diff --git "a/train.log" "b/train.log"
--- "a/train.log"
+++ "b/train.log"
@@ -40995,3 +40995,4238 @@ Eval results for step (45000 / 100000 | Eval Loss: 1.0432617664337158 | Eval wer
 
 60%|██████    | 3/5 [02:19<01:09, 34.52s/it]
 
 80%|████████  | 4/5 [02:19<00:21, 21.13s/it]
 
100%|██████████| 5/5 [02:20<00:00, 13.70s/it]
100%|██████████| 5/5 [02:20<00:00, 28.07s/it]
+
+
+
Evaluating eval...:   0%|          | 0/1900 [00:00<?, ?it/s]
+
+
Evaluating eval...:   0%|          | 1/1900 [00:03<1:54:41,  3.62s/it]
+
+
Evaluating eval...:   0%|          | 2/1900 [00:04<1:10:46,  2.24s/it]
+
+
Evaluating eval...:   0%|          | 3/1900 [00:06<56:24,  1.78s/it]  
+
+
Evaluating eval...:   0%|          | 4/1900 [00:07<49:46,  1.57s/it]
+
+
Evaluating eval...:   0%|          | 5/1900 [00:08<45:51,  1.45s/it]
+
+
Evaluating eval...:   0%|          | 6/1900 [00:09<42:44,  1.35s/it]
+
+
Evaluating eval...:   0%|          | 7/1900 [00:10<41:01,  1.30s/it]
+
+
Evaluating eval...:   0%|          | 8/1900 [00:12<39:43,  1.26s/it]
+
+
Evaluating eval...:   0%|          | 9/1900 [00:13<38:45,  1.23s/it]
+
+
Evaluating eval...:   1%|          | 10/1900 [00:14<38:32,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 11/1900 [00:15<39:09,  1.24s/it]
+
+
Evaluating eval...:   1%|          | 12/1900 [00:17<38:43,  1.23s/it]
+
+
Evaluating eval...:   1%|          | 13/1900 [00:18<38:46,  1.23s/it]
+
+
Evaluating eval...:   1%|          | 14/1900 [00:19<38:10,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 15/1900 [00:20<37:57,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 16/1900 [00:21<37:36,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 17/1900 [00:23<37:43,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 18/1900 [00:24<37:47,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 19/1900 [00:25<37:08,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 20/1900 [00:26<37:18,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 21/1900 [00:27<37:40,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 22/1900 [00:28<37:41,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 23/1900 [00:30<37:08,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 24/1900 [00:31<37:15,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 25/1900 [00:32<36:43,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 26/1900 [00:33<36:27,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 27/1900 [00:34<37:18,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 28/1900 [00:36<37:17,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 29/1900 [00:37<37:02,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 30/1900 [00:38<37:02,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 31/1900 [00:39<36:49,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 32/1900 [00:40<36:58,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 33/1900 [00:42<37:05,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 34/1900 [00:43<37:45,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 35/1900 [00:44<38:06,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 36/1900 [00:45<38:22,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 37/1900 [00:47<38:05,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 38/1900 [00:48<37:41,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 39/1900 [00:49<37:25,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 40/1900 [00:50<37:25,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 41/1900 [00:51<37:10,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 42/1900 [00:52<37:27,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 43/1900 [00:54<37:16,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 44/1900 [00:55<37:35,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 45/1900 [00:56<36:54,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 46/1900 [00:57<36:41,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 47/1900 [00:58<36:09,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 48/1900 [01:00<36:02,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 49/1900 [01:01<35:53,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 50/1900 [01:02<36:27,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 51/1900 [01:03<36:35,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 52/1900 [01:04<36:21,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 53/1900 [01:05<36:18,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 54/1900 [01:07<36:30,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 55/1900 [01:08<37:08,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 56/1900 [01:09<37:10,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 57/1900 [01:10<37:05,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 58/1900 [01:12<37:02,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 59/1900 [01:13<36:46,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 60/1900 [01:14<36:12,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 61/1900 [01:15<37:23,  1.22s/it]
+
+
Evaluating eval...:   3%|▎         | 62/1900 [01:16<36:53,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 63/1900 [01:18<36:39,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 64/1900 [01:19<36:26,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 65/1900 [01:20<36:00,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 66/1900 [01:21<35:42,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 67/1900 [01:22<35:40,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 68/1900 [01:24<37:44,  1.24s/it]
+
+
Evaluating eval...:   4%|▎         | 69/1900 [01:25<36:50,  1.21s/it]
+
+
Evaluating eval...:   4%|▎         | 70/1900 [01:26<37:20,  1.22s/it]
+
+
Evaluating eval...:   4%|▎         | 71/1900 [01:27<37:12,  1.22s/it]
+
+
Evaluating eval...:   4%|▍         | 72/1900 [01:28<36:59,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 73/1900 [01:30<37:00,  1.22s/it]
+
+
Evaluating eval...:   4%|▍         | 74/1900 [01:31<36:46,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 75/1900 [01:32<36:23,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 76/1900 [01:33<36:18,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 77/1900 [01:34<36:34,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 78/1900 [01:36<36:28,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 79/1900 [01:37<36:27,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 80/1900 [01:38<36:12,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 81/1900 [01:39<35:52,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 82/1900 [01:40<36:46,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 83/1900 [01:42<37:23,  1.23s/it]
+
+
Evaluating eval...:   4%|▍         | 84/1900 [01:43<36:51,  1.22s/it]
+
+
Evaluating eval...:   4%|▍         | 85/1900 [01:44<36:35,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 86/1900 [01:45<35:51,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 87/1900 [01:46<36:10,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 88/1900 [01:48<36:04,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 89/1900 [01:49<37:50,  1.25s/it]
+
+
Evaluating eval...:   5%|▍         | 90/1900 [01:50<37:12,  1.23s/it]
+
+
Evaluating eval...:   5%|▍         | 91/1900 [01:51<37:11,  1.23s/it]
+
+
Evaluating eval...:   5%|▍         | 92/1900 [01:53<36:28,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 93/1900 [01:54<36:10,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 94/1900 [01:55<35:37,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 95/1900 [01:56<35:08,  1.17s/it]
+
+
Evaluating eval...:   5%|▌         | 96/1900 [01:57<36:01,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 97/1900 [01:58<35:27,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 98/1900 [02:00<36:21,  1.21s/it]
+
+
Evaluating eval...:   5%|▌         | 99/1900 [02:01<35:55,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 100/1900 [02:02<35:42,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 101/1900 [02:03<36:40,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 102/1900 [02:05<37:04,  1.24s/it]
+
+
Evaluating eval...:   5%|▌         | 103/1900 [02:06<36:45,  1.23s/it]
+
+
Evaluating eval...:   5%|▌         | 104/1900 [02:07<36:16,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 105/1900 [02:08<36:04,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 106/1900 [02:09<35:26,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 107/1900 [02:11<35:48,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 108/1900 [02:12<35:15,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 109/1900 [02:13<35:34,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 110/1900 [02:14<35:14,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 111/1900 [02:15<35:29,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 112/1900 [02:17<36:41,  1.23s/it]
+
+
Evaluating eval...:   6%|▌         | 113/1900 [02:18<36:05,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 114/1900 [02:19<35:35,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 115/1900 [02:20<35:15,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 116/1900 [02:21<34:52,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 117/1900 [02:22<34:56,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 118/1900 [02:24<35:17,  1.19s/it]
+
+
Evaluating eval...:   6%|▋         | 119/1900 [02:25<35:08,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 120/1900 [02:26<35:34,  1.20s/it]
+
+
Evaluating eval...:   6%|▋         | 121/1900 [02:27<35:06,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 122/1900 [02:28<35:04,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 123/1900 [02:30<35:02,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 124/1900 [02:31<35:07,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 125/1900 [02:32<35:18,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 126/1900 [02:33<35:38,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 127/1900 [02:34<35:47,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 128/1900 [02:36<35:18,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 129/1900 [02:37<34:56,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 130/1900 [02:38<34:43,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 131/1900 [02:39<34:52,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 132/1900 [02:40<35:19,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 133/1900 [02:41<34:48,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 134/1900 [02:43<34:58,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 135/1900 [02:44<35:16,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 136/1900 [02:45<35:44,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 137/1900 [02:46<36:27,  1.24s/it]
+
+
Evaluating eval...:   7%|▋         | 138/1900 [02:48<36:14,  1.23s/it]
+
+
Evaluating eval...:   7%|▋         | 139/1900 [02:49<35:45,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 140/1900 [02:50<35:38,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 141/1900 [02:51<35:23,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 142/1900 [02:53<36:33,  1.25s/it]
+
+
Evaluating eval...:   8%|▊         | 143/1900 [02:54<36:15,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 144/1900 [02:55<35:28,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 145/1900 [02:56<35:22,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 146/1900 [02:57<34:57,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 147/1900 [02:59<35:27,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 148/1900 [03:00<34:53,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 149/1900 [03:01<34:53,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 150/1900 [03:02<35:46,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 151/1900 [03:03<35:32,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 152/1900 [03:05<35:24,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 153/1900 [03:06<35:03,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 154/1900 [03:07<35:02,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 155/1900 [03:08<34:54,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 156/1900 [03:09<34:53,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 157/1900 [03:11<36:00,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 158/1900 [03:12<35:33,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 159/1900 [03:13<34:50,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 160/1900 [03:14<34:45,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 161/1900 [03:16<35:31,  1.23s/it]
+
+
Evaluating eval...:   9%|▊         | 162/1900 [03:17<34:56,  1.21s/it]
+
+
Evaluating eval...:   9%|▊         | 163/1900 [03:18<34:20,  1.19s/it]
+
+
Evaluating eval...:   9%|▊         | 164/1900 [03:19<34:37,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 165/1900 [03:20<34:39,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 166/1900 [03:21<34:27,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 167/1900 [03:23<35:12,  1.22s/it]
+
+
Evaluating eval...:   9%|▉         | 168/1900 [03:24<34:45,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 169/1900 [03:25<34:33,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 170/1900 [03:26<34:31,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 171/1900 [03:27<34:25,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 172/1900 [03:29<34:55,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 173/1900 [03:30<34:48,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 174/1900 [03:31<35:11,  1.22s/it]
+
+
Evaluating eval...:   9%|▉         | 175/1900 [03:32<34:30,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 176/1900 [03:33<34:03,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 177/1900 [03:35<35:40,  1.24s/it]
+
+
Evaluating eval...:   9%|▉         | 178/1900 [03:36<35:44,  1.25s/it]
+
+
Evaluating eval...:   9%|▉         | 179/1900 [03:37<35:10,  1.23s/it]
+
+
Evaluating eval...:   9%|▉         | 180/1900 [03:38<34:53,  1.22s/it]
+
+
Evaluating eval...:  10%|▉         | 181/1900 [03:40<34:47,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 182/1900 [03:41<36:17,  1.27s/it]
+
+
Evaluating eval...:  10%|▉         | 183/1900 [03:42<35:53,  1.25s/it]
+
+
Evaluating eval...:  10%|▉         | 184/1900 [03:43<35:05,  1.23s/it]
+
+
Evaluating eval...:  10%|▉         | 185/1900 [03:45<34:42,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 186/1900 [03:46<34:16,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 187/1900 [03:47<34:16,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 188/1900 [03:48<34:16,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 189/1900 [03:49<34:08,  1.20s/it]
+
+
Evaluating eval...:  10%|█         | 190/1900 [03:51<34:12,  1.20s/it]
+
+
Evaluating eval...:  10%|█         | 191/1900 [03:52<34:03,  1.20s/it]
+
+
Evaluating eval...:  10%|█         | 192/1900 [03:53<35:11,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 193/1900 [03:54<36:10,  1.27s/it]
+
+
Evaluating eval...:  10%|█         | 194/1900 [03:56<35:50,  1.26s/it]
+
+
Evaluating eval...:  10%|█         | 195/1900 [03:57<35:35,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 196/1900 [03:58<35:09,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 197/1900 [03:59<35:46,  1.26s/it]
+
+
Evaluating eval...:  10%|█         | 198/1900 [04:01<36:17,  1.28s/it]
+
+
Evaluating eval...:  10%|█         | 199/1900 [04:02<35:22,  1.25s/it]
+
+
Evaluating eval...:  11%|█         | 200/1900 [04:03<34:35,  1.22s/it]
+
+
Evaluating eval...:  11%|█         | 201/1900 [04:04<33:58,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 202/1900 [04:05<33:36,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 203/1900 [04:07<33:59,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 204/1900 [04:08<33:57,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 205/1900 [04:09<33:49,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 206/1900 [04:10<33:43,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 207/1900 [04:11<34:12,  1.21s/it]
+
+
Evaluating eval...:  11%|█         | 208/1900 [04:13<33:51,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 209/1900 [04:14<33:47,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 210/1900 [04:15<33:30,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 211/1900 [04:16<33:32,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 212/1900 [04:17<33:30,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 213/1900 [04:19<34:10,  1.22s/it]
+
+
Evaluating eval...:  11%|█▏        | 214/1900 [04:20<34:23,  1.22s/it]
+
+
Evaluating eval...:  11%|█▏        | 215/1900 [04:21<34:06,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 216/1900 [04:22<34:05,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 217/1900 [04:24<34:09,  1.22s/it]
+
+
Evaluating eval...:  11%|█▏        | 218/1900 [04:25<34:20,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 219/1900 [04:26<34:05,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 220/1900 [04:27<34:36,  1.24s/it]
+
+
Evaluating eval...:  12%|█▏        | 221/1900 [04:28<34:12,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 222/1900 [04:30<33:48,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 223/1900 [04:31<33:14,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 224/1900 [04:32<32:59,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 225/1900 [04:33<33:01,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 226/1900 [04:34<33:05,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 227/1900 [04:36<33:04,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 228/1900 [04:37<33:48,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 229/1900 [04:38<33:18,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 230/1900 [04:39<33:16,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 231/1900 [04:40<33:28,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 232/1900 [04:42<33:10,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 233/1900 [04:43<33:19,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 234/1900 [04:44<33:15,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 235/1900 [04:45<33:08,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 236/1900 [04:46<33:47,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 237/1900 [04:48<34:01,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 238/1900 [04:49<34:14,  1.24s/it]
+
+
Evaluating eval...:  13%|█▎        | 239/1900 [04:50<34:58,  1.26s/it]
+
+
Evaluating eval...:  13%|█▎        | 240/1900 [04:51<34:04,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 241/1900 [04:53<33:34,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 242/1900 [04:54<33:31,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 243/1900 [04:55<33:02,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 244/1900 [04:56<33:00,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 245/1900 [04:57<33:49,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 246/1900 [04:59<33:50,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 247/1900 [05:00<33:31,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 248/1900 [05:01<33:28,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 249/1900 [05:02<32:53,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 250/1900 [05:03<33:07,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 251/1900 [05:05<33:52,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 252/1900 [05:06<33:22,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 253/1900 [05:07<34:07,  1.24s/it]
+
+
Evaluating eval...:  13%|█▎        | 254/1900 [05:08<33:49,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 255/1900 [05:10<33:38,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 256/1900 [05:11<33:11,  1.21s/it]
+
+
Evaluating eval...:  14%|█▎        | 257/1900 [05:12<32:38,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 258/1900 [05:13<32:35,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 259/1900 [05:14<32:44,  1.20s/it]
+
+
Evaluating eval...:  14%|█▎        | 260/1900 [05:16<32:37,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 261/1900 [05:17<32:31,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 262/1900 [05:18<32:11,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 263/1900 [05:19<32:31,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 264/1900 [05:20<32:50,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 265/1900 [05:22<32:47,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 266/1900 [05:23<32:30,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 267/1900 [05:24<32:59,  1.21s/it]
+
+
Evaluating eval...:  14%|█▍        | 268/1900 [05:25<32:53,  1.21s/it]
+
+
Evaluating eval...:  14%|█▍        | 269/1900 [05:26<32:37,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 270/1900 [05:28<32:22,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 271/1900 [05:29<32:03,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 272/1900 [05:30<32:20,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 273/1900 [05:31<33:15,  1.23s/it]
+
+
Evaluating eval...:  14%|█▍        | 274/1900 [05:32<33:19,  1.23s/it]
+
+
Evaluating eval...:  14%|█▍        | 275/1900 [05:34<33:20,  1.23s/it]
+
+
Evaluating eval...:  15%|█▍        | 276/1900 [05:35<33:30,  1.24s/it]
+
+
Evaluating eval...:  15%|█▍        | 277/1900 [05:36<32:50,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 278/1900 [05:37<32:39,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 279/1900 [05:39<32:45,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 280/1900 [05:40<32:50,  1.22s/it]
+
+
Evaluating eval...:  15%|█▍        | 281/1900 [05:41<32:48,  1.22s/it]
+
+
Evaluating eval...:  15%|█▍        | 282/1900 [05:42<33:07,  1.23s/it]
+
+
Evaluating eval...:  15%|█▍        | 283/1900 [05:43<32:42,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 284/1900 [05:45<32:35,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 285/1900 [05:46<32:15,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 286/1900 [05:47<32:39,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 287/1900 [05:48<32:32,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 288/1900 [05:50<33:38,  1.25s/it]
+
+
Evaluating eval...:  15%|█▌        | 289/1900 [05:51<33:15,  1.24s/it]
+
+
Evaluating eval...:  15%|█▌        | 290/1900 [05:52<32:47,  1.22s/it]
+
+
Evaluating eval...:  15%|█▌        | 291/1900 [05:53<32:33,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 292/1900 [05:54<32:34,  1.22s/it]
+
+
Evaluating eval...:  15%|█▌        | 293/1900 [05:56<32:12,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 294/1900 [05:57<31:52,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 295/1900 [05:58<32:01,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 296/1900 [05:59<32:25,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 297/1900 [06:00<32:41,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 298/1900 [06:02<32:45,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 299/1900 [06:03<32:09,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 300/1900 [06:04<32:20,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 301/1900 [06:05<32:52,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 302/1900 [06:07<32:51,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 303/1900 [06:08<32:20,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 304/1900 [06:09<31:56,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 305/1900 [06:10<31:49,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 306/1900 [06:11<31:48,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 307/1900 [06:12<31:43,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 308/1900 [06:14<31:35,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 309/1900 [06:15<31:29,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 310/1900 [06:16<32:08,  1.21s/it]
+
+
Evaluating eval...:  16%|█▋        | 311/1900 [06:17<32:17,  1.22s/it]
+
+
Evaluating eval...:  16%|█▋        | 312/1900 [06:19<32:03,  1.21s/it]
+
+
Evaluating eval...:  16%|█▋        | 313/1900 [06:20<31:49,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 314/1900 [06:21<31:49,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 315/1900 [06:22<31:55,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 316/1900 [06:23<31:32,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 317/1900 [06:25<32:03,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 318/1900 [06:26<31:53,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 319/1900 [06:27<31:50,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 320/1900 [06:28<31:33,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 321/1900 [06:29<31:07,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 322/1900 [06:30<31:21,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 323/1900 [06:32<31:35,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 324/1900 [06:33<31:07,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 325/1900 [06:34<30:59,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 326/1900 [06:35<30:49,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 327/1900 [06:36<30:46,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 328/1900 [06:38<31:30,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 329/1900 [06:39<31:06,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 330/1900 [06:40<31:33,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 331/1900 [06:41<32:39,  1.25s/it]
+
+
Evaluating eval...:  17%|█▋        | 332/1900 [06:43<32:28,  1.24s/it]
+
+
Evaluating eval...:  18%|█▊        | 333/1900 [06:44<32:23,  1.24s/it]
+
+
Evaluating eval...:  18%|█▊        | 334/1900 [06:45<31:36,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 335/1900 [06:46<31:04,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 336/1900 [06:47<31:09,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 337/1900 [06:49<31:07,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 338/1900 [06:50<31:51,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 339/1900 [06:51<31:57,  1.23s/it]
+
+
Evaluating eval...:  18%|█▊        | 340/1900 [06:52<31:39,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 341/1900 [06:54<31:47,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 342/1900 [06:55<31:13,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 343/1900 [06:56<30:53,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 344/1900 [06:57<31:19,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 345/1900 [06:58<31:14,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 346/1900 [06:59<30:51,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 347/1900 [07:01<30:48,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 348/1900 [07:02<30:22,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 349/1900 [07:03<30:11,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 350/1900 [07:04<30:15,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 351/1900 [07:05<30:52,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 352/1900 [07:07<31:11,  1.21s/it]
+
+
Evaluating eval...:  19%|█▊        | 353/1900 [07:08<31:29,  1.22s/it]
+
+
Evaluating eval...:  19%|█▊        | 354/1900 [07:09<31:16,  1.21s/it]
+
+
Evaluating eval...:  19%|█▊        | 355/1900 [07:10<31:41,  1.23s/it]
+
+
Evaluating eval...:  19%|█▊        | 356/1900 [07:12<31:53,  1.24s/it]
+
+
Evaluating eval...:  19%|█▉        | 357/1900 [07:13<31:19,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 358/1900 [07:14<31:24,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 359/1900 [07:15<30:55,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 360/1900 [07:16<30:59,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 361/1900 [07:17<30:30,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 362/1900 [07:19<31:34,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 363/1900 [07:20<30:58,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 364/1900 [07:21<30:35,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 365/1900 [07:22<30:29,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 366/1900 [07:23<30:06,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 367/1900 [07:25<31:16,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 368/1900 [07:26<31:58,  1.25s/it]
+
+
Evaluating eval...:  19%|█▉        | 369/1900 [07:27<31:56,  1.25s/it]
+
+
Evaluating eval...:  19%|█▉        | 370/1900 [07:29<31:21,  1.23s/it]
+
+
Evaluating eval...:  20%|█▉        | 371/1900 [07:30<31:01,  1.22s/it]
+
+
Evaluating eval...:  20%|█▉        | 372/1900 [07:31<30:42,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 373/1900 [07:32<30:32,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 374/1900 [07:33<30:11,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 375/1900 [07:34<29:56,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 376/1900 [07:36<30:04,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 377/1900 [07:37<30:49,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 378/1900 [07:38<31:10,  1.23s/it]
+
+
Evaluating eval...:  20%|█▉        | 379/1900 [07:39<31:01,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 380/1900 [07:41<31:04,  1.23s/it]
+
+
Evaluating eval...:  20%|██        | 381/1900 [07:42<31:04,  1.23s/it]
+
+
Evaluating eval...:  20%|██        | 382/1900 [07:43<31:23,  1.24s/it]
+
+
Evaluating eval...:  20%|██        | 383/1900 [07:44<30:52,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 384/1900 [07:45<30:31,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 385/1900 [07:47<30:22,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 386/1900 [07:48<30:32,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 387/1900 [07:49<30:24,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 388/1900 [07:50<30:17,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 389/1900 [07:51<30:20,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 390/1900 [07:53<30:18,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 391/1900 [07:54<30:21,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 392/1900 [07:55<30:03,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 393/1900 [07:56<29:44,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 394/1900 [07:57<29:50,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 395/1900 [07:59<29:33,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 396/1900 [08:00<30:22,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 397/1900 [08:01<30:38,  1.22s/it]
+
+
Evaluating eval...:  21%|██        | 398/1900 [08:02<30:15,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 399/1900 [08:04<30:39,  1.23s/it]
+
+
Evaluating eval...:  21%|██        | 400/1900 [08:05<30:21,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 401/1900 [08:06<30:32,  1.22s/it]
+
+
Evaluating eval...:  21%|██        | 402/1900 [08:07<30:01,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 403/1900 [08:08<30:17,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 404/1900 [08:10<30:38,  1.23s/it]
+
+
Evaluating eval...:  21%|██▏       | 405/1900 [08:11<30:30,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 406/1900 [08:12<30:13,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 407/1900 [08:13<30:14,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 408/1900 [08:15<30:33,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 409/1900 [08:16<30:38,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 410/1900 [08:17<30:29,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 411/1900 [08:18<30:31,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 412/1900 [08:19<29:54,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 413/1900 [08:21<30:30,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 414/1900 [08:22<30:11,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 415/1900 [08:23<29:28,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 416/1900 [08:24<29:03,  1.17s/it]
+
+
Evaluating eval...:  22%|██▏       | 417/1900 [08:25<29:59,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 418/1900 [08:27<29:38,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 419/1900 [08:28<29:19,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 420/1900 [08:29<29:40,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 421/1900 [08:30<30:07,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 422/1900 [08:31<29:46,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 423/1900 [08:33<30:11,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 424/1900 [08:34<29:52,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 425/1900 [08:35<29:37,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 426/1900 [08:36<29:54,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 427/1900 [08:37<29:36,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 428/1900 [08:39<29:08,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 429/1900 [08:40<29:16,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 430/1900 [08:41<28:51,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 431/1900 [08:42<28:56,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 432/1900 [08:43<29:30,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 433/1900 [08:45<29:28,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 434/1900 [08:46<29:55,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 435/1900 [08:47<29:23,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 436/1900 [08:48<29:37,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 437/1900 [08:49<29:05,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 438/1900 [08:51<28:57,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 439/1900 [08:52<28:58,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 440/1900 [08:53<28:41,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 441/1900 [08:54<28:42,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 442/1900 [08:55<28:29,  1.17s/it]
+
+
Evaluating eval...:  23%|██▎       | 443/1900 [08:57<28:46,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 444/1900 [08:58<28:54,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 445/1900 [08:59<29:06,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 446/1900 [09:00<29:35,  1.22s/it]
+
+
Evaluating eval...:  24%|██▎       | 447/1900 [09:01<29:04,  1.20s/it]
+
+
Evaluating eval...:  24%|██▎       | 448/1900 [09:03<28:55,  1.20s/it]
+
+
Evaluating eval...:  24%|██▎       | 449/1900 [09:04<28:46,  1.19s/it]
+
+
Evaluating eval...:  24%|██▎       | 450/1900 [09:05<28:40,  1.19s/it]
+
+
Evaluating eval...:  24%|██▎       | 451/1900 [09:06<28:51,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 452/1900 [09:07<28:32,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 453/1900 [09:09<29:18,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 454/1900 [09:10<29:46,  1.24s/it]
+
+
Evaluating eval...:  24%|██▍       | 455/1900 [09:11<29:55,  1.24s/it]
+
+
Evaluating eval...:  24%|██▍       | 456/1900 [09:12<29:49,  1.24s/it]
+
+
Evaluating eval...:  24%|██▍       | 457/1900 [09:14<29:43,  1.24s/it]
+
+
Evaluating eval...:  24%|██▍       | 458/1900 [09:15<29:19,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 459/1900 [09:16<28:46,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 460/1900 [09:17<28:26,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 461/1900 [09:18<28:53,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 462/1900 [09:19<28:49,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 463/1900 [09:21<29:06,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 464/1900 [09:22<29:11,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 465/1900 [09:23<28:59,  1.21s/it]
+
+
Evaluating eval...:  25%|██▍       | 466/1900 [09:24<28:32,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 467/1900 [09:26<28:32,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 468/1900 [09:27<28:32,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 469/1900 [09:28<28:28,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 470/1900 [09:29<28:20,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 471/1900 [09:30<28:28,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 472/1900 [09:32<28:59,  1.22s/it]
+
+
Evaluating eval...:  25%|██▍       | 473/1900 [09:33<28:34,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 474/1900 [09:34<28:19,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 475/1900 [09:35<28:18,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 476/1900 [09:36<28:13,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 477/1900 [09:38<28:51,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 478/1900 [09:39<28:50,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 479/1900 [09:40<29:02,  1.23s/it]
+
+
Evaluating eval...:  25%|██▌       | 480/1900 [09:41<29:03,  1.23s/it]
+
+
Evaluating eval...:  25%|██▌       | 481/1900 [09:43<29:58,  1.27s/it]
+
+
Evaluating eval...:  25%|██▌       | 482/1900 [09:44<29:14,  1.24s/it]
+
+
Evaluating eval...:  25%|██▌       | 483/1900 [09:45<28:47,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 484/1900 [09:46<29:09,  1.24s/it]
+
+
Evaluating eval...:  26%|██▌       | 485/1900 [09:47<28:33,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 486/1900 [09:49<28:09,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 487/1900 [09:50<28:00,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 488/1900 [09:51<28:35,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 489/1900 [09:52<28:39,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 490/1900 [09:53<28:26,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 491/1900 [09:55<28:47,  1.23s/it]
+
+
Evaluating eval...:  26%|██▌       | 492/1900 [09:56<28:50,  1.23s/it]
+
+
Evaluating eval...:  26%|██▌       | 493/1900 [09:57<28:52,  1.23s/it]
+
+
Evaluating eval...:  26%|██▌       | 494/1900 [09:58<28:23,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 495/1900 [09:59<28:05,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 496/1900 [10:01<28:17,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 497/1900 [10:02<28:26,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 498/1900 [10:03<28:45,  1.23s/it]
+
+
Evaluating eval...:  26%|██▋       | 499/1900 [10:04<28:37,  1.23s/it]
+
+
Evaluating eval...:  26%|██▋       | 500/1900 [10:06<28:24,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 501/1900 [10:07<28:21,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 502/1900 [10:08<28:18,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 503/1900 [10:09<28:58,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 504/1900 [10:11<29:36,  1.27s/it]
+
+
Evaluating eval...:  27%|██▋       | 505/1900 [10:12<29:30,  1.27s/it]
+
+
Evaluating eval...:  27%|██▋       | 506/1900 [10:13<28:56,  1.25s/it]
+
+
Evaluating eval...:  27%|██▋       | 507/1900 [10:14<28:27,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 508/1900 [10:16<28:49,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 509/1900 [10:17<29:01,  1.25s/it]
+
+
Evaluating eval...:  27%|██▋       | 510/1900 [10:18<28:32,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 511/1900 [10:19<28:10,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 512/1900 [10:20<27:51,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 513/1900 [10:22<27:26,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 514/1900 [10:23<27:13,  1.18s/it]
+
+
Evaluating eval...:  27%|██▋       | 515/1900 [10:24<27:39,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 516/1900 [10:25<27:47,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 517/1900 [10:26<27:30,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 518/1900 [10:28<27:59,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 519/1900 [10:29<28:25,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 520/1900 [10:30<28:00,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 521/1900 [10:31<28:14,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 522/1900 [10:33<28:07,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 523/1900 [10:34<28:21,  1.24s/it]
+
+
Evaluating eval...:  28%|██▊       | 524/1900 [10:35<28:08,  1.23s/it]
+
+
Evaluating eval...:  28%|██▊       | 525/1900 [10:36<27:44,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 526/1900 [10:37<27:41,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 527/1900 [10:39<27:55,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 528/1900 [10:40<27:54,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 529/1900 [10:41<27:53,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 530/1900 [10:42<27:43,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 531/1900 [10:44<27:44,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 532/1900 [10:45<28:10,  1.24s/it]
+
+
Evaluating eval...:  28%|██▊       | 533/1900 [10:46<27:45,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 534/1900 [10:47<27:34,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 535/1900 [10:48<27:13,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 536/1900 [10:50<27:05,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 537/1900 [10:51<27:17,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 538/1900 [10:52<27:09,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 539/1900 [10:53<27:26,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 540/1900 [10:54<27:21,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 541/1900 [10:56<27:02,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 542/1900 [10:57<27:30,  1.22s/it]
+
+
Evaluating eval...:  29%|██▊       | 543/1900 [10:58<27:00,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 544/1900 [10:59<27:00,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 545/1900 [11:00<27:51,  1.23s/it]
+
+
Evaluating eval...:  29%|██▊       | 546/1900 [11:02<27:32,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 547/1900 [11:03<27:40,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 548/1900 [11:04<27:58,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 549/1900 [11:05<27:46,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 550/1900 [11:07<27:55,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 551/1900 [11:08<27:47,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 552/1900 [11:09<28:12,  1.26s/it]
+
+
Evaluating eval...:  29%|██▉       | 553/1900 [11:10<27:55,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 554/1900 [11:12<27:26,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 555/1900 [11:13<27:10,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 556/1900 [11:14<27:19,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 557/1900 [11:15<26:56,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 558/1900 [11:16<26:58,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 559/1900 [11:18<26:44,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 560/1900 [11:19<27:06,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 561/1900 [11:20<27:01,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 562/1900 [11:21<27:16,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 563/1900 [11:22<27:19,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 564/1900 [11:24<27:33,  1.24s/it]
+
+
Evaluating eval...:  30%|██▉       | 565/1900 [11:25<27:14,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 566/1900 [11:26<27:25,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 567/1900 [11:27<27:24,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 568/1900 [11:29<27:20,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 569/1900 [11:30<27:13,  1.23s/it]
+
+
Evaluating eval...:  30%|███       | 570/1900 [11:31<28:09,  1.27s/it]
+
+
Evaluating eval...:  30%|███       | 571/1900 [11:32<27:18,  1.23s/it]
+
+
Evaluating eval...:  30%|███       | 572/1900 [11:34<26:53,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 573/1900 [11:35<26:35,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 574/1900 [11:36<26:34,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 575/1900 [11:37<26:20,  1.19s/it]
+
+
Evaluating eval...:  30%|███       | 576/1900 [11:38<26:29,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 577/1900 [11:40<26:35,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 578/1900 [11:41<26:37,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 579/1900 [11:42<26:31,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 580/1900 [11:43<26:16,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 581/1900 [11:44<26:02,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 582/1900 [11:46<26:59,  1.23s/it]
+
+
Evaluating eval...:  31%|███       | 583/1900 [11:47<26:31,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 584/1900 [11:48<26:11,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 585/1900 [11:49<26:04,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 586/1900 [11:50<26:20,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 587/1900 [11:51<26:00,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 588/1900 [11:53<25:52,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 589/1900 [11:54<25:57,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 590/1900 [11:55<25:58,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 591/1900 [11:56<25:48,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 592/1900 [11:57<25:56,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 593/1900 [11:59<25:48,  1.18s/it]
+
+
Evaluating eval...:  31%|███▏      | 594/1900 [12:00<26:19,  1.21s/it]
+
+
Evaluating eval...:  31%|███▏      | 595/1900 [12:01<25:57,  1.19s/it]
+
+
Evaluating eval...:  31%|███▏      | 596/1900 [12:02<26:07,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 597/1900 [12:04<26:28,  1.22s/it]
+
+
Evaluating eval...:  31%|███▏      | 598/1900 [12:05<26:11,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 599/1900 [12:06<26:12,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 600/1900 [12:07<26:11,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 601/1900 [12:08<26:02,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 602/1900 [12:09<25:39,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 603/1900 [12:11<25:42,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 604/1900 [12:12<25:46,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 605/1900 [12:13<26:00,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 606/1900 [12:14<26:05,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 607/1900 [12:15<25:38,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 608/1900 [12:17<26:02,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 609/1900 [12:18<26:22,  1.23s/it]
+
+
Evaluating eval...:  32%|███▏      | 610/1900 [12:19<26:07,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 611/1900 [12:20<25:40,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 612/1900 [12:22<25:56,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 613/1900 [12:23<25:52,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 614/1900 [12:24<26:19,  1.23s/it]
+
+
Evaluating eval...:  32%|███▏      | 615/1900 [12:25<25:52,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 616/1900 [12:26<25:34,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 617/1900 [12:28<25:19,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 618/1900 [12:29<25:06,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 619/1900 [12:30<25:21,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 620/1900 [12:31<25:19,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 621/1900 [12:32<25:20,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 622/1900 [12:33<25:23,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 623/1900 [12:35<25:31,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 624/1900 [12:36<26:01,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 625/1900 [12:37<26:07,  1.23s/it]
+
+
Evaluating eval...:  33%|███▎      | 626/1900 [12:38<25:37,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 627/1900 [12:40<25:17,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 628/1900 [12:41<25:10,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 629/1900 [12:42<25:26,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 630/1900 [12:43<25:21,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 631/1900 [12:44<25:39,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 632/1900 [12:46<25:14,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 633/1900 [12:47<24:58,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 634/1900 [12:48<24:38,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 635/1900 [12:49<24:41,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 636/1900 [12:50<24:54,  1.18s/it]
+
+
Evaluating eval...:  34%|███▎      | 637/1900 [12:51<25:05,  1.19s/it]
+
+
Evaluating eval...:  34%|███▎      | 638/1900 [12:53<25:08,  1.20s/it]
+
+
Evaluating eval...:  34%|███▎      | 639/1900 [12:54<25:23,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 640/1900 [12:55<25:29,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 641/1900 [12:56<25:22,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 642/1900 [12:57<25:26,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 643/1900 [12:59<25:53,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 644/1900 [13:00<25:42,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 645/1900 [13:01<25:41,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 646/1900 [13:02<25:56,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 647/1900 [13:04<25:30,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 648/1900 [13:05<25:10,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 649/1900 [13:06<25:25,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 650/1900 [13:07<25:48,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 651/1900 [13:09<25:44,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 652/1900 [13:10<25:15,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 653/1900 [13:11<24:52,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 654/1900 [13:12<25:27,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 655/1900 [13:13<25:30,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 656/1900 [13:15<25:05,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 657/1900 [13:16<24:48,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 658/1900 [13:17<25:13,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 659/1900 [13:18<25:02,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 660/1900 [13:19<24:41,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 661/1900 [13:21<24:40,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 662/1900 [13:22<25:20,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 663/1900 [13:23<25:19,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 664/1900 [13:24<25:06,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 665/1900 [13:26<24:53,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 666/1900 [13:27<24:40,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 667/1900 [13:28<25:37,  1.25s/it]
+
+
Evaluating eval...:  35%|███▌      | 668/1900 [13:29<25:07,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 669/1900 [13:30<24:49,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 670/1900 [13:32<24:44,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 671/1900 [13:33<24:49,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 672/1900 [13:34<24:43,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 673/1900 [13:35<24:43,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 674/1900 [13:36<24:43,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 675/1900 [13:38<24:40,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 676/1900 [13:39<24:19,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 677/1900 [13:40<24:18,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 678/1900 [13:41<24:41,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 679/1900 [13:42<24:13,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 680/1900 [13:44<24:25,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 681/1900 [13:45<24:44,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 682/1900 [13:46<24:45,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 683/1900 [13:47<24:47,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 684/1900 [13:49<24:32,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 685/1900 [13:50<24:11,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 686/1900 [13:51<24:33,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 687/1900 [13:52<24:26,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 688/1900 [13:53<24:00,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 689/1900 [13:54<23:54,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 690/1900 [13:56<24:08,  1.20s/it]
+
+
Evaluating eval...:  36%|███▋      | 691/1900 [13:57<24:05,  1.20s/it]
+
+
Evaluating eval...:  36%|███▋      | 692/1900 [13:58<23:46,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 693/1900 [13:59<23:52,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 694/1900 [14:00<23:51,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 695/1900 [14:02<23:58,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 696/1900 [14:03<24:07,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 697/1900 [14:04<24:08,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 698/1900 [14:05<24:27,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 699/1900 [14:07<24:52,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 700/1900 [14:08<24:24,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 701/1900 [14:09<24:19,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 702/1900 [14:10<24:36,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 703/1900 [14:11<24:08,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 704/1900 [14:13<24:44,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 705/1900 [14:14<24:29,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 706/1900 [14:15<24:13,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 707/1900 [14:16<23:50,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 708/1900 [14:18<24:13,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 709/1900 [14:19<24:06,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 710/1900 [14:20<23:59,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 711/1900 [14:21<24:26,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 712/1900 [14:22<24:15,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 713/1900 [14:24<25:13,  1.28s/it]
+
+
Evaluating eval...:  38%|███▊      | 714/1900 [14:25<24:31,  1.24s/it]
+
+
Evaluating eval...:  38%|███▊      | 715/1900 [14:26<24:16,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 716/1900 [14:27<23:49,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 717/1900 [14:28<23:34,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 718/1900 [14:30<23:38,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 719/1900 [14:31<23:33,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 720/1900 [14:32<23:22,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 721/1900 [14:33<23:39,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 722/1900 [14:34<23:30,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 723/1900 [14:36<23:38,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 724/1900 [14:37<23:34,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 725/1900 [14:38<23:13,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 726/1900 [14:39<23:16,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 727/1900 [14:40<23:11,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 728/1900 [14:42<24:00,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 729/1900 [14:43<23:34,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 730/1900 [14:44<23:59,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 731/1900 [14:45<23:50,  1.22s/it]
+
+
Evaluating eval...:  39%|███▊      | 732/1900 [14:47<23:35,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 733/1900 [14:48<23:46,  1.22s/it]
+
+
Evaluating eval...:  39%|███▊      | 734/1900 [14:49<23:32,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 735/1900 [14:50<23:20,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 736/1900 [14:51<23:11,  1.20s/it]
+
+
Evaluating eval...:  39%|███▉      | 737/1900 [14:53<22:57,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 738/1900 [14:54<23:05,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 739/1900 [14:55<23:00,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 740/1900 [14:56<23:10,  1.20s/it]
+
+
Evaluating eval...:  39%|███▉      | 741/1900 [14:57<23:53,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 742/1900 [14:59<23:39,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 743/1900 [15:00<23:43,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 744/1900 [15:01<23:16,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 745/1900 [15:02<23:41,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 746/1900 [15:04<23:42,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 747/1900 [15:05<24:05,  1.25s/it]
+
+
Evaluating eval...:  39%|███▉      | 748/1900 [15:06<23:34,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 749/1900 [15:07<23:47,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 750/1900 [15:09<23:38,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 751/1900 [15:10<23:39,  1.24s/it]
+
+
Evaluating eval...:  40%|███▉      | 752/1900 [15:11<24:06,  1.26s/it]
+
+
Evaluating eval...:  40%|███▉      | 753/1900 [15:12<23:52,  1.25s/it]
+
+
Evaluating eval...:  40%|███▉      | 754/1900 [15:13<23:20,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 755/1900 [15:15<23:01,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 756/1900 [15:16<23:15,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 757/1900 [15:17<23:14,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 758/1900 [15:18<23:23,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 759/1900 [15:20<23:33,  1.24s/it]
+
+
Evaluating eval...:  40%|████      | 760/1900 [15:21<23:44,  1.25s/it]
+
+
Evaluating eval...:  40%|████      | 761/1900 [15:22<23:26,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 762/1900 [15:23<23:02,  1.21s/it]
+
+
Evaluating eval...:  40%|████      | 763/1900 [15:24<22:49,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 764/1900 [15:26<22:38,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 765/1900 [15:27<22:51,  1.21s/it]
+
+
Evaluating eval...:  40%|████      | 766/1900 [15:28<22:52,  1.21s/it]
+
+
Evaluating eval...:  40%|████      | 767/1900 [15:29<23:16,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 768/1900 [15:31<24:04,  1.28s/it]
+
+
Evaluating eval...:  40%|████      | 769/1900 [15:32<23:52,  1.27s/it]
+
+
Evaluating eval...:  41%|████      | 770/1900 [15:33<23:23,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 771/1900 [15:34<23:07,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 772/1900 [15:36<23:23,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 773/1900 [15:37<23:03,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 774/1900 [15:38<22:42,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 775/1900 [15:39<23:23,  1.25s/it]
+
+
Evaluating eval...:  41%|████      | 776/1900 [15:41<23:10,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 777/1900 [15:42<23:09,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 778/1900 [15:43<22:46,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 779/1900 [15:44<22:29,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 780/1900 [15:45<23:12,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 781/1900 [15:47<23:04,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 782/1900 [15:48<23:42,  1.27s/it]
+
+
Evaluating eval...:  41%|████      | 783/1900 [15:49<23:25,  1.26s/it]
+
+
Evaluating eval...:  41%|████▏     | 784/1900 [15:51<23:07,  1.24s/it]
+
+
Evaluating eval...:  41%|████▏     | 785/1900 [15:52<22:37,  1.22s/it]
+
+
Evaluating eval...:  41%|████▏     | 786/1900 [15:53<22:23,  1.21s/it]
+
+
Evaluating eval...:  41%|████▏     | 787/1900 [15:54<22:34,  1.22s/it]
+
+
Evaluating eval...:  41%|████▏     | 788/1900 [15:55<22:30,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 789/1900 [15:57<22:36,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 790/1900 [15:58<22:26,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 791/1900 [15:59<22:42,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 792/1900 [16:00<22:43,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 793/1900 [16:01<22:29,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 794/1900 [16:03<22:14,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 795/1900 [16:04<22:13,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 796/1900 [16:05<21:58,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 797/1900 [16:06<21:56,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 798/1900 [16:07<21:59,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 799/1900 [16:09<21:51,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 800/1900 [16:10<22:34,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 801/1900 [16:11<22:26,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 802/1900 [16:12<22:04,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 803/1900 [16:14<22:23,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 804/1900 [16:15<22:04,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 805/1900 [16:16<22:26,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 806/1900 [16:17<22:02,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 807/1900 [16:18<21:45,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 808/1900 [16:20<22:30,  1.24s/it]
+
+
Evaluating eval...:  43%|████▎     | 809/1900 [16:21<22:28,  1.24s/it]
+
+
Evaluating eval...:  43%|████▎     | 810/1900 [16:22<22:16,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 811/1900 [16:23<21:57,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 812/1900 [16:24<22:05,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 813/1900 [16:26<21:40,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 814/1900 [16:27<21:35,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 815/1900 [16:28<21:31,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 816/1900 [16:29<21:32,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 817/1900 [16:30<21:27,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 818/1900 [16:32<21:51,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 819/1900 [16:33<21:42,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 820/1900 [16:34<21:40,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 821/1900 [16:35<21:28,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 822/1900 [16:36<21:29,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 823/1900 [16:38<21:50,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 824/1900 [16:39<21:46,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 825/1900 [16:40<21:40,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 826/1900 [16:41<21:56,  1.23s/it]
+
+
Evaluating eval...:  44%|████▎     | 827/1900 [16:43<21:49,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 828/1900 [16:44<21:48,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 829/1900 [16:45<21:27,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 830/1900 [16:46<21:42,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 831/1900 [16:47<21:19,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 832/1900 [16:48<21:16,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 833/1900 [16:50<21:14,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 834/1900 [16:51<20:57,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 835/1900 [16:52<21:19,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 836/1900 [16:53<21:25,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 837/1900 [16:54<21:13,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 838/1900 [16:56<20:56,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 839/1900 [16:57<20:50,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 840/1900 [16:58<20:57,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 841/1900 [16:59<21:12,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 842/1900 [17:00<21:13,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 843/1900 [17:02<21:20,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 844/1900 [17:03<20:56,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 845/1900 [17:04<20:49,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 846/1900 [17:05<21:03,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 847/1900 [17:06<20:47,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 848/1900 [17:08<20:50,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 849/1900 [17:09<20:50,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 850/1900 [17:10<21:14,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 851/1900 [17:11<21:05,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 852/1900 [17:13<21:37,  1.24s/it]
+
+
Evaluating eval...:  45%|████▍     | 853/1900 [17:14<21:14,  1.22s/it]
+
+
Evaluating eval...:  45%|████▍     | 854/1900 [17:15<21:16,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 855/1900 [17:16<21:12,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 856/1900 [17:17<20:56,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 857/1900 [17:19<20:53,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 858/1900 [17:20<21:20,  1.23s/it]
+
+
Evaluating eval...:  45%|████▌     | 859/1900 [17:21<21:14,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 860/1900 [17:22<21:18,  1.23s/it]
+
+
Evaluating eval...:  45%|████▌     | 861/1900 [17:24<21:30,  1.24s/it]
+
+
Evaluating eval...:  45%|████▌     | 862/1900 [17:25<21:20,  1.23s/it]
+
+
Evaluating eval...:  45%|████▌     | 863/1900 [17:26<20:51,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 864/1900 [17:27<20:36,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 865/1900 [17:28<20:20,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 866/1900 [17:29<20:21,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 867/1900 [17:31<20:40,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 868/1900 [17:32<21:16,  1.24s/it]
+
+
Evaluating eval...:  46%|████▌     | 869/1900 [17:33<20:54,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 870/1900 [17:34<20:57,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 871/1900 [17:36<21:05,  1.23s/it]
+
+
Evaluating eval...:  46%|████▌     | 872/1900 [17:37<20:54,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 873/1900 [17:38<20:44,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 874/1900 [17:39<21:03,  1.23s/it]
+
+
Evaluating eval...:  46%|████▌     | 875/1900 [17:40<20:58,  1.23s/it]
+
+
Evaluating eval...:  46%|████▌     | 876/1900 [17:42<20:41,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 877/1900 [17:43<20:17,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 878/1900 [17:44<20:33,  1.21s/it]
+
+
Evaluating eval...:  46%|████▋     | 879/1900 [17:45<20:22,  1.20s/it]
+
+
Evaluating eval...:  46%|████▋     | 880/1900 [17:46<20:16,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 881/1900 [17:48<20:07,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 882/1900 [17:49<20:12,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 883/1900 [17:50<20:40,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 884/1900 [17:51<20:40,  1.22s/it]
+
+
Evaluating eval...:  47%|███��▋     | 885/1900 [17:52<20:25,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 886/1900 [17:54<20:18,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 887/1900 [17:55<20:23,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 888/1900 [17:56<20:24,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 889/1900 [17:57<20:17,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 890/1900 [17:58<20:04,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 891/1900 [18:00<20:20,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 892/1900 [18:01<20:24,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 893/1900 [18:02<20:35,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 894/1900 [18:03<20:17,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 895/1900 [18:05<20:31,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 896/1900 [18:06<20:17,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 897/1900 [18:07<20:10,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 898/1900 [18:08<20:36,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 899/1900 [18:09<20:13,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 900/1900 [18:11<20:09,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 901/1900 [18:12<19:54,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 902/1900 [18:13<20:03,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 903/1900 [18:14<20:16,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 904/1900 [18:16<20:15,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 905/1900 [18:17<20:04,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 906/1900 [18:18<20:01,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 907/1900 [18:19<20:18,  1.23s/it]
+
+
Evaluating eval...:  48%|████▊     | 908/1900 [18:20<20:06,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 909/1900 [18:22<20:04,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 910/1900 [18:23<19:52,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 911/1900 [18:24<20:02,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 912/1900 [18:25<19:56,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 913/1900 [18:26<19:50,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 914/1900 [18:28<19:50,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 915/1900 [18:29<20:16,  1.24s/it]
+
+
Evaluating eval...:  48%|████▊     | 916/1900 [18:30<20:03,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 917/1900 [18:31<19:40,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 918/1900 [18:33<20:00,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 919/1900 [18:34<19:46,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 920/1900 [18:35<19:37,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 921/1900 [18:36<19:26,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 922/1900 [18:37<19:22,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 923/1900 [18:39<19:57,  1.23s/it]
+
+
Evaluating eval...:  49%|████▊     | 924/1900 [18:40<19:30,  1.20s/it]
+
+
Evaluating eval...:  49%|████▊     | 925/1900 [18:41<19:38,  1.21s/it]
+
+
Evaluating eval...:  49%|████▊     | 926/1900 [18:42<19:26,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 927/1900 [18:43<19:11,  1.18s/it]
+
+
Evaluating eval...:  49%|████▉     | 928/1900 [18:45<19:40,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 929/1900 [18:46<19:22,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 930/1900 [18:47<19:07,  1.18s/it]
+
+
Evaluating eval...:  49%|████▉     | 931/1900 [18:48<19:25,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 932/1900 [18:49<19:41,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 933/1900 [18:51<19:41,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 934/1900 [18:52<19:20,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 935/1900 [18:53<19:28,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 936/1900 [18:54<20:24,  1.27s/it]
+
+
Evaluating eval...:  49%|████▉     | 937/1900 [18:56<20:10,  1.26s/it]
+
+
Evaluating eval...:  49%|████▉     | 938/1900 [18:57<19:47,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 939/1900 [18:58<19:40,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 940/1900 [18:59<19:39,  1.23s/it]
+
+
Evaluating eval...:  50%|████▉     | 941/1900 [19:00<19:33,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 942/1900 [19:02<19:48,  1.24s/it]
+
+
Evaluating eval...:  50%|████▉     | 943/1900 [19:03<19:26,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 944/1900 [19:04<19:10,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 945/1900 [19:05<18:59,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 946/1900 [19:06<19:10,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 947/1900 [19:08<19:17,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 948/1900 [19:09<19:15,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 949/1900 [19:10<19:17,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 950/1900 [19:11<19:14,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 951/1900 [19:13<19:37,  1.24s/it]
+
+
Evaluating eval...:  50%|█████     | 952/1900 [19:14<19:47,  1.25s/it]
+
+
Evaluating eval...:  50%|█████     | 953/1900 [19:15<19:20,  1.23s/it]
+
+
Evaluating eval...:  50%|█████     | 954/1900 [19:16<19:00,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 955/1900 [19:17<18:59,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 956/1900 [19:19<18:49,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 957/1900 [19:20<18:37,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 958/1900 [19:21<18:43,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 959/1900 [19:22<18:42,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 960/1900 [19:23<18:54,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 961/1900 [19:25<19:16,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 962/1900 [19:26<19:00,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 963/1900 [19:27<19:03,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 964/1900 [19:28<19:13,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 965/1900 [19:30<19:03,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 966/1900 [19:31<18:41,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 967/1900 [19:32<18:31,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 968/1900 [19:33<18:26,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 969/1900 [19:34<18:33,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 970/1900 [19:36<18:47,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 971/1900 [19:37<18:42,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 972/1900 [19:38<19:05,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 973/1900 [19:39<18:43,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 974/1900 [19:40<18:33,  1.20s/it]
+
+
Evaluating eval...:  51%|█████▏    | 975/1900 [19:42<18:52,  1.22s/it]
+
+
Evaluating eval...:  51%|█████▏    | 976/1900 [19:43<18:56,  1.23s/it]
+
+
Evaluating eval...:  51%|█████▏    | 977/1900 [19:44<18:34,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 978/1900 [19:45<18:49,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 979/1900 [19:47<18:37,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 980/1900 [19:48<18:27,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 981/1900 [19:49<18:08,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 982/1900 [19:50<17:59,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 983/1900 [19:51<18:07,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 984/1900 [19:52<18:02,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 985/1900 [19:54<17:57,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 986/1900 [19:55<17:54,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 987/1900 [19:56<18:00,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 988/1900 [19:57<17:58,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 989/1900 [19:58<18:10,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 990/1900 [20:00<18:27,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 991/1900 [20:01<18:17,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 992/1900 [20:02<18:08,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 993/1900 [20:03<18:14,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 994/1900 [20:04<18:11,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 995/1900 [20:06<18:27,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 996/1900 [20:07<18:12,  1.21s/it]
+
+
Evaluating eval...:  52%|████���▏    | 997/1900 [20:08<18:08,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 998/1900 [20:09<17:57,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 999/1900 [20:10<17:58,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1000/1900 [20:12<17:46,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1001/1900 [20:13<17:47,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1002/1900 [20:14<17:50,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1003/1900 [20:15<18:06,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1004/1900 [20:16<18:09,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1005/1900 [20:18<17:49,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1006/1900 [20:19<17:46,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1007/1900 [20:20<17:50,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1008/1900 [20:21<17:41,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1009/1900 [20:22<17:41,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1010/1900 [20:23<17:35,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1011/1900 [20:25<17:36,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1012/1900 [20:26<18:04,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1013/1900 [20:27<17:44,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1014/1900 [20:28<18:06,  1.23s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1015/1900 [20:30<17:54,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1016/1900 [20:31<18:21,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1017/1900 [20:32<18:18,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1018/1900 [20:33<18:14,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1019/1900 [20:35<18:20,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1020/1900 [20:36<18:14,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1021/1900 [20:37<18:05,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1022/1900 [20:38<18:12,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1023/1900 [20:40<18:31,  1.27s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1024/1900 [20:41<18:12,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1025/1900 [20:42<17:45,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1026/1900 [20:43<17:58,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1027/1900 [20:45<17:45,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1028/1900 [20:46<17:32,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1029/1900 [20:47<17:29,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1030/1900 [20:48<17:22,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1031/1900 [20:49<17:56,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1032/1900 [20:51<17:37,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1033/1900 [20:52<17:18,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1034/1900 [20:53<17:49,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1035/1900 [20:54<17:30,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1036/1900 [20:55<17:31,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1037/1900 [20:57<17:27,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1038/1900 [20:58<17:24,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1039/1900 [20:59<17:25,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1040/1900 [21:00<17:16,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1041/1900 [21:01<17:15,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1042/1900 [21:03<17:21,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1043/1900 [21:04<17:09,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1044/1900 [21:05<17:10,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1045/1900 [21:06<16:56,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1046/1900 [21:07<17:00,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1047/1900 [21:09<16:52,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1048/1900 [21:10<16:57,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1049/1900 [21:11<16:57,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1050/1900 [21:12<17:17,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1051/1900 [21:14<17:25,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1052/1900 [21:15<17:23,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1053/1900 [21:16<17:16,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1054/1900 [21:17<17:01,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1055/1900 [21:18<16:46,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1056/1900 [21:20<17:08,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1057/1900 [21:21<17:19,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1058/1900 [21:22<17:09,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1059/1900 [21:23<16:47,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1060/1900 [21:24<16:34,  1.18s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1061/1900 [21:26<16:31,  1.18s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1062/1900 [21:27<16:29,  1.18s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1063/1900 [21:28<16:36,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1064/1900 [21:29<16:48,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1065/1900 [21:30<16:43,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1066/1900 [21:32<16:34,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1067/1900 [21:33<16:42,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1068/1900 [21:34<16:39,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1069/1900 [21:35<16:45,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1070/1900 [21:36<16:39,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1071/1900 [21:38<16:56,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1072/1900 [21:39<17:03,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1073/1900 [21:40<16:43,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1074/1900 [21:41<16:36,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1075/1900 [21:42<16:38,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1076/1900 [21:44<16:50,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1077/1900 [21:45<16:45,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1078/1900 [21:46<16:21,  1.19s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1079/1900 [21:47<16:38,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1080/1900 [21:49<17:15,  1.26s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1081/1900 [21:50<16:58,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1082/1900 [21:51<16:41,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1083/1900 [21:52<16:44,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1084/1900 [21:54<16:28,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1085/1900 [21:55<16:31,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1086/1900 [21:56<16:39,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1087/1900 [21:57<16:29,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1088/1900 [21:58<16:23,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1089/1900 [22:00<16:51,  1.25s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1090/1900 [22:01<16:34,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1091/1900 [22:02<16:12,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1092/1900 [22:03<16:36,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1093/1900 [22:05<16:19,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1094/1900 [22:06<16:11,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1095/1900 [22:07<16:08,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1096/1900 [22:08<15:57,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1097/1900 [22:09<15:46,  1.18s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1098/1900 [22:10<16:08,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1099/1900 [22:12<16:27,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1100/1900 [22:13<16:18,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1101/1900 [22:14<16:10,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1102/1900 [22:15<16:00,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1103/1900 [22:17<16:11,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1104/1900 [22:18<16:01,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1105/1900 [22:19<16:35,  1.25s/it]
+
+
Evaluating eval...:  58%|███���█▊    | 1106/1900 [22:20<16:39,  1.26s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1107/1900 [22:22<16:33,  1.25s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1108/1900 [22:23<16:19,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1109/1900 [22:24<16:11,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1110/1900 [22:25<15:59,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1111/1900 [22:27<16:33,  1.26s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1112/1900 [22:28<16:17,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1113/1900 [22:29<16:18,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1114/1900 [22:30<16:14,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1115/1900 [22:32<16:07,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1116/1900 [22:33<16:00,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1117/1900 [22:34<15:47,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1118/1900 [22:35<15:35,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1119/1900 [22:36<15:42,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1120/1900 [22:38<15:48,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1121/1900 [22:39<15:53,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1122/1900 [22:40<15:34,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1123/1900 [22:41<15:39,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1124/1900 [22:42<15:32,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1125/1900 [22:44<15:36,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1126/1900 [22:45<15:41,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1127/1900 [22:46<15:34,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1128/1900 [22:47<15:46,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1129/1900 [22:48<15:40,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1130/1900 [22:50<15:24,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1131/1900 [22:51<15:30,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1132/1900 [22:52<15:35,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1133/1900 [22:53<15:37,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1134/1900 [22:55<15:33,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1135/1900 [22:56<15:57,  1.25s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1136/1900 [22:57<15:37,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1137/1900 [22:58<15:27,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1138/1900 [22:59<15:37,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1139/1900 [23:01<15:28,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1140/1900 [23:02<15:24,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1141/1900 [23:03<15:27,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1142/1900 [23:04<15:14,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1143/1900 [23:05<15:06,  1.20s/it]
+
+
Evaluating eval...:  60%|██████    | 1144/1900 [23:07<15:02,  1.19s/it]
+
+
Evaluating eval...:  60%|██████    | 1145/1900 [23:08<15:08,  1.20s/it]
+
+
Evaluating eval...:  60%|██████    | 1146/1900 [23:09<15:17,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1147/1900 [23:10<15:18,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1148/1900 [23:12<15:20,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1149/1900 [23:13<15:13,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1150/1900 [23:14<15:22,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1151/1900 [23:15<15:10,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1152/1900 [23:16<15:00,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1153/1900 [23:18<15:13,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1154/1900 [23:19<15:07,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1155/1900 [23:20<15:00,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1156/1900 [23:21<14:45,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1157/1900 [23:22<14:56,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1158/1900 [23:24<15:28,  1.25s/it]
+
+
Evaluating eval...:  61%|██████    | 1159/1900 [23:25<15:08,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1160/1900 [23:26<15:08,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1161/1900 [23:27<15:09,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1162/1900 [23:29<14:56,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1163/1900 [23:30<14:53,  1.21s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1164/1900 [23:31<14:39,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1165/1900 [23:32<14:33,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1166/1900 [23:33<14:42,  1.20s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1167/1900 [23:35<14:45,  1.21s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1168/1900 [23:36<14:46,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1169/1900 [23:37<14:44,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1170/1900 [23:38<14:53,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1171/1900 [23:40<14:57,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1172/1900 [23:41<14:57,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1173/1900 [23:42<14:40,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1174/1900 [23:43<14:29,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1175/1900 [23:44<14:38,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1176/1900 [23:46<14:51,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1177/1900 [23:47<14:38,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1178/1900 [23:48<14:24,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1179/1900 [23:49<14:25,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1180/1900 [23:50<14:24,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1181/1900 [23:52<14:11,  1.18s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1182/1900 [23:53<14:27,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1183/1900 [23:54<14:36,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1184/1900 [23:55<14:35,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1185/1900 [23:56<14:36,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1186/1900 [23:58<14:50,  1.25s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1187/1900 [23:59<14:42,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1188/1900 [24:00<14:33,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1189/1900 [24:01<14:29,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1190/1900 [24:03<14:21,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1191/1900 [24:04<14:38,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1192/1900 [24:05<14:54,  1.26s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1193/1900 [24:06<14:43,  1.25s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1194/1900 [24:08<14:50,  1.26s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1195/1900 [24:09<14:40,  1.25s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1196/1900 [24:10<14:28,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1197/1900 [24:11<14:31,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1198/1900 [24:13<14:23,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1199/1900 [24:14<14:41,  1.26s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1200/1900 [24:15<14:30,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1201/1900 [24:16<14:17,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1202/1900 [24:17<14:04,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1203/1900 [24:19<14:16,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1204/1900 [24:20<14:24,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1205/1900 [24:21<14:08,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1206/1900 [24:22<14:17,  1.24s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1207/1900 [24:24<14:02,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1208/1900 [24:25<14:02,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1209/1900 [24:26<13:53,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1210/1900 [24:27<14:01,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1211/1900 [24:29<14:03,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1212/1900 [24:30<14:02,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1213/1900 [24:31<13:52,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1214/1900 [24:32<13:44,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1215/1900 [24:33<13:40,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1216/1900 [24:35<13:47,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1217/1900 [24:36<13:54,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1218/1900 [24:37<14:01,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1219/1900 [24:38<13:52,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1220/1900 [24:39<13:48,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1221/1900 [24:41<13:46,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1222/1900 [24:42<13:41,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1223/1900 [24:43<13:42,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1224/1900 [24:44<13:31,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1225/1900 [24:46<13:38,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1226/1900 [24:47<13:34,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1227/1900 [24:48<13:29,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1228/1900 [24:49<13:24,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1229/1900 [24:50<13:23,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1230/1900 [24:51<13:25,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1231/1900 [24:53<13:28,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1232/1900 [24:54<13:28,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1233/1900 [24:55<13:29,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1234/1900 [24:56<13:27,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1235/1900 [24:58<13:38,  1.23s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1236/1900 [24:59<13:28,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1237/1900 [25:00<13:18,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1238/1900 [25:01<13:13,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1239/1900 [25:02<13:13,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1240/1900 [25:04<13:38,  1.24s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1241/1900 [25:05<13:24,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1242/1900 [25:06<13:17,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1243/1900 [25:07<13:36,  1.24s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1244/1900 [25:09<13:14,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1245/1900 [25:10<13:00,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1246/1900 [25:11<13:06,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1247/1900 [25:12<13:00,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1248/1900 [25:13<12:52,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1249/1900 [25:14<13:00,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1250/1900 [25:16<13:00,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1251/1900 [25:17<12:56,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1252/1900 [25:18<12:53,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1253/1900 [25:19<12:55,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1254/1900 [25:21<13:00,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1255/1900 [25:22<13:17,  1.24s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1256/1900 [25:23<13:09,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1257/1900 [25:24<12:52,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1258/1900 [25:25<12:53,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1259/1900 [25:27<12:43,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1260/1900 [25:28<12:43,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1261/1900 [25:29<12:40,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1262/1900 [25:30<12:30,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1263/1900 [25:31<12:37,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1264/1900 [25:32<12:41,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1265/1900 [25:34<12:41,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1266/1900 [25:35<12:55,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1267/1900 [25:36<12:51,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1268/1900 [25:37<12:46,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1269/1900 [25:39<12:51,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1270/1900 [25:40<12:41,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1271/1900 [25:41<12:42,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1272/1900 [25:42<12:32,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1273/1900 [25:43<12:29,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1274/1900 [25:45<12:30,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1275/1900 [25:46<12:26,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1276/1900 [25:47<12:29,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1277/1900 [25:48<12:28,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1278/1900 [25:49<12:19,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1279/1900 [25:51<12:19,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1280/1900 [25:52<12:19,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1281/1900 [25:53<12:11,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1282/1900 [25:54<12:08,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1283/1900 [25:55<12:08,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1284/1900 [25:56<12:09,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1285/1900 [25:58<12:12,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1286/1900 [25:59<12:17,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1287/1900 [26:00<12:36,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1288/1900 [26:01<12:34,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1289/1900 [26:03<12:19,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1290/1900 [26:04<12:14,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1291/1900 [26:05<12:07,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1292/1900 [26:06<12:14,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1293/1900 [26:07<12:10,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1294/1900 [26:09<12:22,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1295/1900 [26:10<12:14,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1296/1900 [26:11<12:14,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1297/1900 [26:12<11:59,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1298/1900 [26:13<12:04,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1299/1900 [26:15<12:04,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1300/1900 [26:16<12:14,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1301/1900 [26:17<12:16,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1302/1900 [26:18<12:05,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1303/1900 [26:20<12:09,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1304/1900 [26:21<12:09,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1305/1900 [26:22<12:03,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1306/1900 [26:23<12:08,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1307/1900 [26:24<11:56,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1308/1900 [26:26<11:52,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1309/1900 [26:27<11:51,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1310/1900 [26:28<11:47,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1311/1900 [26:29<11:50,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1312/1900 [26:30<11:47,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1313/1900 [26:32<11:59,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1314/1900 [26:33<11:52,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1315/1900 [26:34<11:54,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1316/1900 [26:35<11:59,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1317/1900 [26:37<11:58,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1318/1900 [26:38<12:19,  1.27s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1319/1900 [26:39<12:03,  1.24s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1320/1900 [26:40<11:44,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1321/1900 [26:42<11:55,  1.24s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1322/1900 [26:43<11:43,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1323/1900 [26:44<11:40,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1324/1900 [26:45<11:30,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1325/1900 [26:46<11:22,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1326/1900 [26:47<11:24,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1327/1900 [26:49<11:21,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1328/1900 [26:50<11:29,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1329/1900 [26:51<11:22,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1330/1900 [26:52<11:29,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1331/1900 [26:54<11:26,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1332/1900 [26:55<11:26,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1333/1900 [26:56<11:21,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1334/1900 [26:57<11:20,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1335/1900 [26:58<11:17,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1336/1900 [26:59<11:12,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1337/1900 [27:01<11:20,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1338/1900 [27:02<11:14,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1339/1900 [27:03<11:12,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1340/1900 [27:04<11:14,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1341/1900 [27:06<11:08,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1342/1900 [27:07<11:11,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1343/1900 [27:08<11:04,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1344/1900 [27:09<11:08,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1345/1900 [27:10<11:17,  1.22s/it]
+
+
Evaluating eval...:  71%|███████   | 1346/1900 [27:12<11:37,  1.26s/it]
+
+
Evaluating eval...:  71%|███████   | 1347/1900 [27:13<11:24,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1348/1900 [27:14<11:11,  1.22s/it]
+
+
Evaluating eval...:  71%|███████   | 1349/1900 [27:15<11:26,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1350/1900 [27:17<11:15,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1351/1900 [27:18<11:20,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1352/1900 [27:19<11:18,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1353/1900 [27:20<11:21,  1.25s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1354/1900 [27:22<11:18,  1.24s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1355/1900 [27:23<11:06,  1.22s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1356/1900 [27:24<11:12,  1.24s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1357/1900 [27:25<11:00,  1.22s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1358/1900 [27:26<10:52,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1359/1900 [27:28<10:50,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1360/1900 [27:29<10:43,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1361/1900 [27:30<10:50,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1362/1900 [27:31<10:43,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1363/1900 [27:32<10:59,  1.23s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1364/1900 [27:34<10:49,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1365/1900 [27:35<10:42,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1366/1900 [27:36<10:35,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1367/1900 [27:37<10:36,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1368/1900 [27:38<10:47,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1369/1900 [27:40<10:44,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1370/1900 [27:41<10:50,  1.23s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1371/1900 [27:42<10:44,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1372/1900 [27:43<10:34,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1373/1900 [27:44<10:26,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1374/1900 [27:46<10:21,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1375/1900 [27:47<10:25,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1376/1900 [27:48<10:29,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1377/1900 [27:49<10:30,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1378/1900 [27:50<10:19,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1379/1900 [27:52<10:19,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1380/1900 [27:53<10:25,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1381/1900 [27:54<10:29,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1382/1900 [27:55<10:27,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1383/1900 [27:56<10:27,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1384/1900 [27:58<10:23,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1385/1900 [27:59<10:25,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1386/1900 [28:00<10:29,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1387/1900 [28:01<10:19,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1388/1900 [28:03<10:17,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1389/1900 [28:04<10:09,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1390/1900 [28:05<10:28,  1.23s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1391/1900 [28:06<10:22,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1392/1900 [28:07<10:17,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1393/1900 [28:09<10:12,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1394/1900 [28:10<10:21,  1.23s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1395/1900 [28:11<10:17,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1396/1900 [28:12<10:10,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1397/1900 [28:13<10:03,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1398/1900 [28:15<10:09,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1399/1900 [28:16<10:08,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1400/1900 [28:17<10:00,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1401/1900 [28:18<10:13,  1.23s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1402/1900 [28:20<10:00,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1403/1900 [28:21<09:56,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1404/1900 [28:22<09:51,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1405/1900 [28:23<09:42,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1406/1900 [28:24<09:45,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1407/1900 [28:25<09:52,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1408/1900 [28:27<10:04,  1.23s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1409/1900 [28:28<09:57,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1410/1900 [28:29<09:53,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1411/1900 [28:30<09:49,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1412/1900 [28:32<09:52,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1413/1900 [28:33<09:49,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1414/1900 [28:34<09:48,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1415/1900 [28:35<09:43,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1416/1900 [28:36<09:33,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1417/1900 [28:38<09:35,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1418/1900 [28:39<09:30,  1.18s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1419/1900 [28:40<09:44,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1420/1900 [28:41<09:42,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1421/1900 [28:42<09:40,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1422/1900 [28:44<09:47,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1423/1900 [28:45<09:37,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1424/1900 [28:46<09:38,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1425/1900 [28:47<09:34,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1426/1900 [28:48<09:30,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1427/1900 [28:50<09:29,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1428/1900 [28:51<09:37,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1429/1900 [28:52<09:33,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1430/1900 [28:53<09:25,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1431/1900 [28:55<09:39,  1.24s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1432/1900 [28:56<10:04,  1.29s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1433/1900 [28:57<09:54,  1.27s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1434/1900 [28:58<09:43,  1.25s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1435/1900 [29:00<09:37,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1436/1900 [29:01<09:36,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1437/1900 [29:02<09:31,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1438/1900 [29:03<09:24,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1439/1900 [29:05<09:19,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1440/1900 [29:06<09:22,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1441/1900 [29:07<09:15,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1442/1900 [29:08<09:16,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1443/1900 [29:09<09:22,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1444/1900 [29:11<09:15,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1445/1900 [29:12<09:12,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1446/1900 [29:13<09:11,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1447/1900 [29:14<09:04,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1448/1900 [29:15<09:01,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1449/1900 [29:17<08:58,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1450/1900 [29:18<09:02,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1451/1900 [29:19<09:07,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1452/1900 [29:20<09:01,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1453/1900 [29:22<09:06,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1454/1900 [29:23<09:19,  1.26s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1455/1900 [29:24<09:09,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1456/1900 [29:25<09:09,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1457/1900 [29:27<09:05,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1458/1900 [29:28<09:05,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1459/1900 [29:29<08:58,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1460/1900 [29:30<08:51,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1461/1900 [29:31<08:47,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1462/1900 [29:33<08:46,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1463/1900 [29:34<08:46,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1464/1900 [29:35<08:51,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1465/1900 [29:36<08:45,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1466/1900 [29:37<08:52,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1467/1900 [29:39<08:43,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1468/1900 [29:40<08:55,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1469/1900 [29:41<08:54,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1470/1900 [29:42<08:43,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1471/1900 [29:44<08:45,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1472/1900 [29:45<08:39,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1473/1900 [29:46<08:40,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1474/1900 [29:47<08:35,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1475/1900 [29:48<08:39,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1476/1900 [29:50<08:39,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1477/1900 [29:51<08:35,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1478/1900 [29:52<08:35,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1479/1900 [29:53<08:45,  1.25s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1480/1900 [29:55<08:33,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1481/1900 [29:56<08:32,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1482/1900 [29:57<08:26,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1483/1900 [29:58<08:19,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1484/1900 [29:59<08:26,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1485/1900 [30:01<08:30,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1486/1900 [30:02<08:24,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1487/1900 [30:03<08:32,  1.24s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1488/1900 [30:04<08:20,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1489/1900 [30:05<08:12,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1490/1900 [30:07<08:13,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1491/1900 [30:08<08:08,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1492/1900 [30:09<08:10,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1493/1900 [30:10<08:14,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1494/1900 [30:11<08:07,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1495/1900 [30:13<08:04,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1496/1900 [30:14<07:59,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1497/1900 [30:15<07:57,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1498/1900 [30:16<07:59,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1499/1900 [30:17<08:01,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1500/1900 [30:19<08:03,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1501/1900 [30:20<07:57,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1502/1900 [30:21<07:55,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1503/1900 [30:22<07:54,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1504/1900 [30:23<07:49,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1505/1900 [30:25<07:51,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1506/1900 [30:26<07:56,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1507/1900 [30:27<07:54,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1508/1900 [30:28<07:56,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1509/1900 [30:30<08:04,  1.24s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1510/1900 [30:31<07:57,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1511/1900 [30:32<07:58,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1512/1900 [30:33<08:04,  1.25s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1513/1900 [30:35<08:04,  1.25s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1514/1900 [30:36<08:01,  1.25s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1515/1900 [30:37<08:07,  1.27s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1516/1900 [30:38<08:02,  1.26s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1517/1900 [30:39<07:49,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1518/1900 [30:41<07:40,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1519/1900 [30:42<07:35,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1520/1900 [30:43<07:40,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1521/1900 [30:44<07:40,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1522/1900 [30:45<07:32,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1523/1900 [30:47<07:33,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1524/1900 [30:48<07:36,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1525/1900 [30:49<07:35,  1.22s/it]
+
+
Evaluating eval...:  80%|████████  | 1526/1900 [30:50<07:29,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1527/1900 [30:52<07:29,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1528/1900 [30:53<07:29,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1529/1900 [30:54<07:24,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1530/1900 [30:55<07:27,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1531/1900 [30:56<07:27,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1532/1900 [30:58<07:34,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1533/1900 [30:59<07:24,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1534/1900 [31:00<07:21,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1535/1900 [31:01<07:12,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1536/1900 [31:02<07:07,  1.18s/it]
+
+
Evaluating eval...:  81%|████████  | 1537/1900 [31:04<07:14,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1538/1900 [31:05<07:10,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1539/1900 [31:06<07:18,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1540/1900 [31:07<07:13,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1541/1900 [31:08<07:22,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1542/1900 [31:10<07:15,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1543/1900 [31:11<07:12,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1544/1900 [31:12<07:11,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1545/1900 [31:13<07:04,  1.20s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1546/1900 [31:14<07:09,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1547/1900 [31:16<07:13,  1.23s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1548/1900 [31:17<07:06,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1549/1900 [31:18<07:00,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1550/1900 [31:19<07:05,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1551/1900 [31:21<07:03,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1552/1900 [31:22<06:56,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1553/1900 [31:23<06:54,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1554/1900 [31:24<06:51,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1555/1900 [31:25<06:49,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1556/1900 [31:27<07:02,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1557/1900 [31:28<06:57,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1558/1900 [31:29<07:02,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1559/1900 [31:30<06:59,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1560/1900 [31:31<06:51,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1561/1900 [31:33<06:57,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1562/1900 [31:34<06:59,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1563/1900 [31:35<06:56,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1564/1900 [31:36<06:48,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1565/1900 [31:38<06:45,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1566/1900 [31:39<06:45,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1567/1900 [31:40<06:43,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1568/1900 [31:41<06:59,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1569/1900 [31:43<06:58,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1570/1900 [31:44<06:52,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1571/1900 [31:45<06:44,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1572/1900 [31:46<06:50,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1573/1900 [31:47<06:41,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1574/1900 [31:49<06:35,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1575/1900 [31:50<06:36,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1576/1900 [31:51<06:29,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1577/1900 [31:52<06:34,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1578/1900 [31:54<06:32,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1579/1900 [31:55<06:30,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1580/1900 [31:56<06:35,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1581/1900 [31:57<06:44,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1582/1900 [31:59<06:41,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1583/1900 [32:00<06:34,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1584/1900 [32:01<06:41,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1585/1900 [32:02<06:39,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1586/1900 [32:04<06:35,  1.26s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1587/1900 [32:05<06:23,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1588/1900 [32:06<06:14,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1589/1900 [32:07<06:15,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1590/1900 [32:08<06:18,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1591/1900 [32:10<06:25,  1.25s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1592/1900 [32:11<06:17,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1593/1900 [32:12<06:17,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1594/1900 [32:13<06:19,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1595/1900 [32:15<06:17,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1596/1900 [32:16<06:16,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1597/1900 [32:17<06:14,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1598/1900 [32:18<06:05,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1599/1900 [32:19<05:58,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1600/1900 [32:21<05:55,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1601/1900 [32:22<05:53,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1602/1900 [32:23<05:53,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1603/1900 [32:24<05:54,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1604/1900 [32:25<06:01,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1605/1900 [32:27<05:54,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1606/1900 [32:28<05:53,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1607/1900 [32:29<05:52,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1608/1900 [32:30<05:54,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1609/1900 [32:32<06:00,  1.24s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1610/1900 [32:33<05:55,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1611/1900 [32:34<05:48,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1612/1900 [32:35<05:43,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1613/1900 [32:36<05:37,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1614/1900 [32:37<05:42,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1615/1900 [32:39<05:39,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1616/1900 [32:40<05:36,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1617/1900 [32:41<05:40,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1618/1900 [32:42<05:42,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1619/1900 [32:44<05:43,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1620/1900 [32:45<05:42,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1621/1900 [32:46<05:38,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1622/1900 [32:47<05:32,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1623/1900 [32:48<05:32,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1624/1900 [32:49<05:28,  1.19s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1625/1900 [32:51<05:30,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1626/1900 [32:52<05:34,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1627/1900 [32:53<05:33,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1628/1900 [32:54<05:31,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1629/1900 [32:56<05:30,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1630/1900 [32:57<05:29,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1631/1900 [32:58<05:36,  1.25s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1632/1900 [32:59<05:30,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1633/1900 [33:01<05:30,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1634/1900 [33:02<05:26,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1635/1900 [33:03<05:20,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1636/1900 [33:04<05:20,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1637/1900 [33:05<05:25,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1638/1900 [33:07<05:17,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1639/1900 [33:08<05:18,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1640/1900 [33:09<05:17,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1641/1900 [33:10<05:13,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1642/1900 [33:12<05:12,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1643/1900 [33:13<05:09,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1644/1900 [33:14<05:02,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1645/1900 [33:15<04:58,  1.17s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1646/1900 [33:16<05:00,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1647/1900 [33:17<05:01,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1648/1900 [33:19<05:03,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1649/1900 [33:20<05:00,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1650/1900 [33:21<05:00,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1651/1900 [33:22<04:55,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1652/1900 [33:23<04:54,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1653/1900 [33:25<04:52,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1654/1900 [33:26<04:53,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1655/1900 [33:27<04:57,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1656/1900 [33:28<04:57,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1657/1900 [33:29<04:56,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1658/1900 [33:31<04:54,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1659/1900 [33:32<05:00,  1.25s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1660/1900 [33:33<04:58,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1661/1900 [33:34<04:57,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1662/1900 [33:36<04:52,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1663/1900 [33:37<04:46,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1664/1900 [33:38<04:49,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1665/1900 [33:39<04:47,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1666/1900 [33:41<05:01,  1.29s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1667/1900 [33:42<04:58,  1.28s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1668/1900 [33:43<04:51,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1669/1900 [33:44<04:49,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1670/1900 [33:46<04:47,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1671/1900 [33:47<04:47,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1672/1900 [33:48<04:44,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1673/1900 [33:49<04:43,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1674/1900 [33:51<04:42,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1675/1900 [33:52<04:40,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1676/1900 [33:53<04:35,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1677/1900 [33:54<04:29,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1678/1900 [33:55<04:25,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1679/1900 [33:57<04:26,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1680/1900 [33:58<04:23,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1681/1900 [33:59<04:23,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1682/1900 [34:00<04:21,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1683/1900 [34:02<04:24,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1684/1900 [34:03<04:21,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1685/1900 [34:04<04:17,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1686/1900 [34:05<04:17,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1687/1900 [34:06<04:18,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1688/1900 [34:08<04:18,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1689/1900 [34:09<04:15,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1690/1900 [34:10<04:11,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1691/1900 [34:11<04:16,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1692/1900 [34:12<04:12,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1693/1900 [34:14<04:16,  1.24s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1694/1900 [34:15<04:14,  1.24s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1695/1900 [34:16<04:11,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1696/1900 [34:17<04:06,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1697/1900 [34:19<04:07,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1698/1900 [34:20<04:05,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1699/1900 [34:21<04:01,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1700/1900 [34:22<04:03,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1701/1900 [34:24<04:08,  1.25s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1702/1900 [34:25<04:05,  1.24s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1703/1900 [34:26<04:02,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1704/1900 [34:27<03:57,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1705/1900 [34:28<03:52,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1706/1900 [34:29<03:52,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1707/1900 [34:31<03:49,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1708/1900 [34:32<03:50,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1709/1900 [34:33<03:50,  1.21s/it]
+
+
Evaluating eval...:  90%|█████████ | 1710/1900 [34:34<03:48,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1711/1900 [34:35<03:45,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1712/1900 [34:37<03:43,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1713/1900 [34:38<03:39,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1714/1900 [34:39<03:37,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1715/1900 [34:40<03:39,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1716/1900 [34:41<03:37,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1717/1900 [34:43<03:45,  1.23s/it]
+
+
Evaluating eval...:  90%|█████████ | 1718/1900 [34:44<03:47,  1.25s/it]
+
+
Evaluating eval...:  90%|█████████ | 1719/1900 [34:45<03:43,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1720/1900 [34:46<03:43,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1721/1900 [34:48<03:39,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1722/1900 [34:49<03:38,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1723/1900 [34:50<03:32,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1724/1900 [34:51<03:38,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1725/1900 [34:53<03:36,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1726/1900 [34:54<03:34,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1727/1900 [34:55<03:33,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1728/1900 [34:56<03:27,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1729/1900 [34:57<03:23,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████ | 1730/1900 [34:59<03:26,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1731/1900 [35:00<03:22,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1732/1900 [35:01<03:23,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1733/1900 [35:02<03:23,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1734/1900 [35:03<03:20,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1735/1900 [35:05<03:18,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1736/1900 [35:06<03:19,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1737/1900 [35:07<03:18,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1738/1900 [35:08<03:15,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1739/1900 [35:09<03:16,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1740/1900 [35:11<03:14,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1741/1900 [35:12<03:12,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1742/1900 [35:13<03:08,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1743/1900 [35:14<03:06,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1744/1900 [35:15<03:05,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1745/1900 [35:17<03:03,  1.18s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1746/1900 [35:18<03:07,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1747/1900 [35:19<03:05,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1748/1900 [35:20<03:04,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1749/1900 [35:22<03:04,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1750/1900 [35:23<03:04,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1751/1900 [35:24<03:02,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1752/1900 [35:25<02:59,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1753/1900 [35:26<02:56,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1754/1900 [35:28<02:55,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1755/1900 [35:29<02:55,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1756/1900 [35:30<02:54,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1757/1900 [35:31<02:54,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1758/1900 [35:32<02:53,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1759/1900 [35:34<02:48,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1760/1900 [35:35<02:45,  1.18s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1761/1900 [35:36<02:45,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1762/1900 [35:37<02:45,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1763/1900 [35:38<02:42,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1764/1900 [35:40<02:45,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1765/1900 [35:41<02:45,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1766/1900 [35:42<02:43,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1767/1900 [35:43<02:42,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1768/1900 [35:45<02:42,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1769/1900 [35:46<02:43,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1770/1900 [35:47<02:46,  1.28s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1771/1900 [35:48<02:44,  1.28s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1772/1900 [35:50<02:39,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1773/1900 [35:51<02:37,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1774/1900 [35:52<02:34,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1775/1900 [35:53<02:35,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1776/1900 [35:55<02:31,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1777/1900 [35:56<02:28,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1778/1900 [35:57<02:26,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1779/1900 [35:58<02:23,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1780/1900 [35:59<02:22,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1781/1900 [36:00<02:20,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1782/1900 [36:02<02:24,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1783/1900 [36:03<02:25,  1.24s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1784/1900 [36:04<02:23,  1.24s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1785/1900 [36:05<02:20,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1786/1900 [36:07<02:18,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1787/1900 [36:08<02:17,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1788/1900 [36:09<02:14,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1789/1900 [36:10<02:11,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1790/1900 [36:11<02:12,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1791/1900 [36:13<02:11,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1792/1900 [36:14<02:09,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1793/1900 [36:15<02:10,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1794/1900 [36:16<02:07,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1795/1900 [36:17<02:06,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1796/1900 [36:19<02:03,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1797/1900 [36:20<02:03,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1798/1900 [36:21<02:04,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1799/1900 [36:22<02:03,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1800/1900 [36:23<02:01,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1801/1900 [36:25<01:58,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1802/1900 [36:26<01:57,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1803/1900 [36:27<01:56,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1804/1900 [36:28<01:54,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1805/1900 [36:29<01:52,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1806/1900 [36:31<01:52,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1807/1900 [36:32<01:50,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1808/1900 [36:33<01:48,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1809/1900 [36:34<01:46,  1.17s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1810/1900 [36:35<01:46,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1811/1900 [36:37<01:48,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1812/1900 [36:38<01:46,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1813/1900 [36:39<01:44,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1814/1900 [36:40<01:44,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1815/1900 [36:41<01:42,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1816/1900 [36:43<01:41,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1817/1900 [36:44<01:43,  1.25s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1818/1900 [36:45<01:40,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1819/1900 [36:46<01:38,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1820/1900 [36:48<01:36,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1821/1900 [36:49<01:35,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1822/1900 [36:50<01:34,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1823/1900 [36:51<01:31,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1824/1900 [36:52<01:31,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1825/1900 [36:54<01:30,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1826/1900 [36:55<01:29,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1827/1900 [36:56<01:29,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1828/1900 [36:57<01:28,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1829/1900 [36:59<01:29,  1.26s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1830/1900 [37:00<01:26,  1.24s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1831/1900 [37:01<01:23,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1832/1900 [37:02<01:21,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1833/1900 [37:03<01:19,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1834/1900 [37:05<01:19,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1835/1900 [37:06<01:18,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1836/1900 [37:07<01:17,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1837/1900 [37:08<01:17,  1.24s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1838/1900 [37:09<01:15,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1839/1900 [37:11<01:14,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1840/1900 [37:12<01:13,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1841/1900 [37:13<01:12,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1842/1900 [37:14<01:11,  1.23s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1843/1900 [37:15<01:09,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1844/1900 [37:17<01:07,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1845/1900 [37:18<01:07,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1846/1900 [37:19<01:06,  1.24s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1847/1900 [37:20<01:05,  1.23s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1848/1900 [37:22<01:05,  1.25s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1849/1900 [37:23<01:03,  1.24s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1850/1900 [37:24<01:01,  1.23s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1851/1900 [37:25<00:59,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1852/1900 [37:27<00:57,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1853/1900 [37:28<00:56,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1854/1900 [37:29<00:54,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1855/1900 [37:30<00:55,  1.23s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1856/1900 [37:31<00:53,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1857/1900 [37:33<00:51,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1858/1900 [37:34<00:51,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1859/1900 [37:35<00:49,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1860/1900 [37:36<00:48,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1861/1900 [37:37<00:46,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1862/1900 [37:39<00:45,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1863/1900 [37:40<00:43,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1864/1900 [37:41<00:43,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1865/1900 [37:42<00:41,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1866/1900 [37:43<00:41,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1867/1900 [37:45<00:40,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1868/1900 [37:46<00:38,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1869/1900 [37:47<00:38,  1.24s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1870/1900 [37:48<00:36,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1871/1900 [37:50<00:36,  1.25s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1872/1900 [37:51<00:34,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1873/1900 [37:52<00:33,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1874/1900 [37:53<00:32,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1875/1900 [37:55<00:30,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1876/1900 [37:56<00:29,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1877/1900 [37:57<00:27,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1878/1900 [37:58<00:26,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1879/1900 [37:59<00:25,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1880/1900 [38:00<00:23,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1881/1900 [38:02<00:22,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1882/1900 [38:03<00:21,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1883/1900 [38:04<00:21,  1.25s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1884/1900 [38:05<00:20,  1.25s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1885/1900 [38:07<00:18,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1886/1900 [38:08<00:17,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1887/1900 [38:09<00:15,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1888/1900 [38:10<00:14,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1889/1900 [38:11<00:13,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1890/1900 [38:13<00:11,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1891/1900 [38:14<00:10,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1892/1900 [38:15<00:09,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1893/1900 [38:16<00:08,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1894/1900 [38:17<00:07,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1895/1900 [38:19<00:05,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1896/1900 [38:20<00:04,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1897/1900 [38:21<00:03,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1898/1900 [38:22<00:02,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1899/1900 [38:23<00:01,  1.20s/it]
+
+
Evaluating eval...: 100%|██████████| 1900/1900 [38:25<00:00,  1.32s/it]
Evaluating eval...: 100%|██████████| 1900/1900 [38:25<00:00,  1.21s/it]
+Eval results for step (50000 / 100000 | Eval Loss: 1.022052526473999 | Eval wer: 26.228243782120465 | Eval wer_ortho: 29.593900188808785 |)
+
                                                                             
