:02:43<11:50:36,  1.71it/s]
Train steps ... :  27%|██▋       | 27192/100000 [8:02:43<11:50:11,  1.71it/s]
Train steps ... :  27%|██▋       | 27193/100000 [8:02:44<11:49:15,  1.71it/s]
Train steps ... :  27%|██▋       | 27194/100000 [8:02:45<11:48:40,  1.71it/s]
Train steps ... :  27%|██▋       | 27195/100000 [8:02:45<11:49:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27196/100000 [8:02:46<11:49:05,  1.71it/s]
Train steps ... :  27%|██▋       | 27197/100000 [8:02:46<11:48:49,  1.71it/s]
Train steps ... :  27%|██▋       | 27198/100000 [8:02:47<11:48:46,  1.71it/s]
Train steps ... :  27%|██▋       | 27199/100000 [8:02:47<11:49:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27200/100000 [8:02:48<11:49:15,  1.71it/s]Step... (27200 / 100000 | Loss: 1.1440627574920654, Learning Rate: 7.316582914572865e-05)
+
                                                                             
Step... (27200 / 100000 | Loss: 1.133901596069336, Learning Rate: 7.316582914572865e-05)
+
Train steps ... :  27%|██▋       | 27200/100000 [8:02:48<11:49:15,  1.71it/s]
Train steps ... :  27%|██▋       | 27201/100000 [8:02:49<11:49:59,  1.71it/s]
Train steps ... :  27%|██▋       | 27202/100000 [8:02:49<11:50:53,  1.71it/s]
Train steps ... :  27%|██▋       | 27203/100000 [8:02:50<11:48:44,  1.71it/s]
Train steps ... :  27%|██▋       | 27204/100000 [8:02:50<11:48:24,  1.71it/s]
Train steps ... :  27%|██▋       | 27205/100000 [8:02:51<11:48:29,  1.71it/s]
Train steps ... :  27%|██▋       | 27206/100000 [8:02:52<11:50:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27207/100000 [8:02:52<11:48:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27208/100000 [8:02:53<11:48:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27209/100000 [8:02:53<11:48:30,  1.71it/s]
Train steps ... :  27%|██▋       | 27210/100000 [8:02:54<11:49:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27211/100000 [8:02:54<11:49:11,  1.71it/s]
Train steps ... :  27%|██▋       | 27212/100000 [8:02:55<11:49:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27213/100000 [8:02:56<11:49:03,  1.71it/s]
Train steps ... :  27%|██▋       | 27214/100000 [8:02:56<11:49:28,  1.71it/s]
Train steps ... :  27%|██▋       | 27215/100000 [8:02:57<11:49:18,  1.71it/s]
Train steps ... :  27%|██▋       | 27216/100000 [8:02:57<11:48:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27217/100000 [8:02:58<11:49:34,  1.71it/s]
Train steps ... :  27%|██▋       | 27218/100000 [8:02:59<11:50:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27219/100000 [8:02:59<11:50:41,  1.71it/s]
Train steps ... :  27%|██▋       | 27220/100000 [8:03:00<11:50:22,  1.71it/s]
Train steps ... :  27%|██▋       | 27221/100000 [8:03:00<11:49:42,  1.71it/s]
Train steps ... :  27%|██▋       | 27222/100000 [8:03:01<11:49:07,  1.71it/s]
Train steps ... :  27%|██▋       | 27223/100000 [8:03:02<11:49:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27224/100000 [8:03:02<11:49:41,  1.71it/s]
Train steps ... :  27%|██▋       | 27225/100000 [8:03:03<11:48:40,  1.71it/s]Step... (27225 / 100000 | Loss: 0.9633651971817017, Learning Rate: 7.314070351758794e-05)
+
                                                                             
Step... (27225 / 100000 | Loss: 1.2630698680877686, Learning Rate: 7.314070351758794e-05)
+
Train steps ... :  27%|██▋       | 27225/100000 [8:03:03<11:48:40,  1.71it/s]
Train steps ... :  27%|██▋       | 27226/100000 [8:03:03<11:48:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27227/100000 [8:03:04<11:50:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27228/100000 [8:03:04<11:49:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27229/100000 [8:03:05<11:50:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27230/100000 [8:03:06<11:49:26,  1.71it/s]
Train steps ... :  27%|██▋       | 27231/100000 [8:03:06<11:50:46,  1.71it/s]
Train steps ... :  27%|���█▋       | 27232/100000 [8:03:07<11:50:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27233/100000 [8:03:07<11:49:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27234/100000 [8:03:08<11:48:47,  1.71it/s]
Train steps ... :  27%|██▋       | 27235/100000 [8:03:09<11:49:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27236/100000 [8:03:09<11:49:53,  1.71it/s]
Train steps ... :  27%|██▋       | 27237/100000 [8:03:10<11:48:42,  1.71it/s]
Train steps ... :  27%|██▋       | 27238/100000 [8:03:10<11:48:41,  1.71it/s]
Train steps ... :  27%|██▋       | 27239/100000 [8:03:11<11:48:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27240/100000 [8:03:11<11:49:44,  1.71it/s]
Train steps ... :  27%|██▋       | 27241/100000 [8:03:12<11:49:40,  1.71it/s]
Train steps ... :  27%|██▋       | 27242/100000 [8:03:13<11:50:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27243/100000 [8:03:13<11:49:57,  1.71it/s]
Train steps ... :  27%|██▋       | 27244/100000 [8:03:14<11:49:07,  1.71it/s]
Train steps ... :  27%|██▋       | 27245/100000 [8:03:14<11:49:32,  1.71it/s]
Train steps ... :  27%|██▋       | 27246/100000 [8:03:15<11:49:30,  1.71it/s]
Train steps ... :  27%|██▋       | 27247/100000 [8:03:16<11:49:18,  1.71it/s]
Train steps ... :  27%|██▋       | 27248/100000 [8:03:16<11:49:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27249/100000 [8:03:17<11:49:36,  1.71it/s]
Train steps ... :  27%|██▋       | 27250/100000 [8:03:17<11:49:15,  1.71it/s]Step... (27250 / 100000 | Loss: 0.8690835237503052, Learning Rate: 7.311557788944724e-05)
+
                                                                             
Step... (27250 / 100000 | Loss: 0.7678602933883667, Learning Rate: 7.311557788944724e-05)
+
Train steps ... :  27%|██▋       | 27250/100000 [8:03:18<11:49:15,  1.71it/s]
Train steps ... :  27%|██▋       | 27251/100000 [8:03:18<11:49:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27252/100000 [8:03:18<11:49:08,  1.71it/s]
Train steps ... :  27%|██▋       | 27253/100000 [8:03:19<11:48:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27254/100000 [8:03:20<11:48:48,  1.71it/s]
Train steps ... :  27%|██▋       | 27255/100000 [8:03:20<11:49:30,  1.71it/s]
Train steps ... :  27%|██▋       | 27256/100000 [8:03:21<11:49:11,  1.71it/s]
Train steps ... :  27%|██▋       | 27257/100000 [8:03:21<11:49:21,  1.71it/s]
Train steps ... :  27%|██▋       | 27258/100000 [8:03:22<11:49:32,  1.71it/s]
Train steps ... :  27%|██▋       | 27259/100000 [8:03:23<11:49:38,  1.71it/s]
Train steps ... :  27%|██▋       | 27260/100000 [8:03:23<11:48:58,  1.71it/s]
Train steps ... :  27%|██▋       | 27261/100000 [8:03:24<11:48:38,  1.71it/s]
Train steps ... :  27%|██▋       | 27262/100000 [8:03:24<11:49:38,  1.71it/s]
Train steps ... :  27%|██▋       | 27263/100000 [8:03:25<11:49:54,  1.71it/s]
Train steps ... :  27%|██▋       | 27264/100000 [8:03:25<11:49:49,  1.71it/s]
Train steps ... :  27%|██▋       | 27265/100000 [8:03:26<11:49:32,  1.71it/s]
Train steps ... :  27%|██▋       | 27266/100000 [8:03:27<11:50:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27267/100000 [8:03:27<11:49:32,  1.71it/s]
Train steps ... :  27%|██▋       | 27268/100000 [8:03:28<11:50:53,  1.71it/s]
Train steps ... :  27%|██▋       | 27269/100000 [8:03:28<11:49:45,  1.71it/s]
Train steps ... :  27%|██▋       | 27270/100000 [8:03:29<11:49:28,  1.71it/s]
Train steps ... :  27%|██▋       | 27271/100000 [8:03:30<11:49:17,  1.71it/s]
Train steps ... :  27%|██▋       | 27272/100000 [8:03:30<11:50:17,  1.71it/s]
Train steps ... :  27%|██▋       | 27273/100000 [8:03:31<11:50:29,  1.71it/s]
Train steps ... :  27%|██▋       | 27274/100000 [8:03:31<11:49:42,  1.71it/s]
Train steps ... :  27%|██▋       | 27275/100000 [8:03:32<11:49:04,  1.71it/s]Step... (27275 / 100000 | Loss: 1.1950517892837524, Learning Rate: 7.309045226130654e-05)
+
                                                                             
Step... (27275 / 100000 | Loss: 0.9683343768119812, Learning Rate: 7.309045226130654e-05)
+
Train steps ... :  27%|██▋       | 27275/100000 [8:03:32<11:49:04,  1.71it/s]
Train steps ... :  27%|██▋       | 27276/100000 [8:03:33<11:48:50,  1.71it/s]
Train steps ... :  27%|██▋       | 27277/100000 [8:03:33<11:47:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27278/100000 [8:03:34<11:49:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27279/100000 [8:03:34<11:50:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27280/100000 [8:03:35<11:49:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27281/100000 [8:03:35<11:49:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27282/100000 [8:03:36<11:50:08,  1.71it/s]
Train steps ... :  27%|██▋       | 27283/100000 [8:03:37<11:49:25,  1.71it/s]
Train steps ... :  27%|██▋       | 27284/100000 [8:03:37<11:50:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27285/100000 [8:03:38<11:50:31,  1.71it/s]
Train steps ... :  27%|██▋       | 27286/100000 [8:03:38<11:50:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27287/100000 [8:03:39<11:49:01,  1.71it/s]
Train steps ... :  27%|██▋       | 27288/100000 [8:03:40<11:49:29,  1.71it/s]
Train steps ... :  27%|██▋       | 27289/100000 [8:03:40<11:49:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27290/100000 [8:03:41<11:48:28,  1.71it/s]
Train steps ... :  27%|██▋       | 27291/100000 [8:03:41<11:48:16,  1.71it/s]
Train steps ... :  27%|██▋       | 27292/100000 [8:03:42<11:48:48,  1.71it/s]
Train steps ... :  27%|██▋       | 27293/100000 [8:03:42<11:48:54,  1.71it/s]
Train steps ... :  27%|██▋       | 27294/100000 [8:03:43<11:48:12,  1.71it/s]
Train steps ... :  27%|██▋       | 27295/100000 [8:03:44<11:48:14,  1.71it/s]
Train steps ... :  27%|██▋       | 27296/100000 [8:03:44<11:48:08,  1.71it/s]
Train steps ... :  27%|██▋       | 27297/100000 [8:03:45<11:47:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27298/100000 [8:03:45<11:48:01,  1.71it/s]
Train steps ... :  27%|██▋       | 27299/100000 [8:03:46<11:48:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27300/100000 [8:03:47<11:49:47,  1.71it/s]Step... (27300 / 100000 | Loss: 0.7136937975883484, Learning Rate: 7.306532663316583e-05)
+
                                                                             
Step... (27300 / 100000 | Loss: 0.7554302215576172, Learning Rate: 7.306532663316583e-05)
+
Train steps ... :  27%|██▋       | 27300/100000 [8:03:47<11:49:47,  1.71it/s]
Train steps ... :  27%|██▋       | 27301/100000 [8:03:47<11:49:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27302/100000 [8:03:48<11:49:43,  1.71it/s]
Train steps ... :  27%|██▋       | 27303/100000 [8:03:48<11:49:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27304/100000 [8:03:49<11:48:29,  1.71it/s]
Train steps ... :  27%|██▋       | 27305/100000 [8:03:49<11:48:55,  1.71it/s]
Train steps ... :  27%|██▋       | 27306/100000 [8:03:50<11:47:43,  1.71it/s]
Train steps ... :  27%|██▋       | 27307/100000 [8:03:51<11:48:31,  1.71it/s]
Train steps ... :  27%|██▋       | 27308/100000 [8:03:51<11:48:01,  1.71it/s]
Train steps ... :  27%|██▋       | 27309/100000 [8:03:52<11:47:57,  1.71it/s]
Train steps ... :  27%|██▋       | 27310/100000 [8:03:52<11:49:08,  1.71it/s]
Train steps ... :  27%|██▋       | 27311/100000 [8:03:53<11:49:16,  1.71it/s]
Train steps ... :  27%|██▋       | 27312/100000 [8:03:54<11:49:25,  1.71it/s]
Train steps ... :  27%|██▋       | 27313/100000 [8:03:54<11:48:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27314/100000 [8:03:55<11:49:16,  1.71it/s]
Train steps ... :  27%|██▋       | 27315/100000 [8:03:55<11:49:27,  1.71it/s]
Train steps ... :  27%|██▋       | 27316/100000 [8:03:56<11:48:44,  1.71it/s]
Train steps ... :  27%|██▋       | 27317/100000 [8:03:57<11:48:27,  1.71it/s]
Train steps ... :  27%|██▋       | 27318/100000 [8:03:57<11:48:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27319/100000 [8:03:58<11:48:57,  1.71it/s]
Train steps ... :  27%|██▋       | 27320/100000 [8:03:58<11:49:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27321/100000 [8:03:59<11:48:46,  1.71it/s]
Train steps ... :  27%|██▋       | 27322/100000 [8:03:59<11:47:43,  1.71it/s]
Train steps ... :  27%|██▋       | 27323/100000 [8:04:00<11:47:44,  1.71it/s]
Train steps ... :  27%|██▋       | 27324/100000 [8:04:01<11:47:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27325/100000 [8:04:01<11:47:36,  1.71it/s]Step... (27325 / 100000 | Loss: 0.6758038997650146, Learning Rate: 7.304020100502513e-05)
+
                                                                             
Step... (27325 / 100000 | Loss: 0.8478286266326904, Learning Rate: 7.304020100502513e-05)
+
Train steps ... :  27%|██▋       | 27325/100000 [8:04:02<11:47:36,  1.71it/s]
Train steps ... :  27%|██▋       | 27326/100000 [8:04:02<11:47:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27327/100000 [8:04:02<11:47:21,  1.71it/s]
Train steps ... :  27%|██▋       | 27328/100000 [8:04:03<11:48:06,  1.71it/s]
Train steps ... :  27%|██▋       | 27329/100000 [8:04:04<11:47:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27330/100000 [8:04:04<11:48:16,  1.71it/s]
Train steps ... :  27%|██▋       | 27331/100000 [8:04:05<11:48:12,  1.71it/s]
Train steps ... :  27%|██▋       | 27332/100000 [8:04:05<11:48:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27333/100000 [8:04:06<11:48:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27334/100000 [8:04:06<11:47:50,  1.71it/s]
Train steps ... :  27%|██▋       | 27335/100000 [8:04:07<11:48:47,  1.71it/s]
Train steps ... :  27%|██▋       | 27336/100000 [8:04:08<11:48:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27337/100000 [8:04:08<11:48:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27338/100000 [8:04:09<11:48:48,  1.71it/s]
Train steps ... :  27%|██▋       | 27339/100000 [8:04:09<11:48:43,  1.71it/s]
Train steps ... :  27%|██▋       | 27340/100000 [8:04:10<11:47:54,  1.71it/s]
Train steps ... :  27%|██▋       | 27341/100000 [8:04:11<11:47:28,  1.71it/s]
Train steps ... :  27%|██▋       | 27342/100000 [8:04:11<11:47:38,  1.71it/s]
Train steps ... :  27%|██▋       | 27343/100000 [8:04:12<11:48:21,  1.71it/s]
Train steps ... :  27%|██▋       | 27344/100000 [8:04:12<11:48:03,  1.71it/s]
Train steps ... :  27%|██▋       | 27345/100000 [8:04:13<11:47:57,  1.71it/s]
Train steps ... :  27%|██▋       | 27346/100000 [8:04:13<11:48:01,  1.71it/s]
Train steps ... :  27%|██▋       | 27347/100000 [8:04:14<11:47:45,  1.71it/s]
Train steps ... :  27%|██▋       | 27348/100000 [8:04:15<11:47:09,  1.71it/s]
Train steps ... :  27%|██▋       | 27349/100000 [8:04:15<11:46:41,  1.71it/s]
Train steps ... :  27%|██▋       | 27350/100000 [8:04:16<11:46:52,  1.71it/s]Step... (27350 / 100000 | Loss: 0.9427402019500732, Learning Rate: 7.301507537688443e-05)
+
                                                                             
Step... (27350 / 100000 | Loss: 0.8904715776443481, Learning Rate: 7.301507537688443e-05)
+
Train steps ... :  27%|██▋       | 27350/100000 [8:04:16<11:46:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27351/100000 [8:04:16<11:47:43,  1.71it/s]
Train steps ... :  27%|██▋       | 27352/100000 [8:04:17<11:47:54,  1.71it/s]
Train steps ... :  27%|██▋       | 27353/100000 [8:04:18<11:48:06,  1.71it/s]
Train steps ... :  27%|██▋       | 27354/100000 [8:04:18<11:48:44,  1.71it/s]
Train steps ... :  27%|██▋       | 27355/100000 [8:04:19<11:49:03,  1.71it/s]
Train steps ... :  27%|██▋       | 27356/100000 [8:04:19<11:48:24,  1.71it/s]
Train steps ... :  27%|██▋       | 27357/100000 [8:04:20<11:47:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27358/100000 [8:04:20<11:49:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27359/100000 [8:04:21<11:49:11,  1.71it/s]
Train steps ... :  27%|██▋       | 27360/100000 [8:04:22<11:49:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27361/100000 [8:04:22<11:49:25,  1.71it/s]
Train steps ... :  27%|██▋       | 27362/100000 [8:04:23<11:48:22,  1.71it/s]
Train steps ... :  27%|██▋       | 27363/100000 [8:04:23<11:48:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27364/100000 [8:04:24<11:48:02,  1.71it/s]
Train steps ... :  27%|██▋       | 27365/100000 [8:04:25<11:47:41,  1.71it/s]
Train steps ... :  27%|██▋       | 27366/100000 [8:04:25<11:48:18,  1.71it/s]
Train steps ... :  27%|██▋       | 27367/100000 [8:04:26<11:48:47,  1.71it/s]
Train steps ... :  27%|██▋       | 27368/100000 [8:04:26<11:48:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27369/100000 [8:04:27<11:48:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27370/100000 [8:04:28<11:47:48,  1.71it/s]
Train steps ... :  27%|██▋       | 27371/100000 [8:04:28<11:47:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27372/100000 [8:04:29<11:47:48,  1.71it/s]
Train steps ... :  27%|██▋       | 27373/100000 [8:04:29<11:48:18,  1.71it/s]
Train steps ... :  27%|██▋       | 27374/100000 [8:04:30<11:48:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27375/100000 [8:04:30<11:48:44,  1.71it/s]Step... (27375 / 100000 | Loss: 0.953273594379425, Learning Rate: 7.298994974874372e-05)
+
                                                                             
Step... (27375 / 100000 | Loss: 0.7696859240531921, Learning Rate: 7.298994974874372e-05)
+
Train steps ... :  27%|██▋       | 27375/100000 [8:04:31<11:48:44,  1.71it/s]
Train steps ... :  27%|██▋       | 27376/100000 [8:04:31<11:48:45,  1.71it/s]
Train steps ... :  27%|██▋       | 27377/100000 [8:04:32<11:47:34,  1.71it/s]
Train steps ... :  27%|██▋       | 27378/100000 [8:04:32<11:47:49,  1.71it/s]
Train steps ... :  27%|██▋       | 27379/100000 [8:04:33<11:48:07,  1.71it/s]
Train steps ... :  27%|██▋       | 27380/100000 [8:04:33<11:48:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27381/100000 [8:04:34<11:47:57,  1.71it/s]
Train steps ... :  27%|██▋       | 27382/100000 [8:04:35<11:48:14,  1.71it/s]
Train steps ... :  27%|██▋       | 27383/100000 [8:04:35<11:48:00,  1.71it/s]
Train steps ... :  27%|██▋       | 27384/100000 [8:04:36<11:48:30,  1.71it/s]
Train steps ... :  27%|██▋       | 27385/100000 [8:04:36<11:48:50,  1.71it/s]
Train steps ... :  27%|██▋       | 27386/100000 [8:04:37<11:47:57,  1.71it/s]
Train steps ... :  27%|██▋       | 27387/100000 [8:04:37<11:48:05,  1.71it/s]
Train steps ... :  27%|██▋       | 27388/100000 [8:04:38<11:48:24,  1.71it/s]
Train steps ... :  27%|██▋       | 27389/100000 [8:04:39<11:48:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27390/100000 [8:04:39<11:47:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27391/100000 [8:04:40<11:47:46,  1.71it/s]
Train steps ... :  27%|██▋       | 27392/100000 [8:04:40<11:47:54,  1.71it/s]
Train steps ... :  27%|██▋       | 27393/100000 [8:04:41<11:48:00,  1.71it/s]
Train steps ... :  27%|██▋       | 27394/100000 [8:04:42<11:47:26,  1.71it/s]
Train steps ... :  27%|██▋       | 27395/100000 [8:04:42<11:47:11,  1.71it/s]
Train steps ... :  27%|██▋       | 27396/100000 [8:04:43<11:46:50,  1.71it/s]
Train steps ... :  27%|██▋       | 27397/100000 [8:04:43<11:46:58,  1.71it/s]
Train steps ... :  27%|██▋       | 27398/100000 [8:04:44<11:47:04,  1.71it/s]
Train steps ... :  27%|██▋       | 27399/100000 [8:04:44<11:46:49,  1.71it/s]
Train steps ... :  27%|██▋       | 27400/100000 [8:04:45<11:46:40,  1.71it/s]Step... (27400 / 100000 | Loss: 1.0016592741012573, Learning Rate: 7.296482412060302e-05)
+
                                                                             
Step... (27400 / 100000 | Loss: 0.9481759667396545, Learning Rate: 7.296482412060302e-05)
+
Train steps ... :  27%|██▋       | 27400/100000 [8:04:45<11:46:40,  1.71it/s]
Train steps ... :  27%|██▋       | 27401/100000 [8:04:46<11:46:32,  1.71it/s]
Train steps ... :  27%|██▋       | 27402/100000 [8:04:46<11:46:53,  1.71it/s]
Train steps ... :  27%|██▋       | 27403/100000 [8:04:47<11:46:47,  1.71it/s]
Train steps ... :  27%|██▋       | 27404/100000 [8:04:47<11:46:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27405/100000 [8:04:48<11:47:00,  1.71it/s]
Train steps ... :  27%|██▋       | 27406/100000 [8:04:49<11:47:30,  1.71it/s]
Train steps ... :  27%|██▋       | 27407/100000 [8:04:49<11:47:12,  1.71it/s]
Train steps ... :  27%|██▋       | 27408/100000 [8:04:50<11:46:47,  1.71it/s]
Train steps ... :  27%|██▋       | 27409/100000 [8:04:50<11:46:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27410/100000 [8:04:51<11:46:44,  1.71it/s]
Train steps ... :  27%|██▋       | 27411/100000 [8:04:51<11:46:59,  1.71it/s]
Train steps ... :  27%|██▋       | 27412/100000 [8:04:52<11:46:42,  1.71it/s]
Train steps ... :  27%|██▋       | 27413/100000 [8:04:53<11:47:23,  1.71it/s]
Train steps ... :  27%|██▋       | 27414/100000 [8:04:53<11:46:59,  1.71it/s]
Train steps ... :  27%|██▋       | 27415/100000 [8:04:54<11:47:18,  1.71it/s]
Train steps ... :  27%|██▋       | 27416/100000 [8:04:54<11:46:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27417/100000 [8:04:55<11:47:58,  1.71it/s]
Train steps ... :  27%|██▋       | 27418/100000 [8:04:56<11:47:18,  1.71it/s]
Train steps ... :  27%|██▋       | 27419/100000 [8:04:56<11:47:00,  1.71it/s]
Train steps ... :  27%|██▋       | 27420/100000 [8:04:57<11:47:43,  1.71it/s]
Train steps ... :  27%|██▋       | 27421/100000 [8:04:57<11:47:05,  1.71it/s]
Train steps ... :  27%|██▋       | 27422/100000 [8:04:58<11:46:41,  1.71it/s]
Train steps ... :  27%|██▋       | 27423/100000 [8:04:58<11:47:26,  1.71it/s]
Train steps ... :  27%|██▋       | 27424/100000 [8:04:59<11:46:45,  1.71it/s]
Train steps ... :  27%|██▋       | 27425/100000 [8:05:00<11:47:15,  1.71it/s]Step... (27425 / 100000 | Loss: 0.7677381038665771, Learning Rate: 7.293969849246232e-05)
+
                                                                             
Step... (27425 / 100000 | Loss: 1.1023657321929932, Learning Rate: 7.293969849246232e-05)
+
Train steps ... :  27%|██▋       | 27425/100000 [8:05:00<11:47:15,  1.71it/s]
Train steps ... :  27%|██▋       | 27426/100000 [8:05:00<11:48:04,  1.71it/s]
Train steps ... :  27%|██▋       | 27427/100000 [8:05:01<11:47:28,  1.71it/s]
Train steps ... :  27%|██▋       | 27428/100000 [8:05:01<11:47:41,  1.71it/s]
Train steps ... :  27%|██▋       | 27429/100000 [8:05:02<11:47:42,  1.71it/s]
Train steps ... :  27%|██▋       | 27430/100000 [8:05:03<11:46:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27431/100000 [8:05:03<11:47:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27432/100000 [8:05:04<11:48:14,  1.71it/s]
Train steps ... :  27%|██▋       | 27433/100000 [8:05:04<11:47:24,  1.71it/s]
Train steps ... :  27%|██▋       | 27434/100000 [8:05:05<11:47:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27435/100000 [8:05:06<11:48:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27436/100000 [8:05:06<11:48:34,  1.71it/s]
Train steps ... :  27%|██▋       | 27437/100000 [8:05:07<11:49:01,  1.71it/s]
Train steps ... :  27%|██▋       | 27438/100000 [8:05:07<11:47:40,  1.71it/s]
Train steps ... :  27%|██▋       | 27439/100000 [8:05:08<11:47:03,  1.71it/s]
Train steps ... :  27%|██▋       | 27440/100000 [8:05:08<11:46:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27441/100000 [8:05:09<11:46:45,  1.71it/s]
Train steps ... :  27%|██▋       | 27442/100000 [8:05:10<11:46:41,  1.71it/s]
Train steps ... :  27%|██▋       | 27443/100000 [8:05:10<11:46:10,  1.71it/s]
Train steps ... :  27%|██▋       | 27444/100000 [8:05:11<11:46:16,  1.71it/s]
Train steps ... :  27%|██▋       | 27445/100000 [8:05:11<11:46:25,  1.71it/s]
Train steps ... :  27%|██▋       | 27446/100000 [8:05:12<11:46:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27447/100000 [8:05:13<11:46:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27448/100000 [8:05:13<11:46:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27449/100000 [8:05:14<11:46:37,  1.71it/s]
Train steps ... :  27%|██▋       | 27450/100000 [8:05:14<11:47:07,  1.71it/s]Step... (27450 / 100000 | Loss: 0.7807537317276001, Learning Rate: 7.291457286432161e-05)
+
                                                                             
Step... (27450 / 100000 | Loss: 0.9266136884689331, Learning Rate: 7.291457286432161e-05)
+
Train steps ... :  27%|██▋       | 27450/100000 [8:05:15<11:47:07,  1.71it/s]
Train steps ... :  27%|██▋       | 27451/100000 [8:05:15<11:47:29,  1.71it/s]
Train steps ... :  27%|██▋       | 27452/100000 [8:05:15<11:46:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27453/100000 [8:05:16<11:48:35,  1.71it/s]
Train steps ... :  27%|██▋       | 27454/100000 [8:05:17<11:46:54,  1.71it/s]
Train steps ... :  27%|██▋       | 27455/100000 [8:05:17<11:47:52,  1.71it/s]
Train steps ... :  27%|██▋       | 27456/100000 [8:05:18<11:48:05,  1.71it/s]
Train steps ... :  27%|██▋       | 27457/100000 [8:05:18<11:48:47,  1.71it/s]
Train steps ... :  27%|██▋       | 27458/100000 [8:05:19<11:48:00,  1.71it/s]
Train steps ... :  27%|██▋       | 27459/100000 [8:05:20<11:47:50,  1.71it/s]
Train steps ... :  27%|██▋       | 27460/100000 [8:05:20<11:47:06,  1.71it/s]
Train steps ... :  27%|██▋       | 27461/100000 [8:05:21<11:47:00,  1.71it/s]
Train steps ... :  27%|██▋       | 27462/100000 [8:05:21<11:46:38,  1.71it/s]
Train steps ... :  27%|██▋       | 27463/100000 [8:05:22<11:46:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27464/100000 [8:05:22<11:46:54,  1.71it/s]
Train steps ... :  27%|██▋       | 27465/100000 [8:05:23<11:46:51,  1.71it/s]
Train steps ... :  27%|██▋       | 27466/100000 [8:05:24<11:46:20,  1.71it/s]
Train steps ... :  27%|██▋       | 27467/100000 [8:05:24<11:47:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27468/100000 [8:05:25<11:46:54,  1.71it/s]
Train steps ... :  27%|██▋       | 27469/100000 [8:05:25<11:46:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27470/100000 [8:05:26<11:46:48,  1.71it/s]
Train steps ... :  27%|██▋       | 27471/100000 [8:05:27<11:46:15,  1.71it/s]
Train steps ... :  27%|██▋       | 27472/100000 [8:05:27<11:45:58,  1.71it/s]
Train steps ... :  27%|██▋       | 27473/100000 [8:05:28<11:45:21,  1.71it/s]
Train steps ... :  27%|██▋       | 27474/100000 [8:05:28<11:45:50,  1.71it/s]
Train steps ... :  27%|██▋       | 27475/100000 [8:05:29<11:47:13,  1.71it/s]Step... (27475 / 100000 | Loss: 0.9583096504211426, Learning Rate: 7.288944723618091e-05)
+
                                                                             
Step... (27475 / 100000 | Loss: 0.6849565505981445, Learning Rate: 7.288944723618091e-05)
+
Train steps ... :  27%|██▋       | 27475/100000 [8:05:29<11:47:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27476/100000 [8:05:29<11:46:53,  1.71it/s]
Train steps ... :  27%|██▋       | 27477/100000 [8:05:30<11:46:43,  1.71it/s]
Train steps ... :  27%|██▋       | 27478/100000 [8:05:31<11:46:27,  1.71it/s]
Train steps ... :  27%|██▋       | 27479/100000 [8:05:31<11:46:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27480/100000 [8:05:32<11:46:38,  1.71it/s]
Train steps ... :  27%|██▋       | 27481/100000 [8:05:32<11:46:25,  1.71it/s]
Train steps ... :  27%|██▋       | 27482/100000 [8:05:33<11:46:13,  1.71it/s]
Train steps ... :  27%|██▋       | 27483/100000 [8:05:34<11:46:41,  1.71it/s]
Train steps ... :  27%|██▋       | 27484/100000 [8:05:34<11:46:59,  1.71it/s]
Train steps ... :  27%|██▋       | 27485/100000 [8:05:35<11:46:34,  1.71it/s]
Train steps ... :  27%|██▋       | 27486/100000 [8:05:35<11:46:27,  1.71it/s]
Train steps ... :  27%|██▋       | 27487/100000 [8:05:36<11:47:36,  1.71it/s]
Train steps ... :  27%|██▋       | 27488/100000 [8:05:37<11:48:03,  1.71it/s]
Train steps ... :  27%|██▋       | 27489/100000 [8:05:37<11:47:53,  1.71it/s]
Train steps ... :  27%|██▋       | 27490/100000 [8:05:38<11:48:57,  1.70it/s]
Train steps ... :  27%|██▋       | 27491/100000 [8:05:38<11:48:47,  1.70it/s]
Train steps ... :  27%|██▋       | 27492/100000 [8:05:39<11:49:26,  1.70it/s]
Train steps ... :  27%|██▋       | 27493/100000 [8:05:39<11:48:19,  1.71it/s]
Train steps ... :  27%|██▋       | 27494/100000 [8:05:40<11:48:16,  1.71it/s]
Train steps ... :  27%|██▋       | 27495/100000 [8:05:41<11:48:54,  1.70it/s]
Train steps ... :  27%|██▋       | 27496/100000 [8:05:41<11:48:05,  1.71it/s]
Train steps ... :  27%|██▋       | 27497/100000 [8:05:42<11:47:39,  1.71it/s]
Train steps ... :  27%|██▋       | 27498/100000 [8:05:42<11:47:33,  1.71it/s]
Train steps ... :  27%|██▋       | 27499/100000 [8:05:43<11:47:33,  1.71it/s]
Train steps ... :  28%|██▊       | 27500/100000 [8:05:44<11:46:55,  1.71it/s]Step... (27500 / 100000 | Loss: 1.074033498764038, Learning Rate: 7.28643216080402e-05)
+
                                                                             
Step... (27500 / 100000 | Loss: 1.0804632902145386, Learning Rate: 7.28643216080402e-05)
+
Train steps ... :  28%|██▊       | 27500/100000 [8:05:44<11:46:55,  1.71it/s]
Train steps ... :  28%|██▊       | 27501/100000 [8:05:44<11:46:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27502/100000 [8:05:45<11:46:42,  1.71it/s]
Train steps ... :  28%|██▊       | 27503/100000 [8:05:45<11:46:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27504/100000 [8:05:46<11:48:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27505/100000 [8:05:46<11:47:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27506/100000 [8:05:47<11:47:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27507/100000 [8:05:48<11:47:04,  1.71it/s]
Train steps ... :  28%|██▊       | 27508/100000 [8:05:48<11:46:20,  1.71it/s]
Train steps ... :  28%|██▊       | 27509/100000 [8:05:49<11:47:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27510/100000 [8:05:49<11:46:47,  1.71it/s]
Train steps ... :  28%|██▊       | 27511/100000 [8:05:50<11:46:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27512/100000 [8:05:51<11:47:00,  1.71it/s]
Train steps ... :  28%|██▊       | 27513/100000 [8:05:51<11:47:28,  1.71it/s]
Train steps ... :  28%|██▊       | 27514/100000 [8:05:52<11:47:06,  1.71it/s]
Train steps ... :  28%|██▊       | 27515/100000 [8:05:52<11:46:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27516/100000 [8:05:53<11:46:47,  1.71it/s]
Train steps ... :  28%|██▊       | 27517/100000 [8:05:53<11:47:32,  1.71it/s]
Train steps ... :  28%|██▊       | 27518/100000 [8:05:54<11:47:27,  1.71it/s]
Train steps ... :  28%|██▊       | 27519/100000 [8:05:55<11:46:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27520/100000 [8:05:55<11:45:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27521/100000 [8:05:56<11:46:57,  1.71it/s]
Train steps ... :  28%|██▊       | 27522/100000 [8:05:56<11:46:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27523/100000 [8:05:57<11:47:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27524/100000 [8:05:58<11:46:44,  1.71it/s]
Train steps ... :  28%|██▊       | 27525/100000 [8:05:58<11:46:31,  1.71it/s]Step... (27525 / 100000 | Loss: 1.1045331954956055, Learning Rate: 7.28391959798995e-05)
+
                                                                             
Step... (27525 / 100000 | Loss: 0.8185467720031738, Learning Rate: 7.28391959798995e-05)
+
Train steps ... :  28%|██▊       | 27525/100000 [8:05:58<11:46:31,  1.71it/s]
Train steps ... :  28%|██▊       | 27526/100000 [8:05:59<11:46:43,  1.71it/s]
Train steps ... :  28%|██▊       | 27527/100000 [8:05:59<11:46:42,  1.71it/s]
Train steps ... :  28%|██▊       | 27528/100000 [8:06:00<11:45:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27529/100000 [8:06:01<11:45:30,  1.71it/s]
Train steps ... :  28%|██▊       | 27530/100000 [8:06:01<11:45:13,  1.71it/s]
Train steps ... :  28%|██▊       | 27531/100000 [8:06:02<11:45:44,  1.71it/s]
Train steps ... :  28%|██▊       | 27532/100000 [8:06:02<11:45:49,  1.71it/s]
Train steps ... :  28%|██▊       | 27533/100000 [8:06:03<11:46:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27534/100000 [8:06:03<11:45:46,  1.71it/s]
Train steps ... :  28%|██▊       | 27535/100000 [8:06:04<11:45:32,  1.71it/s]
Train steps ... :  28%|██▊       | 27536/100000 [8:06:05<11:45:21,  1.71it/s]
Train steps ... :  28%|██▊       | 27537/100000 [8:06:05<11:46:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27538/100000 [8:06:06<11:45:43,  1.71it/s]
Train steps ... :  28%|██▊       | 27539/100000 [8:06:06<11:45:35,  1.71it/s]
Train steps ... :  28%|██▊       | 27540/100000 [8:06:07<11:45:30,  1.71it/s]
Train steps ... :  28%|██▊       | 27541/100000 [8:06:08<11:46:28,  1.71it/s]
Train steps ... :  28%|██▊       | 27542/100000 [8:06:08<11:45:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27543/100000 [8:06:09<11:46:21,  1.71it/s]
Train steps ... :  28%|██▊       | 27544/100000 [8:06:09<11:46:27,  1.71it/s]
Train steps ... :  28%|██▊       | 27545/100000 [8:06:10<11:47:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27546/100000 [8:06:10<11:46:33,  1.71it/s]
Train steps ... :  28%|██▊       | 27547/100000 [8:06:11<11:46:04,  1.71it/s]
Train steps ... :  28%|██▊       | 27548/100000 [8:06:12<11:46:28,  1.71it/s]
Train steps ... :  28%|██▊       | 27549/100000 [8:06:12<11:46:01,  1.71it/s]
Train steps ... :  28%|██▊       | 27550/100000 [8:06:13<11:46:16,  1.71it/s]Step... (27550 / 100000 | Loss: 0.7569035291671753, Learning Rate: 7.28140703517588e-05)
+
                                                                             
Step... (27550 / 100000 | Loss: 1.2910805940628052, Learning Rate: 7.28140703517588e-05)
+
Train steps ... :  28%|██▊       | 27550/100000 [8:06:13<11:46:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27551/100000 [8:06:13<11:47:18,  1.71it/s]
Train steps ... :  28%|██▊       | 27552/100000 [8:06:14<11:48:03,  1.71it/s]
Train steps ... :  28%|██▊       | 27553/100000 [8:06:15<11:46:48,  1.71it/s]
Train steps ... :  28%|██▊       | 27554/100000 [8:06:15<11:46:23,  1.71it/s]
Train steps ... :  28%|██▊       | 27555/100000 [8:06:16<11:45:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27556/100000 [8:06:16<11:47:32,  1.71it/s]
Train steps ... :  28%|██▊       | 27557/100000 [8:06:17<11:48:26,  1.70it/s]
Train steps ... :  28%|██▊       | 27558/100000 [8:06:17<11:46:59,  1.71it/s]
Train steps ... :  28%|██▊       | 27559/100000 [8:06:18<11:46:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27560/100000 [8:06:19<11:45:44,  1.71it/s]
Train steps ... :  28%|██▊       | 27561/100000 [8:06:19<11:46:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27562/100000 [8:06:20<11:45:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27563/100000 [8:06:20<11:45:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27564/100000 [8:06:21<11:44:46,  1.71it/s]
Train steps ... :  28%|██▊       | 27565/100000 [8:06:22<11:45:21,  1.71it/s]
Train steps ... :  28%|██▊       | 27566/100000 [8:06:22<11:45:28,  1.71it/s]
Train steps ... :  28%|██▊       | 27567/100000 [8:06:23<11:45:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27568/100000 [8:06:23<11:45:20,  1.71it/s]
Train steps ... :  28%|██▊       | 27569/100000 [8:06:24<11:45:32,  1.71it/s]
Train steps ... :  28%|██▊       | 27570/100000 [8:06:24<11:45:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27571/100000 [8:06:25<11:45:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27572/100000 [8:06:26<11:45:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27573/100000 [8:06:26<11:45:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27574/100000 [8:06:27<11:45:06,  1.71it/s]
Train steps ... :  28%|██▊       | 27575/100000 [8:06:27<11:45:16,  1.71it/s]Step... (27575 / 100000 | Loss: 0.7447910308837891, Learning Rate: 7.27889447236181e-05)
+
                                                                             