Eval results for step (50000 / 100000 | Eval Loss: 1.022052526473999 | Eval wer: 26.228243782120465 | Eval wer_ortho: 29.593900188808785 |)
+
Train steps ... :  50%|█████     | 50000/100000 [15:16:30<8:07:44,  1.71it/s]
Train steps ... :  50%|█████     | 50001/100000 [15:16:31<10592:35:26, 762.68s/it]
Train steps ... :  50%|█████     | 50002/100000 [15:16:31<7417:05:57, 534.05s/it] 
Train steps ... :  50%|█████     | 50003/100000 [15:16:32<5194:17:53, 374.01s/it]
Train steps ... :  50%|█████     | 50004/100000 [15:16:32<3638:21:41, 261.98s/it]
Train steps ... :  50%|█████     | 50005/100000 [15:16:33<2549:14:47, 183.56s/it]
Train steps ... :  50%|█████     | 50006/100000 [15:16:34<1786:51:54, 128.67s/it]
Train steps ... :  50%|█████     | 50007/100000 [15:16:34<1253:13:05, 90.24s/it] 
Train steps ... :  50%|█████     | 50008/100000 [15:16:35<879:40:11, 63.35s/it] 
Train steps ... :  50%|█████     | 50009/100000 [15:16:35<618:11:09, 44.52s/it]
Train steps ... :  50%|█████     | 50010/100000 [15:16:36<435:09:12, 31.34s/it]
Train steps ... :  50%|█████     | 50011/100000 [15:16:37<307:01:50, 22.11s/it]
Train steps ... :  50%|█████     | 50012/100000 [15:16:37<217:20:45, 15.65s/it]
Train steps ... :  50%|█████     | 50013/100000 [15:16:38<154:34:24, 11.13s/it]
Train steps ... :  50%|█████     | 50014/100000 [15:16:38<110:37:33,  7.97s/it]
Train steps ... :  50%|█████     | 50015/100000 [15:16:39<79:52:19,  5.75s/it] 
Train steps ... :  50%|█████     | 50016/100000 [15:16:39<58:20:26,  4.20s/it]
Train steps ... :  50%|█████     | 50017/100000 [15:16:40<43:15:59,  3.12s/it]
Train steps ... :  50%|█████     | 50018/100000 [15:16:41<32:42:39,  2.36s/it]
Train steps ... :  50%|█████     | 50019/100000 [15:16:41<25:19:37,  1.82s/it]
Train steps ... :  50%|█████     | 50020/100000 [15:16:42<20:09:10,  1.45s/it]
Train steps ... :  50%|█████     | 50021/100000 [15:16:42<16:32:20,  1.19s/it]
Train steps ... :  50%|█████     | 50022/100000 [15:16:43<14:00:20,  1.01s/it]
Train steps ... :  50%|█████     | 50023/100000 [15:16:44<12:14:03,  1.13it/s]
Train steps ... :  50%|█████     | 50024/100000 [15:16:44<10:59:37,  1.26it/s]
Train steps ... :  50%|█████     | 50025/100000 [15:16:45<10:07:21,  1.37it/s]Step... (50025 / 100000 | Loss: 1.1170995235443115, Learning Rate: 5.022613065326633e-05)
+
                                                                              
Step... (50025 / 100000 | Loss: 0.7459732294082642, Learning Rate: 5.022613065326633e-05)
+
Train steps ... :  50%|█████     | 50025/100000 [15:16:45<10:07:21,  1.37it/s]
Train steps ... :  50%|█████     | 50026/100000 [15:16:45<9:31:06,  1.46it/s] 
Train steps ... :  50%|█████     | 50027/100000 [15:16:46<9:05:29,  1.53it/s]
Train steps ... :  50%|█████     | 50028/100000 [15:16:46<8:48:18,  1.58it/s]
Train steps ... :  50%|█████     | 50029/100000 [15:16:47<8:35:32,  1.62it/s]
Train steps ... :  50%|█████     | 50030/100000 [15:16:48<8:27:12,  1.64it/s]
Train steps ... :  50%|█████     | 50031/100000 [15:16:48<8:20:40,  1.66it/s]
Train steps ... :  50%|█████     | 50032/100000 [15:16:49<8:16:42,  1.68it/s]
Train steps ... :  50%|█████     | 50033/100000 [15:16:49<8:13:59,  1.69it/s]
Train steps ... :  50%|█████     | 50034/100000 [15:16:50<8:11:16,  1.70it/s]
Train steps ... :  50%|█████     | 50035/100000 [15:16:51<8:09:32,  1.70it/s]
Train steps ... :  50%|█████     | 50036/100000 [15:16:51<8:08:36,  1.70it/s]
Train steps ... :  50%|█████     | 50037/100000 [15:16:52<8:09:00,  1.70it/s]
Train steps ... :  50%|█████     | 50038/100000 [15:16:52<8:08:15,  1.71it/s]
Train steps ... :  50%|█████     | 50039/100000 [15:16:53<8:07:39,  1.71it/s]
Train steps ... :  50%|█████     | 50040/100000 [15:16:53<8:07:01,  1.71it/s]
Train steps ... :  50%|█████     | 50041/100000 [15:16:54<8:06:31,  1.71it/s]
Train steps ... :  50%|█████     | 50042/100000 [15:16:55<8:06:57,  1.71it/s]
Train steps ... :  50%|█████     | 50043/100000 [15:16:55<8:07:15,  1.71it/s]
Train steps ... :  50%|█████     | 50044/100000 [15:16:56<8:07:34,  1.71it/s]
Train steps ... :  50%|█████     | 50045/100000 [15:16:56<8:07:33,  1.71it/s]
Train steps ... :  50%|█████     | 50046/100000 [15:16:57<8:07:13,  1.71it/s]
Train steps ... :  50%|█████     | 50047/100000 [15:16:58<8:06:40,  1.71it/s]
Train steps ... :  50%|█████     | 50048/100000 [15:16:58<8:06:38,  1.71it/s]
Train steps ... :  50%|█████     | 50049/100000 [15:16:59<8:05:53,  1.71it/s]
Train steps ... :  50%|█████     | 50050/100000 [15:16:59<8:05:55,  1.71it/s]Step... (50050 / 100000 | Loss: 0.9389145374298096, Learning Rate: 5.0201005025125636e-05)
+
                                                                             
Step... (50050 / 100000 | Loss: 1.0904409885406494, Learning Rate: 5.0201005025125636e-05)
+
Train steps ... :  50%|█████     | 50050/100000 [15:17:00<8:05:55,  1.71it/s]
Train steps ... :  50%|█████     | 50051/100000 [15:17:00<8:07:13,  1.71it/s]
Train steps ... :  50%|█████     | 50052/100000 [15:17:00<8:07:21,  1.71it/s]
Train steps ... :  50%|█████     | 50053/100000 [15:17:01<8:06:42,  1.71it/s]
Train steps ... :  50%|█████     | 50054/100000 [15:17:02<8:06:05,  1.71it/s]
Train steps ... :  50%|█████     | 50055/100000 [15:17:02<8:05:55,  1.71it/s]
Train steps ... :  50%|█████     | 50056/100000 [15:17:03<8:06:17,  1.71it/s]
Train steps ... :  50%|█████     | 50057/100000 [15:17:03<8:06:03,  1.71it/s]
Train steps ... :  50%|█████     | 50058/100000 [15:17:04<8:05:41,  1.71it/s]
Train steps ... :  50%|█████     | 50059/100000 [15:17:05<8:05:45,  1.71it/s]
Train steps ... :  50%|█████     | 50060/100000 [15:17:05<8:05:43,  1.71it/s]
Train steps ... :  50%|█████     | 50061/100000 [15:17:06<8:06:04,  1.71it/s]
Train steps ... :  50%|█████     | 50062/100000 [15:17:06<8:06:00,  1.71it/s]
Train steps ... :  50%|█████     | 50063/100000 [15:17:07<8:05:37,  1.71it/s]
Train steps ... :  50%|█████     | 50064/100000 [15:17:07<8:05:31,  1.71it/s]
Train steps ... :  50%|█████     | 50065/100000 [15:17:08<8:05:37,  1.71it/s]
Train steps ... :  50%|█████     | 50066/100000 [15:17:09<8:05:35,  1.71it/s]
Train steps ... :  50%|█████     | 50067/100000 [15:17:09<8:05:33,  1.71it/s]
Train steps ... :  50%|█████     | 50068/100000 [15:17:10<8:05:25,  1.71it/s]
Train steps ... :  50%|█████     | 50069/100000 [15:17:10<8:06:02,  1.71it/s]
Train steps ... :  50%|█████     | 50070/100000 [15:17:11<8:05:48,  1.71it/s]
Train steps ... :  50%|█████     | 50071/100000 [15:17:12<8:06:11,  1.71it/s]
Train steps ... :  50%|█████     | 50072/100000 [15:17:12<8:07:12,  1.71it/s]
Train steps ... :  50%|█████     | 50073/100000 [15:17:13<8:06:48,  1.71it/s]
Train steps ... :  50%|█████     | 50074/100000 [15:17:13<8:06:18,  1.71it/s]
Train steps ... :  50%|█████     | 50075/100000 [15:17:14<8:06:08,  1.71it/s]Step... (50075 / 100000 | Loss: 0.8159153461456299, Learning Rate: 5.0175879396984926e-05)
+
                                                                             
Step... (50075 / 100000 | Loss: 0.6888389587402344, Learning Rate: 5.0175879396984926e-05)
+
Train steps ... :  50%|█████     | 50075/100000 [15:17:14<8:06:08,  1.71it/s]
Train steps ... :  50%|█████     | 50076/100000 [15:17:14<8:05:59,  1.71it/s]
Train steps ... :  50%|█████     | 50077/100000 [15:17:15<8:05:54,  1.71it/s]
Train steps ... :  50%|█████     | 50078/100000 [15:17:16<8:05:23,  1.71it/s]
Train steps ... :  50%|█████     | 50079/100000 [15:17:16<8:05:51,  1.71it/s]
Train steps ... :  50%|█████     | 50080/100000 [15:17:17<8:05:50,  1.71it/s]
Train steps ... :  50%|█████     | 50081/100000 [15:17:17<8:06:32,  1.71it/s]
Train steps ... :  50%|█████     | 50082/100000 [15:17:18<8:06:16,  1.71it/s]
Train steps ... :  50%|█████     | 50083/100000 [15:17:19<8:05:44,  1.71it/s]
Train steps ... :  50%|█████     | 50084/100000 [15:17:19<8:05:57,  1.71it/s]
Train steps ... :  50%|█████     | 50085/100000 [15:17:20<8:05:42,  1.71it/s]
Train steps ... :  50%|█████     | 50086/100000 [15:17:20<8:05:28,  1.71it/s]
Train steps ... :  50%|█████     | 50087/100000 [15:17:21<8:06:39,  1.71it/s]
Train steps ... :  50%|█████     | 50088/100000 [15:17:21<8:06:21,  1.71it/s]
Train steps ... :  50%|█████     | 50089/100000 [15:17:22<8:05:51,  1.71it/s]
Train steps ... :  50%|█████     | 50090/100000 [15:17:23<8:05:36,  1.71it/s]
Train steps ... :  50%|█████     | 50091/100000 [15:17:23<8:05:22,  1.71it/s]
Train steps ... :  50%|█████     | 50092/100000 [15:17:24<8:05:29,  1.71it/s]
Train steps ... :  50%|█████     | 50093/100000 [15:17:24<8:05:35,  1.71it/s]
Train steps ... :  50%|█████     | 50094/100000 [15:17:25<8:05:38,  1.71it/s]
Train steps ... :  50%|█████     | 50095/100000 [15:17:26<8:05:56,  1.71it/s]
Train steps ... :  50%|█████     | 50096/100000 [15:17:26<8:05:36,  1.71it/s]
Train steps ... :  50%|█████     | 50097/100000 [15:17:27<8:05:13,  1.71it/s]
Train steps ... :  50%|█████     | 50098/100000 [15:17:27<8:05:39,  1.71it/s]
Train steps ... :  50%|█████     | 50099/100000 [15:17:28<8:05:24,  1.71it/s]
Train steps ... :  50%|█████     | 50100/100000 [15:17:28<8:05:26,  1.71it/s]Step... (50100 / 100000 | Loss: 0.7393132448196411, Learning Rate: 5.015075376884423e-05)
+
                                                                             
Step... (50100 / 100000 | Loss: 0.7051126956939697, Learning Rate: 5.015075376884423e-05)
+
Train steps ... :  50%|█████     | 50100/100000 [15:17:29<8:05:26,  1.71it/s]
Train steps ... :  50%|█████     | 50101/100000 [15:17:29<8:05:32,  1.71it/s]
Train steps ... :  50%|█████     | 50102/100000 [15:17:30<8:05:08,  1.71it/s]
Train steps ... :  50%|█████     | 50103/100000 [15:17:30<8:05:49,  1.71it/s]
Train steps ... :  50%|█████     | 50104/100000 [15:17:31<8:05:38,  1.71it/s]
Train steps ... :  50%|█████     | 50105/100000 [15:17:31<8:05:44,  1.71it/s]
Train steps ... :  50%|█████     | 50106/100000 [15:17:32<8:05:48,  1.71it/s]
Train steps ... :  50%|█████     | 50107/100000 [15:17:33<8:05:32,  1.71it/s]
Train steps ... :  50%|█████     | 50108/100000 [15:17:33<8:05:28,  1.71it/s]
Train steps ... :  50%|█████     | 50109/100000 [15:17:34<8:05:04,  1.71it/s]
Train steps ... :  50%|█████     | 50110/100000 [15:17:34<8:06:09,  1.71it/s]
Train steps ... :  50%|█████     | 50111/100000 [15:17:35<8:05:47,  1.71it/s]
Train steps ... :  50%|█████     | 50112/100000 [15:17:36<8:06:05,  1.71it/s]
Train steps ... :  50%|█████     | 50113/100000 [15:17:36<8:05:42,  1.71it/s]
Train steps ... :  50%|█████     | 50114/100000 [15:17:37<8:05:17,  1.71it/s]
Train steps ... :  50%|█████     | 50115/100000 [15:17:37<8:05:05,  1.71it/s]
Train steps ... :  50%|█████     | 50116/100000 [15:17:38<8:05:24,  1.71it/s]
Train steps ... :  50%|█████     | 50117/100000 [15:17:38<8:05:06,  1.71it/s]
Train steps ... :  50%|█████     | 50118/100000 [15:17:39<8:05:12,  1.71it/s]
Train steps ... :  50%|█████     | 50119/100000 [15:17:40<8:05:16,  1.71it/s]
Train steps ... :  50%|█████     | 50120/100000 [15:17:40<8:04:51,  1.71it/s]
Train steps ... :  50%|█████     | 50121/100000 [15:17:41<8:04:52,  1.71it/s]
Train steps ... :  50%|█████     | 50122/100000 [15:17:41<8:05:24,  1.71it/s]
Train steps ... :  50%|█████     | 50123/100000 [15:17:42<8:05:34,  1.71it/s]
Train steps ... :  50%|█████     | 50124/100000 [15:17:43<8:05:39,  1.71it/s]
Train steps ... :  50%|█████     | 50125/100000 [15:17:43<8:05:20,  1.71it/s]Step... (50125 / 100000 | Loss: 1.0899385213851929, Learning Rate: 5.012562814070352e-05)
+
                                                                             
Step... (50125 / 100000 | Loss: 0.6003039479255676, Learning Rate: 5.012562814070352e-05)
+
Train steps ... :  50%|█████     | 50125/100000 [15:17:43<8:05:20,  1.71it/s]
Train steps ... :  50%|█████     | 50126/100000 [15:17:44<8:05:35,  1.71it/s]
Train steps ... :  50%|█████     | 50127/100000 [15:17:44<8:05:21,  1.71it/s]
Train steps ... :  50%|█████     | 50128/100000 [15:17:45<8:05:14,  1.71it/s]
Train steps ... :  50%|█████     | 50129/100000 [15:17:45<8:05:21,  1.71it/s]
Train steps ... :  50%|█████     | 50130/100000 [15:17:46<8:05:33,  1.71it/s]
Train steps ... :  50%|█████     | 50131/100000 [15:17:47<8:05:20,  1.71it/s]
Train steps ... :  50%|█████     | 50132/100000 [15:17:47<8:06:07,  1.71it/s]
Train steps ... :  50%|█████     | 50133/100000 [15:17:48<8:05:27,  1.71it/s]
Train steps ... :  50%|█████     | 50134/100000 [15:17:48<8:05:39,  1.71it/s]
Train steps ... :  50%|█████     | 50135/100000 [15:17:49<8:05:08,  1.71it/s]
Train steps ... :  50%|█████     | 50136/100000 [15:17:50<8:04:53,  1.71it/s]
Train steps ... :  50%|█████     | 50137/100000 [15:17:50<8:04:56,  1.71it/s]
Train steps ... :  50%|█████     | 50138/100000 [15:17:51<8:04:46,  1.71it/s]
Train steps ... :  50%|█████     | 50139/100000 [15:17:51<8:05:22,  1.71it/s]
Train steps ... :  50%|█████     | 50140/100000 [15:17:52<8:05:33,  1.71it/s]
Train steps ... :  50%|█████     | 50141/100000 [15:17:52<8:05:26,  1.71it/s]
Train steps ... :  50%|█████     | 50142/100000 [15:17:53<8:05:06,  1.71it/s]
Train steps ... :  50%|█████     | 50143/100000 [15:17:54<8:05:17,  1.71it/s]
Train steps ... :  50%|█████     | 50144/100000 [15:17:54<8:05:03,  1.71it/s]
Train steps ... :  50%|█████     | 50145/100000 [15:17:55<8:05:10,  1.71it/s]
Train steps ... :  50%|█████     | 50146/100000 [15:17:55<8:04:55,  1.71it/s]
Train steps ... :  50%|█████     | 50147/100000 [15:17:56<8:04:43,  1.71it/s]
Train steps ... :  50%|█████     | 50148/100000 [15:17:57<8:04:49,  1.71it/s]
Train steps ... :  50%|█████     | 50149/100000 [15:17:57<8:04:45,  1.71it/s]
Train steps ... :  50%|█████     | 50150/100000 [15:17:58<8:05:19,  1.71it/s]Step... (50150 / 100000 | Loss: 0.7267084121704102, Learning Rate: 5.0100502512562816e-05)
+
                                                                             
Step... (50150 / 100000 | Loss: 0.6381540298461914, Learning Rate: 5.0100502512562816e-05)
+
Train steps ... :  50%|█████     | 50150/100000 [15:17:58<8:05:19,  1.71it/s]
Train steps ... :  50%|█████     | 50151/100000 [15:17:58<8:05:06,  1.71it/s]
Train steps ... :  50%|█████     | 50152/100000 [15:17:59<8:04:36,  1.71it/s]
Train steps ... :  50%|█████     | 50153/100000 [15:17:59<8:04:18,  1.72it/s]
Train steps ... :  50%|█████     | 50154/100000 [15:18:00<8:04:59,  1.71it/s]
Train steps ... :  50%|█████     | 50155/100000 [15:18:01<8:04:45,  1.71it/s]
Train steps ... :  50%|█████     | 50156/100000 [15:18:01<8:04:39,  1.71it/s]
Train steps ... :  50%|█████     | 50157/100000 [15:18:02<8:04:29,  1.71it/s]
Train steps ... :  50%|█████     | 50158/100000 [15:18:02<8:04:35,  1.71it/s]
Train steps ... :  50%|█████     | 50159/100000 [15:18:03<8:04:57,  1.71it/s]
Train steps ... :  50%|█████     | 50160/100000 [15:18:04<8:06:25,  1.71it/s]
Train steps ... :  50%|█████     | 50161/100000 [15:18:04<8:05:52,  1.71it/s]
Train steps ... :  50%|█████     | 50162/100000 [15:18:05<8:06:03,  1.71it/s]
Train steps ... :  50%|█████     | 50163/100000 [15:18:05<8:05:56,  1.71it/s]
Train steps ... :  50%|█████     | 50164/100000 [15:18:06<8:06:36,  1.71it/s]
Train steps ... :  50%|█████     | 50165/100000 [15:18:06<8:05:32,  1.71it/s]
Train steps ... :  50%|█████     | 50166/100000 [15:18:07<8:05:10,  1.71it/s]
Train steps ... :  50%|█████     | 50167/100000 [15:18:08<8:04:51,  1.71it/s]
Train steps ... :  50%|█████     | 50168/100000 [15:18:08<8:04:51,  1.71it/s]
Train steps ... :  50%|█████     | 50169/100000 [15:18:09<8:05:09,  1.71it/s]
Train steps ... :  50%|█████     | 50170/100000 [15:18:09<8:05:15,  1.71it/s]
Train steps ... :  50%|█████     | 50171/100000 [15:18:10<8:05:02,  1.71it/s]
Train steps ... :  50%|█████     | 50172/100000 [15:18:11<8:05:03,  1.71it/s]
Train steps ... :  50%|█████     | 50173/100000 [15:18:11<8:06:06,  1.71it/s]
Train steps ... :  50%|█████     | 50174/100000 [15:18:12<8:05:51,  1.71it/s]
Train steps ... :  50%|█████     | 50175/100000 [15:18:12<8:05:47,  1.71it/s]Step... (50175 / 100000 | Loss: 0.8461249470710754, Learning Rate: 5.007537688442211e-05)
+
                                                                             
Step... (50175 / 100000 | Loss: 0.8923706412315369, Learning Rate: 5.007537688442211e-05)
+
Train steps ... :  50%|█████     | 50175/100000 [15:18:13<8:05:47,  1.71it/s]
Train steps ... :  50%|█████     | 50176/100000 [15:18:13<8:05:46,  1.71it/s]
Train steps ... :  50%|█████     | 50177/100000 [15:18:13<8:05:52,  1.71it/s]
Train steps ... :  50%|█████     | 50178/100000 [15:18:14<8:05:53,  1.71it/s]
Train steps ... :  50%|█████     | 50179/100000 [15:18:15<8:05:33,  1.71it/s]
Train steps ... :  50%|█████     | 50180/100000 [15:18:15<8:05:10,  1.71it/s]
Train steps ... :  50%|█████     | 50181/100000 [15:18:16<8:05:35,  1.71it/s]
Train steps ... :  50%|█████     | 50182/100000 [15:18:16<8:04:46,  1.71it/s]
Train steps ... :  50%|█████     | 50183/100000 [15:18:17<8:05:04,  1.71it/s]
Train steps ... :  50%|█████     | 50184/100000 [15:18:18<8:05:24,  1.71it/s]
Train steps ... :  50%|█████     | 50185/100000 [15:18:18<8:05:14,  1.71it/s]
Train steps ... :  50%|█████     | 50186/100000 [15:18:19<8:04:43,  1.71it/s]
Train steps ... :  50%|█████     | 50187/100000 [15:18:19<8:05:12,  1.71it/s]
Train steps ... :  50%|█████     | 50188/100000 [15:18:20<8:06:17,  1.71it/s]
Train steps ... :  50%|█████     | 50189/100000 [15:18:20<8:06:18,  1.71it/s]
Train steps ... :  50%|█████     | 50190/100000 [15:18:21<8:05:19,  1.71it/s]
Train steps ... :  50%|█████     | 50191/100000 [15:18:22<8:05:08,  1.71it/s]
Train steps ... :  50%|█████     | 50192/100000 [15:18:22<8:04:55,  1.71it/s]
Train steps ... :  50%|█████     | 50193/100000 [15:18:23<8:05:10,  1.71it/s]
Train steps ... :  50%|█████     | 50194/100000 [15:18:23<8:04:38,  1.71it/s]
Train steps ... :  50%|█████     | 50195/100000 [15:18:24<8:04:31,  1.71it/s]
Train steps ... :  50%|█████     | 50196/100000 [15:18:25<8:04:40,  1.71it/s]
Train steps ... :  50%|█████     | 50197/100000 [15:18:25<8:05:18,  1.71it/s]
Train steps ... :  50%|█████     | 50198/100000 [15:18:26<8:04:50,  1.71it/s]
Train steps ... :  50%|█████     | 50199/100000 [15:18:26<8:04:46,  1.71it/s]
Train steps ... :  50%|█████     | 50200/100000 [15:18:27<8:04:26,  1.71it/s]Step... (50200 / 100000 | Loss: 0.7988759875297546, Learning Rate: 5.005025125628141e-05)
+
                                                                             
Step... (50200 / 100000 | Loss: 1.2006274461746216, Learning Rate: 5.005025125628141e-05)
+
Train steps ... :  50%|█████     | 50200/100000 [15:18:27<8:04:26,  1.71it/s]
Train steps ... :  50%|█████     | 50201/100000 [15:18:27<8:04:26,  1.71it/s]
Train steps ... :  50%|█████     | 50202/100000 [15:18:28<8:04:43,  1.71it/s]
Train steps ... :  50%|█████     | 50203/100000 [15:18:29<8:05:11,  1.71it/s]
Train steps ... :  50%|█████     | 50204/100000 [15:18:29<8:05:29,  1.71it/s]
Train steps ... :  50%|█████     | 50205/100000 [15:18:30<8:05:41,  1.71it/s]
Train steps ... :  50%|█████     | 50206/100000 [15:18:30<8:05:12,  1.71it/s]
Train steps ... :  50%|█████     | 50207/100000 [15:18:31<8:04:56,  1.71it/s]
Train steps ... :  50%|█████     | 50208/100000 [15:18:32<8:04:39,  1.71it/s]
Train steps ... :  50%|█████     | 50209/100000 [15:18:32<8:04:20,  1.71it/s]
Train steps ... :  50%|█████     | 50210/100000 [15:18:33<8:04:39,  1.71it/s]
Train steps ... :  50%|█████     | 50211/100000 [15:18:33<8:05:17,  1.71it/s]
Train steps ... :  50%|█████     | 50212/100000 [15:18:34<8:05:06,  1.71it/s]
Train steps ... :  50%|█████     | 50213/100000 [15:18:35<8:05:13,  1.71it/s]
Train steps ... :  50%|█████     | 50214/100000 [15:18:35<8:04:25,  1.71it/s]
Train steps ... :  50%|█████     | 50215/100000 [15:18:36<8:04:23,  1.71it/s]
Train steps ... :  50%|█████     | 50216/100000 [15:18:36<8:04:10,  1.71it/s]
Train steps ... :  50%|█████     | 50217/100000 [15:18:37<8:04:26,  1.71it/s]
Train steps ... :  50%|█████     | 50218/100000 [15:18:37<8:04:50,  1.71it/s]
Train steps ... :  50%|█████     | 50219/100000 [15:18:38<8:04:36,  1.71it/s]
Train steps ... :  50%|█████     | 50220/100000 [15:18:39<8:04:46,  1.71it/s]
Train steps ... :  50%|█████     | 50221/100000 [15:18:39<8:04:11,  1.71it/s]
Train steps ... :  50%|█████     | 50222/100000 [15:18:40<8:04:28,  1.71it/s]
Train steps ... :  50%|█████     | 50223/100000 [15:18:40<8:04:25,  1.71it/s]
Train steps ... :  50%|█████     | 50224/100000 [15:18:41<8:04:12,  1.71it/s]
Train steps ... :  50%|█████     | 50225/100000 [15:18:42<8:04:21,  1.71it/s]Step... (50225 / 100000 | Loss: 0.9054227471351624, Learning Rate: 5.00251256281407e-05)
+
                                                                             
Step... (50225 / 100000 | Loss: 0.977410078048706, Learning Rate: 5.00251256281407e-05)
+
Train steps ... :  50%|█████     | 50225/100000 [15:18:42<8:04:21,  1.71it/s]
Train steps ... :  50%|█████     | 50226/100000 [15:18:42<8:04:53,  1.71it/s]
Train steps ... :  50%|█████     | 50227/100000 [15:18:43<8:04:29,  1.71it/s]
Train steps ... :  50%|█████     | 50228/100000 [15:18:43<8:04:05,  1.71it/s]
Train steps ... :  50%|█████     | 50229/100000 [15:18:44<8:04:09,  1.71it/s]
Train steps ... :  50%|█████     | 50230/100000 [15:18:44<8:04:27,  1.71it/s]
Train steps ... :  50%|█████     | 50231/100000 [15:18:45<8:03:55,  1.71it/s]
Train steps ... :  50%|█████     | 50232/100000 [15:18:46<8:03:49,  1.71it/s]
Train steps ... :  50%|█████     | 50233/100000 [15:18:46<8:04:30,  1.71it/s]
Train steps ... :  50%|█████     | 50234/100000 [15:18:47<8:04:16,  1.71it/s]
Train steps ... :  50%|█████     | 50235/100000 [15:18:47<8:04:29,  1.71it/s]
Train steps ... :  50%|█████     | 50236/100000 [15:18:48<8:04:04,  1.71it/s]
Train steps ... :  50%|█████     | 50237/100000 [15:18:49<8:04:01,  1.71it/s]
Train steps ... :  50%|█████     | 50238/100000 [15:18:49<8:04:11,  1.71it/s]
Train steps ... :  50%|█████     | 50239/100000 [15:18:50<8:03:50,  1.71it/s]
Train steps ... :  50%|█████     | 50240/100000 [15:18:50<8:04:27,  1.71it/s]
Train steps ... :  50%|█████     | 50241/100000 [15:18:51<8:03:52,  1.71it/s]
Train steps ... :  50%|█████     | 50242/100000 [15:18:51<8:03:53,  1.71it/s]
Train steps ... :  50%|█████     | 50243/100000 [15:18:52<8:03:51,  1.71it/s]
Train steps ... :  50%|█████     | 50244/100000 [15:18:53<8:04:00,  1.71it/s]
Train steps ... :  50%|█████     | 50245/100000 [15:18:53<8:03:45,  1.71it/s]
Train steps ... :  50%|█████     | 50246/100000 [15:18:54<8:03:58,  1.71it/s]
Train steps ... :  50%|█████     | 50247/100000 [15:18:54<8:04:43,  1.71it/s]
Train steps ... :  50%|█████     | 50248/100000 [15:18:55<8:04:12,  1.71it/s]
Train steps ... :  50%|█████     | 50249/100000 [15:18:56<8:04:45,  1.71it/s]
Train steps ... :  50%|█████     | 50250/100000 [15:18:56<8:04:27,  1.71it/s]Step... (50250 / 100000 | Loss: 0.9776569604873657, Learning Rate: 5e-05)
+
                                                                             
Step... (50250 / 100000 | Loss: 0.9584190845489502, Learning Rate: 5e-05)
+
Train steps ... :  50%|█████     | 50250/100000 [15:18:56<8:04:27,  1.71it/s]
Train steps ... :  50%|█████     | 50251/100000 [15:18:57<8:04:30,  1.71it/s]
Train steps ... :  50%|█████     | 50252/100000 [15:18:57<8:04:24,  1.71it/s]
Train steps ... :  50%|█████     | 50253/100000 [15:18:58<8:04:19,  1.71it/s]
Train steps ... :  50%|█████     | 50254/100000 [15:18:58<8:04:44,  1.71it/s]
Train steps ... :  50%|█████     | 50255/100000 [15:18:59<8:05:06,  1.71it/s]
Train steps ... :  50%|█████     | 50256/100000 [15:19:00<8:04:41,  1.71it/s]
Train steps ... :  50%|█████     | 50257/100000 [15:19:00<8:04:32,  1.71it/s]
Train steps ... :  50%|█████     | 50258/100000 [15:19:01<8:04:25,  1.71it/s]
Train steps ... :  50%|█████     | 50259/100000 [15:19:01<8:04:20,  1.71it/s]
Train steps ... :  50%|█████     | 50260/100000 [15:19:02<8:04:30,  1.71it/s]
Train steps ... :  50%|█████     | 50261/100000 [15:19:03<8:04:10,  1.71it/s]
Train steps ... :  50%|█████     | 50262/100000 [15:19:03<8:04:01,  1.71it/s]
Train steps ... :  50%|█████     | 50263/100000 [15:19:04<8:03:56,  1.71it/s]
Train steps ... :  50%|█████     | 50264/100000 [15:19:04<8:04:31,  1.71it/s]
Train steps ... :  50%|█████     | 50265/100000 [15:19:05<8:04:39,  1.71it/s]
Train steps ... :  50%|█████     | 50266/100000 [15:19:05<8:05:33,  1.71it/s]
Train steps ... :  50%|█████     | 50267/100000 [15:19:06<8:04:28,  1.71it/s]
Train steps ... :  50%|█████     | 50268/100000 [15:19:07<8:04:24,  1.71it/s]
Train steps ... :  50%|█████     | 50269/100000 [15:19:07<8:03:46,  1.71it/s]
Train steps ... :  50%|█████     | 50270/100000 [15:19:08<8:04:10,  1.71it/s]
Train steps ... :  50%|█████     | 50271/100000 [15:19:08<8:03:49,  1.71it/s]
Train steps ... :  50%|█████     | 50272/100000 [15:19:09<8:05:28,  1.71it/s]
Train steps ... :  50%|█████     | 50273/100000 [15:19:10<8:05:18,  1.71it/s]
Train steps ... :  50%|█████     | 50274/100000 [15:19:10<8:05:55,  1.71it/s]
Train steps ... :  50%|█████     | 50275/100000 [15:19:11<8:04:27,  1.71it/s]Step... (50275 / 100000 | Loss: 0.7449792623519897, Learning Rate: 4.99748743718593e-05)
+
                                                                             
Step... (50275 / 100000 | Loss: 0.5451149940490723, Learning Rate: 4.99748743718593e-05)
+
Train steps ... :  50%|█████     | 50275/100000 [15:19:11<8:04:27,  1.71it/s]
Train steps ... :  50%|█████     | 50276/100000 [15:19:11<8:04:35,  1.71it/s]
Train steps ... :  50%|█████     | 50277/100000 [15:19:12<8:03:44,  1.71it/s]
Train steps ... :  50%|█████     | 50278/100000 [15:19:12<8:04:31,  1.71it/s]
Train steps ... :  50%|█████     | 50279/100000 [15:19:13<8:03:22,  1.71it/s]
Train steps ... :  50%|█████     | 50280/100000 [15:19:14<8:03:36,  1.71it/s]
Train steps ... :  50%|█████     | 50281/100000 [15:19:14<8:03:44,  1.71it/s]
Train steps ... :  50%|█████     | 50282/100000 [15:19:15<8:03:55,  1.71it/s]
Train steps ... :  50%|█████     | 50283/100000 [15:19:15<8:04:09,  1.71it/s]
Train steps ... :  50%|█████     | 50284/100000 [15:19:16<8:03:54,  1.71it/s]
Train steps ... :  50%|█████     | 50285/100000 [15:19:17<8:04:13,  1.71it/s]
Train steps ... :  50%|█████     | 50286/100000 [15:19:17<8:03:11,  1.71it/s]
Train steps ... :  50%|█████     | 50287/100000 [15:19:18<8:03:45,  1.71it/s]
Train steps ... :  50%|█████     | 50288/100000 [15:19:18<8:03:44,  1.71it/s]
Train steps ... :  50%|█████     | 50289/100000 [15:19:19<8:03:26,  1.71it/s]
Train steps ... :  50%|█████     | 50290/100000 [15:19:19<8:03:34,  1.71it/s]
Train steps ... :  50%|█████     | 50291/100000 [15:19:20<8:03:49,  1.71it/s]
Train steps ... :  50%|█████     | 50292/100000 [15:19:21<8:03:36,  1.71it/s]
Train steps ... :  50%|█████     | 50293/100000 [15:19:21<8:03:48,  1.71it/s]
Train steps ... :  50%|█████     | 50294/100000 [15:19:22<8:03:45,  1.71it/s]
Train steps ... :  50%|█████     | 50295/100000 [15:19:22<8:03:29,  1.71it/s]
Train steps ... :  50%|█████     | 50296/100000 [15:19:23<8:03:23,  1.71it/s]
Train steps ... :  50%|█████     | 50297/100000 [15:19:24<8:03:32,  1.71it/s]
Train steps ... :  50%|█████     | 50298/100000 [15:19:24<8:04:43,  1.71it/s]
Train steps ... :  50%|█████     | 50299/100000 [15:19:25<8:04:25,  1.71it/s]
Train steps ... :  50%|█████     | 50300/100000 [15:19:25<8:04:22,  1.71it/s]Step... (50300 / 100000 | Loss: 0.892723798751831, Learning Rate: 4.9949748743718596e-05)
+
                                                                             
Step... (50300 / 100000 | Loss: 0.8148990869522095, Learning Rate: 4.9949748743718596e-05)
+
Train steps ... :  50%|█████     | 50300/100000 [15:19:26<8:04:22,  1.71it/s]
Train steps ... :  50%|█████     | 50301/100000 [15:19:26<8:04:07,  1.71it/s]
Train steps ... :  50%|█████     | 50302/100000 [15:19:26<8:04:04,  1.71it/s]
Train steps ... :  50%|█████     | 50303/100000 [15:19:27<8:03:55,  1.71it/s]
Train steps ... :  50%|█████     | 50304/100000 [15:19:28<8:04:00,  1.71it/s]
Train steps ... :  50%|█████     | 50305/100000 [15:19:28<8:04:01,  1.71it/s]
Train steps ... :  50%|█████     | 50306/100000 [15:19:29<8:03:50,  1.71it/s]
Train steps ... :  50%|█████     | 50307/100000 [15:19:29<8:03:49,  1.71it/s]
Train steps ... :  50%|█████     | 50308/100000 [15:19:30<8:04:05,  1.71it/s]
Train steps ... :  50%|█████     | 50309/100000 [15:19:31<8:03:52,  1.71it/s]
Train steps ... :  50%|█████     | 50310/100000 [15:19:31<8:04:44,  1.71it/s]
Train steps ... :  50%|█████     | 50311/100000 [15:19:32<8:03:35,  1.71it/s]
Train steps ... :  50%|█████     | 50312/100000 [15:19:32<8:03:23,  1.71it/s]
Train steps ... :  50%|█████     | 50313/100000 [15:19:33<8:03:02,  1.71it/s]
Train steps ... :  50%|█████     | 50314/100000 [15:19:33<8:03:13,  1.71it/s]
Train steps ... :  50%|█████     | 50315/100000 [15:19:34<8:04:30,  1.71it/s]
Train steps ... :  50%|█████     | 50316/100000 [15:19:35<8:03:18,  1.71it/s]
Train steps ... :  50%|█████     | 50317/100000 [15:19:35<8:03:44,  1.71it/s]
Train steps ... :  50%|█████     | 50318/100000 [15:19:36<8:04:34,  1.71it/s]
Train steps ... :  50%|█████     | 50319/100000 [15:19:36<8:04:21,  1.71it/s]
Train steps ... :  50%|█████     | 50320/100000 [15:19:37<8:04:12,  1.71it/s]
Train steps ... :  50%|█████     | 50321/100000 [15:19:38<8:04:32,  1.71it/s]
Train steps ... :  50%|█████     | 50322/100000 [15:19:38<8:04:38,  1.71it/s]
Train steps ... :  50%|█████     | 50323/100000 [15:19:39<8:04:13,  1.71it/s]
Train steps ... :  50%|█████     | 50324/100000 [15:19:39<8:04:19,  1.71it/s]
Train steps ... :  50%|█████     | 50325/100000 [15:19:40<8:04:03,  1.71it/s]Step... (50325 / 100000 | Loss: 0.8665035963058472, Learning Rate: 4.992462311557789e-05)
+
                                                                             
Step... (50325 / 100000 | Loss: 0.6628543138504028, Learning Rate: 4.992462311557789e-05)
+
Train steps ... :  50%|█████     | 50325/100000 [15:19:40<8:04:03,  1.71it/s]
Train steps ... :  50%|█████     | 50326/100000 [15:19:41<8:04:22,  1.71it/s]
Train steps ... :  50%|█████     | 50327/100000 [15:19:41<8:03:29,  1.71it/s]
Train steps ... :  50%|█████     | 50328/100000 [15:19:42<8:03:32,  1.71it/s]
Train steps ... :  50%|█████     | 50329/100000 [15:19:42<8:03:55,  1.71it/s]
Train steps ... :  50%|█████     | 50330/100000 [15:19:43<8:03:25,  1.71it/s]
Train steps ... :  50%|█████     | 50331/100000 [15:19:43<8:03:25,  1.71it/s]
Train steps ... :  50%|█████     | 50332/100000 [15:19:44<8:04:10,  1.71it/s]
Train steps ... :  50%|█████     | 50333/100000 [15:19:45<8:03:35,  1.71it/s]
Train steps ... :  50%|█████     | 50334/100000 [15:19:45<8:03:20,  1.71it/s]
Train steps ... :  50%|█████     | 50335/100000 [15:19:46<8:03:53,  1.71it/s]
Train steps ... :  50%|█████     | 50336/100000 [15:19:46<8:03:41,  1.71it/s]
Train steps ... :  50%|█████     | 50337/100000 [15:19:47<8:03:34,  1.71it/s]
Train steps ... :  50%|█████     | 50338/100000 [15:19:48<8:03:32,  1.71it/s]
Train steps ... :  50%|█████     | 50339/100000 [15:19:48<8:03:07,  1.71it/s]
Train steps ... :  50%|█████     | 50340/100000 [15:19:49<8:03:14,  1.71it/s]
Train steps ... :  50%|█████     | 50341/100000 [15:19:49<8:02:57,  1.71it/s]
Train steps ... :  50%|█████     | 50342/100000 [15:19:50<8:02:51,  1.71it/s]
Train steps ... :  50%|█████     | 50343/100000 [15:19:50<8:03:25,  1.71it/s]
Train steps ... :  50%|█████     | 50344/100000 [15:19:51<8:03:16,  1.71it/s]
Train steps ... :  50%|█████     | 50345/100000 [15:19:52<8:03:06,  1.71it/s]
Train steps ... :  50%|█████     | 50346/100000 [15:19:52<8:02:55,  1.71it/s]
Train steps ... :  50%|█████     | 50347/100000 [15:19:53<8:02:43,  1.71it/s]
Train steps ... :  50%|█████     | 50348/100000 [15:19:53<8:02:58,  1.71it/s]
Train steps ... :  50%|█████     | 50349/100000 [15:19:54<8:02:48,  1.71it/s]
Train steps ... :  50%|█████     | 50350/100000 [15:19:55<8:02:40,  1.71it/s]Step... (50350 / 100000 | Loss: 0.8000121116638184, Learning Rate: 4.989949748743719e-05)
+
                                                                             
Step... (50350 / 100000 | Loss: 1.0752536058425903, Learning Rate: 4.989949748743719e-05)
+
Train steps ... :  50%|█████     | 50350/100000 [15:19:55<8:02:40,  1.71it/s]
Train steps ... :  50%|█████     | 50351/100000 [15:19:55<8:02:38,  1.71it/s]
Train steps ... :  50%|█████     | 50352/100000 [15:19:56<8:02:38,  1.71it/s]
Train steps ... :  50%|█████     | 50353/100000 [15:19:56<8:02:48,  1.71it/s]
Train steps ... :  50%|█████     | 50354/100000 [15:19:57<8:02:40,  1.71it/s]
Train steps ... :  50%|█████     | 50355/100000 [15:19:57<8:03:09,  1.71it/s]
Train steps ... :  50%|█████     | 50356/100000 [15:19:58<8:03:02,  1.71it/s]
Train steps ... :  50%|█████     | 50357/100000 [15:19:59<8:02:54,  1.71it/s]
Train steps ... :  50%|█████     | 50358/100000 [15:19:59<8:02:51,  1.71it/s]
Train steps ... :  50%|█████     | 50359/100000 [15:20:00<8:02:51,  1.71it/s]
Train steps ... :  50%|█████     | 50360/100000 [15:20:00<8:02:45,  1.71it/s]
Train steps ... :  50%|█████     | 50361/100000 [15:20:01<8:02:44,  1.71it/s]
Train steps ... :  50%|█████     | 50362/100000 [15:20:02<8:03:07,  1.71it/s]
Train steps ... :  50%|█████     | 50363/100000 [15:20:02<8:02:43,  1.71it/s]
Train steps ... :  50%|█████     | 50364/100000 [15:20:03<8:03:11,  1.71it/s]
Train steps ... :  50%|█████     | 50365/100000 [15:20:03<8:03:21,  1.71it/s]
Train steps ... :  50%|█████     | 50366/100000 [15:20:04<8:03:12,  1.71it/s]
Train steps ... :  50%|█████     | 50367/100000 [15:20:04<8:02:53,  1.71it/s]
Train steps ... :  50%|█████     | 50368/100000 [15:20:05<8:02:55,  1.71it/s]
Train steps ... :  50%|█████     | 50369/100000 [15:20:06<8:03:10,  1.71it/s]
Train steps ... :  50%|█████     | 50370/100000 [15:20:06<8:03:21,  1.71it/s]
Train steps ... :  50%|█████     | 50371/100000 [15:20:07<8:03:18,  1.71it/s]
Train steps ... :  50%|█████     | 50372/100000 [15:20:07<8:03:05,  1.71it/s]
Train steps ... :  50%|█████     | 50373/100000 [15:20:08<8:03:43,  1.71it/s]
Train steps ... :  50%|█████     | 50374/100000 [15:20:09<8:03:24,  1.71it/s]
Train steps ... :  50%|█████     | 50375/100000 [15:20:09<8:02:50,  1.71it/s]Step... (50375 / 100000 | Loss: 0.6316616535186768, Learning Rate: 4.9874371859296486e-05)
+
                                                                             
Step... (50375 / 100000 | Loss: 0.8344413638114929, Learning Rate: 4.9874371859296486e-05)
+
Train steps ... :  50%|█████     | 50375/100000 [15:20:09<8:02:50,  1.71it/s]
Train steps ... :  50%|█████     | 50376/100000 [15:20:10<8:02:53,  1.71it/s]
Train steps ... :  50%|█████     | 50377/100000 [15:20:10<8:03:13,  1.71it/s]
Train steps ... :  50%|█████     | 50378/100000 [15:20:11<8:02:54,  1.71it/s]
Train steps ... :  50%|█████     | 50379/100000 [15:20:11<8:02:33,  1.71it/s]
Train steps ... :  50%|█████     | 50380/100000 [15:20:12<8:02:24,  1.71it/s]
Train steps ... :  50%|█████     | 50381/100000 [15:20:13<8:02:20,  1.71it/s]
Train steps ... :  50%|█████     | 50382/100000 [15:20:13<8:02:36,  1.71it/s]
Train steps ... :  50%|█���███     | 50383/100000 [15:20:14<8:02:46,  1.71it/s]
Train steps ... :  50%|█████     | 50384/100000 [15:20:14<8:02:31,  1.71it/s]
Train steps ... :  50%|█████     | 50385/100000 [15:20:15<8:02:56,  1.71it/s]
Train steps ... :  50%|█████     | 50386/100000 [15:20:16<8:03:06,  1.71it/s]
Train steps ... :  50%|█████     | 50387/100000 [15:20:16<8:02:45,  1.71it/s]
Train steps ... :  50%|█████     | 50388/100000 [15:20:17<8:02:18,  1.71it/s]
Train steps ... :  50%|█████     | 50389/100000 [15:20:17<8:02:32,  1.71it/s]
Train steps ... :  50%|█████     | 50390/100000 [15:20:18<8:02:42,  1.71it/s]
Train steps ... :  50%|█████     | 50391/100000 [15:20:18<8:02:18,  1.71it/s]
Train steps ... :  50%|█████     | 50392/100000 [15:20:19<8:02:32,  1.71it/s]
Train steps ... :  50%|█████     | 50393/100000 [15:20:20<8:03:00,  1.71it/s]
Train steps ... :  50%|█████     | 50394/100000 [15:20:20<8:03:24,  1.71it/s]
Train steps ... :  50%|█████     | 50395/100000 [15:20:21<8:03:06,  1.71it/s]
Train steps ... :  50%|█████     | 50396/100000 [15:20:21<8:03:11,  1.71it/s]
Train steps ... :  50%|█████     | 50397/100000 [15:20:22<8:03:15,  1.71it/s]
Train steps ... :  50%|█████     | 50398/100000 [15:20:23<8:03:18,  1.71it/s]
Train steps ... :  50%|█████     | 50399/100000 [15:20:23<8:03:37,  1.71it/s]
Train steps ... :  50%|█████     | 50400/100000 [15:20:24<8:03:40,  1.71it/s]Step... (50400 / 100000 | Loss: 0.7968581914901733, Learning Rate: 4.984924623115578e-05)
+
                                                                             