Step... (27575 / 100000 | Loss: 0.9612799882888794, Learning Rate: 7.27889447236181e-05)
+
Train steps ... :  28%|██▊       | 27575/100000 [8:06:28<11:45:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27576/100000 [8:06:28<11:45:48,  1.71it/s]
Train steps ... :  28%|██▊       | 27577/100000 [8:06:29<11:46:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27578/100000 [8:06:29<11:46:48,  1.71it/s]
Train steps ... :  28%|██▊       | 27579/100000 [8:06:30<11:45:42,  1.71it/s]
Train steps ... :  28%|██▊       | 27580/100000 [8:06:30<11:46:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27581/100000 [8:06:31<11:45:45,  1.71it/s]
Train steps ... :  28%|██▊       | 27582/100000 [8:06:31<11:45:22,  1.71it/s]
Train steps ... :  28%|██▊       | 27583/100000 [8:06:32<11:46:06,  1.71it/s]
Train steps ... :  28%|██▊       | 27584/100000 [8:06:33<11:46:24,  1.71it/s]
Train steps ... :  28%|██▊       | 27585/100000 [8:06:33<11:44:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27586/100000 [8:06:34<11:45:32,  1.71it/s]
Train steps ... :  28%|██▊       | 27587/100000 [8:06:34<11:45:07,  1.71it/s]
Train steps ... :  28%|██▊       | 27588/100000 [8:06:35<11:45:21,  1.71it/s]
Train steps ... :  28%|██▊       | 27589/100000 [8:06:36<11:45:04,  1.71it/s]
Train steps ... :  28%|██▊       | 27590/100000 [8:06:36<11:44:34,  1.71it/s]
Train steps ... :  28%|██▊       | 27591/100000 [8:06:37<11:44:29,  1.71it/s]
Train steps ... :  28%|██▊       | 27592/100000 [8:06:37<11:45:21,  1.71it/s]
Train steps ... :  28%|██▊       | 27593/100000 [8:06:38<11:45:11,  1.71it/s]
Train steps ... :  28%|██▊       | 27594/100000 [8:06:39<11:44:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27595/100000 [8:06:39<11:45:14,  1.71it/s]
Train steps ... :  28%|██▊       | 27596/100000 [8:06:40<11:44:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27597/100000 [8:06:40<11:45:11,  1.71it/s]
Train steps ... :  28%|██▊       | 27598/100000 [8:06:41<11:45:49,  1.71it/s]
Train steps ... :  28%|██▊       | 27599/100000 [8:06:41<11:44:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27600/100000 [8:06:42<11:44:33,  1.71it/s]Step... (27600 / 100000 | Loss: 0.694475531578064, Learning Rate: 7.276381909547739e-05)
+
                                                                             
Step... (27600 / 100000 | Loss: 1.0460433959960938, Learning Rate: 7.276381909547739e-05)
+
Train steps ... :  28%|██▊       | 27600/100000 [8:06:42<11:44:33,  1.71it/s]
Train steps ... :  28%|██▊       | 27601/100000 [8:06:43<11:45:03,  1.71it/s]
Train steps ... :  28%|██▊       | 27602/100000 [8:06:43<11:44:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27603/100000 [8:06:44<11:45:10,  1.71it/s]
Train steps ... :  28%|██▊       | 27604/100000 [8:06:44<11:44:43,  1.71it/s]
Train steps ... :  28%|██▊       | 27605/100000 [8:06:45<11:44:57,  1.71it/s]
Train steps ... :  28%|██▊       | 27606/100000 [8:06:46<11:45:42,  1.71it/s]
Train steps ... :  28%|██▊       | 27607/100000 [8:06:46<11:46:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27608/100000 [8:06:47<11:46:40,  1.71it/s]
Train steps ... :  28%|██▊       | 27609/100000 [8:06:47<11:46:26,  1.71it/s]
Train steps ... :  28%|██▊       | 27610/100000 [8:06:48<11:45:48,  1.71it/s]
Train steps ... :  28%|██▊       | 27611/100000 [8:06:48<11:47:45,  1.70it/s]
Train steps ... :  28%|██▊       | 27612/100000 [8:06:49<11:46:56,  1.71it/s]
Train steps ... :  28%|██▊       | 27613/100000 [8:06:50<11:47:02,  1.71it/s]
Train steps ... :  28%|██▊       | 27614/100000 [8:06:50<11:46:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27615/100000 [8:06:51<11:46:41,  1.71it/s]
Train steps ... :  28%|██▊       | 27616/100000 [8:06:51<11:45:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27617/100000 [8:06:52<11:45:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27618/100000 [8:06:53<11:45:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27619/100000 [8:06:53<11:45:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27620/100000 [8:06:54<11:46:13,  1.71it/s]
Train steps ... :  28%|██▊       | 27621/100000 [8:06:54<11:45:41,  1.71it/s]
Train steps ... :  28%|██▊       | 27622/100000 [8:06:55<11:45:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27623/100000 [8:06:55<11:45:21,  1.71it/s]
Train steps ... :  28%|██▊       | 27624/100000 [8:06:56<11:44:41,  1.71it/s]
Train steps ... :  28%|██▊       | 27625/100000 [8:06:57<11:44:40,  1.71it/s]Step... (27625 / 100000 | Loss: 1.0657806396484375, Learning Rate: 7.273869346733669e-05)
+
                                                                             
Step... (27625 / 100000 | Loss: 0.7875950336456299, Learning Rate: 7.273869346733669e-05)
+
Train steps ... :  28%|██▊       | 27625/100000 [8:06:57<11:44:40,  1.71it/s]
Train steps ... :  28%|██▊       | 27626/100000 [8:06:57<11:46:02,  1.71it/s]
Train steps ... :  28%|██▊       | 27627/100000 [8:06:58<11:47:01,  1.71it/s]
Train steps ... :  28%|██▊       | 27628/100000 [8:06:58<11:46:42,  1.71it/s]
Train steps ... :  28%|██▊       | 27629/100000 [8:06:59<11:46:28,  1.71it/s]
Train steps ... :  28%|██▊       | 27630/100000 [8:07:00<11:45:55,  1.71it/s]
Train steps ... :  28%|██▊       | 27631/100000 [8:07:00<11:46:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27632/100000 [8:07:01<11:46:11,  1.71it/s]
Train steps ... :  28%|██▊       | 27633/100000 [8:07:01<11:46:34,  1.71it/s]
Train steps ... :  28%|██▊       | 27634/100000 [8:07:02<11:44:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27635/100000 [8:07:02<11:45:52,  1.71it/s]
Train steps ... :  28%|██▊       | 27636/100000 [8:07:03<11:47:06,  1.71it/s]
Train steps ... :  28%|██▊       | 27637/100000 [8:07:04<11:45:31,  1.71it/s]
Train steps ... :  28%|██▊       | 27638/100000 [8:07:04<11:45:25,  1.71it/s]
Train steps ... :  28%|██▊       | 27639/100000 [8:07:05<11:44:19,  1.71it/s]
Train steps ... :  28%|██▊       | 27640/100000 [8:07:05<11:44:15,  1.71it/s]
Train steps ... :  28%|██▊       | 27641/100000 [8:07:06<11:45:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27642/100000 [8:07:07<11:45:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27643/100000 [8:07:07<11:45:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27644/100000 [8:07:08<11:46:15,  1.71it/s]
Train steps ... :  28%|██▊       | 27645/100000 [8:07:08<11:45:53,  1.71it/s]
Train steps ... :  28%|██▊       | 27646/100000 [8:07:09<11:46:27,  1.71it/s]
Train steps ... :  28%|██▊       | 27647/100000 [8:07:10<11:45:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27648/100000 [8:07:10<11:45:02,  1.71it/s]
Train steps ... :  28%|██▊       | 27649/100000 [8:07:11<11:44:37,  1.71it/s]
Train steps ... :  28%|██▊       | 27650/100000 [8:07:11<11:44:20,  1.71it/s]Step... (27650 / 100000 | Loss: 0.7450269460678101, Learning Rate: 7.271356783919599e-05)
+
                                                                             
Step... (27650 / 100000 | Loss: 0.7627832889556885, Learning Rate: 7.271356783919599e-05)
+
Train steps ... :  28%|██▊       | 27650/100000 [8:07:12<11:44:20,  1.71it/s]
Train steps ... :  28%|██▊       | 27651/100000 [8:07:12<11:45:34,  1.71it/s]
Train steps ... :  28%|██▊       | 27652/100000 [8:07:12<11:44:47,  1.71it/s]
Train steps ... :  28%|██▊       | 27653/100000 [8:07:13<11:44:31,  1.71it/s]
Train steps ... :  28%|██▊       | 27654/100000 [8:07:14<11:44:37,  1.71it/s]
Train steps ... :  28%|██▊       | 27655/100000 [8:07:14<11:44:11,  1.71it/s]
Train steps ... :  28%|██▊       | 27656/100000 [8:07:15<11:44:41,  1.71it/s]
Train steps ... :  28%|██▊       | 27657/100000 [8:07:15<11:45:25,  1.71it/s]
Train steps ... :  28%|██▊       | 27658/100000 [8:07:16<11:44:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27659/100000 [8:07:17<11:44:25,  1.71it/s]
Train steps ... :  28%|██▊       | 27660/100000 [8:07:17<11:44:32,  1.71it/s]
Train steps ... :  28%|██▊       | 27661/100000 [8:07:18<11:46:07,  1.71it/s]
Train steps ... :  28%|██▊       | 27662/100000 [8:07:18<11:46:14,  1.71it/s]
Train steps ... :  28%|██▊       | 27663/100000 [8:07:19<11:45:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27664/100000 [8:07:19<11:45:33,  1.71it/s]
Train steps ... :  28%|██▊       | 27665/100000 [8:07:20<11:45:29,  1.71it/s]
Train steps ... :  28%|██▊       | 27666/100000 [8:07:21<11:45:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27667/100000 [8:07:21<11:45:25,  1.71it/s]
Train steps ... :  28%|██▊       | 27668/100000 [8:07:22<11:45:04,  1.71it/s]
Train steps ... :  28%|██▊       | 27669/100000 [8:07:22<11:45:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27670/100000 [8:07:23<11:45:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27671/100000 [8:07:24<11:45:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27672/100000 [8:07:24<11:45:27,  1.71it/s]
Train steps ... :  28%|██▊       | 27673/100000 [8:07:25<11:45:57,  1.71it/s]
Train steps ... :  28%|██▊       | 27674/100000 [8:07:25<11:45:20,  1.71it/s]
Train steps ... :  28%|██▊       | 27675/100000 [8:07:26<11:45:21,  1.71it/s]Step... (27675 / 100000 | Loss: 0.925172746181488, Learning Rate: 7.268844221105528e-05)
+
                                                                             
Step... (27675 / 100000 | Loss: 1.2952227592468262, Learning Rate: 7.268844221105528e-05)
+
Train steps ... :  28%|██▊       | 27675/100000 [8:07:26<11:45:21,  1.71it/s]
Train steps ... :  28%|██▊       | 27676/100000 [8:07:26<11:45:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27677/100000 [8:07:27<11:44:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27678/100000 [8:07:28<11:44:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27679/100000 [8:07:28<11:45:08,  1.71it/s]
Train steps ... :  28%|██▊       | 27680/100000 [8:07:29<11:44:31,  1.71it/s]
Train steps ... :  28%|██▊       | 27681/100000 [8:07:29<11:44:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27682/100000 [8:07:30<11:44:14,  1.71it/s]
Train steps ... :  28%|██▊       | 27683/100000 [8:07:31<11:45:11,  1.71it/s]
Train steps ... :  28%|██▊       | 27684/100000 [8:07:31<11:44:48,  1.71it/s]
Train steps ... :  28%|██▊       | 27685/100000 [8:07:32<11:44:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27686/100000 [8:07:32<11:44:25,  1.71it/s]
Train steps ... :  28%|██▊       | 27687/100000 [8:07:33<11:44:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27688/100000 [8:07:33<11:44:41,  1.71it/s]
Train steps ... :  28%|██▊       | 27689/100000 [8:07:34<11:44:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27690/100000 [8:07:35<11:44:41,  1.71it/s]
Train steps ... :  28%|██▊       | 27691/100000 [8:07:35<11:44:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27692/100000 [8:07:36<11:44:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27693/100000 [8:07:36<11:44:37,  1.71it/s]
Train steps ... :  28%|██▊       | 27694/100000 [8:07:37<11:45:15,  1.71it/s]
Train steps ... :  28%|██▊       | 27695/100000 [8:07:38<11:44:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27696/100000 [8:07:38<11:43:46,  1.71it/s]
Train steps ... :  28%|██▊       | 27697/100000 [8:07:39<11:44:09,  1.71it/s]
Train steps ... :  28%|██▊       | 27698/100000 [8:07:39<11:44:18,  1.71it/s]
Train steps ... :  28%|██▊       | 27699/100000 [8:07:40<11:46:03,  1.71it/s]
Train steps ... :  28%|██▊       | 27700/100000 [8:07:41<11:43:56,  1.71it/s]Step... (27700 / 100000 | Loss: 0.8460663557052612, Learning Rate: 7.266331658291458e-05)
+
                                                                             
Step... (27700 / 100000 | Loss: 0.8195937871932983, Learning Rate: 7.266331658291458e-05)
+
Train steps ... :  28%|██▊       | 27700/100000 [8:07:41<11:43:56,  1.71it/s]
Train steps ... :  28%|██▊       | 27701/100000 [8:07:41<11:44:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27702/100000 [8:07:42<11:43:30,  1.71it/s]
Train steps ... :  28%|██▊       | 27703/100000 [8:07:42<11:44:02,  1.71it/s]
Train steps ... :  28%|██▊       | 27704/100000 [8:07:43<11:43:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27705/100000 [8:07:43<11:43:34,  1.71it/s]
Train steps ... :  28%|██▊       | 27706/100000 [8:07:44<11:43:21,  1.71it/s]
Train steps ... :  28%|██▊       | 27707/100000 [8:07:45<11:43:45,  1.71it/s]
Train steps ... :  28%|██▊       | 27708/100000 [8:07:45<11:44:03,  1.71it/s]
Train steps ... :  28%|██▊       | 27709/100000 [8:07:46<11:43:40,  1.71it/s]
Train steps ... :  28%|██▊       | 27710/100000 [8:07:46<11:44:20,  1.71it/s]
Train steps ... :  28%|██▊       | 27711/100000 [8:07:47<11:45:07,  1.71it/s]
Train steps ... :  28%|██▊       | 27712/100000 [8:07:48<11:44:18,  1.71it/s]
Train steps ... :  28%|██▊       | 27713/100000 [8:07:48<11:45:24,  1.71it/s]
Train steps ... :  28%|██▊       | 27714/100000 [8:07:49<11:45:06,  1.71it/s]
Train steps ... :  28%|██▊       | 27715/100000 [8:07:49<11:44:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27716/100000 [8:07:50<11:45:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27717/100000 [8:07:50<11:45:29,  1.71it/s]
Train steps ... :  28%|██▊       | 27718/100000 [8:07:51<11:45:31,  1.71it/s]
Train steps ... :  28%|██▊       | 27719/100000 [8:07:52<11:44:43,  1.71it/s]
Train steps ... :  28%|██▊       | 27720/100000 [8:07:52<11:45:27,  1.71it/s]
Train steps ... :  28%|██▊       | 27721/100000 [8:07:53<11:44:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27722/100000 [8:07:53<11:44:48,  1.71it/s]
Train steps ... :  28%|██▊       | 27723/100000 [8:07:54<11:44:09,  1.71it/s]
Train steps ... :  28%|██▊       | 27724/100000 [8:07:55<11:44:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27725/100000 [8:07:55<11:43:54,  1.71it/s]Step... (27725 / 100000 | Loss: 1.005741000175476, Learning Rate: 7.263819095477388e-05)
+
                                                                             
Step... (27725 / 100000 | Loss: 0.8493800163269043, Learning Rate: 7.263819095477388e-05)
+
Train steps ... :  28%|██▊       | 27725/100000 [8:07:55<11:43:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27726/100000 [8:07:56<11:44:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27727/100000 [8:07:56<11:44:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27728/100000 [8:07:57<11:44:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27729/100000 [8:07:57<11:45:09,  1.71it/s]
Train steps ... :  28%|██▊       | 27730/100000 [8:07:58<11:44:07,  1.71it/s]
Train steps ... :  28%|██▊       | 27731/100000 [8:07:59<11:45:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27732/100000 [8:07:59<11:44:53,  1.71it/s]
Train steps ... :  28%|██▊       | 27733/100000 [8:08:00<11:44:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27734/100000 [8:08:00<11:44:03,  1.71it/s]
Train steps ... :  28%|██▊       | 27735/100000 [8:08:01<11:43:44,  1.71it/s]
Train steps ... :  28%|██▊       | 27736/100000 [8:08:02<11:43:34,  1.71it/s]
Train steps ... :  28%|██▊       | 27737/100000 [8:08:02<11:44:34,  1.71it/s]
Train steps ... :  28%|██▊       | 27738/100000 [8:08:03<11:43:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27739/100000 [8:08:03<11:44:33,  1.71it/s]
Train steps ... :  28%|██▊       | 27740/100000 [8:08:04<11:43:47,  1.71it/s]
Train steps ... :  28%|██▊       | 27741/100000 [8:08:04<11:43:48,  1.71it/s]
Train steps ... :  28%|██▊       | 27742/100000 [8:08:05<11:43:42,  1.71it/s]
Train steps ... :  28%|██▊       | 27743/100000 [8:08:06<11:44:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27744/100000 [8:08:06<11:44:24,  1.71it/s]
Train steps ... :  28%|██▊       | 27745/100000 [8:08:07<11:43:34,  1.71it/s]
Train steps ... :  28%|██▊       | 27746/100000 [8:08:07<11:45:01,  1.71it/s]
Train steps ... :  28%|██▊       | 27747/100000 [8:08:08<11:44:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27748/100000 [8:08:09<11:43:41,  1.71it/s]
Train steps ... :  28%|██▊       | 27749/100000 [8:08:09<11:44:02,  1.71it/s]
Train steps ... :  28%|██▊       | 27750/100000 [8:08:10<11:43:29,  1.71it/s]Step... (27750 / 100000 | Loss: 0.7886276245117188, Learning Rate: 7.261306532663317e-05)
+
                                                                             
Step... (27750 / 100000 | Loss: 0.8871448040008545, Learning Rate: 7.261306532663317e-05)
+
Train steps ... :  28%|██▊       | 27750/100000 [8:08:10<11:43:29,  1.71it/s]
Train steps ... :  28%|██▊       | 27751/100000 [8:08:10<11:45:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27752/100000 [8:08:11<11:44:37,  1.71it/s]
Train steps ... :  28%|██▊       | 27753/100000 [8:08:12<11:44:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27754/100000 [8:08:12<11:43:57,  1.71it/s]
Train steps ... :  28%|██▊       | 27755/100000 [8:08:13<11:43:08,  1.71it/s]
Train steps ... :  28%|██▊       | 27756/100000 [8:08:13<11:43:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27757/100000 [8:08:14<11:43:56,  1.71it/s]
Train steps ... :  28%|██▊       | 27758/100000 [8:08:14<11:44:04,  1.71it/s]
Train steps ... :  28%|██▊       | 27759/100000 [8:08:15<11:45:14,  1.71it/s]
Train steps ... :  28%|██▊       | 27760/100000 [8:08:16<11:43:34,  1.71it/s]
Train steps ... :  28%|██▊       | 27761/100000 [8:08:16<11:43:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27762/100000 [8:08:17<11:43:37,  1.71it/s]
Train steps ... :  28%|██▊       | 27763/100000 [8:08:17<11:45:09,  1.71it/s]
Train steps ... :  28%|██▊       | 27764/100000 [8:08:18<11:44:01,  1.71it/s]
Train steps ... :  28%|██▊       | 27765/100000 [8:08:19<11:43:57,  1.71it/s]
Train steps ... :  28%|██▊       | 27766/100000 [8:08:19<11:43:33,  1.71it/s]
Train steps ... :  28%|██▊       | 27767/100000 [8:08:20<11:43:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27768/100000 [8:08:20<11:43:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27769/100000 [8:08:21<11:42:59,  1.71it/s]
Train steps ... :  28%|██▊       | 27770/100000 [8:08:21<11:43:29,  1.71it/s]
Train steps ... :  28%|██▊       | 27771/100000 [8:08:22<11:44:07,  1.71it/s]
Train steps ... :  28%|██▊       | 27772/100000 [8:08:23<11:43:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27773/100000 [8:08:23<11:43:25,  1.71it/s]
Train steps ... :  28%|██▊       | 27774/100000 [8:08:24<11:43:10,  1.71it/s]
Train steps ... :  28%|██▊       | 27775/100000 [8:08:24<11:43:04,  1.71it/s]Step... (27775 / 100000 | Loss: 0.9462150931358337, Learning Rate: 7.258793969849247e-05)
+
                                                                             
Step... (27775 / 100000 | Loss: 0.8561854362487793, Learning Rate: 7.258793969849247e-05)
+
Train steps ... :  28%|██▊       | 27775/100000 [8:08:25<11:43:04,  1.71it/s]
Train steps ... :  28%|██▊       | 27776/100000 [8:08:25<11:43:18,  1.71it/s]
Train steps ... :  28%|██▊       | 27777/100000 [8:08:26<11:43:07,  1.71it/s]
Train steps ... :  28%|██▊       | 27778/100000 [8:08:26<11:42:43,  1.71it/s]
Train steps ... :  28%|██▊       | 27779/100000 [8:08:27<11:43:07,  1.71it/s]
Train steps ... :  28%|██▊       | 27780/100000 [8:08:27<11:43:43,  1.71it/s]
Train steps ... :  28%|██▊       | 27781/100000 [8:08:28<11:46:01,  1.70it/s]
Train steps ... :  28%|██▊       | 27782/100000 [8:08:28<11:43:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27783/100000 [8:08:29<11:44:06,  1.71it/s]
Train steps ... :  28%|██▊       | 27784/100000 [8:08:30<11:43:24,  1.71it/s]
Train steps ... :  28%|██▊       | 27785/100000 [8:08:30<11:44:03,  1.71it/s]
Train steps ... :  28%|██▊       | 27786/100000 [8:08:31<11:43:42,  1.71it/s]
Train steps ... :  28%|██▊       | 27787/100000 [8:08:31<11:43:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27788/100000 [8:08:32<11:43:41,  1.71it/s]
Train steps ... :  28%|██▊       | 27789/100000 [8:08:33<11:44:07,  1.71it/s]
Train steps ... :  28%|██▊       | 27790/100000 [8:08:33<11:44:28,  1.71it/s]
Train steps ... :  28%|██▊       | 27791/100000 [8:08:34<11:44:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27792/100000 [8:08:34<11:43:23,  1.71it/s]
Train steps ... :  28%|██▊       | 27793/100000 [8:08:35<11:43:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27794/100000 [8:08:35<11:43:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27795/100000 [8:08:36<11:43:15,  1.71it/s]
Train steps ... :  28%|██▊       | 27796/100000 [8:08:37<11:42:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27797/100000 [8:08:37<11:42:26,  1.71it/s]
Train steps ... :  28%|██▊       | 27798/100000 [8:08:38<11:43:31,  1.71it/s]
Train steps ... :  28%|██▊       | 27799/100000 [8:08:38<11:43:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27800/100000 [8:08:39<11:43:55,  1.71it/s]Step... (27800 / 100000 | Loss: 0.9353333115577698, Learning Rate: 7.256281407035177e-05)
+
                                                                             
Step... (27800 / 100000 | Loss: 1.0749626159667969, Learning Rate: 7.256281407035177e-05)
+
Train steps ... :  28%|██▊       | 27800/100000 [8:08:39<11:43:55,  1.71it/s]
Train steps ... :  28%|██▊       | 27801/100000 [8:08:40<11:43:24,  1.71it/s]
Train steps ... :  28%|██▊       | 27802/100000 [8:08:40<11:44:08,  1.71it/s]
Train steps ... :  28%|██▊       | 27803/100000 [8:08:41<11:43:00,  1.71it/s]
Train steps ... :  28%|██▊       | 27804/100000 [8:08:41<11:43:30,  1.71it/s]
Train steps ... :  28%|██▊       | 27805/100000 [8:08:42<11:43:10,  1.71it/s]
Train steps ... :  28%|██▊       | 27806/100000 [8:08:42<11:43:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27807/100000 [8:08:43<11:42:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27808/100000 [8:08:44<11:43:31,  1.71it/s]
Train steps ... :  28%|██▊       | 27809/100000 [8:08:44<11:43:19,  1.71it/s]
Train steps ... :  28%|██▊       | 27810/100000 [8:08:45<11:43:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27811/100000 [8:08:45<11:43:44,  1.71it/s]
Train steps ... :  28%|██▊       | 27812/100000 [8:08:46<11:44:06,  1.71it/s]
Train steps ... :  28%|██▊       | 27813/100000 [8:08:47<11:43:04,  1.71it/s]
Train steps ... :  28%|██▊       | 27814/100000 [8:08:47<11:44:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27815/100000 [8:08:48<11:42:55,  1.71it/s]
Train steps ... :  28%|██▊       | 27816/100000 [8:08:48<11:44:06,  1.71it/s]
Train steps ... :  28%|██▊       | 27817/100000 [8:08:49<11:42:14,  1.71it/s]
Train steps ... :  28%|██▊       | 27818/100000 [8:08:50<11:42:00,  1.71it/s]
Train steps ... :  28%|██▊       | 27819/100000 [8:08:50<11:42:46,  1.71it/s]
Train steps ... :  28%|██▊       | 27820/100000 [8:08:51<11:43:13,  1.71it/s]
Train steps ... :  28%|██▊       | 27821/100000 [8:08:51<11:42:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27822/100000 [8:08:52<11:42:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27823/100000 [8:08:52<11:43:13,  1.71it/s]
Train steps ... :  28%|██▊       | 27824/100000 [8:08:53<11:42:52,  1.71it/s]
Train steps ... :  28%|██▊       | 27825/100000 [8:08:54<11:43:26,  1.71it/s]Step... (27825 / 100000 | Loss: 0.8826583027839661, Learning Rate: 7.253768844221106e-05)
+
                                                                             
Step... (27825 / 100000 | Loss: 0.7948375940322876, Learning Rate: 7.253768844221106e-05)
+
Train steps ... :  28%|██▊       | 27825/100000 [8:08:54<11:43:26,  1.71it/s]
Train steps ... :  28%|██▊       | 27826/100000 [8:08:54<11:42:53,  1.71it/s]
Train steps ... :  28%|██▊       | 27827/100000 [8:08:55<11:42:40,  1.71it/s]
Train steps ... :  28%|██▊       | 27828/100000 [8:08:55<11:42:10,  1.71it/s]
Train steps ... :  28%|██▊       | 27829/100000 [8:08:56<11:41:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27830/100000 [8:08:57<11:41:45,  1.71it/s]
Train steps ... :  28%|██▊       | 27831/100000 [8:08:57<11:43:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27832/100000 [8:08:58<11:43:26,  1.71it/s]
Train steps ... :  28%|██▊       | 27833/100000 [8:08:58<11:43:48,  1.71it/s]
Train steps ... :  28%|██▊       | 27834/100000 [8:08:59<11:44:53,  1.71it/s]
Train steps ... :  28%|██▊       | 27835/100000 [8:08:59<11:45:41,  1.70it/s]
Train steps ... :  28%|██▊       | 27836/100000 [8:09:00<11:44:26,  1.71it/s]
Train steps ... :  28%|██▊       | 27837/100000 [8:09:01<11:44:18,  1.71it/s]
Train steps ... :  28%|██▊       | 27838/100000 [8:09:01<11:44:00,  1.71it/s]
Train steps ... :  28%|██▊       | 27839/100000 [8:09:02<11:43:44,  1.71it/s]
Train steps ... :  28%|██▊       | 27840/100000 [8:09:02<11:43:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27841/100000 [8:09:03<11:42:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27842/100000 [8:09:04<11:43:34,  1.71it/s]
Train steps ... :  28%|██▊       | 27843/100000 [8:09:04<11:42:43,  1.71it/s]
Train steps ... :  28%|██▊       | 27844/100000 [8:09:05<11:42:34,  1.71it/s]
Train steps ... :  28%|██▊       | 27845/100000 [8:09:05<11:42:30,  1.71it/s]
Train steps ... :  28%|██▊       | 27846/100000 [8:09:06<11:43:00,  1.71it/s]
Train steps ... :  28%|██▊       | 27847/100000 [8:09:06<11:43:00,  1.71it/s]
Train steps ... :  28%|██▊       | 27848/100000 [8:09:07<11:44:00,  1.71it/s]
Train steps ... :  28%|██▊       | 27849/100000 [8:09:08<11:43:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27850/100000 [8:09:08<11:42:47,  1.71it/s]Step... (27850 / 100000 | Loss: 0.9978671073913574, Learning Rate: 7.251256281407035e-05)
+
                                                                             
Step... (27850 / 100000 | Loss: 0.944511890411377, Learning Rate: 7.251256281407035e-05)
+
Train steps ... :  28%|██▊       | 27850/100000 [8:09:09<11:42:47,  1.71it/s]
Train steps ... :  28%|██▊       | 27851/100000 [8:09:09<11:43:31,  1.71it/s]
Train steps ... :  28%|██▊       | 27852/100000 [8:09:09<11:42:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27853/100000 [8:09:10<11:42:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27854/100000 [8:09:11<11:42:27,  1.71it/s]
Train steps ... :  28%|██▊       | 27855/100000 [8:09:11<11:43:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27856/100000 [8:09:12<11:43:30,  1.71it/s]
Train steps ... :  28%|██▊       | 27857/100000 [8:09:12<11:42:31,  1.71it/s]
Train steps ... :  28%|██▊       | 27858/100000 [8:09:13<11:42:08,  1.71it/s]
Train steps ... :  28%|██▊       | 27859/100000 [8:09:13<11:41:57,  1.71it/s]
Train steps ... :  28%|██▊       | 27860/100000 [8:09:14<11:41:52,  1.71it/s]
Train steps ... :  28%|██▊       | 27861/100000 [8:09:15<11:43:43,  1.71it/s]
Train steps ... :  28%|██▊       | 27862/100000 [8:09:15<11:43:22,  1.71it/s]
Train steps ... :  28%|██▊       | 27863/100000 [8:09:16<11:43:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27864/100000 [8:09:16<11:42:52,  1.71it/s]
Train steps ... :  28%|██▊       | 27865/100000 [8:09:17<11:42:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27866/100000 [8:09:18<11:42:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27867/100000 [8:09:18<11:43:33,  1.71it/s]
Train steps ... :  28%|██▊       | 27868/100000 [8:09:19<11:42:24,  1.71it/s]
Train steps ... :  28%|██▊       | 27869/100000 [8:09:19<11:43:14,  1.71it/s]
Train steps ... :  28%|██▊       | 27870/100000 [8:09:20<11:43:25,  1.71it/s]
Train steps ... :  28%|██▊       | 27871/100000 [8:09:20<11:42:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27872/100000 [8:09:21<11:42:01,  1.71it/s]
Train steps ... :  28%|██▊       | 27873/100000 [8:09:22<11:42:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27874/100000 [8:09:22<11:43:51,  1.71it/s]
Train steps ... :  28%|██▊       | 27875/100000 [8:09:23<11:44:40,  1.71it/s]Step... (27875 / 100000 | Loss: 1.0201961994171143, Learning Rate: 7.248743718592966e-05)
+
                                                                             
Step... (27875 / 100000 | Loss: 1.2128889560699463, Learning Rate: 7.248743718592966e-05)
+
Train steps ... :  28%|██▊       | 27875/100000 [8:09:23<11:44:40,  1.71it/s]
Train steps ... :  28%|██▊       | 27876/100000 [8:09:23<11:44:23,  1.71it/s]
Train steps ... :  28%|██▊       | 27877/100000 [8:09:24<11:44:04,  1.71it/s]
Train steps ... :  28%|██▊       | 27878/100000 [8:09:25<11:43:40,  1.71it/s]
Train steps ... :  28%|██▊       | 27879/100000 [8:09:25<11:42:59,  1.71it/s]
Train steps ... :  28%|██▊       | 27880/100000 [8:09:26<11:42:47,  1.71it/s]
Train steps ... :  28%|██▊       | 27881/100000 [8:09:26<11:42:04,  1.71it/s]
Train steps ... :  28%|██▊       | 27882/100000 [8:09:27<11:42:13,  1.71it/s]
Train steps ... :  28%|██▊       | 27883/100000 [8:09:28<11:41:57,  1.71it/s]
Train steps ... :  28%|██▊       | 27884/100000 [8:09:28<11:42:42,  1.71it/s]
Train steps ... :  28%|██▊       | 27885/100000 [8:09:29<11:42:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27886/100000 [8:09:29<11:42:27,  1.71it/s]
Train steps ... :  28%|██▊       | 27887/100000 [8:09:30<11:42:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27888/100000 [8:09:30<11:42:47,  1.71it/s]
Train steps ... :  28%|██▊       | 27889/100000 [8:09:31<11:43:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27890/100000 [8:09:32<11:45:01,  1.70it/s]
Train steps ... :  28%|██▊       | 27891/100000 [8:09:32<11:44:30,  1.71it/s]
Train steps ... :  28%|██▊       | 27892/100000 [8:09:33<11:44:02,  1.71it/s]
Train steps ... :  28%|██▊       | 27893/100000 [8:09:33<11:43:07,  1.71it/s]
Train steps ... :  28%|██▊       | 27894/100000 [8:09:34<11:43:48,  1.71it/s]
Train steps ... :  28%|██▊       | 27895/100000 [8:09:35<11:43:11,  1.71it/s]
Train steps ... :  28%|██▊       | 27896/100000 [8:09:35<11:43:09,  1.71it/s]
Train steps ... :  28%|██▊       | 27897/100000 [8:09:36<11:42:37,  1.71it/s]
Train steps ... :  28%|██▊       | 27898/100000 [8:09:36<11:42:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27899/100000 [8:09:37<11:42:07,  1.71it/s]
Train steps ... :  28%|██▊       | 27900/100000 [8:09:37<11:45:54,  1.70it/s]Step... (27900 / 100000 | Loss: 1.0004163980484009, Learning Rate: 7.246231155778895e-05)
+
                                                                             
Step... (27900 / 100000 | Loss: 1.243833065032959, Learning Rate: 7.246231155778895e-05)
+
Train steps ... :  28%|██▊       | 27900/100000 [8:09:38<11:45:54,  1.70it/s]
Train steps ... :  28%|██▊       | 27901/100000 [8:09:38<11:44:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27902/100000 [8:09:39<11:43:23,  1.71it/s]
Train steps ... :  28%|██▊       | 27903/100000 [8:09:39<11:42:59,  1.71it/s]
Train steps ... :  28%|██▊       | 27904/100000 [8:09:40<11:43:47,  1.71it/s]
Train steps ... :  28%|██▊       | 27905/100000 [8:09:40<11:43:44,  1.71it/s]
Train steps ... :  28%|██▊       | 27906/100000 [8:09:41<11:43:48,  1.71it/s]
Train steps ... :  28%|██▊       | 27907/100000 [8:09:42<11:43:52,  1.71it/s]
Train steps ... :  28%|██▊       | 27908/100000 [8:09:42<11:43:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27909/100000 [8:09:43<11:42:37,  1.71it/s]
Train steps ... :  28%|██▊       | 27910/100000 [8:09:43<11:42:27,  1.71it/s]
Train steps ... :  28%|██▊       | 27911/100000 [8:09:44<11:42:42,  1.71it/s]
Train steps ... :  28%|██▊       | 27912/100000 [8:09:44<11:42:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27913/100000 [8:09:45<11:43:03,  1.71it/s]
Train steps ... :  28%|██▊       | 27914/100000 [8:09:46<11:42:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27915/100000 [8:09:46<11:42:22,  1.71it/s]
Train steps ... :  28%|██▊       | 27916/100000 [8:09:47<11:41:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27917/100000 [8:09:47<11:42:40,  1.71it/s]
Train steps ... :  28%|██▊       | 27918/100000 [8:09:48<11:43:59,  1.71it/s]
Train steps ... :  28%|██▊       | 27919/100000 [8:09:49<11:43:43,  1.71it/s]
Train steps ... :  28%|██▊       | 27920/100000 [8:09:49<11:43:40,  1.71it/s]
Train steps ... :  28%|██▊       | 27921/100000 [8:09:50<11:43:14,  1.71it/s]
Train steps ... :  28%|██▊       | 27922/100000 [8:09:50<11:42:53,  1.71it/s]
Train steps ... :  28%|██▊       | 27923/100000 [8:09:51<11:43:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27924/100000 [8:09:52<11:42:10,  1.71it/s]
Train steps ... :  28%|██▊       | 27925/100000 [8:09:52<11:42:44,  1.71it/s]Step... (27925 / 100000 | Loss: 0.8496427536010742, Learning Rate: 7.243718592964825e-05)
+
                                                                             
Step... (27925 / 100000 | Loss: 0.9032499194145203, Learning Rate: 7.243718592964825e-05)
+
Train steps ... :  28%|██▊       | 27925/100000 [8:09:52<11:42:44,  1.71it/s]
Train steps ... :  28%|██▊       | 27926/100000 [8:09:53<11:42:49,  1.71it/s]
Train steps ... :  28%|██▊       | 27927/100000 [8:09:53<11:41:46,  1.71it/s]
Train steps ... :  28%|██▊       | 27928/100000 [8:09:54<11:41:46,  1.71it/s]
Train steps ... :  28%|██▊       | 27929/100000 [8:09:54<11:41:35,  1.71it/s]
Train steps ... :  28%|██▊       | 27930/100000 [8:09:55<11:41:18,  1.71it/s]
Train steps ... :  28%|██▊       | 27931/100000 [8:09:56<11:41:18,  1.71it/s]
Train steps ... :  28%|██▊       | 27932/100000 [8:09:56<11:41:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27933/100000 [8:09:57<11:41:19,  1.71it/s]
Train steps ... :  28%|██▊       | 27934/100000 [8:09:57<11:42:40,  1.71it/s]
Train steps ... :  28%|██▊       | 27935/100000 [8:09:58<11:43:44,  1.71it/s]
Train steps ... :  28%|██▊       | 27936/100000 [8:09:59<11:43:49,  1.71it/s]
Train steps ... :  28%|██▊       | 27937/100000 [8:09:59<11:44:42,  1.70it/s]
Train steps ... :  28%|██▊       | 27938/100000 [8:10:00<11:44:25,  1.71it/s]
Train steps ... :  28%|██▊       | 27939/100000 [8:10:00<11:43:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27940/100000 [8:10:01<11:42:32,  1.71it/s]
Train steps ... :  28%|██▊       | 27941/100000 [8:10:01<11:42:09,  1.71it/s]
Train steps ... :  28%|██▊       | 27942/100000 [8:10:02<11:42:30,  1.71it/s]
Train steps ... :  28%|██▊       | 27943/100000 [8:10:03<11:41:52,  1.71it/s]
Train steps ... :  28%|██▊       | 27944/100000 [8:10:03<11:41:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27945/100000 [8:10:04<11:42:01,  1.71it/s]
Train steps ... :  28%|██▊       | 27946/100000 [8:10:04<11:41:24,  1.71it/s]
Train steps ... :  28%|██▊       | 27947/100000 [8:10:05<11:41:25,  1.71it/s]
Train steps ... :  28%|██▊       | 27948/100000 [8:10:06<11:41:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27949/100000 [8:10:06<11:41:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27950/100000 [8:10:07<11:41:52,  1.71it/s]Step... (27950 / 100000 | Loss: 1.0602314472198486, Learning Rate: 7.241206030150755e-05)
+
                                                                             
Step... (27950 / 100000 | Loss: 0.8104355931282043, Learning Rate: 7.241206030150755e-05)
+
Train steps ... :  28%|██▊       | 27950/100000 [8:10:07<11:41:52,  1.71it/s]
Train steps ... :  28%|██▊       | 27951/100000 [8:10:07<11:41:57,  1.71it/s]
Train steps ... :  28%|██▊       | 27952/100000 [8:10:08<11:42:14,  1.71it/s]
Train steps ... :  28%|██▊       | 27953/100000 [8:10:08<11:42:59,  1.71it/s]
Train steps ... :  28%|██▊       | 27954/100000 [8:10:09<11:43:10,  1.71it/s]
Train steps ... :  28%|██▊       | 27955/100000 [8:10:10<11:42:23,  1.71it/s]
Train steps ... :  28%|██▊       | 27956/100000 [8:10:10<11:42:54,  1.71it/s]
Train steps ... :  28%|██▊       | 27957/100000 [8:10:11<11:43:06,  1.71it/s]
Train steps ... :  28%|██▊       | 27958/100000 [8:10:11<11:42:39,  1.71it/s]
Train steps ... :  28%|██▊       | 27959/100000 [8:10:12<11:42:11,  1.71it/s]
Train steps ... :  28%|██▊       | 27960/100000 [8:10:13<11:41:56,  1.71it/s]
Train steps ... :  28%|██▊       | 27961/100000 [8:10:13<11:41:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27962/100000 [8:10:14<11:41:32,  1.71it/s]
Train steps ... :  28%|██▊       | 27963/100000 [8:10:14<11:42:22,  1.71it/s]
Train steps ... :  28%|██▊       | 27964/100000 [8:10:15<11:41:24,  1.71it/s]
Train steps ... :  28%|██▊       | 27965/100000 [8:10:15<11:41:36,  1.71it/s]
Train steps ... :  28%|██▊       | 27966/100000 [8:10:16<11:41:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27967/100000 [8:10:17<11:40:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27968/100000 [8:10:17<11:42:47,  1.71it/s]
Train steps ... :  28%|██▊       | 27969/100000 [8:10:18<11:43:29,  1.71it/s]
Train steps ... :  28%|██▊       | 27970/100000 [8:10:18<11:42:21,  1.71it/s]
Train steps ... :  28%|██▊       | 27971/100000 [8:10:19<11:42:56,  1.71it/s]
Train steps ... :  28%|██▊       | 27972/100000 [8:10:20<11:41:38,  1.71it/s]
Train steps ... :  28%|██▊       | 27973/100000 [8:10:20<11:41:15,  1.71it/s]
Train steps ... :  28%|██▊       | 27974/100000 [8:10:21<11:41:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27975/100000 [8:10:21<11:41:12,  1.71it/s]Step... (27975 / 100000 | Loss: 0.9365184307098389, Learning Rate: 7.238693467336683e-05)
+
                                                                             
Step... (27975 / 100000 | Loss: 1.2674462795257568, Learning Rate: 7.238693467336683e-05)
+
Train steps ... :  28%|██▊       | 27975/100000 [8:10:22<11:41:12,  1.71it/s]
Train steps ... :  28%|██▊       | 27976/100000 [8:10:22<11:41:00,  1.71it/s]
Train steps ... :  28%|██▊       | 27977/100000 [8:10:22<11:41:05,  1.71it/s]
Train steps ... :  28%|██▊       | 27978/100000 [8:10:23<11:41:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27979/100000 [8:10:24<11:41:58,  1.71it/s]
Train steps ... :  28%|██▊       | 27980/100000 [8:10:24<11:40:46,  1.71it/s]
Train steps ... :  28%|██▊       | 27981/100000 [8:10:25<11:41:32,  1.71it/s]
Train steps ... :  28%|██▊       | 27982/100000 [8:10:25<11:41:06,  1.71it/s]
Train steps ... :  28%|██▊       | 27983/100000 [8:10:26<11:41:18,  1.71it/s]
Train steps ... :  28%|██▊       | 27984/100000 [8:10:27<11:42:41,  1.71it/s]
Train steps ... :  28%|██▊       | 27985/100000 [8:10:27<11:42:23,  1.71it/s]
Train steps ... :  28%|██▊       | 27986/100000 [8:10:28<11:41:59,  1.71it/s]
Train steps ... :  28%|██▊       | 27987/100000 [8:10:28<11:41:28,  1.71it/s]
Train steps ... :  28%|██▊       | 27988/100000 [8:10:29<11:41:17,  1.71it/s]
Train steps ... :  28%|██▊       | 27989/100000 [8:10:30<11:41:40,  1.71it/s]
Train steps ... :  28%|██▊       | 27990/100000 [8:10:30<11:41:32,  1.71it/s]
Train steps ... :  28%|██▊       | 27991/100000 [8:10:31<11:42:08,  1.71it/s]
Train steps ... :  28%|██▊       | 27992/100000 [8:10:31<11:42:31,  1.71it/s]
Train steps ... :  28%|██▊       | 27993/100000 [8:10:32<11:42:23,  1.71it/s]
Train steps ... :  28%|██▊       | 27994/100000 [8:10:32<11:41:37,  1.71it/s]
Train steps ... :  28%|██▊       | 27995/100000 [8:10:33<11:41:19,  1.71it/s]
Train steps ... :  28%|██▊       | 27996/100000 [8:10:34<11:41:08,  1.71it/s]
Train steps ... :  28%|██▊       | 27997/100000 [8:10:34<11:40:50,  1.71it/s]
Train steps ... :  28%|██▊       | 27998/100000 [8:10:35<11:42:16,  1.71it/s]
Train steps ... :  28%|██▊       | 27999/100000 [8:10:35<11:42:40,  1.71it/s]
Train steps ... :  28%|██▊       | 28000/100000 [8:10:36<11:43:34,  1.71it/s]Step... (28000 / 100000 | Loss: 0.9634521007537842, Learning Rate: 7.236180904522614e-05)
+
                                                                             
Step... (28000 / 100000 | Loss: 0.9403699040412903, Learning Rate: 7.236180904522614e-05)
+
Train steps ... :  28%|██▊       | 28000/100000 [8:10:36<11:43:34,  1.71it/s]
Train steps ... :  28%|██▊       | 28001/100000 [8:10:37<11:42:09,  1.71it/s]
Train steps ... :  28%|██▊       | 28002/100000 [8:10:37<11:42:16,  1.71it/s]
Train steps ... :  28%|██▊       | 28003/100000 [8:10:38<11:42:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28004/100000 [8:10:38<11:41:29,  1.71it/s]
Train steps ... :  28%|██▊       | 28005/100000 [8:10:39<11:42:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28006/100000 [8:10:39<11:42:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28007/100000 [8:10:40<11:41:38,  1.71it/s]
Train steps ... :  28%|██▊       | 28008/100000 [8:10:41<11:41:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28009/100000 [8:10:41<11:41:50,  1.71it/s]
Train steps ... :  28%|██▊       | 28010/100000 [8:10:42<11:41:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28011/100000 [8:10:42<11:42:07,  1.71it/s]
Train steps ... :  28%|██▊       | 28012/100000 [8:10:43<11:40:53,  1.71it/s]
Train steps ... :  28%|██▊       | 28013/100000 [8:10:44<11:40:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28014/100000 [8:10:44<11:41:20,  1.71it/s]
Train steps ... :  28%|██▊       | 28015/100000 [8:10:45<11:40:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28016/100000 [8:10:45<11:41:14,  1.71it/s]
Train steps ... :  28%|██▊       | 28017/100000 [8:10:46<11:40:32,  1.71it/s]
Train steps ... :  28%|██▊       | 28018/100000 [8:10:46<11:41:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28019/100000 [8:10:47<11:41:22,  1.71it/s]
Train steps ... :  28%|██▊       | 28020/100000 [8:10:48<11:41:05,  1.71it/s]
Train steps ... :  28%|██▊       | 28021/100000 [8:10:48<11:42:22,  1.71it/s]
Train steps ... :  28%|██▊       | 28022/100000 [8:10:49<11:42:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28023/100000 [8:10:49<11:40:23,  1.71it/s]
Train steps ... :  28%|██▊       | 28024/100000 [8:10:50<11:40:29,  1.71it/s]
Train steps ... :  28%|██▊       | 28025/100000 [8:10:51<11:41:53,  1.71it/s]Step... (28025 / 100000 | Loss: 1.0146266222000122, Learning Rate: 7.233668341708542e-05)
+
                                                                             
Step... (28025 / 100000 | Loss: 0.7653989791870117, Learning Rate: 7.233668341708542e-05)
+
Train steps ... :  28%|██▊       | 28025/100000 [8:10:51<11:41:53,  1.71it/s]
Train steps ... :  28%|██▊       | 28026/100000 [8:10:51<11:41:50,  1.71it/s]
Train steps ... :  28%|██▊       | 28027/100000 [8:10:52<11:41:32,  1.71it/s]
Train steps ... :  28%|██▊       | 28028/100000 [8:10:52<11:42:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28029/100000 [8:10:53<11:41:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28030/100000 [8:10:53<11:41:21,  1.71it/s]
Train steps ... :  28%|██▊       | 28031/100000 [8:10:54<11:40:34,  1.71it/s]
Train steps ... :  28%|██▊       | 28032/100000 [8:10:55<11:41:08,  1.71it/s]
Train steps ... :  28%|██▊       | 28033/100000 [8:10:55<11:40:54,  1.71it/s]
Train steps ... :  28%|██▊       | 28034/100000 [8:10:56<11:40:19,  1.71it/s]
Train steps ... :  28%|██▊       | 28035/100000 [8:10:56<11:41:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28036/100000 [8:10:57<11:40:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28037/100000 [8:10:58<11:40:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28038/100000 [8:10:58<11:41:19,  1.71it/s]
Train steps ... :  28%|██▊       | 28039/100000 [8:10:59<11:41:43,  1.71it/s]
Train steps ... :  28%|██▊       | 28040/100000 [8:10:59<11:41:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28041/100000 [8:11:00<11:40:40,  1.71it/s]
Train steps ... :  28%|██▊       | 28042/100000 [8:11:01<11:40:17,  1.71it/s]
Train steps ... :  28%|██▊       | 28043/100000 [8:11:01<11:39:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28044/100000 [8:11:02<11:40:13,  1.71it/s]
Train steps ... :  28%|██▊       | 28045/100000 [8:11:02<11:42:05,  1.71it/s]
Train steps ... :  28%|██▊       | 28046/100000 [8:11:03<11:41:42,  1.71it/s]
Train steps ... :  28%|██▊       | 28047/100000 [8:11:03<11:41:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28048/100000 [8:11:04<11:41:51,  1.71it/s]
Train steps ... :  28%|██▊       | 28049/100000 [8:11:05<11:41:20,  1.71it/s]
Train steps ... :  28%|██▊       | 28050/100000 [8:11:05<11:41:04,  1.71it/s]Step... (28050 / 100000 | Loss: 0.9299089908599854, Learning Rate: 7.231155778894473e-05)
+
                                                                             
Step... (28050 / 100000 | Loss: 1.1410932540893555, Learning Rate: 7.231155778894473e-05)
+
Train steps ... :  28%|██▊       | 28050/100000 [8:11:06<11:41:04,  1.71it/s]
Train steps ... :  28%|██▊       | 28051/100000 [8:11:06<11:41:31,  1.71it/s]
Train steps ... :  28%|██▊       | 28052/100000 [8:11:06<11:40:52,  1.71it/s]
Train steps ... :  28%|██▊       | 28053/100000 [8:11:07<11:41:24,  1.71it/s]
Train steps ... :  28%|██▊       | 28054/100000 [8:11:08<11:43:22,  1.70it/s]
Train steps ... :  28%|██▊       | 28055/100000 [8:11:08<11:42:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28056/100000 [8:11:09<11:41:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28057/100000 [8:11:09<11:41:05,  1.71it/s]
Train steps ... :  28%|██▊       | 28058/100000 [8:11:10<11:42:23,  1.71it/s]
Train steps ... :  28%|██▊       | 28059/100000 [8:11:10<11:42:15,  1.71it/s]
Train steps ... :  28%|██▊       | 28060/100000 [8:11:11<11:42:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28061/100000 [8:11:12<11:41:16,  1.71it/s]
Train steps ... :  28%|██▊       | 28062/100000 [8:11:12<11:40:35,  1.71it/s]
Train steps ... :  28%|██▊       | 28063/100000 [8:11:13<11:41:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28064/100000 [8:11:13<11:41:08,  1.71it/s]
Train steps ... :  28%|██▊       | 28065/100000 [8:11:14<11:41:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28066/100000 [8:11:15<11:41:04,  1.71it/s]
Train steps ... :  28%|██▊       | 28067/100000 [8:11:15<11:41:27,  1.71it/s]
Train steps ... :  28%|██▊       | 28068/100000 [8:11:16<11:40:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28069/100000 [8:11:16<11:40:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28070/100000 [8:11:17<11:41:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28071/100000 [8:11:17<11:41:11,  1.71it/s]
Train steps ... :  28%|██▊       | 28072/100000 [8:11:18<11:40:24,  1.71it/s]
Train steps ... :  28%|██▊       | 28073/100000 [8:11:19<11:40:12,  1.71it/s]
Train steps ... :  28%|██▊       | 28074/100000 [8:11:19<11:41:17,  1.71it/s]
Train steps ... :  28%|██▊       | 28075/100000 [8:11:20<11:40:45,  1.71it/s]Step... (28075 / 100000 | Loss: 0.9363770484924316, Learning Rate: 7.228643216080401e-05)
+
                                                                             
Step... (28075 / 100000 | Loss: 1.0406640768051147, Learning Rate: 7.228643216080401e-05)
+
Train steps ... :  28%|██▊       | 28075/100000 [8:11:20<11:40:45,  1.71it/s]
Train steps ... :  28%|██▊       | 28076/100000 [8:11:20<11:41:38,  1.71it/s]
Train steps ... :  28%|██▊       | 28077/100000 [8:11:21<11:41:05,  1.71it/s]
Train steps ... :  28%|██▊       | 28078/100000 [8:11:22<11:40:42,  1.71it/s]
Train steps ... :  28%|██▊       | 28079/100000 [8:11:22<11:41:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28080/100000 [8:11:23<11:41:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28081/100000 [8:11:23<11:41:45,  1.71it/s]
Train steps ... :  28%|██▊       | 28082/100000 [8:11:24<11:41:54,  1.71it/s]
Train steps ... :  28%|██▊       | 28083/100000 [8:11:24<11:41:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28084/100000 [8:11:25<11:40:56,  1.71it/s]
Train steps ... :  28%|██▊       | 28085/100000 [8:11:26<11:40:45,  1.71it/s]
Train steps ... :  28%|██▊       | 28086/100000 [8:11:26<11:41:07,  1.71it/s]
Train steps ... :  28%|██▊       | 28087/100000 [8:11:27<11:40:52,  1.71it/s]
Train steps ... :  28%|██▊       | 28088/100000 [8:11:27<11:40:56,  1.71it/s]
Train steps ... :  28%|██▊       | 28089/100000 [8:11:28<11:41:16,  1.71it/s]
Train steps ... :  28%|██▊       | 28090/100000 [8:11:29<11:40:32,  1.71it/s]
Train steps ... :  28%|██▊       | 28091/100000 [8:11:29<11:40:35,  1.71it/s]
Train steps ... :  28%|██▊       | 28092/100000 [8:11:30<11:41:06,  1.71it/s]
Train steps ... :  28%|██▊       | 28093/100000 [8:11:30<11:40:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28094/100000 [8:11:31<11:41:34,  1.71it/s]
Train steps ... :  28%|██▊       | 28095/100000 [8:11:32<11:41:44,  1.71it/s]
Train steps ... :  28%|██▊       | 28096/100000 [8:11:32<11:41:12,  1.71it/s]
Train steps ... :  28%|██▊       | 28097/100000 [8:11:33<11:40:46,  1.71it/s]
Train steps ... :  28%|██▊       | 28098/100000 [8:11:33<11:41:25,  1.71it/s]
Train steps ... :  28%|██▊       | 28099/100000 [8:11:34<11:40:54,  1.71it/s]
Train steps ... :  28%|██▊       | 28100/100000 [8:11:34<11:39:56,  1.71it/s]Step... (28100 / 100000 | Loss: 0.822523832321167, Learning Rate: 7.226130653266333e-05)
+
                                                                             
Step... (28100 / 100000 | Loss: 0.8960006237030029, Learning Rate: 7.226130653266333e-05)
+
Train steps ... :  28%|██▊       | 28100/100000 [8:11:35<11:39:56,  1.71it/s]
Train steps ... :  28%|██▊       | 28101/100000 [8:11:35<11:40:40,  1.71it/s]
Train steps ... :  28%|██▊       | 28102/100000 [8:11:36<11:41:03,  1.71it/s]
Train steps ... :  28%|██▊       | 28103/100000 [8:11:36<11:40:26,  1.71it/s]
Train steps ... :  28%|██▊       | 28104/100000 [8:11:37<11:40:41,  1.71it/s]
Train steps ... :  28%|██▊       | 28105/100000 [8:11:37<11:40:14,  1.71it/s]
Train steps ... :  28%|██▊       | 28106/100000 [8:11:38<11:39:54,  1.71it/s]
Train steps ... :  28%|██▊       | 28107/100000 [8:11:39<11:40:17,  1.71it/s]
Train steps ... :  28%|██▊       | 28108/100000 [8:11:39<11:41:11,  1.71it/s]
Train steps ... :  28%|██▊       | 28109/100000 [8:11:40<11:40:56,  1.71it/s]
Train steps ... :  28%|██▊       | 28110/100000 [8:11:40<11:40:25,  1.71it/s]
Train steps ... :  28%|██▊       | 28111/100000 [8:11:41<11:39:56,  1.71it/s]
Train steps ... :  28%|██▊       | 28112/100000 [8:11:41<11:39:40,  1.71it/s]
Train steps ... :  28%|██▊       | 28113/100000 [8:11:42<11:40:03,  1.71it/s]
Train steps ... :  28%|██▊       | 28114/100000 [8:11:43<11:39:52,  1.71it/s]
Train steps ... :  28%|██▊       | 28115/100000 [8:11:43<11:39:51,  1.71it/s]
Train steps ... :  28%|██▊       | 28116/100000 [8:11:44<11:40:34,  1.71it/s]
Train steps ... :  28%|██▊       | 28117/100000 [8:11:44<11:40:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28118/100000 [8:11:45<11:40:13,  1.71it/s]
Train steps ... :  28%|██▊       | 28119/100000 [8:11:46<11:40:19,  1.71it/s]
Train steps ... :  28%|██▊       | 28120/100000 [8:11:46<11:40:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28121/100000 [8:11:47<11:40:20,  1.71it/s]
Train steps ... :  28%|██▊       | 28122/100000 [8:11:47<11:39:38,  1.71it/s]
Train steps ... :  28%|██▊       | 28123/100000 [8:11:48<11:39:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28124/100000 [8:11:48<11:40:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28125/100000 [8:11:49<11:40:52,  1.71it/s]Step... (28125 / 100000 | Loss: 1.042196273803711, Learning Rate: 7.223618090452262e-05)
+
                                                                             
Step... (28125 / 100000 | Loss: 1.164046287536621, Learning Rate: 7.223618090452262e-05)
+
Train steps ... :  28%|██▊       | 28125/100000 [8:11:49<11:40:52,  1.71it/s]
Train steps ... :  28%|██▊       | 28126/100000 [8:11:50<11:41:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28127/100000 [8:11:50<11:41:21,  1.71it/s]
Train steps ... :  28%|██▊       | 28128/100000 [8:11:51<11:40:46,  1.71it/s]
Train steps ... :  28%|██▊       | 28129/100000 [8:11:51<11:40:31,  1.71it/s]
Train steps ... :  28%|██▊       | 28130/100000 [8:11:52<11:40:05,  1.71it/s]
Train steps ... :  28%|██▊       | 28131/100000 [8:11:53<11:41:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28132/100000 [8:11:53<11:40:40,  1.71it/s]
Train steps ... :  28%|██▊       | 28133/100000 [8:11:54<11:40:04,  1.71it/s]
Train steps ... :  28%|██▊       | 28134/100000 [8:11:54<11:40:17,  1.71it/s]
Train steps ... :  28%|██▊       | 28135/100000 [8:11:55<11:39:42,  1.71it/s]
Train steps ... :  28%|██▊       | 28136/100000 [8:11:55<11:40:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28137/100000 [8:11:56<11:40:30,  1.71it/s]
Train steps ... :  28%|██▊       | 28138/100000 [8:11:57<11:40:23,  1.71it/s]
Train steps ... :  28%|██▊       | 28139/100000 [8:11:57<11:40:54,  1.71it/s]
Train steps ... :  28%|██▊       | 28140/100000 [8:11:58<11:40:45,  1.71it/s]
Train steps ... :  28%|██▊       | 28141/100000 [8:11:58<11:39:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28142/100000 [8:11:59<11:40:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28143/100000 [8:12:00<11:40:26,  1.71it/s]
Train steps ... :  28%|██▊       | 28144/100000 [8:12:00<11:40:32,  1.71it/s]
Train steps ... :  28%|██▊       | 28145/100000 [8:12:01<11:39:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28146/100000 [8:12:01<11:40:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28147/100000 [8:12:02<11:39:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28148/100000 [8:12:02<11:40:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28149/100000 [8:12:03<11:40:25,  1.71it/s]
Train steps ... :  28%|██▊       | 28150/100000 [8:12:04<11:39:51,  1.71it/s]Step... (28150 / 100000 | Loss: 0.824793815612793, Learning Rate: 7.22110552763819e-05)
+
                                                                             
Step... (28150 / 100000 | Loss: 1.1927387714385986, Learning Rate: 7.22110552763819e-05)
+
Train steps ... :  28%|██▊       | 28150/100000 [8:12:04<11:39:51,  1.71it/s]
Train steps ... :  28%|██▊       | 28151/100000 [8:12:04<11:40:34,  1.71it/s]
Train steps ... :  28%|██▊       | 28152/100000 [8:12:05<11:40:08,  1.71it/s]
Train steps ... :  28%|██▊       | 28153/100000 [8:12:05<11:39:12,  1.71it/s]
Train steps ... :  28%|██▊       | 28154/100000 [8:12:06<11:39:09,  1.71it/s]
Train steps ... :  28%|██▊       | 28155/100000 [8:12:07<11:39:21,  1.71it/s]
Train steps ... :  28%|██▊       | 28156/100000 [8:12:07<11:39:52,  1.71it/s]
Train steps ... :  28%|██▊       | 28157/100000 [8:12:08<11:40:22,  1.71it/s]
Train steps ... :  28%|██▊       | 28158/100000 [8:12:08<11:39:34,  1.71it/s]
Train steps ... :  28%|██▊       | 28159/100000 [8:12:09<11:39:56,  1.71it/s]
Train steps ... :  28%|██▊       | 28160/100000 [8:12:10<11:39:41,  1.71it/s]
Train steps ... :  28%|██▊       | 28161/100000 [8:12:10<11:39:20,  1.71it/s]
Train steps ... :  28%|██▊       | 28162/100000 [8:12:11<11:39:33,  1.71it/s]
Train steps ... :  28%|██▊       | 28163/100000 [8:12:11<11:39:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28164/100000 [8:12:12<11:39:08,  1.71it/s]
Train steps ... :  28%|██▊       | 28165/100000 [8:12:12<11:38:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28166/100000 [8:12:13<11:38:25,  1.71it/s]
Train steps ... :  28%|██▊       | 28167/100000 [8:12:14<11:39:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28168/100000 [8:12:14<11:39:45,  1.71it/s]
Train steps ... :  28%|██▊       | 28169/100000 [8:12:15<11:40:19,  1.71it/s]
Train steps ... :  28%|██▊       | 28170/100000 [8:12:15<11:39:32,  1.71it/s]
Train steps ... :  28%|██▊       | 28171/100000 [8:12:16<11:39:15,  1.71it/s]
Train steps ... :  28%|██▊       | 28172/100000 [8:12:17<11:39:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28173/100000 [8:12:17<11:38:53,  1.71it/s]
Train steps ... :  28%|██▊       | 28174/100000 [8:12:18<11:38:53,  1.71it/s]
Train steps ... :  28%|██▊       | 28175/100000 [8:12:18<11:38:29,  1.71it/s]Step... (28175 / 100000 | Loss: 1.0228874683380127, Learning Rate: 7.218592964824121e-05)
+
                                                                             
Step... (28175 / 100000 | Loss: 1.0353749990463257, Learning Rate: 7.218592964824121e-05)
+
Train steps ... :  28%|██▊       | 28175/100000 [8:12:19<11:38:29,  1.71it/s]
Train steps ... :  28%|██▊       | 28176/100000 [8:12:19<11:38:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28177/100000 [8:12:19<11:41:13,  1.71it/s]
Train steps ... :  28%|██▊       | 28178/100000 [8:12:20<11:40:21,  1.71it/s]
Train steps ... :  28%|██▊       | 28179/100000 [8:12:21<11:40:00,  1.71it/s]
Train steps ... :  28%|██▊       | 28180/100000 [8:12:21<11:39:43,  1.71it/s]
Train steps ... :  28%|██▊       | 28181/100000 [8:12:22<11:39:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28182/100000 [8:12:22<11:38:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28183/100000 [8:12:23<11:38:26,  1.71it/s]
Train steps ... :  28%|██▊       | 28184/100000 [8:12:24<11:39:11,  1.71it/s]
Train steps ... :  28%|██▊       | 28185/100000 [8:12:24<11:39:05,  1.71it/s]
Train steps ... :  28%|██▊       | 28186/100000 [8:12:25<11:39:33,  1.71it/s]
Train steps ... :  28%|██▊       | 28187/100000 [8:12:25<11:38:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28188/100000 [8:12:26<11:38:27,  1.71it/s]
Train steps ... :  28%|██▊       | 28189/100000 [8:12:26<11:39:03,  1.71it/s]
Train steps ... :  28%|██▊       | 28190/100000 [8:12:27<11:38:38,  1.71it/s]
Train steps ... :  28%|██▊       | 28191/100000 [8:12:28<11:40:09,  1.71it/s]
Train steps ... :  28%|██▊       | 28192/100000 [8:12:28<11:42:25,  1.70it/s]
Train steps ... :  28%|██▊       | 28193/100000 [8:12:29<11:41:43,  1.71it/s]
Train steps ... :  28%|██▊       | 28194/100000 [8:12:29<11:41:03,  1.71it/s]
Train steps ... :  28%|██▊       | 28195/100000 [8:12:30<11:40:53,  1.71it/s]
Train steps ... :  28%|██▊       | 28196/100000 [8:12:31<11:40:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28197/100000 [8:12:31<11:40:23,  1.71it/s]
Train steps ... :  28%|██▊       | 28198/100000 [8:12:32<11:40:12,  1.71it/s]
Train steps ... :  28%|██▊       | 28199/100000 [8:12:32<11:40:22,  1.71it/s]
Train steps ... :  28%|██▊       | 28200/100000 [8:12:33<11:39:39,  1.71it/s]Step... (28200 / 100000 | Loss: 0.9028804302215576, Learning Rate: 7.21608040201005e-05)
+
                                                                             
Step... (28200 / 100000 | Loss: 1.115187168121338, Learning Rate: 7.21608040201005e-05)
+
Train steps ... :  28%|██▊       | 28200/100000 [8:12:33<11:39:39,  1.71it/s]
Train steps ... :  28%|██▊       | 28201/100000 [8:12:33<11:39:00,  1.71it/s]
Train steps ... :  28%|██▊       | 28202/100000 [8:12:34<11:38:27,  1.71it/s]
Train steps ... :  28%|██▊       | 28203/100000 [8:12:35<11:39:16,  1.71it/s]
Train steps ... :  28%|██▊       | 28204/100000 [8:12:35<11:38:51,  1.71it/s]
Train steps ... :  28%|██▊       | 28205/100000 [8:12:36<11:39:14,  1.71it/s]
Train steps ... :  28%|██▊       | 28206/100000 [8:12:36<11:40:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28207/100000 [8:12:37<11:40:44,  1.71it/s]
Train steps ... :  28%|██▊       | 28208/100000 [8:12:38<11:41:06,  1.71it/s]
Train steps ... :  28%|██▊       | 28209/100000 [8:12:38<11:39:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28210/100000 [8:12:39<11:40:29,  1.71it/s]
Train steps ... :  28%|██▊       | 28211/100000 [8:12:39<11:40:55,  1.71it/s]
Train steps ... :  28%|██▊       | 28212/100000 [8:12:40<11:40:21,  1.71it/s]
Train steps ... :  28%|██▊       | 28213/100000 [8:12:40<11:40:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28214/100000 [8:12:41<11:40:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28215/100000 [8:12:42<11:40:43,  1.71it/s]
Train steps ... :  28%|██▊       | 28216/100000 [8:12:42<11:39:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28217/100000 [8:12:43<11:39:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28218/100000 [8:12:43<11:40:08,  1.71it/s]
Train steps ... :  28%|██▊       | 28219/100000 [8:12:44<11:39:12,  1.71it/s]
Train steps ... :  28%|██▊       | 28220/100000 [8:12:45<11:39:42,  1.71it/s]
Train steps ... :  28%|██▊       | 28221/100000 [8:12:45<11:39:12,  1.71it/s]
Train steps ... :  28%|██▊       | 28222/100000 [8:12:46<11:39:07,  1.71it/s]
Train steps ... :  28%|██▊       | 28223/100000 [8:12:46<11:39:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28224/100000 [8:12:47<11:40:06,  1.71it/s]
Train steps ... :  28%|██▊       | 28225/100000 [8:12:48<11:39:17,  1.71it/s]Step... (28225 / 100000 | Loss: 0.7733396887779236, Learning Rate: 7.213567839195981e-05)
+
                                                                             
Step... (28225 / 100000 | Loss: 0.6961208581924438, Learning Rate: 7.213567839195981e-05)
+
Train steps ... :  28%|██▊       | 28225/100000 [8:12:48<11:39:17,  1.71it/s]
Train steps ... :  28%|██▊       | 28226/100000 [8:12:48<11:39:29,  1.71it/s]
Train steps ... :  28%|██▊       | 28227/100000 [8:12:49<11:40:35,  1.71it/s]
Train steps ... :  28%|██▊       | 28228/100000 [8:12:49<11:40:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28229/100000 [8:12:50<11:40:54,  1.71it/s]
Train steps ... :  28%|██▊       | 28230/100000 [8:12:50<11:40:05,  1.71it/s]
Train steps ... :  28%|██▊       | 28231/100000 [8:12:51<11:39:20,  1.71it/s]
Train steps ... :  28%|██▊       | 28232/100000 [8:12:52<11:39:05,  1.71it/s]
Train steps ... :  28%|██▊       | 28233/100000 [8:12:52<11:39:12,  1.71it/s]
Train steps ... :  28%|██▊       | 28234/100000 [8:12:53<11:38:32,  1.71it/s]
Train steps ... :  28%|██▊       | 28235/100000 [8:12:53<11:38:21,  1.71it/s]
Train steps ... :  28%|██▊       | 28236/100000 [8:12:54<11:39:22,  1.71it/s]
Train steps ... :  28%|██▊       | 28237/100000 [8:12:55<11:39:19,  1.71it/s]
Train steps ... :  28%|██▊       | 28238/100000 [8:12:55<11:38:44,  1.71it/s]
Train steps ... :  28%|██▊       | 28239/100000 [8:12:56<11:38:46,  1.71it/s]
Train steps ... :  28%|██▊       | 28240/100000 [8:12:56<11:40:08,  1.71it/s]
Train steps ... :  28%|██▊       | 28241/100000 [8:12:57<11:39:30,  1.71it/s]
Train steps ... :  28%|██▊       | 28242/100000 [8:12:57<11:40:14,  1.71it/s]
Train steps ... :  28%|██▊       | 28243/100000 [8:12:58<11:39:46,  1.71it/s]
Train steps ... :  28%|██▊       | 28244/100000 [8:12:59<11:39:54,  1.71it/s]
Train steps ... :  28%|██▊       | 28245/100000 [8:12:59<11:39:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28246/100000 [8:13:00<11:38:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28247/100000 [8:13:00<11:39:23,  1.71it/s]
Train steps ... :  28%|██▊       | 28248/100000 [8:13:01<11:38:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28249/100000 [8:13:02<11:38:21,  1.71it/s]
Train steps ... :  28%|██▊       | 28250/100000 [8:13:02<11:39:49,  1.71it/s]Step... (28250 / 100000 | Loss: 0.7905851602554321, Learning Rate: 7.211055276381909e-05)
+
                                                                             
Step... (28250 / 100000 | Loss: 1.5186331272125244, Learning Rate: 7.211055276381909e-05)
+
Train steps ... :  28%|██▊       | 28250/100000 [8:13:02<11:39:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28251/100000 [8:13:03<11:39:29,  1.71it/s]
Train steps ... :  28%|██▊       | 28252/100000 [8:13:03<11:39:40,  1.71it/s]
Train steps ... :  28%|██▊       | 28253/100000 [8:13:04<11:39:17,  1.71it/s]
Train steps ... :  28%|██▊       | 28254/100000 [8:13:04<11:39:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28255/100000 [8:13:05<11:39:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28256/100000 [8:13:06<11:39:23,  1.71it/s]
Train steps ... :  28%|██▊       | 28257/100000 [8:13:06<11:38:14,  1.71it/s]
Train steps ... :  28%|██▊       | 28258/100000 [8:13:07<11:38:17,  1.71it/s]
Train steps ... :  28%|██▊       | 28259/100000 [8:13:07<11:37:52,  1.71it/s]
Train steps ... :  28%|██▊       | 28260/100000 [8:13:08<11:37:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28261/100000 [8:13:09<11:37:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28262/100000 [8:13:09<11:38:26,  1.71it/s]
Train steps ... :  28%|██▊       | 28263/100000 [8:13:10<11:38:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28264/100000 [8:13:10<11:38:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28265/100000 [8:13:11<11:39:15,  1.71it/s]
Train steps ... :  28%|██▊       | 28266/100000 [8:13:11<11:38:43,  1.71it/s]
Train steps ... :  28%|██▊       | 28267/100000 [8:13:12<11:38:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28268/100000 [8:13:13<11:37:44,  1.71it/s]
Train steps ... :  28%|██▊       | 28269/100000 [8:13:13<11:37:29,  1.71it/s]
Train steps ... :  28%|██▊       | 28270/100000 [8:13:14<11:38:21,  1.71it/s]
Train steps ... :  28%|██▊       | 28271/100000 [8:13:14<11:38:41,  1.71it/s]
Train steps ... :  28%|██▊       | 28272/100000 [8:13:15<11:37:53,  1.71it/s]
Train steps ... :  28%|██▊       | 28273/100000 [8:13:16<11:38:39,  1.71it/s]
Train steps ... :  28%|██▊       | 28274/100000 [8:13:16<11:38:35,  1.71it/s]
Train steps ... :  28%|██▊       | 28275/100000 [8:13:17<11:38:09,  1.71it/s]Step... (28275 / 100000 | Loss: 1.0384669303894043, Learning Rate: 7.20854271356784e-05)
+
                                                                             
Step... (28275 / 100000 | Loss: 1.053294062614441, Learning Rate: 7.20854271356784e-05)
+
Train steps ... :  28%|██▊       | 28275/100000 [8:13:17<11:38:09,  1.71it/s]
Train steps ... :  28%|██▊       | 28276/100000 [8:13:17<11:38:39,  1.71it/s]
Train steps ... :  28%|██▊       | 28277/100000 [8:13:18<11:37:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28278/100000 [8:13:18<11:37:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28279/100000 [8:13:19<11:37:27,  1.71it/s]
Train steps ... :  28%|██▊       | 28280/100000 [8:13:20<11:38:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28281/100000 [8:13:20<11:38:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28282/100000 [8:13:21<11:38:41,  1.71it/s]
Train steps ... :  28%|██▊       | 28283/100000 [8:13:21<11:39:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28284/100000 [8:13:22<11:38:53,  1.71it/s]
Train steps ... :  28%|██▊       | 28285/100000 [8:13:23<11:39:02,  1.71it/s]
Train steps ... :  28%|██▊       | 28286/100000 [8:13:23<11:39:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28287/100000 [8:13:24<11:40:35,  1.71it/s]
Train steps ... :  28%|██▊       | 28288/100000 [8:13:24<11:39:14,  1.71it/s]
Train steps ... :  28%|██▊       | 28289/100000 [8:13:25<11:38:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28290/100000 [8:13:26<11:38:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28291/100000 [8:13:26<11:37:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28292/100000 [8:13:27<11:38:09,  1.71it/s]
Train steps ... :  28%|██▊       | 28293/100000 [8:13:27<11:38:16,  1.71it/s]
Train steps ... :  28%|██▊       | 28294/100000 [8:13:28<11:38:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28295/100000 [8:13:28<11:42:00,  1.70it/s]
Train steps ... :  28%|██▊       | 28296/100000 [8:13:29<11:41:36,  1.70it/s]
Train steps ... :  28%|██▊       | 28297/100000 [8:13:30<11:40:25,  1.71it/s]
Train steps ... :  28%|██▊       | 28298/100000 [8:13:30<11:39:41,  1.71it/s]
Train steps ... :  28%|██▊       | 28299/100000 [8:13:31<11:38:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28300/100000 [8:13:31<11:38:33,  1.71it/s]Step... (28300 / 100000 | Loss: 0.6706995964050293, Learning Rate: 7.206030150753768e-05)
+
                                                                             