Step... (50400 / 100000 | Loss: 0.7747995853424072, Learning Rate: 4.984924623115578e-05)
+
Train steps ... :  50%|█████     | 50400/100000 [15:20:24<8:03:40,  1.71it/s]
Train steps ... :  50%|█████     | 50401/100000 [15:20:24<8:02:55,  1.71it/s]
Train steps ... :  50%|█████     | 50402/100000 [15:20:25<8:02:53,  1.71it/s]
Train steps ... :  50%|█████     | 50403/100000 [15:20:25<8:02:34,  1.71it/s]
Train steps ... :  50%|█████     | 50404/100000 [15:20:26<8:02:22,  1.71it/s]
Train steps ... :  50%|█████     | 50405/100000 [15:20:27<8:02:34,  1.71it/s]
Train steps ... :  50%|█████     | 50406/100000 [15:20:27<8:02:31,  1.71it/s]
Train steps ... :  50%|█████     | 50407/100000 [15:20:28<8:02:32,  1.71it/s]
Train steps ... :  50%|█████     | 50408/100000 [15:20:28<8:02:41,  1.71it/s]
Train steps ... :  50%|█████     | 50409/100000 [15:20:29<8:02:33,  1.71it/s]
Train steps ... :  50%|█████     | 50410/100000 [15:20:30<8:02:58,  1.71it/s]
Train steps ... :  50%|█████     | 50411/100000 [15:20:30<8:03:04,  1.71it/s]
Train steps ... :  50%|█████     | 50412/100000 [15:20:31<8:02:31,  1.71it/s]
Train steps ... :  50%|█████     | 50413/100000 [15:20:31<8:02:46,  1.71it/s]
Train steps ... :  50%|█████     | 50414/100000 [15:20:32<8:02:21,  1.71it/s]
Train steps ... :  50%|█████     | 50415/100000 [15:20:32<8:02:45,  1.71it/s]
Train steps ... :  50%|█████     | 50416/100000 [15:20:33<8:02:56,  1.71it/s]
Train steps ... :  50%|█████     | 50417/100000 [15:20:34<8:02:42,  1.71it/s]
Train steps ... :  50%|█████     | 50418/100000 [15:20:34<8:02:26,  1.71it/s]
Train steps ... :  50%|█████     | 50419/100000 [15:20:35<8:02:50,  1.71it/s]
Train steps ... :  50%|█████     | 50420/100000 [15:20:35<8:03:33,  1.71it/s]
Train steps ... :  50%|█████     | 50421/100000 [15:20:36<8:03:01,  1.71it/s]
Train steps ... :  50%|█████     | 50422/100000 [15:20:37<8:02:50,  1.71it/s]
Train steps ... :  50%|█████     | 50423/100000 [15:20:37<8:02:42,  1.71it/s]
Train steps ... :  50%|█████     | 50424/100000 [15:20:38<8:02:25,  1.71it/s]
Train steps ... :  50%|█████     | 50425/100000 [15:20:38<8:02:17,  1.71it/s]Step... (50425 / 100000 | Loss: 0.5891563296318054, Learning Rate: 4.982412060301508e-05)
+
                                                                             
Step... (50425 / 100000 | Loss: 0.5498707294464111, Learning Rate: 4.982412060301508e-05)
+
Train steps ... :  50%|█████     | 50425/100000 [15:20:39<8:02:17,  1.71it/s]
Train steps ... :  50%|█████     | 50426/100000 [15:20:39<8:02:35,  1.71it/s]
Train steps ... :  50%|█████     | 50427/100000 [15:20:39<8:02:31,  1.71it/s]
Train steps ... :  50%|█████     | 50428/100000 [15:20:40<8:02:48,  1.71it/s]
Train steps ... :  50%|█████     | 50429/100000 [15:20:41<8:03:11,  1.71it/s]
Train steps ... :  50%|█████     | 50430/100000 [15:20:41<8:02:46,  1.71it/s]
Train steps ... :  50%|█████     | 50431/100000 [15:20:42<8:02:33,  1.71it/s]
Train steps ... :  50%|█████     | 50432/100000 [15:20:42<8:02:33,  1.71it/s]
Train steps ... :  50%|█████     | 50433/100000 [15:20:43<8:02:23,  1.71it/s]
Train steps ... :  50%|█████     | 50434/100000 [15:20:44<8:03:00,  1.71it/s]
Train steps ... :  50%|█████     | 50435/100000 [15:20:44<8:02:34,  1.71it/s]
Train steps ... :  50%|█████     | 50436/100000 [15:20:45<8:02:27,  1.71it/s]
Train steps ... :  50%|█████     | 50437/100000 [15:20:45<8:02:02,  1.71it/s]
Train steps ... :  50%|█████     | 50438/100000 [15:20:46<8:01:53,  1.71it/s]
Train steps ... :  50%|█████     | 50439/100000 [15:20:47<8:01:59,  1.71it/s]
Train steps ... :  50%|█████     | 50440/100000 [15:20:47<8:02:01,  1.71it/s]
Train steps ... :  50%|█████     | 50441/100000 [15:20:48<8:01:35,  1.72it/s]
Train steps ... :  50%|█████     | 50442/100000 [15:20:48<8:01:59,  1.71it/s]
Train steps ... :  50%|█████     | 50443/100000 [15:20:49<8:01:45,  1.71it/s]
Train steps ... :  50%|█████     | 50444/100000 [15:20:49<8:01:41,  1.71it/s]
Train steps ... :  50%|█████     | 50445/100000 [15:20:50<8:01:53,  1.71it/s]
Train steps ... :  50%|█████     | 50446/100000 [15:20:51<8:01:53,  1.71it/s]
Train steps ... :  50%|█████     | 50447/100000 [15:20:51<8:01:49,  1.71it/s]
Train steps ... :  50%|█████     | 50448/100000 [15:20:52<8:02:23,  1.71it/s]
Train steps ... :  50%|█████     | 50449/100000 [15:20:52<8:02:05,  1.71it/s]
Train steps ... :  50%|█████     | 50450/100000 [15:20:53<8:01:37,  1.71it/s]Step... (50450 / 100000 | Loss: 1.0976576805114746, Learning Rate: 4.9798994974874375e-05)
+
                                                                             
Step... (50450 / 100000 | Loss: 0.7312214374542236, Learning Rate: 4.9798994974874375e-05)
+
Train steps ... :  50%|█████     | 50450/100000 [15:20:53<8:01:37,  1.71it/s]
Train steps ... :  50%|█████     | 50451/100000 [15:20:54<8:02:02,  1.71it/s]
Train steps ... :  50%|█████     | 50452/100000 [15:20:54<8:02:10,  1.71it/s]
Train steps ... :  50%|█████     | 50453/100000 [15:20:55<8:02:00,  1.71it/s]
Train steps ... :  50%|█████     | 50454/100000 [15:20:55<8:02:06,  1.71it/s]
Train steps ... :  50%|█████     | 50455/100000 [15:20:56<8:02:39,  1.71it/s]
Train steps ... :  50%|█████     | 50456/100000 [15:20:56<8:02:13,  1.71it/s]
Train steps ... :  50%|█████     | 50457/100000 [15:20:57<8:02:08,  1.71it/s]
Train steps ... :  50%|█████     | 50458/100000 [15:20:58<8:02:02,  1.71it/s]
Train steps ... :  50%|█████     | 50459/100000 [15:20:58<8:01:54,  1.71it/s]
Train steps ... :  50%|█████     | 50460/100000 [15:20:59<8:01:57,  1.71it/s]
Train steps ... :  50%|█████     | 50461/100000 [15:20:59<8:01:59,  1.71it/s]
Train steps ... :  50%|█████     | 50462/100000 [15:21:00<8:02:03,  1.71it/s]
Train steps ... :  50%|█████     | 50463/100000 [15:21:01<8:01:47,  1.71it/s]
Train steps ... :  50%|█████     | 50464/100000 [15:21:01<8:01:38,  1.71it/s]
Train steps ... :  50%|█████     | 50465/100000 [15:21:02<8:02:04,  1.71it/s]
Train steps ... :  50%|█████     | 50466/100000 [15:21:02<8:02:28,  1.71it/s]
Train steps ... :  50%|█████     | 50467/100000 [15:21:03<8:02:21,  1.71it/s]
Train steps ... :  50%|█████     | 50468/100000 [15:21:03<8:01:51,  1.71it/s]
Train steps ... :  50%|█████     | 50469/100000 [15:21:04<8:02:03,  1.71it/s]
Train steps ... :  50%|█████     | 50470/100000 [15:21:05<8:01:41,  1.71it/s]
Train steps ... :  50%|█████     | 50471/100000 [15:21:05<8:02:05,  1.71it/s]
Train steps ... :  50%|█████     | 50472/100000 [15:21:06<8:02:16,  1.71it/s]
Train steps ... :  50%|█████     | 50473/100000 [15:21:06<8:02:05,  1.71it/s]
Train steps ... :  50%|█████     | 50474/100000 [15:21:07<8:02:03,  1.71it/s]
Train steps ... :  50%|█████     | 50475/100000 [15:21:08<8:02:23,  1.71it/s]Step... (50475 / 100000 | Loss: 0.854790985584259, Learning Rate: 4.977386934673367e-05)
+
                                                                             
Step... (50475 / 100000 | Loss: 0.6589901447296143, Learning Rate: 4.977386934673367e-05)
+
Train steps ... :  50%|█████     | 50475/100000 [15:21:08<8:02:23,  1.71it/s]
Train steps ... :  50%|█████     | 50476/100000 [15:21:08<8:02:52,  1.71it/s]
Train steps ... :  50%|█████     | 50477/100000 [15:21:09<8:02:59,  1.71it/s]
Train steps ... :  50%|█████     | 50478/100000 [15:21:09<8:02:22,  1.71it/s]
Train steps ... :  50%|█████     | 50479/100000 [15:21:10<8:01:59,  1.71it/s]
Train steps ... :  50%|█████     | 50480/100000 [15:21:10<8:01:40,  1.71it/s]
Train steps ... :  50%|█████     | 50481/100000 [15:21:11<8:01:22,  1.71it/s]
Train steps ... :  50%|█████     | 50482/100000 [15:21:12<8:02:03,  1.71it/s]
Train steps ... :  50%|█████     | 50483/100000 [15:21:12<8:01:35,  1.71it/s]
Train steps ... :  50%|█████     | 50484/100000 [15:21:13<8:02:04,  1.71it/s]
Train steps ... :  50%|█████     | 50485/100000 [15:21:13<8:02:06,  1.71it/s]
Train steps ... :  50%|█████     | 50486/100000 [15:21:14<8:02:01,  1.71it/s]
Train steps ... :  50%|█████     | 50487/100000 [15:21:15<8:01:33,  1.71it/s]
Train steps ... :  50%|█████     | 50488/100000 [15:21:15<8:01:36,  1.71it/s]
Train steps ... :  50%|█████     | 50489/100000 [15:21:16<8:01:32,  1.71it/s]
Train steps ... :  50%|█████     | 50490/100000 [15:21:16<8:01:22,  1.71it/s]
Train steps ... :  50%|█████     | 50491/100000 [15:21:17<8:01:25,  1.71it/s]
Train steps ... :  50%|█████     | 50492/100000 [15:21:17<8:01:24,  1.71it/s]
Train steps ... :  50%|█████     | 50493/100000 [15:21:18<8:01:45,  1.71it/s]
Train steps ... :  50%|█████     | 50494/100000 [15:21:19<8:00:54,  1.72it/s]
Train steps ... :  50%|█████     | 50495/100000 [15:21:19<8:01:21,  1.71it/s]
Train steps ... :  50%|█████     | 50496/100000 [15:21:20<8:01:35,  1.71it/s]
Train steps ... :  50%|█████     | 50497/100000 [15:21:20<8:01:24,  1.71it/s]
Train steps ... :  50%|█████     | 50498/100000 [15:21:21<8:01:53,  1.71it/s]
Train steps ... :  50%|█████     | 50499/100000 [15:21:22<8:01:39,  1.71it/s]
Train steps ... :  50%|█████     | 50500/100000 [15:21:22<8:02:01,  1.71it/s]Step... (50500 / 100000 | Loss: 0.9395037889480591, Learning Rate: 4.974874371859297e-05)
+
                                                                             
Step... (50500 / 100000 | Loss: 0.6817235350608826, Learning Rate: 4.974874371859297e-05)
+
Train steps ... :  50%|█████     | 50500/100000 [15:21:22<8:02:01,  1.71it/s]
Train steps ... :  51%|█████     | 50501/100000 [15:21:23<8:01:56,  1.71it/s]
Train steps ... :  51%|█████     | 50502/100000 [15:21:23<8:01:40,  1.71it/s]
Train steps ... :  51%|█████     | 50503/100000 [15:21:24<8:01:38,  1.71it/s]
Train steps ... :  51%|█████     | 50504/100000 [15:21:24<8:01:27,  1.71it/s]
Train steps ... :  51%|█████     | 50505/100000 [15:21:25<8:01:30,  1.71it/s]
Train steps ... :  51%|█████     | 50506/100000 [15:21:26<8:01:33,  1.71it/s]
Train steps ... :  51%|█████     | 50507/100000 [15:21:26<8:01:34,  1.71it/s]
Train steps ... :  51%|█████     | 50508/100000 [15:21:27<8:01:22,  1.71it/s]
Train steps ... :  51%|█████     | 50509/100000 [15:21:27<8:01:53,  1.71it/s]
Train steps ... :  51%|█████     | 50510/100000 [15:21:28<8:01:39,  1.71it/s]
Train steps ... :  51%|█████     | 50511/100000 [15:21:29<8:01:20,  1.71it/s]
Train steps ... :  51%|█████     | 50512/100000 [15:21:29<8:01:29,  1.71it/s]
Train steps ... :  51%|█████     | 50513/100000 [15:21:30<8:01:42,  1.71it/s]
Train steps ... :  51%|█████     | 50514/100000 [15:21:30<8:01:12,  1.71it/s]
Train steps ... :  51%|█████     | 50515/100000 [15:21:31<8:01:33,  1.71it/s]
Train steps ... :  51%|█████     | 50516/100000 [15:21:31<8:01:48,  1.71it/s]
Train steps ... :  51%|█████     | 50517/100000 [15:21:32<8:02:05,  1.71it/s]
Train steps ... :  51%|█████     | 50518/100000 [15:21:33<8:01:47,  1.71it/s]
Train steps ... :  51%|█████     | 50519/100000 [15:21:33<8:01:22,  1.71it/s]
Train steps ... :  51%|█████     | 50520/100000 [15:21:34<8:01:25,  1.71it/s]
Train steps ... :  51%|█████     | 50521/100000 [15:21:34<8:01:09,  1.71it/s]
Train steps ... :  51%|█████     | 50522/100000 [15:21:35<8:01:07,  1.71it/s]
Train steps ... :  51%|█████     | 50523/100000 [15:21:36<8:01:11,  1.71it/s]
Train steps ... :  51%|█████     | 50524/100000 [15:21:36<8:00:51,  1.71it/s]
Train steps ... :  51%|█████     | 50525/100000 [15:21:37<8:00:46,  1.72it/s]Step... (50525 / 100000 | Loss: 0.6825889348983765, Learning Rate: 4.9723618090452265e-05)
+
                                                                             
Step... (50525 / 100000 | Loss: 0.5739867091178894, Learning Rate: 4.9723618090452265e-05)
+
Train steps ... :  51%|█████     | 50525/100000 [15:21:37<8:00:46,  1.72it/s]
Train steps ... :  51%|█████     | 50526/100000 [15:21:37<8:01:11,  1.71it/s]
Train steps ... :  51%|█████     | 50527/100000 [15:21:38<8:01:48,  1.71it/s]
Train steps ... :  51%|█████     | 50528/100000 [15:21:38<8:01:32,  1.71it/s]
Train steps ... :  51%|█████     | 50529/100000 [15:21:39<8:01:17,  1.71it/s]
Train steps ... :  51%|█████     | 50530/100000 [15:21:40<8:01:00,  1.71it/s]
Train steps ... :  51%|█████     | 50531/100000 [15:21:40<8:00:43,  1.72it/s]
Train steps ... :  51%|█████     | 50532/100000 [15:21:41<8:00:28,  1.72it/s]
Train steps ... :  51%|█████     | 50533/100000 [15:21:41<8:00:42,  1.72it/s]
Train steps ... :  51%|█████     | 50534/100000 [15:21:42<8:00:36,  1.72it/s]
Train steps ... :  51%|█████     | 50535/100000 [15:21:43<8:01:02,  1.71it/s]
Train steps ... :  51%|█████     | 50536/100000 [15:21:43<8:01:12,  1.71it/s]
Train steps ... :  51%|█████     | 50537/100000 [15:21:44<8:01:42,  1.71it/s]
Train steps ... :  51%|█████     | 50538/100000 [15:21:44<8:01:28,  1.71it/s]
Train steps ... :  51%|█████     | 50539/100000 [15:21:45<8:01:23,  1.71it/s]
Train steps ... :  51%|█████     | 50540/100000 [15:21:45<8:01:50,  1.71it/s]
Train steps ... :  51%|█████     | 50541/100000 [15:21:46<8:02:02,  1.71it/s]
Train steps ... :  51%|█████     | 50542/100000 [15:21:47<8:01:28,  1.71it/s]
Train steps ... :  51%|█████     | 50543/100000 [15:21:47<8:02:56,  1.71it/s]
Train steps ... :  51%|█████     | 50544/100000 [15:21:48<8:01:32,  1.71it/s]
Train steps ... :  51%|█████     | 50545/100000 [15:21:48<8:02:47,  1.71it/s]
Train steps ... :  51%|█████     | 50546/100000 [15:21:49<8:02:52,  1.71it/s]
Train steps ... :  51%|█████     | 50547/100000 [15:21:50<8:01:44,  1.71it/s]
Train steps ... :  51%|█████     | 50548/100000 [15:21:50<8:01:20,  1.71it/s]
Train steps ... :  51%|█████     | 50549/100000 [15:21:51<8:01:11,  1.71it/s]
Train steps ... :  51%|█████     | 50550/100000 [15:21:51<8:01:45,  1.71it/s]Step... (50550 / 100000 | Loss: 0.6771305799484253, Learning Rate: 4.9698492462311555e-05)
+
                                                                             
Step... (50550 / 100000 | Loss: 0.798305094242096, Learning Rate: 4.9698492462311555e-05)
+
Train steps ... :  51%|█████     | 50550/100000 [15:21:52<8:01:45,  1.71it/s]
Train steps ... :  51%|█████     | 50551/100000 [15:21:52<8:02:49,  1.71it/s]
Train steps ... :  51%|█████     | 50552/100000 [15:21:52<8:01:58,  1.71it/s]
Train steps ... :  51%|█████     | 50553/100000 [15:21:53<8:02:00,  1.71it/s]
Train steps ... :  51%|█████     | 50554/100000 [15:21:54<8:01:40,  1.71it/s]
Train steps ... :  51%|█████     | 50555/100000 [15:21:54<8:01:38,  1.71it/s]
Train steps ... :  51%|█████     | 50556/100000 [15:21:55<8:02:10,  1.71it/s]
Train steps ... :  51%|█████     | 50557/100000 [15:21:55<8:02:31,  1.71it/s]
Train steps ... :  51%|█████     | 50558/100000 [15:21:56<8:02:03,  1.71it/s]
Train steps ... :  51%|█████     | 50559/100000 [15:21:57<8:02:06,  1.71it/s]
Train steps ... :  51%|█████     | 50560/100000 [15:21:57<8:02:42,  1.71it/s]
Train steps ... :  51%|█████     | 50561/100000 [15:21:58<8:01:52,  1.71it/s]
Train steps ... :  51%|█████     | 50562/100000 [15:21:58<8:01:33,  1.71it/s]
Train steps ... :  51%|█████     | 50563/100000 [15:21:59<8:01:20,  1.71it/s]
Train steps ... :  51%|█████     | 50564/100000 [15:22:00<8:01:15,  1.71it/s]
Train steps ... :  51%|█████     | 50565/100000 [15:22:00<8:01:08,  1.71it/s]
Train steps ... :  51%|█████     | 50566/100000 [15:22:01<8:02:43,  1.71it/s]
Train steps ... :  51%|█████     | 50567/100000 [15:22:01<8:02:08,  1.71it/s]
Train steps ... :  51%|█████     | 50568/100000 [15:22:02<8:02:06,  1.71it/s]
Train steps ... :  51%|█████     | 50569/100000 [15:22:02<8:02:08,  1.71it/s]
Train steps ... :  51%|█████     | 50570/100000 [15:22:03<8:02:50,  1.71it/s]
Train steps ... :  51%|█████     | 50571/100000 [15:22:04<8:02:32,  1.71it/s]
Train steps ... :  51%|█████     | 50572/100000 [15:22:04<8:02:18,  1.71it/s]
Train steps ... :  51%|█████     | 50573/100000 [15:22:05<8:03:10,  1.70it/s]
Train steps ... :  51%|█████     | 50574/100000 [15:22:05<8:02:52,  1.71it/s]
Train steps ... :  51%|█████     | 50575/100000 [15:22:06<8:02:16,  1.71it/s]Step... (50575 / 100000 | Loss: 0.9249884486198425, Learning Rate: 4.967336683417086e-05)
+
                                                                             
Step... (50575 / 100000 | Loss: 0.6316426396369934, Learning Rate: 4.967336683417086e-05)
+
Train steps ... :  51%|█████     | 50575/100000 [15:22:06<8:02:16,  1.71it/s]
Train steps ... :  51%|█████     | 50576/100000 [15:22:07<8:02:32,  1.71it/s]
Train steps ... :  51%|█████     | 50577/100000 [15:22:07<8:01:53,  1.71it/s]
Train steps ... :  51%|█████     | 50578/100000 [15:22:08<8:02:08,  1.71it/s]
Train steps ... :  51%|█████     | 50579/100000 [15:22:08<8:02:06,  1.71it/s]
Train steps ... :  51%|█████     | 50580/100000 [15:22:09<8:01:21,  1.71it/s]
Train steps ... :  51%|█████     | 50581/100000 [15:22:09<8:00:56,  1.71it/s]
Train steps ... :  51%|█████     | 50582/100000 [15:22:10<8:02:01,  1.71it/s]
Train steps ... :  51%|█████     | 50583/100000 [15:22:11<8:00:53,  1.71it/s]
Train steps ... :  51%|█████     | 50584/100000 [15:22:11<8:01:17,  1.71it/s]
Train steps ... :  51%|█████     | 50585/100000 [15:22:12<8:01:33,  1.71it/s]
Train steps ... :  51%|█████     | 50586/100000 [15:22:12<8:01:07,  1.71it/s]
Train steps ... :  51%|█████     | 50587/100000 [15:22:13<8:01:19,  1.71it/s]
Train steps ... :  51%|█████     | 50588/100000 [15:22:14<8:02:22,  1.71it/s]
Train steps ... :  51%|█████     | 50589/100000 [15:22:14<8:02:10,  1.71it/s]
Train steps ... :  51%|█████     | 50590/100000 [15:22:15<8:02:06,  1.71it/s]
Train steps ... :  51%|█████     | 50591/100000 [15:22:15<8:04:11,  1.70it/s]
Train steps ... :  51%|█████     | 50592/100000 [15:22:16<8:03:10,  1.70it/s]
Train steps ... :  51%|█████     | 50593/100000 [15:22:16<8:01:36,  1.71it/s]
Train steps ... :  51%|█████     | 50594/100000 [15:22:17<8:01:57,  1.71it/s]
Train steps ... :  51%|█████     | 50595/100000 [15:22:18<8:01:04,  1.71it/s]
Train steps ... :  51%|█████     | 50596/100000 [15:22:18<8:00:47,  1.71it/s]
Train steps ... :  51%|█████     | 50597/100000 [15:22:19<8:01:46,  1.71it/s]
Train steps ... :  51%|█████     | 50598/100000 [15:22:19<8:02:00,  1.71it/s]
Train steps ... :  51%|█████     | 50599/100000 [15:22:20<8:03:00,  1.70it/s]
Train steps ... :  51%|█████     | 50600/100000 [15:22:21<8:02:31,  1.71it/s]Step... (50600 / 100000 | Loss: 0.7101494073867798, Learning Rate: 4.9648241206030155e-05)
+
                                                                             
Step... (50600 / 100000 | Loss: 1.2924609184265137, Learning Rate: 4.9648241206030155e-05)
+
Train steps ... :  51%|█████     | 50600/100000 [15:22:21<8:02:31,  1.71it/s]
Train steps ... :  51%|█████     | 50601/100000 [15:22:21<8:02:04,  1.71it/s]
Train steps ... :  51%|█████     | 50602/100000 [15:22:22<8:02:49,  1.71it/s]
Train steps ... :  51%|█████     | 50603/100000 [15:22:22<8:01:07,  1.71it/s]
Train steps ... :  51%|█████     | 50604/100000 [15:22:23<8:02:05,  1.71it/s]
Train steps ... :  51%|█████     | 50605/100000 [15:22:24<8:02:17,  1.71it/s]
Train steps ... :  51%|█████     | 50606/100000 [15:22:24<8:02:07,  1.71it/s]
Train steps ... :  51%|█████     | 50607/100000 [15:22:25<8:02:23,  1.71it/s]
Train steps ... :  51%|█████     | 50608/100000 [15:22:25<8:01:56,  1.71it/s]
Train steps ... :  51%|█████     | 50609/100000 [15:22:26<8:01:22,  1.71it/s]
Train steps ... :  51%|█████     | 50610/100000 [15:22:26<8:01:10,  1.71it/s]
Train steps ... :  51%|█████     | 50611/100000 [15:22:27<8:01:43,  1.71it/s]
Train steps ... :  51%|█████     | 50612/100000 [15:22:28<8:00:42,  1.71it/s]
Train steps ... :  51%|█████     | 50613/100000 [15:22:28<8:01:14,  1.71it/s]
Train steps ... :  51%|█████     | 50614/100000 [15:22:29<8:01:04,  1.71it/s]
Train steps ... :  51%|█████     | 50615/100000 [15:22:29<8:01:30,  1.71it/s]
Train steps ... :  51%|█████     | 50616/100000 [15:22:30<8:00:52,  1.71it/s]
Train steps ... :  51%|█████     | 50617/100000 [15:22:31<8:00:53,  1.71it/s]
Train steps ... :  51%|█████     | 50618/100000 [15:22:31<8:01:29,  1.71it/s]
Train steps ... :  51%|█████     | 50619/100000 [15:22:32<8:01:04,  1.71it/s]
Train steps ... :  51%|█████     | 50620/100000 [15:22:32<8:00:52,  1.71it/s]
Train steps ... :  51%|█████     | 50621/100000 [15:22:33<8:00:53,  1.71it/s]
Train steps ... :  51%|█████     | 50622/100000 [15:22:33<8:01:11,  1.71it/s]
Train steps ... :  51%|█████     | 50623/100000 [15:22:34<8:01:15,  1.71it/s]
Train steps ... :  51%|█████     | 50624/100000 [15:22:35<8:00:22,  1.71it/s]
Train steps ... :  51%|█████     | 50625/100000 [15:22:35<8:00:46,  1.71it/s]Step... (50625 / 100000 | Loss: 0.7336509823799133, Learning Rate: 4.962311557788945e-05)
+
                                                                             
Step... (50625 / 100000 | Loss: 0.9373986721038818, Learning Rate: 4.962311557788945e-05)
+
Train steps ... :  51%|█████     | 50625/100000 [15:22:36<8:00:46,  1.71it/s]
Train steps ... :  51%|█████     | 50626/100000 [15:22:36<8:00:45,  1.71it/s]
Train steps ... :  51%|█████     | 50627/100000 [15:22:36<8:00:29,  1.71it/s]
Train steps ... :  51%|█████     | 50628/100000 [15:22:37<8:02:18,  1.71it/s]
Train steps ... :  51%|█████     | 50629/100000 [15:22:38<8:02:02,  1.71it/s]
Train steps ... :  51%|█████     | 50630/100000 [15:22:38<8:01:38,  1.71it/s]
Train steps ... :  51%|█████     | 50631/100000 [15:22:39<8:01:24,  1.71it/s]
Train steps ... :  51%|█████     | 50632/100000 [15:22:39<8:01:16,  1.71it/s]
Train steps ... :  51%|█████     | 50633/100000 [15:22:40<8:01:37,  1.71it/s]
Train steps ... :  51%|█████     | 50634/100000 [15:22:40<8:01:43,  1.71it/s]
Train steps ... :  51%|█████     | 50635/100000 [15:22:41<8:01:34,  1.71it/s]
Train steps ... :  51%|█████     | 50636/100000 [15:22:42<8:00:54,  1.71it/s]
Train steps ... :  51%|█████     | 50637/100000 [15:22:42<8:01:02,  1.71it/s]
Train steps ... :  51%|█████     | 50638/100000 [15:22:43<8:00:52,  1.71it/s]
Train steps ... :  51%|█████     | 50639/100000 [15:22:43<8:00:40,  1.71it/s]
Train steps ... :  51%|█████     | 50640/100000 [15:22:44<8:00:23,  1.71it/s]
Train steps ... :  51%|█████     | 50641/100000 [15:22:45<8:00:46,  1.71it/s]
Train steps ... :  51%|█████     | 50642/100000 [15:22:45<8:01:25,  1.71it/s]
Train steps ... :  51%|█████     | 50643/100000 [15:22:46<8:01:12,  1.71it/s]
Train steps ... :  51%|█████     | 50644/100000 [15:22:46<8:01:34,  1.71it/s]
Train steps ... :  51%|█████     | 50645/100000 [15:22:47<8:01:26,  1.71it/s]
Train steps ... :  51%|█████     | 50646/100000 [15:22:47<8:02:14,  1.71it/s]
Train steps ... :  51%|█████     | 50647/100000 [15:22:48<8:01:45,  1.71it/s]
Train steps ... :  51%|█████     | 50648/100000 [15:22:49<8:01:52,  1.71it/s]
Train steps ... :  51%|█████     | 50649/100000 [15:22:49<8:00:34,  1.71it/s]
Train steps ... :  51%|█████     | 50650/100000 [15:22:50<8:00:48,  1.71it/s]Step... (50650 / 100000 | Loss: 0.7014842629432678, Learning Rate: 4.959798994974875e-05)
+
                                                                             
Step... (50650 / 100000 | Loss: 0.7264809608459473, Learning Rate: 4.959798994974875e-05)
+
Train steps ... :  51%|█████     | 50650/100000 [15:22:50<8:00:48,  1.71it/s]
Train steps ... :  51%|█████     | 50651/100000 [15:22:50<8:00:45,  1.71it/s]
Train steps ... :  51%|█████     | 50652/100000 [15:22:51<8:01:26,  1.71it/s]
Train steps ... :  51%|█████     | 50653/100000 [15:22:52<8:01:42,  1.71it/s]
Train steps ... :  51%|█████     | 50654/100000 [15:22:52<8:00:15,  1.71it/s]
Train steps ... :  51%|█████     | 50655/100000 [15:22:53<8:01:12,  1.71it/s]
Train steps ... :  51%|█████     | 50656/100000 [15:22:53<8:00:40,  1.71it/s]
Train steps ... :  51%|█████     | 50657/100000 [15:22:54<8:00:40,  1.71it/s]
Train steps ... :  51%|█████     | 50658/100000 [15:22:55<8:01:08,  1.71it/s]
Train steps ... :  51%|█████     | 50659/100000 [15:22:55<8:00:45,  1.71it/s]
Train steps ... :  51%|█████     | 50660/100000 [15:22:56<8:00:26,  1.71it/s]
Train steps ... :  51%|█████     | 50661/100000 [15:22:56<8:00:37,  1.71it/s]
Train steps ... :  51%|█████     | 50662/100000 [15:22:57<8:00:23,  1.71it/s]
Train steps ... :  51%|█████     | 50663/100000 [15:22:57<8:00:51,  1.71it/s]
Train steps ... :  51%|█████     | 50664/100000 [15:22:58<8:00:39,  1.71it/s]
Train steps ... :  51%|█████     | 50665/100000 [15:22:59<8:01:36,  1.71it/s]
Train steps ... :  51%|█████     | 50666/100000 [15:22:59<8:01:23,  1.71it/s]
Train steps ... :  51%|█████     | 50667/100000 [15:23:00<8:01:22,  1.71it/s]
Train steps ... :  51%|█████     | 50668/100000 [15:23:00<8:01:05,  1.71it/s]
Train steps ... :  51%|█████     | 50669/100000 [15:23:01<8:01:08,  1.71it/s]
Train steps ... :  51%|█████     | 50670/100000 [15:23:02<8:01:20,  1.71it/s]
Train steps ... :  51%|█████     | 50671/100000 [15:23:02<8:01:12,  1.71it/s]
Train steps ... :  51%|█████     | 50672/100000 [15:23:03<8:00:50,  1.71it/s]
Train steps ... :  51%|█████     | 50673/100000 [15:23:03<8:01:25,  1.71it/s]
Train steps ... :  51%|█████     | 50674/100000 [15:23:04<8:00:43,  1.71it/s]
Train steps ... :  51%|█████     | 50675/100000 [15:23:04<8:00:54,  1.71it/s]Step... (50675 / 100000 | Loss: 0.7670071125030518, Learning Rate: 4.9572864321608045e-05)
+
                                                                             
Step... (50675 / 100000 | Loss: 0.7600135803222656, Learning Rate: 4.9572864321608045e-05)
+
Train steps ... :  51%|█████     | 50675/100000 [15:23:05<8:00:54,  1.71it/s]
Train steps ... :  51%|█████     | 50676/100000 [15:23:05<8:00:47,  1.71it/s]
Train steps ... :  51%|█████     | 50677/100000 [15:23:06<8:00:39,  1.71it/s]
Train steps ... :  51%|█████     | 50678/100000 [15:23:06<8:00:14,  1.71it/s]
Train steps ... :  51%|█████     | 50679/100000 [15:23:07<8:00:29,  1.71it/s]
Train steps ... :  51%|█████     | 50680/100000 [15:23:07<8:01:17,  1.71it/s]
Train steps ... :  51%|█████     | 50681/100000 [15:23:08<8:00:24,  1.71it/s]
Train steps ... :  51%|█████     | 50682/100000 [15:23:09<8:00:33,  1.71it/s]
Train steps ... :  51%|█████     | 50683/100000 [15:23:09<8:00:11,  1.71it/s]
Train steps ... :  51%|█████     | 50684/100000 [15:23:10<8:00:44,  1.71it/s]
Train steps ... :  51%|█████     | 50685/100000 [15:23:10<8:00:29,  1.71it/s]
Train steps ... :  51%|█████     | 50686/100000 [15:23:11<8:00:15,  1.71it/s]
Train steps ... :  51%|█████     | 50687/100000 [15:23:11<8:00:27,  1.71it/s]
Train steps ... :  51%|█████     | 50688/100000 [15:23:12<8:00:40,  1.71it/s]
Train steps ... :  51%|█████     | 50689/100000 [15:23:13<8:00:43,  1.71it/s]
Train steps ... :  51%|█████     | 50690/100000 [15:23:13<8:00:46,  1.71it/s]
Train steps ... :  51%|█████     | 50691/100000 [15:23:14<8:01:04,  1.71it/s]
Train steps ... :  51%|█████     | 50692/100000 [15:23:14<8:00:53,  1.71it/s]
Train steps ... :  51%|█████     | 50693/100000 [15:23:15<8:00:33,  1.71it/s]
Train steps ... :  51%|█████     | 50694/100000 [15:23:16<8:00:51,  1.71it/s]
Train steps ... :  51%|█████     | 50695/100000 [15:23:16<8:00:44,  1.71it/s]
Train steps ... :  51%|█████     | 50696/100000 [15:23:17<8:00:47,  1.71it/s]
Train steps ... :  51%|█████     | 50697/100000 [15:23:17<8:00:47,  1.71it/s]
Train steps ... :  51%|█████     | 50698/100000 [15:23:18<8:00:21,  1.71it/s]
Train steps ... :  51%|█████     | 50699/100000 [15:23:18<7:59:55,  1.71it/s]
Train steps ... :  51%|█████     | 50700/100000 [15:23:19<8:00:17,  1.71it/s]Step... (50700 / 100000 | Loss: 0.9111982583999634, Learning Rate: 4.954773869346734e-05)
+
                                                                             
Step... (50700 / 100000 | Loss: 0.7000244855880737, Learning Rate: 4.954773869346734e-05)
+
Train steps ... :  51%|█████     | 50700/100000 [15:23:19<8:00:17,  1.71it/s]
Train steps ... :  51%|█████     | 50701/100000 [15:23:20<7:59:58,  1.71it/s]
Train steps ... :  51%|█████     | 50702/100000 [15:23:20<7:59:46,  1.71it/s]
Train steps ... :  51%|█████     | 50703/100000 [15:23:21<7:59:32,  1.71it/s]
Train steps ... :  51%|█████     | 50704/100000 [15:23:21<7:59:44,  1.71it/s]
Train steps ... :  51%|█████     | 50705/100000 [15:23:22<8:00:46,  1.71it/s]
Train steps ... :  51%|█████     | 50706/100000 [15:23:23<8:00:04,  1.71it/s]
Train steps ... :  51%|█████     | 50707/100000 [15:23:23<7:59:37,  1.71it/s]
Train steps ... :  51%|█████     | 50708/100000 [15:23:24<7:59:40,  1.71it/s]
Train steps ... :  51%|█████     | 50709/100000 [15:23:24<7:59:44,  1.71it/s]
Train steps ... :  51%|█████     | 50710/100000 [15:23:25<8:00:07,  1.71it/s]
Train steps ... :  51%|█████     | 50711/100000 [15:23:25<8:00:44,  1.71it/s]
Train steps ... :  51%|█████     | 50712/100000 [15:23:26<8:00:33,  1.71it/s]
Train steps ... :  51%|█████     | 50713/100000 [15:23:27<8:01:17,  1.71it/s]
Train steps ... :  51%|█████     | 50714/100000 [15:23:27<8:00:39,  1.71it/s]
Train steps ... :  51%|█████     | 50715/100000 [15:23:28<8:00:36,  1.71it/s]
Train steps ... :  51%|█████     | 50716/100000 [15:23:28<8:02:07,  1.70it/s]
Train steps ... :  51%|█████     | 50717/100000 [15:23:29<8:01:38,  1.71it/s]
Train steps ... :  51%|█████     | 50718/100000 [15:23:30<8:00:55,  1.71it/s]
Train steps ... :  51%|█████     | 50719/100000 [15:23:30<8:01:03,  1.71it/s]
Train steps ... :  51%|█████     | 50720/100000 [15:23:31<8:00:39,  1.71it/s]
Train steps ... :  51%|█████     | 50721/100000 [15:23:31<8:00:02,  1.71it/s]
Train steps ... :  51%|█████     | 50722/100000 [15:23:32<7:59:39,  1.71it/s]
Train steps ... :  51%|█████     | 50723/100000 [15:23:33<7:59:45,  1.71it/s]
Train steps ... :  51%|█████     | 50724/100000 [15:23:33<8:00:49,  1.71it/s]
Train steps ... :  51%|█████     | 50725/100000 [15:23:34<8:00:31,  1.71it/s]Step... (50725 / 100000 | Loss: 0.8660182356834412, Learning Rate: 4.952261306532663e-05)
+
                                                                             
Step... (50725 / 100000 | Loss: 0.7841641902923584, Learning Rate: 4.952261306532663e-05)
+
Train steps ... :  51%|█████     | 50725/100000 [15:23:34<8:00:31,  1.71it/s]
Train steps ... :  51%|█████     | 50726/100000 [15:23:34<8:01:29,  1.71it/s]
Train steps ... :  51%|█████     | 50727/100000 [15:23:35<8:01:29,  1.71it/s]
Train steps ... :  51%|█████     | 50728/100000 [15:23:35<8:01:13,  1.71it/s]
Train steps ... :  51%|█████     | 50729/100000 [15:23:36<8:01:38,  1.70it/s]
Train steps ... :  51%|█████     | 50730/100000 [15:23:37<8:00:24,  1.71it/s]
Train steps ... :  51%|█████     | 50731/100000 [15:23:37<8:00:17,  1.71it/s]
Train steps ... :  51%|█████     | 50732/100000 [15:23:38<8:00:22,  1.71it/s]
Train steps ... :  51%|█████     | 50733/100000 [15:23:38<8:00:46,  1.71it/s]
Train steps ... :  51%|█████     | 50734/100000 [15:23:39<7:59:52,  1.71it/s]
Train steps ... :  51%|█████     | 50735/100000 [15:23:40<8:00:12,  1.71it/s]
Train steps ... :  51%|█████     | 50736/100000 [15:23:40<8:00:17,  1.71it/s]
Train steps ... :  51%|█████     | 50737/100000 [15:23:41<7:59:43,  1.71it/s]
Train steps ... :  51%|█████     | 50738/100000 [15:23:41<7:59:31,  1.71it/s]
Train steps ... :  51%|█████     | 50739/100000 [15:23:42<7:59:25,  1.71it/s]
Train steps ... :  51%|█████     | 50740/100000 [15:23:42<8:00:02,  1.71it/s]
Train steps ... :  51%|█████     | 50741/100000 [15:23:43<8:01:39,  1.70it/s]
Train steps ... :  51%|█████     | 50742/100000 [15:23:44<8:00:51,  1.71it/s]
Train steps ... :  51%|█████     | 50743/100000 [15:23:44<8:00:48,  1.71it/s]
Train steps ... :  51%|█████     | 50744/100000 [15:23:45<8:00:09,  1.71it/s]
Train steps ... :  51%|█████     | 50745/100000 [15:23:45<8:00:13,  1.71it/s]
Train steps ... :  51%|█████     | 50746/100000 [15:23:46<8:00:37,  1.71it/s]
Train steps ... :  51%|█████     | 50747/100000 [15:23:47<8:00:04,  1.71it/s]
Train steps ... :  51%|█████     | 50748/100000 [15:23:47<8:00:32,  1.71it/s]
Train steps ... :  51%|█████     | 50749/100000 [15:23:48<7:59:56,  1.71it/s]
Train steps ... :  51%|█████     | 50750/100000 [15:23:48<7:59:57,  1.71it/s]Step... (50750 / 100000 | Loss: 0.7556475400924683, Learning Rate: 4.949748743718593e-05)
+
                                                                             
Step... (50750 / 100000 | Loss: 0.892859697341919, Learning Rate: 4.949748743718593e-05)
+
Train steps ... :  51%|█████     | 50750/100000 [15:23:49<7:59:57,  1.71it/s]
Train steps ... :  51%|█████     | 50751/100000 [15:23:49<8:00:35,  1.71it/s]
Train steps ... :  51%|█████     | 50752/100000 [15:23:49<8:00:26,  1.71it/s]
Train steps ... :  51%|█████     | 50753/100000 [15:23:50<8:01:22,  1.71it/s]
Train steps ... :  51%|█████     | 50754/100000 [15:23:51<8:00:56,  1.71it/s]
Train steps ... :  51%|█████     | 50755/100000 [15:23:51<8:01:18,  1.71it/s]
Train steps ... :  51%|█████     | 50756/100000 [15:23:52<8:01:51,  1.70it/s]
Train steps ... :  51%|█████     | 50757/100000 [15:23:52<8:00:19,  1.71it/s]
Train steps ... :  51%|█████     | 50758/100000 [15:23:53<7:59:56,  1.71it/s]
Train steps ... :  51%|█████     | 50759/100000 [15:23:54<8:00:11,  1.71it/s]
Train steps ... :  51%|█████     | 50760/100000 [15:23:54<8:00:04,  1.71it/s]
Train steps ... :  51%|█████     | 50761/100000 [15:23:55<8:01:04,  1.71it/s]
Train steps ... :  51%|█████     | 50762/100000 [15:23:55<8:00:52,  1.71it/s]
Train steps ... :  51%|█████     | 50763/100000 [15:23:56<8:02:09,  1.70it/s]
Train steps ... :  51%|█████     | 50764/100000 [15:23:57<8:00:11,  1.71it/s]
Train steps ... :  51%|█████     | 50765/100000 [15:23:57<8:00:14,  1.71it/s]
Train steps ... :  51%|█████     | 50766/100000 [15:23:58<8:00:32,  1.71it/s]
Train steps ... :  51%|█████     | 50767/100000 [15:23:58<8:00:18,  1.71it/s]
Train steps ... :  51%|█████     | 50768/100000 [15:23:59<8:00:19,  1.71it/s]
Train steps ... :  51%|█████     | 50769/100000 [15:23:59<7:59:53,  1.71it/s]
Train steps ... :  51%|█████     | 50770/100000 [15:24:00<7:59:51,  1.71it/s]
Train steps ... :  51%|█████     | 50771/100000 [15:24:01<7:59:20,  1.71it/s]
Train steps ... :  51%|█████     | 50772/100000 [15:24:01<7:59:24,  1.71it/s]
Train steps ... :  51%|█████     | 50773/100000 [15:24:02<7:59:29,  1.71it/s]
Train steps ... :  51%|█████     | 50774/100000 [15:24:02<7:59:17,  1.71it/s]
Train steps ... :  51%|█████     | 50775/100000 [15:24:03<7:59:21,  1.71it/s]Step... (50775 / 100000 | Loss: 0.7365771532058716, Learning Rate: 4.947236180904523e-05)
+
                                                                             
Step... (50775 / 100000 | Loss: 0.7281135320663452, Learning Rate: 4.947236180904523e-05)
+
Train steps ... :  51%|█████     | 50775/100000 [15:24:03<7:59:21,  1.71it/s]
Train steps ... :  51%|█████     | 50776/100000 [15:24:04<7:59:02,  1.71it/s]
Train steps ... :  51%|█████     | 50777/100000 [15:24:04<7:59:07,  1.71it/s]
Train steps ... :  51%|█████     | 50778/100000 [15:24:05<7:59:35,  1.71it/s]
Train steps ... :  51%|█████     | 50779/100000 [15:24:05<7:59:05,  1.71it/s]
Train steps ... :  51%|█████     | 50780/100000 [15:24:06<8:00:33,  1.71it/s]
Train steps ... :  51%|█████     | 50781/100000 [15:24:06<8:01:11,  1.70it/s]
Train steps ... :  51%|█████     | 50782/100000 [15:24:07<8:00:59,  1.71it/s]
Train steps ... :  51%|█████     | 50783/100000 [15:24:08<8:00:00,  1.71it/s]
Train steps ... :  51%|█████     | 50784/100000 [15:24:08<7:59:43,  1.71it/s]
Train steps ... :  51%|█████     | 50785/100000 [15:24:09<8:00:17,  1.71it/s]
Train steps ... :  51%|█████     | 50786/100000 [15:24:09<8:00:27,  1.71it/s]
Train steps ... :  51%|█████     | 50787/100000 [15:24:10<7:59:09,  1.71it/s]
Train steps ... :  51%|█████     | 50788/100000 [15:24:11<7:59:26,  1.71it/s]
Train steps ... :  51%|█████     | 50789/100000 [15:24:11<8:00:00,  1.71it/s]
Train steps ... :  51%|█████     | 50790/100000 [15:24:12<8:00:21,  1.71it/s]
Train steps ... :  51%|█████     | 50791/100000 [15:24:12<7:59:44,  1.71it/s]
Train steps ... :  51%|█████     | 50792/100000 [15:24:13<7:59:42,  1.71it/s]
Train steps ... :  51%|█████     | 50793/100000 [15:24:13<7:59:59,  1.71it/s]
Train steps ... :  51%|█████     | 50794/100000 [15:24:14<7:59:41,  1.71it/s]
Train steps ... :  51%|█████     | 50795/100000 [15:24:15<7:59:45,  1.71it/s]
Train steps ... :  51%|█████     | 50796/100000 [15:24:15<7:59:28,  1.71it/s]
Train steps ... :  51%|█████     | 50797/100000 [15:24:16<8:01:19,  1.70it/s]
Train steps ... :  51%|█████     | 50798/100000 [15:24:16<7:59:35,  1.71it/s]
Train steps ... :  51%|█████     | 50799/100000 [15:24:17<8:00:29,  1.71it/s]
Train steps ... :  51%|█████     | 50800/100000 [15:24:18<8:00:13,  1.71it/s]Step... (50800 / 100000 | Loss: 0.9352281093597412, Learning Rate: 4.944723618090453e-05)
+
                                                                             
Step... (50800 / 100000 | Loss: 0.6421765089035034, Learning Rate: 4.944723618090453e-05)
+
Train steps ... :  51%|█████     | 50800/100000 [15:24:18<8:00:13,  1.71it/s]
Train steps ... :  51%|█████     | 50801/100000 [15:24:18<8:00:32,  1.71it/s]
Train steps ... :  51%|█████     | 50802/100000 [15:24:19<7:59:50,  1.71it/s]
Train steps ... :  51%|█████     | 50803/100000 [15:24:19<8:01:26,  1.70it/s]
Train steps ... :  51%|█████     | 50804/100000 [15:24:20<8:00:30,  1.71it/s]
Train steps ... :  51%|█████     | 50805/100000 [15:24:21<8:00:17,  1.71it/s]
Train steps ... :  51%|█████     | 50806/100000 [15:24:21<8:00:27,  1.71it/s]
Train steps ... :  51%|█████     | 50807/100000 [15:24:22<8:00:18,  1.71it/s]
Train steps ... :  51%|█████     | 50808/100000 [15:24:22<7:59:20,  1.71it/s]
Train steps ... :  51%|█████     | 50809/100000 [15:24:23<8:00:50,  1.71it/s]
Train steps ... :  51%|█████     | 50810/100000 [15:24:23<8:00:32,  1.71it/s]
Train steps ... :  51%|█████     | 50811/100000 [15:24:24<7:59:28,  1.71it/s]
Train steps ... :  51%|█████     | 50812/100000 [15:24:25<8:00:47,  1.71it/s]
Train steps ... :  51%|█████     | 50813/100000 [15:24:25<7:58:49,  1.71it/s]
Train steps ... :  51%|█████     | 50814/100000 [15:24:26<7:59:51,  1.71it/s]
Train steps ... :  51%|█████     | 50815/100000 [15:24:26<8:02:30,  1.70it/s]
Train steps ... :  51%|█████     | 50816/100000 [15:24:27<7:59:56,  1.71it/s]
Train steps ... :  51%|█████     | 50817/100000 [15:24:28<8:00:15,  1.71it/s]
Train steps ... :  51%|█████     | 50818/100000 [15:24:28<8:00:08,  1.71it/s]
Train steps ... :  51%|█████     | 50819/100000 [15:24:29<7:59:52,  1.71it/s]
Train steps ... :  51%|█████     | 50820/100000 [15:24:29<8:00:43,  1.71it/s]
Train steps ... :  51%|█████     | 50821/100000 [15:24:30<8:00:50,  1.70it/s]
Train steps ... :  51%|█████     | 50822/100000 [15:24:30<8:00:02,  1.71it/s]
Train steps ... :  51%|█████     | 50823/100000 [15:24:31<7:59:46,  1.71it/s]
Train steps ... :  51%|█████     | 50824/100000 [15:24:32<7:59:13,  1.71it/s]
Train steps ... :  51%|█████     | 50825/100000 [15:24:32<7:58:49,  1.71it/s]Step... (50825 / 100000 | Loss: 0.5812094211578369, Learning Rate: 4.9422110552763825e-05)
+
                                                                             
Step... (50825 / 100000 | Loss: 0.6785128712654114, Learning Rate: 4.9422110552763825e-05)
+
Train steps ... :  51%|█████     | 50825/100000 [15:24:33<7:58:49,  1.71it/s]
Train steps ... :  51%|█████     | 50826/100000 [15:24:33<7:58:56,  1.71it/s]
Train steps ... :  51%|█████     | 50827/100000 [15:24:33<7:59:52,  1.71it/s]
Train steps ... :  51%|█████     | 50828/100000 [15:24:34<8:00:49,  1.70it/s]
Train steps ... :  51%|█████     | 50829/100000 [15:24:35<8:00:03,  1.71it/s]
Train steps ... :  51%|█████     | 50830/100000 [15:24:35<7:59:26,  1.71it/s]
Train steps ... :  51%|█████     | 50831/100000 [15:24:36<7:59:35,  1.71it/s]
Train steps ... :  51%|█████     | 50832/100000 [15:24:36<7:59:14,  1.71it/s]
Train steps ... :  51%|█████     | 50833/100000 [15:24:37<7:59:50,  1.71it/s]
Train steps ... :  51%|█████     | 50834/100000 [15:24:37<8:00:34,  1.71it/s]
Train steps ... :  51%|█████     | 50835/100000 [15:24:38<7:59:52,  1.71it/s]
Train steps ... :  51%|█████     | 50836/100000 [15:24:39<7:59:32,  1.71it/s]
Train steps ... :  51%|█████     | 50837/100000 [15:24:39<7:58:59,  1.71it/s]
Train steps ... :  51%|█████     | 50838/100000 [15:24:40<7:59:42,  1.71it/s]
Train steps ... :  51%|█████     | 50839/100000 [15:24:40<8:00:44,  1.70it/s]
Train steps ... :  51%|█████     | 50840/100000 [15:24:41<7:59:05,  1.71it/s]
Train steps ... :  51%|█████     | 50841/100000 [15:24:42<7:58:41,  1.71it/s]
Train steps ... :  51%|█████     | 50842/100000 [15:24:42<7:58:55,  1.71it/s]
Train steps ... :  51%|█████     | 50843/100000 [15:24:43<7:58:43,  1.71it/s]
Train steps ... :  51%|█████     | 50844/100000 [15:24:43<7:58:38,  1.71it/s]
Train steps ... :  51%|█████     | 50845/100000 [15:24:44<7:59:31,  1.71it/s]
Train steps ... :  51%|█████     | 50846/100000 [15:24:45<7:59:02,  1.71it/s]
Train steps ... :  51%|█████     | 50847/100000 [15:24:45<7:59:17,  1.71it/s]
Train steps ... :  51%|█████     | 50848/100000 [15:24:46<8:00:28,  1.70it/s]
Train steps ... :  51%|█████     | 50849/100000 [15:24:46<7:59:23,  1.71it/s]
Train steps ... :  51%|█████     | 50850/100000 [15:24:47<8:00:32,  1.70it/s]Step... (50850 / 100000 | Loss: 0.7916241884231567, Learning Rate: 4.939698492462312e-05)
+
                                                                             
Step... (50850 / 100000 | Loss: 0.7029606699943542, Learning Rate: 4.939698492462312e-05)
+
Train steps ... :  51%|█████     | 50850/100000 [15:24:47<8:00:32,  1.70it/s]
Train steps ... :  51%|█████     | 50851/100000 [15:24:47<8:00:00,  1.71it/s]
Train steps ... :  51%|█████     | 50852/100000 [15:24:48<7:59:43,  1.71it/s]
Train steps ... :  51%|█████     | 50853/100000 [15:24:49<8:00:08,  1.71it/s]
Train steps ... :  51%|█████     | 50854/100000 [15:24:49<7:58:51,  1.71it/s]
Train steps ... :  51%|█████     | 50855/100000 [15:24:50<7:58:43,  1.71it/s]
Train steps ... :  51%|█████     | 50856/100000 [15:24:50<7:58:32,  1.71it/s]
Train steps ... :  51%|█████     | 50857/100000 [15:24:51<7:59:29,  1.71it/s]
Train steps ... :  51%|█████     | 50858/100000 [15:24:52<7:59:31,  1.71it/s]
Train steps ... :  51%|█████     | 50859/100000 [15:24:52<7:59:58,  1.71it/s]
Train steps ... :  51%|█████     | 50860/100000 [15:24:53<7:59:28,  1.71it/s]
Train steps ... :  51%|█████     | 50861/100000 [15:24:53<7:59:41,  1.71it/s]
Train steps ... :  51%|█████     | 50862/100000 [15:24:54<7:59:12,  1.71it/s]
Train steps ... :  51%|█████     | 50863/100000 [15:24:54<7:59:07,  1.71it/s]
Train steps ... :  51%|█████     | 50864/100000 [15:24:55<7:59:43,  1.71it/s]
Train steps ... :  51%|█████     | 50865/100000 [15:24:56<8:00:21,  1.70it/s]
Train steps ... :  51%|█████     | 50866/100000 [15:24:56<7:58:58,  1.71it/s]
Train steps ... :  51%|█████     | 50867/100000 [15:24:57<7:58:54,  1.71it/s]
Train steps ... :  51%|█████     | 50868/100000 [15:24:57<7:58:27,  1.71it/s]
Train steps ... :  51%|█████     | 50869/100000 [15:24:58<7:59:04,  1.71it/s]
Train steps ... :  51%|█████     | 50870/100000 [15:24:59<8:00:00,  1.71it/s]
Train steps ... :  51%|█████     | 50871/100000 [15:24:59<7:59:39,  1.71it/s]
Train steps ... :  51%|█████     | 50872/100000 [15:25:00<7:58:17,  1.71it/s]
Train steps ... :  51%|█████     | 50873/100000 [15:25:00<7:58:39,  1.71it/s]
Train steps ... :  51%|█████     | 50874/100000 [15:25:01<7:58:13,  1.71it/s]
Train steps ... :  51%|█████     | 50875/100000 [15:25:01<7:58:30,  1.71it/s]Step... (50875 / 100000 | Loss: 0.7744611501693726, Learning Rate: 4.937185929648241e-05)
+
                                                                             
Step... (50875 / 100000 | Loss: 0.8755049705505371, Learning Rate: 4.937185929648241e-05)
+
Train steps ... :  51%|█████     | 50875/100000 [15:25:02<7:58:30,  1.71it/s]
Train steps ... :  51%|█████     | 50876/100000 [15:25:02<7:58:21,  1.71it/s]
Train steps ... :  51%|█████     | 50877/100000 [15:25:03<7:58:46,  1.71it/s]
Train steps ... :  51%|█████     | 50878/100000 [15:25:03<7:59:20,  1.71it/s]
Train steps ... :  51%|█████     | 50879/100000 [15:25:04<7:59:01,  1.71it/s]
Train steps ... :  51%|█████     | 50880/100000 [15:25:04<7:59:24,  1.71it/s]
Train steps ... :  51%|█████     | 50881/100000 [15:25:05<7:59:59,  1.71it/s]
Train steps ... :  51%|█████     | 50882/100000 [15:25:06<7:59:08,  1.71it/s]
Train steps ... :  51%|█████     | 50883/100000 [15:25:06<7:59:12,  1.71it/s]
Train steps ... :  51%|█████     | 50884/100000 [15:25:07<7:58:59,  1.71it/s]
Train steps ... :  51%|█████     | 50885/100000 [15:25:07<7:58:57,  1.71it/s]
Train steps ... :  51%|█████     | 50886/100000 [15:25:08<7:58:37,  1.71it/s]
Train steps ... :  51%|█████     | 50887/100000 [15:25:09<7:59:19,  1.71it/s]
Train steps ... :  51%|█████     | 50888/100000 [15:25:09<7:59:39,  1.71it/s]
Train steps ... :  51%|█████     | 50889/100000 [15:25:10<7:59:33,  1.71it/s]
Train steps ... :  51%|█████     | 50890/100000 [15:25:10<8:00:43,  1.70it/s]
Train steps ... :  51%|█████     | 50891/100000 [15:25:11<7:59:44,  1.71it/s]
Train steps ... :  51%|█████     | 50892/100000 [15:25:11<7:58:35,  1.71it/s]
Train steps ... :  51%|█████     | 50893/100000 [15:25:12<8:00:09,  1.70it/s]
Train steps ... :  51%|█████     | 50894/100000 [15:25:13<7:58:42,  1.71it/s]
Train steps ... :  51%|█████     | 50895/100000 [15:25:13<7:59:48,  1.71it/s]
Train steps ... :  51%|█████     | 50896/100000 [15:25:14<7:59:08,  1.71it/s]
Train steps ... :  51%|█████     | 50897/100000 [15:25:14<7:58:46,  1.71it/s]
Train steps ... :  51%|█████     | 50898/100000 [15:25:15<7:58:37,  1.71it/s]
Train steps ... :  51%|█████     | 50899/100000 [15:25:16<7:58:36,  1.71it/s]
Train steps ... :  51%|█████     | 50900/100000 [15:25:16<7:59:27,  1.71it/s]Step... (50900 / 100000 | Loss: 0.6498559713363647, Learning Rate: 4.934673366834171e-05)
+
                                                                             
Step... (50900 / 100000 | Loss: 0.6313860416412354, Learning Rate: 4.934673366834171e-05)
+
Train steps ... :  51%|█████     | 50900/100000 [15:25:16<7:59:27,  1.71it/s]
Train steps ... :  51%|█████     | 50901/100000 [15:25:17<7:58:34,  1.71it/s]
Train steps ... :  51%|█████     | 50902/100000 [15:25:17<7:58:33,  1.71it/s]
Train steps ... :  51%|█████     | 50903/100000 [15:25:18<7:58:41,  1.71it/s]
Train steps ... :  51%|█████     | 50904/100000 [15:25:18<7:58:50,  1.71it/s]
Train steps ... :  51%|█████     | 50905/100000 [15:25:19<7:58:39,  1.71it/s]
Train steps ... :  51%|█████     | 50906/100000 [15:25:20<7:59:06,  1.71it/s]
Train steps ... :  51%|█████     | 50907/100000 [15:25:20<7:59:50,  1.71it/s]
Train steps ... :  51%|█████     | 50908/100000 [15:25:21<7:59:16,  1.71it/s]
Train steps ... :  51%|█████     | 50909/100000 [15:25:21<7:58:39,  1.71it/s]
Train steps ... :  51%|█████     | 50910/100000 [15:25:22<7:59:00,  1.71it/s]
Train steps ... :  51%|█████     | 50911/100000 [15:25:23<8:00:12,  1.70it/s]
Train steps ... :  51%|█████     | 50912/100000 [15:25:23<8:00:34,  1.70it/s]
Train steps ... :  51%|█████     | 50913/100000 [15:25:24<8:00:41,  1.70it/s]
Train steps ... :  51%|█████     | 50914/100000 [15:25:24<7:59:35,  1.71it/s]
Train steps ... :  51%|█████     | 50915/100000 [15:25:25<7:59:58,  1.70it/s]
Train steps ... :  51%|█████     | 50916/100000 [15:25:26<8:00:40,  1.70it/s]
Train steps ... :  51%|█████     | 50917/100000 [15:25:26<7:59:30,  1.71it/s]
Train steps ... :  51%|█████     | 50918/100000 [15:25:27<7:59:40,  1.71it/s]
Train steps ... :  51%|█████     | 50919/100000 [15:25:27<7:59:42,  1.71it/s]
Train steps ... :  51%|█████     | 50920/100000 [15:25:28<7:59:52,  1.70it/s]
Train steps ... :  51%|█████     | 50921/100000 [15:25:28<7:59:34,  1.71it/s]
Train steps ... :  51%|█████     | 50922/100000 [15:25:29<8:00:19,  1.70it/s]
Train steps ... :  51%|█████     | 50923/100000 [15:25:30<7:59:40,  1.71it/s]
Train steps ... :  51%|█████     | 50924/100000 [15:25:30<8:00:15,  1.70it/s]
Train steps ... :  51%|█████     | 50925/100000 [15:25:31<7:59:54,  1.70it/s]Step... (50925 / 100000 | Loss: 0.8431972861289978, Learning Rate: 4.9321608040201004e-05)
+
                                                                             
Step... (50925 / 100000 | Loss: 0.7618732452392578, Learning Rate: 4.9321608040201004e-05)
+
Train steps ... :  51%|█████     | 50925/100000 [15:25:31<7:59:54,  1.70it/s]
Train steps ... :  51%|█████     | 50926/100000 [15:25:31<7:59:13,  1.71it/s]
Train steps ... :  51%|█████     | 50927/100000 [15:25:32<7:58:43,  1.71it/s]
Train steps ... :  51%|█████     | 50928/100000 [15:25:33<8:00:16,  1.70it/s]
Train steps ... :  51%|█████     | 50929/100000 [15:25:33<7:58:01,  1.71it/s]
Train steps ... :  51%|█████     | 50930/100000 [15:25:34<7:58:14,  1.71it/s]
Train steps ... :  51%|█████     | 50931/100000 [15:25:34<7:58:17,  1.71it/s]
Train steps ... :  51%|█████     | 50932/100000 [15:25:35<7:58:29,  1.71it/s]
Train steps ... :  51%|█████     | 50933/100000 [15:25:35<7:59:02,  1.71it/s]
Train steps ... :  51%|█████     | 50934/100000 [15:25:36<7:58:33,  1.71it/s]
Train steps ... :  51%|█████     | 50935/100000 [15:25:37<7:58:02,  1.71it/s]
Train steps ... :  51%|█████     | 50936/100000 [15:25:37<7:57:49,  1.71it/s]
Train steps ... :  51%|█████     | 50937/100000 [15:25:38<7:58:36,  1.71it/s]
Train steps ... :  51%|█████     | 50938/100000 [15:25:38<7:57:50,  1.71it/s]
Train steps ... :  51%|█████     | 50939/100000 [15:25:39<7:57:48,  1.71it/s]
Train steps ... :  51%|█████     | 50940/100000 [15:25:40<7:57:37,  1.71it/s]
Train steps ... :  51%|█████     | 50941/100000 [15:25:40<7:58:36,  1.71it/s]
Train steps ... :  51%|█████     | 50942/100000 [15:25:41<7:58:55,  1.71it/s]
Train steps ... :  51%|█████     | 50943/100000 [15:25:41<7:58:59,  1.71it/s]
Train steps ... :  51%|█████     | 50944/100000 [15:25:42<7:58:51,  1.71it/s]
Train steps ... :  51%|█████     | 50945/100000 [15:25:42<7:58:04,  1.71it/s]
Train steps ... :  51%|█████     | 50946/100000 [15:25:43<7:58:31,  1.71it/s]
Train steps ... :  51%|█████     | 50947/100000 [15:25:44<7:58:41,  1.71it/s]
Train steps ... :  51%|█████     | 50948/100000 [15:25:44<7:58:49,  1.71it/s]
Train steps ... :  51%|█████     | 50949/100000 [15:25:45<7:59:56,  1.70it/s]
Train steps ... :  51%|█████     | 50950/100000 [15:25:45<7:58:42,  1.71it/s]Step... (50950 / 100000 | Loss: 0.7455084919929504, Learning Rate: 4.92964824120603e-05)
+
                                                                             
Step... (50950 / 100000 | Loss: 0.8320541977882385, Learning Rate: 4.92964824120603e-05)
+
Train steps ... :  51%|█████     | 50950/100000 [15:25:46<7:58:42,  1.71it/s]
Train steps ... :  51%|█████     | 50951/100000 [15:25:46<7:59:33,  1.70it/s]
Train steps ... :  51%|█████     | 50952/100000 [15:25:47<8:00:06,  1.70it/s]
Train steps ... :  51%|█████     | 50953/100000 [15:25:47<7:59:09,  1.71it/s]
Train steps ... :  51%|█████     | 50954/100000 [15:25:48<7:59:13,  1.71it/s]
Train steps ... :  51%|█████     | 50955/100000 [15:25:48<7:59:07,  1.71it/s]
Train steps ... :  51%|█████     | 50956/100000 [15:25:49<7:58:49,  1.71it/s]
Train steps ... :  51%|█████     | 50957/100000 [15:25:50<7:59:47,  1.70it/s]
Train steps ... :  51%|█████     | 50958/100000 [15:25:50<7:59:08,  1.71it/s]
Train steps ... :  51%|█████     | 50959/100000 [15:25:51<7:59:21,  1.71it/s]
Train steps ... :  51%|█████     | 50960/100000 [15:25:51<7:59:01,  1.71it/s]
Train steps ... :  51%|█████     | 50961/100000 [15:25:52<7:59:30,  1.70it/s]
Train steps ... :  51%|█████     | 50962/100000 [15:25:52<7:59:08,  1.71it/s]
Train steps ... :  51%|█████     | 50963/100000 [15:25:53<7:58:43,  1.71it/s]
Train steps ... :  51%|█████     | 50964/100000 [15:25:54<7:58:23,  1.71it/s]
Train steps ... :  51%|█████     | 50965/100000 [15:25:54<7:57:53,  1.71it/s]
Train steps ... :  51%|█████     | 50966/100000 [15:25:55<7:58:17,  1.71it/s]
Train steps ... :  51%|█████     | 50967/100000 [15:25:55<7:58:33,  1.71it/s]
Train steps ... :  51%|█████     | 50968/100000 [15:25:56<7:58:24,  1.71it/s]
Train steps ... :  51%|█████     | 50969/100000 [15:25:57<7:57:54,  1.71it/s]
Train steps ... :  51%|█████     | 50970/100000 [15:25:57<7:59:11,  1.71it/s]
Train steps ... :  51%|█████     | 50971/100000 [15:25:58<7:57:45,  1.71it/s]
Train steps ... :  51%|█████     | 50972/100000 [15:25:58<7:58:12,  1.71it/s]
Train steps ... :  51%|█████     | 50973/100000 [15:25:59<7:59:07,  1.71it/s]
Train steps ... :  51%|█████     | 50974/100000 [15:25:59<7:58:57,  1.71it/s]
Train steps ... :  51%|█████     | 50975/100000 [15:26:00<7:58:00,  1.71it/s]Step... (50975 / 100000 | Loss: 0.9366468191146851, Learning Rate: 4.92713567839196e-05)
+
                                                                             