Step... (28300 / 100000 | Loss: 1.0440653562545776, Learning Rate: 7.206030150753768e-05)
+
Train steps ... :  28%|██▊       | 28300/100000 [8:13:32<11:38:33,  1.71it/s]
Train steps ... :  28%|██▊       | 28301/100000 [8:13:32<11:39:03,  1.71it/s]
Train steps ... :  28%|██▊       | 28302/100000 [8:13:33<11:38:46,  1.71it/s]
Train steps ... :  28%|██▊       | 28303/100000 [8:13:33<11:38:31,  1.71it/s]
Train steps ... :  28%|██▊       | 28304/100000 [8:13:34<11:38:24,  1.71it/s]
Train steps ... :  28%|██▊       | 28305/100000 [8:13:34<11:38:30,  1.71it/s]
Train steps ... :  28%|██▊       | 28306/100000 [8:13:35<11:37:51,  1.71it/s]
Train steps ... :  28%|██▊       | 28307/100000 [8:13:35<11:37:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28308/100000 [8:13:36<11:38:09,  1.71it/s]
Train steps ... :  28%|██▊       | 28309/100000 [8:13:37<11:38:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28310/100000 [8:13:37<11:38:17,  1.71it/s]
Train steps ... :  28%|██▊       | 28311/100000 [8:13:38<11:37:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28312/100000 [8:13:38<11:37:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28313/100000 [8:13:39<11:38:09,  1.71it/s]
Train steps ... :  28%|██▊       | 28314/100000 [8:13:40<11:37:12,  1.71it/s]
Train steps ... :  28%|██▊       | 28315/100000 [8:13:40<11:38:04,  1.71it/s]
Train steps ... :  28%|██▊       | 28316/100000 [8:13:41<11:37:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28317/100000 [8:13:41<11:38:00,  1.71it/s]
Train steps ... :  28%|██▊       | 28318/100000 [8:13:42<11:38:30,  1.71it/s]
Train steps ... :  28%|██▊       | 28319/100000 [8:13:42<11:38:33,  1.71it/s]
Train steps ... :  28%|██▊       | 28320/100000 [8:13:43<11:39:29,  1.71it/s]
Train steps ... :  28%|██▊       | 28321/100000 [8:13:44<11:38:34,  1.71it/s]
Train steps ... :  28%|██▊       | 28322/100000 [8:13:44<11:37:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28323/100000 [8:13:45<11:37:51,  1.71it/s]
Train steps ... :  28%|██▊       | 28324/100000 [8:13:45<11:37:27,  1.71it/s]
Train steps ... :  28%|██▊       | 28325/100000 [8:13:46<11:37:36,  1.71it/s]Step... (28325 / 100000 | Loss: 1.3671753406524658, Learning Rate: 7.203517587939698e-05)
+
                                                                             
Step... (28325 / 100000 | Loss: 0.8690353631973267, Learning Rate: 7.203517587939698e-05)
+
Train steps ... :  28%|██▊       | 28325/100000 [8:13:46<11:37:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28326/100000 [8:13:47<11:37:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28327/100000 [8:13:47<11:38:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28328/100000 [8:13:48<11:39:19,  1.71it/s]
Train steps ... :  28%|██▊       | 28329/100000 [8:13:48<11:38:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28330/100000 [8:13:49<11:37:33,  1.71it/s]
Train steps ... :  28%|██▊       | 28331/100000 [8:13:49<11:38:33,  1.71it/s]
Train steps ... :  28%|██▊       | 28332/100000 [8:13:50<11:37:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28333/100000 [8:13:51<11:38:41,  1.71it/s]
Train steps ... :  28%|██▊       | 28334/100000 [8:13:51<11:37:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28335/100000 [8:13:52<11:37:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28336/100000 [8:13:52<11:37:14,  1.71it/s]
Train steps ... :  28%|██▊       | 28337/100000 [8:13:53<11:37:45,  1.71it/s]
Train steps ... :  28%|██▊       | 28338/100000 [8:13:54<11:37:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28339/100000 [8:13:54<11:37:32,  1.71it/s]
Train steps ... :  28%|██▊       | 28340/100000 [8:13:55<11:37:24,  1.71it/s]
Train steps ... :  28%|██▊       | 28341/100000 [8:13:55<11:38:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28342/100000 [8:13:56<11:37:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28343/100000 [8:13:56<11:37:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28344/100000 [8:13:57<11:38:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28345/100000 [8:13:58<11:38:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28346/100000 [8:13:58<11:37:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28347/100000 [8:13:59<11:37:31,  1.71it/s]
Train steps ... :  28%|██▊       | 28348/100000 [8:13:59<11:37:27,  1.71it/s]
Train steps ... :  28%|██▊       | 28349/100000 [8:14:00<11:37:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28350/100000 [8:14:01<11:37:28,  1.71it/s]Step... (28350 / 100000 | Loss: 0.9178910851478577, Learning Rate: 7.201005025125629e-05)
+
                                                                             
Step... (28350 / 100000 | Loss: 0.9320681095123291, Learning Rate: 7.201005025125629e-05)
+
Train steps ... :  28%|██▊       | 28350/100000 [8:14:01<11:37:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28351/100000 [8:14:01<11:37:08,  1.71it/s]
Train steps ... :  28%|██▊       | 28352/100000 [8:14:02<11:38:00,  1.71it/s]
Train steps ... :  28%|██▊       | 28353/100000 [8:14:02<11:37:38,  1.71it/s]
Train steps ... :  28%|██▊       | 28354/100000 [8:14:03<11:37:31,  1.71it/s]
Train steps ... :  28%|██▊       | 28355/100000 [8:14:04<11:38:04,  1.71it/s]
Train steps ... :  28%|██▊       | 28356/100000 [8:14:04<11:37:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28357/100000 [8:14:05<11:37:51,  1.71it/s]
Train steps ... :  28%|██▊       | 28358/100000 [8:14:05<11:39:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28359/100000 [8:14:06<11:37:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28360/100000 [8:14:06<11:37:50,  1.71it/s]
Train steps ... :  28%|██▊       | 28361/100000 [8:14:07<11:37:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28362/100000 [8:14:08<11:37:23,  1.71it/s]
Train steps ... :  28%|██▊       | 28363/100000 [8:14:08<11:38:15,  1.71it/s]
Train steps ... :  28%|██▊       | 28364/100000 [8:14:09<11:36:52,  1.71it/s]
Train steps ... :  28%|██▊       | 28365/100000 [8:14:09<11:37:11,  1.71it/s]
Train steps ... :  28%|██▊       | 28366/100000 [8:14:10<11:37:14,  1.71it/s]
Train steps ... :  28%|██▊       | 28367/100000 [8:14:11<11:37:22,  1.71it/s]
Train steps ... :  28%|██▊       | 28368/100000 [8:14:11<11:38:11,  1.71it/s]
Train steps ... :  28%|██▊       | 28369/100000 [8:14:12<11:38:16,  1.71it/s]
Train steps ... :  28%|██▊       | 28370/100000 [8:14:12<11:37:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28371/100000 [8:14:13<11:37:29,  1.71it/s]
Train steps ... :  28%|██▊       | 28372/100000 [8:14:13<11:37:22,  1.71it/s]
Train steps ... :  28%|██▊       | 28373/100000 [8:14:14<11:38:00,  1.71it/s]
Train steps ... :  28%|██▊       | 28374/100000 [8:14:15<11:37:25,  1.71it/s]
Train steps ... :  28%|██▊       | 28375/100000 [8:14:15<11:37:19,  1.71it/s]Step... (28375 / 100000 | Loss: 0.8416301012039185, Learning Rate: 7.198492462311557e-05)
+
                                                                             
Step... (28375 / 100000 | Loss: 0.9032049179077148, Learning Rate: 7.198492462311557e-05)
+
Train steps ... :  28%|██▊       | 28375/100000 [8:14:16<11:37:19,  1.71it/s]
Train steps ... :  28%|██▊       | 28376/100000 [8:14:16<11:37:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28377/100000 [8:14:16<11:38:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28378/100000 [8:14:17<11:37:23,  1.71it/s]
Train steps ... :  28%|██▊       | 28379/100000 [8:14:18<11:37:17,  1.71it/s]
Train steps ... :  28%|██▊       | 28380/100000 [8:14:18<11:37:13,  1.71it/s]
Train steps ... :  28%|██▊       | 28381/100000 [8:14:19<11:37:25,  1.71it/s]
Train steps ... :  28%|██▊       | 28382/100000 [8:14:19<11:38:13,  1.71it/s]
Train steps ... :  28%|██▊       | 28383/100000 [8:14:20<11:37:44,  1.71it/s]
Train steps ... :  28%|██▊       | 28384/100000 [8:14:20<11:37:44,  1.71it/s]
Train steps ... :  28%|██▊       | 28385/100000 [8:14:21<11:37:51,  1.71it/s]
Train steps ... :  28%|██▊       | 28386/100000 [8:14:22<11:37:12,  1.71it/s]
Train steps ... :  28%|██▊       | 28387/100000 [8:14:22<11:36:51,  1.71it/s]
Train steps ... :  28%|██▊       | 28388/100000 [8:14:23<11:36:40,  1.71it/s]
Train steps ... :  28%|██▊       | 28389/100000 [8:14:23<11:36:52,  1.71it/s]
Train steps ... :  28%|██▊       | 28390/100000 [8:14:24<11:36:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28391/100000 [8:14:25<11:36:26,  1.71it/s]
Train steps ... :  28%|██▊       | 28392/100000 [8:14:25<11:37:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28393/100000 [8:14:26<11:37:11,  1.71it/s]
Train steps ... :  28%|██▊       | 28394/100000 [8:14:26<11:36:23,  1.71it/s]
Train steps ... :  28%|██▊       | 28395/100000 [8:14:27<11:36:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28396/100000 [8:14:27<11:37:52,  1.71it/s]
Train steps ... :  28%|██▊       | 28397/100000 [8:14:28<11:37:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28398/100000 [8:14:29<11:37:14,  1.71it/s]
Train steps ... :  28%|██▊       | 28399/100000 [8:14:29<11:38:24,  1.71it/s]
Train steps ... :  28%|██▊       | 28400/100000 [8:14:30<11:38:04,  1.71it/s]Step... (28400 / 100000 | Loss: 0.9528449773788452, Learning Rate: 7.195979899497488e-05)
+
                                                                             
Step... (28400 / 100000 | Loss: 0.8236767649650574, Learning Rate: 7.195979899497488e-05)
+
Train steps ... :  28%|██▊       | 28400/100000 [8:14:30<11:38:04,  1.71it/s]
Train steps ... :  28%|██▊       | 28401/100000 [8:14:30<11:37:15,  1.71it/s]
Train steps ... :  28%|██▊       | 28402/100000 [8:14:31<11:36:50,  1.71it/s]
Train steps ... :  28%|██▊       | 28403/100000 [8:14:32<11:37:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28404/100000 [8:14:32<11:37:26,  1.71it/s]
Train steps ... :  28%|██▊       | 28405/100000 [8:14:33<11:36:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28406/100000 [8:14:33<11:38:17,  1.71it/s]
Train steps ... :  28%|██▊       | 28407/100000 [8:14:34<11:37:35,  1.71it/s]
Train steps ... :  28%|██▊       | 28408/100000 [8:14:34<11:36:41,  1.71it/s]
Train steps ... :  28%|██▊       | 28409/100000 [8:14:35<11:36:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28410/100000 [8:14:36<11:37:39,  1.71it/s]
Train steps ... :  28%|██▊       | 28411/100000 [8:14:36<11:37:07,  1.71it/s]
Train steps ... :  28%|██▊       | 28412/100000 [8:14:37<11:37:06,  1.71it/s]
Train steps ... :  28%|██▊       | 28413/100000 [8:14:37<11:37:03,  1.71it/s]
Train steps ... :  28%|██▊       | 28414/100000 [8:14:38<11:38:19,  1.71it/s]
Train steps ... :  28%|██▊       | 28415/100000 [8:14:39<11:38:26,  1.71it/s]
Train steps ... :  28%|██▊       | 28416/100000 [8:14:39<11:37:51,  1.71it/s]
Train steps ... :  28%|██▊       | 28417/100000 [8:14:40<11:37:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28418/100000 [8:14:40<11:36:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28419/100000 [8:14:41<11:37:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28420/100000 [8:14:41<11:37:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28421/100000 [8:14:42<11:37:03,  1.71it/s]
Train steps ... :  28%|██▊       | 28422/100000 [8:14:43<11:36:56,  1.71it/s]
Train steps ... :  28%|██▊       | 28423/100000 [8:14:43<11:37:29,  1.71it/s]
Train steps ... :  28%|██▊       | 28424/100000 [8:14:44<11:37:47,  1.71it/s]
Train steps ... :  28%|██▊       | 28425/100000 [8:14:44<11:37:20,  1.71it/s]Step... (28425 / 100000 | Loss: 1.0168310403823853, Learning Rate: 7.193467336683417e-05)
+
                                                                             
Step... (28425 / 100000 | Loss: 0.9180203676223755, Learning Rate: 7.193467336683417e-05)
+
Train steps ... :  28%|██▊       | 28425/100000 [8:14:45<11:37:20,  1.71it/s]
Train steps ... :  28%|██▊       | 28426/100000 [8:14:45<11:37:41,  1.71it/s]
Train steps ... :  28%|██▊       | 28427/100000 [8:14:46<11:37:11,  1.71it/s]
Train steps ... :  28%|██▊       | 28428/100000 [8:14:46<11:38:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28429/100000 [8:14:47<11:38:11,  1.71it/s]
Train steps ... :  28%|██▊       | 28430/100000 [8:14:47<11:36:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28431/100000 [8:14:48<11:36:56,  1.71it/s]
Train steps ... :  28%|██▊       | 28432/100000 [8:14:49<11:38:42,  1.71it/s]
Train steps ... :  28%|██▊       | 28433/100000 [8:14:49<11:37:45,  1.71it/s]
Train steps ... :  28%|██▊       | 28434/100000 [8:14:50<11:37:23,  1.71it/s]
Train steps ... :  28%|██▊       | 28435/100000 [8:14:50<11:37:38,  1.71it/s]
Train steps ... :  28%|██▊       | 28436/100000 [8:14:51<11:37:42,  1.71it/s]
Train steps ... :  28%|██��       | 28437/100000 [8:14:51<11:37:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28438/100000 [8:14:52<11:36:41,  1.71it/s]
Train steps ... :  28%|██▊       | 28439/100000 [8:14:53<11:36:24,  1.71it/s]
Train steps ... :  28%|██▊       | 28440/100000 [8:14:53<11:36:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28441/100000 [8:14:54<11:37:04,  1.71it/s]
Train steps ... :  28%|██▊       | 28442/100000 [8:14:54<11:36:14,  1.71it/s]
Train steps ... :  28%|██▊       | 28443/100000 [8:14:55<11:36:40,  1.71it/s]
Train steps ... :  28%|██▊       | 28444/100000 [8:14:56<11:37:06,  1.71it/s]
Train steps ... :  28%|██▊       | 28445/100000 [8:14:56<11:37:28,  1.71it/s]
Train steps ... :  28%|██▊       | 28446/100000 [8:14:57<11:36:26,  1.71it/s]
Train steps ... :  28%|██▊       | 28447/100000 [8:14:57<11:36:53,  1.71it/s]
Train steps ... :  28%|██▊       | 28448/100000 [8:14:58<11:37:02,  1.71it/s]
Train steps ... :  28%|██▊       | 28449/100000 [8:14:58<11:36:53,  1.71it/s]
Train steps ... :  28%|██▊       | 28450/100000 [8:14:59<11:36:50,  1.71it/s]Step... (28450 / 100000 | Loss: 0.9410384893417358, Learning Rate: 7.190954773869348e-05)
+
                                                                             
Step... (28450 / 100000 | Loss: 0.8427327871322632, Learning Rate: 7.190954773869348e-05)
+
Train steps ... :  28%|██▊       | 28450/100000 [8:14:59<11:36:50,  1.71it/s]
Train steps ... :  28%|██▊       | 28451/100000 [8:15:00<11:37:08,  1.71it/s]
Train steps ... :  28%|██▊       | 28452/100000 [8:15:00<11:37:58,  1.71it/s]
Train steps ... :  28%|██▊       | 28453/100000 [8:15:01<11:37:38,  1.71it/s]
Train steps ... :  28%|██▊       | 28454/100000 [8:15:01<11:36:35,  1.71it/s]
Train steps ... :  28%|██▊       | 28455/100000 [8:15:02<11:36:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28456/100000 [8:15:03<11:36:03,  1.71it/s]
Train steps ... :  28%|██▊       | 28457/100000 [8:15:03<11:36:41,  1.71it/s]
Train steps ... :  28%|██▊       | 28458/100000 [8:15:04<11:37:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28459/100000 [8:15:04<11:37:25,  1.71it/s]
Train steps ... :  28%|██▊       | 28460/100000 [8:15:05<11:37:01,  1.71it/s]
Train steps ... :  28%|██▊       | 28461/100000 [8:15:05<11:36:59,  1.71it/s]
Train steps ... :  28%|██▊       | 28462/100000 [8:15:06<11:37:35,  1.71it/s]
Train steps ... :  28%|██▊       | 28463/100000 [8:15:07<11:37:49,  1.71it/s]
Train steps ... :  28%|██▊       | 28464/100000 [8:15:07<11:37:12,  1.71it/s]
Train steps ... :  28%|██▊       | 28465/100000 [8:15:08<11:37:03,  1.71it/s]
Train steps ... :  28%|██▊       | 28466/100000 [8:15:08<11:36:42,  1.71it/s]
Train steps ... :  28%|██▊       | 28467/100000 [8:15:09<11:36:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28468/100000 [8:15:10<11:36:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28469/100000 [8:15:10<11:36:48,  1.71it/s]
Train steps ... :  28%|██▊       | 28470/100000 [8:15:11<11:37:22,  1.71it/s]
Train steps ... :  28%|██▊       | 28471/100000 [8:15:11<11:38:18,  1.71it/s]
Train steps ... :  28%|██▊       | 28472/100000 [8:15:12<11:38:10,  1.71it/s]
Train steps ... :  28%|██▊       | 28473/100000 [8:15:12<11:37:16,  1.71it/s]
Train steps ... :  28%|██▊       | 28474/100000 [8:15:13<11:36:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28475/100000 [8:15:14<11:36:44,  1.71it/s]Step... (28475 / 100000 | Loss: 0.9054692983627319, Learning Rate: 7.188442211055276e-05)
+
                                                                             
Step... (28475 / 100000 | Loss: 1.1767196655273438, Learning Rate: 7.188442211055276e-05)
+
Train steps ... :  28%|██▊       | 28475/100000 [8:15:14<11:36:44,  1.71it/s]
Train steps ... :  28%|██▊       | 28476/100000 [8:15:14<11:36:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28477/100000 [8:15:15<11:36:21,  1.71it/s]
Train steps ... :  28%|██▊       | 28478/100000 [8:15:15<11:36:35,  1.71it/s]
Train steps ... :  28%|██▊       | 28479/100000 [8:15:16<11:36:11,  1.71it/s]
Train steps ... :  28%|██▊       | 28480/100000 [8:15:17<11:35:55,  1.71it/s]
Train steps ... :  28%|██▊       | 28481/100000 [8:15:17<11:36:56,  1.71it/s]
Train steps ... :  28%|██▊       | 28482/100000 [8:15:18<11:36:44,  1.71it/s]
Train steps ... :  28%|██▊       | 28483/100000 [8:15:18<11:37:13,  1.71it/s]
Train steps ... :  28%|██▊       | 28484/100000 [8:15:19<11:36:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28485/100000 [8:15:19<11:37:56,  1.71it/s]
Train steps ... :  28%|██▊       | 28486/100000 [8:15:20<11:38:03,  1.71it/s]
Train steps ... :  28%|██▊       | 28487/100000 [8:15:21<11:38:09,  1.71it/s]
Train steps ... :  28%|██▊       | 28488/100000 [8:15:21<11:38:22,  1.71it/s]
Train steps ... :  28%|██▊       | 28489/100000 [8:15:22<11:37:40,  1.71it/s]
Train steps ... :  28%|██▊       | 28490/100000 [8:15:22<11:36:37,  1.71it/s]
Train steps ... :  28%|██▊       | 28491/100000 [8:15:23<11:36:20,  1.71it/s]
Train steps ... :  28%|██▊       | 28492/100000 [8:15:24<11:36:24,  1.71it/s]
Train steps ... :  28%|██▊       | 28493/100000 [8:15:24<11:36:57,  1.71it/s]
Train steps ... :  28%|██▊       | 28494/100000 [8:15:25<11:37:22,  1.71it/s]
Train steps ... :  28%|██▊       | 28495/100000 [8:15:25<11:36:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28496/100000 [8:15:26<11:36:38,  1.71it/s]
Train steps ... :  28%|██▊       | 28497/100000 [8:15:27<11:36:46,  1.71it/s]
Train steps ... :  28%|██▊       | 28498/100000 [8:15:27<11:36:36,  1.71it/s]
Train steps ... :  28%|██▊       | 28499/100000 [8:15:28<11:36:21,  1.71it/s]
Train steps ... :  28%|██▊       | 28500/100000 [8:15:28<11:36:42,  1.71it/s]Step... (28500 / 100000 | Loss: 0.9523708820343018, Learning Rate: 7.185929648241206e-05)
+
                                                                             
Step... (28500 / 100000 | Loss: 0.7590537071228027, Learning Rate: 7.185929648241206e-05)
+
Train steps ... :  28%|██▊       | 28500/100000 [8:15:29<11:36:42,  1.71it/s]
Train steps ... :  29%|██▊       | 28501/100000 [8:15:29<11:36:49,  1.71it/s]
Train steps ... :  29%|██▊       | 28502/100000 [8:15:29<11:36:20,  1.71it/s]
Train steps ... :  29%|██▊       | 28503/100000 [8:15:30<11:36:11,  1.71it/s]
Train steps ... :  29%|██▊       | 28504/100000 [8:15:31<11:37:04,  1.71it/s]
Train steps ... :  29%|██▊       | 28505/100000 [8:15:31<11:37:52,  1.71it/s]
Train steps ... :  29%|██▊       | 28506/100000 [8:15:32<11:36:53,  1.71it/s]
Train steps ... :  29%|██▊       | 28507/100000 [8:15:32<11:36:20,  1.71it/s]
Train steps ... :  29%|██▊       | 28508/100000 [8:15:33<11:36:42,  1.71it/s]
Train steps ... :  29%|██▊       | 28509/100000 [8:15:34<11:37:06,  1.71it/s]
Train steps ... :  29%|██▊       | 28510/100000 [8:15:34<11:37:44,  1.71it/s]
Train steps ... :  29%|██▊       | 28511/100000 [8:15:35<11:37:10,  1.71it/s]
Train steps ... :  29%|██▊       | 28512/100000 [8:15:35<11:36:45,  1.71it/s]
Train steps ... :  29%|██▊       | 28513/100000 [8:15:36<11:36:55,  1.71it/s]
Train steps ... :  29%|██▊       | 28514/100000 [8:15:36<11:36:39,  1.71it/s]
Train steps ... :  29%|██▊       | 28515/100000 [8:15:37<11:36:24,  1.71it/s]
Train steps ... :  29%|██▊       | 28516/100000 [8:15:38<11:36:43,  1.71it/s]
Train steps ... :  29%|██▊       | 28517/100000 [8:15:38<11:36:47,  1.71it/s]
Train steps ... :  29%|██▊       | 28518/100000 [8:15:39<11:36:39,  1.71it/s]
Train steps ... :  29%|██▊       | 28519/100000 [8:15:39<11:36:26,  1.71it/s]
Train steps ... :  29%|██▊       | 28520/100000 [8:15:40<11:36:11,  1.71it/s]
Train steps ... :  29%|██▊       | 28521/100000 [8:15:41<11:35:21,  1.71it/s]
Train steps ... :  29%|██▊       | 28522/100000 [8:15:41<11:34:59,  1.71it/s]
Train steps ... :  29%|██▊       | 28523/100000 [8:15:42<11:36:09,  1.71it/s]
Train steps ... :  29%|██▊       | 28524/100000 [8:15:42<11:35:07,  1.71it/s]
Train steps ... :  29%|██▊       | 28525/100000 [8:15:43<11:35:17,  1.71it/s]Step... (28525 / 100000 | Loss: 1.332777738571167, Learning Rate: 7.183417085427137e-05)
+
                                                                             
Step... (28525 / 100000 | Loss: 1.0774853229522705, Learning Rate: 7.183417085427137e-05)
+
Train steps ... :  29%|██▊       | 28525/100000 [8:15:43<11:35:17,  1.71it/s]
Train steps ... :  29%|██▊       | 28526/100000 [8:15:43<11:35:24,  1.71it/s]
Train steps ... :  29%|██▊       | 28527/100000 [8:15:44<11:34:55,  1.71it/s]
Train steps ... :  29%|██▊       | 28528/100000 [8:15:45<11:36:23,  1.71it/s]
Train steps ... :  29%|██▊       | 28529/100000 [8:15:45<11:36:10,  1.71it/s]
Train steps ... :  29%|██▊       | 28530/100000 [8:15:46<11:36:05,  1.71it/s]
Train steps ... :  29%|██▊       | 28531/100000 [8:15:46<11:35:52,  1.71it/s]
Train steps ... :  29%|██▊       | 28532/100000 [8:15:47<11:35:54,  1.71it/s]
Train steps ... :  29%|██▊       | 28533/100000 [8:15:48<11:35:24,  1.71it/s]
Train steps ... :  29%|██▊       | 28534/100000 [8:15:48<11:35:31,  1.71it/s]
Train steps ... :  29%|██▊       | 28535/100000 [8:15:49<11:36:12,  1.71it/s]
Train steps ... :  29%|██▊       | 28536/100000 [8:15:49<11:35:52,  1.71it/s]
Train steps ... :  29%|██▊       | 28537/100000 [8:15:50<11:35:36,  1.71it/s]
Train steps ... :  29%|██▊       | 28538/100000 [8:15:50<11:35:55,  1.71it/s]
Train steps ... :  29%|██▊       | 28539/100000 [8:15:51<11:37:01,  1.71it/s]
Train steps ... :  29%|██▊       | 28540/100000 [8:15:52<11:37:41,  1.71it/s]
Train steps ... :  29%|██▊       | 28541/100000 [8:15:52<11:37:37,  1.71it/s]
Train steps ... :  29%|██▊       | 28542/100000 [8:15:53<11:36:55,  1.71it/s]
Train steps ... :  29%|██▊       | 28543/100000 [8:15:53<11:36:39,  1.71it/s]
Train steps ... :  29%|██▊       | 28544/100000 [8:15:54<11:37:30,  1.71it/s]
Train steps ... :  29%|██▊       | 28545/100000 [8:15:55<11:36:57,  1.71it/s]
Train steps ... :  29%|██▊       | 28546/100000 [8:15:55<11:36:21,  1.71it/s]
Train steps ... :  29%|██▊       | 28547/100000 [8:15:56<11:35:55,  1.71it/s]
Train steps ... :  29%|██▊       | 28548/100000 [8:15:56<11:36:49,  1.71it/s]
Train steps ... :  29%|██▊       | 28549/100000 [8:15:57<11:36:23,  1.71it/s]
Train steps ... :  29%|██▊       | 28550/100000 [8:15:57<11:37:02,  1.71it/s]Step... (28550 / 100000 | Loss: 1.0282533168792725, Learning Rate: 7.180904522613065e-05)
+
                                                                             
Step... (28550 / 100000 | Loss: 0.8524099588394165, Learning Rate: 7.180904522613065e-05)
+
Train steps ... :  29%|██▊       | 28550/100000 [8:15:58<11:37:02,  1.71it/s]
Train steps ... :  29%|██▊       | 28551/100000 [8:15:58<11:37:11,  1.71it/s]
Train steps ... :  29%|██▊       | 28552/100000 [8:15:59<11:37:13,  1.71it/s]
Train steps ... :  29%|██▊       | 28553/100000 [8:15:59<11:37:34,  1.71it/s]
Train steps ... :  29%|██▊       | 28554/100000 [8:16:00<11:36:06,  1.71it/s]
Train steps ... :  29%|██▊       | 28555/100000 [8:16:00<11:35:44,  1.71it/s]
Train steps ... :  29%|██▊       | 28556/100000 [8:16:01<11:35:39,  1.71it/s]
Train steps ... :  29%|██▊       | 28557/100000 [8:16:02<11:36:04,  1.71it/s]
Train steps ... :  29%|██▊       | 28558/100000 [8:16:02<11:36:14,  1.71it/s]
Train steps ... :  29%|██▊       | 28559/100000 [8:16:03<11:36:32,  1.71it/s]
Train steps ... :  29%|██▊       | 28560/100000 [8:16:03<11:36:14,  1.71it/s]
Train steps ... :  29%|██▊       | 28561/100000 [8:16:04<11:37:11,  1.71it/s]
Train steps ... :  29%|██▊       | 28562/100000 [8:16:05<11:36:12,  1.71it/s]
Train steps ... :  29%|██▊       | 28563/100000 [8:16:05<11:35:48,  1.71it/s]
Train steps ... :  29%|██▊       | 28564/100000 [8:16:06<11:36:18,  1.71it/s]
Train steps ... :  29%|██▊       | 28565/100000 [8:16:06<11:37:33,  1.71it/s]
Train steps ... :  29%|██▊       | 28566/100000 [8:16:07<11:37:38,  1.71it/s]
Train steps ... :  29%|██▊       | 28567/100000 [8:16:07<11:37:10,  1.71it/s]
Train steps ... :  29%|██▊       | 28568/100000 [8:16:08<11:37:51,  1.71it/s]
Train steps ... :  29%|██▊       | 28569/100000 [8:16:09<11:36:27,  1.71it/s]
Train steps ... :  29%|██▊       | 28570/100000 [8:16:09<11:36:44,  1.71it/s]
Train steps ... :  29%|██▊       | 28571/100000 [8:16:10<11:36:13,  1.71it/s]
Train steps ... :  29%|██▊       | 28572/100000 [8:16:10<11:35:53,  1.71it/s]
Train steps ... :  29%|██▊       | 28573/100000 [8:16:11<11:35:32,  1.71it/s]
Train steps ... :  29%|██▊       | 28574/100000 [8:16:12<11:34:57,  1.71it/s]
Train steps ... :  29%|██▊       | 28575/100000 [8:16:12<11:35:30,  1.71it/s]Step... (28575 / 100000 | Loss: 1.1177406311035156, Learning Rate: 7.178391959798996e-05)
+
                                                                             
Step... (28575 / 100000 | Loss: 0.918906033039093, Learning Rate: 7.178391959798996e-05)
+
Train steps ... :  29%|██▊       | 28575/100000 [8:16:12<11:35:30,  1.71it/s]
Train steps ... :  29%|██▊       | 28576/100000 [8:16:13<11:35:55,  1.71it/s]
Train steps ... :  29%|██▊       | 28577/100000 [8:16:13<11:35:27,  1.71it/s]
Train steps ... :  29%|██▊       | 28578/100000 [8:16:14<11:35:39,  1.71it/s]
Train steps ... :  29%|██▊       | 28579/100000 [8:16:14<11:35:18,  1.71it/s]
Train steps ... :  29%|██▊       | 28580/100000 [8:16:15<11:34:58,  1.71it/s]
Train steps ... :  29%|██▊       | 28581/100000 [8:16:16<11:34:46,  1.71it/s]
Train steps ... :  29%|██▊       | 28582/100000 [8:16:16<11:34:52,  1.71it/s]
Train steps ... :  29%|██▊       | 28583/100000 [8:16:17<11:36:01,  1.71it/s]
Train steps ... :  29%|██▊       | 28584/100000 [8:16:17<11:36:03,  1.71it/s]
Train steps ... :  29%|██▊       | 28585/100000 [8:16:18<11:36:01,  1.71it/s]
Train steps ... :  29%|██▊       | 28586/100000 [8:16:19<11:35:34,  1.71it/s]
Train steps ... :  29%|██▊       | 28587/100000 [8:16:19<11:35:38,  1.71it/s]
Train steps ... :  29%|██▊       | 28588/100000 [8:16:20<11:35:24,  1.71it/s]
Train steps ... :  29%|██▊       | 28589/100000 [8:16:20<11:35:55,  1.71it/s]
Train steps ... :  29%|██▊       | 28590/100000 [8:16:21<11:35:22,  1.71it/s]
Train steps ... :  29%|██▊       | 28591/100000 [8:16:21<11:35:18,  1.71it/s]
Train steps ... :  29%|██▊       | 28592/100000 [8:16:22<11:34:45,  1.71it/s]
Train steps ... :  29%|██▊       | 28593/100000 [8:16:23<11:35:17,  1.71it/s]
Train steps ... :  29%|██▊       | 28594/100000 [8:16:23<11:34:53,  1.71it/s]
Train steps ... :  29%|██▊       | 28595/100000 [8:16:24<11:35:56,  1.71it/s]
Train steps ... :  29%|██▊       | 28596/100000 [8:16:24<11:35:41,  1.71it/s]
Train steps ... :  29%|██▊       | 28597/100000 [8:16:25<11:35:46,  1.71it/s]
Train steps ... :  29%|██▊       | 28598/100000 [8:16:26<11:35:51,  1.71it/s]
Train steps ... :  29%|██▊       | 28599/100000 [8:16:26<11:35:12,  1.71it/s]
Train steps ... :  29%|██▊       | 28600/100000 [8:16:27<11:36:11,  1.71it/s]Step... (28600 / 100000 | Loss: 0.8009798526763916, Learning Rate: 7.175879396984924e-05)
+
                                                                             
Step... (28600 / 100000 | Loss: 0.793571949005127, Learning Rate: 7.175879396984924e-05)
+
Train steps ... :  29%|██▊       | 28600/100000 [8:16:27<11:36:11,  1.71it/s]
Train steps ... :  29%|██▊       | 28601/100000 [8:16:27<11:36:09,  1.71it/s]
Train steps ... :  29%|██▊       | 28602/100000 [8:16:28<11:35:56,  1.71it/s]
Train steps ... :  29%|██▊       | 28603/100000 [8:16:28<11:35:09,  1.71it/s]
Train steps ... :  29%|██▊       | 28604/100000 [8:16:29<11:35:57,  1.71it/s]
Train steps ... :  29%|██▊       | 28605/100000 [8:16:30<11:37:20,  1.71it/s]
Train steps ... :  29%|██▊       | 28606/100000 [8:16:30<11:37:06,  1.71it/s]
Train steps ... :  29%|██▊       | 28607/100000 [8:16:31<11:36:07,  1.71it/s]
Train steps ... :  29%|██▊       | 28608/100000 [8:16:31<11:35:37,  1.71it/s]
Train steps ... :  29%|██▊       | 28609/100000 [8:16:32<11:35:03,  1.71it/s]
Train steps ... :  29%|██▊       | 28610/100000 [8:16:33<11:35:11,  1.71it/s]
Train steps ... :  29%|██▊       | 28611/100000 [8:16:33<11:35:34,  1.71it/s]
Train steps ... :  29%|██▊       | 28612/100000 [8:16:34<11:35:18,  1.71it/s]
Train steps ... :  29%|██▊       | 28613/100000 [8:16:34<11:36:17,  1.71it/s]
Train steps ... :  29%|██▊       | 28614/100000 [8:16:35<11:35:46,  1.71it/s]
Train steps ... :  29%|██▊       | 28615/100000 [8:16:35<11:35:58,  1.71it/s]
Train steps ... :  29%|██▊       | 28616/100000 [8:16:36<11:35:45,  1.71it/s]
Train steps ... :  29%|██▊       | 28617/100000 [8:16:37<11:35:41,  1.71it/s]
Train steps ... :  29%|██▊       | 28618/100000 [8:16:37<11:36:08,  1.71it/s]
Train steps ... :  29%|██▊       | 28619/100000 [8:16:38<11:35:17,  1.71it/s]
Train steps ... :  29%|██▊       | 28620/100000 [8:16:38<11:35:43,  1.71it/s]
Train steps ... :  29%|██▊       | 28621/100000 [8:16:39<11:35:21,  1.71it/s]
Train steps ... :  29%|██▊       | 28622/100000 [8:16:40<11:36:24,  1.71it/s]
Train steps ... :  29%|██▊       | 28623/100000 [8:16:40<11:35:47,  1.71it/s]
Train steps ... :  29%|██▊       | 28624/100000 [8:16:41<11:35:25,  1.71it/s]
Train steps ... :  29%|██▊       | 28625/100000 [8:16:41<11:35:37,  1.71it/s]Step... (28625 / 100000 | Loss: 1.1142146587371826, Learning Rate: 7.173366834170855e-05)
+
                                                                             
Step... (28625 / 100000 | Loss: 0.9618755578994751, Learning Rate: 7.173366834170855e-05)
+
Train steps ... :  29%|██▊       | 28625/100000 [8:16:42<11:35:37,  1.71it/s]
Train steps ... :  29%|██▊       | 28626/100000 [8:16:42<11:35:48,  1.71it/s]
Train steps ... :  29%|██▊       | 28627/100000 [8:16:43<11:34:54,  1.71it/s]
Train steps ... :  29%|██▊       | 28628/100000 [8:16:43<11:34:40,  1.71it/s]
Train steps ... :  29%|██▊       | 28629/100000 [8:16:44<11:34:22,  1.71it/s]
Train steps ... :  29%|██▊       | 28630/100000 [8:16:44<11:35:02,  1.71it/s]
Train steps ... :  29%|██▊       | 28631/100000 [8:16:45<11:34:37,  1.71it/s]
Train steps ... :  29%|██▊       | 28632/100000 [8:16:45<11:35:05,  1.71it/s]
Train steps ... :  29%|██▊       | 28633/100000 [8:16:46<11:35:03,  1.71it/s]
Train steps ... :  29%|██▊       | 28634/100000 [8:16:47<11:35:21,  1.71it/s]
Train steps ... :  29%|██▊       | 28635/100000 [8:16:47<11:34:58,  1.71it/s]
Train steps ... :  29%|██▊       | 28636/100000 [8:16:48<11:35:21,  1.71it/s]
Train steps ... :  29%|██▊       | 28637/100000 [8:16:48<11:35:07,  1.71it/s]
Train steps ... :  29%|██▊       | 28638/100000 [8:16:49<11:34:42,  1.71it/s]
Train steps ... :  29%|██▊       | 28639/100000 [8:16:50<11:35:15,  1.71it/s]
Train steps ... :  29%|██▊       | 28640/100000 [8:16:50<11:35:53,  1.71it/s]
Train steps ... :  29%|██▊       | 28641/100000 [8:16:51<11:34:57,  1.71it/s]
Train steps ... :  29%|██▊       | 28642/100000 [8:16:51<11:35:23,  1.71it/s]
Train steps ... :  29%|██▊       | 28643/100000 [8:16:52<11:34:52,  1.71it/s]
Train steps ... :  29%|██▊       | 28644/100000 [8:16:52<11:35:51,  1.71it/s]
Train steps ... :  29%|██▊       | 28645/100000 [8:16:53<11:36:13,  1.71it/s]
Train steps ... :  29%|██▊       | 28646/100000 [8:16:54<11:35:10,  1.71it/s]
Train steps ... :  29%|██▊       | 28647/100000 [8:16:54<11:35:30,  1.71it/s]
Train steps ... :  29%|██���       | 28648/100000 [8:16:55<11:34:54,  1.71it/s]
Train steps ... :  29%|██▊       | 28649/100000 [8:16:55<11:34:17,  1.71it/s]
Train steps ... :  29%|██▊       | 28650/100000 [8:16:56<11:35:44,  1.71it/s]Step... (28650 / 100000 | Loss: 0.8302571773529053, Learning Rate: 7.170854271356784e-05)
+
                                                                             
Step... (28650 / 100000 | Loss: 0.9691042900085449, Learning Rate: 7.170854271356784e-05)
+
Train steps ... :  29%|██▊       | 28650/100000 [8:16:56<11:35:44,  1.71it/s]
Train steps ... :  29%|██▊       | 28651/100000 [8:16:57<11:35:27,  1.71it/s]
Train steps ... :  29%|██▊       | 28652/100000 [8:16:57<11:34:59,  1.71it/s]
Train steps ... :  29%|██▊       | 28653/100000 [8:16:58<11:34:46,  1.71it/s]
Train steps ... :  29%|██▊       | 28654/100000 [8:16:58<11:35:08,  1.71it/s]
Train steps ... :  29%|██▊       | 28655/100000 [8:16:59<11:34:53,  1.71it/s]
Train steps ... :  29%|██▊       | 28656/100000 [8:16:59<11:34:28,  1.71it/s]
Train steps ... :  29%|██▊       | 28657/100000 [8:17:00<11:34:29,  1.71it/s]
Train steps ... :  29%|██▊       | 28658/100000 [8:17:01<11:34:22,  1.71it/s]
Train steps ... :  29%|██▊       | 28659/100000 [8:17:01<11:33:58,  1.71it/s]
Train steps ... :  29%|██▊       | 28660/100000 [8:17:02<11:34:47,  1.71it/s]
Train steps ... :  29%|██▊       | 28661/100000 [8:17:02<11:35:26,  1.71it/s]
Train steps ... :  29%|██▊       | 28662/100000 [8:17:03<11:35:54,  1.71it/s]
Train steps ... :  29%|██▊       | 28663/100000 [8:17:04<11:35:36,  1.71it/s]
Train steps ... :  29%|██▊       | 28664/100000 [8:17:04<11:35:10,  1.71it/s]
Train steps ... :  29%|██▊       | 28665/100000 [8:17:05<11:35:21,  1.71it/s]
Train steps ... :  29%|██▊       | 28666/100000 [8:17:05<11:34:46,  1.71it/s]
Train steps ... :  29%|██▊       | 28667/100000 [8:17:06<11:34:46,  1.71it/s]
Train steps ... :  29%|██▊       | 28668/100000 [8:17:06<11:35:57,  1.71it/s]
Train steps ... :  29%|██▊       | 28669/100000 [8:17:07<11:35:45,  1.71it/s]
Train steps ... :  29%|██▊       | 28670/100000 [8:17:08<11:35:32,  1.71it/s]
Train steps ... :  29%|██▊       | 28671/100000 [8:17:08<11:35:18,  1.71it/s]
Train steps ... :  29%|██▊       | 28672/100000 [8:17:09<11:35:01,  1.71it/s]
Train steps ... :  29%|██▊       | 28673/100000 [8:17:09<11:35:03,  1.71it/s]
Train steps ... :  29%|██▊       | 28674/100000 [8:17:10<11:34:52,  1.71it/s]
Train steps ... :  29%|██▊       | 28675/100000 [8:17:11<11:34:32,  1.71it/s]Step... (28675 / 100000 | Loss: 0.9730486869812012, Learning Rate: 7.168341708542713e-05)
+
                                                                             
Step... (28675 / 100000 | Loss: 0.8239189386367798, Learning Rate: 7.168341708542713e-05)
+
Train steps ... :  29%|██▊       | 28675/100000 [8:17:11<11:34:32,  1.71it/s]
Train steps ... :  29%|██▊       | 28676/100000 [8:17:11<11:35:33,  1.71it/s]
Train steps ... :  29%|██▊       | 28677/100000 [8:17:12<11:35:45,  1.71it/s]
Train steps ... :  29%|██▊       | 28678/100000 [8:17:12<11:36:10,  1.71it/s]
Train steps ... :  29%|██▊       | 28679/100000 [8:17:13<11:35:50,  1.71it/s]
Train steps ... :  29%|██▊       | 28680/100000 [8:17:14<11:35:26,  1.71it/s]
Train steps ... :  29%|██▊       | 28681/100000 [8:17:14<11:35:16,  1.71it/s]
Train steps ... :  29%|██▊       | 28682/100000 [8:17:15<11:35:42,  1.71it/s]
Train steps ... :  29%|██▊       | 28683/100000 [8:17:15<11:34:57,  1.71it/s]
Train steps ... :  29%|██▊       | 28684/100000 [8:17:16<11:34:59,  1.71it/s]
Train steps ... :  29%|██▊       | 28685/100000 [8:17:16<11:34:24,  1.71it/s]
Train steps ... :  29%|██▊       | 28686/100000 [8:17:17<11:35:36,  1.71it/s]
Train steps ... :  29%|██▊       | 28687/100000 [8:17:18<11:34:10,  1.71it/s]
Train steps ... :  29%|██▊       | 28688/100000 [8:17:18<11:34:19,  1.71it/s]
Train steps ... :  29%|██▊       | 28689/100000 [8:17:19<11:33:47,  1.71it/s]
Train steps ... :  29%|██▊       | 28690/100000 [8:17:19<11:34:35,  1.71it/s]
Train steps ... :  29%|██▊       | 28691/100000 [8:17:20<11:34:48,  1.71it/s]
Train steps ... :  29%|██▊       | 28692/100000 [8:17:21<11:35:01,  1.71it/s]
Train steps ... :  29%|██▊       | 28693/100000 [8:17:21<11:34:48,  1.71it/s]
Train steps ... :  29%|██▊       | 28694/100000 [8:17:22<11:34:43,  1.71it/s]
Train steps ... :  29%|██▊       | 28695/100000 [8:17:22<11:34:08,  1.71it/s]
Train steps ... :  29%|██▊       | 28696/100000 [8:17:23<11:33:46,  1.71it/s]
Train steps ... :  29%|██▊       | 28697/100000 [8:17:23<11:34:41,  1.71it/s]
Train steps ... :  29%|██▊       | 28698/100000 [8:17:24<11:34:21,  1.71it/s]
Train steps ... :  29%|██▊       | 28699/100000 [8:17:25<11:34:01,  1.71it/s]
Train steps ... :  29%|██▊       | 28700/100000 [8:17:25<11:34:05,  1.71it/s]Step... (28700 / 100000 | Loss: 1.1412161588668823, Learning Rate: 7.165829145728643e-05)
+
                                                                             
Step... (28700 / 100000 | Loss: 0.8954319953918457, Learning Rate: 7.165829145728643e-05)
+
Train steps ... :  29%|██▊       | 28700/100000 [8:17:26<11:34:05,  1.71it/s]
Train steps ... :  29%|██▊       | 28701/100000 [8:17:26<11:35:13,  1.71it/s]
Train steps ... :  29%|██▊       | 28702/100000 [8:17:26<11:35:25,  1.71it/s]
Train steps ... :  29%|██▊       | 28703/100000 [8:17:27<11:35:45,  1.71it/s]
Train steps ... :  29%|██▊       | 28704/100000 [8:17:28<11:36:17,  1.71it/s]
Train steps ... :  29%|██▊       | 28705/100000 [8:17:28<11:35:17,  1.71it/s]
Train steps ... :  29%|██▊       | 28706/100000 [8:17:29<11:35:24,  1.71it/s]
Train steps ... :  29%|██▊       | 28707/100000 [8:17:29<11:34:39,  1.71it/s]
Train steps ... :  29%|██▊       | 28708/100000 [8:17:30<11:34:43,  1.71it/s]
Train steps ... :  29%|██▊       | 28709/100000 [8:17:30<11:34:37,  1.71it/s]
Train steps ... :  29%|██▊       | 28710/100000 [8:17:31<11:33:57,  1.71it/s]
Train steps ... :  29%|██▊       | 28711/100000 [8:17:32<11:33:34,  1.71it/s]
Train steps ... :  29%|██▊       | 28712/100000 [8:17:32<11:33:55,  1.71it/s]
Train steps ... :  29%|██▊       | 28713/100000 [8:17:33<11:34:07,  1.71it/s]
Train steps ... :  29%|██▊       | 28714/100000 [8:17:33<11:34:37,  1.71it/s]
Train steps ... :  29%|██▊       | 28715/100000 [8:17:34<11:34:18,  1.71it/s]
Train steps ... :  29%|██▊       | 28716/100000 [8:17:35<11:33:58,  1.71it/s]
Train steps ... :  29%|██▊       | 28717/100000 [8:17:35<11:34:59,  1.71it/s]
Train steps ... :  29%|██▊       | 28718/100000 [8:17:36<11:35:41,  1.71it/s]
Train steps ... :  29%|██▊       | 28719/100000 [8:17:36<11:35:22,  1.71it/s]
Train steps ... :  29%|██▊       | 28720/100000 [8:17:37<11:34:45,  1.71it/s]
Train steps ... :  29%|██▊       | 28721/100000 [8:17:37<11:35:08,  1.71it/s]
Train steps ... :  29%|██▊       | 28722/100000 [8:17:38<11:35:38,  1.71it/s]
Train steps ... :  29%|██▊       | 28723/100000 [8:17:39<11:35:29,  1.71it/s]
Train steps ... :  29%|██▊       | 28724/100000 [8:17:39<11:36:15,  1.71it/s]
Train steps ... :  29%|██▊       | 28725/100000 [8:17:40<11:35:19,  1.71it/s]Step... (28725 / 100000 | Loss: 1.2324804067611694, Learning Rate: 7.163316582914573e-05)
+
                                                                             
Step... (28725 / 100000 | Loss: 0.7226203083992004, Learning Rate: 7.163316582914573e-05)
+
Train steps ... :  29%|██▊       | 28725/100000 [8:17:40<11:35:19,  1.71it/s]
Train steps ... :  29%|██▊       | 28726/100000 [8:17:40<11:35:04,  1.71it/s]
Train steps ... :  29%|██▊       | 28727/100000 [8:17:41<11:35:35,  1.71it/s]
Train steps ... :  29%|██▊       | 28728/100000 [8:17:42<11:35:18,  1.71it/s]
Train steps ... :  29%|██▊       | 28729/100000 [8:17:42<11:34:54,  1.71it/s]
Train steps ... :  29%|██▊       | 28730/100000 [8:17:43<11:34:17,  1.71it/s]
Train steps ... :  29%|██▊       | 28731/100000 [8:17:43<11:34:03,  1.71it/s]
Train steps ... :  29%|██▊       | 28732/100000 [8:17:44<11:33:57,  1.71it/s]
Train steps ... :  29%|██▊       | 28733/100000 [8:17:44<11:33:49,  1.71it/s]
Train steps ... :  29%|██▊       | 28734/100000 [8:17:45<11:34:26,  1.71it/s]
Train steps ... :  29%|██▊       | 28735/100000 [8:17:46<11:34:05,  1.71it/s]
Train steps ... :  29%|██▊       | 28736/100000 [8:17:46<11:35:18,  1.71it/s]
Train steps ... :  29%|██▊       | 28737/100000 [8:17:47<11:34:53,  1.71it/s]
Train steps ... :  29%|██▊       | 28738/100000 [8:17:47<11:35:36,  1.71it/s]
Train steps ... :  29%|██▊       | 28739/100000 [8:17:48<11:36:05,  1.71it/s]
Train steps ... :  29%|██▊       | 28740/100000 [8:17:49<11:35:25,  1.71it/s]
Train steps ... :  29%|██▊       | 28741/100000 [8:17:49<11:35:57,  1.71it/s]
Train steps ... :  29%|██▊       | 28742/100000 [8:17:50<11:35:07,  1.71it/s]
Train steps ... :  29%|██▊       | 28743/100000 [8:17:50<11:35:54,  1.71it/s]
Train steps ... :  29%|██▊       | 28744/100000 [8:17:51<11:36:08,  1.71it/s]
Train steps ... :  29%|██▊       | 28745/100000 [8:17:52<11:35:24,  1.71it/s]
Train steps ... :  29%|██▊       | 28746/100000 [8:17:52<11:35:00,  1.71it/s]
Train steps ... :  29%|██▊       | 28747/100000 [8:17:53<11:34:42,  1.71it/s]
Train steps ... :  29%|██▊       | 28748/100000 [8:17:53<11:34:35,  1.71it/s]
Train steps ... :  29%|██▊       | 28749/100000 [8:17:54<11:34:31,  1.71it/s]
Train steps ... :  29%|██▉       | 28750/100000 [8:17:54<11:33:31,  1.71it/s]Step... (28750 / 100000 | Loss: 1.026596188545227, Learning Rate: 7.160804020100504e-05)
+
                                                                             
Step... (28750 / 100000 | Loss: 1.124592661857605, Learning Rate: 7.160804020100504e-05)
+
Train steps ... :  29%|██▉       | 28750/100000 [8:17:55<11:33:31,  1.71it/s]
Train steps ... :  29%|██▉       | 28751/100000 [8:17:55<11:34:13,  1.71it/s]
Train steps ... :  29%|██▉       | 28752/100000 [8:17:56<11:33:52,  1.71it/s]
Train steps ... :  29%|██▉       | 28753/100000 [8:17:56<11:33:51,  1.71it/s]
Train steps ... :  29%|██▉       | 28754/100000 [8:17:57<11:34:10,  1.71it/s]
Train steps ... :  29%|██▉       | 28755/100000 [8:17:57<11:33:47,  1.71it/s]
Train steps ... :  29%|██▉       | 28756/100000 [8:17:58<11:34:08,  1.71it/s]
Train steps ... :  29%|██▉       | 28757/100000 [8:17:59<11:33:47,  1.71it/s]
Train steps ... :  29%|██▉       | 28758/100000 [8:17:59<11:34:50,  1.71it/s]
Train steps ... :  29%|██▉       | 28759/100000 [8:18:00<11:34:59,  1.71it/s]
Train steps ... :  29%|██▉       | 28760/100000 [8:18:00<11:34:08,  1.71it/s]
Train steps ... :  29%|██▉       | 28761/100000 [8:18:01<11:33:49,  1.71it/s]
Train steps ... :  29%|██▉       | 28762/100000 [8:18:01<11:33:16,  1.71it/s]
Train steps ... :  29%|██▉       | 28763/100000 [8:18:02<11:33:33,  1.71it/s]
Train steps ... :  29%|██▉       | 28764/100000 [8:18:03<11:33:22,  1.71it/s]
Train steps ... :  29%|██▉       | 28765/100000 [8:18:03<11:34:06,  1.71it/s]
Train steps ... :  29%|██▉       | 28766/100000 [8:18:04<11:33:23,  1.71it/s]
Train steps ... :  29%|██▉       | 28767/100000 [8:18:04<11:33:26,  1.71it/s]
Train steps ... :  29%|██▉       | 28768/100000 [8:18:05<11:34:48,  1.71it/s]
Train steps ... :  29%|██▉       | 28769/100000 [8:18:06<11:34:48,  1.71it/s]
Train steps ... :  29%|██▉       | 28770/100000 [8:18:06<11:34:19,  1.71it/s]
Train steps ... :  29%|██▉       | 28771/100000 [8:18:07<11:35:18,  1.71it/s]
Train steps ... :  29%|██▉       | 28772/100000 [8:18:07<11:34:06,  1.71it/s]
Train steps ... :  29%|██▉       | 28773/100000 [8:18:08<11:35:22,  1.71it/s]
Train steps ... :  29%|██▉       | 28774/100000 [8:18:08<11:34:45,  1.71it/s]
Train steps ... :  29%|██▉       | 28775/100000 [8:18:09<11:35:24,  1.71it/s]Step... (28775 / 100000 | Loss: 0.8518745303153992, Learning Rate: 7.158291457286432e-05)
+
                                                                             
Step... (28775 / 100000 | Loss: 1.247478723526001, Learning Rate: 7.158291457286432e-05)
+
Train steps ... :  29%|██▉       | 28775/100000 [8:18:09<11:35:24,  1.71it/s]
Train steps ... :  29%|██▉       | 28776/100000 [8:18:10<11:35:36,  1.71it/s]
Train steps ... :  29%|██▉       | 28777/100000 [8:18:10<11:34:33,  1.71it/s]
Train steps ... :  29%|██▉       | 28778/100000 [8:18:11<11:34:10,  1.71it/s]
Train steps ... :  29%|██▉       | 28779/100000 [8:18:11<11:34:27,  1.71it/s]
Train steps ... :  29%|██▉       | 28780/100000 [8:18:12<11:34:01,  1.71it/s]
Train steps ... :  29%|██▉       | 28781/100000 [8:18:13<11:34:18,  1.71it/s]
Train steps ... :  29%|██▉       | 28782/100000 [8:18:13<11:34:30,  1.71it/s]
Train steps ... :  29%|██▉       | 28783/100000 [8:18:14<11:33:38,  1.71it/s]
Train steps ... :  29%|██▉       | 28784/100000 [8:18:14<11:34:20,  1.71it/s]
Train steps ... :  29%|██▉       | 28785/100000 [8:18:15<11:33:56,  1.71it/s]
Train steps ... :  29%|██▉       | 28786/100000 [8:18:15<11:34:41,  1.71it/s]
Train steps ... :  29%|██▉       | 28787/100000 [8:18:16<11:34:57,  1.71it/s]
Train steps ... :  29%|██▉       | 28788/100000 [8:18:17<11:34:00,  1.71it/s]
Train steps ... :  29%|██▉       | 28789/100000 [8:18:17<11:34:13,  1.71it/s]
Train steps ... :  29%|██▉       | 28790/100000 [8:18:18<11:33:48,  1.71it/s]
Train steps ... :  29%|██▉       | 28791/100000 [8:18:18<11:34:16,  1.71it/s]
Train steps ... :  29%|██▉       | 28792/100000 [8:18:19<11:34:38,  1.71it/s]
Train steps ... :  29%|██▉       | 28793/100000 [8:18:20<11:34:35,  1.71it/s]
Train steps ... :  29%|██▉       | 28794/100000 [8:18:20<11:33:40,  1.71it/s]
Train steps ... :  29%|██▉       | 28795/100000 [8:18:21<11:33:14,  1.71it/s]
Train steps ... :  29%|██▉       | 28796/100000 [8:18:21<11:33:08,  1.71it/s]
Train steps ... :  29%|██▉       | 28797/100000 [8:18:22<11:32:57,  1.71it/s]
Train steps ... :  29%|██▉       | 28798/100000 [8:18:23<11:33:51,  1.71it/s]
Train steps ... :  29%|██▉       | 28799/100000 [8:18:23<11:34:13,  1.71it/s]
Train steps ... :  29%|██▉       | 28800/100000 [8:18:24<11:33:56,  1.71it/s]Step... (28800 / 100000 | Loss: 1.0931367874145508, Learning Rate: 7.155778894472363e-05)
+
                                                                             
Step... (28800 / 100000 | Loss: 0.7466185092926025, Learning Rate: 7.155778894472363e-05)
+
Train steps ... :  29%|██▉       | 28800/100000 [8:18:24<11:33:56,  1.71it/s]
Train steps ... :  29%|██▉       | 28801/100000 [8:18:24<11:33:55,  1.71it/s]
Train steps ... :  29%|██▉       | 28802/100000 [8:18:25<11:33:28,  1.71it/s]
Train steps ... :  29%|██▉       | 28803/100000 [8:18:25<11:33:53,  1.71it/s]
Train steps ... :  29%|██▉       | 28804/100000 [8:18:26<11:33:46,  1.71it/s]
Train steps ... :  29%|██▉       | 28805/100000 [8:18:27<11:33:25,  1.71it/s]
Train steps ... :  29%|██▉       | 28806/100000 [8:18:27<11:33:34,  1.71it/s]
Train steps ... :  29%|██▉       | 28807/100000 [8:18:28<11:33:40,  1.71it/s]
Train steps ... :  29%|██▉       | 28808/100000 [8:18:28<11:33:48,  1.71it/s]
Train steps ... :  29%|██▉       | 28809/100000 [8:18:29<11:33:20,  1.71it/s]
Train steps ... :  29%|██▉       | 28810/100000 [8:18:30<11:33:02,  1.71it/s]
Train steps ... :  29%|██▉       | 28811/100000 [8:18:30<11:32:40,  1.71it/s]
Train steps ... :  29%|██▉       | 28812/100000 [8:18:31<11:32:58,  1.71it/s]
Train steps ... :  29%|██▉       | 28813/100000 [8:18:31<11:32:55,  1.71it/s]
Train steps ... :  29%|██▉       | 28814/100000 [8:18:32<11:34:54,  1.71it/s]
Train steps ... :  29%|██▉       | 28815/100000 [8:18:32<11:33:43,  1.71it/s]
Train steps ... :  29%|██▉       | 28816/100000 [8:18:33<11:34:03,  1.71it/s]
Train steps ... :  29%|██▉       | 28817/100000 [8:18:34<11:34:22,  1.71it/s]
Train steps ... :  29%|██▉       | 28818/100000 [8:18:34<11:34:45,  1.71it/s]
Train steps ... :  29%|██▉       | 28819/100000 [8:18:35<11:34:31,  1.71it/s]
Train steps ... :  29%|██▉       | 28820/100000 [8:18:35<11:33:33,  1.71it/s]
Train steps ... :  29%|██▉       | 28821/100000 [8:18:36<11:33:50,  1.71it/s]
Train steps ... :  29%|██▉       | 28822/100000 [8:18:37<11:33:14,  1.71it/s]
Train steps ... :  29%|██▉       | 28823/100000 [8:18:37<11:33:10,  1.71it/s]
Train steps ... :  29%|██▉       | 28824/100000 [8:18:38<11:34:06,  1.71it/s]
Train steps ... :  29%|██▉       | 28825/100000 [8:18:38<11:34:07,  1.71it/s]Step... (28825 / 100000 | Loss: 0.772201657295227, Learning Rate: 7.153266331658291e-05)
+
                                                                             
Step... (28825 / 100000 | Loss: 0.9694113731384277, Learning Rate: 7.153266331658291e-05)
+
Train steps ... :  29%|██▉       | 28825/100000 [8:18:39<11:34:07,  1.71it/s]
Train steps ... :  29%|██▉       | 28826/100000 [8:18:39<11:34:41,  1.71it/s]
Train steps ... :  29%|██▉       | 28827/100000 [8:18:39<11:32:56,  1.71it/s]
Train steps ... :  29%|██▉       | 28828/100000 [8:18:40<11:32:22,  1.71it/s]
Train steps ... :  29%|██▉       | 28829/100000 [8:18:41<11:33:25,  1.71it/s]
Train steps ... :  29%|██▉       | 28830/100000 [8:18:41<11:32:42,  1.71it/s]
Train steps ... :  29%|██▉       | 28831/100000 [8:18:42<11:32:41,  1.71it/s]
Train steps ... :  29%|██▉       | 28832/100000 [8:18:42<11:32:48,  1.71it/s]
Train steps ... :  29%|██▉       | 28833/100000 [8:18:43<11:33:31,  1.71it/s]
Train steps ... :  29%|██▉       | 28834/100000 [8:18:44<11:33:23,  1.71it/s]
Train steps ... :  29%|██▉       | 28835/100000 [8:18:44<11:33:13,  1.71it/s]
Train steps ... :  29%|██▉       | 28836/100000 [8:18:45<11:34:05,  1.71it/s]
Train steps ... :  29%|██▉       | 28837/100000 [8:18:45<11:33:23,  1.71it/s]
Train steps ... :  29%|██▉       | 28838/100000 [8:18:46<11:33:14,  1.71it/s]
Train steps ... :  29%|██▉       | 28839/100000 [8:18:46<11:33:09,  1.71it/s]
Train steps ... :  29%|██▉       | 28840/100000 [8:18:47<11:33:03,  1.71it/s]
Train steps ... :  29%|██▉       | 28841/100000 [8:18:48<11:33:25,  1.71it/s]
Train steps ... :  29%|██▉       | 28842/100000 [8:18:48<11:33:45,  1.71it/s]
Train steps ... :  29%|██▉       | 28843/100000 [8:18:49<11:34:30,  1.71it/s]
Train steps ... :  29%|██▉       | 28844/100000 [8:18:49<11:34:11,  1.71it/s]
Train steps ... :  29%|██▉       | 28845/100000 [8:18:50<11:33:48,  1.71it/s]
Train steps ... :  29%|██▉       | 28846/100000 [8:18:51<11:34:09,  1.71it/s]
Train steps ... :  29%|██▉       | 28847/100000 [8:18:51<11:34:04,  1.71it/s]
Train steps ... :  29%|██▉       | 28848/100000 [8:18:52<11:33:16,  1.71it/s]
Train steps ... :  29%|██▉       | 28849/100000 [8:18:52<11:34:18,  1.71it/s]
Train steps ... :  29%|██▉       | 28850/100000 [8:18:53<11:33:47,  1.71it/s]Step... (28850 / 100000 | Loss: 0.8168007135391235, Learning Rate: 7.150753768844221e-05)
+
                                                                             
Step... (28850 / 100000 | Loss: 0.8739308714866638, Learning Rate: 7.150753768844221e-05)
+
Train steps ... :  29%|██▉       | 28850/100000 [8:18:53<11:33:47,  1.71it/s]
Train steps ... :  29%|██▉       | 28851/100000 [8:18:54<11:33:10,  1.71it/s]
Train steps ... :  29%|██▉       | 28852/100000 [8:18:54<11:32:50,  1.71it/s]
Train steps ... :  29%|██▉       | 28853/100000 [8:18:55<11:32:44,  1.71it/s]
Train steps ... :  29%|██▉       | 28854/100000 [8:18:55<11:32:37,  1.71it/s]
Train steps ... :  29%|██▉       | 28855/100000 [8:18:56<11:32:34,  1.71it/s]
Train steps ... :  29%|██▉       | 28856/100000 [8:18:56<11:33:41,  1.71it/s]
Train steps ... :  29%|██▉       | 28857/100000 [8:18:57<11:33:50,  1.71it/s]
Train steps ... :  29%|██▉       | 28858/100000 [8:18:58<11:33:05,  1.71it/s]
Train steps ... :  29%|██▉       | 28859/100000 [8:18:58<11:33:35,  1.71it/s]
Train steps ... :  29%|██▉       | 28860/100000 [8:18:59<11:33:30,  1.71it/s]
Train steps ... :  29%|██▉       | 28861/100000 [8:18:59<11:34:05,  1.71it/s]
Train steps ... :  29%|██▉       | 28862/100000 [8:19:00<11:33:15,  1.71it/s]
Train steps ... :  29%|██▉       | 28863/100000 [8:19:01<11:32:26,  1.71it/s]
Train steps ... :  29%|██▉       | 28864/100000 [8:19:01<11:32:28,  1.71it/s]
Train steps ... :  29%|██▉       | 28865/100000 [8:19:02<11:33:30,  1.71it/s]
Train steps ... :  29%|██▉       | 28866/100000 [8:19:02<11:33:59,  1.71it/s]
Train steps ... :  29%|██▉       | 28867/100000 [8:19:03<11:33:43,  1.71it/s]
Train steps ... :  29%|██▉       | 28868/100000 [8:19:03<11:33:48,  1.71it/s]
Train steps ... :  29%|██▉       | 28869/100000 [8:19:04<11:33:23,  1.71it/s]
Train steps ... :  29%|██▉       | 28870/100000 [8:19:05<11:33:41,  1.71it/s]
Train steps ... :  29%|██▉       | 28871/100000 [8:19:05<11:32:53,  1.71it/s]
Train steps ... :  29%|██▉       | 28872/100000 [8:19:06<11:32:34,  1.71it/s]
Train steps ... :  29%|██▉       | 28873/100000 [8:19:06<11:32:48,  1.71it/s]
Train steps ... :  29%|██▉       | 28874/100000 [8:19:07<11:32:48,  1.71it/s]
Train steps ... :  29%|██▉       | 28875/100000 [8:19:08<11:34:44,  1.71it/s]Step... (28875 / 100000 | Loss: 0.9291427135467529, Learning Rate: 7.148241206030151e-05)
+
                                                                             
Step... (28875 / 100000 | Loss: 0.9356244802474976, Learning Rate: 7.148241206030151e-05)
+
Train steps ... :  29%|██▉       | 28875/100000 [8:19:08<11:34:44,  1.71it/s]
Train steps ... :  29%|██▉       | 28876/100000 [8:19:08<11:34:33,  1.71it/s]
Train steps ... :  29%|██▉       | 28877/100000 [8:19:09<11:35:03,  1.71it/s]
Train steps ... :  29%|██▉       | 28878/100000 [8:19:09<11:33:32,  1.71it/s]
Train steps ... :  29%|██▉       | 28879/100000 [8:19:10<11:32:29,  1.71it/s]
Train steps ... :  29%|██▉       | 28880/100000 [8:19:10<11:32:47,  1.71it/s]
Train steps ... :  29%|██▉       | 28881/100000 [8:19:11<11:32:25,  1.71it/s]
Train steps ... :  29%|██▉       | 28882/100000 [8:19:12<11:31:53,  1.71it/s]
Train steps ... :  29%|██▉       | 28883/100000 [8:19:12<11:32:49,  1.71it/s]
Train steps ... :  29%|██▉       | 28884/100000 [8:19:13<11:33:04,  1.71it/s]
Train steps ... :  29%|██▉       | 28885/100000 [8:19:13<11:32:41,  1.71it/s]
Train steps ... :  29%|██▉       | 28886/100000 [8:19:14<11:32:42,  1.71it/s]
Train steps ... :  29%|██▉       | 28887/100000 [8:19:15<11:32:12,  1.71it/s]
Train steps ... :  29%|██▉       | 28888/100000 [8:19:15<11:32:22,  1.71it/s]
Train steps ... :  29%|██▉       | 28889/100000 [8:19:16<11:32:47,  1.71it/s]
Train steps ... :  29%|██▉       | 28890/100000 [8:19:16<11:32:42,  1.71it/s]
Train steps ... :  29%|██▉       | 28891/100000 [8:19:17<11:32:45,  1.71it/s]
Train steps ... :  29%|██▉       | 28892/100000 [8:19:17<11:33:49,  1.71it/s]
Train steps ... :  29%|██▉       | 28893/100000 [8:19:18<11:33:14,  1.71it/s]
Train steps ... :  29%|██▉       | 28894/100000 [8:19:19<11:33:32,  1.71it/s]
Train steps ... :  29%|██▉       | 28895/100000 [8:19:19<11:32:49,  1.71it/s]
Train steps ... :  29%|██▉       | 28896/100000 [8:19:20<11:32:55,  1.71it/s]
Train steps ... :  29%|██▉       | 28897/100000 [8:19:20<11:33:18,  1.71it/s]
Train steps ... :  29%|██▉       | 28898/100000 [8:19:21<11:32:36,  1.71it/s]
Train steps ... :  29%|██▉       | 28899/100000 [8:19:22<11:32:54,  1.71it/s]
Train steps ... :  29%|██▉       | 28900/100000 [8:19:22<11:34:18,  1.71it/s]Step... (28900 / 100000 | Loss: 0.8433921337127686, Learning Rate: 7.14572864321608e-05)
+
                                                                             
Step... (28900 / 100000 | Loss: 0.7817264795303345, Learning Rate: 7.14572864321608e-05)
+
Train steps ... :  29%|██▉       | 28900/100000 [8:19:22<11:34:18,  1.71it/s]
Train steps ... :  29%|██▉       | 28901/100000 [8:19:23<11:33:27,  1.71it/s]
Train steps ... :  29%|██▉       | 28902/100000 [8:19:23<11:32:52,  1.71it/s]
Train steps ... :  29%|██▉       | 28903/100000 [8:19:24<11:32:24,  1.71it/s]
Train steps ... :  29%|██▉       | 28904/100000 [8:19:24<11:32:45,  1.71it/s]
Train steps ... :  29%|██▉       | 28905/100000 [8:19:25<11:33:13,  1.71it/s]
Train steps ... :  29%|██▉       | 28906/100000 [8:19:26<11:32:32,  1.71it/s]
Train steps ... :  29%|██▉       | 28907/100000 [8:19:26<11:32:04,  1.71it/s]
Train steps ... :  29%|██▉       | 28908/100000 [8:19:27<11:32:31,  1.71it/s]
Train steps ... :  29%|██▉       | 28909/100000 [8:19:27<11:32:42,  1.71it/s]
Train steps ... :  29%|██▉       | 28910/100000 [8:19:28<11:33:45,  1.71it/s]
Train steps ... :  29%|██▉       | 28911/100000 [8:19:29<11:33:20,  1.71it/s]
Train steps ... :  29%|██▉       | 28912/100000 [8:19:29<11:33:08,  1.71it/s]
Train steps ... :  29%|██▉       | 28913/100000 [8:19:30<11:32:06,  1.71it/s]
Train steps ... :  29%|██▉       | 28914/100000 [8:19:30<11:32:40,  1.71it/s]
Train steps ... :  29%|██▉       | 28915/100000 [8:19:31<11:33:57,  1.71it/s]
Train steps ... :  29%|██▉       | 28916/100000 [8:19:32<11:33:19,  1.71it/s]
Train steps ... :  29%|██▉       | 28917/100000 [8:19:32<11:33:02,  1.71it/s]
Train steps ... :  29%|██▉       | 28918/100000 [8:19:33<11:33:29,  1.71it/s]
Train steps ... :  29%|██▉       | 28919/100000 [8:19:33<11:33:55,  1.71it/s]
Train steps ... :  29%|██▉       | 28920/100000 [8:19:34<11:33:19,  1.71it/s]
Train steps ... :  29%|██▉       | 28921/100000 [8:19:34<11:33:26,  1.71it/s]
Train steps ... :  29%|██▉       | 28922/100000 [8:19:35<11:32:55,  1.71it/s]
Train steps ... :  29%|██▉       | 28923/100000 [8:19:36<11:32:34,  1.71it/s]
Train steps ... :  29%|██▉       | 28924/100000 [8:19:36<11:31:36,  1.71it/s]
Train steps ... :  29%|██▉       | 28925/100000 [8:19:37<11:31:33,  1.71it/s]Step... (28925 / 100000 | Loss: 1.2882652282714844, Learning Rate: 7.14321608040201e-05)
+
                                                                             
Step... (28925 / 100000 | Loss: 0.7833235859870911, Learning Rate: 7.14321608040201e-05)
+
Train steps ... :  29%|██▉       | 28925/100000 [8:19:37<11:31:33,  1.71it/s]
Train steps ... :  29%|██▉       | 28926/100000 [8:19:37<11:31:46,  1.71it/s]
Train steps ... :  29%|██▉       | 28927/100000 [8:19:38<11:32:14,  1.71it/s]
Train steps ... :  29%|██▉       | 28928/100000 [8:19:39<11:32:37,  1.71it/s]
Train steps ... :  29%|██▉       | 28929/100000 [8:19:39<11:32:41,  1.71it/s]
Train steps ... :  29%|██▉       | 28930/100000 [8:19:40<11:32:02,  1.71it/s]
Train steps ... :  29%|██▉       | 28931/100000 [8:19:40<11:32:21,  1.71it/s]
Train steps ... :  29%|██▉       | 28932/100000 [8:19:41<11:31:28,  1.71it/s]
Train steps ... :  29%|██▉       | 28933/100000 [8:19:41<11:31:57,  1.71it/s]
Train steps ... :  29%|██▉       | 28934/100000 [8:19:42<11:32:50,  1.71it/s]
Train steps ... :  29%|██▉       | 28935/100000 [8:19:43<11:33:47,  1.71it/s]
Train steps ... :  29%|██▉       | 28936/100000 [8:19:43<11:33:55,  1.71it/s]
Train steps ... :  29%|██▉       | 28937/100000 [8:19:44<11:32:42,  1.71it/s]
Train steps ... :  29%|██▉       | 28938/100000 [8:19:44<11:32:51,  1.71it/s]
Train steps ... :  29%|██▉       | 28939/100000 [8:19:45<11:34:00,  1.71it/s]
Train steps ... :  29%|██▉       | 28940/100000 [8:19:46<11:33:28,  1.71it/s]
Train steps ... :  29%|██▉       | 28941/100000 [8:19:46<11:33:12,  1.71it/s]
Train steps ... :  29%|██▉       | 28942/100000 [8:19:47<11:33:07,  1.71it/s]
Train steps ... :  29%|██▉       | 28943/100000 [8:19:47<11:34:14,  1.71it/s]
Train steps ... :  29%|██▉       | 28944/100000 [8:19:48<11:33:56,  1.71it/s]
Train steps ... :  29%|██▉       | 28945/100000 [8:19:48<11:37:54,  1.70it/s]
Train steps ... :  29%|██▉       | 28946/100000 [8:19:49<11:36:12,  1.70it/s]
Train steps ... :  29%|██▉       | 28947/100000 [8:19:50<11:33:27,  1.71it/s]
Train steps ... :  29%|██▉       | 28948/100000 [8:19:50<11:32:28,  1.71it/s]
Train steps ... :  29%|██▉       | 28949/100000 [8:19:51<11:32:24,  1.71it/s]
Train steps ... :  29%|██▉       | 28950/100000 [8:19:51<11:32:33,  1.71it/s]Step... (28950 / 100000 | Loss: 0.6928129196166992, Learning Rate: 7.14070351758794e-05)
+
                                                                             
Step... (28950 / 100000 | Loss: 0.9185549020767212, Learning Rate: 7.14070351758794e-05)
+
Train steps ... :  29%|██▉       | 28950/100000 [8:19:52<11:32:33,  1.71it/s]
Train steps ... :  29%|██▉       | 28951/100000 [8:19:52<11:32:46,  1.71it/s]
Train steps ... :  29%|██▉       | 28952/100000 [8:19:53<11:33:23,  1.71it/s]
Train steps ... :  29%|██▉       | 28953/100000 [8:19:53<11:32:57,  1.71it/s]
Train steps ... :  29%|██▉       | 28954/100000 [8:19:54<11:32:45,  1.71it/s]
Train steps ... :  29%|██▉       | 28955/100000 [8:19:54<11:32:17,  1.71it/s]
Train steps ... :  29%|██▉       | 28956/100000 [8:19:55<11:33:01,  1.71it/s]
Train steps ... :  29%|██▉       | 28957/100000 [8:19:56<11:32:58,  1.71it/s]
Train steps ... :  29%|██▉       | 28958/100000 [8:19:56<11:33:22,  1.71it/s]
Train steps ... :  29%|██▉       | 28959/100000 [8:19:57<11:32:30,  1.71it/s]
Train steps ... :  29%|██▉       | 28960/100000 [8:19:57<11:32:21,  1.71it/s]
Train steps ... :  29%|██▉       | 28961/100000 [8:19:58<11:32:24,  1.71it/s]
Train steps ... :  29%|██▉       | 28962/100000 [8:19:58<11:31:30,  1.71it/s]
Train steps ... :  29%|██▉       | 28963/100000 [8:19:59<11:31:32,  1.71it/s]
Train steps ... :  29%|██▉       | 28964/100000 [8:20:00<11:32:38,  1.71it/s]
Train steps ... :  29%|██▉       | 28965/100000 [8:20:00<11:30:59,  1.71it/s]
Train steps ... :  29%|██▉       | 28966/100000 [8:20:01<11:30:57,  1.71it/s]
Train steps ... :  29%|██▉       | 28967/100000 [8:20:01<11:33:16,  1.71it/s]
Train steps ... :  29%|██▉       | 28968/100000 [8:20:02<11:32:44,  1.71it/s]
Train steps ... :  29%|██▉       | 28969/100000 [8:20:03<11:32:05,  1.71it/s]
Train steps ... :  29%|██▉       | 28970/100000 [8:20:03<11:31:48,  1.71it/s]
Train steps ... :  29%|██▉       | 28971/100000 [8:20:04<11:31:25,  1.71it/s]
Train steps ... :  29%|██▉       | 28972/100000 [8:20:04<11:32:11,  1.71it/s]
Train steps ... :  29%|██▉       | 28973/100000 [8:20:05<11:31:39,  1.71it/s]
Train steps ... :  29%|██▉       | 28974/100000 [8:20:05<11:32:06,  1.71it/s]
Train steps ... :  29%|██▉       | 28975/100000 [8:20:06<11:33:29,  1.71it/s]Step... (28975 / 100000 | Loss: 0.8099135756492615, Learning Rate: 7.138190954773871e-05)
+
                                                                             