Step... (50975 / 100000 | Loss: 0.9772243499755859, Learning Rate: 4.92713567839196e-05)
+
Train steps ... :  51%|█████     | 50975/100000 [15:26:00<7:58:00,  1.71it/s]
Train steps ... :  51%|█████     | 50976/100000 [15:26:01<7:59:15,  1.70it/s]
Train steps ... :  51%|█████     | 50977/100000 [15:26:01<7:58:46,  1.71it/s]
Train steps ... :  51%|█████     | 50978/100000 [15:26:02<7:58:42,  1.71it/s]
Train steps ... :  51%|█████     | 50979/100000 [15:26:02<7:57:59,  1.71it/s]
Train steps ... :  51%|█████     | 50980/100000 [15:26:03<7:58:20,  1.71it/s]
Train steps ... :  51%|█████     | 50981/100000 [15:26:04<7:57:56,  1.71it/s]
Train steps ... :  51%|█████     | 50982/100000 [15:26:04<7:58:45,  1.71it/s]
Train steps ... :  51%|█████     | 50983/100000 [15:26:05<7:58:19,  1.71it/s]
Train steps ... :  51%|█████     | 50984/100000 [15:26:05<7:58:50,  1.71it/s]
Train steps ... :  51%|█████     | 50985/100000 [15:26:06<7:58:38,  1.71it/s]
Train steps ... :  51%|█████     | 50986/100000 [15:26:07<7:58:13,  1.71it/s]
Train steps ... :  51%|█████     | 50987/100000 [15:26:07<7:57:57,  1.71it/s]
Train steps ... :  51%|█████     | 50988/100000 [15:26:08<7:58:56,  1.71it/s]
Train steps ... :  51%|█████     | 50989/100000 [15:26:08<7:57:59,  1.71it/s]
Train steps ... :  51%|█████     | 50990/100000 [15:26:09<7:57:50,  1.71it/s]
Train steps ... :  51%|█████     | 50991/100000 [15:26:09<7:57:49,  1.71it/s]
Train steps ... :  51%|█████     | 50992/100000 [15:26:10<7:57:35,  1.71it/s]
Train steps ... :  51%|█████     | 50993/100000 [15:26:11<7:57:23,  1.71it/s]
Train steps ... :  51%|█████     | 50994/100000 [15:26:11<7:57:11,  1.71it/s]
Train steps ... :  51%|█████     | 50995/100000 [15:26:12<7:57:10,  1.71it/s]
Train steps ... :  51%|█████     | 50996/100000 [15:26:12<7:58:28,  1.71it/s]
Train steps ... :  51%|█████     | 50997/100000 [15:26:13<7:57:57,  1.71it/s]
Train steps ... :  51%|█████     | 50998/100000 [15:26:14<7:58:16,  1.71it/s]
Train steps ... :  51%|█████     | 50999/100000 [15:26:14<7:57:30,  1.71it/s]
Train steps ... :  51%|█████     | 51000/100000 [15:26:15<7:57:55,  1.71it/s]Step... (51000 / 100000 | Loss: 0.906682550907135, Learning Rate: 4.92462311557789e-05)
+
                                                                             
Step... (51000 / 100000 | Loss: 0.9792234897613525, Learning Rate: 4.92462311557789e-05)
+
Train steps ... :  51%|█████     | 51000/100000 [15:26:15<7:57:55,  1.71it/s]
Train steps ... :  51%|█████     | 51001/100000 [15:26:15<7:57:49,  1.71it/s]
Train steps ... :  51%|█████     | 51002/100000 [15:26:16<7:58:20,  1.71it/s]
Train steps ... :  51%|█████     | 51003/100000 [15:26:16<7:57:43,  1.71it/s]
Train steps ... :  51%|█████     | 51004/100000 [15:26:17<7:57:40,  1.71it/s]
Train steps ... :  51%|█████     | 51005/100000 [15:26:18<7:57:18,  1.71it/s]
Train steps ... :  51%|█████     | 51006/100000 [15:26:18<7:57:35,  1.71it/s]
Train steps ... :  51%|█████     | 51007/100000 [15:26:19<7:57:23,  1.71it/s]
Train steps ... :  51%|█████     | 51008/100000 [15:26:19<7:57:37,  1.71it/s]
Train steps ... :  51%|█████     | 51009/100000 [15:26:20<7:57:27,  1.71it/s]
Train steps ... :  51%|█████     | 51010/100000 [15:26:21<7:58:31,  1.71it/s]
Train steps ... :  51%|█████     | 51011/100000 [15:26:21<7:57:56,  1.71it/s]
Train steps ... :  51%|█████     | 51012/100000 [15:26:22<7:57:08,  1.71it/s]
Train steps ... :  51%|█████     | 51013/100000 [15:26:22<7:57:42,  1.71it/s]
Train steps ... :  51%|█████     | 51014/100000 [15:26:23<7:58:20,  1.71it/s]
Train steps ... :  51%|█████     | 51015/100000 [15:26:23<7:58:27,  1.71it/s]
Train steps ... :  51%|█████     | 51016/100000 [15:26:24<7:57:47,  1.71it/s]
Train steps ... :  51%|█████     | 51017/100000 [15:26:25<7:58:25,  1.71it/s]
Train steps ... :  51%|█████     | 51018/100000 [15:26:25<7:59:15,  1.70it/s]
Train steps ... :  51%|█████     | 51019/100000 [15:26:26<7:57:41,  1.71it/s]
Train steps ... :  51%|█████     | 51020/100000 [15:26:26<7:57:38,  1.71it/s]
Train steps ... :  51%|█████     | 51021/100000 [15:26:27<7:58:03,  1.71it/s]
Train steps ... :  51%|█████     | 51022/100000 [15:26:28<7:56:56,  1.71it/s]
Train steps ... :  51%|█████     | 51023/100000 [15:26:28<7:57:02,  1.71it/s]
Train steps ... :  51%|█████     | 51024/100000 [15:26:29<7:57:02,  1.71it/s]
Train steps ... :  51%|█████     | 51025/100000 [15:26:29<7:56:19,  1.71it/s]Step... (51025 / 100000 | Loss: 1.0386779308319092, Learning Rate: 4.92211055276382e-05)
+
                                                                             
Step... (51025 / 100000 | Loss: 0.7390068769454956, Learning Rate: 4.92211055276382e-05)
+
Train steps ... :  51%|█████     | 51025/100000 [15:26:30<7:56:19,  1.71it/s]
Train steps ... :  51%|█████     | 51026/100000 [15:26:30<7:56:57,  1.71it/s]
Train steps ... :  51%|█████     | 51027/100000 [15:26:30<7:56:58,  1.71it/s]
Train steps ... :  51%|█████     | 51028/100000 [15:26:31<7:57:29,  1.71it/s]
Train steps ... :  51%|█████     | 51029/100000 [15:26:32<7:57:42,  1.71it/s]
Train steps ... :  51%|█████     | 51030/100000 [15:26:32<7:57:47,  1.71it/s]
Train steps ... :  51%|█████     | 51031/100000 [15:26:33<7:58:32,  1.71it/s]
Train steps ... :  51%|█████     | 51032/100000 [15:26:33<7:57:43,  1.71it/s]
Train steps ... :  51%|█████     | 51033/100000 [15:26:34<7:57:23,  1.71it/s]
Train steps ... :  51%|█████     | 51034/100000 [15:26:35<7:57:12,  1.71it/s]
Train steps ... :  51%|█████     | 51035/100000 [15:26:35<7:57:48,  1.71it/s]
Train steps ... :  51%|█████     | 51036/100000 [15:26:36<7:57:35,  1.71it/s]
Train steps ... :  51%|█████     | 51037/100000 [15:26:36<7:57:45,  1.71it/s]
Train steps ... :  51%|█████     | 51038/100000 [15:26:37<7:57:50,  1.71it/s]
Train steps ... :  51%|█████     | 51039/100000 [15:26:38<7:57:57,  1.71it/s]
Train steps ... :  51%|█████     | 51040/100000 [15:26:38<7:59:22,  1.70it/s]
Train steps ... :  51%|█████     | 51041/100000 [15:26:39<7:57:50,  1.71it/s]
Train steps ... :  51%|█████     | 51042/100000 [15:26:39<7:59:10,  1.70it/s]
Train steps ... :  51%|█████     | 51043/100000 [15:26:40<7:58:10,  1.71it/s]
Train steps ... :  51%|█████     | 51044/100000 [15:26:40<7:59:21,  1.70it/s]
Train steps ... :  51%|█████     | 51045/100000 [15:26:41<8:01:58,  1.69it/s]
Train steps ... :  51%|█████     | 51046/100000 [15:26:42<8:01:35,  1.69it/s]
Train steps ... :  51%|█████     | 51047/100000 [15:26:42<8:00:04,  1.70it/s]
Train steps ... :  51%|█████     | 51048/100000 [15:26:43<8:00:24,  1.70it/s]
Train steps ... :  51%|█████     | 51049/100000 [15:26:43<7:59:22,  1.70it/s]
Train steps ... :  51%|█████     | 51050/100000 [15:26:44<7:58:39,  1.70it/s]Step... (51050 / 100000 | Loss: 0.9603981971740723, Learning Rate: 4.919597989949749e-05)
+
                                                                             
Step... (51050 / 100000 | Loss: 0.7987639307975769, Learning Rate: 4.919597989949749e-05)
+
Train steps ... :  51%|█████     | 51050/100000 [15:26:44<7:58:39,  1.70it/s]
Train steps ... :  51%|█████     | 51051/100000 [15:26:45<7:58:30,  1.70it/s]
Train steps ... :  51%|█████     | 51052/100000 [15:26:45<7:58:06,  1.71it/s]
Train steps ... :  51%|█████     | 51053/100000 [15:26:46<7:57:51,  1.71it/s]
Train steps ... :  51%|█████     | 51054/100000 [15:26:46<7:57:50,  1.71it/s]
Train steps ... :  51%|█████     | 51055/100000 [15:26:47<7:58:12,  1.71it/s]
Train steps ... :  51%|█████     | 51056/100000 [15:26:48<7:58:21,  1.71it/s]
Train steps ... :  51%|█████     | 51057/100000 [15:26:48<7:57:51,  1.71it/s]
Train steps ... :  51%|█████     | 51058/100000 [15:26:49<7:57:23,  1.71it/s]
Train steps ... :  51%|█████     | 51059/100000 [15:26:49<7:57:43,  1.71it/s]
Train steps ... :  51%|█████     | 51060/100000 [15:26:50<7:57:31,  1.71it/s]
Train steps ... :  51%|█████     | 51061/100000 [15:26:50<7:57:41,  1.71it/s]
Train steps ... :  51%|█████     | 51062/100000 [15:26:51<7:57:30,  1.71it/s]
Train steps ... :  51%|█████     | 51063/100000 [15:26:52<7:56:52,  1.71it/s]
Train steps ... :  51%|█████     | 51064/100000 [15:26:52<7:57:02,  1.71it/s]
Train steps ... :  51%|█████     | 51065/100000 [15:26:53<7:56:46,  1.71it/s]
Train steps ... :  51%|█████     | 51066/100000 [15:26:53<7:56:41,  1.71it/s]
Train steps ... :  51%|█████     | 51067/100000 [15:26:54<7:56:41,  1.71it/s]
Train steps ... :  51%|█████     | 51068/100000 [15:26:55<7:56:43,  1.71it/s]
Train steps ... :  51%|█████     | 51069/100000 [15:26:55<7:57:33,  1.71it/s]
Train steps ... :  51%|█████     | 51070/100000 [15:26:56<7:57:32,  1.71it/s]
Train steps ... :  51%|█████     | 51071/100000 [15:26:56<7:56:04,  1.71it/s]
Train steps ... :  51%|█████     | 51072/100000 [15:26:57<7:56:51,  1.71it/s]
Train steps ... :  51%|█████     | 51073/100000 [15:26:57<7:58:16,  1.70it/s]
Train steps ... :  51%|█████     | 51074/100000 [15:26:58<7:56:59,  1.71it/s]
Train steps ... :  51%|█████     | 51075/100000 [15:26:59<7:57:29,  1.71it/s]Step... (51075 / 100000 | Loss: 0.7398592233657837, Learning Rate: 4.9170854271356784e-05)
+
                                                                             
Step... (51075 / 100000 | Loss: 0.9138013124465942, Learning Rate: 4.9170854271356784e-05)
+
Train steps ... :  51%|█████     | 51075/100000 [15:26:59<7:57:29,  1.71it/s]
Train steps ... :  51%|█████     | 51076/100000 [15:26:59<7:57:41,  1.71it/s]
Train steps ... :  51%|█████     | 51077/100000 [15:27:00<7:56:42,  1.71it/s]
Train steps ... :  51%|█████     | 51078/100000 [15:27:00<7:57:10,  1.71it/s]
Train steps ... :  51%|█████     | 51079/100000 [15:27:01<7:57:17,  1.71it/s]
Train steps ... :  51%|█████     | 51080/100000 [15:27:02<7:57:11,  1.71it/s]
Train steps ... :  51%|█████     | 51081/100000 [15:27:02<7:56:43,  1.71it/s]
Train steps ... :  51%|█████     | 51082/100000 [15:27:03<7:56:33,  1.71it/s]
Train steps ... :  51%|█████     | 51083/100000 [15:27:03<7:57:02,  1.71it/s]
Train steps ... :  51%|█████     | 51084/100000 [15:27:04<7:56:47,  1.71it/s]
Train steps ... :  51%|█████     | 51085/100000 [15:27:04<7:58:56,  1.70it/s]
Train steps ... :  51%|█████     | 51086/100000 [15:27:05<7:58:07,  1.71it/s]
Train steps ... :  51%|█████     | 51087/100000 [15:27:06<7:57:42,  1.71it/s]
Train steps ... :  51%|█████     | 51088/100000 [15:27:06<7:57:54,  1.71it/s]
Train steps ... :  51%|█████     | 51089/100000 [15:27:07<7:59:20,  1.70it/s]
Train steps ... :  51%|█████     | 51090/100000 [15:27:07<7:58:11,  1.70it/s]
Train steps ... :  51%|█████     | 51091/100000 [15:27:08<7:58:16,  1.70it/s]
Train steps ... :  51%|█████     | 51092/100000 [15:27:09<7:58:14,  1.70it/s]
Train steps ... :  51%|█████     | 51093/100000 [15:27:09<7:57:40,  1.71it/s]
Train steps ... :  51%|█████     | 51094/100000 [15:27:10<7:57:14,  1.71it/s]
Train steps ... :  51%|█████     | 51095/100000 [15:27:10<7:57:05,  1.71it/s]
Train steps ... :  51%|█████     | 51096/100000 [15:27:11<7:57:02,  1.71it/s]
Train steps ... :  51%|█████     | 51097/100000 [15:27:12<7:56:18,  1.71it/s]
Train steps ... :  51%|█████     | 51098/100000 [15:27:12<7:56:33,  1.71it/s]
Train steps ... :  51%|█████     | 51099/100000 [15:27:13<7:56:50,  1.71it/s]
Train steps ... :  51%|█████     | 51100/100000 [15:27:13<7:56:16,  1.71it/s]Step... (51100 / 100000 | Loss: 1.117527723312378, Learning Rate: 4.914572864321608e-05)
+
                                                                             
Step... (51100 / 100000 | Loss: 0.856187105178833, Learning Rate: 4.914572864321608e-05)
+
Train steps ... :  51%|█████     | 51100/100000 [15:27:14<7:56:16,  1.71it/s]
Train steps ... :  51%|█████     | 51101/100000 [15:27:14<7:57:48,  1.71it/s]
Train steps ... :  51%|█████     | 51102/100000 [15:27:14<7:56:09,  1.71it/s]
Train steps ... :  51%|█████     | 51103/100000 [15:27:15<7:57:08,  1.71it/s]
Train steps ... :  51%|█████     | 51104/100000 [15:27:16<7:57:21,  1.71it/s]
Train steps ... :  51%|█████     | 51105/100000 [15:27:16<7:56:37,  1.71it/s]
Train steps ... :  51%|█████     | 51106/100000 [15:27:17<7:56:23,  1.71it/s]
Train steps ... :  51%|█████     | 51107/100000 [15:27:17<7:56:43,  1.71it/s]
Train steps ... :  51%|█████     | 51108/100000 [15:27:18<7:56:50,  1.71it/s]
Train steps ... :  51%|█████     | 51109/100000 [15:27:19<7:57:27,  1.71it/s]
Train steps ... :  51%|█████     | 51110/100000 [15:27:19<7:56:34,  1.71it/s]
Train steps ... :  51%|█████     | 51111/100000 [15:27:20<7:56:56,  1.71it/s]
Train steps ... :  51%|█████     | 51112/100000 [15:27:20<7:56:51,  1.71it/s]
Train steps ... :  51%|█████     | 51113/100000 [15:27:21<7:56:32,  1.71it/s]
Train steps ... :  51%|█████     | 51114/100000 [15:27:21<7:56:08,  1.71it/s]
Train steps ... :  51%|█████     | 51115/100000 [15:27:22<7:56:30,  1.71it/s]
Train steps ... :  51%|█████     | 51116/100000 [15:27:23<7:56:19,  1.71it/s]
Train steps ... :  51%|█████     | 51117/100000 [15:27:23<7:56:11,  1.71it/s]
Train steps ... :  51%|█████     | 51118/100000 [15:27:24<7:56:44,  1.71it/s]
Train steps ... :  51%|█████     | 51119/100000 [15:27:24<7:56:38,  1.71it/s]
Train steps ... :  51%|█████     | 51120/100000 [15:27:25<7:58:00,  1.70it/s]
Train steps ... :  51%|█████     | 51121/100000 [15:27:26<7:56:28,  1.71it/s]
Train steps ... :  51%|█████     | 51122/100000 [15:27:26<7:57:13,  1.71it/s]
Train steps ... :  51%|█████     | 51123/100000 [15:27:27<7:57:07,  1.71it/s]
Train steps ... :  51%|█████     | 51124/100000 [15:27:27<7:57:14,  1.71it/s]
Train steps ... :  51%|█████     | 51125/100000 [15:27:28<7:57:32,  1.71it/s]Step... (51125 / 100000 | Loss: 0.9157470464706421, Learning Rate: 4.912060301507538e-05)
+
                                                                             
Step... (51125 / 100000 | Loss: 0.6925010681152344, Learning Rate: 4.912060301507538e-05)
+
Train steps ... :  51%|█████     | 51125/100000 [15:27:28<7:57:32,  1.71it/s]
Train steps ... :  51%|█████     | 51126/100000 [15:27:28<7:57:11,  1.71it/s]
Train steps ... :  51%|█████     | 51127/100000 [15:27:29<7:57:35,  1.71it/s]
Train steps ... :  51%|█████     | 51128/100000 [15:27:30<7:56:36,  1.71it/s]
Train steps ... :  51%|█████     | 51129/100000 [15:27:30<7:57:18,  1.71it/s]
Train steps ... :  51%|█████     | 51130/100000 [15:27:31<7:57:06,  1.71it/s]
Train steps ... :  51%|█████     | 51131/100000 [15:27:31<7:56:40,  1.71it/s]
Train steps ... :  51%|█████     | 51132/100000 [15:27:32<7:57:25,  1.71it/s]
Train steps ... :  51%|█████     | 51133/100000 [15:27:33<7:56:25,  1.71it/s]
Train steps ... :  51%|█████     | 51134/100000 [15:27:33<7:56:45,  1.71it/s]
Train steps ... :  51%|█████     | 51135/100000 [15:27:34<7:57:11,  1.71it/s]
Train steps ... :  51%|█████     | 51136/100000 [15:27:34<7:56:35,  1.71it/s]
Train steps ... :  51%|█████     | 51137/100000 [15:27:35<7:56:29,  1.71it/s]
Train steps ... :  51%|█████     | 51138/100000 [15:27:36<7:56:31,  1.71it/s]
Train steps ... :  51%|█████     | 51139/100000 [15:27:36<7:57:28,  1.71it/s]
Train steps ... :  51%|█████     | 51140/100000 [15:27:37<7:57:59,  1.70it/s]
Train steps ... :  51%|█████     | 51141/100000 [15:27:37<7:56:59,  1.71it/s]
Train steps ... :  51%|█████     | 51142/100000 [15:27:38<7:57:04,  1.71it/s]
Train steps ... :  51%|█████     | 51143/100000 [15:27:38<7:56:07,  1.71it/s]
Train steps ... :  51%|█████     | 51144/100000 [15:27:39<7:55:53,  1.71it/s]
Train steps ... :  51%|█████     | 51145/100000 [15:27:40<7:55:48,  1.71it/s]
Train steps ... :  51%|█████     | 51146/100000 [15:27:40<7:55:30,  1.71it/s]
Train steps ... :  51%|█████     | 51147/100000 [15:27:41<7:55:52,  1.71it/s]
Train steps ... :  51%|█████     | 51148/100000 [15:27:41<7:55:56,  1.71it/s]
Train steps ... :  51%|█████     | 51149/100000 [15:27:42<7:55:59,  1.71it/s]
Train steps ... :  51%|█████     | 51150/100000 [15:27:43<7:56:13,  1.71it/s]Step... (51150 / 100000 | Loss: 0.7199920415878296, Learning Rate: 4.9095477386934674e-05)
+
                                                                             
Step... (51150 / 100000 | Loss: 0.6816083192825317, Learning Rate: 4.9095477386934674e-05)
+
Train steps ... :  51%|█████     | 51150/100000 [15:27:43<7:56:13,  1.71it/s]
Train steps ... :  51%|█████     | 51151/100000 [15:27:43<7:56:09,  1.71it/s]
Train steps ... :  51%|█████     | 51152/100000 [15:27:44<7:56:26,  1.71it/s]
Train steps ... :  51%|█████     | 51153/100000 [15:27:44<7:57:21,  1.71it/s]
Train steps ... :  51%|█████     | 51154/100000 [15:27:45<7:56:28,  1.71it/s]
Train steps ... :  51%|█████     | 51155/100000 [15:27:45<7:56:37,  1.71it/s]
Train steps ... :  51%|█████     | 51156/100000 [15:27:46<7:56:29,  1.71it/s]
Train steps ... :  51%|█████     | 51157/100000 [15:27:47<7:56:45,  1.71it/s]
Train steps ... :  51%|█████     | 51158/100000 [15:27:47<7:56:17,  1.71it/s]
Train steps ... :  51%|█████     | 51159/100000 [15:27:48<7:56:59,  1.71it/s]
Train steps ... :  51%|█████     | 51160/100000 [15:27:48<7:56:17,  1.71it/s]
Train steps ... :  51%|█████     | 51161/100000 [15:27:49<7:56:57,  1.71it/s]
Train steps ... :  51%|█████     | 51162/100000 [15:27:50<7:57:20,  1.71it/s]
Train steps ... :  51%|█████     | 51163/100000 [15:27:50<7:57:23,  1.70it/s]
Train steps ... :  51%|█████     | 51164/100000 [15:27:51<7:57:31,  1.70it/s]
Train steps ... :  51%|█████     | 51165/100000 [15:27:51<7:57:15,  1.71it/s]
Train steps ... :  51%|█████     | 51166/100000 [15:27:52<7:56:46,  1.71it/s]
Train steps ... :  51%|█████     | 51167/100000 [15:27:52<7:57:02,  1.71it/s]
Train steps ... :  51%|█████     | 51168/100000 [15:27:53<7:57:07,  1.71it/s]
Train steps ... :  51%|█████     | 51169/100000 [15:27:54<7:56:28,  1.71it/s]
Train steps ... :  51%|█████     | 51170/100000 [15:27:54<7:57:46,  1.70it/s]
Train steps ... :  51%|█████     | 51171/100000 [15:27:55<7:56:53,  1.71it/s]
Train steps ... :  51%|█████     | 51172/100000 [15:27:55<7:57:26,  1.70it/s]
Train steps ... :  51%|█████     | 51173/100000 [15:27:56<7:56:39,  1.71it/s]
Train steps ... :  51%|█████     | 51174/100000 [15:27:57<7:57:18,  1.70it/s]
Train steps ... :  51%|█████     | 51175/100000 [15:27:57<7:56:38,  1.71it/s]Step... (51175 / 100000 | Loss: 0.8086338043212891, Learning Rate: 4.907035175879397e-05)
+
                                                                             
Step... (51175 / 100000 | Loss: 0.6256269216537476, Learning Rate: 4.907035175879397e-05)
+
Train steps ... :  51%|█████     | 51175/100000 [15:27:58<7:56:38,  1.71it/s]
Train steps ... :  51%|█████     | 51176/100000 [15:27:58<7:56:20,  1.71it/s]
Train steps ... :  51%|█████     | 51177/100000 [15:27:58<7:56:02,  1.71it/s]
Train steps ... :  51%|█████     | 51178/100000 [15:27:59<7:55:43,  1.71it/s]
Train steps ... :  51%|█████     | 51179/100000 [15:28:00<7:56:14,  1.71it/s]
Train steps ... :  51%|█████     | 51180/100000 [15:28:00<7:56:44,  1.71it/s]
Train steps ... :  51%|█████     | 51181/100000 [15:28:01<7:56:42,  1.71it/s]
Train steps ... :  51%|█████     | 51182/100000 [15:28:01<7:55:53,  1.71it/s]
Train steps ... :  51%|█████     | 51183/100000 [15:28:02<7:56:00,  1.71it/s]
Train steps ... :  51%|█████     | 51184/100000 [15:28:02<7:55:44,  1.71it/s]
Train steps ... :  51%|█████     | 51185/100000 [15:28:03<7:55:24,  1.71it/s]
Train steps ... :  51%|█████     | 51186/100000 [15:28:04<7:55:47,  1.71it/s]
Train steps ... :  51%|█████     | 51187/100000 [15:28:04<7:56:01,  1.71it/s]
Train steps ... :  51%|█████     | 51188/100000 [15:28:05<7:58:45,  1.70it/s]
Train steps ... :  51%|█████     | 51189/100000 [15:28:05<7:57:10,  1.70it/s]
Train steps ... :  51%|█████     | 51190/100000 [15:28:06<7:56:33,  1.71it/s]
Train steps ... :  51%|█████     | 51191/100000 [15:28:07<7:57:22,  1.70it/s]
Train steps ... :  51%|█████     | 51192/100000 [15:28:07<7:55:54,  1.71it/s]
Train steps ... :  51%|█████     | 51193/100000 [15:28:08<7:56:25,  1.71it/s]
Train steps ... :  51%|█████     | 51194/100000 [15:28:08<7:56:10,  1.71it/s]
Train steps ... :  51%|█████     | 51195/100000 [15:28:09<7:55:44,  1.71it/s]
Train steps ... :  51%|█████     | 51196/100000 [15:28:09<7:55:32,  1.71it/s]
Train steps ... :  51%|█████     | 51197/100000 [15:28:10<7:56:29,  1.71it/s]
Train steps ... :  51%|█████     | 51198/100000 [15:28:11<7:55:53,  1.71it/s]
Train steps ... :  51%|█████     | 51199/100000 [15:28:11<7:55:24,  1.71it/s]
Train steps ... :  51%|█████     | 51200/100000 [15:28:12<7:55:45,  1.71it/s]Step... (51200 / 100000 | Loss: 0.9118192195892334, Learning Rate: 4.9045226130653274e-05)
+
                                                                             
Step... (51200 / 100000 | Loss: 0.5236124992370605, Learning Rate: 4.9045226130653274e-05)
+
Train steps ... :  51%|█████     | 51200/100000 [15:28:12<7:55:45,  1.71it/s]
Train steps ... :  51%|█████     | 51201/100000 [15:28:12<7:55:54,  1.71it/s]
Train steps ... :  51%|█████     | 51202/100000 [15:28:13<7:55:59,  1.71it/s]
Train steps ... :  51%|█████     | 51203/100000 [15:28:14<7:56:07,  1.71it/s]
Train steps ... :  51%|█████     | 51204/100000 [15:28:14<7:56:15,  1.71it/s]
Train steps ... :  51%|█████     | 51205/100000 [15:28:15<7:55:44,  1.71it/s]
Train steps ... :  51%|█████     | 51206/100000 [15:28:15<7:55:55,  1.71it/s]
Train steps ... :  51%|█████     | 51207/100000 [15:28:16<7:55:14,  1.71it/s]
Train steps ... :  51%|█████     | 51208/100000 [15:28:16<7:55:51,  1.71it/s]
Train steps ... :  51%|█████     | 51209/100000 [15:28:17<7:56:14,  1.71it/s]
Train steps ... :  51%|█████     | 51210/100000 [15:28:18<7:57:39,  1.70it/s]
Train steps ... :  51%|█████     | 51211/100000 [15:28:18<7:56:16,  1.71it/s]
Train steps ... :  51%|█████     | 51212/100000 [15:28:19<7:56:10,  1.71it/s]
Train steps ... :  51%|█████     | 51213/100000 [15:28:19<7:56:23,  1.71it/s]
Train steps ... :  51%|█████     | 51214/100000 [15:28:20<7:56:01,  1.71it/s]
Train steps ... :  51%|█████     | 51215/100000 [15:28:21<7:55:38,  1.71it/s]
Train steps ... :  51%|█████     | 51216/100000 [15:28:21<7:56:18,  1.71it/s]
Train steps ... :  51%|█████     | 51217/100000 [15:28:22<7:56:08,  1.71it/s]
Train steps ... :  51%|█████     | 51218/100000 [15:28:22<7:55:54,  1.71it/s]
Train steps ... :  51%|█████     | 51219/100000 [15:28:23<7:56:16,  1.71it/s]
Train steps ... :  51%|█████     | 51220/100000 [15:28:24<7:56:08,  1.71it/s]
Train steps ... :  51%|█████     | 51221/100000 [15:28:24<7:56:27,  1.71it/s]
Train steps ... :  51%|█████     | 51222/100000 [15:28:25<7:55:43,  1.71it/s]
Train steps ... :  51%|█████     | 51223/100000 [15:28:25<7:56:11,  1.71it/s]
Train steps ... :  51%|█████     | 51224/100000 [15:28:26<7:55:30,  1.71it/s]
Train steps ... :  51%|█████     | 51225/100000 [15:28:26<7:55:53,  1.71it/s]Step... (51225 / 100000 | Loss: 0.9544655680656433, Learning Rate: 4.9020100502512564e-05)
+
                                                                             
Step... (51225 / 100000 | Loss: 1.2022877931594849, Learning Rate: 4.9020100502512564e-05)
+
Train steps ... :  51%|█████     | 51225/100000 [15:28:27<7:55:53,  1.71it/s]
Train steps ... :  51%|█████     | 51226/100000 [15:28:27<7:55:59,  1.71it/s]
Train steps ... :  51%|█████     | 51227/100000 [15:28:28<7:54:50,  1.71it/s]
Train steps ... :  51%|█████     | 51228/100000 [15:28:28<7:54:52,  1.71it/s]
Train steps ... :  51%|█████     | 51229/100000 [15:28:29<7:56:34,  1.71it/s]
Train steps ... :  51%|█████     | 51230/100000 [15:28:29<7:56:53,  1.70it/s]
Train steps ... :  51%|█████     | 51231/100000 [15:28:30<7:55:05,  1.71it/s]
Train steps ... :  51%|█████     | 51232/100000 [15:28:31<7:54:46,  1.71it/s]
Train steps ... :  51%|█████     | 51233/100000 [15:28:31<7:54:30,  1.71it/s]
Train steps ... :  51%|█████     | 51234/100000 [15:28:32<7:55:06,  1.71it/s]
Train steps ... :  51%|█████     | 51235/100000 [15:28:32<7:55:14,  1.71it/s]
Train steps ... :  51%|█████     | 51236/100000 [15:28:33<7:56:40,  1.70it/s]
Train steps ... :  51%|█████     | 51237/100000 [15:28:33<7:55:09,  1.71it/s]
Train steps ... :  51%|█████     | 51238/100000 [15:28:34<7:55:32,  1.71it/s]
Train steps ... :  51%|█████     | 51239/100000 [15:28:35<7:55:35,  1.71it/s]
Train steps ... :  51%|█████     | 51240/100000 [15:28:35<7:55:26,  1.71it/s]
Train steps ... :  51%|█████     | 51241/100000 [15:28:36<7:55:50,  1.71it/s]
Train steps ... :  51%|█████     | 51242/100000 [15:28:36<7:56:00,  1.71it/s]
Train steps ... :  51%|█████     | 51243/100000 [15:28:37<7:55:32,  1.71it/s]
Train steps ... :  51%|█████     | 51244/100000 [15:28:38<7:55:58,  1.71it/s]
Train steps ... :  51%|█████     | 51245/100000 [15:28:38<7:55:25,  1.71it/s]
Train steps ... :  51%|█████     | 51246/100000 [15:28:39<7:54:43,  1.71it/s]
Train steps ... :  51%|█████     | 51247/100000 [15:28:39<7:55:11,  1.71it/s]
Train steps ... :  51%|█████     | 51248/100000 [15:28:40<7:55:07,  1.71it/s]
Train steps ... :  51%|█████     | 51249/100000 [15:28:40<7:54:50,  1.71it/s]
Train steps ... :  51%|█████▏    | 51250/100000 [15:28:41<7:55:14,  1.71it/s]Step... (51250 / 100000 | Loss: 0.7136038541793823, Learning Rate: 4.899497487437186e-05)
+
                                                                             
Step... (51250 / 100000 | Loss: 0.6775742769241333, Learning Rate: 4.899497487437186e-05)
+
Train steps ... :  51%|█████▏    | 51250/100000 [15:28:41<7:55:14,  1.71it/s]
Train steps ... :  51%|█████▏    | 51251/100000 [15:28:42<7:55:10,  1.71it/s]
Train steps ... :  51%|█████▏    | 51252/100000 [15:28:42<7:54:47,  1.71it/s]
Train steps ... :  51%|█████▏    | 51253/100000 [15:28:43<7:54:18,  1.71it/s]
Train steps ... :  51%|█████▏    | 51254/100000 [15:28:43<7:54:23,  1.71it/s]
Train steps ... :  51%|█████▏    | 51255/100000 [15:28:44<7:54:07,  1.71it/s]
Train steps ... :  51%|█████▏    | 51256/100000 [15:28:45<7:54:20,  1.71it/s]
Train steps ... :  51%|█████▏    | 51257/100000 [15:28:45<7:54:54,  1.71it/s]
Train steps ... :  51%|█████▏    | 51258/100000 [15:28:46<7:54:55,  1.71it/s]
Train steps ... :  51%|█████▏    | 51259/100000 [15:28:46<7:54:16,  1.71it/s]
Train steps ... :  51%|█████▏    | 51260/100000 [15:28:47<7:54:09,  1.71it/s]
Train steps ... :  51%|█████▏    | 51261/100000 [15:28:47<7:54:59,  1.71it/s]
Train steps ... :  51%|█████▏    | 51262/100000 [15:28:48<7:54:13,  1.71it/s]
Train steps ... :  51%|█████▏    | 51263/100000 [15:28:49<7:54:16,  1.71it/s]
Train steps ... :  51%|█████▏    | 51264/100000 [15:28:49<7:54:00,  1.71it/s]
Train steps ... :  51%|█████▏    | 51265/100000 [15:28:50<7:54:36,  1.71it/s]
Train steps ... :  51%|█████▏    | 51266/100000 [15:28:50<7:54:14,  1.71it/s]
Train steps ... :  51%|█████▏    | 51267/100000 [15:28:51<7:54:12,  1.71it/s]
Train steps ... :  51%|█████▏    | 51268/100000 [15:28:52<7:54:32,  1.71it/s]
Train steps ... :  51%|█████▏    | 51269/100000 [15:28:52<7:54:48,  1.71it/s]
Train steps ... :  51%|█████▏    | 51270/100000 [15:28:53<9:43:32,  1.39it/s]
Train steps ... :  51%|█████▏    | 51271/100000 [15:28:57<20:54:57,  1.55s/it]
Train steps ... :  51%|█████▏    | 51272/100000 [15:28:58<18:04:42,  1.34s/it]
Train steps ... :  51%|█████▏    | 51273/100000 [15:28:58<15:01:56,  1.11s/it]
Train steps ... :  51%|█████▏    | 51274/100000 [15:28:59<12:54:23,  1.05it/s]
Train steps ... :  51%|█████▏    | 51275/100000 [15:28:59<11:24:03,  1.19it/s]Step... (51275 / 100000 | Loss: 0.7342524528503418, Learning Rate: 4.896984924623116e-05)
+
                                                                              
Step... (51275 / 100000 | Loss: 0.5469158887863159, Learning Rate: 4.896984924623116e-05)
+
Train steps ... :  51%|█████▏    | 51275/100000 [15:29:00<11:24:03,  1.19it/s]
Train steps ... :  51%|█████▏    | 51276/100000 [15:29:00<10:22:23,  1.30it/s]
Train steps ... :  51%|█████▏    | 51277/100000 [15:29:00<9:37:53,  1.41it/s] 
Train steps ... :  51%|█████▏    | 51278/100000 [15:29:01<9:06:43,  1.49it/s]
Train steps ... :  51%|█████▏    | 51279/100000 [15:29:02<8:44:49,  1.55it/s]
Train steps ... :  51%|█████▏    | 51280/100000 [15:29:02<8:29:36,  1.59it/s]
Train steps ... :  51%|█████▏    | 51281/100000 [15:29:03<8:18:51,  1.63it/s]
Train steps ... :  51%|█████▏    | 51282/100000 [15:29:03<8:12:33,  1.65it/s]
Train steps ... :  51%|█████▏    | 51283/100000 [15:29:04<8:07:28,  1.67it/s]
Train steps ... :  51%|█████▏    | 51284/100000 [15:29:05<8:03:14,  1.68it/s]
Train steps ... :  51%|█████▏    | 51285/100000 [15:29:05<8:00:26,  1.69it/s]
Train steps ... :  51%|█████▏    | 51286/100000 [15:29:06<7:59:25,  1.69it/s]
Train steps ... :  51%|█████▏    | 51287/100000 [15:29:06<7:57:45,  1.70it/s]
Train steps ... :  51%|█████▏    | 51288/100000 [15:29:07<7:56:21,  1.70it/s]
Train steps ... :  51%|█████▏    | 51289/100000 [15:29:07<7:55:19,  1.71it/s]
Train steps ... :  51%|█████▏    | 51290/100000 [15:29:08<7:55:01,  1.71it/s]
Train steps ... :  51%|█████▏    | 51291/100000 [15:29:09<7:54:25,  1.71it/s]
Train steps ... :  51%|█████▏    | 51292/100000 [15:29:09<7:54:43,  1.71it/s]
Train steps ... :  51%|█████▏    | 51293/100000 [15:29:10<7:54:44,  1.71it/s]
Train steps ... :  51%|█████▏    | 51294/100000 [15:29:10<7:54:21,  1.71it/s]
Train steps ... :  51%|█████▏    | 51295/100000 [15:29:11<7:54:15,  1.71it/s]
Train steps ... :  51%|█████▏    | 51296/100000 [15:29:12<7:54:06,  1.71it/s]
Train steps ... :  51%|█████▏    | 51297/100000 [15:29:12<7:54:19,  1.71it/s]
Train steps ... :  51%|█████▏    | 51298/100000 [15:29:13<7:54:14,  1.71it/s]
Train steps ... :  51%|█████▏    | 51299/100000 [15:29:13<7:54:12,  1.71it/s]
Train steps ... :  51%|█████▏    | 51300/100000 [15:29:14<7:54:03,  1.71it/s]Step... (51300 / 100000 | Loss: 0.772553563117981, Learning Rate: 4.8944723618090454e-05)
+
                                                                             
Step... (51300 / 100000 | Loss: 0.6654553413391113, Learning Rate: 4.8944723618090454e-05)
+
Train steps ... :  51%|█████▏    | 51300/100000 [15:29:14<7:54:03,  1.71it/s]
Train steps ... :  51%|█████▏    | 51301/100000 [15:29:14<7:54:18,  1.71it/s]
Train steps ... :  51%|█████▏    | 51302/100000 [15:29:15<7:54:13,  1.71it/s]
Train steps ... :  51%|█████▏    | 51303/100000 [15:29:16<7:54:13,  1.71it/s]
Train steps ... :  51%|█████▏    | 51304/100000 [15:29:16<7:53:58,  1.71it/s]
Train steps ... :  51%|█████▏    | 51305/100000 [15:29:17<7:54:28,  1.71it/s]
Train steps ... :  51%|█████▏    | 51306/100000 [15:29:17<7:54:10,  1.71it/s]
Train steps ... :  51%|█████▏    | 51307/100000 [15:29:18<7:54:06,  1.71it/s]
Train steps ... :  51%|█████▏    | 51308/100000 [15:29:19<7:53:45,  1.71it/s]
Train steps ... :  51%|█████▏    | 51309/100000 [15:29:19<7:54:20,  1.71it/s]
Train steps ... :  51%|█████▏    | 51310/100000 [15:29:20<7:54:44,  1.71it/s]
Train steps ... :  51%|█████▏    | 51311/100000 [15:29:20<7:54:39,  1.71it/s]
Train steps ... :  51%|█████▏    | 51312/100000 [15:29:21<7:54:20,  1.71it/s]
Train steps ... :  51%|█████▏    | 51313/100000 [15:29:21<7:54:14,  1.71it/s]
Train steps ... :  51%|█████▏    | 51314/100000 [15:29:22<7:53:46,  1.71it/s]
Train steps ... :  51%|█████▏    | 51315/100000 [15:29:23<7:54:18,  1.71it/s]
Train steps ... :  51%|█████▏    | 51316/100000 [15:29:23<7:54:02,  1.71it/s]
Train steps ... :  51%|█████▏    | 51317/100000 [15:29:24<7:53:50,  1.71it/s]
Train steps ... :  51%|█████▏    | 51318/100000 [15:29:24<7:54:26,  1.71it/s]
Train steps ... :  51%|█████▏    | 51319/100000 [15:29:25<7:54:16,  1.71it/s]
Train steps ... :  51%|█████▏    | 51320/100000 [15:29:26<7:53:54,  1.71it/s]
Train steps ... :  51%|█████▏    | 51321/100000 [15:29:26<7:53:46,  1.71it/s]
Train steps ... :  51%|█████▏    | 51322/100000 [15:29:27<7:53:49,  1.71it/s]
Train steps ... :  51%|█████▏    | 51323/100000 [15:29:27<7:54:04,  1.71it/s]
Train steps ... :  51%|█████▏    | 51324/100000 [15:29:28<7:53:57,  1.71it/s]
Train steps ... :  51%|█████▏    | 51325/100000 [15:29:28<7:53:35,  1.71it/s]Step... (51325 / 100000 | Loss: 1.0827362537384033, Learning Rate: 4.891959798994975e-05)
+
                                                                             
Step... (51325 / 100000 | Loss: 0.7334262132644653, Learning Rate: 4.891959798994975e-05)
+
Train steps ... :  51%|█████▏    | 51325/100000 [15:29:29<7:53:35,  1.71it/s]
Train steps ... :  51%|█████▏    | 51326/100000 [15:29:29<7:54:41,  1.71it/s]
Train steps ... :  51%|█████▏    | 51327/100000 [15:29:30<7:53:54,  1.71it/s]
Train steps ... :  51%|█████▏    | 51328/100000 [15:29:30<7:54:04,  1.71it/s]
Train steps ... :  51%|█████▏    | 51329/100000 [15:29:31<7:54:00,  1.71it/s]
Train steps ... :  51%|█████▏    | 51330/100000 [15:29:31<7:54:29,  1.71it/s]
Train steps ... :  51%|█████▏    | 51331/100000 [15:29:32<7:54:12,  1.71it/s]
Train steps ... :  51%|█████▏    | 51332/100000 [15:29:33<7:54:37,  1.71it/s]
Train steps ... :  51%|█████▏    | 51333/100000 [15:29:33<7:54:45,  1.71it/s]
Train steps ... :  51%|█████▏    | 51334/100000 [15:29:34<7:55:02,  1.71it/s]
Train steps ... :  51%|█████▏    | 51335/100000 [15:29:34<7:54:54,  1.71it/s]
Train steps ... :  51%|█████▏    | 51336/100000 [15:29:35<7:54:23,  1.71it/s]
Train steps ... :  51%|█████▏    | 51337/100000 [15:29:36<7:54:09,  1.71it/s]
Train steps ... :  51%|█████▏    | 51338/100000 [15:29:36<7:53:55,  1.71it/s]
Train steps ... :  51%|█████▏    | 51339/100000 [15:29:37<7:53:45,  1.71it/s]
Train steps ... :  51%|█████▏    | 51340/100000 [15:29:37<7:54:31,  1.71it/s]
Train steps ... :  51%|█████▏    | 51341/100000 [15:29:38<7:53:47,  1.71it/s]
Train steps ... :  51%|█████▏    | 51342/100000 [15:29:38<7:53:35,  1.71it/s]
Train steps ... :  51%|█████▏    | 51343/100000 [15:29:39<7:53:41,  1.71it/s]
Train steps ... :  51%|█████▏    | 51344/100000 [15:29:40<7:53:25,  1.71it/s]
Train steps ... :  51%|█████▏    | 51345/100000 [15:29:40<7:53:27,  1.71it/s]
Train steps ... :  51%|█████▏    | 51346/100000 [15:29:41<7:53:23,  1.71it/s]
Train steps ... :  51%|█████▏    | 51347/100000 [15:29:41<7:53:34,  1.71it/s]
Train steps ... :  51%|█████▏    | 51348/100000 [15:29:42<7:54:14,  1.71it/s]
Train steps ... :  51%|█████▏    | 51349/100000 [15:29:43<7:54:25,  1.71it/s]
Train steps ... :  51%|█████▏    | 51350/100000 [15:29:43<7:53:49,  1.71it/s]Step... (51350 / 100000 | Loss: 0.7102869749069214, Learning Rate: 4.889447236180905e-05)
+
                                                                             
Step... (51350 / 100000 | Loss: 0.6528253555297852, Learning Rate: 4.889447236180905e-05)
+
Train steps ... :  51%|█████▏    | 51350/100000 [15:29:43<7:53:49,  1.71it/s]
Train steps ... :  51%|█████▏    | 51351/100000 [15:29:44<7:54:03,  1.71it/s]
Train steps ... :  51%|█████▏    | 51352/100000 [15:29:44<7:53:36,  1.71it/s]
Train steps ... :  51%|█████▏    | 51353/100000 [15:29:45<7:53:58,  1.71it/s]
Train steps ... :  51%|█████▏    | 51354/100000 [15:29:45<7:53:45,  1.71it/s]
Train steps ... :  51%|█████▏    | 51355/100000 [15:29:46<7:54:15,  1.71it/s]
Train steps ... :  51%|█████▏    | 51356/100000 [15:29:47<7:54:17,  1.71it/s]
Train steps ... :  51%|█████▏    | 51357/100000 [15:29:47<7:53:51,  1.71it/s]
Train steps ... :  51%|█████▏    | 51358/100000 [15:29:48<7:54:42,  1.71it/s]
Train steps ... :  51%|█████▏    | 51359/100000 [15:29:48<7:53:55,  1.71it/s]
Train steps ... :  51%|█████▏    | 51360/100000 [15:29:49<7:53:34,  1.71it/s]
Train steps ... :  51%|█████▏    | 51361/100000 [15:29:50<7:53:25,  1.71it/s]
Train steps ... :  51%|█████▏    | 51362/100000 [15:29:50<7:53:38,  1.71it/s]
Train steps ... :  51%|█████▏    | 51363/100000 [15:29:51<7:54:16,  1.71it/s]
Train steps ... :  51%|█████▏    | 51364/100000 [15:29:51<7:54:03,  1.71it/s]
Train steps ... :  51%|█████▏    | 51365/100000 [15:29:52<7:53:49,  1.71it/s]
Train steps ... :  51%|█████▏    | 51366/100000 [15:29:52<7:53:55,  1.71it/s]
Train steps ... :  51%|█████▏    | 51367/100000 [15:29:53<7:53:31,  1.71it/s]
Train steps ... :  51%|█████▏    | 51368/100000 [15:29:54<7:53:40,  1.71it/s]
Train steps ... :  51%|█████▏    | 51369/100000 [15:29:54<7:53:43,  1.71it/s]
Train steps ... :  51%|█████▏    | 51370/100000 [15:29:55<7:53:46,  1.71it/s]
Train steps ... :  51%|█████▏    | 51371/100000 [15:29:55<7:53:35,  1.71it/s]
Train steps ... :  51%|█████▏    | 51372/100000 [15:29:56<7:53:23,  1.71it/s]
Train steps ... :  51%|█████▏    | 51373/100000 [15:29:57<7:53:08,  1.71it/s]
Train steps ... :  51%|█████▏    | 51374/100000 [15:29:57<7:53:10,  1.71it/s]
Train steps ... :  51%|█████▏    | 51375/100000 [15:29:58<7:53:26,  1.71it/s]Step... (51375 / 100000 | Loss: 0.8760834336280823, Learning Rate: 4.8869346733668344e-05)
+
                                                                             
Step... (51375 / 100000 | Loss: 0.6818380951881409, Learning Rate: 4.8869346733668344e-05)
+
Train steps ... :  51%|█████▏    | 51375/100000 [15:29:58<7:53:26,  1.71it/s]
Train steps ... :  51%|█████▏    | 51376/100000 [15:29:58<7:54:23,  1.71it/s]
Train steps ... :  51%|█████▏    | 51377/100000 [15:29:59<7:54:08,  1.71it/s]
Train steps ... :  51%|█████▏    | 51378/100000 [15:29:59<7:53:54,  1.71it/s]
Train steps ... :  51%|█████▏    | 51379/100000 [15:30:00<7:53:31,  1.71it/s]
Train steps ... :  51%|█████▏    | 51380/100000 [15:30:01<7:54:12,  1.71it/s]
Train steps ... :  51%|█████▏    | 51381/100000 [15:30:01<7:54:19,  1.71it/s]
Train steps ... :  51%|█████▏    | 51382/100000 [15:30:02<7:53:55,  1.71it/s]
Train steps ... :  51%|█████▏    | 51383/100000 [15:30:02<7:53:30,  1.71it/s]
Train steps ... :  51%|█████▏    | 51384/100000 [15:30:03<7:53:26,  1.71it/s]
Train steps ... :  51%|█████▏    | 51385/100000 [15:30:04<7:53:21,  1.71it/s]
Train steps ... :  51%|█████▏    | 51386/100000 [15:30:04<7:53:17,  1.71it/s]
Train steps ... :  51%|█████▏    | 51387/100000 [15:30:05<7:53:23,  1.71it/s]
Train steps ... :  51%|█████▏    | 51388/100000 [15:30:05<7:53:48,  1.71it/s]
Train steps ... :  51%|█████▏    | 51389/100000 [15:30:06<7:54:04,  1.71it/s]
Train steps ... :  51%|█████▏    | 51390/100000 [15:30:06<7:53:41,  1.71it/s]
Train steps ... :  51%|█████▏    | 51391/100000 [15:30:07<7:53:27,  1.71it/s]
Train steps ... :  51%|█████▏    | 51392/100000 [15:30:08<7:53:23,  1.71it/s]
Train steps ... :  51%|█████▏    | 51393/100000 [15:30:08<7:53:00,  1.71it/s]
Train steps ... :  51%|█████▏    | 51394/100000 [15:30:09<7:53:16,  1.71it/s]
Train steps ... :  51%|█████▏    | 51395/100000 [15:30:09<7:53:28,  1.71it/s]
Train steps ... :  51%|█████▏    | 51396/100000 [15:30:10<7:53:04,  1.71it/s]
Train steps ... :  51%|█████▏    | 51397/100000 [15:30:11<7:53:07,  1.71it/s]
Train steps ... :  51%|█████▏    | 51398/100000 [15:30:11<7:53:11,  1.71it/s]
Train steps ... :  51%|█████▏    | 51399/100000 [15:30:12<7:53:00,  1.71it/s]
Train steps ... :  51%|█████▏    | 51400/100000 [15:30:12<7:52:52,  1.71it/s]Step... (51400 / 100000 | Loss: 0.5738080739974976, Learning Rate: 4.884422110552764e-05)
+
                                                                             
Step... (51400 / 100000 | Loss: 0.7431921362876892, Learning Rate: 4.884422110552764e-05)
+
Train steps ... :  51%|█████▏    | 51400/100000 [15:30:13<7:52:52,  1.71it/s]
Train steps ... :  51%|█████▏    | 51401/100000 [15:30:13<7:52:57,  1.71it/s]
Train steps ... :  51%|█████▏    | 51402/100000 [15:30:13<7:53:14,  1.71it/s]
Train steps ... :  51%|█████▏    | 51403/100000 [15:30:14<7:53:30,  1.71it/s]
Train steps ... :  51%|█████▏    | 51404/100000 [15:30:15<7:53:17,  1.71it/s]
Train steps ... :  51%|█████▏    | 51405/100000 [15:30:15<7:53:22,  1.71it/s]
Train steps ... :  51%|█████▏    | 51406/100000 [15:30:16<7:53:52,  1.71it/s]
Train steps ... :  51%|█████▏    | 51407/100000 [15:30:16<7:53:36,  1.71it/s]
Train steps ... :  51%|█████▏    | 51408/100000 [15:30:17<7:53:08,  1.71it/s]
Train steps ... :  51%|█████▏    | 51409/100000 [15:30:18<7:53:16,  1.71it/s]
Train steps ... :  51%|█████▏    | 51410/100000 [15:30:18<7:53:22,  1.71it/s]
Train steps ... :  51%|█████▏    | 51411/100000 [15:30:19<7:53:40,  1.71it/s]
Train steps ... :  51%|█████▏    | 51412/100000 [15:30:19<7:54:21,  1.71it/s]
Train steps ... :  51%|█████▏    | 51413/100000 [15:30:20<7:53:49,  1.71it/s]
Train steps ... :  51%|█████▏    | 51414/100000 [15:30:21<7:53:45,  1.71it/s]
Train steps ... :  51%|█████▏    | 51415/100000 [15:30:21<7:53:41,  1.71it/s]
Train steps ... :  51%|█████▏    | 51416/100000 [15:30:22<7:53:22,  1.71it/s]
Train steps ... :  51%|█████▏    | 51417/100000 [15:30:22<7:54:11,  1.71it/s]
Train steps ... :  51%|█████▏    | 51418/100000 [15:30:23<7:53:52,  1.71it/s]
Train steps ... :  51%|█████▏    | 51419/100000 [15:30:23<7:53:16,  1.71it/s]
Train steps ... :  51%|█████▏    | 51420/100000 [15:30:24<7:53:44,  1.71it/s]
Train steps ... :  51%|█████▏    | 51421/100000 [15:30:25<7:53:53,  1.71it/s]
Train steps ... :  51%|█████▏    | 51422/100000 [15:30:25<7:53:37,  1.71it/s]
Train steps ... :  51%|█████▏    | 51423/100000 [15:30:26<7:54:03,  1.71it/s]
Train steps ... :  51%|█████▏    | 51424/100000 [15:30:26<7:53:41,  1.71it/s]
Train steps ... :  51%|█████▏    | 51425/100000 [15:30:27<7:53:23,  1.71it/s]Step... (51425 / 100000 | Loss: 1.0450289249420166, Learning Rate: 4.881909547738694e-05)
+
                                                                             
Step... (51425 / 100000 | Loss: 0.6649742722511292, Learning Rate: 4.881909547738694e-05)
+
Train steps ... :  51%|█████▏    | 51425/100000 [15:30:27<7:53:23,  1.71it/s]
Train steps ... :  51%|█████▏    | 51426/100000 [15:30:28<7:53:39,  1.71it/s]
Train steps ... :  51%|█████▏    | 51427/100000 [15:30:28<7:53:21,  1.71it/s]
Train steps ... :  51%|█████▏    | 51428/100000 [15:30:29<7:53:04,  1.71it/s]
Train steps ... :  51%|█████▏    | 51429/100000 [15:30:29<7:52:51,  1.71it/s]
Train steps ... :  51%|█████▏    | 51430/100000 [15:30:30<7:53:16,  1.71it/s]
Train steps ... :  51%|█████▏    | 51431/100000 [15:30:30<7:52:57,  1.71it/s]
Train steps ... :  51%|█████▏    | 51432/100000 [15:30:31<7:52:43,  1.71it/s]
Train steps ... :  51%|█████▏    | 51433/100000 [15:30:32<7:53:05,  1.71it/s]
Train steps ... :  51%|█████▏    | 51434/100000 [15:30:32<7:53:00,  1.71it/s]
Train steps ... :  51%|█████▏    | 51435/100000 [15:30:33<7:52:35,  1.71it/s]
Train steps ... :  51%|█████▏    | 51436/100000 [15:30:33<7:52:33,  1.71it/s]
Train steps ... :  51%|█████▏    | 51437/100000 [15:30:34<7:52:37,  1.71it/s]
Train steps ... :  51%|█████▏    | 51438/100000 [15:30:35<7:53:00,  1.71it/s]
Train steps ... :  51%|█████▏    | 51439/100000 [15:30:35<7:53:05,  1.71it/s]
Train steps ... :  51%|█████▏    | 51440/100000 [15:30:36<7:53:26,  1.71it/s]
Train steps ... :  51%|█████▏    | 51441/100000 [15:30:36<7:53:27,  1.71it/s]
Train steps ... :  51%|█████▏    | 51442/100000 [15:30:37<7:53:21,  1.71it/s]
Train steps ... :  51%|█████▏    | 51443/100000 [15:30:37<7:53:07,  1.71it/s]
Train steps ... :  51%|█████▏    | 51444/100000 [15:30:38<7:53:15,  1.71it/s]
Train steps ... :  51%|█████▏    | 51445/100000 [15:30:39<7:53:23,  1.71it/s]
Train steps ... :  51%|█████▏    | 51446/100000 [15:30:39<7:53:19,  1.71it/s]
Train steps ... :  51%|█████▏    | 51447/100000 [15:30:40<7:53:00,  1.71it/s]
Train steps ... :  51%|█████▏    | 51448/100000 [15:30:40<7:53:15,  1.71it/s]
Train steps ... :  51%|█████▏    | 51449/100000 [15:30:41<7:53:38,  1.71it/s]
Train steps ... :  51%|█████▏    | 51450/100000 [15:30:42<7:53:41,  1.71it/s]Step... (51450 / 100000 | Loss: 0.9521728754043579, Learning Rate: 4.8793969849246233e-05)
+
                                                                             
Step... (51450 / 100000 | Loss: 0.6734664440155029, Learning Rate: 4.8793969849246233e-05)
+
Train steps ... :  51%|█████▏    | 51450/100000 [15:30:42<7:53:41,  1.71it/s]
Train steps ... :  51%|█████▏    | 51451/100000 [15:30:42<7:53:16,  1.71it/s]
Train steps ... :  51%|█████▏    | 51452/100000 [15:30:43<7:53:08,  1.71it/s]
Train steps ... :  51%|█████▏    | 51453/100000 [15:30:43<7:53:31,  1.71it/s]
Train steps ... :  51%|█████▏    | 51454/100000 [15:30:44<7:53:08,  1.71it/s]
Train steps ... :  51%|█████▏    | 51455/100000 [15:30:44<7:52:52,  1.71it/s]
Train steps ... :  51%|█████▏    | 51456/100000 [15:30:45<7:52:43,  1.71it/s]
Train steps ... :  51%|█████▏    | 51457/100000 [15:30:46<7:52:30,  1.71it/s]
Train steps ... :  51%|█████▏    | 51458/100000 [15:30:46<7:53:01,  1.71it/s]
Train steps ... :  51%|█████▏    | 51459/100000 [15:30:47<7:52:43,  1.71it/s]
Train steps ... :  51%|█████▏    | 51460/100000 [15:30:47<7:53:19,  1.71it/s]
Train steps ... :  51%|█████▏    | 51461/100000 [15:30:48<7:54:01,  1.71it/s]
Train steps ... :  51%|█████▏    | 51462/100000 [15:30:49<7:53:31,  1.71it/s]
Train steps ... :  51%|█████▏    | 51463/100000 [15:30:49<7:53:55,  1.71it/s]
Train steps ... :  51%|█████▏    | 51464/100000 [15:30:50<7:53:51,  1.71it/s]
Train steps ... :  51%|█████▏    | 51465/100000 [15:30:50<7:53:14,  1.71it/s]
Train steps ... :  51%|█████▏    | 51466/100000 [15:30:51<7:53:09,  1.71it/s]
Train steps ... :  51%|█████▏    | 51467/100000 [15:30:52<7:53:11,  1.71it/s]
Train steps ... :  51%|█████▏    | 51468/100000 [15:30:52<7:52:51,  1.71it/s]
Train steps ... :  51%|█████▏    | 51469/100000 [15:30:53<7:53:09,  1.71it/s]
Train steps ... :  51%|█████▏    | 51470/100000 [15:30:53<7:52:52,  1.71it/s]
Train steps ... :  51%|█████▏    | 51471/100000 [15:30:54<7:53:14,  1.71it/s]
Train steps ... :  51%|█████▏    | 51472/100000 [15:30:54<7:53:07,  1.71it/s]
Train steps ... :  51%|█████▏    | 51473/100000 [15:30:55<7:53:29,  1.71it/s]
Train steps ... :  51%|█████▏    | 51474/100000 [15:30:56<7:52:53,  1.71it/s]
Train steps ... :  51%|█████▏    | 51475/100000 [15:30:56<7:53:28,  1.71it/s]Step... (51475 / 100000 | Loss: 0.8352031707763672, Learning Rate: 4.876884422110553e-05)
+
                                                                             
Step... (51475 / 100000 | Loss: 0.9919711351394653, Learning Rate: 4.876884422110553e-05)
+
Train steps ... :  51%|█████▏    | 51475/100000 [15:30:57<7:53:28,  1.71it/s]
Train steps ... :  51%|█████▏    | 51476/100000 [15:30:57<7:53:04,  1.71it/s]
Train steps ... :  51%|█████▏    | 51477/100000 [15:30:57<7:53:08,  1.71it/s]
Train steps ... :  51%|█████▏    | 51478/100000 [15:30:58<7:53:25,  1.71it/s]
Train steps ... :  51%|█████▏    | 51479/100000 [15:30:59<7:52:59,  1.71it/s]
Train steps ... :  51%|█████▏    | 51480/100000 [15:30:59<7:52:47,  1.71it/s]
Train steps ... :  51%|█████▏    | 51481/100000 [15:31:00<7:52:41,  1.71it/s]
Train steps ... :  51%|█████▏    | 51482/100000 [15:31:00<7:52:47,  1.71it/s]
Train steps ... :  51%|█████▏    | 51483/100000 [15:31:01<7:52:46,  1.71it/s]
Train steps ... :  51%|█████▏    | 51484/100000 [15:31:01<7:52:47,  1.71it/s]
Train steps ... :  51%|█████▏    | 51485/100000 [15:31:02<7:53:58,  1.71it/s]
Train steps ... :  51%|█████▏    | 51486/100000 [15:31:03<7:52:18,  1.71it/s]
Train steps ... :  51%|█████▏    | 51487/100000 [15:31:03<7:52:22,  1.71it/s]
Train steps ... :  51%|█████▏    | 51488/100000 [15:31:04<7:52:07,  1.71it/s]
Train steps ... :  51%|█████▏    | 51489/100000 [15:31:04<7:52:19,  1.71it/s]
Train steps ... :  51%|█████▏    | 51490/100000 [15:31:05<7:52:18,  1.71it/s]
Train steps ... :  51%|█████▏    | 51491/100000 [15:31:06<7:52:20,  1.71it/s]
Train steps ... :  51%|█████▏    | 51492/100000 [15:31:06<7:52:37,  1.71it/s]
Train steps ... :  51%|█████▏    | 51493/100000 [15:31:07<7:52:47,  1.71it/s]
Train steps ... :  51%|█████▏    | 51494/100000 [15:31:07<7:53:10,  1.71it/s]
Train steps ... :  51%|█████▏    | 51495/100000 [15:31:08<7:53:35,  1.71it/s]
Train steps ... :  51%|█████▏    | 51496/100000 [15:31:08<7:53:13,  1.71it/s]
Train steps ... :  51%|█████▏    | 51497/100000 [15:31:09<7:53:13,  1.71it/s]
Train steps ... :  51%|█████▏    | 51498/100000 [15:31:10<7:53:10,  1.71it/s]
Train steps ... :  51%|█████▏    | 51499/100000 [15:31:10<7:53:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 51500/100000 [15:31:11<7:53:03,  1.71it/s]Step... (51500 / 100000 | Loss: 0.6046307682991028, Learning Rate: 4.874371859296483e-05)
+
                                                                             
Step... (51500 / 100000 | Loss: 0.9287923574447632, Learning Rate: 4.874371859296483e-05)
+
Train steps ... :  52%|█████▏    | 51500/100000 [15:31:11<7:53:03,  1.71it/s]
Train steps ... :  52%|█████▏    | 51501/100000 [15:31:11<7:53:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 51502/100000 [15:31:12<7:52:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 51503/100000 [15:31:13<7:52:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 51504/100000 [15:31:13<7:52:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 51505/100000 [15:31:14<7:52:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 51506/100000 [15:31:14<7:52:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51507/100000 [15:31:15<7:52:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 51508/100000 [15:31:15<7:53:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 51509/100000 [15:31:16<7:52:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 51510/100000 [15:31:17<7:52:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51511/100000 [15:31:17<7:52:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51512/100000 [15:31:18<7:52:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 51513/100000 [15:31:18<7:53:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 51514/100000 [15:31:19<7:52:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 51515/100000 [15:31:20<7:52:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51516/100000 [15:31:20<7:52:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 51517/100000 [15:31:21<7:52:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 51518/100000 [15:31:21<7:52:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 51519/100000 [15:31:22<7:52:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 51520/100000 [15:31:23<7:51:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51521/100000 [15:31:23<7:52:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51522/100000 [15:31:24<7:52:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 51523/100000 [15:31:24<7:53:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 51524/100000 [15:31:25<7:52:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51525/100000 [15:31:25<7:52:31,  1.71it/s]Step... (51525 / 100000 | Loss: 1.0589476823806763, Learning Rate: 4.871859296482412e-05)
+
                                                                             
Step... (51525 / 100000 | Loss: 0.9669155478477478, Learning Rate: 4.871859296482412e-05)
+
Train steps ... :  52%|█████▏    | 51525/100000 [15:31:26<7:52:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 51526/100000 [15:31:26<7:53:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51527/100000 [15:31:27<7:53:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 51528/100000 [15:31:27<7:52:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 51529/100000 [15:31:28<7:51:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51530/100000 [15:31:28<7:51:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 51531/100000 [15:31:29<7:51:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51532/100000 [15:31:30<7:51:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51533/100000 [15:31:30<7:51:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51534/100000 [15:31:31<7:51:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 51535/100000 [15:31:31<7:52:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 51536/100000 [15:31:32<7:51:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51537/100000 [15:31:32<7:51:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51538/100000 [15:31:33<7:52:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 51539/100000 [15:31:34<7:52:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 51540/100000 [15:31:34<7:52:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51541/100000 [15:31:35<7:52:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 51542/100000 [15:31:35<7:52:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 51543/100000 [15:31:36<7:52:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51544/100000 [15:31:37<7:51:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51545/100000 [15:31:37<7:52:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 51546/100000 [15:31:38<7:52:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 51547/100000 [15:31:38<7:53:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 51548/100000 [15:31:39<7:52:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51549/100000 [15:31:39<7:52:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51550/100000 [15:31:40<7:52:20,  1.71it/s]Step... (51550 / 100000 | Loss: 0.8260430097579956, Learning Rate: 4.869346733668342e-05)
+
                                                                             