Step... (28975 / 100000 | Loss: 0.6107010841369629, Learning Rate: 7.138190954773871e-05)
+
Train steps ... :  29%|██▉       | 28975/100000 [8:20:06<11:33:29,  1.71it/s]
Train steps ... :  29%|██▉       | 28976/100000 [8:20:07<11:33:08,  1.71it/s]
Train steps ... :  29%|██▉       | 28977/100000 [8:20:07<11:33:59,  1.71it/s]
Train steps ... :  29%|██▉       | 28978/100000 [8:20:08<11:32:56,  1.71it/s]
Train steps ... :  29%|██▉       | 28979/100000 [8:20:08<11:32:22,  1.71it/s]
Train steps ... :  29%|██▉       | 28980/100000 [8:20:09<11:32:31,  1.71it/s]
Train steps ... :  29%|██▉       | 28981/100000 [8:20:10<11:31:23,  1.71it/s]
Train steps ... :  29%|██▉       | 28982/100000 [8:20:10<11:32:10,  1.71it/s]
Train steps ... :  29%|██▉       | 28983/100000 [8:20:11<11:32:02,  1.71it/s]
Train steps ... :  29%|██▉       | 28984/100000 [8:20:11<11:32:10,  1.71it/s]
Train steps ... :  29%|██▉       | 28985/100000 [8:20:12<11:32:06,  1.71it/s]
Train steps ... :  29%|██▉       | 28986/100000 [8:20:12<11:33:07,  1.71it/s]
Train steps ... :  29%|██▉       | 28987/100000 [8:20:13<11:32:00,  1.71it/s]
Train steps ... :  29%|██▉       | 28988/100000 [8:20:14<11:31:54,  1.71it/s]
Train steps ... :  29%|██▉       | 28989/100000 [8:20:14<11:31:06,  1.71it/s]
Train steps ... :  29%|██▉       | 28990/100000 [8:20:15<11:31:59,  1.71it/s]
Train steps ... :  29%|██▉       | 28991/100000 [8:20:15<11:32:10,  1.71it/s]
Train steps ... :  29%|██▉       | 28992/100000 [8:20:16<11:31:56,  1.71it/s]
Train steps ... :  29%|██▉       | 28993/100000 [8:20:17<11:31:51,  1.71it/s]
Train steps ... :  29%|██▉       | 28994/100000 [8:20:17<11:31:10,  1.71it/s]
Train steps ... :  29%|██▉       | 28995/100000 [8:20:18<11:31:34,  1.71it/s]
Train steps ... :  29%|██▉       | 28996/100000 [8:20:18<11:30:50,  1.71it/s]
Train steps ... :  29%|██▉       | 28997/100000 [8:20:19<11:31:49,  1.71it/s]
Train steps ... :  29%|██▉       | 28998/100000 [8:20:19<11:32:12,  1.71it/s]
Train steps ... :  29%|██▉       | 28999/100000 [8:20:20<11:32:05,  1.71it/s]
Train steps ... :  29%|██▉       | 29000/100000 [8:20:21<11:31:31,  1.71it/s]Step... (29000 / 100000 | Loss: 0.778009295463562, Learning Rate: 7.135678391959799e-05)
+
                                                                             
Step... (29000 / 100000 | Loss: 0.6436086893081665, Learning Rate: 7.135678391959799e-05)
+
Train steps ... :  29%|██▉       | 29000/100000 [8:20:21<11:31:31,  1.71it/s]
Train steps ... :  29%|██▉       | 29001/100000 [8:20:21<11:31:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29002/100000 [8:20:22<11:31:13,  1.71it/s]
Train steps ... :  29%|██▉       | 29003/100000 [8:20:22<11:30:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29004/100000 [8:20:23<11:31:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29005/100000 [8:20:24<11:31:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29006/100000 [8:20:24<11:30:48,  1.71it/s]
Train steps ... :  29%|██▉       | 29007/100000 [8:20:25<11:31:02,  1.71it/s]
Train steps ... :  29%|██▉       | 29008/100000 [8:20:25<11:30:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29009/100000 [8:20:26<11:30:14,  1.71it/s]
Train steps ... :  29%|██▉       | 29010/100000 [8:20:26<11:30:09,  1.71it/s]
Train steps ... :  29%|██▉       | 29011/100000 [8:20:27<11:31:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29012/100000 [8:20:28<11:33:40,  1.71it/s]
Train steps ... :  29%|██▉       | 29013/100000 [8:20:28<11:32:38,  1.71it/s]
Train steps ... :  29%|██▉       | 29014/100000 [8:20:29<11:32:16,  1.71it/s]
Train steps ... :  29%|██▉       | 29015/100000 [8:20:29<11:32:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29016/100000 [8:20:30<11:32:05,  1.71it/s]
Train steps ... :  29%|██▉       | 29017/100000 [8:20:31<11:32:27,  1.71it/s]
Train steps ... :  29%|██▉       | 29018/100000 [8:20:31<11:31:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29019/100000 [8:20:32<11:31:21,  1.71it/s]
Train steps ... :  29%|██▉       | 29020/100000 [8:20:32<11:31:06,  1.71it/s]
Train steps ... :  29%|██▉       | 29021/100000 [8:20:33<11:31:08,  1.71it/s]
Train steps ... :  29%|██▉       | 29022/100000 [8:20:34<11:31:38,  1.71it/s]
Train steps ... :  29%|██▉       | 29023/100000 [8:20:34<11:31:32,  1.71it/s]
Train steps ... :  29%|██▉       | 29024/100000 [8:20:35<11:31:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29025/100000 [8:20:35<11:31:24,  1.71it/s]Step... (29025 / 100000 | Loss: 0.9187657833099365, Learning Rate: 7.133165829145729e-05)
+
                                                                             
Step... (29025 / 100000 | Loss: 1.2091996669769287, Learning Rate: 7.133165829145729e-05)
+
Train steps ... :  29%|██▉       | 29025/100000 [8:20:36<11:31:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29026/100000 [8:20:36<11:31:39,  1.71it/s]
Train steps ... :  29%|██▉       | 29027/100000 [8:20:36<11:31:46,  1.71it/s]
Train steps ... :  29%|██▉       | 29028/100000 [8:20:37<11:31:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29029/100000 [8:20:38<11:31:27,  1.71it/s]
Train steps ... :  29%|██▉       | 29030/100000 [8:20:38<11:32:18,  1.71it/s]
Train steps ... :  29%|██▉       | 29031/100000 [8:20:39<11:31:51,  1.71it/s]
Train steps ... :  29%|██▉       | 29032/100000 [8:20:39<11:31:49,  1.71it/s]
Train steps ... :  29%|██▉       | 29033/100000 [8:20:40<11:31:48,  1.71it/s]
Train steps ... :  29%|██▉       | 29034/100000 [8:20:41<11:33:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29035/100000 [8:20:41<11:32:42,  1.71it/s]
Train steps ... :  29%|██▉       | 29036/100000 [8:20:42<11:33:03,  1.71it/s]
Train steps ... :  29%|██▉       | 29037/100000 [8:20:42<11:32:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29038/100000 [8:20:43<11:31:55,  1.71it/s]
Train steps ... :  29%|██▉       | 29039/100000 [8:20:43<11:32:14,  1.71it/s]
Train steps ... :  29%|██▉       | 29040/100000 [8:20:44<11:31:11,  1.71it/s]
Train steps ... :  29%|██▉       | 29041/100000 [8:20:45<11:31:03,  1.71it/s]
Train steps ... :  29%|██▉       | 29042/100000 [8:20:45<11:31:15,  1.71it/s]
Train steps ... :  29%|██▉       | 29043/100000 [8:20:46<11:31:53,  1.71it/s]
Train steps ... :  29%|██▉       | 29044/100000 [8:20:46<11:32:22,  1.71it/s]
Train steps ... :  29%|██▉       | 29045/100000 [8:20:47<11:32:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29046/100000 [8:20:48<11:33:31,  1.71it/s]
Train steps ... :  29%|██▉       | 29047/100000 [8:20:48<11:31:05,  1.71it/s]
Train steps ... :  29%|██▉       | 29048/100000 [8:20:49<11:30:52,  1.71it/s]
Train steps ... :  29%|██▉       | 29049/100000 [8:20:49<11:31:57,  1.71it/s]
Train steps ... :  29%|██▉       | 29050/100000 [8:20:50<11:31:51,  1.71it/s]Step... (29050 / 100000 | Loss: 0.9122419953346252, Learning Rate: 7.130653266331658e-05)
+
                                                                             
Step... (29050 / 100000 | Loss: 0.8534983396530151, Learning Rate: 7.130653266331658e-05)
+
Train steps ... :  29%|██▉       | 29050/100000 [8:20:50<11:31:51,  1.71it/s]
Train steps ... :  29%|██▉       | 29051/100000 [8:20:50<11:32:03,  1.71it/s]
Train steps ... :  29%|██▉       | 29052/100000 [8:20:51<11:31:35,  1.71it/s]
Train steps ... :  29%|██▉       | 29053/100000 [8:20:52<11:32:32,  1.71it/s]
Train steps ... :  29%|██▉       | 29054/100000 [8:20:52<11:31:58,  1.71it/s]
Train steps ... :  29%|██▉       | 29055/100000 [8:20:53<11:32:15,  1.71it/s]
Train steps ... :  29%|██▉       | 29056/100000 [8:20:53<11:31:15,  1.71it/s]
Train steps ... :  29%|██▉       | 29057/100000 [8:20:54<11:31:48,  1.71it/s]
Train steps ... :  29%|██▉       | 29058/100000 [8:20:55<11:30:46,  1.71it/s]
Train steps ... :  29%|██▉       | 29059/100000 [8:20:55<11:31:05,  1.71it/s]
Train steps ... :  29%|██▉       | 29060/100000 [8:20:56<11:30:51,  1.71it/s]
Train steps ... :  29%|██▉       | 29061/100000 [8:20:56<11:31:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29062/100000 [8:20:57<11:31:32,  1.71it/s]
Train steps ... :  29%|██▉       | 29063/100000 [8:20:57<11:31:13,  1.71it/s]
Train steps ... :  29%|██▉       | 29064/100000 [8:20:58<11:31:51,  1.71it/s]
Train steps ... :  29%|██▉       | 29065/100000 [8:20:59<11:31:10,  1.71it/s]
Train steps ... :  29%|���█▉       | 29066/100000 [8:20:59<11:33:21,  1.71it/s]
Train steps ... :  29%|██▉       | 29067/100000 [8:21:00<11:32:08,  1.71it/s]
Train steps ... :  29%|██▉       | 29068/100000 [8:21:00<11:31:31,  1.71it/s]
Train steps ... :  29%|██▉       | 29069/100000 [8:21:01<11:30:58,  1.71it/s]
Train steps ... :  29%|██▉       | 29070/100000 [8:21:02<11:31:25,  1.71it/s]
Train steps ... :  29%|██▉       | 29071/100000 [8:21:02<11:31:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29072/100000 [8:21:03<11:31:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29073/100000 [8:21:03<11:31:01,  1.71it/s]
Train steps ... :  29%|██▉       | 29074/100000 [8:21:04<11:30:57,  1.71it/s]
Train steps ... :  29%|██▉       | 29075/100000 [8:21:05<11:31:31,  1.71it/s]Step... (29075 / 100000 | Loss: 0.9006747007369995, Learning Rate: 7.128140703517588e-05)
+
                                                                             
Step... (29075 / 100000 | Loss: 0.9647225141525269, Learning Rate: 7.128140703517588e-05)
+
Train steps ... :  29%|██▉       | 29075/100000 [8:21:05<11:31:31,  1.71it/s]
Train steps ... :  29%|██▉       | 29076/100000 [8:21:05<11:31:21,  1.71it/s]
Train steps ... :  29%|██▉       | 29077/100000 [8:21:06<11:31:53,  1.71it/s]
Train steps ... :  29%|██▉       | 29078/100000 [8:21:06<11:31:34,  1.71it/s]
Train steps ... :  29%|██▉       | 29079/100000 [8:21:07<11:30:54,  1.71it/s]
Train steps ... :  29%|██▉       | 29080/100000 [8:21:07<11:31:17,  1.71it/s]
Train steps ... :  29%|██▉       | 29081/100000 [8:21:08<11:32:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29082/100000 [8:21:09<11:30:55,  1.71it/s]
Train steps ... :  29%|██▉       | 29083/100000 [8:21:09<11:31:25,  1.71it/s]
Train steps ... :  29%|██▉       | 29084/100000 [8:21:10<11:31:04,  1.71it/s]
Train steps ... :  29%|██▉       | 29085/100000 [8:21:10<11:30:41,  1.71it/s]
Train steps ... :  29%|██▉       | 29086/100000 [8:21:11<11:30:44,  1.71it/s]
Train steps ... :  29%|██▉       | 29087/100000 [8:21:12<11:31:10,  1.71it/s]
Train steps ... :  29%|██▉       | 29088/100000 [8:21:12<11:31:36,  1.71it/s]
Train steps ... :  29%|██▉       | 29089/100000 [8:21:13<11:31:36,  1.71it/s]
Train steps ... :  29%|██▉       | 29090/100000 [8:21:13<11:30:45,  1.71it/s]
Train steps ... :  29%|██▉       | 29091/100000 [8:21:14<11:30:25,  1.71it/s]
Train steps ... :  29%|██▉       | 29092/100000 [8:21:14<11:30:13,  1.71it/s]
Train steps ... :  29%|██▉       | 29093/100000 [8:21:15<11:30:54,  1.71it/s]
Train steps ... :  29%|██▉       | 29094/100000 [8:21:16<11:30:27,  1.71it/s]
Train steps ... :  29%|██▉       | 29095/100000 [8:21:16<11:30:20,  1.71it/s]
Train steps ... :  29%|██▉       | 29096/100000 [8:21:17<11:30:15,  1.71it/s]
Train steps ... :  29%|██▉       | 29097/100000 [8:21:17<11:29:47,  1.71it/s]
Train steps ... :  29%|██▉       | 29098/100000 [8:21:18<11:30:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29099/100000 [8:21:19<11:30:31,  1.71it/s]
Train steps ... :  29%|██▉       | 29100/100000 [8:21:19<11:32:29,  1.71it/s]Step... (29100 / 100000 | Loss: 0.9843193292617798, Learning Rate: 7.125628140703518e-05)
+
                                                                             
Step... (29100 / 100000 | Loss: 0.9071996212005615, Learning Rate: 7.125628140703518e-05)
+
Train steps ... :  29%|██▉       | 29100/100000 [8:21:19<11:32:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29101/100000 [8:21:20<11:32:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29102/100000 [8:21:20<11:30:57,  1.71it/s]
Train steps ... :  29%|██▉       | 29103/100000 [8:21:21<11:31:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29104/100000 [8:21:21<11:31:22,  1.71it/s]
Train steps ... :  29%|██▉       | 29105/100000 [8:21:22<11:30:38,  1.71it/s]
Train steps ... :  29%|██▉       | 29106/100000 [8:21:23<11:30:49,  1.71it/s]
Train steps ... :  29%|██▉       | 29107/100000 [8:21:23<11:30:38,  1.71it/s]
Train steps ... :  29%|██▉       | 29108/100000 [8:21:24<11:30:41,  1.71it/s]
Train steps ... :  29%|██▉       | 29109/100000 [8:21:24<11:31:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29110/100000 [8:21:25<11:31:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29111/100000 [8:21:26<11:30:45,  1.71it/s]
Train steps ... :  29%|██▉       | 29112/100000 [8:21:26<11:30:48,  1.71it/s]
Train steps ... :  29%|██▉       | 29113/100000 [8:21:27<11:31:02,  1.71it/s]
Train steps ... :  29%|██▉       | 29114/100000 [8:21:27<11:31:21,  1.71it/s]
Train steps ... :  29%|██▉       | 29115/100000 [8:21:28<11:31:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29116/100000 [8:21:28<11:32:04,  1.71it/s]
Train steps ... :  29%|██▉       | 29117/100000 [8:21:29<11:30:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29118/100000 [8:21:30<11:31:01,  1.71it/s]
Train steps ... :  29%|██▉       | 29119/100000 [8:21:30<11:31:43,  1.71it/s]
Train steps ... :  29%|██▉       | 29120/100000 [8:21:31<11:31:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29121/100000 [8:21:31<11:30:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29122/100000 [8:21:32<11:30:09,  1.71it/s]
Train steps ... :  29%|██▉       | 29123/100000 [8:21:33<11:30:01,  1.71it/s]
Train steps ... :  29%|██▉       | 29124/100000 [8:21:33<11:30:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29125/100000 [8:21:34<11:30:34,  1.71it/s]Step... (29125 / 100000 | Loss: 0.8804758787155151, Learning Rate: 7.123115577889447e-05)
+
                                                                             
Step... (29125 / 100000 | Loss: 0.7891814708709717, Learning Rate: 7.123115577889447e-05)
+
Train steps ... :  29%|██▉       | 29125/100000 [8:21:34<11:30:34,  1.71it/s]
Train steps ... :  29%|██▉       | 29126/100000 [8:21:34<11:30:14,  1.71it/s]
Train steps ... :  29%|██▉       | 29127/100000 [8:21:35<11:29:38,  1.71it/s]
Train steps ... :  29%|██▉       | 29128/100000 [8:21:35<11:29:35,  1.71it/s]
Train steps ... :  29%|██▉       | 29129/100000 [8:21:36<11:30:08,  1.71it/s]
Train steps ... :  29%|██▉       | 29130/100000 [8:21:37<11:30:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29131/100000 [8:21:37<11:30:15,  1.71it/s]
Train steps ... :  29%|██▉       | 29132/100000 [8:21:38<11:30:02,  1.71it/s]
Train steps ... :  29%|██▉       | 29133/100000 [8:21:38<11:30:12,  1.71it/s]
Train steps ... :  29%|██▉       | 29134/100000 [8:21:39<11:30:08,  1.71it/s]
Train steps ... :  29%|██▉       | 29135/100000 [8:21:40<11:30:35,  1.71it/s]
Train steps ... :  29%|██▉       | 29136/100000 [8:21:40<11:29:39,  1.71it/s]
Train steps ... :  29%|██▉       | 29137/100000 [8:21:41<11:30:47,  1.71it/s]
Train steps ... :  29%|██▉       | 29138/100000 [8:21:41<11:28:53,  1.71it/s]
Train steps ... :  29%|██▉       | 29139/100000 [8:21:42<11:30:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29140/100000 [8:21:43<11:30:44,  1.71it/s]
Train steps ... :  29%|██▉       | 29141/100000 [8:21:43<11:30:55,  1.71it/s]
Train steps ... :  29%|██▉       | 29142/100000 [8:21:44<11:31:25,  1.71it/s]
Train steps ... :  29%|██▉       | 29143/100000 [8:21:44<11:31:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29144/100000 [8:21:45<11:31:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29145/100000 [8:21:45<11:31:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29146/100000 [8:21:46<11:30:46,  1.71it/s]
Train steps ... :  29%|██▉       | 29147/100000 [8:21:47<11:30:16,  1.71it/s]
Train steps ... :  29%|██▉       | 29148/100000 [8:21:47<11:29:45,  1.71it/s]
Train steps ... :  29%|██▉       | 29149/100000 [8:21:48<11:30:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29150/100000 [8:21:48<11:30:56,  1.71it/s]Step... (29150 / 100000 | Loss: 0.9679555892944336, Learning Rate: 7.120603015075378e-05)
+
                                                                             
Step... (29150 / 100000 | Loss: 1.3719087839126587, Learning Rate: 7.120603015075378e-05)
+
Train steps ... :  29%|██▉       | 29150/100000 [8:21:49<11:30:56,  1.71it/s]
Train steps ... :  29%|██▉       | 29151/100000 [8:21:49<11:31:22,  1.71it/s]
Train steps ... :  29%|██▉       | 29152/100000 [8:21:50<11:31:03,  1.71it/s]
Train steps ... :  29%|██▉       | 29153/100000 [8:21:50<11:32:26,  1.71it/s]
Train steps ... :  29%|██▉       | 29154/100000 [8:21:51<11:31:25,  1.71it/s]
Train steps ... :  29%|██▉       | 29155/100000 [8:21:51<11:31:10,  1.71it/s]
Train steps ... :  29%|██▉       | 29156/100000 [8:21:52<11:30:57,  1.71it/s]
Train steps ... :  29%|██▉       | 29157/100000 [8:21:52<11:30:18,  1.71it/s]
Train steps ... :  29%|██▉       | 29158/100000 [8:21:53<11:29:59,  1.71it/s]
Train steps ... :  29%|██▉       | 29159/100000 [8:21:54<11:30:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29160/100000 [8:21:54<11:31:09,  1.71it/s]
Train steps ... :  29%|██▉       | 29161/100000 [8:21:55<11:30:18,  1.71it/s]
Train steps ... :  29%|██▉       | 29162/100000 [8:21:55<11:31:09,  1.71it/s]
Train steps ... :  29%|██▉       | 29163/100000 [8:21:56<11:30:43,  1.71it/s]
Train steps ... :  29%|██▉       | 29164/100000 [8:21:57<11:30:39,  1.71it/s]
Train steps ... :  29%|██▉       | 29165/100000 [8:21:57<11:30:30,  1.71it/s]
Train steps ... :  29%|██▉       | 29166/100000 [8:21:58<11:30:54,  1.71it/s]
Train steps ... :  29%|██▉       | 29167/100000 [8:21:58<11:30:18,  1.71it/s]
Train steps ... :  29%|██▉       | 29168/100000 [8:21:59<11:30:40,  1.71it/s]
Train steps ... :  29%|██▉       | 29169/100000 [8:21:59<11:31:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29170/100000 [8:22:00<11:31:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29171/100000 [8:22:01<11:30:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29172/100000 [8:22:01<11:29:49,  1.71it/s]
Train steps ... :  29%|██▉       | 29173/100000 [8:22:02<11:30:06,  1.71it/s]
Train steps ... :  29%|██▉       | 29174/100000 [8:22:02<11:29:12,  1.71it/s]
Train steps ... :  29%|██▉       | 29175/100000 [8:22:03<11:30:09,  1.71it/s]Step... (29175 / 100000 | Loss: 0.7398332357406616, Learning Rate: 7.118090452261307e-05)
+
                                                                             
Step... (29175 / 100000 | Loss: 0.8118484020233154, Learning Rate: 7.118090452261307e-05)
+
Train steps ... :  29%|██▉       | 29175/100000 [8:22:03<11:30:09,  1.71it/s]
Train steps ... :  29%|██▉       | 29176/100000 [8:22:04<11:30:12,  1.71it/s]
Train steps ... :  29%|██▉       | 29177/100000 [8:22:04<11:30:13,  1.71it/s]
Train steps ... :  29%|██▉       | 29178/100000 [8:22:05<11:28:40,  1.71it/s]
Train steps ... :  29%|██▉       | 29179/100000 [8:22:05<11:29:11,  1.71it/s]
Train steps ... :  29%|██▉       | 29180/100000 [8:22:06<11:29:40,  1.71it/s]
Train steps ... :  29%|██▉       | 29181/100000 [8:22:06<11:29:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29182/100000 [8:22:07<11:30:27,  1.71it/s]
Train steps ... :  29%|██▉       | 29183/100000 [8:22:08<11:30:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29184/100000 [8:22:08<11:29:57,  1.71it/s]
Train steps ... :  29%|██▉       | 29185/100000 [8:22:09<11:31:11,  1.71it/s]
Train steps ... :  29%|██▉       | 29186/100000 [8:22:09<11:30:08,  1.71it/s]
Train steps ... :  29%|██▉       | 29187/100000 [8:22:10<11:29:52,  1.71it/s]
Train steps ... :  29%|██▉       | 29188/100000 [8:22:11<11:29:55,  1.71it/s]
Train steps ... :  29%|██▉       | 29189/100000 [8:22:11<11:30:08,  1.71it/s]
Train steps ... :  29%|██▉       | 29190/100000 [8:22:12<11:30:20,  1.71it/s]
Train steps ... :  29%|██▉       | 29191/100000 [8:22:12<11:30:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29192/100000 [8:22:13<11:29:41,  1.71it/s]
Train steps ... :  29%|██▉       | 29193/100000 [8:22:14<11:29:05,  1.71it/s]
Train steps ... :  29%|██▉       | 29194/100000 [8:22:14<11:29:02,  1.71it/s]
Train steps ... :  29%|██▉       | 29195/100000 [8:22:15<11:28:30,  1.71it/s]
Train steps ... :  29%|██▉       | 29196/100000 [8:22:15<11:28:42,  1.71it/s]
Train steps ... :  29%|██▉       | 29197/100000 [8:22:16<11:28:27,  1.71it/s]
Train steps ... :  29%|██▉       | 29198/100000 [8:22:16<11:29:28,  1.71it/s]
Train steps ... :  29%|██▉       | 29199/100000 [8:22:17<11:30:39,  1.71it/s]
Train steps ... :  29%|██▉       | 29200/100000 [8:22:18<11:29:41,  1.71it/s]Step... (29200 / 100000 | Loss: 1.497731328010559, Learning Rate: 7.115577889447236e-05)
+
                                                                             
Step... (29200 / 100000 | Loss: 1.2046153545379639, Learning Rate: 7.115577889447236e-05)
+
Train steps ... :  29%|██▉       | 29200/100000 [8:22:18<11:29:41,  1.71it/s]
Train steps ... :  29%|██▉       | 29201/100000 [8:22:18<11:30:11,  1.71it/s]
Train steps ... :  29%|██▉       | 29202/100000 [8:22:19<11:30:11,  1.71it/s]
Train steps ... :  29%|██▉       | 29203/100000 [8:22:19<11:29:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29204/100000 [8:22:20<11:29:34,  1.71it/s]
Train steps ... :  29%|██▉       | 29205/100000 [8:22:21<11:30:45,  1.71it/s]
Train steps ... :  29%|██▉       | 29206/100000 [8:22:21<11:30:04,  1.71it/s]
Train steps ... :  29%|██▉       | 29207/100000 [8:22:22<11:29:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29208/100000 [8:22:22<11:29:16,  1.71it/s]
Train steps ... :  29%|██▉       | 29209/100000 [8:22:23<11:30:26,  1.71it/s]
Train steps ... :  29%|██▉       | 29210/100000 [8:22:23<11:30:36,  1.71it/s]
Train steps ... :  29%|██▉       | 29211/100000 [8:22:24<11:29:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29212/100000 [8:22:25<11:28:55,  1.71it/s]
Train steps ... :  29%|██▉       | 29213/100000 [8:22:25<11:29:02,  1.71it/s]
Train steps ... :  29%|██▉       | 29214/100000 [8:22:26<11:29:01,  1.71it/s]
Train steps ... :  29%|██▉       | 29215/100000 [8:22:26<11:28:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29216/100000 [8:22:27<11:29:32,  1.71it/s]
Train steps ... :  29%|██▉       | 29217/100000 [8:22:28<11:28:36,  1.71it/s]
Train steps ... :  29%|██▉       | 29218/100000 [8:22:28<11:28:17,  1.71it/s]
Train steps ... :  29%|██▉       | 29219/100000 [8:22:29<11:29:16,  1.71it/s]
Train steps ... :  29%|██▉       | 29220/100000 [8:22:29<11:28:57,  1.71it/s]
Train steps ... :  29%|██▉       | 29221/100000 [8:22:30<11:29:08,  1.71it/s]
Train steps ... :  29%|██▉       | 29222/100000 [8:22:30<11:29:14,  1.71it/s]
Train steps ... :  29%|██▉       | 29223/100000 [8:22:31<11:29:10,  1.71it/s]
Train steps ... :  29%|██▉       | 29224/100000 [8:22:32<11:28:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29225/100000 [8:22:32<11:29:12,  1.71it/s]Step... (29225 / 100000 | Loss: 0.8457975387573242, Learning Rate: 7.113065326633166e-05)
+
                                                                             
Step... (29225 / 100000 | Loss: 0.8836734294891357, Learning Rate: 7.113065326633166e-05)
+
Train steps ... :  29%|██▉       | 29225/100000 [8:22:33<11:29:12,  1.71it/s]
Train steps ... :  29%|██▉       | 29226/100000 [8:22:33<11:28:45,  1.71it/s]
Train steps ... :  29%|██▉       | 29227/100000 [8:22:33<11:29:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29228/100000 [8:22:34<11:28:52,  1.71it/s]
Train steps ... :  29%|██▉       | 29229/100000 [8:22:35<11:28:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29230/100000 [8:22:35<11:29:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29231/100000 [8:22:36<11:29:44,  1.71it/s]
Train steps ... :  29%|██▉       | 29232/100000 [8:22:36<11:29:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29233/100000 [8:22:37<11:30:09,  1.71it/s]
Train steps ... :  29%|██▉       | 29234/100000 [8:22:37<11:29:51,  1.71it/s]
Train steps ... :  29%|██▉       | 29235/100000 [8:22:38<11:30:02,  1.71it/s]
Train steps ... :  29%|██▉       | 29236/100000 [8:22:39<11:29:11,  1.71it/s]
Train steps ... :  29%|██▉       | 29237/100000 [8:22:39<11:29:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29238/100000 [8:22:40<11:30:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29239/100000 [8:22:40<11:30:48,  1.71it/s]
Train steps ... :  29%|██▉       | 29240/100000 [8:22:41<11:30:56,  1.71it/s]
Train steps ... :  29%|██▉       | 29241/100000 [8:22:42<11:30:18,  1.71it/s]
Train steps ... :  29%|██▉       | 29242/100000 [8:22:42<11:29:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29243/100000 [8:22:43<11:29:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29244/100000 [8:22:43<11:29:13,  1.71it/s]
Train steps ... :  29%|██▉       | 29245/100000 [8:22:44<11:29:10,  1.71it/s]
Train steps ... :  29%|██▉       | 29246/100000 [8:22:44<11:28:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29247/100000 [8:22:45<11:28:41,  1.71it/s]
Train steps ... :  29%|██▉       | 29248/100000 [8:22:46<11:28:15,  1.71it/s]
Train steps ... :  29%|██▉       | 29249/100000 [8:22:46<11:29:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29250/100000 [8:22:47<11:28:37,  1.71it/s]Step... (29250 / 100000 | Loss: 0.8536421656608582, Learning Rate: 7.110552763819096e-05)
+
                                                                             
Step... (29250 / 100000 | Loss: 0.910947859287262, Learning Rate: 7.110552763819096e-05)
+
Train steps ... :  29%|██▉       | 29250/100000 [8:22:47<11:28:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29251/100000 [8:22:47<11:28:49,  1.71it/s]
Train steps ... :  29%|██▉       | 29252/100000 [8:22:48<11:28:43,  1.71it/s]
Train steps ... :  29%|██▉       | 29253/100000 [8:22:49<11:28:18,  1.71it/s]
Train steps ... :  29%|██▉       | 29254/100000 [8:22:49<11:28:15,  1.71it/s]
Train steps ... :  29%|██▉       | 29255/100000 [8:22:50<11:28:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29256/100000 [8:22:50<11:28:22,  1.71it/s]
Train steps ... :  29%|██▉       | 29257/100000 [8:22:51<11:28:02,  1.71it/s]
Train steps ... :  29%|██▉       | 29258/100000 [8:22:51<11:28:38,  1.71it/s]
Train steps ... :  29%|██▉       | 29259/100000 [8:22:52<11:29:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29260/100000 [8:22:53<11:28:27,  1.71it/s]
Train steps ... :  29%|██▉       | 29261/100000 [8:22:53<11:28:57,  1.71it/s]
Train steps ... :  29%|██▉       | 29262/100000 [8:22:54<11:29:27,  1.71it/s]
Train steps ... :  29%|██▉       | 29263/100000 [8:22:54<11:28:58,  1.71it/s]
Train steps ... :  29%|██▉       | 29264/100000 [8:22:55<11:28:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29265/100000 [8:22:56<11:28:45,  1.71it/s]
Train steps ... :  29%|██▉       | 29266/100000 [8:22:56<11:29:05,  1.71it/s]
Train steps ... :  29%|██▉       | 29267/100000 [8:22:57<11:29:22,  1.71it/s]
Train steps ... :  29%|██▉       | 29268/100000 [8:22:57<11:29:03,  1.71it/s]
Train steps ... :  29%|██▉       | 29269/100000 [8:22:58<11:29:13,  1.71it/s]
Train steps ... :  29%|██▉       | 29270/100000 [8:22:59<11:28:48,  1.71it/s]
Train steps ... :  29%|██▉       | 29271/100000 [8:22:59<11:29:27,  1.71it/s]
Train steps ... :  29%|██▉       | 29272/100000 [8:23:00<11:30:17,  1.71it/s]
Train steps ... :  29%|██▉       | 29273/100000 [8:23:00<11:29:51,  1.71it/s]
Train steps ... :  29%|██▉       | 29274/100000 [8:23:01<11:29:03,  1.71it/s]
Train steps ... :  29%|██▉       | 29275/100000 [8:23:01<11:28:43,  1.71it/s]Step... (29275 / 100000 | Loss: 1.1935243606567383, Learning Rate: 7.108040201005025e-05)
+
                                                                             
Step... (29275 / 100000 | Loss: 0.9893076419830322, Learning Rate: 7.108040201005025e-05)
+
Train steps ... :  29%|██▉       | 29275/100000 [8:23:02<11:28:43,  1.71it/s]
Train steps ... :  29%|██▉       | 29276/100000 [8:23:02<11:28:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29277/100000 [8:23:03<11:28:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29278/100000 [8:23:03<11:28:32,  1.71it/s]
Train steps ... :  29%|██▉       | 29279/100000 [8:23:04<11:28:15,  1.71it/s]
Train steps ... :  29%|██▉       | 29280/100000 [8:23:04<11:28:53,  1.71it/s]
Train steps ... :  29%|██▉       | 29281/100000 [8:23:05<11:28:22,  1.71it/s]
Train steps ... :  29%|██▉       | 29282/100000 [8:23:06<11:28:28,  1.71it/s]
Train steps ... :  29%|██▉       | 29283/100000 [8:23:06<11:28:14,  1.71it/s]
Train steps ... :  29%|██▉       | 29284/100000 [8:23:07<11:28:17,  1.71it/s]
Train steps ... :  29%|██▉       | 29285/100000 [8:23:07<11:28:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29286/100000 [8:23:08<11:27:36,  1.71it/s]
Train steps ... :  29%|██▉       | 29287/100000 [8:23:08<11:28:34,  1.71it/s]
Train steps ... :  29%|██▉       | 29288/100000 [8:23:09<11:28:05,  1.71it/s]
Train steps ... :  29%|██▉       | 29289/100000 [8:23:10<11:28:40,  1.71it/s]
Train steps ... :  29%|██▉       | 29290/100000 [8:23:10<11:28:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29291/100000 [8:23:11<11:27:59,  1.71it/s]
Train steps ... :  29%|██▉       | 29292/100000 [8:23:11<11:28:34,  1.71it/s]
Train steps ... :  29%|██▉       | 29293/100000 [8:23:12<11:28:32,  1.71it/s]
Train steps ... :  29%|██▉       | 29294/100000 [8:23:13<11:28:26,  1.71it/s]
Train steps ... :  29%|██▉       | 29295/100000 [8:23:13<11:28:06,  1.71it/s]
Train steps ... :  29%|██▉       | 29296/100000 [8:23:14<11:27:56,  1.71it/s]
Train steps ... :  29%|██▉       | 29297/100000 [8:23:14<11:28:25,  1.71it/s]
Train steps ... :  29%|██▉       | 29298/100000 [8:23:15<11:28:16,  1.71it/s]
Train steps ... :  29%|██▉       | 29299/100000 [8:23:15<11:28:49,  1.71it/s]
Train steps ... :  29%|██▉       | 29300/100000 [8:23:16<11:29:09,  1.71it/s]Step... (29300 / 100000 | Loss: 1.0451924800872803, Learning Rate: 7.105527638190955e-05)
+
                                                                             
Step... (29300 / 100000 | Loss: 0.8422131538391113, Learning Rate: 7.105527638190955e-05)
+
Train steps ... :  29%|██▉       | 29300/100000 [8:23:16<11:29:09,  1.71it/s]
Train steps ... :  29%|██▉       | 29301/100000 [8:23:17<11:29:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29302/100000 [8:23:17<11:29:05,  1.71it/s]
Train steps ... :  29%|██▉       | 29303/100000 [8:23:18<11:30:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29304/100000 [8:23:18<11:29:32,  1.71it/s]
Train steps ... :  29%|██▉       | 29305/100000 [8:23:19<11:28:47,  1.71it/s]
Train steps ... :  29%|██▉       | 29306/100000 [8:23:20<11:29:43,  1.71it/s]
Train steps ... :  29%|██▉       | 29307/100000 [8:23:20<11:30:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29308/100000 [8:23:21<11:29:56,  1.71it/s]
Train steps ... :  29%|██▉       | 29309/100000 [8:23:21<11:29:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29310/100000 [8:23:22<11:28:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29311/100000 [8:23:22<11:28:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29312/100000 [8:23:23<11:27:46,  1.71it/s]
Train steps ... :  29%|██▉       | 29313/100000 [8:23:24<11:27:26,  1.71it/s]
Train steps ... :  29%|██▉       | 29314/100000 [8:23:24<11:28:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29315/100000 [8:23:25<11:28:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29316/100000 [8:23:25<11:27:56,  1.71it/s]
Train steps ... :  29%|██▉       | 29317/100000 [8:23:26<11:28:12,  1.71it/s]
Train steps ... :  29%|██▉       | 29318/100000 [8:23:27<11:27:51,  1.71it/s]
Train steps ... :  29%|██▉       | 29319/100000 [8:23:27<11:28:04,  1.71it/s]
Train steps ... :  29%|██▉       | 29320/100000 [8:23:28<11:28:28,  1.71it/s]
Train steps ... :  29%|██▉       | 29321/100000 [8:23:28<11:28:42,  1.71it/s]
Train steps ... :  29%|██▉       | 29322/100000 [8:23:29<11:28:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29323/100000 [8:23:29<11:28:54,  1.71it/s]
Train steps ... :  29%|██▉       | 29324/100000 [8:23:30<11:28:22,  1.71it/s]
Train steps ... :  29%|██▉       | 29325/100000 [8:23:31<11:28:12,  1.71it/s]Step... (29325 / 100000 | Loss: 0.7640067338943481, Learning Rate: 7.103015075376885e-05)
+
                                                                             
Step... (29325 / 100000 | Loss: 0.8746753334999084, Learning Rate: 7.103015075376885e-05)
+
Train steps ... :  29%|██▉       | 29325/100000 [8:23:31<11:28:12,  1.71it/s]
Train steps ... :  29%|██▉       | 29326/100000 [8:23:31<11:29:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29327/100000 [8:23:32<11:28:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29328/100000 [8:23:32<11:29:28,  1.71it/s]
Train steps ... :  29%|██▉       | 29329/100000 [8:23:33<11:28:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29330/100000 [8:23:34<11:28:04,  1.71it/s]
Train steps ... :  29%|██▉       | 29331/100000 [8:23:34<11:27:40,  1.71it/s]
Train steps ... :  29%|██▉       | 29332/100000 [8:23:35<11:27:54,  1.71it/s]
Train steps ... :  29%|██▉       | 29333/100000 [8:23:35<11:27:38,  1.71it/s]
Train steps ... :  29%|██▉       | 29334/100000 [8:23:36<11:27:18,  1.71it/s]
Train steps ... :  29%|██▉       | 29335/100000 [8:23:36<11:27:20,  1.71it/s]
Train steps ... :  29%|██▉       | 29336/100000 [8:23:37<11:27:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29337/100000 [8:23:38<11:27:41,  1.71it/s]
Train steps ... :  29%|██▉       | 29338/100000 [8:23:38<11:28:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29339/100000 [8:23:39<11:27:45,  1.71it/s]
Train steps ... :  29%|██▉       | 29340/100000 [8:23:39<11:28:01,  1.71it/s]
Train steps ... :  29%|██▉       | 29341/100000 [8:23:40<11:28:20,  1.71it/s]
Train steps ... :  29%|██▉       | 29342/100000 [8:23:41<11:29:03,  1.71it/s]
Train steps ... :  29%|██▉       | 29343/100000 [8:23:41<11:28:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29344/100000 [8:23:42<11:28:28,  1.71it/s]
Train steps ... :  29%|██▉       | 29345/100000 [8:23:42<11:27:45,  1.71it/s]
Train steps ... :  29%|██▉       | 29346/100000 [8:23:43<11:28:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29347/100000 [8:23:44<11:27:14,  1.71it/s]
Train steps ... :  29%|██▉       | 29348/100000 [8:23:44<11:27:15,  1.71it/s]
Train steps ... :  29%|██▉       | 29349/100000 [8:23:45<11:27:43,  1.71it/s]
Train steps ... :  29%|██▉       | 29350/100000 [8:23:45<11:28:26,  1.71it/s]Step... (29350 / 100000 | Loss: 0.6365097761154175, Learning Rate: 7.100502512562814e-05)
+
                                                                             