Step... (51550 / 100000 | Loss: 0.9242474436759949, Learning Rate: 4.869346733668342e-05)
+
Train steps ... :  52%|█████▏    | 51550/100000 [15:31:40<7:52:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 51551/100000 [15:31:41<7:52:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 51552/100000 [15:31:41<7:52:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51553/100000 [15:31:42<7:52:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 51554/100000 [15:31:42<7:52:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 51555/100000 [15:31:43<7:52:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 51556/100000 [15:31:44<7:51:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51557/100000 [15:31:44<7:52:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51558/100000 [15:31:45<7:52:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 51559/100000 [15:31:45<7:51:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51560/100000 [15:31:46<7:52:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 51561/100000 [15:31:46<7:51:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 51562/100000 [15:31:47<7:51:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 51563/100000 [15:31:48<7:51:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51564/100000 [15:31:48<7:51:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51565/100000 [15:31:49<7:51:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 51566/100000 [15:31:49<7:52:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 51567/100000 [15:31:50<7:52:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51568/100000 [15:31:51<7:51:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51569/100000 [15:31:51<7:52:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51570/100000 [15:31:52<7:52:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 51571/100000 [15:31:52<7:52:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 51572/100000 [15:31:53<7:52:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 51573/100000 [15:31:54<7:51:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51574/100000 [15:31:54<7:52:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 51575/100000 [15:31:55<7:51:59,  1.71it/s]Step... (51575 / 100000 | Loss: 0.7572939395904541, Learning Rate: 4.8668341708542717e-05)
+
                                                                             
Step... (51575 / 100000 | Loss: 0.6219091415405273, Learning Rate: 4.8668341708542717e-05)
+
Train steps ... :  52%|█████▏    | 51575/100000 [15:31:55<7:51:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51576/100000 [15:31:55<7:52:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 51577/100000 [15:31:56<7:52:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51578/100000 [15:31:56<7:52:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 51579/100000 [15:31:57<7:52:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 51580/100000 [15:31:58<7:52:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 51581/100000 [15:31:58<7:51:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51582/100000 [15:31:59<7:51:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51583/100000 [15:31:59<7:51:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 51584/100000 [15:32:00<7:51:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 51585/100000 [15:32:01<7:51:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 51586/100000 [15:32:01<7:52:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 51587/100000 [15:32:02<7:52:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 51588/100000 [15:32:02<7:52:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51589/100000 [15:32:03<7:51:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51590/100000 [15:32:03<7:51:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 51591/100000 [15:32:04<7:52:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 51592/100000 [15:32:05<7:51:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 51593/100000 [15:32:05<7:51:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 51594/100000 [15:32:06<7:52:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51595/100000 [15:32:06<7:52:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51596/100000 [15:32:07<7:53:15,  1.70it/s]
Train steps ... :  52%|█████▏    | 51597/100000 [15:32:08<7:52:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 51598/100000 [15:32:08<7:52:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51599/100000 [15:32:09<7:51:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 51600/100000 [15:32:09<7:51:43,  1.71it/s]Step... (51600 / 100000 | Loss: 0.6956347823143005, Learning Rate: 4.864321608040201e-05)
+
                                                                             
Step... (51600 / 100000 | Loss: 0.961357831954956, Learning Rate: 4.864321608040201e-05)
+
Train steps ... :  52%|█████▏    | 51600/100000 [15:32:10<7:51:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51601/100000 [15:32:10<7:52:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51602/100000 [15:32:10<7:51:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51603/100000 [15:32:11<7:51:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 51604/100000 [15:32:12<7:51:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 51605/100000 [15:32:12<7:51:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51606/100000 [15:32:13<7:51:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51607/100000 [15:32:13<7:51:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51608/100000 [15:32:14<7:51:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 51609/100000 [15:32:15<7:52:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51610/100000 [15:32:15<7:51:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51611/100000 [15:32:16<7:51:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 51612/100000 [15:32:16<7:53:49,  1.70it/s]
Train steps ... :  52%|█████▏    | 51613/100000 [15:32:17<7:53:37,  1.70it/s]
Train steps ... :  52%|█████▏    | 51614/100000 [15:32:17<7:52:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 51615/100000 [15:32:18<7:52:58,  1.70it/s]
Train steps ... :  52%|█████▏    | 51616/100000 [15:32:19<7:52:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51617/100000 [15:32:19<7:52:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 51618/100000 [15:32:20<7:51:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51619/100000 [15:32:20<7:51:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51620/100000 [15:32:21<7:51:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 51621/100000 [15:32:22<7:50:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 51622/100000 [15:32:22<7:51:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51623/100000 [15:32:23<7:50:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 51624/100000 [15:32:23<7:50:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51625/100000 [15:32:24<7:50:59,  1.71it/s]Step... (51625 / 100000 | Loss: 0.7428196668624878, Learning Rate: 4.861809045226131e-05)
+
                                                                             
Step... (51625 / 100000 | Loss: 0.7165751457214355, Learning Rate: 4.861809045226131e-05)
+
Train steps ... :  52%|█████▏    | 51625/100000 [15:32:24<7:50:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51626/100000 [15:32:25<7:51:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 51627/100000 [15:32:25<7:51:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 51628/100000 [15:32:26<7:51:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 51629/100000 [15:32:26<7:51:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 51630/100000 [15:32:27<7:50:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 51631/100000 [15:32:27<7:50:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51632/100000 [15:32:28<7:51:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 51633/100000 [15:32:29<7:50:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51634/100000 [15:32:29<7:50:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51635/100000 [15:32:30<7:50:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51636/100000 [15:32:30<7:50:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 51637/100000 [15:32:31<7:51:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 51638/100000 [15:32:32<7:51:49,  1.71it/s]
Train steps ... :  52%|█████▏    | 51639/100000 [15:32:32<7:51:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51640/100000 [15:32:33<7:51:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 51641/100000 [15:32:33<7:51:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 51642/100000 [15:32:34<7:51:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51643/100000 [15:32:34<7:51:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 51644/100000 [15:32:35<7:51:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 51645/100000 [15:32:36<7:51:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51646/100000 [15:32:36<7:51:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 51647/100000 [15:32:37<7:50:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51648/100000 [15:32:37<7:51:03,  1.71it/s]
Train steps ... :  52%|█████▏    | 51649/100000 [15:32:38<7:51:45,  1.71it/s]
Train steps ... :  52%|█████▏    | 51650/100000 [15:32:39<7:51:42,  1.71it/s]Step... (51650 / 100000 | Loss: 0.8951276540756226, Learning Rate: 4.8592964824120606e-05)
+
                                                                             
Step... (51650 / 100000 | Loss: 0.5863017439842224, Learning Rate: 4.8592964824120606e-05)
+
Train steps ... :  52%|█████▏    | 51650/100000 [15:32:39<7:51:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51651/100000 [15:32:39<7:51:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 51652/100000 [15:32:40<7:51:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 51653/100000 [15:32:40<7:51:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 51654/100000 [15:32:41<7:51:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 51655/100000 [15:32:41<7:51:22,  1.71it/s]
Train steps ... :  52%|█████▏    | 51656/100000 [15:32:42<7:51:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 51657/100000 [15:32:43<7:50:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 51658/100000 [15:32:43<7:50:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 51659/100000 [15:32:44<7:51:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 51660/100000 [15:32:44<7:50:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51661/100000 [15:32:45<7:51:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 51662/100000 [15:32:46<7:52:44,  1.70it/s]
Train steps ... :  52%|█████▏    | 51663/100000 [15:32:46<7:51:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 51664/100000 [15:32:47<7:51:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 51665/100000 [15:32:47<7:51:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51666/100000 [15:32:48<7:51:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 51667/100000 [15:32:48<7:50:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51668/100000 [15:32:49<7:51:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51669/100000 [15:32:50<7:51:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51670/100000 [15:32:50<7:51:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 51671/100000 [15:32:51<7:51:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 51672/100000 [15:32:51<7:51:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 51673/100000 [15:32:52<7:51:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51674/100000 [15:32:53<7:51:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 51675/100000 [15:32:53<7:51:55,  1.71it/s]Step... (51675 / 100000 | Loss: 0.6041247248649597, Learning Rate: 4.85678391959799e-05)
+
                                                                             
Step... (51675 / 100000 | Loss: 0.6176780462265015, Learning Rate: 4.85678391959799e-05)
+
Train steps ... :  52%|█████▏    | 51675/100000 [15:32:54<7:51:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51676/100000 [15:32:54<7:51:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 51677/100000 [15:32:54<7:51:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 51678/100000 [15:32:55<7:52:47,  1.70it/s]
Train steps ... :  52%|███��█▏    | 51679/100000 [15:32:56<7:51:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 51680/100000 [15:32:56<7:51:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 51681/100000 [15:32:57<7:50:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51682/100000 [15:32:57<7:51:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 51683/100000 [15:32:58<7:50:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 51684/100000 [15:32:58<7:50:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 51685/100000 [15:32:59<7:52:03,  1.71it/s]
Train steps ... :  52%|█████▏    | 51686/100000 [15:33:00<7:50:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51687/100000 [15:33:00<7:50:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51688/100000 [15:33:01<7:51:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51689/100000 [15:33:01<7:51:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 51690/100000 [15:33:02<7:51:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 51691/100000 [15:33:03<7:51:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 51692/100000 [15:33:03<7:51:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51693/100000 [15:33:04<7:51:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 51694/100000 [15:33:04<7:50:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51695/100000 [15:33:05<7:50:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51696/100000 [15:33:05<7:50:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 51697/100000 [15:33:06<7:50:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 51698/100000 [15:33:07<7:50:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51699/100000 [15:33:07<7:50:26,  1.71it/s]
Train steps ... :  52%|█████▏    | 51700/100000 [15:33:08<7:50:48,  1.71it/s]Step... (51700 / 100000 | Loss: 0.6360296010971069, Learning Rate: 4.85427135678392e-05)
+
                                                                             
Step... (51700 / 100000 | Loss: 0.7690691947937012, Learning Rate: 4.85427135678392e-05)
+
Train steps ... :  52%|█████▏    | 51700/100000 [15:33:08<7:50:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 51701/100000 [15:33:08<7:50:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51702/100000 [15:33:09<7:50:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 51703/100000 [15:33:10<7:51:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 51704/100000 [15:33:10<7:50:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 51705/100000 [15:33:11<7:50:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 51706/100000 [15:33:11<7:50:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 51707/100000 [15:33:12<7:50:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 51708/100000 [15:33:12<7:51:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 51709/100000 [15:33:13<7:50:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 51710/100000 [15:33:14<7:51:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 51711/100000 [15:33:14<7:50:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51712/100000 [15:33:15<7:50:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51713/100000 [15:33:15<7:50:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51714/100000 [15:33:16<7:50:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51715/100000 [15:33:17<7:50:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51716/100000 [15:33:17<7:51:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 51717/100000 [15:33:18<7:51:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51718/100000 [15:33:18<7:51:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51719/100000 [15:33:19<7:50:49,  1.71it/s]
Train steps ... :  52%|█████▏    | 51720/100000 [15:33:20<7:50:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51721/100000 [15:33:20<7:50:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 51722/100000 [15:33:21<7:50:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51723/100000 [15:33:21<7:50:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 51724/100000 [15:33:22<7:50:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 51725/100000 [15:33:22<7:50:34,  1.71it/s]Step... (51725 / 100000 | Loss: 0.8027445077896118, Learning Rate: 4.8517587939698496e-05)
+
                                                                             
Step... (51725 / 100000 | Loss: 0.7325465679168701, Learning Rate: 4.8517587939698496e-05)
+
Train steps ... :  52%|█████▏    | 51725/100000 [15:33:23<7:50:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 51726/100000 [15:33:23<7:50:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 51727/100000 [15:33:24<7:50:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51728/100000 [15:33:24<7:50:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 51729/100000 [15:33:25<7:50:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 51730/100000 [15:33:25<7:50:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 51731/100000 [15:33:26<7:50:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 51732/100000 [15:33:27<7:50:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 51733/100000 [15:33:27<7:50:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 51734/100000 [15:33:28<7:51:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51735/100000 [15:33:28<7:51:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51736/100000 [15:33:29<7:51:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 51737/100000 [15:33:29<7:50:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 51738/100000 [15:33:30<7:50:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 51739/100000 [15:33:31<7:50:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 51740/100000 [15:33:31<7:50:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 51741/100000 [15:33:32<7:50:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 51742/100000 [15:33:32<7:49:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51743/100000 [15:33:33<7:50:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51744/100000 [15:33:34<7:50:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51745/100000 [15:33:34<7:50:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51746/100000 [15:33:35<7:50:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 51747/100000 [15:33:35<7:50:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 51748/100000 [15:33:36<7:50:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 51749/100000 [15:33:36<7:49:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 51750/100000 [15:33:37<7:49:30,  1.71it/s]Step... (51750 / 100000 | Loss: 0.6701098084449768, Learning Rate: 4.849246231155779e-05)
+
                                                                             
Step... (51750 / 100000 | Loss: 0.8384784460067749, Learning Rate: 4.849246231155779e-05)
+
Train steps ... :  52%|█████▏    | 51750/100000 [15:33:37<7:49:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 51751/100000 [15:33:38<7:50:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 51752/100000 [15:33:38<7:50:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 51753/100000 [15:33:39<7:50:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51754/100000 [15:33:39<7:49:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51755/100000 [15:33:40<7:49:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 51756/100000 [15:33:41<7:50:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 51757/100000 [15:33:41<7:50:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 51758/100000 [15:33:42<7:49:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51759/100000 [15:33:42<7:50:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 51760/100000 [15:33:43<7:49:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51761/100000 [15:33:43<7:49:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 51762/100000 [15:33:44<7:50:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 51763/100000 [15:33:45<7:49:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51764/100000 [15:33:45<7:49:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 51765/100000 [15:33:46<7:50:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 51766/100000 [15:33:46<7:50:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 51767/100000 [15:33:47<7:49:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51768/100000 [15:33:48<7:50:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 51769/100000 [15:33:48<7:50:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 51770/100000 [15:33:49<7:50:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51771/100000 [15:33:49<7:50:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 51772/100000 [15:33:50<7:50:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 51773/100000 [15:33:50<7:49:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51774/100000 [15:33:51<7:49:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51775/100000 [15:33:52<7:49:40,  1.71it/s]Step... (51775 / 100000 | Loss: 0.6875429153442383, Learning Rate: 4.846733668341709e-05)
+
                                                                             
Step... (51775 / 100000 | Loss: 0.5849898457527161, Learning Rate: 4.846733668341709e-05)
+
Train steps ... :  52%|█████▏    | 51775/100000 [15:33:52<7:49:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51776/100000 [15:33:52<7:50:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51777/100000 [15:33:53<7:49:46,  1.71it/s]
Train steps ... :  52%|█████▏    | 51778/100000 [15:33:53<7:49:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51779/100000 [15:33:54<7:49:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 51780/100000 [15:33:55<7:50:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 51781/100000 [15:33:55<7:49:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51782/100000 [15:33:56<7:49:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 51783/100000 [15:33:56<7:49:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51784/100000 [15:33:57<7:49:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 51785/100000 [15:33:58<7:49:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 51786/100000 [15:33:58<7:49:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 51787/100000 [15:33:59<7:49:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51788/100000 [15:33:59<7:49:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51789/100000 [15:34:00<7:49:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 51790/100000 [15:34:00<7:49:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 51791/100000 [15:34:01<7:49:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 51792/100000 [15:34:02<7:48:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 51793/100000 [15:34:02<7:48:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 51794/100000 [15:34:03<7:49:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 51795/100000 [15:34:03<7:48:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51796/100000 [15:34:04<7:48:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51797/100000 [15:34:05<7:49:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 51798/100000 [15:34:05<7:49:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 51799/100000 [15:34:06<7:50:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 51800/100000 [15:34:06<7:49:52,  1.71it/s]Step... (51800 / 100000 | Loss: 0.8346518874168396, Learning Rate: 4.844221105527638e-05)
+
                                                                             
Step... (51800 / 100000 | Loss: 0.7559729814529419, Learning Rate: 4.844221105527638e-05)
+
Train steps ... :  52%|█████▏    | 51800/100000 [15:34:07<7:49:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51801/100000 [15:34:07<7:50:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 51802/100000 [15:34:07<7:50:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51803/100000 [15:34:08<7:49:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 51804/100000 [15:34:09<7:49:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 51805/100000 [15:34:09<7:49:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 51806/100000 [15:34:10<7:49:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 51807/100000 [15:34:10<7:48:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 51808/100000 [15:34:11<7:49:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 51809/100000 [15:34:12<7:49:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 51810/100000 [15:34:12<7:49:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 51811/100000 [15:34:13<7:49:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51812/100000 [15:34:13<7:49:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 51813/100000 [15:34:14<7:49:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 51814/100000 [15:34:14<7:49:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51815/100000 [15:34:15<7:49:49,  1.71it/s]
Train steps ... :  52%|█████▏    | 51816/100000 [15:34:16<7:49:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 51817/100000 [15:34:16<7:49:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 51818/100000 [15:34:17<7:49:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 51819/100000 [15:34:17<7:49:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51820/100000 [15:34:18<7:49:03,  1.71it/s]
Train steps ... :  52%|█████▏    | 51821/100000 [15:34:19<7:50:03,  1.71it/s]
Train steps ... :  52%|█████▏    | 51822/100000 [15:34:19<7:49:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51823/100000 [15:34:20<7:50:03,  1.71it/s]
Train steps ... :  52%|█████▏    | 51824/100000 [15:34:20<7:49:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51825/100000 [15:34:21<7:49:31,  1.71it/s]Step... (51825 / 100000 | Loss: 0.6917217969894409, Learning Rate: 4.841708542713568e-05)
+
                                                                             
Step... (51825 / 100000 | Loss: 0.7204389572143555, Learning Rate: 4.841708542713568e-05)
+
Train steps ... :  52%|█████▏    | 51825/100000 [15:34:21<7:49:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 51826/100000 [15:34:21<7:50:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 51827/100000 [15:34:22<7:50:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 51828/100000 [15:34:23<7:50:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51829/100000 [15:34:23<7:49:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51830/100000 [15:34:24<7:50:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 51831/100000 [15:34:24<7:49:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51832/100000 [15:34:25<7:50:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 51833/100000 [15:34:26<7:49:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51834/100000 [15:34:26<7:49:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 51835/100000 [15:34:27<7:49:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 51836/100000 [15:34:27<7:49:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 51837/100000 [15:34:28<7:49:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 51838/100000 [15:34:28<7:48:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51839/100000 [15:34:29<7:49:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 51840/100000 [15:34:30<7:49:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 51841/100000 [15:34:30<7:49:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 51842/100000 [15:34:31<7:49:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 51843/100000 [15:34:31<7:48:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51844/100000 [15:34:32<7:49:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 51845/100000 [15:34:33<7:49:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 51846/100000 [15:34:33<7:48:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 51847/100000 [15:34:34<7:49:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 51848/100000 [15:34:34<7:49:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 51849/100000 [15:34:35<7:49:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 51850/100000 [15:34:36<7:49:28,  1.71it/s]Step... (51850 / 100000 | Loss: 0.8207908868789673, Learning Rate: 4.839195979899498e-05)
+
                                                                             
Step... (51850 / 100000 | Loss: 0.7581207156181335, Learning Rate: 4.839195979899498e-05)
+
Train steps ... :  52%|█████▏    | 51850/100000 [15:34:36<7:49:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 51851/100000 [15:34:36<7:49:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51852/100000 [15:34:37<7:49:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 51853/100000 [15:34:37<7:49:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51854/100000 [15:34:38<7:49:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 51855/100000 [15:34:38<7:49:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 51856/100000 [15:34:39<7:49:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 51857/100000 [15:34:40<7:48:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 51858/100000 [15:34:40<7:49:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 51859/100000 [15:34:41<7:48:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 51860/100000 [15:34:41<7:49:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 51861/100000 [15:34:42<7:49:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 51862/100000 [15:34:43<7:48:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51863/100000 [15:34:43<7:48:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 51864/100000 [15:34:44<7:49:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 51865/100000 [15:34:44<7:49:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 51866/100000 [15:34:45<7:48:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 51867/100000 [15:34:45<7:49:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 51868/100000 [15:34:46<7:48:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51869/100000 [15:34:47<7:49:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 51870/100000 [15:34:47<7:49:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51871/100000 [15:34:48<7:49:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 51872/100000 [15:34:48<7:48:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51873/100000 [15:34:49<7:49:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51874/100000 [15:34:50<7:49:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 51875/100000 [15:34:50<7:49:02,  1.71it/s]Step... (51875 / 100000 | Loss: 0.9039156436920166, Learning Rate: 4.8366834170854276e-05)
+
                                                                             
Step... (51875 / 100000 | Loss: 0.6801214218139648, Learning Rate: 4.8366834170854276e-05)
+
Train steps ... :  52%|█████▏    | 51875/100000 [15:34:50<7:49:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 51876/100000 [15:34:51<7:49:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 51877/100000 [15:34:51<7:48:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 51878/100000 [15:34:52<7:48:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51879/100000 [15:34:52<7:49:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 51880/100000 [15:34:53<7:48:45,  1.71it/s]
Train steps ... :  52%|█████▏    | 51881/100000 [15:34:54<7:48:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51882/100000 [15:34:54<7:48:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 51883/100000 [15:34:55<7:48:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 51884/100000 [15:34:55<7:48:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51885/100000 [15:34:56<7:48:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51886/100000 [15:34:57<7:48:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 51887/100000 [15:34:57<7:48:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 51888/100000 [15:34:58<7:48:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 51889/100000 [15:34:58<7:48:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 51890/100000 [15:34:59<7:48:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 51891/100000 [15:34:59<7:48:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 51892/100000 [15:35:00<7:48:22,  1.71it/s]
Train steps ... :  52%|█████▏    | 51893/100000 [15:35:01<7:48:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 51894/100000 [15:35:01<7:48:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51895/100000 [15:35:02<7:49:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 51896/100000 [15:35:02<7:48:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 51897/100000 [15:35:03<7:48:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51898/100000 [15:35:04<7:49:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 51899/100000 [15:35:04<7:48:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51900/100000 [15:35:05<7:49:16,  1.71it/s]Step... (51900 / 100000 | Loss: 0.6531901359558105, Learning Rate: 4.834170854271357e-05)
+
                                                                             
Step... (51900 / 100000 | Loss: 0.5405232310295105, Learning Rate: 4.834170854271357e-05)
+
Train steps ... :  52%|█████▏    | 51900/100000 [15:35:05<7:49:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 51901/100000 [15:35:05<7:49:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51902/100000 [15:35:06<7:48:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 51903/100000 [15:35:07<7:49:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 51904/100000 [15:35:07<7:49:22,  1.71it/s]
Train steps ... :  52%|█████▏    | 51905/100000 [15:35:08<7:49:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 51906/100000 [15:35:08<7:48:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51907/100000 [15:35:09<7:48:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51908/100000 [15:35:09<7:48:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51909/100000 [15:35:10<7:48:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 51910/100000 [15:35:11<7:49:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 51911/100000 [15:35:11<7:49:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51912/100000 [15:35:12<7:48:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 51913/100000 [15:35:12<7:48:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 51914/100000 [15:35:13<7:50:31,  1.70it/s]
Train steps ... :  52%|█████▏    | 51915/100000 [15:35:14<7:48:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51916/100000 [15:35:14<7:49:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 51917/100000 [15:35:15<7:48:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 51918/100000 [15:35:15<7:48:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51919/100000 [15:35:16<7:49:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51920/100000 [15:35:16<7:48:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 51921/100000 [15:35:17<7:49:03,  1.71it/s]
Train steps ... :  52%|█████▏    | 51922/100000 [15:35:18<7:48:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 51923/100000 [15:35:18<7:49:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 51924/100000 [15:35:19<7:49:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 51925/100000 [15:35:19<7:50:57,  1.70it/s]Step... (51925 / 100000 | Loss: 1.131286859512329, Learning Rate: 4.831658291457287e-05)
+
                                                                             
Step... (51925 / 100000 | Loss: 0.5191848874092102, Learning Rate: 4.831658291457287e-05)
+
Train steps ... :  52%|█████▏    | 51925/100000 [15:35:20<7:50:57,  1.70it/s]
Train steps ... :  52%|█████▏    | 51926/100000 [15:35:20<7:49:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 51927/100000 [15:35:21<7:49:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 51928/100000 [15:35:21<7:49:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51929/100000 [15:35:22<7:48:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51930/100000 [15:35:22<7:48:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51931/100000 [15:35:23<7:48:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51932/100000 [15:35:23<7:48:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 51933/100000 [15:35:24<7:48:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 51934/100000 [15:35:25<7:48:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 51935/100000 [15:35:25<7:47:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51936/100000 [15:35:26<7:47:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51937/100000 [15:35:26<7:47:26,  1.71it/s]
Train steps ... :  52%|█████▏    | 51938/100000 [15:35:27<7:48:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 51939/100000 [15:35:28<7:47:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 51940/100000 [15:35:28<7:48:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 51941/100000 [15:35:29<7:48:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 51942/100000 [15:35:29<7:48:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 51943/100000 [15:35:30<7:48:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 51944/100000 [15:35:30<7:48:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51945/100000 [15:35:31<7:47:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51946/100000 [15:35:32<7:48:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 51947/100000 [15:35:32<7:48:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 51948/100000 [15:35:33<7:48:26,  1.71it/s]
Train steps ... :  52%|█████▏    | 51949/100000 [15:35:33<7:48:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 51950/100000 [15:35:34<7:48:47,  1.71it/s]Step... (51950 / 100000 | Loss: 0.6503928899765015, Learning Rate: 4.829145728643216e-05)
+
                                                                             
Step... (51950 / 100000 | Loss: 0.9785122871398926, Learning Rate: 4.829145728643216e-05)
+
Train steps ... :  52%|█████▏    | 51950/100000 [15:35:34<7:48:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51951/100000 [15:35:35<7:49:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 51952/100000 [15:35:35<7:50:20,  1.70it/s]
Train steps ... :  52%|█████▏    | 51953/100000 [15:35:36<7:48:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 51954/100000 [15:35:36<7:48:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 51955/100000 [15:35:37<7:50:05,  1.70it/s]
Train steps ... :  52%|█████▏    | 51956/100000 [15:35:38<7:47:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 51957/100000 [15:35:38<7:48:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51958/100000 [15:35:39<7:49:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 51959/100000 [15:35:39<7:48:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 51960/100000 [15:35:40<7:48:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 51961/100000 [15:35:40<7:48:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 51962/100000 [15:35:41<7:47:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 51963/100000 [15:35:42<7:48:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 51964/100000 [15:35:42<7:47:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 51965/100000 [15:35:43<7:47:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 51966/100000 [15:35:43<7:48:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 51967/100000 [15:35:44<7:48:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 51968/100000 [15:35:45<7:48:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 51969/100000 [15:35:45<7:48:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51970/100000 [15:35:46<7:48:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 51971/100000 [15:35:46<7:48:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51972/100000 [15:35:47<7:49:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 51973/100000 [15:35:47<7:49:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 51974/100000 [15:35:48<7:48:46,  1.71it/s]
Train steps ... :  52%|█████▏    | 51975/100000 [15:35:49<7:49:48,  1.70it/s]Step... (51975 / 100000 | Loss: 0.7813507914543152, Learning Rate: 4.8266331658291456e-05)
+
                                                                             
Step... (51975 / 100000 | Loss: 0.6272789835929871, Learning Rate: 4.8266331658291456e-05)
+
Train steps ... :  52%|█████▏    | 51975/100000 [15:35:49<7:49:48,  1.70it/s]
Train steps ... :  52%|█████▏    | 51976/100000 [15:35:49<7:48:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51977/100000 [15:35:50<7:48:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 51978/100000 [15:35:50<7:48:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 51979/100000 [15:35:51<7:48:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 51980/100000 [15:35:52<7:48:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 51981/100000 [15:35:52<7:48:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 51982/100000 [15:35:53<7:48:22,  1.71it/s]
Train steps ... :  52%|█████▏    | 51983/100000 [15:35:53<7:47:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 51984/100000 [15:35:54<7:47:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 51985/100000 [15:35:54<7:48:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 51986/100000 [15:35:55<7:47:45,  1.71it/s]
Train steps ... :  52%|█████▏    | 51987/100000 [15:35:56<7:48:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 51988/100000 [15:35:56<7:48:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 51989/100000 [15:35:57<7:47:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 51990/100000 [15:35:57<7:47:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 51991/100000 [15:35:58<7:47:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 51992/100000 [15:35:59<7:47:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 51993/100000 [15:35:59<7:47:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 51994/100000 [15:36:00<7:47:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 51995/100000 [15:36:00<7:47:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 51996/100000 [15:36:01<7:48:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 51997/100000 [15:36:02<7:47:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 51998/100000 [15:36:02<7:47:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 51999/100000 [15:36:03<7:47:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 52000/100000 [15:36:03<7:47:07,  1.71it/s]Step... (52000 / 100000 | Loss: 0.6140231490135193, Learning Rate: 4.824120603015075e-05)
+
                                                                             
Step... (52000 / 100000 | Loss: 0.7254855036735535, Learning Rate: 4.824120603015075e-05)
+
Train steps ... :  52%|█████▏    | 52000/100000 [15:36:04<7:47:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52001/100000 [15:36:04<7:47:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 52002/100000 [15:36:04<7:47:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 52003/100000 [15:36:05<7:47:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 52004/100000 [15:36:06<7:47:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 52005/100000 [15:36:06<7:47:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 52006/100000 [15:36:07<7:48:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52007/100000 [15:36:07<7:48:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 52008/100000 [15:36:08<7:48:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 52009/100000 [15:36:09<7:47:46,  1.71it/s]
Train steps ... :  52%|█████▏    | 52010/100000 [15:36:09<7:48:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52011/100000 [15:36:10<7:48:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52012/100000 [15:36:10<7:47:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 52013/100000 [15:36:11<7:47:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52014/100000 [15:36:11<7:46:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 52015/100000 [15:36:12<7:46:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 52016/100000 [15:36:13<7:46:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 52017/100000 [15:36:13<7:46:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 52018/100000 [15:36:14<7:46:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 52019/100000 [15:36:14<7:47:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52020/100000 [15:36:15<7:47:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 52021/100000 [15:36:16<7:47:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 52022/100000 [15:36:16<7:46:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 52023/100000 [15:36:17<7:47:03,  1.71it/s]
Train steps ... :  52%|█████▏    | 52024/100000 [15:36:17<7:46:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 52025/100000 [15:36:18<7:47:07,  1.71it/s]Step... (52025 / 100000 | Loss: 0.7066876292228699, Learning Rate: 4.821608040201005e-05)
+
                                                                             
Step... (52025 / 100000 | Loss: 0.7540121078491211, Learning Rate: 4.821608040201005e-05)
+
Train steps ... :  52%|█████▏    | 52025/100000 [15:36:18<7:47:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52026/100000 [15:36:18<7:48:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52027/100000 [15:36:19<7:47:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 52028/100000 [15:36:20<7:47:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 52029/100000 [15:36:20<7:47:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 52030/100000 [15:36:21<7:47:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52031/100000 [15:36:21<7:47:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52032/100000 [15:36:22<7:46:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52033/100000 [15:36:23<7:46:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 52034/100000 [15:36:23<7:46:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52035/100000 [15:36:24<7:46:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52036/100000 [15:36:24<7:46:46,  1.71it/s]
Train steps ... :  52%|█████▏    | 52037/100000 [15:36:25<7:46:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 52038/100000 [15:36:25<7:46:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 52039/100000 [15:36:26<7:47:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 52040/100000 [15:36:27<7:46:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52041/100000 [15:36:27<7:47:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 52042/100000 [15:36:28<7:47:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 52043/100000 [15:36:28<7:46:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 52044/100000 [15:36:29<7:46:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 52045/100000 [15:36:30<7:46:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 52046/100000 [15:36:30<7:46:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 52047/100000 [15:36:31<7:46:49,  1.71it/s]
Train steps ... :  52%|█████▏    | 52048/100000 [15:36:31<7:47:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 52049/100000 [15:36:32<7:47:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52050/100000 [15:36:32<7:47:00,  1.71it/s]Step... (52050 / 100000 | Loss: 0.7607926726341248, Learning Rate: 4.819095477386935e-05)
+
                                                                             
Step... (52050 / 100000 | Loss: 0.5502598881721497, Learning Rate: 4.819095477386935e-05)
+
Train steps ... :  52%|█████▏    | 52050/100000 [15:36:33<7:47:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 52051/100000 [15:36:33<7:47:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 52052/100000 [15:36:34<7:47:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52053/100000 [15:36:34<7:47:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 52054/100000 [15:36:35<7:47:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 52055/100000 [15:36:35<7:47:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 52056/100000 [15:36:36<7:47:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 52057/100000 [15:36:37<7:46:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52058/100000 [15:36:37<7:47:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 52059/100000 [15:36:38<7:47:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 52060/100000 [15:36:38<7:47:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 52061/100000 [15:36:39<7:47:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 52062/100000 [15:36:40<7:47:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 52063/100000 [15:36:40<7:46:49,  1.71it/s]
Train steps ... :  52%|█████▏    | 52064/100000 [15:36:41<7:47:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52065/100000 [15:36:41<7:47:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52066/100000 [15:36:42<7:47:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 52067/100000 [15:36:42<7:47:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52068/100000 [15:36:43<7:47:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52069/100000 [15:36:44<7:47:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 52070/100000 [15:36:44<7:47:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 52071/100000 [15:36:45<7:47:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52072/100000 [15:36:45<7:47:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 52073/100000 [15:36:46<7:47:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 52074/100000 [15:36:47<7:47:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52075/100000 [15:36:47<7:47:15,  1.71it/s]Step... (52075 / 100000 | Loss: 0.7663124799728394, Learning Rate: 4.816582914572865e-05)
+
                                                                             
Step... (52075 / 100000 | Loss: 0.7007259130477905, Learning Rate: 4.816582914572865e-05)
+
Train steps ... :  52%|█████▏    | 52075/100000 [15:36:47<7:47:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 52076/100000 [15:36:48<7:48:45,  1.70it/s]
Train steps ... :  52%|█████▏    | 52077/100000 [15:36:48<7:47:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 52078/100000 [15:36:49<7:47:26,  1.71it/s]
Train steps ... :  52%|█████▏    | 52079/100000 [15:36:49<7:47:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 52080/100000 [15:36:50<7:47:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 52081/100000 [15:36:51<7:47:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52082/100000 [15:36:51<7:46:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 52083/100000 [15:36:52<7:46:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52084/100000 [15:36:52<7:46:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 52085/100000 [15:36:53<7:47:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52086/100000 [15:36:54<7:46:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 52087/100000 [15:36:54<7:46:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52088/100000 [15:36:55<7:47:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52089/100000 [15:36:55<7:47:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 52090/100000 [15:36:56<7:46:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 52091/100000 [15:36:56<7:46:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 52092/100000 [15:36:57<7:47:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52093/100000 [15:36:58<7:48:20,  1.70it/s]
Train steps ... :  52%|█████▏    | 52094/100000 [15:36:58<7:47:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 52095/100000 [15:36:59<7:47:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52096/100000 [15:36:59<7:46:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 52097/100000 [15:37:00<7:46:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 52098/100000 [15:37:01<7:46:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 52099/100000 [15:37:01<7:47:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52100/100000 [15:37:02<7:46:47,  1.71it/s]Step... (52100 / 100000 | Loss: 0.7401456236839294, Learning Rate: 4.8140703517587946e-05)
+
                                                                             
Step... (52100 / 100000 | Loss: 0.577283501625061, Learning Rate: 4.8140703517587946e-05)
+
Train steps ... :  52%|█████▏    | 52100/100000 [15:37:02<7:46:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 52101/100000 [15:37:02<7:47:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 52102/100000 [15:37:03<7:47:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 52103/100000 [15:37:03<7:46:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 52104/100000 [15:37:04<7:46:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 52105/100000 [15:37:05<7:46:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 52106/100000 [15:37:05<7:46:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52107/100000 [15:37:06<7:46:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52108/100000 [15:37:06<7:46:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 52109/100000 [15:37:07<7:46:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 52110/100000 [15:37:08<7:47:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52111/100000 [15:37:08<7:46:46,  1.71it/s]
Train steps ... :  52%|█████▏    | 52112/100000 [15:37:09<7:46:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 52113/100000 [15:37:09<7:46:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 52114/100000 [15:37:10<7:46:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52115/100000 [15:37:11<7:46:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 52116/100000 [15:37:11<7:46:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 52117/100000 [15:37:12<7:47:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52118/100000 [15:37:12<7:46:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 52119/100000 [15:37:13<7:46:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 52120/100000 [15:37:13<7:46:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 52121/100000 [15:37:14<7:46:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52122/100000 [15:37:15<7:46:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52123/100000 [15:37:15<7:45:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52124/100000 [15:37:16<7:46:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 52125/100000 [15:37:16<7:46:48,  1.71it/s]Step... (52125 / 100000 | Loss: 0.7754952311515808, Learning Rate: 4.8115577889447235e-05)
+
                                                                             
Step... (52125 / 100000 | Loss: 0.6897283792495728, Learning Rate: 4.8115577889447235e-05)
+
Train steps ... :  52%|█████▏    | 52125/100000 [15:37:17<7:46:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 52126/100000 [15:37:17<7:46:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 52127/100000 [15:37:18<7:46:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52128/100000 [15:37:18<7:46:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52129/100000 [15:37:19<7:46:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52130/100000 [15:37:19<7:46:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 52131/100000 [15:37:20<7:46:26,  1.71it/s]
Train steps ... :  52%|█████▏    | 52132/100000 [15:37:20<7:46:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 52133/100000 [15:37:21<7:46:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 52134/100000 [15:37:22<7:46:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52135/100000 [15:37:22<7:46:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52136/100000 [15:37:23<7:46:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52137/100000 [15:37:23<7:46:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 52138/100000 [15:37:24<7:46:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52139/100000 [15:37:25<7:46:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 52140/100000 [15:37:25<7:46:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52141/100000 [15:37:26<7:47:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52142/100000 [15:37:26<7:46:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 52143/100000 [15:37:27<7:46:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52144/100000 [15:37:27<7:46:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 52145/100000 [15:37:28<7:46:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52146/100000 [15:37:29<7:46:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52147/100000 [15:37:29<7:45:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 52148/100000 [15:37:30<7:46:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52149/100000 [15:37:30<7:45:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 52150/100000 [15:37:31<7:45:36,  1.71it/s]Step... (52150 / 100000 | Loss: 0.6381909847259521, Learning Rate: 4.809045226130653e-05)
+
                                                                             
Step... (52150 / 100000 | Loss: 0.945738673210144, Learning Rate: 4.809045226130653e-05)
+
Train steps ... :  52%|█████▏    | 52150/100000 [15:37:31<7:45:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 52151/100000 [15:37:32<7:45:45,  1.71it/s]
Train steps ... :  52%|█████▏    | 52152/100000 [15:37:32<7:45:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52153/100000 [15:37:33<7:45:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 52154/100000 [15:37:33<7:46:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 52155/100000 [15:37:34<7:46:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 52156/100000 [15:37:34<7:45:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 52157/100000 [15:37:35<7:45:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 52158/100000 [15:37:36<7:45:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 52159/100000 [15:37:36<7:45:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52160/100000 [15:37:37<7:45:45,  1.71it/s]
Train steps ... :  52%|█████▏    | 52161/100000 [15:37:37<7:46:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52162/100000 [15:37:38<7:45:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 52163/100000 [15:37:39<7:45:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 52164/100000 [15:37:39<7:46:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52165/100000 [15:37:40<7:46:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 52166/100000 [15:37:40<7:46:46,  1.71it/s]
Train steps ... :  52%|█████▏    | 52167/100000 [15:37:41<7:46:03,  1.71it/s]
Train steps ... :  52%|█████▏    | 52168/100000 [15:37:41<7:45:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 52169/100000 [15:37:42<7:45:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 52170/100000 [15:37:43<7:46:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52171/100000 [15:37:43<7:46:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 52172/100000 [15:37:44<7:45:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 52173/100000 [15:37:44<7:45:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 52174/100000 [15:37:45<7:45:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 52175/100000 [15:37:46<7:45:37,  1.71it/s]Step... (52175 / 100000 | Loss: 0.7299771308898926, Learning Rate: 4.806532663316583e-05)
+
                                                                             
Step... (52175 / 100000 | Loss: 0.6920522451400757, Learning Rate: 4.806532663316583e-05)
+
Train steps ... :  52%|█████▏    | 52175/100000 [15:37:46<7:45:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 52176/100000 [15:37:46<7:46:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 52177/100000 [15:37:47<7:46:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52178/100000 [15:37:47<7:46:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52179/100000 [15:37:48<7:46:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 52180/100000 [15:37:48<7:46:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 52181/100000 [15:37:49<7:46:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 52182/100000 [15:37:50<7:46:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 52183/100000 [15:37:50<7:45:49,  1.71it/s]
Train steps ... :  52%|█████▏    | 52184/100000 [15:37:51<7:45:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 52185/100000 [15:37:51<7:45:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 52186/100000 [15:37:52<7:45:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52187/100000 [15:37:53<7:45:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 52188/100000 [15:37:53<7:45:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 52189/100000 [15:37:54<7:45:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52190/100000 [15:37:54<7:45:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 52191/100000 [15:37:55<7:45:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52192/100000 [15:37:56<7:45:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 52193/100000 [15:37:56<7:45:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52194/100000 [15:37:57<7:46:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 52195/100000 [15:37:57<7:45:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 52196/100000 [15:37:58<7:45:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 52197/100000 [15:37:58<7:45:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52198/100000 [15:37:59<7:45:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 52199/100000 [15:38:00<7:45:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52200/100000 [15:38:00<7:45:02,  1.71it/s]Step... (52200 / 100000 | Loss: 0.6332755088806152, Learning Rate: 4.8040201005025125e-05)
+
                                                                             
Step... (52200 / 100000 | Loss: 1.049197793006897, Learning Rate: 4.8040201005025125e-05)
+
Train steps ... :  52%|█████▏    | 52200/100000 [15:38:01<7:45:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52201/100000 [15:38:01<7:45:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 52202/100000 [15:38:01<7:45:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 52203/100000 [15:38:02<7:45:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52204/100000 [15:38:03<7:45:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 52205/100000 [15:38:03<7:45:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 52206/100000 [15:38:04<7:45:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52207/100000 [15:38:04<7:45:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 52208/100000 [15:38:05<7:46:22,  1.71it/s]
Train steps ... :  52%|█████▏    | 52209/100000 [15:38:05<7:45:26,  1.71it/s]
Train steps ... :  52%|█████▏    | 52210/100000 [15:38:06<7:46:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 52211/100000 [15:38:07<7:47:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 52212/100000 [15:38:07<7:46:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 52213/100000 [15:38:08<7:47:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52214/100000 [15:38:08<7:46:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52215/100000 [15:38:09<7:46:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 52216/100000 [15:38:10<7:46:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 52217/100000 [15:38:10<7:45:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 52218/100000 [15:38:11<7:45:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 52219/100000 [15:38:11<7:45:26,  1.71it/s]
Train steps ... :  52%|█████▏    | 52220/100000 [15:38:12<7:45:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 52221/100000 [15:38:12<7:45:45,  1.71it/s]
Train steps ... :  52%|█████▏    | 52222/100000 [15:38:13<7:45:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52223/100000 [15:38:14<7:45:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 52224/100000 [15:38:14<7:45:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 52225/100000 [15:38:15<7:46:31,  1.71it/s]Step... (52225 / 100000 | Loss: 1.0605067014694214, Learning Rate: 4.801507537688442e-05)
+
                                                                             
Step... (52225 / 100000 | Loss: 0.7518904209136963, Learning Rate: 4.801507537688442e-05)
+
Train steps ... :  52%|█████▏    | 52225/100000 [15:38:15<7:46:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52226/100000 [15:38:15<7:46:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 52227/100000 [15:38:16<7:45:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 52228/100000 [15:38:17<7:45:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 52229/100000 [15:38:17<7:45:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 52230/100000 [15:38:18<7:45:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 52231/100000 [15:38:18<7:45:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 52232/100000 [15:38:19<7:45:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 52233/100000 [15:38:19<7:44:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 52234/100000 [15:38:20<7:45:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 52235/100000 [15:38:21<7:45:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 52236/100000 [15:38:21<7:44:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 52237/100000 [15:38:22<7:45:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52238/100000 [15:38:22<7:45:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52239/100000 [15:38:23<7:45:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 52240/100000 [15:38:24<7:44:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 52241/100000 [15:38:24<7:45:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 52242/100000 [15:38:25<7:46:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 52243/100000 [15:38:25<7:44:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 52244/100000 [15:38:26<7:44:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52245/100000 [15:38:26<7:45:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 52246/100000 [15:38:27<7:45:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 52247/100000 [15:38:28<7:45:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 52248/100000 [15:38:28<7:45:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 52249/100000 [15:38:29<7:45:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 52250/100000 [15:38:29<7:45:57,  1.71it/s]Step... (52250 / 100000 | Loss: 0.8354973793029785, Learning Rate: 4.7989949748743725e-05)
+
                                                                             
Step... (52250 / 100000 | Loss: 0.8335710763931274, Learning Rate: 4.7989949748743725e-05)
+
Train steps ... :  52%|█████▏    | 52250/100000 [15:38:30<7:45:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52251/100000 [15:38:30<7:46:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 52252/100000 [15:38:31<7:45:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 52253/100000 [15:38:31<7:45:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 52254/100000 [15:38:32<7:45:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 52255/100000 [15:38:32<7:45:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52256/100000 [15:38:33<7:45:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52257/100000 [15:38:34<7:45:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52258/100000 [15:38:34<7:45:22,  1.71it/s]
Train steps ... :  52%|█████▏    | 52259/100000 [15:38:35<7:45:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52260/100000 [15:38:35<7:45:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52261/100000 [15:38:36<7:45:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 52262/100000 [15:38:36<7:45:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 52263/100000 [15:38:37<7:45:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 52264/100000 [15:38:38<7:45:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52265/100000 [15:38:38<7:45:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52266/100000 [15:38:39<7:44:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52267/100000 [15:38:39<7:45:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52268/100000 [15:38:40<7:45:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 52269/100000 [15:38:41<7:45:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52270/100000 [15:38:41<7:45:26,  1.71it/s]
Train steps ... :  52%|█████▏    | 52271/100000 [15:38:42<7:45:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 52272/100000 [15:38:42<7:45:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 52273/100000 [15:38:43<7:45:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 52274/100000 [15:38:43<7:45:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 52275/100000 [15:38:44<7:45:02,  1.71it/s]Step... (52275 / 100000 | Loss: 0.6972342729568481, Learning Rate: 4.796482412060302e-05)
+
                                                                             
Step... (52275 / 100000 | Loss: 0.7712655067443848, Learning Rate: 4.796482412060302e-05)
+
Train steps ... :  52%|█████▏    | 52275/100000 [15:38:44<7:45:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52276/100000 [15:38:45<7:44:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52277/100000 [15:38:45<7:44:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 52278/100000 [15:38:46<7:45:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 52279/100000 [15:38:46<7:45:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 52280/100000 [15:38:47<7:45:22,  1.71it/s]
Train steps ... :  52%|█████▏    | 52281/100000 [15:38:48<7:45:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 52282/100000 [15:38:48<7:45:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52283/100000 [15:38:49<7:45:15,  1.71it/s]
Train steps ... :  52%|█████▏    | 52284/100000 [15:38:49<7:44:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 52285/100000 [15:38:50<7:45:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52286/100000 [15:38:50<7:44:49,  1.71it/s]
Train steps ... :  52%|█████▏    | 52287/100000 [15:38:51<7:44:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 52288/100000 [15:38:52<7:45:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 52289/100000 [15:38:52<7:45:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52290/100000 [15:38:53<7:45:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52291/100000 [15:38:53<7:44:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52292/100000 [15:38:54<7:44:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 52293/100000 [15:38:55<7:44:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52294/100000 [15:38:55<7:44:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 52295/100000 [15:38:56<7:44:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52296/100000 [15:38:56<7:44:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 52297/100000 [15:38:57<7:44:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 52298/100000 [15:38:57<7:44:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52299/100000 [15:38:58<7:45:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 52300/100000 [15:38:59<7:45:13,  1.71it/s]Step... (52300 / 100000 | Loss: 0.6535464525222778, Learning Rate: 4.793969849246231e-05)
+
                                                                             
Step... (52300 / 100000 | Loss: 0.8009612560272217, Learning Rate: 4.793969849246231e-05)
+
Train steps ... :  52%|█████▏    | 52300/100000 [15:38:59<7:45:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 52301/100000 [15:38:59<7:45:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52302/100000 [15:39:00<7:45:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52303/100000 [15:39:00<7:45:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52304/100000 [15:39:01<7:45:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 52305/100000 [15:39:02<7:45:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 52306/100000 [15:39:02<7:44:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 52307/100000 [15:39:03<7:44:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 52308/100000 [15:39:03<7:44:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 52309/100000 [15:39:04<7:44:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 52310/100000 [15:39:05<7:44:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 52311/100000 [15:39:05<7:45:49,  1.71it/s]
Train steps ... :  52%|█████▏    | 52312/100000 [15:39:06<7:45:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 52313/100000 [15:39:06<7:45:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 52314/100000 [15:39:07<7:45:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 52315/100000 [15:39:07<7:45:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52316/100000 [15:39:08<7:44:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 52317/100000 [15:39:09<7:44:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 52318/100000 [15:39:09<7:45:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52319/100000 [15:39:10<7:45:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52320/100000 [15:39:10<7:44:39,  1.71it/s]
Train steps ... :  52%|██��██▏    | 52321/100000 [15:39:11<7:44:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 52322/100000 [15:39:12<7:44:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 52323/100000 [15:39:12<7:44:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 52324/100000 [15:39:13<7:44:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 52325/100000 [15:39:13<7:44:17,  1.71it/s]Step... (52325 / 100000 | Loss: 0.6259605288505554, Learning Rate: 4.791457286432161e-05)
+
                                                                             
Step... (52325 / 100000 | Loss: 0.9025731086730957, Learning Rate: 4.791457286432161e-05)
+
Train steps ... :  52%|█████▏    | 52325/100000 [15:39:14<7:44:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52326/100000 [15:39:14<7:44:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52327/100000 [15:39:14<7:44:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 52328/100000 [15:39:15<7:45:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 52329/100000 [15:39:16<7:44:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 52330/100000 [15:39:16<7:44:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 52331/100000 [15:39:17<7:44:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 52332/100000 [15:39:17<7:44:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 52333/100000 [15:39:18<7:44:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 52334/100000 [15:39:19<7:43:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 52335/100000 [15:39:19<7:44:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52336/100000 [15:39:20<7:44:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 52337/100000 [15:39:20<7:44:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 52338/100000 [15:39:21<7:44:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52339/100000 [15:39:21<7:44:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 52340/100000 [15:39:22<7:44:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 52341/100000 [15:39:23<7:45:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52342/100000 [15:39:23<7:45:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 52343/100000 [15:39:24<7:45:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52344/100000 [15:39:24<7:45:45,  1.71it/s]
Train steps ... :  52%|█████▏    | 52345/100000 [15:39:25<7:44:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 52346/100000 [15:39:26<7:44:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 52347/100000 [15:39:26<7:44:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 52348/100000 [15:39:27<7:45:24,  1.71it/s]
Train steps ... :  52%|█████▏    | 52349/100000 [15:39:27<7:45:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52350/100000 [15:39:28<7:44:46,  1.71it/s]Step... (52350 / 100000 | Loss: 0.690773606300354, Learning Rate: 4.7889447236180905e-05)
+
                                                                             
Step... (52350 / 100000 | Loss: 0.7228797078132629, Learning Rate: 4.7889447236180905e-05)
+
Train steps ... :  52%|█████▏    | 52350/100000 [15:39:28<7:44:46,  1.71it/s]
Train steps ... :  52%|█████▏    | 52351/100000 [15:39:29<7:44:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 52352/100000 [15:39:29<7:43:46,  1.71it/s]
Train steps ... :  52%|█████▏    | 52353/100000 [15:39:30<7:44:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52354/100000 [15:39:30<7:44:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52355/100000 [15:39:31<7:44:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52356/100000 [15:39:31<7:44:03,  1.71it/s]
Train steps ... :  52%|█████▏    | 52357/100000 [15:39:32<7:43:40,  1.71it/s]
Train steps ... :  52%|█████▏    | 52358/100000 [15:39:33<7:43:48,  1.71it/s]
Train steps ... :  52%|█████▏    | 52359/100000 [15:39:33<7:43:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 52360/100000 [15:39:34<7:43:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 52361/100000 [15:39:34<7:44:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 52362/100000 [15:39:35<7:45:26,  1.71it/s]
Train steps ... :  52%|█████▏    | 52363/100000 [15:39:36<7:45:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52364/100000 [15:39:36<7:44:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 52365/100000 [15:39:37<7:44:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 52366/100000 [15:39:37<7:44:09,  1.71it/s]
Train steps ... :  52%|█████▏    | 52367/100000 [15:39:38<7:44:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52368/100000 [15:39:38<7:44:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52369/100000 [15:39:39<7:44:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52370/100000 [15:39:40<7:43:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 52371/100000 [15:39:40<7:44:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52372/100000 [15:39:41<7:44:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 52373/100000 [15:39:41<7:43:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52374/100000 [15:39:42<7:43:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 52375/100000 [15:39:43<7:44:00,  1.71it/s]Step... (52375 / 100000 | Loss: 0.6905298829078674, Learning Rate: 4.78643216080402e-05)
+
                                                                             
Step... (52375 / 100000 | Loss: 0.8371618986129761, Learning Rate: 4.78643216080402e-05)
+
Train steps ... :  52%|█████▏    | 52375/100000 [15:39:43<7:44:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 52376/100000 [15:39:43<7:44:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 52377/100000 [15:39:44<7:43:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 52378/100000 [15:39:44<7:44:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 52379/100000 [15:39:45<7:44:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 52380/100000 [15:39:45<7:44:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 52381/100000 [15:39:46<7:44:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 52382/100000 [15:39:47<7:43:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 52383/100000 [15:39:47<7:44:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 52384/100000 [15:39:48<7:43:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 52385/100000 [15:39:48<7:44:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52386/100000 [15:39:49<7:44:46,  1.71it/s]
Train steps ... :  52%|█████▏    | 52387/100000 [15:39:50<7:44:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 52388/100000 [15:39:50<7:44:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 52389/100000 [15:39:51<7:44:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 52390/100000 [15:39:51<7:43:52,  1.71it/s]
Train steps ... :  52%|█████▏    | 52391/100000 [15:39:52<7:43:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52392/100000 [15:39:52<7:43:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 52393/100000 [15:39:53<7:43:49,  1.71it/s]
Train steps ... :  52%|█████▏    | 52394/100000 [15:39:54<7:45:25,  1.70it/s]
Train steps ... :  52%|█████▏    | 52395/100000 [15:39:54<7:43:46,  1.71it/s]
Train steps ... :  52%|█████▏    | 52396/100000 [15:39:55<7:44:12,  1.71it/s]
Train steps ... :  52%|█████▏    | 52397/100000 [15:39:55<7:44:37,  1.71it/s]
Train steps ... :  52%|█████▏    | 52398/100000 [15:39:56<7:44:19,  1.71it/s]
Train steps ... :  52%|█████▏    | 52399/100000 [15:39:57<7:44:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52400/100000 [15:39:57<7:44:32,  1.71it/s]Step... (52400 / 100000 | Loss: 0.6936869621276855, Learning Rate: 4.78391959798995e-05)
+
                                                                             
Step... (52400 / 100000 | Loss: 0.6994937658309937, Learning Rate: 4.78391959798995e-05)
+
Train steps ... :  52%|█████▏    | 52400/100000 [15:39:57<7:44:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 52401/100000 [15:39:58<7:44:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 52402/100000 [15:39:58<7:44:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52403/100000 [15:39:59<7:44:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 52404/100000 [15:40:00<7:44:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 52405/100000 [15:40:00<7:44:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52406/100000 [15:40:01<7:43:43,  1.71it/s]
Train steps ... :  52%|█████▏    | 52407/100000 [15:40:01<7:43:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52408/100000 [15:40:02<7:43:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52409/100000 [15:40:02<7:43:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 52410/100000 [15:40:03<7:43:23,  1.71it/s]
Train steps ... :  52%|█████▏    | 52411/100000 [15:40:04<7:43:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52412/100000 [15:40:04<7:43:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52413/100000 [15:40:05<7:44:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52414/100000 [15:40:05<7:42:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52415/100000 [15:40:06<7:42:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52416/100000 [15:40:07<7:43:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 52417/100000 [15:40:07<7:42:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 52418/100000 [15:40:08<7:42:58,  1.71it/s]
Train steps ... :  52%|█████▏    | 52419/100000 [15:40:08<7:43:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 52420/100000 [15:40:09<7:43:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52421/100000 [15:40:09<7:43:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 52422/100000 [15:40:10<7:43:16,  1.71it/s]
Train steps ... :  52%|█████▏    | 52423/100000 [15:40:11<7:43:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 52424/100000 [15:40:11<7:43:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52425/100000 [15:40:12<7:43:59,  1.71it/s]Step... (52425 / 100000 | Loss: 0.7680913209915161, Learning Rate: 4.7814070351758795e-05)
+
                                                                             
Step... (52425 / 100000 | Loss: 0.9487055540084839, Learning Rate: 4.7814070351758795e-05)
+
Train steps ... :  52%|█████▏    | 52425/100000 [15:40:12<7:43:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 52426/100000 [15:40:12<7:43:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 52427/100000 [15:40:13<7:43:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 52428/100000 [15:40:14<7:43:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 52429/100000 [15:40:14<7:43:13,  1.71it/s]
Train steps ... :  52%|█████▏    | 52430/100000 [15:40:15<7:43:50,  1.71it/s]
Train steps ... :  52%|█████▏    | 52431/100000 [15:40:15<7:43:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52432/100000 [15:40:16<7:43:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52433/100000 [15:40:16<7:44:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52434/100000 [15:40:17<7:43:57,  1.71it/s]
Train steps ... :  52%|█████▏    | 52435/100000 [15:40:18<7:43:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52436/100000 [15:40:18<7:44:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52437/100000 [15:40:19<7:43:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 52438/100000 [15:40:19<7:43:30,  1.71it/s]
Train steps ... :  52%|█████▏    | 52439/100000 [15:40:20<7:43:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52440/100000 [15:40:21<7:43:45,  1.71it/s]
Train steps ... :  52%|█████▏    | 52441/100000 [15:40:21<7:43:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 52442/100000 [15:40:22<7:43:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 52443/100000 [15:40:22<7:43:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52444/100000 [15:40:23<7:43:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 52445/100000 [15:40:23<7:42:59,  1.71it/s]
Train steps ... :  52%|█████▏    | 52446/100000 [15:40:24<7:43:26,  1.71it/s]
Train steps ... :  52%|█████▏    | 52447/100000 [15:40:25<7:43:34,  1.71it/s]
Train steps ... :  52%|█████▏    | 52448/100000 [15:40:25<7:43:47,  1.71it/s]
Train steps ... :  52%|█████▏    | 52449/100000 [15:40:26<7:43:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 52450/100000 [15:40:26<7:43:39,  1.71it/s]Step... (52450 / 100000 | Loss: 0.6026496887207031, Learning Rate: 4.77889447236181e-05)
+
                                                                             
Step... (52450 / 100000 | Loss: 0.6681309938430786, Learning Rate: 4.77889447236181e-05)
+
Train steps ... :  52%|█████▏    | 52450/100000 [15:40:27<7:43:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52451/100000 [15:40:27<7:43:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 52452/100000 [15:40:28<7:43:44,  1.71it/s]
Train steps ... :  52%|█████▏    | 52453/100000 [15:40:28<7:43:29,  1.71it/s]
Train steps ... :  52%|█████▏    | 52454/100000 [15:40:29<7:43:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 52455/100000 [15:40:29<7:43:42,  1.71it/s]
Train steps ... :  52%|█████▏    | 52456/100000 [15:40:30<7:43:00,  1.71it/s]
Train steps ... :  52%|█████▏    | 52457/100000 [15:40:30<7:43:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 52458/100000 [15:40:31<7:43:10,  1.71it/s]
Train steps ... :  52%|█████▏    | 52459/100000 [15:40:32<7:43:01,  1.71it/s]
Train steps ... :  52%|█████▏    | 52460/100000 [15:40:32<7:43:07,  1.71it/s]
Train steps ... :  52%|█████▏    | 52461/100000 [15:40:33<7:43:17,  1.71it/s]
Train steps ... :  52%|█████▏    | 52462/100000 [15:40:33<7:43:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52463/100000 [15:40:34<7:43:21,  1.71it/s]
Train steps ... :  52%|█████▏    | 52464/100000 [15:40:35<7:42:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 52465/100000 [15:40:35<7:42:53,  1.71it/s]
Train steps ... :  52%|█████▏    | 52466/100000 [15:40:36<7:42:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 52467/100000 [15:40:36<7:43:31,  1.71it/s]
Train steps ... :  52%|█████▏    | 52468/100000 [15:40:37<7:43:28,  1.71it/s]
Train steps ... :  52%|█████▏    | 52469/100000 [15:40:38<7:43:11,  1.71it/s]
Train steps ... :  52%|█████▏    | 52470/100000 [15:40:38<7:42:38,  1.71it/s]
Train steps ... :  52%|█████▏    | 52471/100000 [15:40:39<7:42:33,  1.71it/s]
Train steps ... :  52%|█████▏    | 52472/100000 [15:40:39<7:42:54,  1.71it/s]
Train steps ... :  52%|█████▏    | 52473/100000 [15:40:40<7:43:08,  1.71it/s]
Train steps ... :  52%|█████▏    | 52474/100000 [15:40:40<7:43:06,  1.71it/s]
Train steps ... :  52%|█████▏    | 52475/100000 [15:40:41<7:42:51,  1.71it/s]Step... (52475 / 100000 | Loss: 0.952096164226532, Learning Rate: 4.776381909547739e-05)
+
                                                                             
Step... (52475 / 100000 | Loss: 0.8014791011810303, Learning Rate: 4.776381909547739e-05)
+
Train steps ... :  52%|█████▏    | 52475/100000 [15:40:41<7:42:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52476/100000 [15:40:42<7:42:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52477/100000 [15:40:42<7:42:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 52478/100000 [15:40:43<7:42:56,  1.71it/s]
Train steps ... :  52%|█████▏    | 52479/100000 [15:40:43<7:42:32,  1.71it/s]
Train steps ... :  52%|█████▏    | 52480/100000 [15:40:44<7:42:41,  1.71it/s]
Train steps ... :  52%|█████▏    | 52481/100000 [15:40:45<7:43:02,  1.71it/s]
Train steps ... :  52%|█████▏    | 52482/100000 [15:40:45<7:43:14,  1.71it/s]
Train steps ... :  52%|█████▏    | 52483/100000 [15:40:46<7:43:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52484/100000 [15:40:46<7:43:18,  1.71it/s]
Train steps ... :  52%|█████▏    | 52485/100000 [15:40:47<7:44:44,  1.70it/s]
Train steps ... :  52%|█████▏    | 52486/100000 [15:40:47<7:44:05,  1.71it/s]
Train steps ... :  52%|█████▏    | 52487/100000 [15:40:48<7:44:27,  1.70it/s]
Train steps ... :  52%|█████▏    | 52488/100000 [15:40:49<7:43:25,  1.71it/s]
Train steps ... :  52%|█████▏    | 52489/100000 [15:40:49<7:43:27,  1.71it/s]
Train steps ... :  52%|█████▏    | 52490/100000 [15:40:50<7:43:04,  1.71it/s]
Train steps ... :  52%|█████▏    | 52491/100000 [15:40:50<7:43:20,  1.71it/s]
Train steps ... :  52%|█████▏    | 52492/100000 [15:40:51<7:42:51,  1.71it/s]
Train steps ... :  52%|█████▏    | 52493/100000 [15:40:52<7:42:35,  1.71it/s]
Train steps ... :  52%|█████▏    | 52494/100000 [15:40:52<7:42:36,  1.71it/s]
Train steps ... :  52%|█████▏    | 52495/100000 [15:40:53<7:42:49,  1.71it/s]
Train steps ... :  52%|█████▏    | 52496/100000 [15:40:53<7:42:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52497/100000 [15:40:54<7:42:39,  1.71it/s]
Train steps ... :  52%|█████▏    | 52498/100000 [15:40:54<7:42:55,  1.71it/s]
Train steps ... :  52%|█████▏    | 52499/100000 [15:40:55<7:42:36,  1.71it/s]
Train steps ... :  52%|█████▎    | 52500/100000 [15:40:56<7:43:21,  1.71it/s]Step... (52500 / 100000 | Loss: 1.1107707023620605, Learning Rate: 4.7738693467336685e-05)
+
                                                                             
Step... (52500 / 100000 | Loss: 0.6278119087219238, Learning Rate: 4.7738693467336685e-05)
+
Train steps ... :  52%|█████▎    | 52500/100000 [15:40:56<7:43:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 52501/100000 [15:40:56<7:42:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 52502/100000 [15:40:57<7:42:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 52503/100000 [15:40:57<7:42:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 52504/100000 [15:40:58<7:42:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 52505/100000 [15:40:59<7:42:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 52506/100000 [15:40:59<7:42:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52507/100000 [15:41:00<7:42:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 52508/100000 [15:41:00<7:42:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52509/100000 [15:41:01<7:42:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52510/100000 [15:41:01<7:42:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 52511/100000 [15:41:02<7:42:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52512/100000 [15:41:03<7:42:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 52513/100000 [15:41:03<7:42:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 52514/100000 [15:41:04<7:42:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52515/100000 [15:41:04<7:42:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 52516/100000 [15:41:05<7:42:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 52517/100000 [15:41:06<7:42:41,  1.71it/s]
Train steps ... :  53%|█████▎    | 52518/100000 [15:41:06<7:42:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 52519/100000 [15:41:07<7:42:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52520/100000 [15:41:07<7:42:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52521/100000 [15:41:08<7:42:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52522/100000 [15:41:08<7:42:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 52523/100000 [15:41:09<7:42:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 52524/100000 [15:41:10<7:42:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 52525/100000 [15:41:10<7:43:02,  1.71it/s]Step... (52525 / 100000 | Loss: 0.7707740068435669, Learning Rate: 4.771356783919598e-05)
+
                                                                             
Step... (52525 / 100000 | Loss: 0.7308107614517212, Learning Rate: 4.771356783919598e-05)
+
Train steps ... :  53%|█████▎    | 52525/100000 [15:41:11<7:43:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 52526/100000 [15:41:11<7:43:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52527/100000 [15:41:11<7:43:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 52528/100000 [15:41:12<7:42:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 52529/100000 [15:41:13<7:43:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52530/100000 [15:41:13<7:42:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 52531/100000 [15:41:14<7:42:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52532/100000 [15:41:14<7:42:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 52533/100000 [15:41:15<7:42:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 52534/100000 [15:41:16<7:42:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52535/100000 [15:41:16<7:41:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52536/100000 [15:41:17<7:42:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 52537/100000 [15:41:17<7:42:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52538/100000 [15:41:18<7:42:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52539/100000 [15:41:18<7:42:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52540/100000 [15:41:19<7:42:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 52541/100000 [15:41:20<7:42:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52542/100000 [15:41:20<7:42:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 52543/100000 [15:41:21<7:42:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 52544/100000 [15:41:21<7:43:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52545/100000 [15:41:22<7:42:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 52546/100000 [15:41:23<7:42:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 52547/100000 [15:41:23<7:43:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 52548/100000 [15:41:24<7:42:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52549/100000 [15:41:24<7:43:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52550/100000 [15:41:25<7:42:52,  1.71it/s]Step... (52550 / 100000 | Loss: 0.9450297951698303, Learning Rate: 4.768844221105528e-05)
+
                                                                             
Step... (52550 / 100000 | Loss: 0.6027633547782898, Learning Rate: 4.768844221105528e-05)
+
Train steps ... :  53%|█████▎    | 52550/100000 [15:41:25<7:42:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 52551/100000 [15:41:25<7:42:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 52552/100000 [15:41:26<7:42:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 52553/100000 [15:41:27<7:42:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52554/100000 [15:41:27<7:42:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 52555/100000 [15:41:28<7:42:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52556/100000 [15:41:28<7:42:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 52557/100000 [15:41:29<7:43:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52558/100000 [15:41:30<7:42:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52559/100000 [15:41:30<7:43:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 52560/100000 [15:41:31<7:42:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52561/100000 [15:41:31<7:42:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52562/100000 [15:41:32<7:42:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52563/100000 [15:41:32<7:42:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52564/100000 [15:41:33<7:41:59,  1.71it/s]
Train steps ... :  53%|█████▎    | 52565/100000 [15:41:34<7:41:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 52566/100000 [15:41:34<7:41:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 52567/100000 [15:41:35<7:41:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 52568/100000 [15:41:35<7:43:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 52569/100000 [15:41:36<7:42:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52570/100000 [15:41:37<7:42:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 52571/100000 [15:41:37<7:42:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 52572/100000 [15:41:38<7:42:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 52573/100000 [15:41:38<7:42:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 52574/100000 [15:41:39<7:42:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52575/100000 [15:41:39<7:41:57,  1.71it/s]Step... (52575 / 100000 | Loss: 0.6686316728591919, Learning Rate: 4.7663316582914575e-05)
+
                                                                             
Step... (52575 / 100000 | Loss: 0.8912545442581177, Learning Rate: 4.7663316582914575e-05)
+
Train steps ... :  53%|█████▎    | 52575/100000 [15:41:40<7:41:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 52576/100000 [15:41:40<7:41:41,  1.71it/s]
Train steps ... :  53%|█████▎    | 52577/100000 [15:41:41<7:42:11,  1.71it/s]
Train steps ... :  53%|█████▎    | 52578/100000 [15:41:41<7:42:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 52579/100000 [15:41:42<7:42:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 52580/100000 [15:41:42<7:42:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52581/100000 [15:41:43<7:42:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 52582/100000 [15:41:44<7:41:46,  1.71it/s]
Train steps ... :  53%|█████▎    | 52583/100000 [15:41:44<7:41:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52584/100000 [15:41:45<7:41:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 52585/100000 [15:41:45<7:41:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 52586/100000 [15:41:46<7:42:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52587/100000 [15:41:47<7:42:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 52588/100000 [15:41:47<7:41:51,  1.71it/s]
Train steps ... :  53%|█████▎    | 52589/100000 [15:41:48<7:42:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 52590/100000 [15:41:48<7:42:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 52591/100000 [15:41:49<7:42:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 52592/100000 [15:41:49<7:42:11,  1.71it/s]
Train steps ... :  53%|█████▎    | 52593/100000 [15:41:50<7:42:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 52594/100000 [15:41:51<7:41:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52595/100000 [15:41:51<7:41:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52596/100000 [15:41:52<7:42:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52597/100000 [15:41:52<7:41:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52598/100000 [15:41:53<7:42:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 52599/100000 [15:41:54<7:42:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52600/100000 [15:41:54<7:43:22,  1.70it/s]Step... (52600 / 100000 | Loss: 0.6566155552864075, Learning Rate: 4.763819095477387e-05)
+
                                                                             
Step... (52600 / 100000 | Loss: 0.9122857451438904, Learning Rate: 4.763819095477387e-05)
+
Train steps ... :  53%|█████▎    | 52600/100000 [15:41:54<7:43:22,  1.70it/s]
Train steps ... :  53%|█████▎    | 52601/100000 [15:41:55<7:42:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52602/100000 [15:41:55<7:41:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 52603/100000 [15:41:56<7:42:09,  1.71it/s]
Train steps ... :  53%|█████▎    | 52604/100000 [15:41:56<7:41:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52605/100000 [15:41:57<7:41:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52606/100000 [15:41:58<7:41:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52607/100000 [15:41:58<7:41:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 52608/100000 [15:41:59<7:41:46,  1.71it/s]
Train steps ... :  53%|█████▎    | 52609/100000 [15:41:59<7:41:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 52610/100000 [15:42:00<7:41:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 52611/100000 [15:42:01<7:41:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 52612/100000 [15:42:01<7:42:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 52613/100000 [15:42:02<7:41:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 52614/100000 [15:42:02<7:41:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52615/100000 [15:42:03<7:42:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 52616/100000 [15:42:03<7:42:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 52617/100000 [15:42:04<7:42:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 52618/100000 [15:42:05<7:42:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 52619/100000 [15:42:05<7:42:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52620/100000 [15:42:06<7:41:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 52621/100000 [15:42:06<7:42:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52622/100000 [15:42:07<7:42:16,  1.71it/s]
Train steps ... :  53%|█████▎    | 52623/100000 [15:42:08<7:42:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 52624/100000 [15:42:08<7:42:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52625/100000 [15:42:09<7:42:27,  1.71it/s]Step... (52625 / 100000 | Loss: 0.6753696799278259, Learning Rate: 4.761306532663317e-05)
+
                                                                             
Step... (52625 / 100000 | Loss: 0.7021828889846802, Learning Rate: 4.761306532663317e-05)
+
Train steps ... :  53%|█████▎    | 52625/100000 [15:42:09<7:42:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 52626/100000 [15:42:09<7:42:41,  1.71it/s]
Train steps ... :  53%|█████▎    | 52627/100000 [15:42:10<7:42:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52628/100000 [15:42:10<7:41:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 52629/100000 [15:42:11<7:41:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 52630/100000 [15:42:12<7:40:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 52631/100000 [15:42:12<7:41:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 52632/100000 [15:42:13<7:41:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 52633/100000 [15:42:13<7:40:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 52634/100000 [15:42:14<7:40:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 52635/100000 [15:42:15<7:40:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 52636/100000 [15:42:15<7:40:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 52637/100000 [15:42:16<7:42:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 52638/100000 [15:42:16<7:41:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 52639/100000 [15:42:17<7:41:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52640/100000 [15:42:18<7:41:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52641/100000 [15:42:18<7:41:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 52642/100000 [15:42:19<7:41:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 52643/100000 [15:42:19<7:41:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 52644/100000 [15:42:20<7:41:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 52645/100000 [15:42:20<7:41:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 52646/100000 [15:42:21<7:41:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 52647/100000 [15:42:22<7:41:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 52648/100000 [15:42:22<7:41:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 52649/100000 [15:42:23<7:42:11,  1.71it/s]
Train steps ... :  53%|█████▎    | 52650/100000 [15:42:23<7:40:54,  1.71it/s]Step... (52650 / 100000 | Loss: 0.8058227300643921, Learning Rate: 4.7587939698492464e-05)
+
                                                                             
Step... (52650 / 100000 | Loss: 0.7684469223022461, Learning Rate: 4.7587939698492464e-05)
+
Train steps ... :  53%|█████▎    | 52650/100000 [15:42:24<7:40:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52651/100000 [15:42:24<7:41:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 52652/100000 [15:42:25<7:40:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 52653/100000 [15:42:25<7:41:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 52654/100000 [15:42:26<7:40:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52655/100000 [15:42:26<7:40:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52656/100000 [15:42:27<7:40:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 52657/100000 [15:42:27<7:40:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 52658/100000 [15:42:28<7:40:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 52659/100000 [15:42:29<7:40:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52660/100000 [15:42:29<7:41:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52661/100000 [15:42:30<7:42:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 52662/100000 [15:42:30<7:42:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 52663/100000 [15:42:31<7:41:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 52664/100000 [15:42:32<7:41:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 52665/100000 [15:42:32<7:41:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52666/100000 [15:42:33<7:41:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 52667/100000 [15:42:33<7:41:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 52668/100000 [15:42:34<7:41:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 52669/100000 [15:42:34<7:41:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52670/100000 [15:42:35<7:41:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 52671/100000 [15:42:36<7:41:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 52672/100000 [15:42:36<7:40:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 52673/100000 [15:42:37<7:41:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 52674/100000 [15:42:37<7:40:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52675/100000 [15:42:38<7:40:47,  1.71it/s]Step... (52675 / 100000 | Loss: 0.6049081087112427, Learning Rate: 4.756281407035176e-05)
+
                                                                             
Step... (52675 / 100000 | Loss: 0.686221718788147, Learning Rate: 4.756281407035176e-05)
+
Train steps ... :  53%|█████▎    | 52675/100000 [15:42:38<7:40:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52676/100000 [15:42:39<7:41:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52677/100000 [15:42:39<7:40:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52678/100000 [15:42:40<7:40:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52679/100000 [15:42:40<7:40:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 52680/100000 [15:42:41<7:40:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 52681/100000 [15:42:41<7:40:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 52682/100000 [15:42:42<7:41:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 52683/100000 [15:42:43<7:41:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 52684/100000 [15:42:43<7:41:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52685/100000 [15:42:44<7:41:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 52686/100000 [15:42:44<7:41:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 52687/100000 [15:42:45<7:41:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52688/100000 [15:42:46<7:41:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 52689/100000 [15:42:46<7:41:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52690/100000 [15:42:47<7:41:16,  1.71it/s]
Train steps ... :  53%|█████▎    | 52691/100000 [15:42:47<7:40:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 52692/100000 [15:42:48<7:41:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52693/100000 [15:42:48<7:41:08,  1.71it/s]
Train steps ... :  53%|█████▎    | 52694/100000 [15:42:49<7:41:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 52695/100000 [15:42:50<7:40:59,  1.71it/s]
Train steps ... :  53%|█████▎    | 52696/100000 [15:42:50<7:40:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52697/100000 [15:42:51<7:40:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52698/100000 [15:42:51<7:40:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52699/100000 [15:42:52<7:40:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 52700/100000 [15:42:53<7:40:33,  1.71it/s]Step... (52700 / 100000 | Loss: 0.6018903255462646, Learning Rate: 4.753768844221106e-05)
+
                                                                             
Step... (52700 / 100000 | Loss: 0.6554933190345764, Learning Rate: 4.753768844221106e-05)
+
Train steps ... :  53%|█████▎    | 52700/100000 [15:42:53<7:40:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 52701/100000 [15:42:53<7:40:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 52702/100000 [15:42:54<7:41:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 52703/100000 [15:42:54<7:40:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 52704/100000 [15:42:55<7:42:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 52705/100000 [15:42:55<7:40:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 52706/100000 [15:42:56<7:41:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 52707/100000 [15:42:57<7:40:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 52708/100000 [15:42:57<7:40:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 52709/100000 [15:42:58<7:40:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 52710/100000 [15:42:58<7:40:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 52711/100000 [15:42:59<7:41:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 52712/100000 [15:43:00<7:40:59,  1.71it/s]
Train steps ... :  53%|█████▎    | 52713/100000 [15:43:00<7:40:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52714/100000 [15:43:01<7:40:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52715/100000 [15:43:01<7:40:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52716/100000 [15:43:02<7:40:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 52717/100000 [15:43:03<7:40:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 52718/100000 [15:43:03<7:40:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52719/100000 [15:43:04<7:40:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52720/100000 [15:43:04<7:40:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52721/100000 [15:43:05<7:40:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 52722/100000 [15:43:05<7:40:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52723/100000 [15:43:06<7:40:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 52724/100000 [15:43:07<7:40:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 52725/100000 [15:43:07<7:40:02,  1.71it/s]Step... (52725 / 100000 | Loss: 0.6151479482650757, Learning Rate: 4.7512562814070354e-05)
+
                                                                             
Step... (52725 / 100000 | Loss: 0.6016151905059814, Learning Rate: 4.7512562814070354e-05)
+
Train steps ... :  53%|█████▎    | 52725/100000 [15:43:08<7:40:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 52726/100000 [15:43:08<7:40:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52727/100000 [15:43:08<7:40:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 52728/100000 [15:43:09<7:41:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 52729/100000 [15:43:10<7:40:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52730/100000 [15:43:10<7:40:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 52731/100000 [15:43:11<7:41:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 52732/100000 [15:43:11<7:39:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 52733/100000 [15:43:12<7:41:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52734/100000 [15:43:12<7:40:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 52735/100000 [15:43:13<7:40:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 52736/100000 [15:43:14<7:39:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52737/100000 [15:43:14<7:39:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 52738/100000 [15:43:15<7:39:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 52739/100000 [15:43:15<7:39:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 52740/100000 [15:43:16<7:40:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 52741/100000 [15:43:17<7:40:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 52742/100000 [15:43:17<7:40:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 52743/100000 [15:43:18<7:40:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52744/100000 [15:43:18<7:40:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52745/100000 [15:43:19<7:40:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52746/100000 [15:43:19<7:40:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52747/100000 [15:43:20<7:40:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52748/100000 [15:43:21<7:40:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52749/100000 [15:43:21<7:40:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52750/100000 [15:43:22<7:40:43,  1.71it/s]Step... (52750 / 100000 | Loss: 0.6725336313247681, Learning Rate: 4.748743718592965e-05)
+
                                                                             
Step... (52750 / 100000 | Loss: 0.8473876714706421, Learning Rate: 4.748743718592965e-05)
+
Train steps ... :  53%|█████▎    | 52750/100000 [15:43:22<7:40:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 52751/100000 [15:43:22<7:40:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 52752/100000 [15:43:23<7:40:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52753/100000 [15:43:24<7:41:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52754/100000 [15:43:24<7:41:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 52755/100000 [15:43:25<7:40:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 52756/100000 [15:43:25<7:40:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 52757/100000 [15:43:26<7:40:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52758/100000 [15:43:26<7:39:59,  1.71it/s]
Train steps ... :  53%|█████▎    | 52759/100000 [15:43:27<7:40:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 52760/100000 [15:43:28<7:40:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52761/100000 [15:43:28<7:40:16,  1.71it/s]
Train steps ... :  53%|█████▎    | 52762/100000 [15:43:29<7:40:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 52763/100000 [15:43:29<7:39:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52764/100000 [15:43:30<7:40:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 52765/100000 [15:43:31<7:40:51,  1.71it/s]
Train steps ... :  53%|█████▎    | 52766/100000 [15:43:31<7:40:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52767/100000 [15:43:32<7:40:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 52768/100000 [15:43:32<7:40:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 52769/100000 [15:43:33<7:40:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 52770/100000 [15:43:34<7:40:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52771/100000 [15:43:34<7:40:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 52772/100000 [15:43:35<7:40:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 52773/100000 [15:43:35<7:40:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 52774/100000 [15:43:36<7:40:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52775/100000 [15:43:36<7:40:52,  1.71it/s]Step... (52775 / 100000 | Loss: 0.8366479277610779, Learning Rate: 4.746231155778895e-05)
+
                                                                             
Step... (52775 / 100000 | Loss: 0.8088909983634949, Learning Rate: 4.746231155778895e-05)
+
Train steps ... :  53%|█████▎    | 52775/100000 [15:43:37<7:40:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 52776/100000 [15:43:37<7:41:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 52777/100000 [15:43:38<7:40:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 52778/100000 [15:43:38<7:40:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52779/100000 [15:43:39<7:40:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 52780/100000 [15:43:39<7:40:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 52781/100000 [15:43:40<7:39:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52782/100000 [15:43:41<7:40:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52783/100000 [15:43:41<7:40:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52784/100000 [15:43:42<7:40:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52785/100000 [15:43:42<7:40:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52786/100000 [15:43:43<7:40:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52787/100000 [15:43:43<7:39:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52788/100000 [15:43:44<7:40:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52789/100000 [15:43:45<7:40:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 52790/100000 [15:43:45<7:40:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52791/100000 [15:43:46<7:40:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 52792/100000 [15:43:46<7:40:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 52793/100000 [15:43:47<7:40:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 52794/100000 [15:43:48<7:40:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52795/100000 [15:43:48<7:39:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 52796/100000 [15:43:49<7:39:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 52797/100000 [15:43:49<7:39:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52798/100000 [15:43:50<7:39:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 52799/100000 [15:43:50<7:40:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 52800/100000 [15:43:51<7:40:15,  1.71it/s]Step... (52800 / 100000 | Loss: 0.6537817716598511, Learning Rate: 4.7437185929648244e-05)
+
                                                                             
Step... (52800 / 100000 | Loss: 0.6430398225784302, Learning Rate: 4.7437185929648244e-05)
+
Train steps ... :  53%|█████▎    | 52800/100000 [15:43:51<7:40:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 52801/100000 [15:43:52<7:39:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 52802/100000 [15:43:52<7:40:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 52803/100000 [15:43:53<7:39:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 52804/100000 [15:43:53<7:40:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52805/100000 [15:43:54<7:40:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 52806/100000 [15:43:55<7:40:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 52807/100000 [15:43:55<7:40:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 52808/100000 [15:43:56<7:39:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52809/100000 [15:43:56<7:40:16,  1.71it/s]
Train steps ... :  53%|█████▎    | 52810/100000 [15:43:57<7:39:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 52811/100000 [15:43:57<7:39:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 52812/100000 [15:43:58<7:39:51,  1.71it/s]
Train steps ... :  53%|█████▎    | 52813/100000 [15:43:59<7:40:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 52814/100000 [15:43:59<7:39:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 52815/100000 [15:44:00<7:39:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 52816/100000 [15:44:00<7:40:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52817/100000 [15:44:01<7:40:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 52818/100000 [15:44:02<7:40:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52819/100000 [15:44:02<7:39:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 52820/100000 [15:44:03<7:40:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 52821/100000 [15:44:03<7:40:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52822/100000 [15:44:04<7:40:11,  1.71it/s]
Train steps ... :  53%|█████▎    | 52823/100000 [15:44:05<7:40:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52824/100000 [15:44:05<7:40:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 52825/100000 [15:44:06<7:40:09,  1.71it/s]Step... (52825 / 100000 | Loss: 0.6341897249221802, Learning Rate: 4.741206030150754e-05)
+
                                                                             
Step... (52825 / 100000 | Loss: 0.6185973882675171, Learning Rate: 4.741206030150754e-05)
+
Train steps ... :  53%|█████▎    | 52825/100000 [15:44:06<7:40:09,  1.71it/s]
Train steps ... :  53%|█████▎    | 52826/100000 [15:44:06<7:40:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 52827/100000 [15:44:07<7:40:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 52828/100000 [15:44:07<7:40:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52829/100000 [15:44:08<7:40:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52830/100000 [15:44:09<7:40:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 52831/100000 [15:44:09<7:40:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52832/100000 [15:44:10<7:39:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 52833/100000 [15:44:10<7:39:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 52834/100000 [15:44:11<7:39:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 52835/100000 [15:44:12<7:39:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 52836/100000 [15:44:12<7:39:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 52837/100000 [15:44:13<7:39:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 52838/100000 [15:44:13<7:39:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 52839/100000 [15:44:14<7:39:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 52840/100000 [15:44:14<7:39:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 52841/100000 [15:44:15<7:38:59,  1.71it/s]
Train steps ... :  53%|█████▎    | 52842/100000 [15:44:16<7:39:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52843/100000 [15:44:16<7:39:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52844/100000 [15:44:17<7:39:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 52845/100000 [15:44:17<7:39:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 52846/100000 [15:44:18<7:39:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 52847/100000 [15:44:19<7:39:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52848/100000 [15:44:19<7:39:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 52849/100000 [15:44:20<7:39:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52850/100000 [15:44:20<7:40:36,  1.71it/s]Step... (52850 / 100000 | Loss: 0.7742527723312378, Learning Rate: 4.738693467336683e-05)
+
                                                                             
Step... (52850 / 100000 | Loss: 0.6139201521873474, Learning Rate: 4.738693467336683e-05)
+
Train steps ... :  53%|█████▎    | 52850/100000 [15:44:21<7:40:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 52851/100000 [15:44:21<7:40:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 52852/100000 [15:44:21<7:39:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 52853/100000 [15:44:22<7:40:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52854/100000 [15:44:23<7:40:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 52855/100000 [15:44:23<7:40:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 52856/100000 [15:44:24<7:39:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52857/100000 [15:44:24<7:39:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52858/100000 [15:44:25<7:39:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 52859/100000 [15:44:26<7:39:46,  1.71it/s]
Train steps ... :  53%|█████▎    | 52860/100000 [15:44:26<7:40:55,  1.70it/s]
Train steps ... :  53%|���████▎    | 52861/100000 [15:44:27<7:40:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 52862/100000 [15:44:27<7:40:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52863/100000 [15:44:28<7:40:08,  1.71it/s]
Train steps ... :  53%|█████▎    | 52864/100000 [15:44:29<7:39:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 52865/100000 [15:44:29<7:39:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 52866/100000 [15:44:30<7:39:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52867/100000 [15:44:30<7:39:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 52868/100000 [15:44:31<7:39:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 52869/100000 [15:44:31<7:39:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 52870/100000 [15:44:32<7:39:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52871/100000 [15:44:33<7:39:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 52872/100000 [15:44:33<7:39:46,  1.71it/s]
Train steps ... :  53%|█████▎    | 52873/100000 [15:44:34<7:39:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52874/100000 [15:44:34<7:39:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 52875/100000 [15:44:35<7:39:37,  1.71it/s]Step... (52875 / 100000 | Loss: 0.8777090311050415, Learning Rate: 4.7361809045226134e-05)
+
                                                                             
Step... (52875 / 100000 | Loss: 0.6436929106712341, Learning Rate: 4.7361809045226134e-05)
+
Train steps ... :  53%|█████▎    | 52875/100000 [15:44:35<7:39:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 52876/100000 [15:44:36<7:40:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52877/100000 [15:44:36<7:40:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 52878/100000 [15:44:37<7:39:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52879/100000 [15:44:37<7:39:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 52880/100000 [15:44:38<7:39:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52881/100000 [15:44:38<7:39:08,  1.71it/s]
Train steps ... :  53%|█████▎    | 52882/100000 [15:44:39<7:39:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 52883/100000 [15:44:40<7:40:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 52884/100000 [15:44:40<7:38:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52885/100000 [15:44:41<7:39:11,  1.71it/s]
Train steps ... :  53%|█████▎    | 52886/100000 [15:44:41<7:39:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 52887/100000 [15:44:42<7:39:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 52888/100000 [15:44:43<7:39:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52889/100000 [15:44:43<7:39:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 52890/100000 [15:44:44<7:39:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 52891/100000 [15:44:44<7:38:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52892/100000 [15:44:45<7:38:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52893/100000 [15:44:45<7:39:09,  1.71it/s]
Train steps ... :  53%|█████▎    | 52894/100000 [15:44:46<7:38:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 52895/100000 [15:44:47<7:39:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 52896/100000 [15:44:47<7:39:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 52897/100000 [15:44:48<7:38:41,  1.71it/s]
Train steps ... :  53%|█████▎    | 52898/100000 [15:44:48<7:38:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 52899/100000 [15:44:49<7:38:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52900/100000 [15:44:50<7:39:20,  1.71it/s]Step... (52900 / 100000 | Loss: 0.5607756972312927, Learning Rate: 4.733668341708543e-05)
+
                                                                             
Step... (52900 / 100000 | Loss: 0.6324316263198853, Learning Rate: 4.733668341708543e-05)
+
Train steps ... :  53%|█████▎    | 52900/100000 [15:44:50<7:39:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 52901/100000 [15:44:50<7:39:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 52902/100000 [15:44:51<7:39:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 52903/100000 [15:44:51<7:38:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 52904/100000 [15:44:52<7:38:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 52905/100000 [15:44:52<7:39:51,  1.71it/s]
Train steps ... :  53%|█████▎    | 52906/100000 [15:44:53<7:39:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52907/100000 [15:44:54<7:39:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52908/100000 [15:44:54<7:38:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 52909/100000 [15:44:55<7:39:50,  1.71it/s]
Train steps ... :  53%|██���██▎    | 52910/100000 [15:44:55<7:40:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 52911/100000 [15:44:56<7:40:24,  1.70it/s]
Train steps ... :  53%|█████▎    | 52912/100000 [15:44:57<7:39:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52913/100000 [15:44:57<7:39:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 52914/100000 [15:44:58<7:39:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 52915/100000 [15:44:58<7:38:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52916/100000 [15:44:59<7:38:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 52917/100000 [15:45:00<7:38:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 52918/100000 [15:45:00<7:38:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 52919/100000 [15:45:01<7:38:11,  1.71it/s]
Train steps ... :  53%|█████▎    | 52920/100000 [15:45:01<7:38:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52921/100000 [15:45:02<7:38:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52922/100000 [15:45:02<7:38:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 52923/100000 [15:45:03<7:38:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 52924/100000 [15:45:04<7:38:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 52925/100000 [15:45:04<7:38:39,  1.71it/s]Step... (52925 / 100000 | Loss: 0.729918360710144, Learning Rate: 4.731155778894473e-05)
+
                                                                             
Step... (52925 / 100000 | Loss: 1.0454586744308472, Learning Rate: 4.731155778894473e-05)
+
Train steps ... :  53%|█████▎    | 52925/100000 [15:45:05<7:38:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 52926/100000 [15:45:05<7:39:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 52927/100000 [15:45:05<7:38:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 52928/100000 [15:45:06<7:38:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 52929/100000 [15:45:07<7:38:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52930/100000 [15:45:07<7:38:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 52931/100000 [15:45:08<7:38:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52932/100000 [15:45:08<7:38:16,  1.71it/s]
Train steps ... :  53%|█████▎    | 52933/100000 [15:45:09<7:38:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52934/100000 [15:45:09<7:38:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52935/100000 [15:45:10<7:38:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 52936/100000 [15:45:11<7:38:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52937/100000 [15:45:11<7:38:51,  1.71it/s]
Train steps ... :  53%|█████▎    | 52938/100000 [15:45:12<7:39:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52939/100000 [15:45:12<7:38:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 52940/100000 [15:45:13<7:38:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 52941/100000 [15:45:14<7:38:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 52942/100000 [15:45:14<7:38:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 52943/100000 [15:45:15<7:38:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 52944/100000 [15:45:15<7:38:46,  1.71it/s]
Train steps ... :  53%|█████▎    | 52945/100000 [15:45:16<7:38:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 52946/100000 [15:45:16<7:39:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 52947/100000 [15:45:17<7:38:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52948/100000 [15:45:18<7:38:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 52949/100000 [15:45:18<7:38:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 52950/100000 [15:45:19<7:38:25,  1.71it/s]Step... (52950 / 100000 | Loss: 0.8632861375808716, Learning Rate: 4.7286432160804024e-05)
+
                                                                             
Step... (52950 / 100000 | Loss: 0.7731890678405762, Learning Rate: 4.7286432160804024e-05)
+
Train steps ... :  53%|█████▎    | 52950/100000 [15:45:19<7:38:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 52951/100000 [15:45:19<7:38:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52952/100000 [15:45:20<7:38:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52953/100000 [15:45:21<7:38:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 52954/100000 [15:45:21<7:38:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 52955/100000 [15:45:22<7:38:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 52956/100000 [15:45:22<7:38:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 52957/100000 [15:45:23<7:38:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 52958/100000 [15:45:23<7:38:31,  1.71it/s]
Train steps ... :  53%|████��▎    | 52959/100000 [15:45:24<7:38:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 52960/100000 [15:45:25<7:38:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 52961/100000 [15:45:25<7:38:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 52962/100000 [15:45:26<7:37:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 52963/100000 [15:45:26<7:39:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 52964/100000 [15:45:27<7:38:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 52965/100000 [15:45:28<7:37:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 52966/100000 [15:45:28<7:38:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52967/100000 [15:45:29<7:37:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 52968/100000 [15:45:29<7:37:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 52969/100000 [15:45:30<7:37:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 52970/100000 [15:45:30<7:37:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 52971/100000 [15:45:31<7:37:51,  1.71it/s]
Train steps ... :  53%|█████▎    | 52972/100000 [15:45:32<7:38:08,  1.71it/s]
Train steps ... :  53%|█████▎    | 52973/100000 [15:45:32<7:37:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 52974/100000 [15:45:33<7:37:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 52975/100000 [15:45:33<7:37:57,  1.71it/s]Step... (52975 / 100000 | Loss: 0.6590198874473572, Learning Rate: 4.726130653266332e-05)
+
                                                                             
Step... (52975 / 100000 | Loss: 0.6700195074081421, Learning Rate: 4.726130653266332e-05)
+
Train steps ... :  53%|█████▎    | 52975/100000 [15:45:34<7:37:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 52976/100000 [15:45:34<7:38:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52977/100000 [15:45:35<7:38:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 52978/100000 [15:45:35<7:38:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 52979/100000 [15:45:36<7:38:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 52980/100000 [15:45:36<7:38:16,  1.71it/s]
Train steps ... :  53%|█████▎    | 52981/100000 [15:45:37<7:38:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 52982/100000 [15:45:38<7:39:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 52983/100000 [15:45:38<7:38:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 52984/100000 [15:45:39<7:38:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 52985/100000 [15:45:39<7:37:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 52986/100000 [15:45:40<7:38:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 52987/100000 [15:45:40<7:37:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 52988/100000 [15:45:41<7:37:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 52989/100000 [15:45:42<7:37:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 52990/100000 [15:45:42<7:37:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 52991/100000 [15:45:43<7:37:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 52992/100000 [15:45:43<7:38:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52993/100000 [15:45:44<7:37:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 52994/100000 [15:45:45<7:37:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52995/100000 [15:45:45<7:37:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 52996/100000 [15:45:46<7:37:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 52997/100000 [15:45:46<7:37:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 52998/100000 [15:45:47<7:37:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 52999/100000 [15:45:47<7:39:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 53000/100000 [15:45:48<7:38:00,  1.71it/s]Step... (53000 / 100000 | Loss: 0.9299881458282471, Learning Rate: 4.723618090452262e-05)
+
                                                                             
Step... (53000 / 100000 | Loss: 0.7603649497032166, Learning Rate: 4.723618090452262e-05)
+
Train steps ... :  53%|█████▎    | 53000/100000 [15:45:48<7:38:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 53001/100000 [15:45:49<7:38:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 53002/100000 [15:45:49<7:38:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 53003/100000 [15:45:50<7:38:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53004/100000 [15:45:50<7:37:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53005/100000 [15:45:51<7:37:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 53006/100000 [15:45:52<7:37:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 53007/100000 [15:45:52<7:38:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 53008/100000 [15:45:53<7:37:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53009/100000 [15:45:53<7:37:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53010/100000 [15:45:54<7:37:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53011/100000 [15:45:54<7:37:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 53012/100000 [15:45:55<7:37:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 53013/100000 [15:45:56<7:37:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53014/100000 [15:45:56<7:38:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 53015/100000 [15:45:57<7:38:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 53016/100000 [15:45:57<7:38:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 53017/100000 [15:45:58<7:37:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 53018/100000 [15:45:59<7:37:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 53019/100000 [15:45:59<7:37:16,  1.71it/s]
Train steps ... :  53%|█████▎    | 53020/100000 [15:46:00<7:37:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53021/100000 [15:46:00<7:37:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53022/100000 [15:46:01<7:37:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 53023/100000 [15:46:01<7:37:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 53024/100000 [15:46:02<7:37:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53025/100000 [15:46:03<7:37:58,  1.71it/s]Step... (53025 / 100000 | Loss: 0.5894007086753845, Learning Rate: 4.721105527638191e-05)
+
                                                                             
Step... (53025 / 100000 | Loss: 0.6643481254577637, Learning Rate: 4.721105527638191e-05)
+
Train steps ... :  53%|█████▎    | 53025/100000 [15:46:03<7:37:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 53026/100000 [15:46:03<7:38:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53027/100000 [15:46:04<7:37:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53028/100000 [15:46:04<7:38:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 53029/100000 [15:46:05<7:38:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53030/100000 [15:46:06<7:37:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 53031/100000 [15:46:06<7:37:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 53032/100000 [15:46:07<7:37:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53033/100000 [15:46:07<7:37:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 53034/100000 [15:46:08<7:37:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53035/100000 [15:46:08<7:37:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 53036/100000 [15:46:09<7:37:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53037/100000 [15:46:10<7:37:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53038/100000 [15:46:10<7:37:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 53039/100000 [15:46:11<7:37:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 53040/100000 [15:46:11<7:37:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53041/100000 [15:46:12<7:37:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53042/100000 [15:46:13<7:37:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 53043/100000 [15:46:13<7:37:09,  1.71it/s]
Train steps ... :  53%|█████▎    | 53044/100000 [15:46:14<7:38:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 53045/100000 [15:46:14<7:38:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 53046/100000 [15:46:15<7:38:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53047/100000 [15:46:16<7:37:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53048/100000 [15:46:16<7:38:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 53049/100000 [15:46:17<7:36:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 53050/100000 [15:46:17<7:37:39,  1.71it/s]Step... (53050 / 100000 | Loss: 0.5715165734291077, Learning Rate: 4.7185929648241204e-05)
+
                                                                             
Step... (53050 / 100000 | Loss: 0.5336803197860718, Learning Rate: 4.7185929648241204e-05)
+
Train steps ... :  53%|█████▎    | 53050/100000 [15:46:18<7:37:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53051/100000 [15:46:18<7:37:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 53052/100000 [15:46:18<7:37:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 53053/100000 [15:46:19<7:37:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53054/100000 [15:46:20<7:37:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53055/100000 [15:46:20<7:37:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53056/100000 [15:46:21<7:37:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 53057/100000 [15:46:21<7:37:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53058/100000 [15:46:22<7:37:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53059/100000 [15:46:23<7:37:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 53060/100000 [15:46:23<7:37:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 53061/100000 [15:46:24<7:37:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 53062/100000 [15:46:24<7:37:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 53063/100000 [15:46:25<7:38:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 53064/100000 [15:46:25<7:37:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 53065/100000 [15:46:26<7:37:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 53066/100000 [15:46:27<7:37:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53067/100000 [15:46:27<7:37:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53068/100000 [15:46:28<7:37:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 53069/100000 [15:46:28<7:36:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 53070/100000 [15:46:29<7:36:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 53071/100000 [15:46:30<7:36:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 53072/100000 [15:46:30<7:36:51,  1.71it/s]
Train steps ... :  53%|█████▎    | 53073/100000 [15:46:31<7:36:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53074/100000 [15:46:31<7:37:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 53075/100000 [15:46:32<7:37:19,  1.71it/s]Step... (53075 / 100000 | Loss: 0.9007980227470398, Learning Rate: 4.716080402010051e-05)
+
                                                                             
Step... (53075 / 100000 | Loss: 0.6460164785385132, Learning Rate: 4.716080402010051e-05)
+
Train steps ... :  53%|█████▎    | 53075/100000 [15:46:32<7:37:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 53076/100000 [15:46:32<7:37:51,  1.71it/s]
Train steps ... :  53%|█████▎    | 53077/100000 [15:46:33<7:38:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 53078/100000 [15:46:34<7:37:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53079/100000 [15:46:34<7:37:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53080/100000 [15:46:35<7:37:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 53081/100000 [15:46:35<7:37:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53082/100000 [15:46:36<7:37:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 53083/100000 [15:46:37<7:38:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 53084/100000 [15:46:37<7:37:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53085/100000 [15:46:38<7:37:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 53086/100000 [15:46:38<7:36:59,  1.71it/s]
Train steps ... :  53%|█████▎    | 53087/100000 [15:46:39<7:37:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53088/100000 [15:46:39<7:37:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 53089/100000 [15:46:40<7:37:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53090/100000 [15:46:41<7:37:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53091/100000 [15:46:41<7:37:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 53092/100000 [15:46:42<7:37:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 53093/100000 [15:46:42<7:37:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53094/100000 [15:46:43<7:37:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53095/100000 [15:46:44<7:37:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 53096/100000 [15:46:44<7:36:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 53097/100000 [15:46:45<7:36:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53098/100000 [15:46:45<7:36:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53099/100000 [15:46:46<7:36:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53100/100000 [15:46:47<7:36:54,  1.71it/s]Step... (53100 / 100000 | Loss: 1.0433281660079956, Learning Rate: 4.7135678391959804e-05)
+
                                                                             
Step... (53100 / 100000 | Loss: 0.799762487411499, Learning Rate: 4.7135678391959804e-05)
+
Train steps ... :  53%|█████▎    | 53100/100000 [15:46:47<7:36:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53101/100000 [15:46:47<7:36:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 53102/100000 [15:46:48<7:36:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53103/100000 [15:46:48<7:37:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 53104/100000 [15:46:49<7:37:09,  1.71it/s]
Train steps ... :  53%|█████▎    | 53105/100000 [15:46:49<7:36:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53106/100000 [15:46:50<7:36:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53107/100000 [15:46:51<7:36:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 53108/100000 [15:46:51<7:36:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 53109/100000 [15:46:52<7:36:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53110/100000 [15:46:52<7:36:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 53111/100000 [15:46:53<7:36:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 53112/100000 [15:46:54<7:36:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53113/100000 [15:46:54<7:36:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53114/100000 [15:46:55<7:36:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53115/100000 [15:46:55<7:36:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53116/100000 [15:46:56<7:36:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 53117/100000 [15:46:56<7:36:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 53118/100000 [15:46:57<7:37:08,  1.71it/s]
Train steps ... :  53%|█████▎    | 53119/100000 [15:46:58<7:37:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 53120/100000 [15:46:58<7:36:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 53121/100000 [15:46:59<7:36:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 53122/100000 [15:46:59<7:36:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 53123/100000 [15:47:00<7:36:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53124/100000 [15:47:01<7:37:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 53125/100000 [15:47:01<7:37:00,  1.71it/s]Step... (53125 / 100000 | Loss: 0.6011602878570557, Learning Rate: 4.71105527638191e-05)
+
                                                                             
Step... (53125 / 100000 | Loss: 0.693159818649292, Learning Rate: 4.71105527638191e-05)
+
Train steps ... :  53%|█████▎    | 53125/100000 [15:47:01<7:37:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 53126/100000 [15:47:02<7:37:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53127/100000 [15:47:02<7:36:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53128/100000 [15:47:03<7:36:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53129/100000 [15:47:03<7:36:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 53130/100000 [15:47:04<7:36:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 53131/100000 [15:47:05<7:36:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 53132/100000 [15:47:05<7:36:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53133/100000 [15:47:06<7:37:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53134/100000 [15:47:06<7:36:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53135/100000 [15:47:07<7:36:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 53136/100000 [15:47:08<7:36:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 53137/100000 [15:47:08<7:36:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 53138/100000 [15:47:09<7:36:11,  1.71it/s]
Train steps ... :  53%|█████▎    | 53139/100000 [15:47:09<7:36:09,  1.71it/s]
Train steps ... :  53%|█████▎    | 53140/100000 [15:47:10<7:36:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53141/100000 [15:47:10<7:35:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 53142/100000 [15:47:11<7:36:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 53143/100000 [15:47:12<7:36:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 53144/100000 [15:47:12<7:36:09,  1.71it/s]
Train steps ... :  53%|█████▎    | 53145/100000 [15:47:13<7:35:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53146/100000 [15:47:13<7:35:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53147/100000 [15:47:14<7:35:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53148/100000 [15:47:15<7:35:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 53149/100000 [15:47:15<7:36:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53150/100000 [15:47:16<7:36:14,  1.71it/s]Step... (53150 / 100000 | Loss: 0.7004319429397583, Learning Rate: 4.70854271356784e-05)
+
                                                                             
Step... (53150 / 100000 | Loss: 0.5315672755241394, Learning Rate: 4.70854271356784e-05)
+
Train steps ... :  53%|█████▎    | 53150/100000 [15:47:16<7:36:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53151/100000 [15:47:16<7:36:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 53152/100000 [15:47:17<7:36:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 53153/100000 [15:47:17<7:36:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 53154/100000 [15:47:18<7:36:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 53155/100000 [15:47:19<7:36:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53156/100000 [15:47:19<7:36:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53157/100000 [15:47:20<7:36:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53158/100000 [15:47:20<7:36:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 53159/100000 [15:47:21<7:36:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53160/100000 [15:47:22<7:36:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 53161/100000 [15:47:22<7:36:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53162/100000 [15:47:23<7:36:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 53163/100000 [15:47:23<7:36:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 53164/100000 [15:47:24<7:36:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 53165/100000 [15:47:24<7:35:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 53166/100000 [15:47:25<7:35:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 53167/100000 [15:47:26<7:36:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 53168/100000 [15:47:26<7:36:41,  1.71it/s]
Train steps ... :  53%|█████▎    | 53169/100000 [15:47:27<7:37:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 53170/100000 [15:47:27<7:37:08,  1.71it/s]
Train steps ... :  53%|█████▎    | 53171/100000 [15:47:28<7:36:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53172/100000 [15:47:29<7:36:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53173/100000 [15:47:29<7:36:09,  1.71it/s]
Train steps ... :  53%|█████▎    | 53174/100000 [15:47:30<7:36:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 53175/100000 [15:47:30<7:36:23,  1.71it/s]Step... (53175 / 100000 | Loss: 0.7069655656814575, Learning Rate: 4.7060301507537693e-05)
+
                                                                             
Step... (53175 / 100000 | Loss: 1.0331846475601196, Learning Rate: 4.7060301507537693e-05)
+
Train steps ... :  53%|█████▎    | 53175/100000 [15:47:31<7:36:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 53176/100000 [15:47:31<7:36:16,  1.71it/s]
Train steps ... :  53%|█████▎    | 53177/100000 [15:47:32<7:35:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53178/100000 [15:47:32<7:35:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 53179/100000 [15:47:33<7:36:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 53180/100000 [15:47:33<7:35:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 53181/100000 [15:47:34<7:35:59,  1.71it/s]
Train steps ... :  53%|█████▎    | 53182/100000 [15:47:34<7:35:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 53183/100000 [15:47:35<7:35:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53184/100000 [15:47:36<7:35:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53185/100000 [15:47:36<7:35:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 53186/100000 [15:47:37<7:35:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 53187/100000 [15:47:37<7:35:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 53188/100000 [15:47:38<7:35:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53189/100000 [15:47:39<7:36:16,  1.71it/s]
Train steps ... :  53%|█████▎    | 53190/100000 [15:47:39<7:35:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 53191/100000 [15:47:40<7:35:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 53192/100000 [15:47:40<7:36:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 53193/100000 [15:47:41<7:36:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53194/100000 [15:47:41<7:36:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 53195/100000 [15:47:42<7:36:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53196/100000 [15:47:43<7:36:16,  1.71it/s]
Train steps ... :  53%|█████▎    | 53197/100000 [15:47:43<7:35:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53198/100000 [15:47:44<7:35:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 53199/100000 [15:47:44<7:36:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53200/100000 [15:47:45<7:35:56,  1.71it/s]Step... (53200 / 100000 | Loss: 0.6589765548706055, Learning Rate: 4.703517587939698e-05)
+
                                                                             
Step... (53200 / 100000 | Loss: 0.9079458713531494, Learning Rate: 4.703517587939698e-05)
+
Train steps ... :  53%|█████▎    | 53200/100000 [15:47:45<7:35:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 53201/100000 [15:47:46<7:36:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53202/100000 [15:47:46<7:36:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 53203/100000 [15:47:47<7:36:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 53204/100000 [15:47:47<7:36:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53205/100000 [15:47:48<7:36:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 53206/100000 [15:47:48<7:36:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 53207/100000 [15:47:49<7:35:59,  1.71it/s]
Train steps ... :  53%|█████▎    | 53208/100000 [15:47:50<7:35:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53209/100000 [15:47:50<7:35:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 53210/100000 [15:47:51<7:35:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53211/100000 [15:47:51<7:35:26,  1.71it/s]
Train steps ... :  53%|█████▎    | 53212/100000 [15:47:52<7:35:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 53213/100000 [15:47:53<7:35:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53214/100000 [15:47:53<7:36:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53215/100000 [15:47:54<7:35:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53216/100000 [15:47:54<7:35:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 53217/100000 [15:47:55<7:35:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 53218/100000 [15:47:55<7:36:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 53219/100000 [15:47:56<7:36:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 53220/100000 [15:47:57<7:36:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 53221/100000 [15:47:57<7:35:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 53222/100000 [15:47:58<7:36:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 53223/100000 [15:47:58<7:35:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 53224/100000 [15:47:59<7:35:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 53225/100000 [15:48:00<7:35:12,  1.71it/s]Step... (53225 / 100000 | Loss: 0.7206705808639526, Learning Rate: 4.701005025125628e-05)
+
                                                                             
Step... (53225 / 100000 | Loss: 0.639862060546875, Learning Rate: 4.701005025125628e-05)
+
Train steps ... :  53%|█████▎    | 53225/100000 [15:48:00<7:35:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53226/100000 [15:48:00<7:35:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53227/100000 [15:48:01<7:36:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 53228/100000 [15:48:01<7:35:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 53229/100000 [15:48:02<7:35:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53230/100000 [15:48:02<7:36:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 53231/100000 [15:48:03<7:36:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 53232/100000 [15:48:04<7:35:51,  1.71it/s]
Train steps ... :  53%|█████▎    | 53233/100000 [15:48:04<7:35:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53234/100000 [15:48:05<7:35:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53235/100000 [15:48:05<7:35:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 53236/100000 [15:48:06<7:35:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53237/100000 [15:48:07<7:35:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53238/100000 [15:48:07<7:35:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53239/100000 [15:48:08<7:35:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 53240/100000 [15:48:08<7:35:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 53241/100000 [15:48:09<7:35:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 53242/100000 [15:48:10<7:35:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53243/100000 [15:48:10<7:35:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 53244/100000 [15:48:11<7:36:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 53245/100000 [15:48:11<7:35:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 53246/100000 [15:48:12<7:35:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 53247/100000 [15:48:12<7:35:46,  1.71it/s]
Train steps ... :  53%|█████▎    | 53248/100000 [15:48:13<7:36:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53249/100000 [15:48:14<7:36:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 53250/100000 [15:48:14<7:36:05,  1.71it/s]Step... (53250 / 100000 | Loss: 0.7003109455108643, Learning Rate: 4.6984924623115577e-05)
+
                                                                             
Step... (53250 / 100000 | Loss: 0.8872958421707153, Learning Rate: 4.6984924623115577e-05)
+
Train steps ... :  53%|█████▎    | 53250/100000 [15:48:15<7:36:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 53251/100000 [15:48:15<7:35:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 53252/100000 [15:48:15<7:35:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 53253/100000 [15:48:16<7:35:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53254/100000 [15:48:17<7:35:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 53255/100000 [15:48:17<7:35:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 53256/100000 [15:48:18<7:35:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 53257/100000 [15:48:18<7:34:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 53258/100000 [15:48:19<7:35:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 53259/100000 [15:48:19<7:35:00,  1.71it/s]
Train steps ... :  53%|█████▎    | 53260/100000 [15:48:20<7:35:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 53261/100000 [15:48:21<7:34:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 53262/100000 [15:48:21<7:35:09,  1.71it/s]
Train steps ... :  53%|█████▎    | 53263/100000 [15:48:22<7:35:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53264/100000 [15:48:22<7:35:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53265/100000 [15:48:23<7:35:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53266/100000 [15:48:24<7:35:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 53267/100000 [15:48:24<7:35:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53268/100000 [15:48:25<7:35:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 53269/100000 [15:48:25<7:35:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 53270/100000 [15:48:26<7:35:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 53271/100000 [15:48:26<7:35:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 53272/100000 [15:48:27<7:35:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 53273/100000 [15:48:28<7:35:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 53274/100000 [15:48:28<7:35:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 53275/100000 [15:48:29<7:35:14,  1.71it/s]Step... (53275 / 100000 | Loss: 0.8449341058731079, Learning Rate: 4.695979899497487e-05)
+
                                                                             
Step... (53275 / 100000 | Loss: 0.6214615702629089, Learning Rate: 4.695979899497487e-05)
+
Train steps ... :  53%|█████▎    | 53275/100000 [15:48:29<7:35:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53276/100000 [15:48:29<7:35:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 53277/100000 [15:48:30<7:36:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 53278/100000 [15:48:31<7:35:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 53279/100000 [15:48:31<7:35:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 53280/100000 [15:48:32<7:35:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 53281/100000 [15:48:32<7:35:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53282/100000 [15:48:33<7:34:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53283/100000 [15:48:33<7:34:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 53284/100000 [15:48:34<7:34:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53285/100000 [15:48:35<7:34:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 53286/100000 [15:48:35<7:34:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53287/100000 [15:48:36<7:34:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 53288/100000 [15:48:36<7:35:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53289/100000 [15:48:37<7:35:08,  1.71it/s]
Train steps ... :  53%|█████▎    | 53290/100000 [15:48:38<7:35:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53291/100000 [15:48:38<7:35:27,  1.71it/s]
Train steps ... :  53%|█████▎    | 53292/100000 [15:48:39<7:35:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 53293/100000 [15:48:39<7:34:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 53294/100000 [15:48:40<7:35:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53295/100000 [15:48:41<7:35:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53296/100000 [15:48:41<7:34:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 53297/100000 [15:48:42<7:35:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53298/100000 [15:48:42<7:35:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53299/100000 [15:48:43<7:35:08,  1.71it/s]
Train steps ... :  53%|█████▎    | 53300/100000 [15:48:43<7:35:20,  1.71it/s]Step... (53300 / 100000 | Loss: 0.8347796201705933, Learning Rate: 4.6934673366834177e-05)
+
                                                                             
Step... (53300 / 100000 | Loss: 0.5603266358375549, Learning Rate: 4.6934673366834177e-05)
+
Train steps ... :  53%|█████▎    | 53300/100000 [15:48:44<7:35:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 53301/100000 [15:48:44<7:35:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 53302/100000 [15:48:45<7:34:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53303/100000 [15:48:45<7:35:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 53304/100000 [15:48:46<7:35:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53305/100000 [15:48:46<7:35:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53306/100000 [15:48:47<7:35:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 53307/100000 [15:48:48<7:34:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53308/100000 [15:48:48<7:35:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53309/100000 [15:48:49<7:34:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53310/100000 [15:48:49<7:35:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 53311/100000 [15:48:50<7:34:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 53312/100000 [15:48:50<7:35:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53313/100000 [15:48:51<7:35:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53314/100000 [15:48:52<7:35:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53315/100000 [15:48:52<7:34:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53316/100000 [15:48:53<7:34:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53317/100000 [15:48:53<7:35:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 53318/100000 [15:48:54<7:35:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53319/100000 [15:48:55<7:35:11,  1.71it/s]
Train steps ... :  53%|█████▎    | 53320/100000 [15:48:55<7:36:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53321/100000 [15:48:56<7:35:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 53322/100000 [15:48:56<7:35:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 53323/100000 [15:48:57<7:34:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53324/100000 [15:48:57<7:34:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 53325/100000 [15:48:58<7:34:54,  1.71it/s]Step... (53325 / 100000 | Loss: 0.9105554819107056, Learning Rate: 4.690954773869347e-05)
+
                                                                             
Step... (53325 / 100000 | Loss: 0.6231091022491455, Learning Rate: 4.690954773869347e-05)
+
Train steps ... :  53%|█████▎    | 53325/100000 [15:48:58<7:34:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53326/100000 [15:48:59<7:34:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 53327/100000 [15:48:59<7:34:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 53328/100000 [15:49:00<7:34:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 53329/100000 [15:49:00<7:34:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 53330/100000 [15:49:01<7:34:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 53331/100000 [15:49:02<7:34:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 53332/100000 [15:49:02<7:34:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 53333/100000 [15:49:03<7:34:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53334/100000 [15:49:03<7:34:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53335/100000 [15:49:04<7:34:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 53336/100000 [15:49:04<7:34:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53337/100000 [15:49:05<7:34:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53338/100000 [15:49:06<7:34:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 53339/100000 [15:49:06<7:34:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53340/100000 [15:49:07<7:34:05,  1.71it/s]
Train steps ... :  53%|█████▎    | 53341/100000 [15:49:07<7:34:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 53342/100000 [15:49:08<7:34:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53343/100000 [15:49:09<7:34:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 53344/100000 [15:49:09<7:34:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 53345/100000 [15:49:10<7:34:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53346/100000 [15:49:10<7:34:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 53347/100000 [15:49:11<7:34:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 53348/100000 [15:49:11<7:34:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 53349/100000 [15:49:12<7:34:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 53350/100000 [15:49:13<7:35:03,  1.71it/s]Step... (53350 / 100000 | Loss: 0.8624143600463867, Learning Rate: 4.688442211055277e-05)
+
                                                                             
Step... (53350 / 100000 | Loss: 0.8971362113952637, Learning Rate: 4.688442211055277e-05)
+
Train steps ... :  53%|█████▎    | 53350/100000 [15:49:13<7:35:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 53351/100000 [15:49:13<7:34:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 53352/100000 [15:49:14<7:34:06,  1.71it/s]
Train steps ... :  53%|█████▎    | 53353/100000 [15:49:14<7:34:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 53354/100000 [15:49:15<7:34:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53355/100000 [15:49:16<7:35:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 53356/100000 [15:49:16<7:35:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53357/100000 [15:49:17<7:34:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 53358/100000 [15:49:17<7:35:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 53359/100000 [15:49:18<7:34:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53360/100000 [15:49:19<7:34:24,  1.71it/s]
Train steps ... :  53%|█████▎    | 53361/100000 [15:49:19<7:34:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53362/100000 [15:49:20<7:34:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53363/100000 [15:49:20<7:34:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 53364/100000 [15:49:21<7:33:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 53365/100000 [15:49:21<7:33:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53366/100000 [15:49:22<7:34:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 53367/100000 [15:49:23<7:34:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53368/100000 [15:49:23<7:34:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 53369/100000 [15:49:24<7:34:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53370/100000 [15:49:24<7:35:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53371/100000 [15:49:25<7:34:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 53372/100000 [15:49:26<7:34:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 53373/100000 [15:49:26<7:34:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 53374/100000 [15:49:27<7:34:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53375/100000 [15:49:27<7:34:01,  1.71it/s]Step... (53375 / 100000 | Loss: 0.7296411991119385, Learning Rate: 4.685929648241206e-05)
+
                                                                             
Step... (53375 / 100000 | Loss: 0.6461269855499268, Learning Rate: 4.685929648241206e-05)
+
Train steps ... :  53%|█████▎    | 53375/100000 [15:49:28<7:34:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 53376/100000 [15:49:28<7:34:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53377/100000 [15:49:28<7:34:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 53378/100000 [15:49:29<7:34:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 53379/100000 [15:49:30<7:34:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 53380/100000 [15:49:30<7:34:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53381/100000 [15:49:31<7:34:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53382/100000 [15:49:31<7:33:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 53383/100000 [15:49:32<7:33:51,  1.71it/s]
Train steps ... :  53%|█████▎    | 53384/100000 [15:49:33<7:33:29,  1.71it/s]
Train steps ... :  53%|█████▎    | 53385/100000 [15:49:33<7:33:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 53386/100000 [15:49:34<7:33:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53387/100000 [15:49:34<7:34:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53388/100000 [15:49:35<7:34:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53389/100000 [15:49:35<7:34:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53390/100000 [15:49:36<7:34:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53391/100000 [15:49:37<7:34:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53392/100000 [15:49:37<7:34:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 53393/100000 [15:49:38<7:33:49,  1.71it/s]
Train steps ... :  53%|█████▎    | 53394/100000 [15:49:38<7:33:56,  1.71it/s]
Train steps ... :  53%|█████▎    | 53395/100000 [15:49:39<7:33:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 53396/100000 [15:49:40<7:33:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53397/100000 [15:49:40<7:34:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53398/100000 [15:49:41<7:33:46,  1.71it/s]
Train steps ... :  53%|█████▎    | 53399/100000 [15:49:41<7:34:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 53400/100000 [15:49:42<7:33:30,  1.71it/s]Step... (53400 / 100000 | Loss: 0.6859567165374756, Learning Rate: 4.6834170854271356e-05)
+
                                                                             
Step... (53400 / 100000 | Loss: 0.6078019142150879, Learning Rate: 4.6834170854271356e-05)
+
Train steps ... :  53%|█████▎    | 53400/100000 [15:49:42<7:33:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 53401/100000 [15:49:42<7:33:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 53402/100000 [15:49:43<7:33:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 53403/100000 [15:49:44<7:33:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 53404/100000 [15:49:44<7:33:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 53405/100000 [15:49:45<7:33:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53406/100000 [15:49:45<7:33:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53407/100000 [15:49:46<7:34:10,  1.71it/s]
Train steps ... :  53%|█████▎    | 53408/100000 [15:49:47<7:33:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 53409/100000 [15:49:47<7:33:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 53410/100000 [15:49:48<7:33:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 53411/100000 [15:49:48<7:34:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53412/100000 [15:49:49<7:34:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 53413/100000 [15:49:49<7:33:55,  1.71it/s]
Train steps ... :  53%|█████▎    | 53414/100000 [15:49:50<7:34:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53415/100000 [15:49:51<7:33:50,  1.71it/s]
Train steps ... :  53%|█████▎    | 53416/100000 [15:49:51<7:33:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 53417/100000 [15:49:52<7:33:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 53418/100000 [15:49:52<7:33:34,  1.71it/s]
Train steps ... :  53%|█████▎    | 53419/100000 [15:49:53<7:33:41,  1.71it/s]
Train steps ... :  53%|█████▎    | 53420/100000 [15:49:54<7:33:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53421/100000 [15:49:54<7:34:21,  1.71it/s]
Train steps ... :  53%|█████▎    | 53422/100000 [15:49:55<7:33:41,  1.71it/s]
Train steps ... :  53%|█████▎    | 53423/100000 [15:49:55<7:33:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 53424/100000 [15:49:56<7:33:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53425/100000 [15:49:57<7:33:59,  1.71it/s]Step... (53425 / 100000 | Loss: 0.8250362277030945, Learning Rate: 4.680904522613065e-05)
+
                                                                             
Step... (53425 / 100000 | Loss: 0.8202797174453735, Learning Rate: 4.680904522613065e-05)
+
Train steps ... :  53%|█████▎    | 53425/100000 [15:49:57<7:33:59,  1.71it/s]
Train steps ... :  53%|█████▎    | 53426/100000 [15:49:57<7:34:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 53427/100000 [15:49:58<7:34:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53428/100000 [15:49:58<7:34:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 53429/100000 [15:49:59<7:33:41,  1.71it/s]
Train steps ... :  53%|█████▎    | 53430/100000 [15:49:59<7:34:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53431/100000 [15:50:00<7:33:37,  1.71it/s]
Train steps ... :  53%|█████▎    | 53432/100000 [15:50:01<7:33:32,  1.71it/s]
Train steps ... :  53%|█████▎    | 53433/100000 [15:50:01<7:34:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 53434/100000 [15:50:02<7:33:59,  1.71it/s]
Train steps ... :  53%|█████▎    | 53435/100000 [15:50:02<7:33:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 53436/100000 [15:50:03<7:33:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 53437/100000 [15:50:04<7:33:40,  1.71it/s]
Train steps ... :  53%|█████▎    | 53438/100000 [15:50:04<7:33:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53439/100000 [15:50:05<7:33:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53440/100000 [15:50:05<7:33:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 53441/100000 [15:50:06<7:32:52,  1.71it/s]
Train steps ... :  53%|█████▎    | 53442/100000 [15:50:06<7:32:58,  1.71it/s]
Train steps ... :  53%|█████▎    | 53443/100000 [15:50:07<7:33:17,  1.71it/s]
Train steps ... :  53%|█████▎    | 53444/100000 [15:50:08<7:33:19,  1.71it/s]
Train steps ... :  53%|█████▎    | 53445/100000 [15:50:08<7:34:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 53446/100000 [15:50:09<7:33:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 53447/100000 [15:50:09<7:33:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 53448/100000 [15:50:10<7:33:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53449/100000 [15:50:11<7:33:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 53450/100000 [15:50:11<7:33:04,  1.71it/s]Step... (53450 / 100000 | Loss: 0.767514705657959, Learning Rate: 4.678391959798995e-05)
+
                                                                             
Step... (53450 / 100000 | Loss: 0.630425214767456, Learning Rate: 4.678391959798995e-05)
+
Train steps ... :  53%|���████▎    | 53450/100000 [15:50:11<7:33:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 53451/100000 [15:50:12<7:34:57,  1.71it/s]
Train steps ... :  53%|█████▎    | 53452/100000 [15:50:12<7:33:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53453/100000 [15:50:13<7:33:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53454/100000 [15:50:13<7:34:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53455/100000 [15:50:14<7:33:43,  1.71it/s]
Train steps ... :  53%|█████▎    | 53456/100000 [15:50:15<7:33:28,  1.71it/s]
Train steps ... :  53%|█████▎    | 53457/100000 [15:50:15<7:33:41,  1.71it/s]
Train steps ... :  53%|█████▎    | 53458/100000 [15:50:16<7:34:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 53459/100000 [15:50:16<7:34:18,  1.71it/s]
Train steps ... :  53%|█████▎    | 53460/100000 [15:50:17<7:33:48,  1.71it/s]
Train steps ... :  53%|█████▎    | 53461/100000 [15:50:18<7:33:38,  1.71it/s]
Train steps ... :  53%|█████▎    | 53462/100000 [15:50:18<7:33:25,  1.71it/s]
Train steps ... :  53%|█████▎    | 53463/100000 [15:50:19<7:33:44,  1.71it/s]
Train steps ... :  53%|█████▎    | 53464/100000 [15:50:19<7:33:35,  1.71it/s]
Train steps ... :  53%|█████▎    | 53465/100000 [15:50:20<7:33:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53466/100000 [15:50:20<7:34:04,  1.71it/s]
Train steps ... :  53%|█████▎    | 53467/100000 [15:50:21<7:33:45,  1.71it/s]
Train steps ... :  53%|█████▎    | 53468/100000 [15:50:22<7:33:23,  1.71it/s]
Train steps ... :  53%|█████▎    | 53469/100000 [15:50:22<7:33:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 53470/100000 [15:50:23<7:33:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53471/100000 [15:50:23<7:33:42,  1.71it/s]
Train steps ... :  53%|█████▎    | 53472/100000 [15:50:24<7:33:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 53473/100000 [15:50:25<7:33:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53474/100000 [15:50:25<7:33:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 53475/100000 [15:50:26<7:33:12,  1.71it/s]Step... (53475 / 100000 | Loss: 0.7488590478897095, Learning Rate: 4.6758793969849246e-05)
+
                                                                             
Step... (53475 / 100000 | Loss: 0.7913268208503723, Learning Rate: 4.6758793969849246e-05)
+
Train steps ... :  53%|█████▎    | 53475/100000 [15:50:26<7:33:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53476/100000 [15:50:26<7:33:22,  1.71it/s]
Train steps ... :  53%|█████▎    | 53477/100000 [15:50:27<7:33:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53478/100000 [15:50:27<7:33:07,  1.71it/s]
Train steps ... :  53%|█████▎    | 53479/100000 [15:50:28<7:33:09,  1.71it/s]
Train steps ... :  53%|█████▎    | 53480/100000 [15:50:29<7:32:53,  1.71it/s]
Train steps ... :  53%|█████▎    | 53481/100000 [15:50:29<7:32:46,  1.71it/s]
Train steps ... :  53%|█████▎    | 53482/100000 [15:50:30<7:33:03,  1.71it/s]
Train steps ... :  53%|█████▎    | 53483/100000 [15:50:30<7:33:02,  1.71it/s]
Train steps ... :  53%|█████▎    | 53484/100000 [15:50:31<7:33:14,  1.71it/s]
Train steps ... :  53%|█████▎    | 53485/100000 [15:50:32<7:33:08,  1.71it/s]
Train steps ... :  53%|█████▎    | 53486/100000 [15:50:32<7:33:12,  1.71it/s]
Train steps ... :  53%|█████▎    | 53487/100000 [15:50:33<7:32:47,  1.71it/s]
Train steps ... :  53%|█████▎    | 53488/100000 [15:50:33<7:34:01,  1.71it/s]
Train steps ... :  53%|█████▎    | 53489/100000 [15:50:34<7:33:20,  1.71it/s]
Train steps ... :  53%|█████▎    | 53490/100000 [15:50:35<7:34:15,  1.71it/s]
Train steps ... :  53%|█████▎    | 53491/100000 [15:50:35<7:33:33,  1.71it/s]
Train steps ... :  53%|█████▎    | 53492/100000 [15:50:36<7:33:31,  1.71it/s]
Train steps ... :  53%|█████▎    | 53493/100000 [15:50:36<7:34:36,  1.71it/s]
Train steps ... :  53%|█████▎    | 53494/100000 [15:50:37<7:34:13,  1.71it/s]
Train steps ... :  53%|█████▎    | 53495/100000 [15:50:37<7:34:40,  1.70it/s]
Train steps ... :  53%|█████▎    | 53496/100000 [15:50:38<7:33:39,  1.71it/s]
Train steps ... :  53%|█████▎    | 53497/100000 [15:50:39<7:33:54,  1.71it/s]
Train steps ... :  53%|█████▎    | 53498/100000 [15:50:39<7:34:30,  1.71it/s]
Train steps ... :  53%|█████▎    | 53499/100000 [15:50:40<7:33:51,  1.71it/s]
Train steps ... :  54%|█████▎    | 53500/100000 [15:50:40<7:33:34,  1.71it/s]Step... (53500 / 100000 | Loss: 0.6169453263282776, Learning Rate: 4.673366834170855e-05)
+
                                                                             
Step... (53500 / 100000 | Loss: 0.7939555644989014, Learning Rate: 4.673366834170855e-05)
+
Train steps ... :  54%|█████▎    | 53500/100000 [15:50:41<7:33:34,  1.71it/s]
Train steps ... :  54%|█████▎    | 53501/100000 [15:50:41<7:33:50,  1.71it/s]
Train steps ... :  54%|█████▎    | 53502/100000 [15:50:42<7:33:39,  1.71it/s]
Train steps ... :  54%|█████▎    | 53503/100000 [15:50:42<7:34:11,  1.71it/s]
Train steps ... :  54%|█████▎    | 53504/100000 [15:50:43<7:33:08,  1.71it/s]
Train steps ... :  54%|█████▎    | 53505/100000 [15:50:43<7:33:28,  1.71it/s]
Train steps ... :  54%|█████▎    | 53506/100000 [15:50:44<7:33:36,  1.71it/s]
Train steps ... :  54%|█████▎    | 53507/100000 [15:50:44<7:33:21,  1.71it/s]
Train steps ... :  54%|█████▎    | 53508/100000 [15:50:45<7:33:01,  1.71it/s]
Train steps ... :  54%|█████▎    | 53509/100000 [15:50:46<7:33:50,  1.71it/s]
Train steps ... :  54%|█████▎    | 53510/100000 [15:50:46<7:32:58,  1.71it/s]
Train steps ... :  54%|█████▎    | 53511/100000 [15:50:47<7:32:48,  1.71it/s]
Train steps ... :  54%|█████▎    | 53512/100000 [15:50:47<7:32:35,  1.71it/s]
Train steps ... :  54%|█████▎    | 53513/100000 [15:50:48<7:32:38,  1.71it/s]
Train steps ... :  54%|█████▎    | 53514/100000 [15:50:49<7:33:05,  1.71it/s]
Train steps ... :  54%|█████▎    | 53515/100000 [15:50:49<7:32:47,  1.71it/s]
Train steps ... :  54%|█████▎    | 53516/100000 [15:50:50<7:32:37,  1.71it/s]
Train steps ... :  54%|█████▎    | 53517/100000 [15:50:50<7:32:42,  1.71it/s]
Train steps ... :  54%|█████▎    | 53518/100000 [15:50:51<7:32:49,  1.71it/s]
Train steps ... :  54%|█████▎    | 53519/100000 [15:50:51<7:32:45,  1.71it/s]
Train steps ... :  54%|█████▎    | 53520/100000 [15:50:52<7:32:37,  1.71it/s]
Train steps ... :  54%|█████▎    | 53521/100000 [15:50:53<7:33:04,  1.71it/s]
Train steps ... :  54%|█████▎    | 53522/100000 [15:50:53<7:33:11,  1.71it/s]
Train steps ... :  54%|█████▎    | 53523/100000 [15:50:54<7:32:43,  1.71it/s]
Train steps ... :  54%|█████▎    | 53524/100000 [15:50:54<7:33:29,  1.71it/s]
Train steps ... :  54%|█████▎    | 53525/100000 [15:50:55<7:32:27,  1.71it/s]Step... (53525 / 100000 | Loss: 0.7693607807159424, Learning Rate: 4.6708542713567846e-05)
+
                                                                             
Step... (53525 / 100000 | Loss: 0.6423028111457825, Learning Rate: 4.6708542713567846e-05)
+
Train steps ... :  54%|█████▎    | 53525/100000 [15:50:55<7:32:27,  1.71it/s]
Train steps ... :  54%|█████▎    | 53526/100000 [15:50:56<7:32:35,  1.71it/s]
Train steps ... :  54%|█████▎    | 53527/100000 [15:50:56<7:32:53,  1.71it/s]
Train steps ... :  54%|█████▎    | 53528/100000 [15:50:57<7:32:52,  1.71it/s]
Train steps ... :  54%|█████▎    | 53529/100000 [15:50:57<7:32:24,  1.71it/s]
Train steps ... :  54%|█████▎    | 53530/100000 [15:50:58<7:32:26,  1.71it/s]
Train steps ... :  54%|█████▎    | 53531/100000 [15:50:58<7:32:27,  1.71it/s]
Train steps ... :  54%|█████▎    | 53532/100000 [15:50:59<7:32:42,  1.71it/s]
Train steps ... :  54%|█████▎    | 53533/100000 [15:51:00<7:32:13,  1.71it/s]
Train steps ... :  54%|█████▎    | 53534/100000 [15:51:00<7:32:10,  1.71it/s]
Train steps ... :  54%|█████▎    | 53535/100000 [15:51:01<7:32:57,  1.71it/s]
Train steps ... :  54%|█████▎    | 53536/100000 [15:51:01<7:32:48,  1.71it/s]
Train steps ... :  54%|█████▎    | 53537/100000 [15:51:02<7:32:27,  1.71it/s]
Train steps ... :  54%|█████▎    | 53538/100000 [15:51:03<7:32:31,  1.71it/s]
Train steps ... :  54%|█████▎    | 53539/100000 [15:51:03<7:32:18,  1.71it/s]
Train steps ... :  54%|█████▎    | 53540/100000 [15:51:04<7:32:07,  1.71it/s]
Train steps ... :  54%|█████▎    | 53541/100000 [15:51:04<7:32:22,  1.71it/s]
Train steps ... :  54%|█████▎    | 53542/100000 [15:51:05<7:32:40,  1.71it/s]
Train steps ... :  54%|█████▎    | 53543/100000 [15:51:06<7:33:30,  1.71it/s]
Train steps ... :  54%|█████▎    | 53544/100000 [15:51:06<7:33:59,  1.71it/s]
Train steps ... :  54%|█████▎    | 53545/100000 [15:51:07<7:33:33,  1.71it/s]
Train steps ... :  54%|█████▎    | 53546/100000 [15:51:07<7:33:43,  1.71it/s]
Train steps ... :  54%|█████▎    | 53547/100000 [15:51:08<7:33:42,  1.71it/s]
Train steps ... :  54%|█████▎    | 53548/100000 [15:51:08<7:33:13,  1.71it/s]
Train steps ... :  54%|█████▎    | 53549/100000 [15:51:09<7:32:53,  1.71it/s]
Train steps ... :  54%|█████▎    | 53550/100000 [15:51:10<7:32:29,  1.71it/s]Step... (53550 / 100000 | Loss: 0.7966396808624268, Learning Rate: 4.6683417085427136e-05)
+
                                                                             