Step... (29350 / 100000 | Loss: 1.0272140502929688, Learning Rate: 7.100502512562814e-05)
+
Train steps ... :  29%|██▉       | 29350/100000 [8:23:46<11:28:26,  1.71it/s]
Train steps ... :  29%|██▉       | 29351/100000 [8:23:46<11:28:53,  1.71it/s]
Train steps ... :  29%|██▉       | 29352/100000 [8:23:46<11:28:49,  1.71it/s]
Train steps ... :  29%|██▉       | 29353/100000 [8:23:47<11:28:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29354/100000 [8:23:48<11:28:47,  1.71it/s]
Train steps ... :  29%|██▉       | 29355/100000 [8:23:48<11:28:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29356/100000 [8:23:49<11:27:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29357/100000 [8:23:49<11:27:41,  1.71it/s]
Train steps ... :  29%|██▉       | 29358/100000 [8:23:50<11:27:37,  1.71it/s]
Train steps ... :  29%|██▉       | 29359/100000 [8:23:51<11:28:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29360/100000 [8:23:51<11:27:41,  1.71it/s]
Train steps ... :  29%|██▉       | 29361/100000 [8:23:52<11:28:21,  1.71it/s]
Train steps ... :  29%|██▉       | 29362/100000 [8:23:52<11:28:27,  1.71it/s]
Train steps ... :  29%|██▉       | 29363/100000 [8:23:53<11:27:40,  1.71it/s]
Train steps ... :  29%|██▉       | 29364/100000 [8:23:53<11:28:11,  1.71it/s]
Train steps ... :  29%|██▉       | 29365/100000 [8:23:54<11:28:14,  1.71it/s]
Train steps ... :  29%|██▉       | 29366/100000 [8:23:55<11:29:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29367/100000 [8:23:55<11:28:36,  1.71it/s]
Train steps ... :  29%|██▉       | 29368/100000 [8:23:56<11:27:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29369/100000 [8:23:56<11:27:26,  1.71it/s]
Train steps ... :  29%|██▉       | 29370/100000 [8:23:57<11:28:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29371/100000 [8:23:58<11:27:42,  1.71it/s]
Train steps ... :  29%|██▉       | 29372/100000 [8:23:58<11:27:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29373/100000 [8:23:59<11:26:40,  1.71it/s]
Train steps ... :  29%|██▉       | 29374/100000 [8:23:59<11:27:28,  1.71it/s]
Train steps ... :  29%|██▉       | 29375/100000 [8:24:00<11:27:21,  1.71it/s]Step... (29375 / 100000 | Loss: 0.7136338949203491, Learning Rate: 7.097989949748744e-05)
+
                                                                             
Step... (29375 / 100000 | Loss: 1.409144401550293, Learning Rate: 7.097989949748744e-05)
+
Train steps ... :  29%|██▉       | 29375/100000 [8:24:00<11:27:21,  1.71it/s]
Train steps ... :  29%|██▉       | 29376/100000 [8:24:00<11:28:02,  1.71it/s]
Train steps ... :  29%|██▉       | 29377/100000 [8:24:01<11:27:30,  1.71it/s]
Train steps ... :  29%|██▉       | 29378/100000 [8:24:02<11:27:53,  1.71it/s]
Train steps ... :  29%|██▉       | 29379/100000 [8:24:02<11:28:21,  1.71it/s]
Train steps ... :  29%|██▉       | 29380/100000 [8:24:03<11:27:26,  1.71it/s]
Train steps ... :  29%|██▉       | 29381/100000 [8:24:03<11:27:22,  1.71it/s]
Train steps ... :  29%|██▉       | 29382/100000 [8:24:04<11:27:47,  1.71it/s]
Train steps ... :  29%|██▉       | 29383/100000 [8:24:05<11:27:54,  1.71it/s]
Train steps ... :  29%|██▉       | 29384/100000 [8:24:05<11:28:48,  1.71it/s]
Train steps ... :  29%|██▉       | 29385/100000 [8:24:06<11:27:45,  1.71it/s]
Train steps ... :  29%|██▉       | 29386/100000 [8:24:06<11:27:43,  1.71it/s]
Train steps ... :  29%|██▉       | 29387/100000 [8:24:07<11:27:17,  1.71it/s]
Train steps ... :  29%|██▉       | 29388/100000 [8:24:07<11:26:43,  1.71it/s]
Train steps ... :  29%|██▉       | 29389/100000 [8:24:08<11:27:03,  1.71it/s]
Train steps ... :  29%|██▉       | 29390/100000 [8:24:09<11:27:51,  1.71it/s]
Train steps ... :  29%|██▉       | 29391/100000 [8:24:09<11:27:03,  1.71it/s]
Train steps ... :  29%|██▉       | 29392/100000 [8:24:10<11:27:46,  1.71it/s]
Train steps ... :  29%|██▉       | 29393/100000 [8:24:10<11:27:25,  1.71it/s]
Train steps ... :  29%|██▉       | 29394/100000 [8:24:11<11:26:44,  1.71it/s]
Train steps ... :  29%|██▉       | 29395/100000 [8:24:12<11:26:24,  1.71it/s]
Train steps ... :  29%|██▉       | 29396/100000 [8:24:12<11:27:11,  1.71it/s]
Train steps ... :  29%|██▉       | 29397/100000 [8:24:13<11:26:25,  1.71it/s]
Train steps ... :  29%|██▉       | 29398/100000 [8:24:13<11:26:07,  1.72it/s]
Train steps ... :  29%|██▉       | 29399/100000 [8:24:14<11:26:55,  1.71it/s]
Train steps ... :  29%|██▉       | 29400/100000 [8:24:14<11:27:07,  1.71it/s]Step... (29400 / 100000 | Loss: 1.1335723400115967, Learning Rate: 7.095477386934674e-05)
+
                                                                             
Step... (29400 / 100000 | Loss: 1.0433048009872437, Learning Rate: 7.095477386934674e-05)
+
Train steps ... :  29%|██▉       | 29400/100000 [8:24:15<11:27:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29401/100000 [8:24:15<11:27:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29402/100000 [8:24:16<11:28:16,  1.71it/s]
Train steps ... :  29%|██▉       | 29403/100000 [8:24:16<11:27:40,  1.71it/s]
Train steps ... :  29%|██▉       | 29404/100000 [8:24:17<11:27:26,  1.71it/s]
Train steps ... :  29%|██▉       | 29405/100000 [8:24:17<11:27:53,  1.71it/s]
Train steps ... :  29%|██▉       | 29406/100000 [8:24:18<11:27:51,  1.71it/s]
Train steps ... :  29%|██▉       | 29407/100000 [8:24:19<11:28:21,  1.71it/s]
Train steps ... :  29%|██▉       | 29408/100000 [8:24:19<11:27:46,  1.71it/s]
Train steps ... :  29%|██▉       | 29409/100000 [8:24:20<11:27:40,  1.71it/s]
Train steps ... :  29%|██▉       | 29410/100000 [8:24:20<11:27:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29411/100000 [8:24:21<11:27:25,  1.71it/s]
Train steps ... :  29%|██▉       | 29412/100000 [8:24:21<11:27:32,  1.71it/s]
Train steps ... :  29%|██▉       | 29413/100000 [8:24:22<11:27:20,  1.71it/s]
Train steps ... :  29%|██▉       | 29414/100000 [8:24:23<11:27:42,  1.71it/s]
Train steps ... :  29%|██▉       | 29415/100000 [8:24:23<11:27:09,  1.71it/s]
Train steps ... :  29%|██▉       | 29416/100000 [8:24:24<11:26:54,  1.71it/s]
Train steps ... :  29%|██▉       | 29417/100000 [8:24:24<11:26:13,  1.71it/s]
Train steps ... :  29%|██▉       | 29418/100000 [8:24:25<11:26:17,  1.71it/s]
Train steps ... :  29%|██▉       | 29419/100000 [8:24:26<11:26:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29420/100000 [8:24:26<11:27:02,  1.71it/s]
Train steps ... :  29%|██▉       | 29421/100000 [8:24:27<11:26:47,  1.71it/s]
Train steps ... :  29%|██▉       | 29422/100000 [8:24:27<11:26:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29423/100000 [8:24:28<11:27:16,  1.71it/s]
Train steps ... :  29%|██▉       | 29424/100000 [8:24:28<11:27:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29425/100000 [8:24:29<11:29:25,  1.71it/s]Step... (29425 / 100000 | Loss: 1.0506263971328735, Learning Rate: 7.092964824120603e-05)
+
                                                                             
Step... (29425 / 100000 | Loss: 1.7904034852981567, Learning Rate: 7.092964824120603e-05)
+
Train steps ... :  29%|██▉       | 29425/100000 [8:24:29<11:29:25,  1.71it/s]
Train steps ... :  29%|██▉       | 29426/100000 [8:24:30<11:28:22,  1.71it/s]
Train steps ... :  29%|██▉       | 29427/100000 [8:24:30<11:27:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29428/100000 [8:24:31<11:27:35,  1.71it/s]
Train steps ... :  29%|██▉       | 29429/100000 [8:24:31<11:27:44,  1.71it/s]
Train steps ... :  29%|██▉       | 29430/100000 [8:24:32<11:27:08,  1.71it/s]
Train steps ... :  29%|██▉       | 29431/100000 [8:24:33<11:27:10,  1.71it/s]
Train steps ... :  29%|██▉       | 29432/100000 [8:24:33<11:28:20,  1.71it/s]
Train steps ... :  29%|██▉       | 29433/100000 [8:24:34<11:27:21,  1.71it/s]
Train steps ... :  29%|██▉       | 29434/100000 [8:24:34<11:27:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29435/100000 [8:24:35<11:26:59,  1.71it/s]
Train steps ... :  29%|██▉       | 29436/100000 [8:24:36<11:26:39,  1.71it/s]
Train steps ... :  29%|██▉       | 29437/100000 [8:24:36<11:26:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29438/100000 [8:24:37<11:26:38,  1.71it/s]
Train steps ... :  29%|██▉       | 29439/100000 [8:24:37<11:26:55,  1.71it/s]
Train steps ... :  29%|██▉       | 29440/100000 [8:24:38<11:28:50,  1.71it/s]
Train steps ... :  29%|██▉       | 29441/100000 [8:24:38<11:26:54,  1.71it/s]
Train steps ... :  29%|██▉       | 29442/100000 [8:24:39<11:26:13,  1.71it/s]
Train steps ... :  29%|██▉       | 29443/100000 [8:24:40<11:26:48,  1.71it/s]
Train steps ... :  29%|██▉       | 29444/100000 [8:24:40<11:27:54,  1.71it/s]
Train steps ... :  29%|██▉       | 29445/100000 [8:24:41<11:27:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29446/100000 [8:24:41<11:26:43,  1.71it/s]
Train steps ... :  29%|██▉       | 29447/100000 [8:24:42<11:27:30,  1.71it/s]
Train steps ... :  29%|██▉       | 29448/100000 [8:24:43<11:27:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29449/100000 [8:24:43<11:26:35,  1.71it/s]
Train steps ... :  29%|██▉       | 29450/100000 [8:24:44<11:27:14,  1.71it/s]Step... (29450 / 100000 | Loss: 1.0144612789154053, Learning Rate: 7.090452261306533e-05)
+
                                                                             
Step... (29450 / 100000 | Loss: 1.0834566354751587, Learning Rate: 7.090452261306533e-05)
+
Train steps ... :  29%|██▉       | 29450/100000 [8:24:44<11:27:14,  1.71it/s]
Train steps ... :  29%|██▉       | 29451/100000 [8:24:44<11:27:58,  1.71it/s]
Train steps ... :  29%|██▉       | 29452/100000 [8:24:45<11:27:34,  1.71it/s]
Train steps ... :  29%|██▉       | 29453/100000 [8:24:45<11:26:48,  1.71it/s]
Train steps ... :  29%|██▉       | 29454/100000 [8:24:46<11:26:16,  1.71it/s]
Train steps ... :  29%|██▉       | 29455/100000 [8:24:47<11:26:10,  1.71it/s]
Train steps ... :  29%|██▉       | 29456/100000 [8:24:47<11:25:45,  1.71it/s]
Train steps ... :  29%|██▉       | 29457/100000 [8:24:48<11:26:23,  1.71it/s]
Train steps ... :  29%|██▉       | 29458/100000 [8:24:48<11:27:09,  1.71it/s]
Train steps ... :  29%|██▉       | 29459/100000 [8:24:49<11:27:15,  1.71it/s]
Train steps ... :  29%|██▉       | 29460/100000 [8:24:50<11:27:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29461/100000 [8:24:50<11:27:03,  1.71it/s]
Train steps ... :  29%|██▉       | 29462/100000 [8:24:51<11:26:27,  1.71it/s]
Train steps ... :  29%|██▉       | 29463/100000 [8:24:51<11:26:18,  1.71it/s]
Train steps ... :  29%|██▉       | 29464/100000 [8:24:52<11:27:11,  1.71it/s]
Train steps ... :  29%|██▉       | 29465/100000 [8:24:52<11:26:42,  1.71it/s]
Train steps ... :  29%|██▉       | 29466/100000 [8:24:53<11:26:14,  1.71it/s]
Train steps ... :  29%|██▉       | 29467/100000 [8:24:54<11:26:28,  1.71it/s]
Train steps ... :  29%|██▉       | 29468/100000 [8:24:54<11:26:16,  1.71it/s]
Train steps ... :  29%|██▉       | 29469/100000 [8:24:55<11:26:16,  1.71it/s]
Train steps ... :  29%|██▉       | 29470/100000 [8:24:55<11:26:12,  1.71it/s]
Train steps ... :  29%|██▉       | 29471/100000 [8:24:56<11:26:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29472/100000 [8:24:57<11:26:18,  1.71it/s]
Train steps ... :  29%|██▉       | 29473/100000 [8:24:57<11:26:52,  1.71it/s]
Train steps ... :  29%|██▉       | 29474/100000 [8:24:58<11:27:06,  1.71it/s]
Train steps ... :  29%|██▉       | 29475/100000 [8:24:58<11:28:13,  1.71it/s]Step... (29475 / 100000 | Loss: 1.2901380062103271, Learning Rate: 7.087939698492463e-05)
+
                                                                             
Step... (29475 / 100000 | Loss: 0.9261928200721741, Learning Rate: 7.087939698492463e-05)
+
Train steps ... :  29%|██▉       | 29475/100000 [8:24:59<11:28:13,  1.71it/s]
Train steps ... :  29%|██▉       | 29476/100000 [8:24:59<11:28:13,  1.71it/s]
Train steps ... :  29%|██▉       | 29477/100000 [8:24:59<11:31:09,  1.70it/s]
Train steps ... :  29%|██▉       | 29478/100000 [8:25:00<11:31:16,  1.70it/s]
Train steps ... :  29%|██▉       | 29479/100000 [8:25:01<11:30:14,  1.70it/s]
Train steps ... :  29%|██▉       | 29480/100000 [8:25:01<11:30:47,  1.70it/s]
Train steps ... :  29%|██▉       | 29481/100000 [8:25:02<11:31:35,  1.70it/s]
Train steps ... :  29%|██▉       | 29482/100000 [8:25:02<11:30:46,  1.70it/s]
Train steps ... :  29%|██▉       | 29483/100000 [8:25:03<11:29:54,  1.70it/s]
Train steps ... :  29%|██▉       | 29484/100000 [8:25:04<11:28:59,  1.71it/s]
Train steps ... :  29%|██▉       | 29485/100000 [8:25:04<11:29:33,  1.70it/s]
Train steps ... :  29%|██▉       | 29486/100000 [8:25:05<11:29:40,  1.70it/s]
Train steps ... :  29%|██▉       | 29487/100000 [8:25:05<11:28:58,  1.71it/s]
Train steps ... :  29%|██▉       | 29488/100000 [8:25:06<11:28:36,  1.71it/s]
Train steps ... :  29%|██▉       | 29489/100000 [8:25:07<11:28:29,  1.71it/s]
Train steps ... :  29%|██▉       | 29490/100000 [8:25:07<11:29:57,  1.70it/s]
Train steps ... :  29%|██▉       | 29491/100000 [8:25:08<11:29:29,  1.70it/s]
Train steps ... :  29%|██▉       | 29492/100000 [8:25:08<11:28:06,  1.71it/s]
Train steps ... :  29%|██▉       | 29493/100000 [8:25:09<11:27:46,  1.71it/s]
Train steps ... :  29%|██▉       | 29494/100000 [8:25:09<11:27:33,  1.71it/s]
Train steps ... :  29%|██▉       | 29495/100000 [8:25:10<11:27:07,  1.71it/s]
Train steps ... :  29%|██▉       | 29496/100000 [8:25:11<11:27:00,  1.71it/s]
Train steps ... :  29%|██▉       | 29497/100000 [8:25:11<11:27:19,  1.71it/s]
Train steps ... :  29%|██▉       | 29498/100000 [8:25:12<11:26:48,  1.71it/s]
Train steps ... :  29%|██▉       | 29499/100000 [8:25:12<11:27:48,  1.71it/s]
Train steps ... :  30%|██▉       | 29500/100000 [8:25:13<11:27:44,  1.71it/s]Step... (29500 / 100000 | Loss: 1.1461459398269653, Learning Rate: 7.085427135678392e-05)
+
                                                                             
Step... (29500 / 100000 | Loss: 1.0567599534988403, Learning Rate: 7.085427135678392e-05)
+
Train steps ... :  30%|██▉       | 29500/100000 [8:25:13<11:27:44,  1.71it/s]
Train steps ... :  30%|██▉       | 29501/100000 [8:25:14<11:29:11,  1.70it/s]
Train steps ... :  30%|██▉       | 29502/100000 [8:25:14<11:28:42,  1.71it/s]
Train steps ... :  30%|██▉       | 29503/100000 [8:25:15<11:28:26,  1.71it/s]
Train steps ... :  30%|██▉       | 29504/100000 [8:25:15<11:28:45,  1.71it/s]
Train steps ... :  30%|██▉       | 29505/100000 [8:25:16<11:28:37,  1.71it/s]
Train steps ... :  30%|██▉       | 29506/100000 [8:25:16<11:27:35,  1.71it/s]
Train steps ... :  30%|██▉       | 29507/100000 [8:25:17<11:27:10,  1.71it/s]
Train steps ... :  30%|██▉       | 29508/100000 [8:25:18<11:26:46,  1.71it/s]
Train steps ... :  30%|██▉       | 29509/100000 [8:25:18<11:26:31,  1.71it/s]
Train steps ... :  30%|██▉       | 29510/100000 [8:25:19<11:26:22,  1.71it/s]
Train steps ... :  30%|██▉       | 29511/100000 [8:25:19<11:28:03,  1.71it/s]
Train steps ... :  30%|██▉       | 29512/100000 [8:25:20<11:27:43,  1.71it/s]
Train steps ... :  30%|██▉       | 29513/100000 [8:25:21<11:27:01,  1.71it/s]
Train steps ... :  30%|██▉       | 29514/100000 [8:25:21<11:26:40,  1.71it/s]
Train steps ... :  30%|██▉       | 29515/100000 [8:25:22<11:26:39,  1.71it/s]
Train steps ... :  30%|██▉       | 29516/100000 [8:25:22<11:26:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29517/100000 [8:25:23<11:27:10,  1.71it/s]
Train steps ... :  30%|██▉       | 29518/100000 [8:25:23<11:27:29,  1.71it/s]
Train steps ... :  30%|██▉       | 29519/100000 [8:25:24<11:27:38,  1.71it/s]
Train steps ... :  30%|██▉       | 29520/100000 [8:25:25<11:28:04,  1.71it/s]
Train steps ... :  30%|██▉       | 29521/100000 [8:25:25<11:28:01,  1.71it/s]
Train steps ... :  30%|██▉       | 29522/100000 [8:25:26<11:27:21,  1.71it/s]
Train steps ... :  30%|██▉       | 29523/100000 [8:25:26<11:27:06,  1.71it/s]
Train steps ... :  30%|██▉       | 29524/100000 [8:25:27<11:26:44,  1.71it/s]
Train steps ... :  30%|██▉       | 29525/100000 [8:25:28<11:27:10,  1.71it/s]Step... (29525 / 100000 | Loss: 1.0369935035705566, Learning Rate: 7.082914572864322e-05)
+
                                                                             
Step... (29525 / 100000 | Loss: 0.8926676511764526, Learning Rate: 7.082914572864322e-05)
+
Train steps ... :  30%|██▉       | 29525/100000 [8:25:28<11:27:10,  1.71it/s]
Train steps ... :  30%|██▉       | 29526/100000 [8:25:28<11:27:25,  1.71it/s]
Train steps ... :  30%|██▉       | 29527/100000 [8:25:29<11:27:14,  1.71it/s]
Train steps ... :  30%|██▉       | 29528/100000 [8:25:29<11:27:00,  1.71it/s]
Train steps ... :  30%|██▉       | 29529/100000 [8:25:30<11:27:52,  1.71it/s]
Train steps ... :  30%|██▉       | 29530/100000 [8:25:31<11:28:56,  1.70it/s]
Train steps ... :  30%|██▉       | 29531/100000 [8:25:31<11:26:48,  1.71it/s]
Train steps ... :  30%|██▉       | 29532/100000 [8:25:32<11:26:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29533/100000 [8:25:32<11:25:57,  1.71it/s]
Train steps ... :  30%|██▉       | 29534/100000 [8:25:33<11:25:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29535/100000 [8:25:33<11:25:44,  1.71it/s]
Train steps ... :  30%|██▉       | 29536/100000 [8:25:34<11:26:48,  1.71it/s]
Train steps ... :  30%|██▉       | 29537/100000 [8:25:35<11:26:37,  1.71it/s]
Train steps ... :  30%|██▉       | 29538/100000 [8:25:35<11:26:05,  1.71it/s]
Train steps ... :  30%|██▉       | 29539/100000 [8:25:36<11:27:28,  1.71it/s]
Train steps ... :  30%|██▉       | 29540/100000 [8:25:36<11:26:54,  1.71it/s]
Train steps ... :  30%|██▉       | 29541/100000 [8:25:37<11:26:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29542/100000 [8:25:38<11:28:01,  1.71it/s]
Train steps ... :  30%|██▉       | 29543/100000 [8:25:38<11:28:58,  1.70it/s]
Train steps ... :  30%|██▉       | 29544/100000 [8:25:39<11:26:12,  1.71it/s]
Train steps ... :  30%|██▉       | 29545/100000 [8:25:39<11:26:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29546/100000 [8:25:40<11:28:49,  1.70it/s]
Train steps ... :  30%|██▉       | 29547/100000 [8:25:40<11:26:20,  1.71it/s]
Train steps ... :  30%|██▉       | 29548/100000 [8:25:41<11:26:21,  1.71it/s]
Train steps ... :  30%|██▉       | 29549/100000 [8:25:42<11:26:23,  1.71it/s]
Train steps ... :  30%|██▉       | 29550/100000 [8:25:42<11:25:51,  1.71it/s]Step... (29550 / 100000 | Loss: 0.820185661315918, Learning Rate: 7.080402010050252e-05)
+
                                                                             
Step... (29550 / 100000 | Loss: 0.9797148704528809, Learning Rate: 7.080402010050252e-05)
+
Train steps ... :  30%|██▉       | 29550/100000 [8:25:43<11:25:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29551/100000 [8:25:43<11:26:19,  1.71it/s]
Train steps ... :  30%|██▉       | 29552/100000 [8:25:43<11:27:43,  1.71it/s]
Train steps ... :  30%|██▉       | 29553/100000 [8:25:44<11:26:45,  1.71it/s]
Train steps ... :  30%|██▉       | 29554/100000 [8:25:45<11:26:28,  1.71it/s]
Train steps ... :  30%|██▉       | 29555/100000 [8:25:45<11:26:48,  1.71it/s]
Train steps ... :  30%|██▉       | 29556/100000 [8:25:46<11:27:24,  1.71it/s]
Train steps ... :  30%|██▉       | 29557/100000 [8:25:46<11:26:50,  1.71it/s]
Train steps ... :  30%|██▉       | 29558/100000 [8:25:47<11:27:54,  1.71it/s]
Train steps ... :  30%|██▉       | 29559/100000 [8:25:47<11:27:04,  1.71it/s]
Train steps ... :  30%|██▉       | 29560/100000 [8:25:48<11:28:04,  1.71it/s]
Train steps ... :  30%|██▉       | 29561/100000 [8:25:49<11:27:16,  1.71it/s]
Train steps ... :  30%|██▉       | 29562/100000 [8:25:49<11:30:05,  1.70it/s]
Train steps ... :  30%|██▉       | 29563/100000 [8:25:50<11:30:33,  1.70it/s]
Train steps ... :  30%|██▉       | 29564/100000 [8:25:50<11:29:11,  1.70it/s]
Train steps ... :  30%|██▉       | 29565/100000 [8:25:51<11:29:56,  1.70it/s]
Train steps ... :  30%|██▉       | 29566/100000 [8:25:52<11:29:45,  1.70it/s]
Train steps ... :  30%|██▉       | 29567/100000 [8:25:52<11:28:24,  1.71it/s]
Train steps ... :  30%|██▉       | 29568/100000 [8:25:53<11:27:16,  1.71it/s]
Train steps ... :  30%|██▉       | 29569/100000 [8:25:53<11:28:39,  1.70it/s]
Train steps ... :  30%|██▉       | 29570/100000 [8:25:54<11:26:44,  1.71it/s]
Train steps ... :  30%|██▉       | 29571/100000 [8:25:55<11:26:38,  1.71it/s]
Train steps ... :  30%|██▉       | 29572/100000 [8:25:55<11:27:15,  1.71it/s]
Train steps ... :  30%|██▉       | 29573/100000 [8:25:56<11:27:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29574/100000 [8:25:56<11:27:20,  1.71it/s]
Train steps ... :  30%|██▉       | 29575/100000 [8:25:57<11:25:54,  1.71it/s]Step... (29575 / 100000 | Loss: 0.6808580160140991, Learning Rate: 7.077889447236181e-05)
+
                                                                             
Step... (29575 / 100000 | Loss: 0.7919939756393433, Learning Rate: 7.077889447236181e-05)
+
Train steps ... :  30%|██▉       | 29575/100000 [8:25:57<11:25:54,  1.71it/s]
Train steps ... :  30%|██▉       | 29576/100000 [8:25:57<11:26:35,  1.71it/s]
Train steps ... :  30%|██▉       | 29577/100000 [8:25:58<11:29:44,  1.70it/s]
Train steps ... :  30%|██▉       | 29578/100000 [8:25:59<11:27:02,  1.71it/s]
Train steps ... :  30%|██▉       | 29579/100000 [8:25:59<11:27:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29580/100000 [8:26:00<11:29:04,  1.70it/s]
Train steps ... :  30%|██▉       | 29581/100000 [8:26:00<11:29:41,  1.70it/s]
Train steps ... :  30%|██▉       | 29582/100000 [8:26:01<11:29:38,  1.70it/s]
Train steps ... :  30%|██▉       | 29583/100000 [8:26:02<11:28:52,  1.70it/s]
Train steps ... :  30%|██▉       | 29584/100000 [8:26:02<11:28:12,  1.71it/s]
Train steps ... :  30%|██▉       | 29585/100000 [8:26:03<11:27:17,  1.71it/s]
Train steps ... :  30%|██▉       | 29586/100000 [8:26:03<11:28:52,  1.70it/s]
Train steps ... :  30%|██▉       | 29587/100000 [8:26:04<11:25:49,  1.71it/s]
Train steps ... :  30%|██▉       | 29588/100000 [8:26:04<11:26:13,  1.71it/s]
Train steps ... :  30%|██▉       | 29589/100000 [8:26:05<11:26:29,  1.71it/s]
Train steps ... :  30%|██▉       | 29590/100000 [8:26:06<11:26:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29591/100000 [8:26:06<11:26:44,  1.71it/s]
Train steps ... :  30%|██▉       | 29592/100000 [8:26:07<11:25:57,  1.71it/s]
Train steps ... :  30%|██▉       | 29593/100000 [8:26:07<11:25:54,  1.71it/s]
Train steps ... :  30%|██▉       | 29594/100000 [8:26:08<11:25:26,  1.71it/s]
Train steps ... :  30%|██▉       | 29595/100000 [8:26:09<11:26:02,  1.71it/s]
Train steps ... :  30%|██▉       | 29596/100000 [8:26:09<11:26:10,  1.71it/s]
Train steps ... :  30%|██▉       | 29597/100000 [8:26:10<11:27:01,  1.71it/s]
Train steps ... :  30%|██▉       | 29598/100000 [8:26:10<11:27:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29599/100000 [8:26:11<11:27:26,  1.71it/s]
Train steps ... :  30%|██▉       | 29600/100000 [8:26:11<11:27:27,  1.71it/s]Step... (29600 / 100000 | Loss: 0.7726453542709351, Learning Rate: 7.075376884422111e-05)
+
                                                                             
Step... (29600 / 100000 | Loss: 1.1528148651123047, Learning Rate: 7.075376884422111e-05)
+
Train steps ... :  30%|██▉       | 29600/100000 [8:26:12<11:27:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29601/100000 [8:26:12<11:29:26,  1.70it/s]
Train steps ... :  30%|██▉       | 29602/100000 [8:26:13<11:27:55,  1.71it/s]
Train steps ... :  30%|██▉       | 29603/100000 [8:26:13<11:28:10,  1.70it/s]
Train steps ... :  30%|██▉       | 29604/100000 [8:26:14<11:34:52,  1.69it/s]
Train steps ... :  30%|██▉       | 29605/100000 [8:26:14<11:30:58,  1.70it/s]
Train steps ... :  30%|██▉       | 29606/100000 [8:26:15<11:31:21,  1.70it/s]
Train steps ... :  30%|██▉       | 29607/100000 [8:26:16<11:30:04,  1.70it/s]
Train steps ... :  30%|██▉       | 29608/100000 [8:26:16<11:30:16,  1.70it/s]
Train steps ... :  30%|██▉       | 29609/100000 [8:26:17<11:28:18,  1.70it/s]
Train steps ... :  30%|██▉       | 29610/100000 [8:26:17<11:26:57,  1.71it/s]
Train steps ... :  30%|██▉       | 29611/100000 [8:26:18<11:27:09,  1.71it/s]
Train steps ... :  30%|██▉       | 29612/100000 [8:26:19<11:26:26,  1.71it/s]
Train steps ... :  30%|██▉       | 29613/100000 [8:26:19<11:26:05,  1.71it/s]
Train steps ... :  30%|██▉       | 29614/100000 [8:26:20<11:26:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29615/100000 [8:26:20<11:27:06,  1.71it/s]
Train steps ... :  30%|██▉       | 29616/100000 [8:26:21<11:27:11,  1.71it/s]
Train steps ... :  30%|██▉       | 29617/100000 [8:26:21<11:26:21,  1.71it/s]
Train steps ... :  30%|██▉       | 29618/100000 [8:26:22<11:28:09,  1.70it/s]
Train steps ... :  30%|██▉       | 29619/100000 [8:26:23<11:26:15,  1.71it/s]
Train steps ... :  30%|██▉       | 29620/100000 [8:26:23<11:25:41,  1.71it/s]
Train steps ... :  30%|██▉       | 29621/100000 [8:26:24<11:26:09,  1.71it/s]
Train steps ... :  30%|██▉       | 29622/100000 [8:26:24<11:26:17,  1.71it/s]
Train steps ... :  30%|██▉       | 29623/100000 [8:26:25<11:27:26,  1.71it/s]
Train steps ... :  30%|██▉       | 29624/100000 [8:26:26<11:27:15,  1.71it/s]
Train steps ... :  30%|██▉       | 29625/100000 [8:26:26<11:27:41,  1.71it/s]Step... (29625 / 100000 | Loss: 1.007269263267517, Learning Rate: 7.07286432160804e-05)
+
                                                                             
Step... (29625 / 100000 | Loss: 0.9239040017127991, Learning Rate: 7.07286432160804e-05)
+
Train steps ... :  30%|██▉       | 29625/100000 [8:26:26<11:27:41,  1.71it/s]
Train steps ... :  30%|██▉       | 29626/100000 [8:26:27<11:28:46,  1.70it/s]
Train steps ... :  30%|██▉       | 29627/100000 [8:26:27<11:29:14,  1.70it/s]
Train steps ... :  30%|██▉       | 29628/100000 [8:26:28<11:27:48,  1.71it/s]
Train steps ... :  30%|██▉       | 29629/100000 [8:26:29<11:27:58,  1.70it/s]
Train steps ... :  30%|██▉       | 29630/100000 [8:26:29<11:27:56,  1.70it/s]
Train steps ... :  30%|██▉       | 29631/100000 [8:26:30<11:29:49,  1.70it/s]
Train steps ... :  30%|██▉       | 29632/100000 [8:26:30<11:27:40,  1.71it/s]
Train steps ... :  30%|██▉       | 29633/100000 [8:26:31<11:27:26,  1.71it/s]
Train steps ... :  30%|██▉       | 29634/100000 [8:26:31<11:27:43,  1.71it/s]
Train steps ... :  30%|██▉       | 29635/100000 [8:26:32<11:27:31,  1.71it/s]
Train steps ... :  30%|██▉       | 29636/100000 [8:26:33<11:28:35,  1.70it/s]
Train steps ... :  30%|██▉       | 29637/100000 [8:26:33<11:26:57,  1.71it/s]
Train steps ... :  30%|██▉       | 29638/100000 [8:26:34<11:27:16,  1.71it/s]
Train steps ... :  30%|██▉       | 29639/100000 [8:26:34<11:26:52,  1.71it/s]
Train steps ... :  30%|██▉       | 29640/100000 [8:26:35<11:27:20,  1.71it/s]
Train steps ... :  30%|██▉       | 29641/100000 [8:26:36<11:26:41,  1.71it/s]
Train steps ... :  30%|██▉       | 29642/100000 [8:26:36<11:27:50,  1.70it/s]
Train steps ... :  30%|██▉       | 29643/100000 [8:26:37<11:26:34,  1.71it/s]
Train steps ... :  30%|██▉       | 29644/100000 [8:26:37<11:28:02,  1.70it/s]
Train steps ... :  30%|██▉       | 29645/100000 [8:26:38<11:27:54,  1.70it/s]
Train steps ... :  30%|██▉       | 29646/100000 [8:26:38<11:27:17,  1.71it/s]
Train steps ... :  30%|██▉       | 29647/100000 [8:26:39<11:27:12,  1.71it/s]
Train steps ... :  30%|██▉       | 29648/100000 [8:26:40<11:27:22,  1.71it/s]
Train steps ... :  30%|██▉       | 29649/100000 [8:26:40<11:26:54,  1.71it/s]
Train steps ... :  30%|██▉       | 29650/100000 [8:26:41<11:26:01,  1.71it/s]Step... (29650 / 100000 | Loss: 1.1499426364898682, Learning Rate: 7.07035175879397e-05)
+
                                                                             
Step... (29650 / 100000 | Loss: 1.0576103925704956, Learning Rate: 7.07035175879397e-05)
+
Train steps ... :  30%|██▉       | 29650/100000 [8:26:41<11:26:01,  1.71it/s]
Train steps ... :  30%|██▉       | 29651/100000 [8:26:41<11:26:05,  1.71it/s]
Train steps ... :  30%|██▉       | 29652/100000 [8:26:42<11:25:22,  1.71it/s]
Train steps ... :  30%|██▉       | 29653/100000 [8:26:43<11:25:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29654/100000 [8:26:43<11:25:20,  1.71it/s]
Train steps ... :  30%|██▉       | 29655/100000 [8:26:44<11:26:13,  1.71it/s]
Train steps ... :  30%|██▉       | 29656/100000 [8:26:44<11:28:00,  1.70it/s]
Train steps ... :  30%|██▉       | 29657/100000 [8:26:45<11:26:52,  1.71it/s]
Train steps ... :  30%|██▉       | 29658/100000 [8:26:46<11:27:22,  1.71it/s]
Train steps ... :  30%|██▉       | 29659/100000 [8:26:46<11:26:30,  1.71it/s]
Train steps ... :  30%|██▉       | 29660/100000 [8:26:47<11:26:20,  1.71it/s]
Train steps ... :  30%|██▉       | 29661/100000 [8:26:47<11:25:30,  1.71it/s]
Train steps ... :  30%|██▉       | 29662/100000 [8:26:48<11:26:11,  1.71it/s]
Train steps ... :  30%|██▉       | 29663/100000 [8:26:48<11:26:25,  1.71it/s]
Train steps ... :  30%|██▉       | 29664/100000 [8:26:49<11:25:24,  1.71it/s]
Train steps ... :  30%|██▉       | 29665/100000 [8:26:50<11:27:21,  1.71it/s]
Train steps ... :  30%|██▉       | 29666/100000 [8:26:50<11:24:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29667/100000 [8:26:51<11:26:54,  1.71it/s]
Train steps ... :  30%|██▉       | 29668/100000 [8:26:51<11:25:46,  1.71it/s]
Train steps ... :  30%|██▉       | 29669/100000 [8:26:52<11:26:23,  1.71it/s]
Train steps ... :  30%|██▉       | 29670/100000 [8:26:53<11:27:02,  1.71it/s]
Train steps ... :  30%|██▉       | 29671/100000 [8:26:53<11:24:37,  1.71it/s]
Train steps ... :  30%|██▉       | 29672/100000 [8:26:54<11:25:21,  1.71it/s]
Train steps ... :  30%|██▉       | 29673/100000 [8:26:54<11:25:29,  1.71it/s]
Train steps ... :  30%|██▉       | 29674/100000 [8:26:55<11:26:18,  1.71it/s]
Train steps ... :  30%|██▉       | 29675/100000 [8:26:55<11:25:07,  1.71it/s]Step... (29675 / 100000 | Loss: 1.3930385112762451, Learning Rate: 7.0678391959799e-05)
+
                                                                             