Step... (53550 / 100000 | Loss: 0.7302408218383789, Learning Rate: 4.6683417085427136e-05)
+
Train steps ... :  54%|█████▎    | 53550/100000 [15:51:10<7:32:29,  1.71it/s]
Train steps ... :  54%|█████▎    | 53551/100000 [15:51:10<7:32:48,  1.71it/s]
Train steps ... :  54%|█████▎    | 53552/100000 [15:51:11<7:32:57,  1.71it/s]
Train steps ... :  54%|█████▎    | 53553/100000 [15:51:11<7:32:41,  1.71it/s]
Train steps ... :  54%|█████▎    | 53554/100000 [15:51:12<7:33:13,  1.71it/s]
Train steps ... :  54%|█████▎    | 53555/100000 [15:51:13<7:33:24,  1.71it/s]
Train steps ... :  54%|█████▎    | 53556/100000 [15:51:13<7:32:53,  1.71it/s]
Train steps ... :  54%|█████▎    | 53557/100000 [15:51:14<7:32:43,  1.71it/s]
Train steps ... :  54%|█████▎    | 53558/100000 [15:51:14<7:32:46,  1.71it/s]
Train steps ... :  54%|█████▎    | 53559/100000 [15:51:15<7:32:28,  1.71it/s]
Train steps ... :  54%|█████▎    | 53560/100000 [15:51:15<7:32:55,  1.71it/s]
Train steps ... :  54%|█████▎    | 53561/100000 [15:51:16<7:33:37,  1.71it/s]
Train steps ... :  54%|█████▎    | 53562/100000 [15:51:17<7:33:09,  1.71it/s]
Train steps ... :  54%|█████▎    | 53563/100000 [15:51:17<7:32:36,  1.71it/s]
Train steps ... :  54%|█████▎    | 53564/100000 [15:51:18<7:32:23,  1.71it/s]
Train steps ... :  54%|█████▎    | 53565/100000 [15:51:18<7:32:58,  1.71it/s]
Train steps ... :  54%|█████▎    | 53566/100000 [15:51:19<7:33:02,  1.71it/s]
Train steps ... :  54%|█████▎    | 53567/100000 [15:51:20<7:32:40,  1.71it/s]
Train steps ... :  54%|█████▎    | 53568/100000 [15:51:20<7:32:11,  1.71it/s]
Train steps ... :  54%|█████▎    | 53569/100000 [15:51:21<7:32:07,  1.71it/s]
Train steps ... :  54%|█████▎    | 53570/100000 [15:51:21<7:33:45,  1.71it/s]
Train steps ... :  54%|█████▎    | 53571/100000 [15:51:22<7:33:04,  1.71it/s]
Train steps ... :  54%|█████▎    | 53572/100000 [15:51:22<7:33:12,  1.71it/s]
Train steps ... :  54%|█████▎    | 53573/100000 [15:51:23<7:33:23,  1.71it/s]
Train steps ... :  54%|█████▎    | 53574/100000 [15:51:24<7:34:33,  1.70it/s]
Train steps ... :  54%|█████▎    | 53575/100000 [15:51:24<7:34:47,  1.70it/s]Step... (53575 / 100000 | Loss: 1.007383108139038, Learning Rate: 4.665829145728643e-05)
+
                                                                             
Step... (53575 / 100000 | Loss: 0.9937126636505127, Learning Rate: 4.665829145728643e-05)
+
Train steps ... :  54%|█████▎    | 53575/100000 [15:51:25<7:34:47,  1.70it/s]
Train steps ... :  54%|█████▎    | 53576/100000 [15:51:25<7:33:59,  1.70it/s]
Train steps ... :  54%|█████▎    | 53577/100000 [15:51:25<7:33:30,  1.71it/s]
Train steps ... :  54%|█████▎    | 53578/100000 [15:51:26<7:33:32,  1.71it/s]
Train steps ... :  54%|█████▎    | 53579/100000 [15:51:27<7:33:11,  1.71it/s]
Train steps ... :  54%|█████▎    | 53580/100000 [15:51:27<7:33:07,  1.71it/s]
Train steps ... :  54%|█████▎    | 53581/100000 [15:51:28<7:32:56,  1.71it/s]
Train steps ... :  54%|█████▎    | 53582/100000 [15:51:28<7:32:37,  1.71it/s]
Train steps ... :  54%|█████▎    | 53583/100000 [15:51:29<7:32:12,  1.71it/s]
Train steps ... :  54%|█████▎    | 53584/100000 [15:51:30<7:32:16,  1.71it/s]
Train steps ... :  54%|█████▎    | 53585/100000 [15:51:30<7:32:23,  1.71it/s]
Train steps ... :  54%|█████▎    | 53586/100000 [15:51:31<7:32:30,  1.71it/s]
Train steps ... :  54%|█████▎    | 53587/100000 [15:51:31<7:32:28,  1.71it/s]
Train steps ... :  54%|█████▎    | 53588/100000 [15:51:32<7:32:25,  1.71it/s]
Train steps ... :  54%|█████▎    | 53589/100000 [15:51:32<7:32:37,  1.71it/s]
Train steps ... :  54%|█████▎    | 53590/100000 [15:51:33<7:32:41,  1.71it/s]
Train steps ... :  54%|█████▎    | 53591/100000 [15:51:34<7:32:23,  1.71it/s]
Train steps ... :  54%|█████▎    | 53592/100000 [15:51:34<7:32:27,  1.71it/s]
Train steps ... :  54%|█████▎    | 53593/100000 [15:51:35<7:32:26,  1.71it/s]
Train steps ... :  54%|█████▎    | 53594/100000 [15:51:35<7:32:17,  1.71it/s]
Train steps ... :  54%|█████▎    | 53595/100000 [15:51:36<7:32:15,  1.71it/s]
Train steps ... :  54%|█████▎    | 53596/100000 [15:51:37<7:32:30,  1.71it/s]
Train steps ... :  54%|█████▎    | 53597/100000 [15:51:37<7:32:05,  1.71it/s]
Train steps ... :  54%|█████▎    | 53598/100000 [15:51:38<7:32:10,  1.71it/s]
Train steps ... :  54%|█████▎    | 53599/100000 [15:51:38<7:32:04,  1.71it/s]
Train steps ... :  54%|█████▎    | 53600/100000 [15:51:39<7:31:54,  1.71it/s]Step... (53600 / 100000 | Loss: 0.7662086486816406, Learning Rate: 4.663316582914573e-05)
+
                                                                             
Step... (53600 / 100000 | Loss: 0.9693970680236816, Learning Rate: 4.663316582914573e-05)
+
Train steps ... :  54%|█████▎    | 53600/100000 [15:51:39<7:31:54,  1.71it/s]
Train steps ... :  54%|█████▎    | 53601/100000 [15:51:39<7:31:40,  1.71it/s]
Train steps ... :  54%|█████▎    | 53602/100000 [15:51:40<7:31:57,  1.71it/s]
Train steps ... :  54%|█████▎    | 53603/100000 [15:51:41<7:31:53,  1.71it/s]
Train steps ... :  54%|█████▎    | 53604/100000 [15:51:41<7:32:03,  1.71it/s]
Train steps ... :  54%|█████▎    | 53605/100000 [15:51:42<7:31:50,  1.71it/s]
Train steps ... :  54%|█████▎    | 53606/100000 [15:51:42<7:32:17,  1.71it/s]
Train steps ... :  54%|█████▎    | 53607/100000 [15:51:43<7:31:48,  1.71it/s]
Train steps ... :  54%|█████▎    | 53608/100000 [15:51:44<7:31:43,  1.71it/s]
Train steps ... :  54%|█████▎    | 53609/100000 [15:51:44<7:31:34,  1.71it/s]
Train steps ... :  54%|█████▎    | 53610/100000 [15:51:45<7:31:52,  1.71it/s]
Train steps ... :  54%|█████▎    | 53611/100000 [15:51:45<7:32:46,  1.71it/s]
Train steps ... :  54%|█████▎    | 53612/100000 [15:51:46<7:32:33,  1.71it/s]
Train steps ... :  54%|█████▎    | 53613/100000 [15:51:46<7:32:10,  1.71it/s]
Train steps ... :  54%|█████▎    | 53614/100000 [15:51:47<7:31:50,  1.71it/s]
Train steps ... :  54%|█████▎    | 53615/100000 [15:51:48<7:31:54,  1.71it/s]
Train steps ... :  54%|█████▎    | 53616/100000 [15:51:48<7:31:45,  1.71it/s]
Train steps ... :  54%|█████▎    | 53617/100000 [15:51:49<7:31:34,  1.71it/s]
Train steps ... :  54%|█████▎    | 53618/100000 [15:51:49<7:31:52,  1.71it/s]
Train steps ... :  54%|█████▎    | 53619/100000 [15:51:50<7:31:45,  1.71it/s]
Train steps ... :  54%|█████▎    | 53620/100000 [15:51:51<7:31:50,  1.71it/s]
Train steps ... :  54%|█████▎    | 53621/100000 [15:51:51<7:31:48,  1.71it/s]
Train steps ... :  54%|█████▎    | 53622/100000 [15:51:52<7:31:28,  1.71it/s]
Train steps ... :  54%|█████▎    | 53623/100000 [15:51:52<7:32:11,  1.71it/s]
Train steps ... :  54%|█████▎    | 53624/100000 [15:51:53<7:32:32,  1.71it/s]
Train steps ... :  54%|█████▎    | 53625/100000 [15:51:53<7:32:14,  1.71it/s]Step... (53625 / 100000 | Loss: 0.9595383405685425, Learning Rate: 4.6608040201005026e-05)
+
                                                                             
Step... (53625 / 100000 | Loss: 0.7673168182373047, Learning Rate: 4.6608040201005026e-05)
+
Train steps ... :  54%|█████▎    | 53625/100000 [15:51:54<7:32:14,  1.71it/s]
Train steps ... :  54%|█████▎    | 53626/100000 [15:51:54<7:32:02,  1.71it/s]
Train steps ... :  54%|█████▎    | 53627/100000 [15:51:55<7:31:43,  1.71it/s]
Train steps ... :  54%|█████▎    | 53628/100000 [15:51:55<7:31:58,  1.71it/s]
Train steps ... :  54%|█████▎    | 53629/100000 [15:51:56<7:31:53,  1.71it/s]
Train steps ... :  54%|█████▎    | 53630/100000 [15:51:56<7:31:52,  1.71it/s]
Train steps ... :  54%|█████▎    | 53631/100000 [15:51:57<7:31:46,  1.71it/s]
Train steps ... :  54%|█████▎    | 53632/100000 [15:51:58<7:31:42,  1.71it/s]
Train steps ... :  54%|█████▎    | 53633/100000 [15:51:58<7:31:43,  1.71it/s]
Train steps ... :  54%|█████▎    | 53634/100000 [15:51:59<7:31:55,  1.71it/s]
Train steps ... :  54%|█████▎    | 53635/100000 [15:51:59<7:31:50,  1.71it/s]
Train steps ... :  54%|█████▎    | 53636/100000 [15:52:00<7:32:01,  1.71it/s]
Train steps ... :  54%|█████▎    | 53637/100000 [15:52:01<7:31:37,  1.71it/s]
Train steps ... :  54%|█████▎    | 53638/100000 [15:52:01<7:31:40,  1.71it/s]
Train steps ... :  54%|█████▎    | 53639/100000 [15:52:02<7:32:12,  1.71it/s]
Train steps ... :  54%|█████▎    | 53640/100000 [15:52:02<7:32:07,  1.71it/s]
Train steps ... :  54%|█████▎    | 53641/100000 [15:52:03<7:32:10,  1.71it/s]
Train steps ... :  54%|█████▎    | 53642/100000 [15:52:03<7:32:52,  1.71it/s]
Train steps ... :  54%|█████▎    | 53643/100000 [15:52:04<7:32:55,  1.71it/s]
Train steps ... :  54%|█████▎    | 53644/100000 [15:52:05<7:32:21,  1.71it/s]
Train steps ... :  54%|█████▎    | 53645/100000 [15:52:05<7:31:43,  1.71it/s]
Train steps ... :  54%|█████▎    | 53646/100000 [15:52:06<7:31:51,  1.71it/s]
Train steps ... :  54%|█████▎    | 53647/100000 [15:52:06<7:32:02,  1.71it/s]
Train steps ... :  54%|█████▎    | 53648/100000 [15:52:07<7:31:50,  1.71it/s]
Train steps ... :  54%|█████▎    | 53649/100000 [15:52:08<7:32:32,  1.71it/s]
Train steps ... :  54%|█████��    | 53650/100000 [15:52:08<7:31:41,  1.71it/s]Step... (53650 / 100000 | Loss: 0.619880199432373, Learning Rate: 4.658291457286432e-05)
+
                                                                             
Step... (53650 / 100000 | Loss: 0.5434302091598511, Learning Rate: 4.658291457286432e-05)
+
Train steps ... :  54%|█████▎    | 53650/100000 [15:52:08<7:31:41,  1.71it/s]
Train steps ... :  54%|█████▎    | 53651/100000 [15:52:09<7:32:17,  1.71it/s]
Train steps ... :  54%|█████▎    | 53652/100000 [15:52:09<7:32:25,  1.71it/s]
Train steps ... :  54%|█████▎    | 53653/100000 [15:52:10<7:32:17,  1.71it/s]
Train steps ... :  54%|█████▎    | 53654/100000 [15:52:10<7:31:50,  1.71it/s]
Train steps ... :  54%|█████▎    | 53655/100000 [15:52:11<7:31:59,  1.71it/s]
Train steps ... :  54%|█████▎    | 53656/100000 [15:52:12<7:31:25,  1.71it/s]
Train steps ... :  54%|█████▎    | 53657/100000 [15:52:12<7:31:37,  1.71it/s]
Train steps ... :  54%|█████▎    | 53658/100000 [15:52:13<7:31:44,  1.71it/s]
Train steps ... :  54%|█████▎    | 53659/100000 [15:52:13<7:31:22,  1.71it/s]
Train steps ... :  54%|█████▎    | 53660/100000 [15:52:14<7:31:14,  1.71it/s]
Train steps ... :  54%|█████▎    | 53661/100000 [15:52:15<7:31:03,  1.71it/s]
Train steps ... :  54%|█████▎    | 53662/100000 [15:52:15<7:31:16,  1.71it/s]
Train steps ... :  54%|█████▎    | 53663/100000 [15:52:16<7:31:03,  1.71it/s]
Train steps ... :  54%|█████▎    | 53664/100000 [15:52:16<7:31:08,  1.71it/s]
Train steps ... :  54%|█████▎    | 53665/100000 [15:52:17<7:30:51,  1.71it/s]
Train steps ... :  54%|█████▎    | 53666/100000 [15:52:17<7:31:07,  1.71it/s]
Train steps ... :  54%|█████▎    | 53667/100000 [15:52:18<7:31:05,  1.71it/s]
Train steps ... :  54%|█████▎    | 53668/100000 [15:52:19<7:31:22,  1.71it/s]
Train steps ... :  54%|█████▎    | 53669/100000 [15:52:19<7:31:16,  1.71it/s]
Train steps ... :  54%|█████▎    | 53670/100000 [15:52:20<7:31:26,  1.71it/s]
Train steps ... :  54%|█████▎    | 53671/100000 [15:52:20<7:31:41,  1.71it/s]
Train steps ... :  54%|█████▎    | 53672/100000 [15:52:21<7:31:03,  1.71it/s]
Train steps ... :  54%|█████▎    | 53673/100000 [15:52:22<7:31:10,  1.71it/s]
Train steps ... :  54%|█████▎    | 53674/100000 [15:52:22<7:30:50,  1.71it/s]
Train steps ... :  54%|█████▎    | 53675/100000 [15:52:23<7:30:54,  1.71it/s]Step... (53675 / 100000 | Loss: 0.8185029029846191, Learning Rate: 4.655778894472362e-05)
+
                                                                             
Step... (53675 / 100000 | Loss: 0.7925316095352173, Learning Rate: 4.655778894472362e-05)
+
Train steps ... :  54%|█████▎    | 53675/100000 [15:52:23<7:30:54,  1.71it/s]
Train steps ... :  54%|█████▎    | 53676/100000 [15:52:23<7:30:44,  1.71it/s]
Train steps ... :  54%|█████▎    | 53677/100000 [15:52:24<7:31:00,  1.71it/s]
Train steps ... :  54%|█████▎    | 53678/100000 [15:52:24<7:30:42,  1.71it/s]
Train steps ... :  54%|█████▎    | 53679/100000 [15:52:25<7:31:09,  1.71it/s]
Train steps ... :  54%|█████▎    | 53680/100000 [15:52:26<7:31:06,  1.71it/s]
Train steps ... :  54%|█████▎    | 53681/100000 [15:52:26<7:30:57,  1.71it/s]
Train steps ... :  54%|█████▎    | 53682/100000 [15:52:27<7:30:58,  1.71it/s]
Train steps ... :  54%|█████▎    | 53683/100000 [15:52:27<7:30:57,  1.71it/s]
Train steps ... :  54%|█████▎    | 53684/100000 [15:52:28<7:30:47,  1.71it/s]
Train steps ... :  54%|█████▎    | 53685/100000 [15:52:29<7:31:03,  1.71it/s]
Train steps ... :  54%|█████▎    | 53686/100000 [15:52:29<7:30:57,  1.71it/s]
Train steps ... :  54%|█████▎    | 53687/100000 [15:52:30<7:31:03,  1.71it/s]
Train steps ... :  54%|█████▎    | 53688/100000 [15:52:30<7:31:03,  1.71it/s]
Train steps ... :  54%|█████▎    | 53689/100000 [15:52:31<7:31:01,  1.71it/s]
Train steps ... :  54%|█████▎    | 53690/100000 [15:52:31<7:30:44,  1.71it/s]
Train steps ... :  54%|█████▎    | 53691/100000 [15:52:32<7:31:14,  1.71it/s]
Train steps ... :  54%|█████▎    | 53692/100000 [15:52:33<7:31:28,  1.71it/s]
Train steps ... :  54%|█████▎    | 53693/100000 [15:52:33<7:31:11,  1.71it/s]
Train steps ... :  54%|█████▎    | 53694/100000 [15:52:34<7:30:57,  1.71it/s]
Train steps ... :  54%|█████▎    | 53695/100000 [15:52:34<7:31:06,  1.71it/s]
Train steps ... :  54%|█████▎    | 53696/100000 [15:52:35<7:31:45,  1.71it/s]
Train steps ... :  54%|█████▎    | 53697/100000 [15:52:36<7:31:25,  1.71it/s]
Train steps ... :  54%|█████▎    | 53698/100000 [15:52:36<7:31:28,  1.71it/s]
Train steps ... :  54%|█████▎    | 53699/100000 [15:52:37<7:31:33,  1.71it/s]
Train steps ... :  54%|█████▎    | 53700/100000 [15:52:37<7:31:20,  1.71it/s]Step... (53700 / 100000 | Loss: 0.7133066058158875, Learning Rate: 4.653266331658292e-05)
+
                                                                             
Step... (53700 / 100000 | Loss: 0.9575806260108948, Learning Rate: 4.653266331658292e-05)
+
Train steps ... :  54%|█████▎    | 53700/100000 [15:52:38<7:31:20,  1.71it/s]
Train steps ... :  54%|█████▎    | 53701/100000 [15:52:38<7:31:19,  1.71it/s]
Train steps ... :  54%|█████▎    | 53702/100000 [15:52:39<7:31:39,  1.71it/s]
Train steps ... :  54%|█████▎    | 53703/100000 [15:52:39<7:31:57,  1.71it/s]
Train steps ... :  54%|█████▎    | 53704/100000 [15:52:40<7:31:34,  1.71it/s]
Train steps ... :  54%|█████▎    | 53705/100000 [15:52:40<7:31:19,  1.71it/s]
Train steps ... :  54%|█████▎    | 53706/100000 [15:52:41<7:31:27,  1.71it/s]
Train steps ... :  54%|█████▎    | 53707/100000 [15:52:41<7:31:16,  1.71it/s]
Train steps ... :  54%|█████▎    | 53708/100000 [15:52:42<7:31:00,  1.71it/s]
Train steps ... :  54%|█████▎    | 53709/100000 [15:52:43<7:30:56,  1.71it/s]
Train steps ... :  54%|█████▎    | 53710/100000 [15:52:43<7:30:54,  1.71it/s]
Train steps ... :  54%|█████▎    | 53711/100000 [15:52:44<7:30:49,  1.71it/s]
Train steps ... :  54%|█████▎    | 53712/100000 [15:52:44<7:31:08,  1.71it/s]
Train steps ... :  54%|█████▎    | 53713/100000 [15:52:45<7:31:40,  1.71it/s]
Train steps ... :  54%|█████▎    | 53714/100000 [15:52:46<7:31:26,  1.71it/s]
Train steps ... :  54%|█████▎    | 53715/100000 [15:52:46<7:31:20,  1.71it/s]
Train steps ... :  54%|█████▎    | 53716/100000 [15:52:47<7:31:24,  1.71it/s]
Train steps ... :  54%|█████▎    | 53717/100000 [15:52:47<7:31:52,  1.71it/s]
Train steps ... :  54%|█████▎    | 53718/100000 [15:52:48<7:31:25,  1.71it/s]
Train steps ... :  54%|█████▎    | 53719/100000 [15:52:48<7:30:59,  1.71it/s]
Train steps ... :  54%|█████▎    | 53720/100000 [15:52:49<7:30:55,  1.71it/s]
Train steps ... :  54%|█████▎    | 53721/100000 [15:52:50<7:30:59,  1.71it/s]
Train steps ... :  54%|█████▎    | 53722/100000 [15:52:50<7:30:49,  1.71it/s]
Train steps ... :  54%|█████▎    | 53723/100000 [15:52:51<7:30:51,  1.71it/s]
Train steps ... :  54%|█████▎    | 53724/100000 [15:52:51<7:31:25,  1.71it/s]
Train steps ... :  54%|█████▎    | 53725/100000 [15:52:52<7:31:08,  1.71it/s]Step... (53725 / 100000 | Loss: 0.5987159013748169, Learning Rate: 4.650753768844221e-05)
+
                                                                             
Step... (53725 / 100000 | Loss: 0.8742696046829224, Learning Rate: 4.650753768844221e-05)
+
Train steps ... :  54%|█████▎    | 53725/100000 [15:52:52<7:31:08,  1.71it/s]
Train steps ... :  54%|█████▎    | 53726/100000 [15:52:53<7:31:26,  1.71it/s]
Train steps ... :  54%|█████▎    | 53727/100000 [15:52:53<7:31:03,  1.71it/s]
Train steps ... :  54%|█████▎    | 53728/100000 [15:52:54<7:30:50,  1.71it/s]
Train steps ... :  54%|█████▎    | 53729/100000 [15:52:54<7:30:22,  1.71it/s]
Train steps ... :  54%|█████▎    | 53730/100000 [15:52:55<7:30:52,  1.71it/s]
Train steps ... :  54%|█████▎    | 53731/100000 [15:52:55<7:30:43,  1.71it/s]
Train steps ... :  54%|█████▎    | 53732/100000 [15:52:56<7:31:07,  1.71it/s]
Train steps ... :  54%|█████▎    | 53733/100000 [15:52:57<7:31:30,  1.71it/s]
Train steps ... :  54%|█████▎    | 53734/100000 [15:52:57<7:31:19,  1.71it/s]
Train steps ... :  54%|█████▎    | 53735/100000 [15:52:58<7:31:26,  1.71it/s]
Train steps ... :  54%|█████▎    | 53736/100000 [15:52:58<7:31:03,  1.71it/s]
Train steps ... :  54%|█████▎    | 53737/100000 [15:52:59<7:30:53,  1.71it/s]
Train steps ... :  54%|█████▎    | 53738/100000 [15:53:00<7:31:07,  1.71it/s]
Train steps ... :  54%|█████▎    | 53739/100000 [15:53:00<7:30:46,  1.71it/s]
Train steps ... :  54%|█████▎    | 53740/100000 [15:53:01<7:31:32,  1.71it/s]
Train steps ... :  54%|█████▎    | 53741/100000 [15:53:01<7:31:36,  1.71it/s]
Train steps ... :  54%|█████▎    | 53742/100000 [15:53:02<7:31:13,  1.71it/s]
Train steps ... :  54%|█████▎    | 53743/100000 [15:53:02<7:30:45,  1.71it/s]
Train steps ... :  54%|█████▎    | 53744/100000 [15:53:03<7:30:37,  1.71it/s]
Train steps ... :  54%|█████▎    | 53745/100000 [15:53:04<7:30:51,  1.71it/s]
Train steps ... :  54%|█████▎    | 53746/100000 [15:53:04<7:31:12,  1.71it/s]
Train steps ... :  54%|█████▎    | 53747/100000 [15:53:05<7:31:07,  1.71it/s]
Train steps ... :  54%|█████▎    | 53748/100000 [15:53:05<7:31:10,  1.71it/s]
Train steps ... :  54%|█████▎    | 53749/100000 [15:53:06<7:31:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 53750/100000 [15:53:07<7:31:37,  1.71it/s]Step... (53750 / 100000 | Loss: 0.76506507396698, Learning Rate: 4.648241206030151e-05)
+
                                                                             
Step... (53750 / 100000 | Loss: 0.6585092544555664, Learning Rate: 4.648241206030151e-05)
+
Train steps ... :  54%|█████▍    | 53750/100000 [15:53:07<7:31:37,  1.71it/s]
Train steps ... :  54%|█████▍    | 53751/100000 [15:53:07<7:31:37,  1.71it/s]
Train steps ... :  54%|█████▍    | 53752/100000 [15:53:08<7:31:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 53753/100000 [15:53:08<7:30:50,  1.71it/s]
Train steps ... :  54%|█████▍    | 53754/100000 [15:53:09<7:30:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 53755/100000 [15:53:10<7:30:47,  1.71it/s]
Train steps ... :  54%|█████▍    | 53756/100000 [15:53:10<7:30:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 53757/100000 [15:53:11<7:30:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 53758/100000 [15:53:11<7:30:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 53759/100000 [15:53:12<7:30:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 53760/100000 [15:53:12<7:30:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 53761/100000 [15:53:13<7:30:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 53762/100000 [15:53:14<7:30:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 53763/100000 [15:53:14<7:30:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 53764/100000 [15:53:15<7:30:52,  1.71it/s]
Train steps ... :  54%|█████▍    | 53765/100000 [15:53:15<7:31:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 53766/100000 [15:53:16<7:31:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 53767/100000 [15:53:17<7:30:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 53768/100000 [15:53:17<7:31:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 53769/100000 [15:53:18<7:30:47,  1.71it/s]
Train steps ... :  54%|█████▍    | 53770/100000 [15:53:18<7:30:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 53771/100000 [15:53:19<7:30:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 53772/100000 [15:53:19<7:30:50,  1.71it/s]
Train steps ... :  54%|█████▍    | 53773/100000 [15:53:20<7:30:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 53774/100000 [15:53:21<7:30:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 53775/100000 [15:53:21<7:30:20,  1.71it/s]Step... (53775 / 100000 | Loss: 0.915186882019043, Learning Rate: 4.6457286432160806e-05)
+
                                                                             
Step... (53775 / 100000 | Loss: 0.8264679312705994, Learning Rate: 4.6457286432160806e-05)
+
Train steps ... :  54%|█████▍    | 53775/100000 [15:53:22<7:30:20,  1.71it/s]
Train steps ... :  54%|█████▍    | 53776/100000 [15:53:22<7:30:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 53777/100000 [15:53:22<7:30:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 53778/100000 [15:53:23<7:30:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 53779/100000 [15:53:24<7:30:49,  1.71it/s]
Train steps ... :  54%|█████▍    | 53780/100000 [15:53:24<7:30:51,  1.71it/s]
Train steps ... :  54%|█████▍    | 53781/100000 [15:53:25<7:30:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 53782/100000 [15:53:25<7:30:21,  1.71it/s]
Train steps ... :  54%|█████▍    | 53783/100000 [15:53:26<7:30:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 53784/100000 [15:53:26<7:30:55,  1.71it/s]
Train steps ... :  54%|█████▍    | 53785/100000 [15:53:27<7:31:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 53786/100000 [15:53:28<7:30:21,  1.71it/s]
Train steps ... :  54%|█████▍    | 53787/100000 [15:53:28<7:30:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 53788/100000 [15:53:29<7:30:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 53789/100000 [15:53:29<7:30:12,  1.71it/s]
Train steps ... :  54%|█████▍    | 53790/100000 [15:53:30<7:30:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 53791/100000 [15:53:31<7:29:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 53792/100000 [15:53:31<7:30:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 53793/100000 [15:53:32<7:30:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 53794/100000 [15:53:32<7:30:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 53795/100000 [15:53:33<7:29:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 53796/100000 [15:53:33<7:29:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 53797/100000 [15:53:34<7:29:52,  1.71it/s]
Train steps ... :  54%|█████▍    | 53798/100000 [15:53:35<7:29:49,  1.71it/s]
Train steps ... :  54%|█████▍    | 53799/100000 [15:53:35<7:30:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 53800/100000 [15:53:36<7:30:22,  1.71it/s]Step... (53800 / 100000 | Loss: 1.0057811737060547, Learning Rate: 4.64321608040201e-05)
+
                                                                             
Step... (53800 / 100000 | Loss: 1.008401870727539, Learning Rate: 4.64321608040201e-05)
+
Train steps ... :  54%|█████▍    | 53800/100000 [15:53:36<7:30:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 53801/100000 [15:53:36<7:30:35,  1.71it/s]
Train steps ... :  54%|█████▍    | 53802/100000 [15:53:37<7:30:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 53803/100000 [15:53:38<7:30:01,  1.71it/s]
Train steps ... :  54%|█████▍    | 53804/100000 [15:53:38<7:29:37,  1.71it/s]
Train steps ... :  54%|█████▍    | 53805/100000 [15:53:39<7:29:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 53806/100000 [15:53:39<7:29:46,  1.71it/s]
Train steps ... :  54%|█████▍    | 53807/100000 [15:53:40<7:29:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 53808/100000 [15:53:41<7:29:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 53809/100000 [15:53:41<7:29:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 53810/100000 [15:53:42<7:29:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 53811/100000 [15:53:42<7:29:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 53812/100000 [15:53:43<7:29:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 53813/100000 [15:53:43<7:29:51,  1.71it/s]
Train steps ... :  54%|█████▍    | 53814/100000 [15:53:44<7:29:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 53815/100000 [15:53:45<7:30:21,  1.71it/s]
Train steps ... :  54%|█████▍    | 53816/100000 [15:53:45<7:30:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 53817/100000 [15:53:46<7:30:21,  1.71it/s]
Train steps ... :  54%|█████▍    | 53818/100000 [15:53:46<7:30:00,  1.71it/s]
Train steps ... :  54%|█████▍    | 53819/100000 [15:53:47<7:30:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 53820/100000 [15:53:48<7:30:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 53821/100000 [15:53:48<7:30:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 53822/100000 [15:53:49<7:29:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 53823/100000 [15:53:49<7:29:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 53824/100000 [15:53:50<7:29:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 53825/100000 [15:53:50<7:29:43,  1.71it/s]Step... (53825 / 100000 | Loss: 0.6313787698745728, Learning Rate: 4.64070351758794e-05)
+
                                                                             
Step... (53825 / 100000 | Loss: 0.6868913769721985, Learning Rate: 4.64070351758794e-05)
+
Train steps ... :  54%|█████▍    | 53825/100000 [15:53:51<7:29:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 53826/100000 [15:53:51<7:29:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 53827/100000 [15:53:52<7:29:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 53828/100000 [15:53:52<7:29:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 53829/100000 [15:53:53<7:29:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 53830/100000 [15:53:53<7:30:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 53831/100000 [15:53:54<7:29:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 53832/100000 [15:53:55<7:29:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 53833/100000 [15:53:55<7:29:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 53834/100000 [15:53:56<7:29:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 53835/100000 [15:53:56<7:29:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 53836/100000 [15:53:57<7:29:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 53837/100000 [15:53:57<7:29:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 53838/100000 [15:53:58<7:29:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 53839/100000 [15:53:59<7:30:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 53840/100000 [15:53:59<7:29:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 53841/100000 [15:54:00<7:29:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 53842/100000 [15:54:00<7:29:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 53843/100000 [15:54:01<7:29:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 53844/100000 [15:54:02<7:30:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 53845/100000 [15:54:02<7:29:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 53846/100000 [15:54:03<7:29:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 53847/100000 [15:54:03<7:30:20,  1.71it/s]
Train steps ... :  54%|█████▍    | 53848/100000 [15:54:04<7:29:46,  1.71it/s]
Train steps ... :  54%|█████▍    | 53849/100000 [15:54:04<7:30:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 53850/100000 [15:54:05<7:30:09,  1.71it/s]Step... (53850 / 100000 | Loss: 0.5790723562240601, Learning Rate: 4.6381909547738695e-05)
+
                                                                             
Step... (53850 / 100000 | Loss: 0.6120836734771729, Learning Rate: 4.6381909547738695e-05)
+
Train steps ... :  54%|█████▍    | 53850/100000 [15:54:05<7:30:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 53851/100000 [15:54:06<7:30:03,  1.71it/s]
Train steps ... :  54%|█████▍    | 53852/100000 [15:54:06<7:29:49,  1.71it/s]
Train steps ... :  54%|█████▍    | 53853/100000 [15:54:07<7:30:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 53854/100000 [15:54:07<7:30:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 53855/100000 [15:54:08<7:29:46,  1.71it/s]
Train steps ... :  54%|█████▍    | 53856/100000 [15:54:09<7:29:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 53857/100000 [15:54:09<7:29:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 53858/100000 [15:54:10<7:29:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 53859/100000 [15:54:10<7:29:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 53860/100000 [15:54:11<7:29:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 53861/100000 [15:54:11<7:29:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 53862/100000 [15:54:12<7:30:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 53863/100000 [15:54:13<7:30:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 53864/100000 [15:54:13<7:29:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 53865/100000 [15:54:14<7:30:03,  1.71it/s]
Train steps ... :  54%|█████▍    | 53866/100000 [15:54:14<7:29:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 53867/100000 [15:54:15<7:30:12,  1.71it/s]
Train steps ... :  54%|█████▍    | 53868/100000 [15:54:16<7:30:16,  1.71it/s]
Train steps ... :  54%|█████▍    | 53869/100000 [15:54:16<7:30:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 53870/100000 [15:54:17<7:29:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 53871/100000 [15:54:17<7:31:05,  1.70it/s]
Train steps ... :  54%|█████▍    | 53872/100000 [15:54:18<7:30:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 53873/100000 [15:54:19<7:30:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 53874/100000 [15:54:19<7:29:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 53875/100000 [15:54:20<7:30:01,  1.71it/s]Step... (53875 / 100000 | Loss: 0.9343838691711426, Learning Rate: 4.635678391959799e-05)
+
                                                                             
Step... (53875 / 100000 | Loss: 0.8987624645233154, Learning Rate: 4.635678391959799e-05)
+
Train steps ... :  54%|█████▍    | 53875/100000 [15:54:20<7:30:01,  1.71it/s]
Train steps ... :  54%|█████▍    | 53876/100000 [15:54:20<7:29:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 53877/100000 [15:54:21<7:29:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 53878/100000 [15:54:21<7:29:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 53879/100000 [15:54:22<7:29:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 53880/100000 [15:54:23<7:28:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 53881/100000 [15:54:23<7:28:50,  1.71it/s]
Train steps ... :  54%|█████▍    | 53882/100000 [15:54:24<7:28:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 53883/100000 [15:54:24<7:28:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 53884/100000 [15:54:25<7:29:20,  1.71it/s]
Train steps ... :  54%|█████▍    | 53885/100000 [15:54:26<7:28:50,  1.71it/s]
Train steps ... :  54%|█████▍    | 53886/100000 [15:54:26<7:29:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 53887/100000 [15:54:27<7:29:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 53888/100000 [15:54:27<7:29:55,  1.71it/s]
Train steps ... :  54%|█████▍    | 53889/100000 [15:54:28<7:29:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 53890/100000 [15:54:28<7:29:13,  1.71it/s]
Train steps ... :  54%|█████▍    | 53891/100000 [15:54:29<7:29:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 53892/100000 [15:54:30<7:28:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 53893/100000 [15:54:30<7:29:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 53894/100000 [15:54:31<7:28:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 53895/100000 [15:54:31<7:29:00,  1.71it/s]
Train steps ... :  54%|█████▍    | 53896/100000 [15:54:32<7:29:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 53897/100000 [15:54:33<7:29:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 53898/100000 [15:54:33<7:29:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 53899/100000 [15:54:34<7:29:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 53900/100000 [15:54:34<7:29:08,  1.71it/s]Step... (53900 / 100000 | Loss: 1.0301759243011475, Learning Rate: 4.633165829145729e-05)
+
                                                                             
Step... (53900 / 100000 | Loss: 0.792059063911438, Learning Rate: 4.633165829145729e-05)
+
Train steps ... :  54%|█████▍    | 53900/100000 [15:54:35<7:29:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 53901/100000 [15:54:35<7:29:16,  1.71it/s]
Train steps ... :  54%|█████▍    | 53902/100000 [15:54:35<7:28:51,  1.71it/s]
Train steps ... :  54%|█████▍    | 53903/100000 [15:54:36<7:29:37,  1.71it/s]
Train steps ... :  54%|█████▍    | 53904/100000 [15:54:37<7:29:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 53905/100000 [15:54:37<7:29:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 53906/100000 [15:54:38<7:29:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 53907/100000 [15:54:38<7:28:46,  1.71it/s]
Train steps ... :  54%|█████▍    | 53908/100000 [15:54:39<7:28:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 53909/100000 [15:54:40<7:28:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 53910/100000 [15:54:40<7:28:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 53911/100000 [15:54:41<7:28:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 53912/100000 [15:54:41<7:28:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 53913/100000 [15:54:42<7:28:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 53914/100000 [15:54:42<7:28:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 53915/100000 [15:54:43<7:28:37,  1.71it/s]
Train steps ... :  54%|█████▍    | 53916/100000 [15:54:44<7:28:13,  1.71it/s]
Train steps ... :  54%|█████▍    | 53917/100000 [15:54:44<7:28:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 53918/100000 [15:54:45<7:28:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 53919/100000 [15:54:45<7:28:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 53920/100000 [15:54:46<7:28:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 53921/100000 [15:54:47<7:28:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 53922/100000 [15:54:47<7:28:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 53923/100000 [15:54:48<7:28:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 53924/100000 [15:54:48<7:28:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 53925/100000 [15:54:49<7:28:28,  1.71it/s]Step... (53925 / 100000 | Loss: 0.6625066995620728, Learning Rate: 4.6306532663316585e-05)
+
                                                                             
Step... (53925 / 100000 | Loss: 0.7225705981254578, Learning Rate: 4.6306532663316585e-05)
+
Train steps ... :  54%|█████▍    | 53925/100000 [15:54:49<7:28:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 53926/100000 [15:54:49<7:28:35,  1.71it/s]
Train steps ... :  54%|█████▍    | 53927/100000 [15:54:50<7:28:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 53928/100000 [15:54:51<7:28:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 53929/100000 [15:54:51<7:28:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 53930/100000 [15:54:52<7:28:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 53931/100000 [15:54:52<7:28:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 53932/100000 [15:54:53<7:28:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 53933/100000 [15:54:54<7:28:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 53934/100000 [15:54:54<7:28:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 53935/100000 [15:54:55<7:28:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 53936/100000 [15:54:55<7:28:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 53937/100000 [15:54:56<7:28:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 53938/100000 [15:54:57<7:30:12,  1.71it/s]
Train steps ... :  54%|█████▍    | 53939/100000 [15:54:57<7:29:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 53940/100000 [15:54:58<7:29:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 53941/100000 [15:54:58<7:29:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 53942/100000 [15:54:59<7:29:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 53943/100000 [15:54:59<7:28:49,  1.71it/s]
Train steps ... :  54%|█████▍    | 53944/100000 [15:55:00<7:28:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 53945/100000 [15:55:01<7:28:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 53946/100000 [15:55:01<7:28:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 53947/100000 [15:55:02<7:28:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 53948/100000 [15:55:02<7:29:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 53949/100000 [15:55:03<7:29:01,  1.71it/s]
Train steps ... :  54%|█████▍    | 53950/100000 [15:55:04<7:28:44,  1.71it/s]Step... (53950 / 100000 | Loss: 0.9067845940589905, Learning Rate: 4.628140703517588e-05)
+
                                                                             
Step... (53950 / 100000 | Loss: 0.8715093731880188, Learning Rate: 4.628140703517588e-05)
+
Train steps ... :  54%|█████▍    | 53950/100000 [15:55:04<7:28:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 53951/100000 [15:55:04<7:29:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 53952/100000 [15:55:05<7:29:01,  1.71it/s]
Train steps ... :  54%|█████▍    | 53953/100000 [15:55:05<7:28:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 53954/100000 [15:55:06<7:28:55,  1.71it/s]
Train steps ... :  54%|█████▍    | 53955/100000 [15:55:06<7:28:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 53956/100000 [15:55:07<7:28:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 53957/100000 [15:55:08<7:28:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 53958/100000 [15:55:08<7:28:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 53959/100000 [15:55:09<7:28:46,  1.71it/s]
Train steps ... :  54%|█████▍    | 53960/100000 [15:55:09<7:28:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 53961/100000 [15:55:10<7:28:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 53962/100000 [15:55:11<7:28:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 53963/100000 [15:55:11<7:28:52,  1.71it/s]
Train steps ... :  54%|█████▍    | 53964/100000 [15:55:12<7:29:03,  1.71it/s]
Train steps ... :  54%|█████▍    | 53965/100000 [15:55:12<7:29:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 53966/100000 [15:55:13<7:28:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 53967/100000 [15:55:13<7:28:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 53968/100000 [15:55:14<7:28:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 53969/100000 [15:55:15<7:28:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 53970/100000 [15:55:15<7:28:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 53971/100000 [15:55:16<7:28:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 53972/100000 [15:55:16<7:29:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 53973/100000 [15:55:17<7:29:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 53974/100000 [15:55:18<7:28:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 53975/100000 [15:55:18<7:28:47,  1.71it/s]Step... (53975 / 100000 | Loss: 0.7017648220062256, Learning Rate: 4.625628140703518e-05)
+
                                                                             
Step... (53975 / 100000 | Loss: 0.48781269788742065, Learning Rate: 4.625628140703518e-05)
+
Train steps ... :  54%|█████▍    | 53975/100000 [15:55:18<7:28:47,  1.71it/s]
Train steps ... :  54%|█████▍    | 53976/100000 [15:55:19<7:28:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 53977/100000 [15:55:19<7:29:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 53978/100000 [15:55:20<7:28:35,  1.71it/s]
Train steps ... :  54%|█████▍    | 53979/100000 [15:55:20<7:28:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 53980/100000 [15:55:21<7:28:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 53981/100000 [15:55:22<7:28:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 53982/100000 [15:55:22<7:28:14,  1.71it/s]
Train steps ... :  54%|█████▍    | 53983/100000 [15:55:23<7:28:37,  1.71it/s]
Train steps ... :  54%|█████▍    | 53984/100000 [15:55:23<7:28:16,  1.71it/s]
Train steps ... :  54%|█████▍    | 53985/100000 [15:55:24<7:28:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 53986/100000 [15:55:25<7:28:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 53987/100000 [15:55:25<7:28:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 53988/100000 [15:55:26<7:28:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 53989/100000 [15:55:26<7:28:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 53990/100000 [15:55:27<7:29:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 53991/100000 [15:55:28<7:28:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 53992/100000 [15:55:28<7:28:14,  1.71it/s]
Train steps ... :  54%|█████▍    | 53993/100000 [15:55:29<7:28:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 53994/100000 [15:55:29<7:28:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 53995/100000 [15:55:30<7:28:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 53996/100000 [15:55:30<7:28:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 53997/100000 [15:55:31<7:28:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 53998/100000 [15:55:32<7:28:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 53999/100000 [15:55:32<7:28:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 54000/100000 [15:55:33<7:29:03,  1.71it/s]Step... (54000 / 100000 | Loss: 0.5463149547576904, Learning Rate: 4.6231155778894475e-05)
+
                                                                             
Step... (54000 / 100000 | Loss: 0.6871451139450073, Learning Rate: 4.6231155778894475e-05)
+
Train steps ... :  54%|█████▍    | 54000/100000 [15:55:33<7:29:03,  1.71it/s]
Train steps ... :  54%|█████▍    | 54001/100000 [15:55:33<7:28:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 54002/100000 [15:55:34<7:28:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 54003/100000 [15:55:35<7:28:12,  1.71it/s]
Train steps ... :  54%|█████▍    | 54004/100000 [15:55:35<7:27:51,  1.71it/s]
Train steps ... :  54%|█████▍    | 54005/100000 [15:55:36<7:28:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 54006/100000 [15:55:36<7:27:51,  1.71it/s]
Train steps ... :  54%|█████▍    | 54007/100000 [15:55:37<7:27:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 54008/100000 [15:55:37<7:28:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 54009/100000 [15:55:38<7:28:13,  1.71it/s]
Train steps ... :  54%|█████▍    | 54010/100000 [15:55:39<7:28:14,  1.71it/s]
Train steps ... :  54%|█████▍    | 54011/100000 [15:55:39<7:28:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 54012/100000 [15:55:40<7:28:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 54013/100000 [15:55:40<7:27:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 54014/100000 [15:55:41<7:28:16,  1.71it/s]
Train steps ... :  54%|█████▍    | 54015/100000 [15:55:42<7:28:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 54016/100000 [15:55:42<7:27:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54017/100000 [15:55:43<7:27:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 54018/100000 [15:55:43<7:27:49,  1.71it/s]
Train steps ... :  54%|█████▍    | 54019/100000 [15:55:44<7:27:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54020/100000 [15:55:44<7:27:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54021/100000 [15:55:45<7:27:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54022/100000 [15:55:46<7:28:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 54023/100000 [15:55:46<7:27:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54024/100000 [15:55:47<7:27:35,  1.71it/s]
Train steps ... :  54%|█████▍    | 54025/100000 [15:55:47<7:28:15,  1.71it/s]Step... (54025 / 100000 | Loss: 0.6619250774383545, Learning Rate: 4.620603015075377e-05)
+
                                                                             
Step... (54025 / 100000 | Loss: 0.7112640142440796, Learning Rate: 4.620603015075377e-05)
+
Train steps ... :  54%|█████▍    | 54025/100000 [15:55:48<7:28:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 54026/100000 [15:55:48<7:27:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 54027/100000 [15:55:49<7:27:16,  1.71it/s]
Train steps ... :  54%|█████▍    | 54028/100000 [15:55:49<7:27:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54029/100000 [15:55:50<7:27:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 54030/100000 [15:55:50<7:27:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54031/100000 [15:55:51<7:27:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54032/100000 [15:55:51<7:27:51,  1.71it/s]
Train steps ... :  54%|█████▍    | 54033/100000 [15:55:52<7:28:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 54034/100000 [15:55:53<7:28:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 54035/100000 [15:55:53<7:27:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 54036/100000 [15:55:54<7:27:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 54037/100000 [15:55:54<7:27:37,  1.71it/s]
Train steps ... :  54%|█████▍    | 54038/100000 [15:55:55<7:28:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 54039/100000 [15:55:56<7:28:01,  1.71it/s]
Train steps ... :  54%|█████▍    | 54040/100000 [15:55:56<7:28:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54041/100000 [15:55:57<7:28:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54042/100000 [15:55:57<7:28:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 54043/100000 [15:55:58<7:28:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 54044/100000 [15:55:58<7:28:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 54045/100000 [15:55:59<7:27:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54046/100000 [15:56:00<7:27:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 54047/100000 [15:56:00<7:27:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54048/100000 [15:56:01<7:27:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 54049/100000 [15:56:01<7:27:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 54050/100000 [15:56:02<7:27:17,  1.71it/s]Step... (54050 / 100000 | Loss: 0.9617835283279419, Learning Rate: 4.618090452261307e-05)
+
                                                                             
Step... (54050 / 100000 | Loss: 1.1257331371307373, Learning Rate: 4.618090452261307e-05)
+
Train steps ... :  54%|█████▍    | 54050/100000 [15:56:02<7:27:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 54051/100000 [15:56:03<7:27:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54052/100000 [15:56:03<7:27:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 54053/100000 [15:56:04<7:27:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 54054/100000 [15:56:04<7:27:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 54055/100000 [15:56:05<7:28:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 54056/100000 [15:56:06<7:27:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 54057/100000 [15:56:06<7:28:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 54058/100000 [15:56:07<7:28:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 54059/100000 [15:56:07<7:28:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 54060/100000 [15:56:08<7:28:00,  1.71it/s]
Train steps ... :  54%|█████▍    | 54061/100000 [15:56:08<7:27:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 54062/100000 [15:56:09<7:28:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 54063/100000 [15:56:10<7:27:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 54064/100000 [15:56:10<7:27:13,  1.71it/s]
Train steps ... :  54%|█████▍    | 54065/100000 [15:56:11<7:26:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 54066/100000 [15:56:11<7:27:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 54067/100000 [15:56:12<7:27:03,  1.71it/s]
Train steps ... :  54%|█████▍    | 54068/100000 [15:56:13<7:27:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 54069/100000 [15:56:13<7:27:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54070/100000 [15:56:14<7:27:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 54071/100000 [15:56:14<7:27:13,  1.71it/s]
Train steps ... :  54%|█████▍    | 54072/100000 [15:56:15<7:27:50,  1.71it/s]
Train steps ... :  54%|█████▍    | 54073/100000 [15:56:15<7:28:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54074/100000 [15:56:16<7:27:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 54075/100000 [15:56:17<7:27:43,  1.71it/s]Step... (54075 / 100000 | Loss: 0.7806007862091064, Learning Rate: 4.6155778894472365e-05)
+
                                                                             
Step... (54075 / 100000 | Loss: 0.6146780252456665, Learning Rate: 4.6155778894472365e-05)
+
Train steps ... :  54%|█████▍    | 54075/100000 [15:56:17<7:27:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 54076/100000 [15:56:17<7:27:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 54077/100000 [15:56:18<7:27:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54078/100000 [15:56:18<7:27:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54079/100000 [15:56:19<7:27:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 54080/100000 [15:56:20<7:27:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 54081/100000 [15:56:20<7:27:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54082/100000 [15:56:21<7:26:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 54083/100000 [15:56:21<7:26:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54084/100000 [15:56:22<7:27:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54085/100000 [15:56:22<7:27:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 54086/100000 [15:56:23<7:27:20,  1.71it/s]
Train steps ... :  54%|█████▍    | 54087/100000 [15:56:24<7:27:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 54088/100000 [15:56:24<7:27:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 54089/100000 [15:56:25<7:27:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 54090/100000 [15:56:25<7:27:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 54091/100000 [15:56:26<7:27:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 54092/100000 [15:56:27<7:28:00,  1.71it/s]
Train steps ... :  54%|█████▍    | 54093/100000 [15:56:27<7:27:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 54094/100000 [15:56:28<7:27:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 54095/100000 [15:56:28<7:26:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54096/100000 [15:56:29<7:27:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 54097/100000 [15:56:29<7:26:52,  1.71it/s]
Train steps ... :  54%|█████▍    | 54098/100000 [15:56:30<7:26:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 54099/100000 [15:56:31<7:26:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54100/100000 [15:56:31<7:27:02,  1.71it/s]Step... (54100 / 100000 | Loss: 0.9151102304458618, Learning Rate: 4.6130653266331655e-05)
+
                                                                             
Step... (54100 / 100000 | Loss: 0.5686546564102173, Learning Rate: 4.6130653266331655e-05)
+
Train steps ... :  54%|█████▍    | 54100/100000 [15:56:32<7:27:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54101/100000 [15:56:32<7:27:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54102/100000 [15:56:32<7:27:14,  1.71it/s]
Train steps ... :  54%|█████▍    | 54103/100000 [15:56:33<7:27:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 54104/100000 [15:56:34<7:27:21,  1.71it/s]
Train steps ... :  54%|█████▍    | 54105/100000 [15:56:34<7:27:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54106/100000 [15:56:35<7:27:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54107/100000 [15:56:35<7:26:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 54108/100000 [15:56:36<7:26:47,  1.71it/s]
Train steps ... :  54%|█████▍    | 54109/100000 [15:56:36<7:27:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 54110/100000 [15:56:37<7:27:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 54111/100000 [15:56:38<7:27:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 54112/100000 [15:56:38<7:27:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 54113/100000 [15:56:39<7:27:46,  1.71it/s]
Train steps ... :  54%|█████▍    | 54114/100000 [15:56:39<7:27:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 54115/100000 [15:56:40<7:26:55,  1.71it/s]
Train steps ... :  54%|█████▍    | 54116/100000 [15:56:41<7:27:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 54117/100000 [15:56:41<7:27:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54118/100000 [15:56:42<7:26:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 54119/100000 [15:56:42<7:27:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54120/100000 [15:56:43<7:27:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 54121/100000 [15:56:44<7:27:35,  1.71it/s]
Train steps ... :  54%|█████▍    | 54122/100000 [15:56:44<7:27:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 54123/100000 [15:56:45<7:27:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54124/100000 [15:56:45<7:26:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 54125/100000 [15:56:46<7:27:23,  1.71it/s]Step... (54125 / 100000 | Loss: 0.6493918299674988, Learning Rate: 4.610552763819096e-05)
+
                                                                             
Step... (54125 / 100000 | Loss: 0.6974738240242004, Learning Rate: 4.610552763819096e-05)
+
Train steps ... :  54%|█████▍    | 54125/100000 [15:56:46<7:27:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 54126/100000 [15:56:46<7:28:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 54127/100000 [15:56:47<7:26:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 54128/100000 [15:56:48<7:27:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 54129/100000 [15:56:48<7:27:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 54130/100000 [15:56:49<7:26:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54131/100000 [15:56:49<7:26:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54132/100000 [15:56:50<7:26:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 54133/100000 [15:56:51<7:26:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 54134/100000 [15:56:51<7:26:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 54135/100000 [15:56:52<7:26:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 54136/100000 [15:56:52<7:26:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54137/100000 [15:56:53<7:26:35,  1.71it/s]
Train steps ... :  54%|█████▍    | 54138/100000 [15:56:53<7:26:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 54139/100000 [15:56:54<7:26:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 54140/100000 [15:56:55<7:26:41,  1.71it/s]
Train steps ... :  54%|█���███▍    | 54141/100000 [15:56:55<7:26:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54142/100000 [15:56:56<7:26:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 54143/100000 [15:56:56<7:26:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 54144/100000 [15:56:57<7:26:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 54145/100000 [15:56:58<7:26:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54146/100000 [15:56:58<7:26:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 54147/100000 [15:56:59<7:26:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 54148/100000 [15:56:59<7:26:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 54149/100000 [15:57:00<7:26:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54150/100000 [15:57:00<7:26:20,  1.71it/s]Step... (54150 / 100000 | Loss: 0.7986818552017212, Learning Rate: 4.6080402010050255e-05)
+
                                                                             
Step... (54150 / 100000 | Loss: 0.751227617263794, Learning Rate: 4.6080402010050255e-05)
+
Train steps ... :  54%|█████▍    | 54150/100000 [15:57:01<7:26:20,  1.71it/s]
Train steps ... :  54%|█████▍    | 54151/100000 [15:57:01<7:26:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 54152/100000 [15:57:02<7:27:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 54153/100000 [15:57:02<7:26:46,  1.71it/s]
Train steps ... :  54%|█████▍    | 54154/100000 [15:57:03<7:26:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 54155/100000 [15:57:03<7:26:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 54156/100000 [15:57:04<7:26:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 54157/100000 [15:57:05<7:26:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 54158/100000 [15:57:05<7:26:21,  1.71it/s]
Train steps ... :  54%|█████▍    | 54159/100000 [15:57:06<7:26:04,  1.71it/s]
Train steps ... :  54%|█████▍    | 54160/100000 [15:57:06<7:26:04,  1.71it/s]
Train steps ... :  54%|█████▍    | 54161/100000 [15:57:07<7:26:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 54162/100000 [15:57:07<7:26:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54163/100000 [15:57:08<7:25:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54164/100000 [15:57:09<7:25:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 54165/100000 [15:57:09<7:25:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54166/100000 [15:57:10<7:25:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 54167/100000 [15:57:10<7:25:55,  1.71it/s]
Train steps ... :  54%|█████▍    | 54168/100000 [15:57:11<7:25:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 54169/100000 [15:57:12<7:25:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 54170/100000 [15:57:12<7:25:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54171/100000 [15:57:13<7:25:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54172/100000 [15:57:13<7:25:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54173/100000 [15:57:14<7:25:49,  1.71it/s]
Train steps ... :  54%|█████▍    | 54174/100000 [15:57:14<7:25:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 54175/100000 [15:57:15<7:26:33,  1.71it/s]Step... (54175 / 100000 | Loss: 0.8820443153381348, Learning Rate: 4.605527638190955e-05)
+
                                                                             
Step... (54175 / 100000 | Loss: 0.7559001445770264, Learning Rate: 4.605527638190955e-05)
+
Train steps ... :  54%|█████▍    | 54175/100000 [15:57:15<7:26:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54176/100000 [15:57:16<7:27:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54177/100000 [15:57:16<7:27:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54178/100000 [15:57:17<7:28:05,  1.70it/s]
Train steps ... :  54%|█████▍    | 54179/100000 [15:57:17<7:26:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 54180/100000 [15:57:18<7:26:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 54181/100000 [15:57:19<7:25:49,  1.71it/s]
Train steps ... :  54%|█████▍    | 54182/100000 [15:57:19<7:26:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 54183/100000 [15:57:20<7:26:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 54184/100000 [15:57:20<7:26:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 54185/100000 [15:57:21<7:25:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 54186/100000 [15:57:21<7:26:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54187/100000 [15:57:22<7:26:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 54188/100000 [15:57:23<7:26:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54189/100000 [15:57:23<7:26:10,  1.71it/s]
Train steps ... :  54%|███��█▍    | 54190/100000 [15:57:24<7:26:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54191/100000 [15:57:24<7:25:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54192/100000 [15:57:25<7:25:52,  1.71it/s]
Train steps ... :  54%|█████▍    | 54193/100000 [15:57:26<7:25:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54194/100000 [15:57:26<7:25:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 54195/100000 [15:57:27<7:25:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54196/100000 [15:57:27<7:25:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 54197/100000 [15:57:28<7:25:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54198/100000 [15:57:29<7:26:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 54199/100000 [15:57:29<7:25:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54200/100000 [15:57:30<7:26:13,  1.71it/s]Step... (54200 / 100000 | Loss: 0.7832887172698975, Learning Rate: 4.603015075376885e-05)
+
                                                                             
Step... (54200 / 100000 | Loss: 0.6179048418998718, Learning Rate: 4.603015075376885e-05)
+
Train steps ... :  54%|█████▍    | 54200/100000 [15:57:30<7:26:13,  1.71it/s]
Train steps ... :  54%|█████▍    | 54201/100000 [15:57:30<7:26:01,  1.71it/s]
Train steps ... :  54%|█████▍    | 54202/100000 [15:57:31<7:25:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54203/100000 [15:57:31<7:25:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54204/100000 [15:57:32<7:26:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 54205/100000 [15:57:33<7:26:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54206/100000 [15:57:33<7:26:00,  1.71it/s]
Train steps ... :  54%|█████▍    | 54207/100000 [15:57:34<7:25:51,  1.71it/s]
Train steps ... :  54%|█████▍    | 54208/100000 [15:57:34<7:26:04,  1.71it/s]
Train steps ... :  54%|█████▍    | 54209/100000 [15:57:35<7:25:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 54210/100000 [15:57:36<7:26:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 54211/100000 [15:57:36<7:25:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 54212/100000 [15:57:37<7:26:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54213/100000 [15:57:37<7:25:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54214/100000 [15:57:38<7:25:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 54215/100000 [15:57:38<7:25:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54216/100000 [15:57:39<7:25:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54217/100000 [15:57:40<7:25:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 54218/100000 [15:57:40<7:25:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 54219/100000 [15:57:41<7:26:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 54220/100000 [15:57:41<7:26:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 54221/100000 [15:57:42<7:26:14,  1.71it/s]
Train steps ... :  54%|█████▍    | 54222/100000 [15:57:43<7:25:46,  1.71it/s]
Train steps ... :  54%|█████▍    | 54223/100000 [15:57:43<7:25:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 54224/100000 [15:57:44<7:25:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 54225/100000 [15:57:44<7:25:14,  1.71it/s]Step... (54225 / 100000 | Loss: 0.6576381325721741, Learning Rate: 4.6005025125628145e-05)
+
                                                                             
Step... (54225 / 100000 | Loss: 0.6360324025154114, Learning Rate: 4.6005025125628145e-05)
+
Train steps ... :  54%|█████▍    | 54225/100000 [15:57:45<7:25:14,  1.71it/s]
Train steps ... :  54%|█████▍    | 54226/100000 [15:57:45<7:25:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 54227/100000 [15:57:45<7:26:16,  1.71it/s]
Train steps ... :  54%|█████▍    | 54228/100000 [15:57:46<7:25:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 54229/100000 [15:57:47<7:25:52,  1.71it/s]
Train steps ... :  54%|█████▍    | 54230/100000 [15:57:47<7:25:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 54231/100000 [15:57:48<7:26:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 54232/100000 [15:57:48<7:26:47,  1.71it/s]
Train steps ... :  54%|█████▍    | 54233/100000 [15:57:49<7:26:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54234/100000 [15:57:50<7:26:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 54235/100000 [15:57:50<7:25:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 54236/100000 [15:57:51<7:25:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 54237/100000 [15:57:51<7:25:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 54238/100000 [15:57:52<7:25:40,  1.71it/s]
Train steps ... :  54%|█████��    | 54239/100000 [15:57:52<7:26:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54240/100000 [15:57:53<7:25:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 54241/100000 [15:57:54<7:25:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 54242/100000 [15:57:54<7:25:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 54243/100000 [15:57:55<7:26:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 54244/100000 [15:57:55<7:26:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 54245/100000 [15:57:56<7:26:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54246/100000 [15:57:57<7:26:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 54247/100000 [15:57:57<7:25:51,  1.71it/s]
Train steps ... :  54%|█████▍    | 54248/100000 [15:57:58<7:25:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 54249/100000 [15:57:58<7:26:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 54250/100000 [15:57:59<7:25:56,  1.71it/s]Step... (54250 / 100000 | Loss: 0.8009312152862549, Learning Rate: 4.597989949748744e-05)
+
                                                                             
Step... (54250 / 100000 | Loss: 0.6225605010986328, Learning Rate: 4.597989949748744e-05)
+
Train steps ... :  54%|█████▍    | 54250/100000 [15:57:59<7:25:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54251/100000 [15:57:59<7:25:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 54252/100000 [15:58:00<7:25:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 54253/100000 [15:58:01<7:25:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 54254/100000 [15:58:01<7:25:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54255/100000 [15:58:02<7:26:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 54256/100000 [15:58:02<7:25:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54257/100000 [15:58:03<7:25:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 54258/100000 [15:58:04<7:25:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 54259/100000 [15:58:04<7:25:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54260/100000 [15:58:05<7:25:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 54261/100000 [15:58:05<7:26:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54262/100000 [15:58:06<7:26:16,  1.71it/s]
Train steps ... :  54%|█████▍    | 54263/100000 [15:58:07<7:26:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 54264/100000 [15:58:07<7:26:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 54265/100000 [15:58:08<7:26:35,  1.71it/s]
Train steps ... :  54%|█████▍    | 54266/100000 [15:58:08<7:26:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 54267/100000 [15:58:09<7:26:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 54268/100000 [15:58:09<7:26:16,  1.71it/s]
Train steps ... :  54%|█████▍    | 54269/100000 [15:58:10<7:25:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 54270/100000 [15:58:11<7:25:49,  1.71it/s]
Train steps ... :  54%|█████▍    | 54271/100000 [15:58:11<7:25:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54272/100000 [15:58:12<7:26:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 54273/100000 [15:58:12<7:28:22,  1.70it/s]
Train steps ... :  54%|█████▍    | 54274/100000 [15:58:13<7:26:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 54275/100000 [15:58:14<7:26:13,  1.71it/s]Step... (54275 / 100000 | Loss: 0.7050014138221741, Learning Rate: 4.595477386934673e-05)
+
                                                                             
Step... (54275 / 100000 | Loss: 0.7682002782821655, Learning Rate: 4.595477386934673e-05)
+
Train steps ... :  54%|█████▍    | 54275/100000 [15:58:14<7:26:13,  1.71it/s]
Train steps ... :  54%|█████▍    | 54276/100000 [15:58:14<7:25:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 54277/100000 [15:58:15<7:25:35,  1.71it/s]
Train steps ... :  54%|█████▍    | 54278/100000 [15:58:15<7:25:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 54279/100000 [15:58:16<7:25:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 54280/100000 [15:58:16<7:25:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 54281/100000 [15:58:17<7:25:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 54282/100000 [15:58:18<7:25:03,  1.71it/s]
Train steps ... :  54%|█████▍    | 54283/100000 [15:58:18<7:25:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 54284/100000 [15:58:19<7:26:54,  1.70it/s]
Train steps ... :  54%|█████▍    | 54285/100000 [15:58:19<7:27:04,  1.70it/s]
Train steps ... :  54%|█████▍    | 54286/100000 [15:58:20<7:26:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 54287/100000 [15:58:21<7:25:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54288/100000 [15:58:21<7:25:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 54289/100000 [15:58:22<7:25:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 54290/100000 [15:58:22<7:25:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54291/100000 [15:58:23<7:25:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 54292/100000 [15:58:23<7:25:21,  1.71it/s]
Train steps ... :  54%|█████▍    | 54293/100000 [15:58:24<7:28:17,  1.70it/s]
Train steps ... :  54%|█████▍    | 54294/100000 [15:58:25<7:26:58,  1.70it/s]
Train steps ... :  54%|█████▍    | 54295/100000 [15:58:25<7:26:47,  1.70it/s]
Train steps ... :  54%|█████▍    | 54296/100000 [15:58:26<7:26:37,  1.71it/s]
Train steps ... :  54%|█████▍    | 54297/100000 [15:58:26<7:26:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54298/100000 [15:58:27<7:25:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 54299/100000 [15:58:28<7:25:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 54300/100000 [15:58:28<7:25:42,  1.71it/s]Step... (54300 / 100000 | Loss: 0.5440472364425659, Learning Rate: 4.592964824120603e-05)
+
                                                                             
Step... (54300 / 100000 | Loss: 0.6288244128227234, Learning Rate: 4.592964824120603e-05)
+
Train steps ... :  54%|█████▍    | 54300/100000 [15:58:29<7:25:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 54301/100000 [15:58:29<7:25:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 54302/100000 [15:58:29<7:25:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54303/100000 [15:58:30<7:25:00,  1.71it/s]
Train steps ... :  54%|█████▍    | 54304/100000 [15:58:31<7:24:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 54305/100000 [15:58:31<7:25:04,  1.71it/s]
Train steps ... :  54%|█████▍    | 54306/100000 [15:58:32<7:24:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54307/100000 [15:58:32<7:25:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 54308/100000 [15:58:33<7:25:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54309/100000 [15:58:33<7:25:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54310/100000 [15:58:34<7:25:21,  1.71it/s]
Train steps ... :  54%|█████▍    | 54311/100000 [15:58:35<7:25:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54312/100000 [15:58:35<7:25:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54313/100000 [15:58:36<7:25:35,  1.71it/s]
Train steps ... :  54%|█████▍    | 54314/100000 [15:58:36<7:25:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54315/100000 [15:58:37<7:25:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 54316/100000 [15:58:38<7:24:47,  1.71it/s]
Train steps ... :  54%|█████▍    | 54317/100000 [15:58:38<7:25:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 54318/100000 [15:58:39<7:25:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54319/100000 [15:58:39<7:25:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 54320/100000 [15:58:40<7:25:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 54321/100000 [15:58:40<7:25:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54322/100000 [15:58:41<7:25:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54323/100000 [15:58:42<7:25:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 54324/100000 [15:58:42<7:25:16,  1.71it/s]
Train steps ... :  54%|█████▍    | 54325/100000 [15:58:43<7:25:28,  1.71it/s]Step... (54325 / 100000 | Loss: 0.7185819149017334, Learning Rate: 4.5904522613065324e-05)
+
                                                                             