Step... (29675 / 100000 | Loss: 1.1229667663574219, Learning Rate: 7.0678391959799e-05)
+
Train steps ... :  30%|██▉       | 29675/100000 [8:26:56<11:25:07,  1.71it/s]
Train steps ... :  30%|██▉       | 29676/100000 [8:26:56<11:26:06,  1.71it/s]
Train steps ... :  30%|██▉       | 29677/100000 [8:26:57<11:25:41,  1.71it/s]
Train steps ... :  30%|██▉       | 29678/100000 [8:26:57<11:26:44,  1.71it/s]
Train steps ... :  30%|██▉       | 29679/100000 [8:26:58<11:27:00,  1.71it/s]
Train steps ... :  30%|██▉       | 29680/100000 [8:26:58<11:26:19,  1.71it/s]
Train steps ... :  30%|██▉       | 29681/100000 [8:26:59<11:25:55,  1.71it/s]
Train steps ... :  30%|██▉       | 29682/100000 [8:27:00<11:27:24,  1.70it/s]
Train steps ... :  30%|██▉       | 29683/100000 [8:27:00<11:26:24,  1.71it/s]
Train steps ... :  30%|██▉       | 29684/100000 [8:27:01<11:26:44,  1.71it/s]
Train steps ... :  30%|██▉       | 29685/100000 [8:27:01<11:26:10,  1.71it/s]
Train steps ... :  30%|██▉       | 29686/100000 [8:27:02<11:26:11,  1.71it/s]
Train steps ... :  30%|██▉       | 29687/100000 [8:27:02<11:24:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29688/100000 [8:27:03<11:26:07,  1.71it/s]
Train steps ... :  30%|██▉       | 29689/100000 [8:27:04<11:26:37,  1.71it/s]
Train steps ... :  30%|██▉       | 29690/100000 [8:27:04<11:26:20,  1.71it/s]
Train steps ... :  30%|██▉       | 29691/100000 [8:27:05<11:27:38,  1.70it/s]
Train steps ... :  30%|██▉       | 29692/100000 [8:27:05<11:27:01,  1.71it/s]
Train steps ... :  30%|██▉       | 29693/100000 [8:27:06<11:26:49,  1.71it/s]
Train steps ... :  30%|██▉       | 29694/100000 [8:27:07<11:26:35,  1.71it/s]
Train steps ... :  30%|██▉       | 29695/100000 [8:27:07<11:26:05,  1.71it/s]
Train steps ... :  30%|██▉       | 29696/100000 [8:27:08<11:25:44,  1.71it/s]
Train steps ... :  30%|██▉       | 29697/100000 [8:27:08<11:25:37,  1.71it/s]
Train steps ... :  30%|██▉       | 29698/100000 [8:27:09<11:25:30,  1.71it/s]
Train steps ... :  30%|██▉       | 29699/100000 [8:27:10<11:25:02,  1.71it/s]
Train steps ... :  30%|██▉       | 29700/100000 [8:27:10<11:25:32,  1.71it/s]Step... (29700 / 100000 | Loss: 0.9793838262557983, Learning Rate: 7.06532663316583e-05)
+
                                                                             
Step... (29700 / 100000 | Loss: 0.914279580116272, Learning Rate: 7.06532663316583e-05)
+
Train steps ... :  30%|██▉       | 29700/100000 [8:27:10<11:25:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29701/100000 [8:27:11<11:25:59,  1.71it/s]
Train steps ... :  30%|██▉       | 29702/100000 [8:27:11<11:25:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29703/100000 [8:27:12<11:25:29,  1.71it/s]
Train steps ... :  30%|██▉       | 29704/100000 [8:27:12<11:24:46,  1.71it/s]
Train steps ... :  30%|██▉       | 29705/100000 [8:27:13<11:25:50,  1.71it/s]
Train steps ... :  30%|██▉       | 29706/100000 [8:27:14<11:24:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29707/100000 [8:27:14<11:25:13,  1.71it/s]
Train steps ... :  30%|██▉       | 29708/100000 [8:27:15<11:24:50,  1.71it/s]
Train steps ... :  30%|██▉       | 29709/100000 [8:27:15<11:24:52,  1.71it/s]
Train steps ... :  30%|██▉       | 29710/100000 [8:27:16<11:25:04,  1.71it/s]
Train steps ... :  30%|██▉       | 29711/100000 [8:27:17<11:25:15,  1.71it/s]
Train steps ... :  30%|██▉       | 29712/100000 [8:27:17<11:24:29,  1.71it/s]
Train steps ... :  30%|██▉       | 29713/100000 [8:27:18<11:25:10,  1.71it/s]
Train steps ... :  30%|██▉       | 29714/100000 [8:27:18<11:25:55,  1.71it/s]
Train steps ... :  30%|██▉       | 29715/100000 [8:27:19<11:26:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29716/100000 [8:27:19<11:26:34,  1.71it/s]
Train steps ... :  30%|██▉       | 29717/100000 [8:27:20<11:26:31,  1.71it/s]
Train steps ... :  30%|██▉       | 29718/100000 [8:27:21<11:27:15,  1.70it/s]
Train steps ... :  30%|██▉       | 29719/100000 [8:27:21<11:27:03,  1.70it/s]
Train steps ... :  30%|██▉       | 29720/100000 [8:27:22<11:27:57,  1.70it/s]
Train steps ... :  30%|██▉       | 29721/100000 [8:27:22<11:25:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29722/100000 [8:27:23<11:25:30,  1.71it/s]
Train steps ... :  30%|██▉       | 29723/100000 [8:27:24<11:26:00,  1.71it/s]
Train steps ... :  30%|██▉       | 29724/100000 [8:27:24<11:26:40,  1.71it/s]
Train steps ... :  30%|██▉       | 29725/100000 [8:27:25<11:26:56,  1.71it/s]Step... (29725 / 100000 | Loss: 1.0878348350524902, Learning Rate: 7.062814070351759e-05)
+
                                                                             
Step... (29725 / 100000 | Loss: 1.0580974817276, Learning Rate: 7.062814070351759e-05)
+
Train steps ... :  30%|██▉       | 29725/100000 [8:27:25<11:26:56,  1.71it/s]
Train steps ... :  30%|██▉       | 29726/100000 [8:27:25<11:27:29,  1.70it/s]
Train steps ... :  30%|██▉       | 29727/100000 [8:27:26<11:25:36,  1.71it/s]
Train steps ... :  30%|██▉       | 29728/100000 [8:27:26<11:26:36,  1.71it/s]
Train steps ... :  30%|██▉       | 29729/100000 [8:27:27<11:26:24,  1.71it/s]
Train steps ... :  30%|██▉       | 29730/100000 [8:27:28<11:25:42,  1.71it/s]
Train steps ... :  30%|██▉       | 29731/100000 [8:27:28<11:28:27,  1.70it/s]
Train steps ... :  30%|██▉       | 29732/100000 [8:27:29<11:26:53,  1.70it/s]
Train steps ... :  30%|██▉       | 29733/100000 [8:27:29<11:26:09,  1.71it/s]
Train steps ... :  30%|██▉       | 29734/100000 [8:27:30<11:26:31,  1.71it/s]
Train steps ... :  30%|██▉       | 29735/100000 [8:27:31<11:27:10,  1.70it/s]
Train steps ... :  30%|██▉       | 29736/100000 [8:27:31<11:27:22,  1.70it/s]
Train steps ... :  30%|██▉       | 29737/100000 [8:27:32<11:26:30,  1.71it/s]
Train steps ... :  30%|██▉       | 29738/100000 [8:27:32<11:26:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29739/100000 [8:27:33<11:27:36,  1.70it/s]
Train steps ... :  30%|██▉       | 29740/100000 [8:27:34<11:25:52,  1.71it/s]
Train steps ... :  30%|██▉       | 29741/100000 [8:27:34<11:26:51,  1.70it/s]
Train steps ... :  30%|██▉       | 29742/100000 [8:27:35<11:26:18,  1.71it/s]
Train steps ... :  30%|██▉       | 29743/100000 [8:27:35<11:26:47,  1.70it/s]
Train steps ... :  30%|██▉       | 29744/100000 [8:27:36<11:25:21,  1.71it/s]
Train steps ... :  30%|██▉       | 29745/100000 [8:27:36<11:25:33,  1.71it/s]
Train steps ... :  30%|██▉       | 29746/100000 [8:27:37<11:25:48,  1.71it/s]
Train steps ... :  30%|██▉       | 29747/100000 [8:27:38<11:25:48,  1.71it/s]
Train steps ... :  30%|██▉       | 29748/100000 [8:27:38<11:25:00,  1.71it/s]
Train steps ... :  30%|██▉       | 29749/100000 [8:27:39<11:25:17,  1.71it/s]
Train steps ... :  30%|██▉       | 29750/100000 [8:27:39<11:25:51,  1.71it/s]Step... (29750 / 100000 | Loss: 0.8181333541870117, Learning Rate: 7.060301507537689e-05)
+
                                                                             
Step... (29750 / 100000 | Loss: 1.2489036321640015, Learning Rate: 7.060301507537689e-05)
+
Train steps ... :  30%|██▉       | 29750/100000 [8:27:40<11:25:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29751/100000 [8:27:40<11:25:59,  1.71it/s]
Train steps ... :  30%|██▉       | 29752/100000 [8:27:41<11:26:00,  1.71it/s]
Train steps ... :  30%|██▉       | 29753/100000 [8:27:41<11:25:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29754/100000 [8:27:42<11:24:57,  1.71it/s]
Train steps ... :  30%|██▉       | 29755/100000 [8:27:42<11:24:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29756/100000 [8:27:43<11:26:08,  1.71it/s]
Train steps ... :  30%|██▉       | 29757/100000 [8:27:43<11:25:35,  1.71it/s]
Train steps ... :  30%|██▉       | 29758/100000 [8:27:44<11:26:40,  1.70it/s]
Train steps ... :  30%|██▉       | 29759/100000 [8:27:45<11:25:15,  1.71it/s]
Train steps ... :  30%|██▉       | 29760/100000 [8:27:45<11:26:08,  1.71it/s]
Train steps ... :  30%|██▉       | 29761/100000 [8:27:46<11:25:52,  1.71it/s]
Train steps ... :  30%|██▉       | 29762/100000 [8:27:46<11:25:55,  1.71it/s]
Train steps ... :  30%|██▉       | 29763/100000 [8:27:47<11:26:45,  1.70it/s]
Train steps ... :  30%|██▉       | 29764/100000 [8:27:48<11:25:40,  1.71it/s]
Train steps ... :  30%|██▉       | 29765/100000 [8:27:48<11:25:21,  1.71it/s]
Train steps ... :  30%|██▉       | 29766/100000 [8:27:49<11:26:14,  1.71it/s]
Train steps ... :  30%|██▉       | 29767/100000 [8:27:49<11:25:38,  1.71it/s]
Train steps ... :  30%|██▉       | 29768/100000 [8:27:50<11:25:48,  1.71it/s]
Train steps ... :  30%|██▉       | 29769/100000 [8:27:51<11:26:05,  1.71it/s]
Train steps ... :  30%|██▉       | 29770/100000 [8:27:51<11:25:19,  1.71it/s]
Train steps ... :  30%|██▉       | 29771/100000 [8:27:52<11:25:24,  1.71it/s]
Train steps ... :  30%|██▉       | 29772/100000 [8:27:52<11:26:02,  1.71it/s]
Train steps ... :  30%|██▉       | 29773/100000 [8:27:53<11:25:13,  1.71it/s]
Train steps ... :  30%|██▉       | 29774/100000 [8:27:53<11:24:46,  1.71it/s]
Train steps ... :  30%|██▉       | 29775/100000 [8:27:54<11:25:29,  1.71it/s]Step... (29775 / 100000 | Loss: 0.9309499859809875, Learning Rate: 7.057788944723619e-05)
+
                                                                             
Step... (29775 / 100000 | Loss: 0.8330235481262207, Learning Rate: 7.057788944723619e-05)
+
Train steps ... :  30%|██▉       | 29775/100000 [8:27:54<11:25:29,  1.71it/s]
Train steps ... :  30%|██▉       | 29776/100000 [8:27:55<11:24:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29777/100000 [8:27:55<11:25:49,  1.71it/s]
Train steps ... :  30%|██▉       | 29778/100000 [8:27:56<11:25:21,  1.71it/s]
Train steps ... :  30%|██▉       | 29779/100000 [8:27:56<11:25:00,  1.71it/s]
Train steps ... :  30%|██▉       | 29780/100000 [8:27:57<11:24:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29781/100000 [8:27:58<11:24:42,  1.71it/s]
Train steps ... :  30%|██▉       | 29782/100000 [8:27:58<11:26:57,  1.70it/s]
Train steps ... :  30%|██▉       | 29783/100000 [8:27:59<11:26:03,  1.71it/s]
Train steps ... :  30%|██▉       | 29784/100000 [8:27:59<11:24:34,  1.71it/s]
Train steps ... :  30%|██▉       | 29785/100000 [8:28:00<11:23:37,  1.71it/s]
Train steps ... :  30%|██▉       | 29786/100000 [8:28:00<11:23:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29787/100000 [8:28:01<11:24:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29788/100000 [8:28:02<11:25:29,  1.71it/s]
Train steps ... :  30%|██▉       | 29789/100000 [8:28:02<11:24:11,  1.71it/s]
Train steps ... :  30%|██▉       | 29790/100000 [8:28:03<11:25:40,  1.71it/s]
Train steps ... :  30%|██▉       | 29791/100000 [8:28:03<11:25:36,  1.71it/s]
Train steps ... :  30%|██▉       | 29792/100000 [8:28:04<11:25:09,  1.71it/s]
Train steps ... :  30%|██▉       | 29793/100000 [8:28:05<11:25:21,  1.71it/s]
Train steps ... :  30%|██▉       | 29794/100000 [8:28:05<11:26:30,  1.70it/s]
Train steps ... :  30%|██▉       | 29795/100000 [8:28:06<11:24:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29796/100000 [8:28:06<11:24:15,  1.71it/s]
Train steps ... :  30%|██▉       | 29797/100000 [8:28:07<11:25:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29798/100000 [8:28:07<11:26:37,  1.70it/s]
Train steps ... :  30%|██▉       | 29799/100000 [8:28:08<11:27:10,  1.70it/s]
Train steps ... :  30%|██▉       | 29800/100000 [8:28:09<11:27:30,  1.70it/s]Step... (29800 / 100000 | Loss: 1.0564301013946533, Learning Rate: 7.055276381909548e-05)
+
                                                                             
Step... (29800 / 100000 | Loss: 0.7323832511901855, Learning Rate: 7.055276381909548e-05)
+
Train steps ... :  30%|██▉       | 29800/100000 [8:28:09<11:27:30,  1.70it/s]
Train steps ... :  30%|██▉       | 29801/100000 [8:28:09<11:26:36,  1.70it/s]
Train steps ... :  30%|██▉       | 29802/100000 [8:28:10<11:25:05,  1.71it/s]
Train steps ... :  30%|██▉       | 29803/100000 [8:28:10<11:24:57,  1.71it/s]
Train steps ... :  30%|██▉       | 29804/100000 [8:28:11<11:24:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29805/100000 [8:28:12<11:26:51,  1.70it/s]
Train steps ... :  30%|██▉       | 29806/100000 [8:28:12<11:24:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29807/100000 [8:28:13<11:24:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29808/100000 [8:28:13<11:23:54,  1.71it/s]
Train steps ... :  30%|██▉       | 29809/100000 [8:28:14<11:23:56,  1.71it/s]
Train steps ... :  30%|██▉       | 29810/100000 [8:28:15<11:23:41,  1.71it/s]
Train steps ... :  30%|██▉       | 29811/100000 [8:28:15<11:23:29,  1.71it/s]
Train steps ... :  30%|██▉       | 29812/100000 [8:28:16<11:23:08,  1.71it/s]
Train steps ... :  30%|██▉       | 29813/100000 [8:28:16<11:23:35,  1.71it/s]
Train steps ... :  30%|██▉       | 29814/100000 [8:28:17<11:24:11,  1.71it/s]
Train steps ... :  30%|██▉       | 29815/100000 [8:28:17<11:24:48,  1.71it/s]
Train steps ... :  30%|██▉       | 29816/100000 [8:28:18<11:27:15,  1.70it/s]
Train steps ... :  30%|██▉       | 29817/100000 [8:28:19<11:26:02,  1.71it/s]
Train steps ... :  30%|██▉       | 29818/100000 [8:28:19<11:26:07,  1.70it/s]
Train steps ... :  30%|██▉       | 29819/100000 [8:28:20<11:25:59,  1.71it/s]
Train steps ... :  30%|██▉       | 29820/100000 [8:28:20<11:26:23,  1.70it/s]
Train steps ... :  30%|██▉       | 29821/100000 [8:28:21<11:25:12,  1.71it/s]
Train steps ... :  30%|██▉       | 29822/100000 [8:28:22<11:25:56,  1.71it/s]
Train steps ... :  30%|██▉       | 29823/100000 [8:28:22<11:27:52,  1.70it/s]
Train steps ... :  30%|██▉       | 29824/100000 [8:28:23<11:26:03,  1.70it/s]
Train steps ... :  30%|██▉       | 29825/100000 [8:28:23<11:25:42,  1.71it/s]Step... (29825 / 100000 | Loss: 0.9339151978492737, Learning Rate: 7.052763819095478e-05)
+
                                                                             
Step... (29825 / 100000 | Loss: 0.773242712020874, Learning Rate: 7.052763819095478e-05)
+
Train steps ... :  30%|██▉       | 29825/100000 [8:28:24<11:25:42,  1.71it/s]
Train steps ... :  30%|██▉       | 29826/100000 [8:28:24<11:26:50,  1.70it/s]
Train steps ... :  30%|██▉       | 29827/100000 [8:28:24<11:26:15,  1.70it/s]
Train steps ... :  30%|██▉       | 29828/100000 [8:28:25<11:26:04,  1.70it/s]
Train steps ... :  30%|██▉       | 29829/100000 [8:28:26<11:25:42,  1.71it/s]
Train steps ... :  30%|██▉       | 29830/100000 [8:28:26<11:25:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29831/100000 [8:28:27<11:24:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29832/100000 [8:28:27<11:24:45,  1.71it/s]
Train steps ... :  30%|██▉       | 29833/100000 [8:28:28<11:26:08,  1.70it/s]
Train steps ... :  30%|██▉       | 29834/100000 [8:28:29<11:25:35,  1.71it/s]
Train steps ... :  30%|██▉       | 29835/100000 [8:28:29<11:25:59,  1.70it/s]
Train steps ... :  30%|██▉       | 29836/100000 [8:28:30<11:24:19,  1.71it/s]
Train steps ... :  30%|██▉       | 29837/100000 [8:28:30<11:24:47,  1.71it/s]
Train steps ... :  30%|██▉       | 29838/100000 [8:28:31<11:26:23,  1.70it/s]
Train steps ... :  30%|██▉       | 29839/100000 [8:28:32<11:28:44,  1.70it/s]
Train steps ... :  30%|██▉       | 29840/100000 [8:28:32<11:27:08,  1.70it/s]
Train steps ... :  30%|██▉       | 29841/100000 [8:28:33<11:24:59,  1.71it/s]
Train steps ... :  30%|██▉       | 29842/100000 [8:28:33<11:27:32,  1.70it/s]
Train steps ... :  30%|██▉       | 29843/100000 [8:28:34<11:23:49,  1.71it/s]
Train steps ... :  30%|██▉       | 29844/100000 [8:28:34<11:25:50,  1.70it/s]
Train steps ... :  30%|██▉       | 29845/100000 [8:28:35<11:24:42,  1.71it/s]
Train steps ... :  30%|██▉       | 29846/100000 [8:28:36<11:26:22,  1.70it/s]
Train steps ... :  30%|██▉       | 29847/100000 [8:28:36<11:26:00,  1.70it/s]
Train steps ... :  30%|██▉       | 29848/100000 [8:28:37<11:25:43,  1.71it/s]
Train steps ... :  30%|██▉       | 29849/100000 [8:28:37<11:26:36,  1.70it/s]
Train steps ... :  30%|██▉       | 29850/100000 [8:28:38<11:29:52,  1.69it/s]Step... (29850 / 100000 | Loss: 1.1252447366714478, Learning Rate: 7.050251256281408e-05)
+
                                                                             
Step... (29850 / 100000 | Loss: 1.0581676959991455, Learning Rate: 7.050251256281408e-05)
+
Train steps ... :  30%|██▉       | 29850/100000 [8:28:38<11:29:52,  1.69it/s]
Train steps ... :  30%|██▉       | 29851/100000 [8:28:39<11:27:07,  1.70it/s]
Train steps ... :  30%|██▉       | 29852/100000 [8:28:39<11:27:33,  1.70it/s]
Train steps ... :  30%|██▉       | 29853/100000 [8:28:40<11:25:28,  1.71it/s]
Train steps ... :  30%|██▉       | 29854/100000 [8:28:40<11:25:38,  1.71it/s]
Train steps ... :  30%|██▉       | 29855/100000 [8:28:41<11:26:36,  1.70it/s]
Train steps ... :  30%|██▉       | 29856/100000 [8:28:41<11:25:02,  1.71it/s]
Train steps ... :  30%|██▉       | 29857/100000 [8:28:42<11:26:01,  1.70it/s]
Train steps ... :  30%|██▉       | 29858/100000 [8:28:43<11:25:08,  1.71it/s]
Train steps ... :  30%|██▉       | 29859/100000 [8:28:43<11:25:25,  1.71it/s]
Train steps ... :  30%|██▉       | 29860/100000 [8:28:44<11:25:22,  1.71it/s]
Train steps ... :  30%|██▉       | 29861/100000 [8:28:44<11:26:38,  1.70it/s]
Train steps ... :  30%|██▉       | 29862/100000 [8:28:45<11:25:41,  1.70it/s]
Train steps ... :  30%|██▉       | 29863/100000 [8:28:46<11:25:33,  1.71it/s]
Train steps ... :  30%|██▉       | 29864/100000 [8:28:46<11:26:16,  1.70it/s]
Train steps ... :  30%|██▉       | 29865/100000 [8:28:47<11:26:57,  1.70it/s]
Train steps ... :  30%|██▉       | 29866/100000 [8:28:47<11:24:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29867/100000 [8:28:48<11:24:58,  1.71it/s]
Train steps ... :  30%|██▉       | 29868/100000 [8:28:49<11:25:11,  1.71it/s]
Train steps ... :  30%|██▉       | 29869/100000 [8:28:49<11:24:50,  1.71it/s]
Train steps ... :  30%|██▉       | 29870/100000 [8:28:50<11:25:02,  1.71it/s]
Train steps ... :  30%|██▉       | 29871/100000 [8:28:50<11:25:10,  1.71it/s]
Train steps ... :  30%|██▉       | 29872/100000 [8:28:51<11:24:45,  1.71it/s]
Train steps ... :  30%|██▉       | 29873/100000 [8:28:51<11:24:55,  1.71it/s]
Train steps ... :  30%|██▉       | 29874/100000 [8:28:52<11:23:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29875/100000 [8:28:53<11:23:27,  1.71it/s]Step... (29875 / 100000 | Loss: 1.2748315334320068, Learning Rate: 7.047738693467337e-05)
+
                                                                             
Step... (29875 / 100000 | Loss: 0.9265941977500916, Learning Rate: 7.047738693467337e-05)
+
Train steps ... :  30%|██▉       | 29875/100000 [8:28:53<11:23:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29876/100000 [8:28:53<11:24:38,  1.71it/s]
Train steps ... :  30%|██▉       | 29877/100000 [8:28:54<11:24:05,  1.71it/s]
Train steps ... :  30%|██▉       | 29878/100000 [8:28:54<11:23:14,  1.71it/s]
Train steps ... :  30%|██▉       | 29879/100000 [8:28:55<11:24:11,  1.71it/s]
Train steps ... :  30%|██▉       | 29880/100000 [8:28:56<11:24:05,  1.71it/s]
Train steps ... :  30%|██▉       | 29881/100000 [8:28:56<11:24:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29882/100000 [8:28:57<11:26:58,  1.70it/s]
Train steps ... :  30%|██▉       | 29883/100000 [8:28:57<11:25:56,  1.70it/s]
Train steps ... :  30%|██▉       | 29884/100000 [8:28:58<11:23:49,  1.71it/s]
Train steps ... :  30%|██▉       | 29885/100000 [8:28:58<11:23:50,  1.71it/s]
Train steps ... :  30%|██▉       | 29886/100000 [8:28:59<11:23:56,  1.71it/s]
Train steps ... :  30%|██▉       | 29887/100000 [8:29:00<11:27:32,  1.70it/s]
Train steps ... :  30%|██▉       | 29888/100000 [8:29:00<11:26:25,  1.70it/s]
Train steps ... :  30%|██▉       | 29889/100000 [8:29:01<11:26:37,  1.70it/s]
Train steps ... :  30%|██▉       | 29890/100000 [8:29:01<11:25:22,  1.70it/s]
Train steps ... :  30%|██▉       | 29891/100000 [8:29:02<11:25:14,  1.71it/s]
Train steps ... :  30%|██▉       | 29892/100000 [8:29:03<11:25:05,  1.71it/s]
Train steps ... :  30%|██▉       | 29893/100000 [8:29:03<11:25:15,  1.71it/s]
Train steps ... :  30%|██▉       | 29894/100000 [8:29:04<11:26:29,  1.70it/s]
Train steps ... :  30%|██▉       | 29895/100000 [8:29:04<11:25:42,  1.70it/s]
Train steps ... :  30%|██▉       | 29896/100000 [8:29:05<11:24:23,  1.71it/s]
Train steps ... :  30%|██▉       | 29897/100000 [8:29:06<11:23:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29898/100000 [8:29:06<11:23:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29899/100000 [8:29:07<11:23:18,  1.71it/s]
Train steps ... :  30%|██▉       | 29900/100000 [8:29:07<11:23:58,  1.71it/s]Step... (29900 / 100000 | Loss: 0.978723406791687, Learning Rate: 7.045226130653267e-05)
+
                                                                             
Step... (29900 / 100000 | Loss: 1.2160602807998657, Learning Rate: 7.045226130653267e-05)
+
Train steps ... :  30%|██▉       | 29900/100000 [8:29:08<11:23:58,  1.71it/s]
Train steps ... :  30%|██▉       | 29901/100000 [8:29:08<11:23:35,  1.71it/s]
Train steps ... :  30%|██▉       | 29902/100000 [8:29:08<11:23:17,  1.71it/s]
Train steps ... :  30%|██▉       | 29903/100000 [8:29:09<11:23:25,  1.71it/s]
Train steps ... :  30%|██▉       | 29904/100000 [8:29:10<11:23:09,  1.71it/s]
Train steps ... :  30%|██▉       | 29905/100000 [8:29:10<11:22:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29906/100000 [8:29:11<11:23:58,  1.71it/s]
Train steps ... :  30%|██▉       | 29907/100000 [8:29:11<11:23:37,  1.71it/s]
Train steps ... :  30%|██▉       | 29908/100000 [8:29:12<11:23:04,  1.71it/s]
Train steps ... :  30%|██▉       | 29909/100000 [8:29:13<11:23:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29910/100000 [8:29:13<11:22:37,  1.71it/s]
Train steps ... :  30%|██▉       | 29911/100000 [8:29:14<11:24:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29912/100000 [8:29:14<11:23:05,  1.71it/s]
Train steps ... :  30%|██▉       | 29913/100000 [8:29:15<11:22:55,  1.71it/s]
Train steps ... :  30%|██▉       | 29914/100000 [8:29:15<11:24:55,  1.71it/s]
Train steps ... :  30%|██▉       | 29915/100000 [8:29:16<11:22:59,  1.71it/s]
Train steps ... :  30%|██▉       | 29916/100000 [8:29:17<11:23:36,  1.71it/s]
Train steps ... :  30%|██▉       | 29917/100000 [8:29:17<11:24:46,  1.71it/s]
Train steps ... :  30%|██▉       | 29918/100000 [8:29:18<11:23:03,  1.71it/s]
Train steps ... :  30%|██▉       | 29919/100000 [8:29:18<11:23:43,  1.71it/s]
Train steps ... :  30%|██▉       | 29920/100000 [8:29:19<11:24:26,  1.71it/s]
Train steps ... :  30%|██▉       | 29921/100000 [8:29:20<11:24:25,  1.71it/s]
Train steps ... :  30%|██▉       | 29922/100000 [8:29:20<11:23:49,  1.71it/s]
Train steps ... :  30%|██▉       | 29923/100000 [8:29:21<11:24:46,  1.71it/s]
Train steps ... :  30%|██▉       | 29924/100000 [8:29:21<11:24:36,  1.71it/s]
Train steps ... :  30%|██▉       | 29925/100000 [8:29:22<11:24:53,  1.71it/s]Step... (29925 / 100000 | Loss: 0.8477841019630432, Learning Rate: 7.042713567839196e-05)
+
                                                                             
Step... (29925 / 100000 | Loss: 0.8590049743652344, Learning Rate: 7.042713567839196e-05)
+
Train steps ... :  30%|██▉       | 29925/100000 [8:29:22<11:24:53,  1.71it/s]
Train steps ... :  30%|██▉       | 29926/100000 [8:29:23<11:25:44,  1.70it/s]
Train steps ... :  30%|██▉       | 29927/100000 [8:29:23<11:24:33,  1.71it/s]
Train steps ... :  30%|██▉       | 29928/100000 [8:29:24<11:24:49,  1.71it/s]
Train steps ... :  30%|██▉       | 29929/100000 [8:29:24<11:23:22,  1.71it/s]
Train steps ... :  30%|██▉       | 29930/100000 [8:29:25<11:26:15,  1.70it/s]
Train steps ... :  30%|██▉       | 29931/100000 [8:29:25<11:28:08,  1.70it/s]
Train steps ... :  30%|██▉       | 29932/100000 [8:29:26<11:26:35,  1.70it/s]
Train steps ... :  30%|██▉       | 29933/100000 [8:29:27<11:25:02,  1.70it/s]
Train steps ... :  30%|██▉       | 29934/100000 [8:29:27<11:25:25,  1.70it/s]
Train steps ... :  30%|██▉       | 29935/100000 [8:29:28<11:24:14,  1.71it/s]
Train steps ... :  30%|██▉       | 29936/100000 [8:29:28<11:23:56,  1.71it/s]
Train steps ... :  30%|██▉       | 29937/100000 [8:29:29<11:24:18,  1.71it/s]
Train steps ... :  30%|██▉       | 29938/100000 [8:29:30<11:23:41,  1.71it/s]
Train steps ... :  30%|██▉       | 29939/100000 [8:29:30<11:24:30,  1.71it/s]
Train steps ... :  30%|██▉       | 29940/100000 [8:29:31<11:24:03,  1.71it/s]
Train steps ... :  30%|██▉       | 29941/100000 [8:29:31<11:23:45,  1.71it/s]
Train steps ... :  30%|██▉       | 29942/100000 [8:29:32<11:24:15,  1.71it/s]
Train steps ... :  30%|██▉       | 29943/100000 [8:29:32<11:23:40,  1.71it/s]
Train steps ... :  30%|██▉       | 29944/100000 [8:29:33<11:24:26,  1.71it/s]
Train steps ... :  30%|██▉       | 29945/100000 [8:29:34<11:23:51,  1.71it/s]
Train steps ... :  30%|██▉       | 29946/100000 [8:29:34<11:23:57,  1.71it/s]
Train steps ... :  30%|██▉       | 29947/100000 [8:29:35<11:23:35,  1.71it/s]
Train steps ... :  30%|██▉       | 29948/100000 [8:29:35<11:25:41,  1.70it/s]
Train steps ... :  30%|██▉       | 29949/100000 [8:29:36<11:27:33,  1.70it/s]
Train steps ... :  30%|██▉       | 29950/100000 [8:29:37<11:27:05,  1.70it/s]Step... (29950 / 100000 | Loss: 1.3313050270080566, Learning Rate: 7.040201005025126e-05)
+
                                                                             
Step... (29950 / 100000 | Loss: 0.8931991457939148, Learning Rate: 7.040201005025126e-05)
+
Train steps ... :  30%|██▉       | 29950/100000 [8:29:37<11:27:05,  1.70it/s]
Train steps ... :  30%|██▉       | 29951/100000 [8:29:37<11:28:00,  1.70it/s]
Train steps ... :  30%|██▉       | 29952/100000 [8:29:38<11:24:57,  1.70it/s]
Train steps ... :  30%|██▉       | 29953/100000 [8:29:38<11:24:15,  1.71it/s]
Train steps ... :  30%|██▉       | 29954/100000 [8:29:39<11:24:10,  1.71it/s]
Train steps ... :  30%|██▉       | 29955/100000 [8:29:40<11:23:37,  1.71it/s]
Train steps ... :  30%|██▉       | 29956/100000 [8:29:40<11:23:43,  1.71it/s]
Train steps ... :  30%|██▉       | 29957/100000 [8:29:41<11:23:41,  1.71it/s]
Train steps ... :  30%|██▉       | 29958/100000 [8:29:41<11:26:11,  1.70it/s]
Train steps ... :  30%|██▉       | 29959/100000 [8:29:42<11:23:54,  1.71it/s]
Train steps ... :  30%|██▉       | 29960/100000 [8:29:42<11:24:04,  1.71it/s]
Train steps ... :  30%|██▉       | 29961/100000 [8:29:43<11:26:05,  1.70it/s]
Train steps ... :  30%|██▉       | 29962/100000 [8:29:44<11:24:16,  1.71it/s]
Train steps ... :  30%|██▉       | 29963/100000 [8:29:44<11:25:59,  1.70it/s]
Train steps ... :  30%|██▉       | 29964/100000 [8:29:45<11:25:10,  1.70it/s]
Train steps ... :  30%|██▉       | 29965/100000 [8:29:45<11:26:11,  1.70it/s]
Train steps ... :  30%|██▉       | 29966/100000 [8:29:46<11:24:49,  1.70it/s]
Train steps ... :  30%|██▉       | 29967/100000 [8:29:47<11:24:13,  1.71it/s]
Train steps ... :  30%|██▉       | 29968/100000 [8:29:47<11:24:41,  1.70it/s]
Train steps ... :  30%|██▉       | 29969/100000 [8:29:48<11:24:27,  1.71it/s]
Train steps ... :  30%|██▉       | 29970/100000 [8:29:48<11:23:07,  1.71it/s]
Train steps ... :  30%|██▉       | 29971/100000 [8:29:49<11:24:32,  1.71it/s]
Train steps ... :  30%|██▉       | 29972/100000 [8:29:49<11:24:22,  1.71it/s]
Train steps ... :  30%|██▉       | 29973/100000 [8:29:50<11:24:50,  1.70it/s]
Train steps ... :  30%|██▉       | 29974/100000 [8:29:51<11:23:41,  1.71it/s]
Train steps ... :  30%|██▉       | 29975/100000 [8:29:51<11:23:09,  1.71it/s]Step... (29975 / 100000 | Loss: 0.9237031936645508, Learning Rate: 7.037688442211056e-05)
+
                                                                             
Step... (29975 / 100000 | Loss: 1.0994155406951904, Learning Rate: 7.037688442211056e-05)
+
Train steps ... :  30%|██▉       | 29975/100000 [8:29:52<11:23:09,  1.71it/s]
Train steps ... :  30%|██▉       | 29976/100000 [8:29:52<11:24:36,  1.70it/s]
Train steps ... :  30%|██▉       | 29977/100000 [8:29:52<11:23:38,  1.71it/s]
Train steps ... :  30%|██▉       | 29978/100000 [8:29:53<11:24:45,  1.70it/s]
Train steps ... :  30%|██▉       | 29979/100000 [8:29:54<11:24:13,  1.71it/s]
Train steps ... :  30%|██▉       | 29980/100000 [8:29:54<11:22:34,  1.71it/s]
Train steps ... :  30%|██▉       | 29981/100000 [8:29:55<11:23:55,  1.71it/s]
Train steps ... :  30%|██▉       | 29982/100000 [8:29:55<11:21:49,  1.71it/s]
Train steps ... :  30%|██▉       | 29983/100000 [8:29:56<11:21:48,  1.71it/s]
Train steps ... :  30%|██▉       | 29984/100000 [8:29:57<11:22:21,  1.71it/s]
Train steps ... :  30%|██▉       | 29985/100000 [8:29:57<11:22:22,  1.71it/s]
Train steps ... :  30%|██▉       | 29986/100000 [8:29:58<11:21:46,  1.71it/s]
Train steps ... :  30%|██▉       | 29987/100000 [8:29:58<11:22:45,  1.71it/s]
Train steps ... :  30%|██▉       | 29988/100000 [8:29:59<11:22:49,  1.71it/s]
Train steps ... :  30%|██▉       | 29989/100000 [8:29:59<11:23:01,  1.71it/s]
Train steps ... :  30%|██▉       | 29990/100000 [8:30:00<11:23:31,  1.71it/s]
Train steps ... :  30%|██▉       | 29991/100000 [8:30:01<11:23:58,  1.71it/s]
Train steps ... :  30%|██▉       | 29992/100000 [8:30:01<11:25:16,  1.70it/s]
Train steps ... :  30%|██▉       | 29993/100000 [8:30:02<11:27:49,  1.70it/s]
Train steps ... :  30%|██▉       | 29994/100000 [8:30:02<11:24:33,  1.70it/s]
Train steps ... :  30%|██▉       | 29995/100000 [8:30:03<11:24:45,  1.70it/s]
Train steps ... :  30%|██▉       | 29996/100000 [8:30:04<11:24:59,  1.70it/s]
Train steps ... :  30%|██▉       | 29997/100000 [8:30:04<11:23:37,  1.71it/s]
Train steps ... :  30%|██▉       | 29998/100000 [8:30:05<11:26:58,  1.70it/s]
Train steps ... :  30%|██▉       | 29999/100000 [8:30:05<11:28:07,  1.70it/s]
Train steps ... :  30%|███       | 30000/100000 [8:30:06<11:26:52,  1.70it/s]Step... (30000 / 100000 | Loss: 0.7693487405776978, Learning Rate: 7.035175879396985e-05)
+
                                                                             
Step... (30000 / 100000 | Loss: 1.0223495960235596, Learning Rate: 7.035175879396985e-05)
+
Train steps ... :  30%|███       | 30000/100000 [8:30:06<11:26:52,  1.70it/s]06/18/2024 00:24:33 - INFO - accelerate.accelerator - Saving current state to ./checkpoint-30000-epoch-1
+06/18/2024 00:24:33 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/18/2024 00:24:37 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-30000-epoch-1/model.safetensors
+06/18/2024 00:24:37 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/18/2024 00:24:40 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-30000-epoch-1/model_1.safetensors
+06/18/2024 00:24:41 - INFO - accelerate.checkpointing - Optimizer state saved in checkpoint-30000-epoch-1/optimizer.bin
+06/18/2024 00:24:41 - INFO - accelerate.checkpointing - Scheduler state saved in checkpoint-30000-epoch-1/scheduler.bin
+06/18/2024 00:24:41 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in checkpoint-30000-epoch-1/sampler.bin
+06/18/2024 00:24:41 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in checkpoint-30000-epoch-1/sampler_1.bin
+06/18/2024 00:24:41 - INFO - accelerate.checkpointing - Sampler state for dataloader 2 saved in checkpoint-30000-epoch-1/sampler_2.bin
+06/18/2024 00:24:41 - INFO - accelerate.checkpointing - Sampler state for dataloader 3 saved in checkpoint-30000-epoch-1/sampler_3.bin
+06/18/2024 00:24:41 - INFO - accelerate.checkpointing - Sampler state for dataloader 4 saved in checkpoint-30000-epoch-1/sampler_4.bin
+06/18/2024 00:24:41 - INFO - accelerate.checkpointing - Sampler state for dataloader 5 saved in checkpoint-30000-epoch-1/sampler_5.bin
+06/18/2024 00:24:41 - INFO - accelerate.checkpointing - Sampler state for dataloader 6 saved in checkpoint-30000-epoch-1/sampler_6.bin
+06/18/2024 00:24:41 - INFO - accelerate.checkpointing - Random states saved in checkpoint-30000-epoch-1/random_states_0.pkl
+06/18/2024 00:24:41 - INFO - __main__ - Deleting older checkpoint [checkpoint-5000-epoch-0] due to args.save_total_limit
+
+
  0%|          | 0/5 [00:00<?, ?it/s]
+
 20%|██        | 1/5 [01:46<07:04, 106.19s/it]
+
 40%|████      | 2/5 [02:20<03:12, 64.18s/it] 
+
 60%|██████    | 3/5 [02:21<01:10, 35.19s/it]
+
 80%|████████  | 4/5 [02:22<00:21, 21.61s/it]
+
100%|██████████| 5/5 [02:23<00:00, 14.05s/it]
100%|██████████| 5/5 [02:23<00:00, 28.62s/it]