Step... (54325 / 100000 | Loss: 0.8648127317428589, Learning Rate: 4.5904522613065324e-05)
+
Train steps ... :  54%|█████▍    | 54325/100000 [15:58:43<7:25:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 54326/100000 [15:58:43<7:24:55,  1.71it/s]
Train steps ... :  54%|█████▍    | 54327/100000 [15:58:44<7:24:43,  1.71it/s]
Train steps ... :  54%|█████▍    | 54328/100000 [15:58:45<7:25:52,  1.71it/s]
Train steps ... :  54%|█████▍    | 54329/100000 [15:58:45<7:24:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54330/100000 [15:58:46<7:24:37,  1.71it/s]
Train steps ... :  54%|█████▍    | 54331/100000 [15:58:46<7:24:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 54332/100000 [15:58:47<7:24:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 54333/100000 [15:58:47<7:24:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 54334/100000 [15:58:48<7:24:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 54335/100000 [15:58:49<7:24:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 54336/100000 [15:58:49<7:24:52,  1.71it/s]
Train steps ... :  54%|█████▍    | 54337/100000 [15:58:50<7:24:46,  1.71it/s]
Train steps ... :  54%|█████▍    | 54338/100000 [15:58:50<7:24:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 54339/100000 [15:58:51<7:24:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 54340/100000 [15:58:52<7:24:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54341/100000 [15:58:52<7:25:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 54342/100000 [15:58:53<7:24:52,  1.71it/s]
Train steps ... :  54%|█████▍    | 54343/100000 [15:58:53<7:24:50,  1.71it/s]
Train steps ... :  54%|█████▍    | 54344/100000 [15:58:54<7:24:56,  1.71it/s]
Train steps ... :  54%|█████▍    | 54345/100000 [15:58:54<7:25:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 54346/100000 [15:58:55<7:25:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54347/100000 [15:58:56<7:24:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 54348/100000 [15:58:56<7:25:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 54349/100000 [15:58:57<7:25:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 54350/100000 [15:58:57<7:24:54,  1.71it/s]Step... (54350 / 100000 | Loss: 0.6652831435203552, Learning Rate: 4.587939698492463e-05)
+
                                                                             
Step... (54350 / 100000 | Loss: 0.7260481119155884, Learning Rate: 4.587939698492463e-05)
+
Train steps ... :  54%|█████▍    | 54350/100000 [15:58:58<7:24:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 54351/100000 [15:58:58<7:25:01,  1.71it/s]
Train steps ... :  54%|█████▍    | 54352/100000 [15:58:59<7:24:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 54353/100000 [15:58:59<7:24:28,  1.71it/s]
Train steps ... :  54%|█████▍    | 54354/100000 [15:59:00<7:24:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 54355/100000 [15:59:00<7:24:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54356/100000 [15:59:01<7:24:30,  1.71it/s]
Train steps ... :  54%|█████▍    | 54357/100000 [15:59:02<7:24:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54358/100000 [15:59:02<7:24:20,  1.71it/s]
Train steps ... :  54%|█████▍    | 54359/100000 [15:59:03<7:24:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 54360/100000 [15:59:03<7:24:50,  1.71it/s]
Train steps ... :  54%|█████▍    | 54361/100000 [15:59:04<7:25:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 54362/100000 [15:59:04<7:24:58,  1.71it/s]
Train steps ... :  54%|█████▍    | 54363/100000 [15:59:05<7:24:59,  1.71it/s]
Train steps ... :  54%|█████▍    | 54364/100000 [15:59:06<7:24:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54365/100000 [15:59:06<7:25:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54366/100000 [15:59:07<7:24:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 54367/100000 [15:59:07<7:25:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 54368/100000 [15:59:08<7:24:22,  1.71it/s]
Train steps ... :  54%|█████▍    | 54369/100000 [15:59:09<7:24:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 54370/100000 [15:59:09<7:24:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 54371/100000 [15:59:10<7:24:12,  1.71it/s]
Train steps ... :  54%|█████▍    | 54372/100000 [15:59:10<7:24:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54373/100000 [15:59:11<7:24:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54374/100000 [15:59:11<7:24:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54375/100000 [15:59:12<7:24:02,  1.71it/s]Step... (54375 / 100000 | Loss: 0.5796736478805542, Learning Rate: 4.5854271356783925e-05)
+
                                                                             
Step... (54375 / 100000 | Loss: 0.7439436912536621, Learning Rate: 4.5854271356783925e-05)
+
Train steps ... :  54%|█████▍    | 54375/100000 [15:59:12<7:24:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54376/100000 [15:59:13<7:24:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 54377/100000 [15:59:13<7:24:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54378/100000 [15:59:14<7:25:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 54379/100000 [15:59:14<7:24:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 54380/100000 [15:59:15<7:25:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 54381/100000 [15:59:16<7:24:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 54382/100000 [15:59:16<7:25:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 54383/100000 [15:59:17<7:24:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54384/100000 [15:59:17<7:24:35,  1.71it/s]
Train steps ... :  54%|█████▍    | 54385/100000 [15:59:18<7:24:21,  1.71it/s]
Train steps ... :  54%|█████▍    | 54386/100000 [15:59:18<7:24:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 54387/100000 [15:59:19<7:24:16,  1.71it/s]
Train steps ... :  54%|█████▍    | 54388/100000 [15:59:20<7:24:17,  1.71it/s]
Train steps ... :  54%|█████▍    | 54389/100000 [15:59:20<7:25:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54390/100000 [15:59:21<7:24:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 54391/100000 [15:59:21<7:24:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54392/100000 [15:59:22<7:24:14,  1.71it/s]
Train steps ... :  54%|█████▍    | 54393/100000 [15:59:23<7:24:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54394/100000 [15:59:23<7:24:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 54395/100000 [15:59:24<7:24:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 54396/100000 [15:59:24<7:24:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54397/100000 [15:59:25<7:24:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 54398/100000 [15:59:25<7:24:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54399/100000 [15:59:26<7:23:51,  1.71it/s]
Train steps ... :  54%|█████▍    | 54400/100000 [15:59:27<7:24:11,  1.71it/s]Step... (54400 / 100000 | Loss: 0.8749963045120239, Learning Rate: 4.582914572864322e-05)
+
                                                                             
Step... (54400 / 100000 | Loss: 0.8738243579864502, Learning Rate: 4.582914572864322e-05)
+
Train steps ... :  54%|█████▍    | 54400/100000 [15:59:27<7:24:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 54401/100000 [15:59:27<7:24:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54402/100000 [15:59:28<7:24:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 54403/100000 [15:59:28<7:23:52,  1.71it/s]
Train steps ... :  54%|█████▍    | 54404/100000 [15:59:29<7:24:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54405/100000 [15:59:30<7:23:46,  1.71it/s]
Train steps ... :  54%|█████▍    | 54406/100000 [15:59:30<7:23:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 54407/100000 [15:59:31<7:23:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54408/100000 [15:59:31<7:24:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 54409/100000 [15:59:32<7:25:29,  1.71it/s]
Train steps ... :  54%|█████▍    | 54410/100000 [15:59:32<7:24:38,  1.71it/s]
Train steps ... :  54%|█████▍    | 54411/100000 [15:59:33<7:24:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 54412/100000 [15:59:34<7:24:04,  1.71it/s]
Train steps ... :  54%|█████▍    | 54413/100000 [15:59:34<7:24:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54414/100000 [15:59:35<7:24:40,  1.71it/s]
Train steps ... :  54%|█████▍    | 54415/100000 [15:59:35<7:24:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 54416/100000 [15:59:36<7:25:05,  1.71it/s]
Train steps ... :  54%|█████▍    | 54417/100000 [15:59:37<7:24:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 54418/100000 [15:59:37<7:25:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54419/100000 [15:59:38<7:24:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 54420/100000 [15:59:38<7:23:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 54421/100000 [15:59:39<7:23:51,  1.71it/s]
Train steps ... :  54%|█████▍    | 54422/100000 [15:59:40<7:23:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54423/100000 [15:59:40<7:24:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 54424/100000 [15:59:41<7:24:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54425/100000 [15:59:41<7:23:57,  1.71it/s]Step... (54425 / 100000 | Loss: 0.6985136270523071, Learning Rate: 4.580402010050252e-05)
+
                                                                             
Step... (54425 / 100000 | Loss: 0.6359254121780396, Learning Rate: 4.580402010050252e-05)
+
Train steps ... :  54%|█████▍    | 54425/100000 [15:59:42<7:23:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 54426/100000 [15:59:42<7:24:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 54427/100000 [15:59:42<7:24:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54428/100000 [15:59:43<7:24:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54429/100000 [15:59:44<7:24:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 54430/100000 [15:59:44<7:24:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 54431/100000 [15:59:45<7:25:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 54432/100000 [15:59:45<7:24:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 54433/100000 [15:59:46<7:23:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 54434/100000 [15:59:47<7:24:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 54435/100000 [15:59:47<7:24:11,  1.71it/s]
Train steps ... :  54%|█████▍    | 54436/100000 [15:59:48<7:23:47,  1.71it/s]
Train steps ... :  54%|█████▍    | 54437/100000 [15:59:48<7:24:12,  1.71it/s]
Train steps ... :  54%|█████▍    | 54438/100000 [15:59:49<7:23:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54439/100000 [15:59:49<7:23:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 54440/100000 [15:59:50<7:24:02,  1.71it/s]
Train steps ... :  54%|█████▍    | 54441/100000 [15:59:51<7:24:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54442/100000 [15:59:51<7:23:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 54443/100000 [15:59:52<7:23:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 54444/100000 [15:59:52<7:24:04,  1.71it/s]
Train steps ... :  54%|█████▍    | 54445/100000 [15:59:53<7:23:44,  1.71it/s]
Train steps ... :  54%|█████▍    | 54446/100000 [15:59:54<7:23:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54447/100000 [15:59:54<7:23:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 54448/100000 [15:59:55<7:24:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54449/100000 [15:59:55<7:23:36,  1.71it/s]
Train steps ... :  54%|█████▍    | 54450/100000 [15:59:56<7:23:24,  1.71it/s]Step... (54450 / 100000 | Loss: 0.5888256430625916, Learning Rate: 4.577889447236181e-05)
+
                                                                             
Step... (54450 / 100000 | Loss: 0.839550793170929, Learning Rate: 4.577889447236181e-05)
+
Train steps ... :  54%|█████▍    | 54450/100000 [15:59:56<7:23:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54451/100000 [15:59:56<7:24:27,  1.71it/s]
Train steps ... :  54%|█████▍    | 54452/100000 [15:59:57<7:24:07,  1.71it/s]
Train steps ... :  54%|█████▍    | 54453/100000 [15:59:58<7:24:04,  1.71it/s]
Train steps ... :  54%|█████▍    | 54454/100000 [15:59:58<7:23:41,  1.71it/s]
Train steps ... :  54%|█████▍    | 54455/100000 [15:59:59<7:23:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 54456/100000 [15:59:59<7:23:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 54457/100000 [16:00:00<7:24:21,  1.71it/s]
Train steps ... :  54%|█████▍    | 54458/100000 [16:00:01<7:24:01,  1.71it/s]
Train steps ... :  54%|█████▍    | 54459/100000 [16:00:01<7:23:31,  1.71it/s]
Train steps ... :  54%|█████▍    | 54460/100000 [16:00:02<7:23:39,  1.71it/s]
Train steps ... :  54%|█████▍    | 54461/100000 [16:00:02<7:23:48,  1.71it/s]
Train steps ... :  54%|█████▍    | 54462/100000 [16:00:03<7:23:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 54463/100000 [16:00:03<7:23:33,  1.71it/s]
Train steps ... :  54%|█████▍    | 54464/100000 [16:00:04<7:23:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 54465/100000 [16:00:05<7:23:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 54466/100000 [16:00:05<7:23:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54467/100000 [16:00:06<7:23:45,  1.71it/s]
Train steps ... :  54%|█████▍    | 54468/100000 [16:00:06<7:24:10,  1.71it/s]
Train steps ... :  54%|█████▍    | 54469/100000 [16:00:07<7:23:20,  1.71it/s]
Train steps ... :  54%|█████▍    | 54470/100000 [16:00:08<7:23:34,  1.71it/s]
Train steps ... :  54%|█████▍    | 54471/100000 [16:00:08<7:23:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 54472/100000 [16:00:09<7:22:49,  1.71it/s]
Train steps ... :  54%|█████▍    | 54473/100000 [16:00:09<7:23:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 54474/100000 [16:00:10<7:23:06,  1.71it/s]
Train steps ... :  54%|█████▍    | 54475/100000 [16:00:10<7:22:54,  1.71it/s]Step... (54475 / 100000 | Loss: 0.632437527179718, Learning Rate: 4.5753768844221104e-05)
+
                                                                             
Step... (54475 / 100000 | Loss: 0.696422278881073, Learning Rate: 4.5753768844221104e-05)
+
Train steps ... :  54%|█████▍    | 54475/100000 [16:00:11<7:22:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 54476/100000 [16:00:11<7:23:24,  1.71it/s]
Train steps ... :  54%|█████▍    | 54477/100000 [16:00:12<7:23:25,  1.71it/s]
Train steps ... :  54%|█████▍    | 54478/100000 [16:00:12<7:23:37,  1.71it/s]
Train steps ... :  54%|█████▍    | 54479/100000 [16:00:13<7:23:18,  1.71it/s]
Train steps ... :  54%|█████▍    | 54480/100000 [16:00:13<7:23:57,  1.71it/s]
Train steps ... :  54%|█████▍    | 54481/100000 [16:00:14<7:23:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 54482/100000 [16:00:15<7:23:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54483/100000 [16:00:15<7:23:49,  1.71it/s]
Train steps ... :  54%|█████▍    | 54484/100000 [16:00:16<7:23:26,  1.71it/s]
Train steps ... :  54%|█████▍    | 54485/100000 [16:00:16<7:23:42,  1.71it/s]
Train steps ... :  54%|█████▍    | 54486/100000 [16:00:17<7:23:53,  1.71it/s]
Train steps ... :  54%|█████▍    | 54487/100000 [16:00:18<7:24:01,  1.71it/s]
Train steps ... :  54%|█████▍    | 54488/100000 [16:00:18<7:23:32,  1.71it/s]
Train steps ... :  54%|█████▍    | 54489/100000 [16:00:19<7:23:00,  1.71it/s]
Train steps ... :  54%|█████▍    | 54490/100000 [16:00:19<7:23:09,  1.71it/s]
Train steps ... :  54%|█████▍    | 54491/100000 [16:00:20<7:22:54,  1.71it/s]
Train steps ... :  54%|█████▍    | 54492/100000 [16:00:20<7:23:20,  1.71it/s]
Train steps ... :  54%|█████▍    | 54493/100000 [16:00:21<7:23:01,  1.71it/s]
Train steps ... :  54%|█████▍    | 54494/100000 [16:00:22<7:23:19,  1.71it/s]
Train steps ... :  54%|█████▍    | 54495/100000 [16:00:22<7:23:47,  1.71it/s]
Train steps ... :  54%|█████▍    | 54496/100000 [16:00:23<7:23:23,  1.71it/s]
Train steps ... :  54%|█████▍    | 54497/100000 [16:00:23<7:23:15,  1.71it/s]
Train steps ... :  54%|█████▍    | 54498/100000 [16:00:24<7:23:08,  1.71it/s]
Train steps ... :  54%|█████▍    | 54499/100000 [16:00:25<7:23:02,  1.71it/s]
Train steps ... :  55%|█████▍    | 54500/100000 [16:00:25<7:22:52,  1.71it/s]Step... (54500 / 100000 | Loss: 0.7787028551101685, Learning Rate: 4.57286432160804e-05)
+
                                                                             
Step... (54500 / 100000 | Loss: 0.7068498134613037, Learning Rate: 4.57286432160804e-05)
+
Train steps ... :  55%|█████▍    | 54500/100000 [16:00:25<7:22:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54501/100000 [16:00:26<7:23:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54502/100000 [16:00:26<7:23:17,  1.71it/s]
Train steps ... :  55%|█████▍    | 54503/100000 [16:00:27<7:23:55,  1.71it/s]
Train steps ... :  55%|█████▍    | 54504/100000 [16:00:27<7:23:19,  1.71it/s]
Train steps ... :  55%|█████▍    | 54505/100000 [16:00:28<7:23:19,  1.71it/s]
Train steps ... :  55%|█████▍    | 54506/100000 [16:00:29<7:22:54,  1.71it/s]
Train steps ... :  55%|█████▍    | 54507/100000 [16:00:29<7:22:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54508/100000 [16:00:30<7:22:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54509/100000 [16:00:30<7:22:54,  1.71it/s]
Train steps ... :  55%|█████▍    | 54510/100000 [16:00:31<7:24:52,  1.70it/s]
Train steps ... :  55%|█████▍    | 54511/100000 [16:00:32<7:23:41,  1.71it/s]
Train steps ... :  55%|█████▍    | 54512/100000 [16:00:32<7:23:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54513/100000 [16:00:33<7:23:24,  1.71it/s]
Train steps ... :  55%|█████▍    | 54514/100000 [16:00:33<7:23:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54515/100000 [16:00:34<7:22:47,  1.71it/s]
Train steps ... :  55%|█████▍    | 54516/100000 [16:00:34<7:23:35,  1.71it/s]
Train steps ... :  55%|█████▍    | 54517/100000 [16:00:35<7:23:10,  1.71it/s]
Train steps ... :  55%|█████▍    | 54518/100000 [16:00:36<7:23:14,  1.71it/s]
Train steps ... :  55%|█████▍    | 54519/100000 [16:00:36<7:23:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54520/100000 [16:00:37<7:24:03,  1.71it/s]
Train steps ... :  55%|█████▍    | 54521/100000 [16:00:37<7:23:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54522/100000 [16:00:38<7:23:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54523/100000 [16:00:39<7:23:05,  1.71it/s]
Train steps ... :  55%|█████▍    | 54524/100000 [16:00:39<7:23:11,  1.71it/s]
Train steps ... :  55%|█████▍    | 54525/100000 [16:00:40<7:23:17,  1.71it/s]Step... (54525 / 100000 | Loss: 0.5839763283729553, Learning Rate: 4.57035175879397e-05)
+
                                                                             
Step... (54525 / 100000 | Loss: 0.6877063512802124, Learning Rate: 4.57035175879397e-05)
+
Train steps ... :  55%|█████▍    | 54525/100000 [16:00:40<7:23:17,  1.71it/s]
Train steps ... :  55%|█████▍    | 54526/100000 [16:00:40<7:23:01,  1.71it/s]
Train steps ... :  55%|█████▍    | 54527/100000 [16:00:41<7:22:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54528/100000 [16:00:41<7:22:44,  1.71it/s]
Train steps ... :  55%|█████▍    | 54529/100000 [16:00:42<7:22:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54530/100000 [16:00:43<7:23:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54531/100000 [16:00:43<7:22:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54532/100000 [16:00:44<7:22:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54533/100000 [16:00:44<7:22:25,  1.71it/s]
Train steps ... :  55%|█████▍    | 54534/100000 [16:00:45<7:22:58,  1.71it/s]
Train steps ... :  55%|█████▍    | 54535/100000 [16:00:46<7:23:01,  1.71it/s]
Train steps ... :  55%|█████▍    | 54536/100000 [16:00:46<7:22:30,  1.71it/s]
Train steps ... :  55%|█████▍    | 54537/100000 [16:00:47<7:23:10,  1.71it/s]
Train steps ... :  55%|█████▍    | 54538/100000 [16:00:47<7:22:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54539/100000 [16:00:48<7:22:36,  1.71it/s]
Train steps ... :  55%|█████▍    | 54540/100000 [16:00:48<7:22:32,  1.71it/s]
Train steps ... :  55%|█████▍    | 54541/100000 [16:00:49<7:22:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54542/100000 [16:00:50<7:22:22,  1.71it/s]
Train steps ... :  55%|█████▍    | 54543/100000 [16:00:50<7:22:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54544/100000 [16:00:51<7:23:05,  1.71it/s]
Train steps ... :  55%|█████▍    | 54545/100000 [16:00:51<7:22:48,  1.71it/s]
Train steps ... :  55%|█████▍    | 54546/100000 [16:00:52<7:22:34,  1.71it/s]
Train steps ... :  55%|█████▍    | 54547/100000 [16:00:53<7:23:37,  1.71it/s]
Train steps ... :  55%|█████▍    | 54548/100000 [16:00:53<7:23:10,  1.71it/s]
Train steps ... :  55%|█████▍    | 54549/100000 [16:00:54<7:23:35,  1.71it/s]
Train steps ... :  55%|█████▍    | 54550/100000 [16:00:54<7:23:32,  1.71it/s]Step... (54550 / 100000 | Loss: 0.6688004732131958, Learning Rate: 4.5678391959799e-05)
+
                                                                             
Step... (54550 / 100000 | Loss: 0.8256129026412964, Learning Rate: 4.5678391959799e-05)
+
Train steps ... :  55%|█████▍    | 54550/100000 [16:00:55<7:23:32,  1.71it/s]
Train steps ... :  55%|█████▍    | 54551/100000 [16:00:55<7:23:26,  1.71it/s]
Train steps ... :  55%|█████▍    | 54552/100000 [16:00:56<7:23:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54553/100000 [16:00:56<7:23:36,  1.71it/s]
Train steps ... :  55%|█████▍    | 54554/100000 [16:00:57<7:25:12,  1.70it/s]
Train steps ... :  55%|█████▍    | 54555/100000 [16:00:57<7:24:59,  1.70it/s]
Train steps ... :  55%|█████▍    | 54556/100000 [16:00:58<7:24:03,  1.71it/s]
Train steps ... :  55%|█████▍    | 54557/100000 [16:00:58<7:23:33,  1.71it/s]
Train steps ... :  55%|█████▍    | 54558/100000 [16:00:59<7:23:31,  1.71it/s]
Train steps ... :  55%|█████▍    | 54559/100000 [16:01:00<7:23:44,  1.71it/s]
Train steps ... :  55%|█████▍    | 54560/100000 [16:01:00<7:23:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54561/100000 [16:01:01<7:23:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54562/100000 [16:01:01<7:22:58,  1.71it/s]
Train steps ... :  55%|█████▍    | 54563/100000 [16:01:02<7:23:01,  1.71it/s]
Train steps ... :  55%|█████▍    | 54564/100000 [16:01:03<7:22:55,  1.71it/s]
Train steps ... :  55%|█████▍    | 54565/100000 [16:01:03<7:22:33,  1.71it/s]
Train steps ... :  55%|█████▍    | 54566/100000 [16:01:04<7:22:53,  1.71it/s]
Train steps ... :  55%|█████▍    | 54567/100000 [16:01:04<7:22:24,  1.71it/s]
Train steps ... :  55%|█████▍    | 54568/100000 [16:01:05<7:22:15,  1.71it/s]
Train steps ... :  55%|█████▍    | 54569/100000 [16:01:05<7:22:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54570/100000 [16:01:06<7:22:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54571/100000 [16:01:07<7:22:32,  1.71it/s]
Train steps ... :  55%|█████▍    | 54572/100000 [16:01:07<7:22:32,  1.71it/s]
Train steps ... :  55%|█████▍    | 54573/100000 [16:01:08<7:22:30,  1.71it/s]
Train steps ... :  55%|█████▍    | 54574/100000 [16:01:08<7:22:35,  1.71it/s]
Train steps ... :  55%|█████▍    | 54575/100000 [16:01:09<7:23:02,  1.71it/s]Step... (54575 / 100000 | Loss: 0.9734473824501038, Learning Rate: 4.56532663316583e-05)
+
                                                                             
Step... (54575 / 100000 | Loss: 0.6153930425643921, Learning Rate: 4.56532663316583e-05)
+
Train steps ... :  55%|█████▍    | 54575/100000 [16:01:09<7:23:02,  1.71it/s]
Train steps ... :  55%|█████▍    | 54576/100000 [16:01:10<7:22:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54577/100000 [16:01:10<7:22:25,  1.71it/s]
Train steps ... :  55%|█████▍    | 54578/100000 [16:01:11<7:22:22,  1.71it/s]
Train steps ... :  55%|█████▍    | 54579/100000 [16:01:11<7:22:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54580/100000 [16:01:12<7:22:48,  1.71it/s]
Train steps ... :  55%|█████▍    | 54581/100000 [16:01:12<7:22:33,  1.71it/s]
Train steps ... :  55%|█████▍    | 54582/100000 [16:01:13<7:22:19,  1.71it/s]
Train steps ... :  55%|█████▍    | 54583/100000 [16:01:14<7:22:15,  1.71it/s]
Train steps ... :  55%|█████▍    | 54584/100000 [16:01:14<7:22:17,  1.71it/s]
Train steps ... :  55%|█████▍    | 54585/100000 [16:01:15<7:22:41,  1.71it/s]
Train steps ... :  55%|█████▍    | 54586/100000 [16:01:15<7:22:34,  1.71it/s]
Train steps ... :  55%|█████▍    | 54587/100000 [16:01:16<7:22:21,  1.71it/s]
Train steps ... :  55%|█████▍    | 54588/100000 [16:01:17<7:22:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54589/100000 [16:01:17<7:22:40,  1.71it/s]
Train steps ... :  55%|█████▍    | 54590/100000 [16:01:18<7:21:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54591/100000 [16:01:18<7:22:59,  1.71it/s]
Train steps ... :  55%|█████▍    | 54592/100000 [16:01:19<7:22:36,  1.71it/s]
Train steps ... :  55%|█████▍    | 54593/100000 [16:01:19<7:22:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54594/100000 [16:01:20<7:22:36,  1.71it/s]
Train steps ... :  55%|█████▍    | 54595/100000 [16:01:21<7:22:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54596/100000 [16:01:21<7:22:22,  1.71it/s]
Train steps ... :  55%|█████▍    | 54597/100000 [16:01:22<7:22:50,  1.71it/s]
Train steps ... :  55%|█████▍    | 54598/100000 [16:01:22<7:22:54,  1.71it/s]
Train steps ... :  55%|█████▍    | 54599/100000 [16:01:23<7:22:56,  1.71it/s]
Train steps ... :  55%|█████▍    | 54600/100000 [16:01:24<7:22:44,  1.71it/s]Step... (54600 / 100000 | Loss: 0.6459659337997437, Learning Rate: 4.5628140703517594e-05)
+
                                                                             
Step... (54600 / 100000 | Loss: 0.6127496361732483, Learning Rate: 4.5628140703517594e-05)
+
Train steps ... :  55%|█████▍    | 54600/100000 [16:01:24<7:22:44,  1.71it/s]
Train steps ... :  55%|█████▍    | 54601/100000 [16:01:24<7:22:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54602/100000 [16:01:25<7:22:20,  1.71it/s]
Train steps ... :  55%|█████▍    | 54603/100000 [16:01:25<7:22:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54604/100000 [16:01:26<7:22:30,  1.71it/s]
Train steps ... :  55%|█████▍    | 54605/100000 [16:01:27<7:22:54,  1.71it/s]
Train steps ... :  55%|█████▍    | 54606/100000 [16:01:27<7:22:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54607/100000 [16:01:28<7:22:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54608/100000 [16:01:28<7:21:58,  1.71it/s]
Train steps ... :  55%|█████▍    | 54609/100000 [16:01:29<7:22:03,  1.71it/s]
Train steps ... :  55%|█████▍    | 54610/100000 [16:01:29<7:22:37,  1.71it/s]
Train steps ... :  55%|█████▍    | 54611/100000 [16:01:30<7:23:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54612/100000 [16:01:31<7:22:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54613/100000 [16:01:31<7:22:34,  1.71it/s]
Train steps ... :  55%|█████▍    | 54614/100000 [16:01:32<7:22:18,  1.71it/s]
Train steps ... :  55%|█████▍    | 54615/100000 [16:01:32<7:22:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54616/100000 [16:01:33<7:22:36,  1.71it/s]
Train steps ... :  55%|█████▍    | 54617/100000 [16:01:34<7:22:55,  1.71it/s]
Train steps ... :  55%|█████▍    | 54618/100000 [16:01:34<7:22:50,  1.71it/s]
Train steps ... :  55%|█████▍    | 54619/100000 [16:01:35<7:22:24,  1.71it/s]
Train steps ... :  55%|█████▍    | 54620/100000 [16:01:35<7:23:37,  1.70it/s]
Train steps ... :  55%|█████▍    | 54621/100000 [16:01:36<7:22:40,  1.71it/s]
Train steps ... :  55%|█████▍    | 54622/100000 [16:01:36<7:22:07,  1.71it/s]
Train steps ... :  55%|█████▍    | 54623/100000 [16:01:37<7:21:47,  1.71it/s]
Train steps ... :  55%|█████▍    | 54624/100000 [16:01:38<7:21:53,  1.71it/s]
Train steps ... :  55%|█████▍    | 54625/100000 [16:01:38<7:21:54,  1.71it/s]Step... (54625 / 100000 | Loss: 0.889423668384552, Learning Rate: 4.5603015075376884e-05)
+
                                                                             
Step... (54625 / 100000 | Loss: 0.7735416889190674, Learning Rate: 4.5603015075376884e-05)
+
Train steps ... :  55%|█████▍    | 54625/100000 [16:01:39<7:21:54,  1.71it/s]
Train steps ... :  55%|█████▍    | 54626/100000 [16:01:39<7:21:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54627/100000 [16:01:39<7:22:08,  1.71it/s]
Train steps ... :  55%|█████▍    | 54628/100000 [16:01:40<7:22:31,  1.71it/s]
Train steps ... :  55%|█████▍    | 54629/100000 [16:01:41<7:23:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54630/100000 [16:01:41<7:24:00,  1.70it/s]
Train steps ... :  55%|█████▍    | 54631/100000 [16:01:42<7:23:49,  1.70it/s]
Train steps ... :  55%|█████▍    | 54632/100000 [16:01:42<7:23:20,  1.71it/s]
Train steps ... :  55%|█████▍    | 54633/100000 [16:01:43<7:21:38,  1.71it/s]
Train steps ... :  55%|█████▍    | 54634/100000 [16:01:43<7:21:15,  1.71it/s]
Train steps ... :  55%|█████▍    | 54635/100000 [16:01:44<7:21:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54636/100000 [16:01:45<7:22:41,  1.71it/s]
Train steps ... :  55%|█████▍    | 54637/100000 [16:01:45<7:22:28,  1.71it/s]
Train steps ... :  55%|█████▍    | 54638/100000 [16:01:46<7:21:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54639/100000 [16:01:46<7:22:19,  1.71it/s]
Train steps ... :  55%|█████▍    | 54640/100000 [16:01:47<7:21:48,  1.71it/s]
Train steps ... :  55%|█████▍    | 54641/100000 [16:01:48<7:22:22,  1.71it/s]
Train steps ... :  55%|█████▍    | 54642/100000 [16:01:48<7:21:33,  1.71it/s]
Train steps ... :  55%|█████▍    | 54643/100000 [16:01:49<7:22:05,  1.71it/s]
Train steps ... :  55%|█████▍    | 54644/100000 [16:01:49<7:22:26,  1.71it/s]
Train steps ... :  55%|█████▍    | 54645/100000 [16:01:50<7:23:53,  1.70it/s]
Train steps ... :  55%|█████▍    | 54646/100000 [16:01:51<7:22:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54647/100000 [16:01:51<7:22:23,  1.71it/s]
Train steps ... :  55%|█████▍    | 54648/100000 [16:01:52<7:21:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54649/100000 [16:01:52<7:22:01,  1.71it/s]
Train steps ... :  55%|█████▍    | 54650/100000 [16:01:53<7:22:33,  1.71it/s]Step... (54650 / 100000 | Loss: 0.7843712568283081, Learning Rate: 4.557788944723618e-05)
+
                                                                             
Step... (54650 / 100000 | Loss: 0.897027850151062, Learning Rate: 4.557788944723618e-05)
+
Train steps ... :  55%|█████▍    | 54650/100000 [16:01:53<7:22:33,  1.71it/s]
Train steps ... :  55%|█████▍    | 54651/100000 [16:01:53<7:23:23,  1.70it/s]
Train steps ... :  55%|█████▍    | 54652/100000 [16:01:54<7:22:57,  1.71it/s]
Train steps ... :  55%|█████▍    | 54653/100000 [16:01:55<7:23:04,  1.71it/s]
Train steps ... :  55%|█████▍    | 54654/100000 [16:01:55<7:24:12,  1.70it/s]
Train steps ... :  55%|█████▍    | 54655/100000 [16:01:56<7:23:08,  1.71it/s]
Train steps ... :  55%|█████▍    | 54656/100000 [16:01:56<7:22:53,  1.71it/s]
Train steps ... :  55%|█████▍    | 54657/100000 [16:01:57<7:22:57,  1.71it/s]
Train steps ... :  55%|█████▍    | 54658/100000 [16:01:58<7:22:44,  1.71it/s]
Train steps ... :  55%|█████▍    | 54659/100000 [16:01:58<7:22:27,  1.71it/s]
Train steps ... :  55%|█████▍    | 54660/100000 [16:01:59<7:22:19,  1.71it/s]
Train steps ... :  55%|█████▍    | 54661/100000 [16:01:59<7:21:53,  1.71it/s]
Train steps ... :  55%|█████▍    | 54662/100000 [16:02:00<7:22:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54663/100000 [16:02:00<7:22:49,  1.71it/s]
Train steps ... :  55%|█████▍    | 54664/100000 [16:02:01<7:22:31,  1.71it/s]
Train steps ... :  55%|█████▍    | 54665/100000 [16:02:02<7:22:39,  1.71it/s]
Train steps ... :  55%|█████▍    | 54666/100000 [16:02:02<7:21:57,  1.71it/s]
Train steps ... :  55%|█████▍    | 54667/100000 [16:02:03<7:22:55,  1.71it/s]
Train steps ... :  55%|█████▍    | 54668/100000 [16:02:03<7:22:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54669/100000 [16:02:04<7:24:13,  1.70it/s]
Train steps ... :  55%|█████▍    | 54670/100000 [16:02:05<7:23:22,  1.70it/s]
Train steps ... :  55%|█████▍    | 54671/100000 [16:02:05<7:22:53,  1.71it/s]
Train steps ... :  55%|█████▍    | 54672/100000 [16:02:06<7:22:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54673/100000 [16:02:06<7:22:33,  1.71it/s]
Train steps ... :  55%|█████▍    | 54674/100000 [16:02:07<7:21:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54675/100000 [16:02:07<7:22:00,  1.71it/s]Step... (54675 / 100000 | Loss: 0.8911238312721252, Learning Rate: 4.555276381909548e-05)
+
                                                                             
Step... (54675 / 100000 | Loss: 0.6637052297592163, Learning Rate: 4.555276381909548e-05)
+
Train steps ... :  55%|█████▍    | 54675/100000 [16:02:08<7:22:00,  1.71it/s]
Train steps ... :  55%|█████▍    | 54676/100000 [16:02:08<7:22:36,  1.71it/s]
Train steps ... :  55%|█████▍    | 54677/100000 [16:02:09<7:21:49,  1.71it/s]
Train steps ... :  55%|█████▍    | 54678/100000 [16:02:09<7:21:37,  1.71it/s]
Train steps ... :  55%|█████▍    | 54679/100000 [16:02:10<7:22:14,  1.71it/s]
Train steps ... :  55%|█████▍    | 54680/100000 [16:02:10<7:21:29,  1.71it/s]
Train steps ... :  55%|█���███▍    | 54681/100000 [16:02:11<7:21:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54682/100000 [16:02:12<7:22:59,  1.71it/s]
Train steps ... :  55%|█████▍    | 54683/100000 [16:02:12<7:23:15,  1.70it/s]
Train steps ... :  55%|█████▍    | 54684/100000 [16:02:13<7:22:57,  1.71it/s]
Train steps ... :  55%|█████▍    | 54685/100000 [16:02:13<7:22:47,  1.71it/s]
Train steps ... :  55%|█████▍    | 54686/100000 [16:02:14<7:22:01,  1.71it/s]
Train steps ... :  55%|█████▍    | 54687/100000 [16:02:15<7:22:02,  1.71it/s]
Train steps ... :  55%|█████▍    | 54688/100000 [16:02:15<7:21:49,  1.71it/s]
Train steps ... :  55%|█████▍    | 54689/100000 [16:02:16<7:22:58,  1.70it/s]
Train steps ... :  55%|█████▍    | 54690/100000 [16:02:16<7:23:35,  1.70it/s]
Train steps ... :  55%|█████▍    | 54691/100000 [16:02:17<7:22:41,  1.71it/s]
Train steps ... :  55%|█████▍    | 54692/100000 [16:02:17<7:23:52,  1.70it/s]
Train steps ... :  55%|█████▍    | 54693/100000 [16:02:18<7:23:49,  1.70it/s]
Train steps ... :  55%|█████▍    | 54694/100000 [16:02:19<7:22:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54695/100000 [16:02:19<7:22:52,  1.70it/s]
Train steps ... :  55%|█████▍    | 54696/100000 [16:02:20<7:23:08,  1.70it/s]
Train steps ... :  55%|█████▍    | 54697/100000 [16:02:20<7:21:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54698/100000 [16:02:21<7:22:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54699/100000 [16:02:22<7:21:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54700/100000 [16:02:22<7:22:48,  1.71it/s]Step... (54700 / 100000 | Loss: 0.6607077121734619, Learning Rate: 4.5527638190954774e-05)
+
                                                                             
Step... (54700 / 100000 | Loss: 0.6674286127090454, Learning Rate: 4.5527638190954774e-05)
+
Train steps ... :  55%|█████▍    | 54700/100000 [16:02:22<7:22:48,  1.71it/s]
Train steps ... :  55%|█████▍    | 54701/100000 [16:02:23<7:22:06,  1.71it/s]
Train steps ... :  55%|█████▍    | 54702/100000 [16:02:23<7:21:31,  1.71it/s]
Train steps ... :  55%|█████▍    | 54703/100000 [16:02:24<7:21:34,  1.71it/s]
Train steps ... :  55%|█████▍    | 54704/100000 [16:02:24<7:21:30,  1.71it/s]
Train steps ... :  55%|█████▍    | 54705/100000 [16:02:25<7:21:36,  1.71it/s]
Train steps ... :  55%|█████▍    | 54706/100000 [16:02:26<7:22:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54707/100000 [16:02:26<7:21:48,  1.71it/s]
Train steps ... :  55%|█████▍    | 54708/100000 [16:02:27<7:21:27,  1.71it/s]
Train steps ... :  55%|█████▍    | 54709/100000 [16:02:27<7:21:56,  1.71it/s]
Train steps ... :  55%|█████▍    | 54710/100000 [16:02:28<7:22:28,  1.71it/s]
Train steps ... :  55%|█████▍    | 54711/100000 [16:02:29<7:21:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54712/100000 [16:02:29<7:21:35,  1.71it/s]
Train steps ... :  55%|█████▍    | 54713/100000 [16:02:30<7:21:17,  1.71it/s]
Train steps ... :  55%|█████▍    | 54714/100000 [16:02:30<7:21:12,  1.71it/s]
Train steps ... :  55%|█████▍    | 54715/100000 [16:02:31<7:21:36,  1.71it/s]
Train steps ... :  55%|█████▍    | 54716/100000 [16:02:32<7:21:28,  1.71it/s]
Train steps ... :  55%|█████▍    | 54717/100000 [16:02:32<7:21:04,  1.71it/s]
Train steps ... :  55%|█████▍    | 54718/100000 [16:02:33<7:20:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54719/100000 [16:02:33<7:20:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54720/100000 [16:02:34<7:21:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54721/100000 [16:02:34<7:20:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54722/100000 [16:02:35<7:21:49,  1.71it/s]
Train steps ... :  55%|█████▍    | 54723/100000 [16:02:36<7:22:26,  1.71it/s]
Train steps ... :  55%|█████▍    | 54724/100000 [16:02:36<7:21:56,  1.71it/s]
Train steps ... :  55%|█████▍    | 54725/100000 [16:02:37<7:22:04,  1.71it/s]Step... (54725 / 100000 | Loss: 0.7450374364852905, Learning Rate: 4.550251256281407e-05)
+
                                                                             
Step... (54725 / 100000 | Loss: 0.6571905612945557, Learning Rate: 4.550251256281407e-05)
+
Train steps ... :  55%|█████▍    | 54725/100000 [16:02:37<7:22:04,  1.71it/s]
Train steps ... :  55%|█████▍    | 54726/100000 [16:02:37<7:21:47,  1.71it/s]
Train steps ... :  55%|█████▍    | 54727/100000 [16:02:38<7:21:56,  1.71it/s]
Train steps ... :  55%|█████▍    | 54728/100000 [16:02:39<7:22:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54729/100000 [16:02:39<7:21:31,  1.71it/s]
Train steps ... :  55%|███���█▍    | 54730/100000 [16:02:40<7:21:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54731/100000 [16:02:40<7:20:59,  1.71it/s]
Train steps ... :  55%|█████▍    | 54732/100000 [16:02:41<7:20:47,  1.71it/s]
Train steps ... :  55%|█████▍    | 54733/100000 [16:02:41<7:21:03,  1.71it/s]
Train steps ... :  55%|█████▍    | 54734/100000 [16:02:42<7:20:47,  1.71it/s]
Train steps ... :  55%|█████▍    | 54735/100000 [16:02:43<7:21:36,  1.71it/s]
Train steps ... :  55%|█████▍    | 54736/100000 [16:02:43<7:20:57,  1.71it/s]
Train steps ... :  55%|█████▍    | 54737/100000 [16:02:44<7:22:11,  1.71it/s]
Train steps ... :  55%|█████▍    | 54738/100000 [16:02:44<7:21:01,  1.71it/s]
Train steps ... :  55%|█████▍    | 54739/100000 [16:02:45<7:21:18,  1.71it/s]
Train steps ... :  55%|█████▍    | 54740/100000 [16:02:46<7:22:39,  1.70it/s]
Train steps ... :  55%|█████▍    | 54741/100000 [16:02:46<7:20:56,  1.71it/s]
Train steps ... :  55%|█████▍    | 54742/100000 [16:02:47<7:21:05,  1.71it/s]
Train steps ... :  55%|█████▍    | 54743/100000 [16:02:47<7:21:33,  1.71it/s]
Train steps ... :  55%|█████▍    | 54744/100000 [16:02:48<7:20:57,  1.71it/s]
Train steps ... :  55%|█████▍    | 54745/100000 [16:02:48<7:21:19,  1.71it/s]
Train steps ... :  55%|█████▍    | 54746/100000 [16:02:49<7:21:40,  1.71it/s]
Train steps ... :  55%|█████▍    | 54747/100000 [16:02:50<7:20:26,  1.71it/s]
Train steps ... :  55%|█████▍    | 54748/100000 [16:02:50<7:21:53,  1.71it/s]
Train steps ... :  55%|█████▍    | 54749/100000 [16:02:51<7:21:22,  1.71it/s]
Train steps ... :  55%|█████▍    | 54750/100000 [16:02:51<7:21:27,  1.71it/s]Step... (54750 / 100000 | Loss: 1.0381942987442017, Learning Rate: 4.5477386934673374e-05)
+
                                                                             
Step... (54750 / 100000 | Loss: 0.7748363018035889, Learning Rate: 4.5477386934673374e-05)
+
Train steps ... :  55%|█████▍    | 54750/100000 [16:02:52<7:21:27,  1.71it/s]
Train steps ... :  55%|█████▍    | 54751/100000 [16:02:52<7:22:22,  1.70it/s]
Train steps ... :  55%|█████▍    | 54752/100000 [16:02:53<7:21:58,  1.71it/s]
Train steps ... :  55%|█████▍    | 54753/100000 [16:02:53<7:22:04,  1.71it/s]
Train steps ... :  55%|█████▍    | 54754/100000 [16:02:54<7:22:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54755/100000 [16:02:54<7:22:07,  1.71it/s]
Train steps ... :  55%|█████▍    | 54756/100000 [16:02:55<7:23:22,  1.70it/s]
Train steps ... :  55%|█████▍    | 54757/100000 [16:02:56<7:22:48,  1.70it/s]
Train steps ... :  55%|█████▍    | 54758/100000 [16:02:56<7:22:49,  1.70it/s]
Train steps ... :  55%|█████▍    | 54759/100000 [16:02:57<7:22:02,  1.71it/s]
Train steps ... :  55%|█████▍    | 54760/100000 [16:02:57<7:22:30,  1.70it/s]
Train steps ... :  55%|█████▍    | 54761/100000 [16:02:58<7:21:54,  1.71it/s]
Train steps ... :  55%|█████▍    | 54762/100000 [16:02:58<7:21:23,  1.71it/s]
Train steps ... :  55%|█████▍    | 54763/100000 [16:02:59<7:21:30,  1.71it/s]
Train steps ... :  55%|█████▍    | 54764/100000 [16:03:00<7:20:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54765/100000 [16:03:00<7:20:58,  1.71it/s]
Train steps ... :  55%|█████▍    | 54766/100000 [16:03:01<7:21:11,  1.71it/s]
Train steps ... :  55%|█████▍    | 54767/100000 [16:03:01<7:20:50,  1.71it/s]
Train steps ... :  55%|█████▍    | 54768/100000 [16:03:02<7:20:30,  1.71it/s]
Train steps ... :  55%|█████▍    | 54769/100000 [16:03:03<7:20:38,  1.71it/s]
Train steps ... :  55%|█████▍    | 54770/100000 [16:03:03<7:21:57,  1.71it/s]
Train steps ... :  55%|█████▍    | 54771/100000 [16:03:04<7:21:14,  1.71it/s]
Train steps ... :  55%|█████▍    | 54772/100000 [16:03:04<7:20:17,  1.71it/s]
Train steps ... :  55%|█████▍    | 54773/100000 [16:03:05<7:20:18,  1.71it/s]
Train steps ... :  55%|█████▍    | 54774/100000 [16:03:05<7:20:56,  1.71it/s]
Train steps ... :  55%|█████▍    | 54775/100000 [16:03:06<7:20:16,  1.71it/s]Step... (54775 / 100000 | Loss: 0.9294847249984741, Learning Rate: 4.545226130653267e-05)
+
                                                                             
Step... (54775 / 100000 | Loss: 0.5905216932296753, Learning Rate: 4.545226130653267e-05)
+
Train steps ... :  55%|█████▍    | 54775/100000 [16:03:06<7:20:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54776/100000 [16:03:07<7:20:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54777/100000 [16:03:07<7:20:21,  1.71it/s]
Train steps ... :  55%|█████▍    | 54778/100000 [16:03:08<7:20:00,  1.71it/s]
Train steps ... :  55%|█████���    | 54779/100000 [16:03:08<7:19:58,  1.71it/s]
Train steps ... :  55%|█████▍    | 54780/100000 [16:03:09<7:19:58,  1.71it/s]
Train steps ... :  55%|█████▍    | 54781/100000 [16:03:10<7:19:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54782/100000 [16:03:10<7:19:38,  1.71it/s]
Train steps ... :  55%|█████▍    | 54783/100000 [16:03:11<7:20:00,  1.71it/s]
Train steps ... :  55%|█████▍    | 54784/100000 [16:03:11<7:19:46,  1.71it/s]
Train steps ... :  55%|█████▍    | 54785/100000 [16:03:12<7:19:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54786/100000 [16:03:12<7:20:07,  1.71it/s]
Train steps ... :  55%|█████▍    | 54787/100000 [16:03:13<7:20:20,  1.71it/s]
Train steps ... :  55%|█████▍    | 54788/100000 [16:03:14<7:21:21,  1.71it/s]
Train steps ... :  55%|█████▍    | 54789/100000 [16:03:14<7:20:33,  1.71it/s]
Train steps ... :  55%|█████▍    | 54790/100000 [16:03:15<7:20:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54791/100000 [16:03:15<7:20:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54792/100000 [16:03:16<7:20:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54793/100000 [16:03:17<7:20:08,  1.71it/s]
Train steps ... :  55%|█████▍    | 54794/100000 [16:03:17<7:21:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54795/100000 [16:03:18<7:20:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54796/100000 [16:03:18<7:21:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54797/100000 [16:03:19<7:21:12,  1.71it/s]
Train steps ... :  55%|█████▍    | 54798/100000 [16:03:19<7:20:08,  1.71it/s]
Train steps ... :  55%|█████▍    | 54799/100000 [16:03:20<7:21:44,  1.71it/s]
Train steps ... :  55%|█████▍    | 54800/100000 [16:03:21<7:21:15,  1.71it/s]Step... (54800 / 100000 | Loss: 0.5732749700546265, Learning Rate: 4.542713567839196e-05)
+
                                                                             
Step... (54800 / 100000 | Loss: 0.8639810681343079, Learning Rate: 4.542713567839196e-05)
+
Train steps ... :  55%|█████▍    | 54800/100000 [16:03:21<7:21:15,  1.71it/s]
Train steps ... :  55%|█████▍    | 54801/100000 [16:03:21<7:21:46,  1.71it/s]
Train steps ... :  55%|█████▍    | 54802/100000 [16:03:22<7:20:32,  1.71it/s]
Train steps ... :  55%|█████▍    | 54803/100000 [16:03:22<7:21:56,  1.70it/s]
Train steps ... :  55%|█████▍    | 54804/100000 [16:03:23<7:20:37,  1.71it/s]
Train steps ... :  55%|█████▍    | 54805/100000 [16:03:24<7:21:06,  1.71it/s]
Train steps ... :  55%|█████▍    | 54806/100000 [16:03:24<7:21:15,  1.71it/s]
Train steps ... :  55%|█████▍    | 54807/100000 [16:03:25<7:20:03,  1.71it/s]
Train steps ... :  55%|█████▍    | 54808/100000 [16:03:25<7:20:15,  1.71it/s]
Train steps ... :  55%|█████▍    | 54809/100000 [16:03:26<7:20:35,  1.71it/s]
Train steps ... :  55%|█████▍    | 54810/100000 [16:03:27<7:21:22,  1.71it/s]
Train steps ... :  55%|█████▍    | 54811/100000 [16:03:27<7:20:33,  1.71it/s]
Train steps ... :  55%|█████▍    | 54812/100000 [16:03:28<7:21:41,  1.71it/s]
Train steps ... :  55%|█████▍    | 54813/100000 [16:03:28<7:21:12,  1.71it/s]
Train steps ... :  55%|█████▍    | 54814/100000 [16:03:29<7:21:50,  1.70it/s]
Train steps ... :  55%|█████▍    | 54815/100000 [16:03:29<7:21:00,  1.71it/s]
Train steps ... :  55%|█████▍    | 54816/100000 [16:03:30<7:21:04,  1.71it/s]
Train steps ... :  55%|█████▍    | 54817/100000 [16:03:31<7:21:03,  1.71it/s]
Train steps ... :  55%|█████▍    | 54818/100000 [16:03:31<7:21:05,  1.71it/s]
Train steps ... :  55%|█████▍    | 54819/100000 [16:03:32<7:20:40,  1.71it/s]
Train steps ... :  55%|█████▍    | 54820/100000 [16:03:32<7:20:12,  1.71it/s]
Train steps ... :  55%|█████▍    | 54821/100000 [16:03:33<7:20:37,  1.71it/s]
Train steps ... :  55%|█████▍    | 54822/100000 [16:03:34<7:19:55,  1.71it/s]
Train steps ... :  55%|█████▍    | 54823/100000 [16:03:34<7:20:24,  1.71it/s]
Train steps ... :  55%|█████▍    | 54824/100000 [16:03:35<7:21:11,  1.71it/s]
Train steps ... :  55%|█████▍    | 54825/100000 [16:03:35<7:21:01,  1.71it/s]Step... (54825 / 100000 | Loss: 0.7281416058540344, Learning Rate: 4.540201005025126e-05)
+
                                                                             
Step... (54825 / 100000 | Loss: 0.6837235689163208, Learning Rate: 4.540201005025126e-05)
+
Train steps ... :  55%|█████▍    | 54825/100000 [16:03:36<7:21:01,  1.71it/s]
Train steps ... :  55%|█████▍    | 54826/100000 [16:03:36<7:20:30,  1.71it/s]
Train steps ... :  55%|█████▍    | 54827/100000 [16:03:36<7:20:59,  1.71it/s]
Train steps ... :  55%|█████▍    | 54828/100000 [16:03:37<7:21:27,  1.71it/s]
Train steps ... :  55%|█████▍    | 54829/100000 [16:03:38<7:20:49,  1.71it/s]
Train steps ... :  55%|█████▍    | 54830/100000 [16:03:38<7:20:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54831/100000 [16:03:39<7:20:25,  1.71it/s]
Train steps ... :  55%|█████▍    | 54832/100000 [16:03:39<7:20:35,  1.71it/s]
Train steps ... :  55%|█████▍    | 54833/100000 [16:03:40<7:21:24,  1.71it/s]
Train steps ... :  55%|█████▍    | 54834/100000 [16:03:41<7:20:57,  1.71it/s]
Train steps ... :  55%|█████▍    | 54835/100000 [16:03:41<7:21:28,  1.71it/s]
Train steps ... :  55%|█████▍    | 54836/100000 [16:03:42<7:20:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54837/100000 [16:03:42<7:20:55,  1.71it/s]
Train steps ... :  55%|█████▍    | 54838/100000 [16:03:43<7:20:25,  1.71it/s]
Train steps ... :  55%|█████▍    | 54839/100000 [16:03:43<7:20:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54840/100000 [16:03:44<7:20:10,  1.71it/s]
Train steps ... :  55%|█████▍    | 54841/100000 [16:03:45<7:20:07,  1.71it/s]
Train steps ... :  55%|█████▍    | 54842/100000 [16:03:45<7:20:04,  1.71it/s]
Train steps ... :  55%|█████▍    | 54843/100000 [16:03:46<7:20:24,  1.71it/s]
Train steps ... :  55%|█████▍    | 54844/100000 [16:03:46<7:20:01,  1.71it/s]
Train steps ... :  55%|█████▍    | 54845/100000 [16:03:47<7:20:26,  1.71it/s]
Train steps ... :  55%|█████▍    | 54846/100000 [16:03:48<7:20:14,  1.71it/s]
Train steps ... :  55%|█████▍    | 54847/100000 [16:03:48<7:20:23,  1.71it/s]
Train steps ... :  55%|█████▍    | 54848/100000 [16:03:49<7:20:01,  1.71it/s]
Train steps ... :  55%|█████▍    | 54849/100000 [16:03:49<7:19:48,  1.71it/s]
Train steps ... :  55%|█████▍    | 54850/100000 [16:03:50<7:19:45,  1.71it/s]Step... (54850 / 100000 | Loss: 0.7811331152915955, Learning Rate: 4.5376884422110554e-05)
+
                                                                             
Step... (54850 / 100000 | Loss: 0.7160775065422058, Learning Rate: 4.5376884422110554e-05)
+
Train steps ... :  55%|█████▍    | 54850/100000 [16:03:50<7:19:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54851/100000 [16:03:51<7:20:20,  1.71it/s]
Train steps ... :  55%|█████▍    | 54852/100000 [16:03:51<7:20:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54853/100000 [16:03:52<7:20:05,  1.71it/s]
Train steps ... :  55%|█████▍    | 54854/100000 [16:03:52<7:20:14,  1.71it/s]
Train steps ... :  55%|█████▍    | 54855/100000 [16:03:53<7:19:47,  1.71it/s]
Train steps ... :  55%|█████▍    | 54856/100000 [16:03:53<7:19:30,  1.71it/s]
Train steps ... :  55%|█████▍    | 54857/100000 [16:03:54<7:19:50,  1.71it/s]
Train steps ... :  55%|█████▍    | 54858/100000 [16:03:55<7:20:04,  1.71it/s]
Train steps ... :  55%|█████▍    | 54859/100000 [16:03:55<7:20:47,  1.71it/s]
Train steps ... :  55%|█████▍    | 54860/100000 [16:03:56<7:19:53,  1.71it/s]
Train steps ... :  55%|█████▍    | 54861/100000 [16:03:56<7:19:56,  1.71it/s]
Train steps ... :  55%|█████▍    | 54862/100000 [16:03:57<7:20:19,  1.71it/s]
Train steps ... :  55%|█████▍    | 54863/100000 [16:03:58<7:20:37,  1.71it/s]
Train steps ... :  55%|█████▍    | 54864/100000 [16:03:58<7:20:12,  1.71it/s]
Train steps ... :  55%|█████▍    | 54865/100000 [16:03:59<7:20:38,  1.71it/s]
Train steps ... :  55%|█████▍    | 54866/100000 [16:03:59<7:20:50,  1.71it/s]
Train steps ... :  55%|█████▍    | 54867/100000 [16:04:00<7:21:21,  1.70it/s]
Train steps ... :  55%|█████▍    | 54868/100000 [16:04:00<7:21:08,  1.71it/s]
Train steps ... :  55%|█████▍    | 54869/100000 [16:04:01<7:20:25,  1.71it/s]
Train steps ... :  55%|█████▍    | 54870/100000 [16:04:02<7:20:18,  1.71it/s]
Train steps ... :  55%|█████▍    | 54871/100000 [16:04:02<7:20:15,  1.71it/s]
Train steps ... :  55%|█████▍    | 54872/100000 [16:04:03<7:21:44,  1.70it/s]
Train steps ... :  55%|█████▍    | 54873/100000 [16:04:03<7:19:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54874/100000 [16:04:04<7:19:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54875/100000 [16:04:05<7:19:59,  1.71it/s]Step... (54875 / 100000 | Loss: 0.8189815282821655, Learning Rate: 4.535175879396985e-05)
+
                                                                             
Step... (54875 / 100000 | Loss: 0.6169577240943909, Learning Rate: 4.535175879396985e-05)
+
Train steps ... :  55%|█████▍    | 54875/100000 [16:04:05<7:19:59,  1.71it/s]
Train steps ... :  55%|█████▍    | 54876/100000 [16:04:05<7:20:07,  1.71it/s]
Train steps ... :  55%|█████▍    | 54877/100000 [16:04:06<7:19:58,  1.71it/s]
Train steps ... :  55%|█████▍    | 54878/100000 [16:04:06<7:19:59,  1.71it/s]
Train steps ... :  55%|█████▍    | 54879/100000 [16:04:07<7:20:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54880/100000 [16:04:07<7:19:55,  1.71it/s]
Train steps ... :  55%|█████▍    | 54881/100000 [16:04:08<7:22:30,  1.70it/s]
Train steps ... :  55%|█████▍    | 54882/100000 [16:04:09<7:21:52,  1.70it/s]
Train steps ... :  55%|█████▍    | 54883/100000 [16:04:09<7:21:43,  1.70it/s]
Train steps ... :  55%|█████▍    | 54884/100000 [16:04:10<7:23:22,  1.70it/s]
Train steps ... :  55%|█████▍    | 54885/100000 [16:04:10<7:20:12,  1.71it/s]
Train steps ... :  55%|█████▍    | 54886/100000 [16:04:11<7:20:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54887/100000 [16:04:12<7:20:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54888/100000 [16:04:12<7:21:21,  1.70it/s]
Train steps ... :  55%|█████▍    | 54889/100000 [16:04:13<7:20:28,  1.71it/s]
Train steps ... :  55%|█████▍    | 54890/100000 [16:04:13<7:21:01,  1.70it/s]
Train steps ... :  55%|█████▍    | 54891/100000 [16:04:14<7:22:00,  1.70it/s]
Train steps ... :  55%|█████▍    | 54892/100000 [16:04:15<7:21:23,  1.70it/s]
Train steps ... :  55%|█████▍    | 54893/100000 [16:04:15<7:21:28,  1.70it/s]
Train steps ... :  55%|█████▍    | 54894/100000 [16:04:16<7:21:53,  1.70it/s]
Train steps ... :  55%|█████▍    | 54895/100000 [16:04:16<7:20:49,  1.71it/s]
Train steps ... :  55%|█████▍    | 54896/100000 [16:04:17<7:21:39,  1.70it/s]
Train steps ... :  55%|█████▍    | 54897/100000 [16:04:17<7:20:58,  1.70it/s]
Train steps ... :  55%|█████▍    | 54898/100000 [16:04:18<7:23:01,  1.70it/s]
Train steps ... :  55%|█████▍    | 54899/100000 [16:04:19<7:21:02,  1.70it/s]
Train steps ... :  55%|█████▍    | 54900/100000 [16:04:19<7:20:28,  1.71it/s]Step... (54900 / 100000 | Loss: 0.8149491548538208, Learning Rate: 4.532663316582915e-05)
+
                                                                             
Step... (54900 / 100000 | Loss: 0.7955968379974365, Learning Rate: 4.532663316582915e-05)
+
Train steps ... :  55%|█████▍    | 54900/100000 [16:04:20<7:20:28,  1.71it/s]
Train steps ... :  55%|█████▍    | 54901/100000 [16:04:20<7:21:32,  1.70it/s]
Train steps ... :  55%|█████▍    | 54902/100000 [16:04:20<7:22:36,  1.70it/s]
Train steps ... :  55%|█████▍    | 54903/100000 [16:04:21<7:21:23,  1.70it/s]
Train steps ... :  55%|█████▍    | 54904/100000 [16:04:22<7:20:37,  1.71it/s]
Train steps ... :  55%|█████▍    | 54905/100000 [16:04:22<7:21:06,  1.70it/s]
Train steps ... :  55%|█████▍    | 54906/100000 [16:04:23<7:20:20,  1.71it/s]
Train steps ... :  55%|█████▍    | 54907/100000 [16:04:23<7:20:05,  1.71it/s]
Train steps ... :  55%|█████▍    | 54908/100000 [16:04:24<7:20:07,  1.71it/s]
Train steps ... :  55%|█████▍    | 54909/100000 [16:04:25<7:20:37,  1.71it/s]
Train steps ... :  55%|█████▍    | 54910/100000 [16:04:25<7:20:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54911/100000 [16:04:26<7:20:46,  1.70it/s]
Train steps ... :  55%|█████▍    | 54912/100000 [16:04:26<7:19:49,  1.71it/s]
Train steps ... :  55%|█████▍    | 54913/100000 [16:04:27<7:20:28,  1.71it/s]
Train steps ... :  55%|█████▍    | 54914/100000 [16:04:27<7:20:26,  1.71it/s]
Train steps ... :  55%|█████▍    | 54915/100000 [16:04:28<7:19:28,  1.71it/s]
Train steps ... :  55%|█████▍    | 54916/100000 [16:04:29<7:19:07,  1.71it/s]
Train steps ... :  55%|█████▍    | 54917/100000 [16:04:29<7:19:10,  1.71it/s]
Train steps ... :  55%|█████▍    | 54918/100000 [16:04:30<7:19:08,  1.71it/s]
Train steps ... :  55%|█████▍    | 54919/100000 [16:04:30<7:20:12,  1.71it/s]
Train steps ... :  55%|█████▍    | 54920/100000 [16:04:31<7:19:36,  1.71it/s]
Train steps ... :  55%|█████▍    | 54921/100000 [16:04:32<7:18:28,  1.71it/s]
Train steps ... :  55%|█████▍    | 54922/100000 [16:04:32<7:19:41,  1.71it/s]
Train steps ... :  55%|█████▍    | 54923/100000 [16:04:33<7:19:18,  1.71it/s]
Train steps ... :  55%|█████▍    | 54924/100000 [16:04:33<7:20:11,  1.71it/s]
Train steps ... :  55%|█████▍    | 54925/100000 [16:04:34<7:18:54,  1.71it/s]Step... (54925 / 100000 | Loss: 0.9911764860153198, Learning Rate: 4.530150753768844e-05)
+
                                                                             
Step... (54925 / 100000 | Loss: 0.7205020189285278, Learning Rate: 4.530150753768844e-05)
+
Train steps ... :  55%|█████▍    | 54925/100000 [16:04:34<7:18:54,  1.71it/s]
Train steps ... :  55%|█████▍    | 54926/100000 [16:04:34<7:19:35,  1.71it/s]
Train steps ... :  55%|█████▍    | 54927/100000 [16:04:35<7:20:11,  1.71it/s]
Train steps ... :  55%|█████▍    | 54928/100000 [16:04:36<7:19:15,  1.71it/s]
Train steps ... :  55%|█████▍    | 54929/100000 [16:04:36<7:20:36,  1.70it/s]
Train steps ... :  55%|█████▍    | 54930/100000 [16:04:37<7:19:02,  1.71it/s]
Train steps ... :  55%|█████▍    | 54931/100000 [16:04:37<7:19:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54932/100000 [16:04:38<7:20:00,  1.71it/s]
Train steps ... :  55%|█████▍    | 54933/100000 [16:04:39<7:19:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54934/100000 [16:04:39<7:19:39,  1.71it/s]
Train steps ... :  55%|█████▍    | 54935/100000 [16:04:40<7:19:21,  1.71it/s]
Train steps ... :  55%|█████▍    | 54936/100000 [16:04:40<7:19:21,  1.71it/s]
Train steps ... :  55%|█████▍    | 54937/100000 [16:04:41<7:19:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54938/100000 [16:04:41<7:18:59,  1.71it/s]
Train steps ... :  55%|█████▍    | 54939/100000 [16:04:42<7:19:24,  1.71it/s]
Train steps ... :  55%|█████▍    | 54940/100000 [16:04:43<7:19:33,  1.71it/s]
Train steps ... :  55%|█████▍    | 54941/100000 [16:04:43<7:19:00,  1.71it/s]
Train steps ... :  55%|█████▍    | 54942/100000 [16:04:44<7:19:31,  1.71it/s]
Train steps ... :  55%|█████▍    | 54943/100000 [16:04:44<7:18:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54944/100000 [16:04:45<7:19:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54945/100000 [16:04:46<7:19:09,  1.71it/s]
Train steps ... :  55%|█████▍    | 54946/100000 [16:04:46<7:19:31,  1.71it/s]
Train steps ... :  55%|█████▍    | 54947/100000 [16:04:47<7:19:28,  1.71it/s]
Train steps ... :  55%|█████▍    | 54948/100000 [16:04:47<7:18:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54949/100000 [16:04:48<7:19:05,  1.71it/s]
Train steps ... :  55%|█████▍    | 54950/100000 [16:04:49<7:18:58,  1.71it/s]Step... (54950 / 100000 | Loss: 0.7594696283340454, Learning Rate: 4.527638190954774e-05)
+
                                                                             
Step... (54950 / 100000 | Loss: 0.761326789855957, Learning Rate: 4.527638190954774e-05)
+
Train steps ... :  55%|█████▍    | 54950/100000 [16:04:49<7:18:58,  1.71it/s]
Train steps ... :  55%|█████▍    | 54951/100000 [16:04:49<7:19:15,  1.71it/s]
Train steps ... :  55%|█████▍    | 54952/100000 [16:04:50<7:18:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54953/100000 [16:04:50<7:19:12,  1.71it/s]
Train steps ... :  55%|█████▍    | 54954/100000 [16:04:51<7:19:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54955/100000 [16:04:51<7:18:57,  1.71it/s]
Train steps ... :  55%|█████▍    | 54956/100000 [16:04:52<7:19:31,  1.71it/s]
Train steps ... :  55%|█████▍    | 54957/100000 [16:04:53<7:19:42,  1.71it/s]
Train steps ... :  55%|█████▍    | 54958/100000 [16:04:53<7:19:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54959/100000 [16:04:54<7:19:29,  1.71it/s]
Train steps ... :  55%|█████▍    | 54960/100000 [16:04:54<7:18:57,  1.71it/s]
Train steps ... :  55%|█████▍    | 54961/100000 [16:04:55<7:18:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54962/100000 [16:04:56<7:19:34,  1.71it/s]
Train steps ... :  55%|█████▍    | 54963/100000 [16:04:56<7:18:50,  1.71it/s]
Train steps ... :  55%|█████▍    | 54964/100000 [16:04:57<7:18:58,  1.71it/s]
Train steps ... :  55%|█████▍    | 54965/100000 [16:04:57<7:20:16,  1.70it/s]
Train steps ... :  55%|█████▍    | 54966/100000 [16:04:58<7:18:54,  1.71it/s]
Train steps ... :  55%|█████▍    | 54967/100000 [16:04:58<7:20:20,  1.70it/s]
Train steps ... :  55%|█████▍    | 54968/100000 [16:04:59<7:19:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54969/100000 [16:05:00<7:19:01,  1.71it/s]
Train steps ... :  55%|█████▍    | 54970/100000 [16:05:00<7:20:05,  1.71it/s]
Train steps ... :  55%|█████▍    | 54971/100000 [16:05:01<7:19:35,  1.71it/s]
Train steps ... :  55%|█████▍    | 54972/100000 [16:05:01<7:19:16,  1.71it/s]
Train steps ... :  55%|█████▍    | 54973/100000 [16:05:02<7:18:20,  1.71it/s]
Train steps ... :  55%|█████▍    | 54974/100000 [16:05:03<7:18:18,  1.71it/s]
Train steps ... :  55%|█████▍    | 54975/100000 [16:05:03<7:18:52,  1.71it/s]Step... (54975 / 100000 | Loss: 0.9526070356369019, Learning Rate: 4.525125628140704e-05)
+
                                                                             
Step... (54975 / 100000 | Loss: 0.5229194164276123, Learning Rate: 4.525125628140704e-05)
+
Train steps ... :  55%|█████▍    | 54975/100000 [16:05:03<7:18:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54976/100000 [16:05:04<7:18:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54977/100000 [16:05:04<7:18:30,  1.71it/s]
Train steps ... :  55%|█████▍    | 54978/100000 [16:05:05<7:18:46,  1.71it/s]
Train steps ... :  55%|█████▍    | 54979/100000 [16:05:05<7:18:23,  1.71it/s]
Train steps ... :  55%|█████▍    | 54980/100000 [16:05:06<7:18:59,  1.71it/s]
Train steps ... :  55%|█████▍    | 54981/100000 [16:05:07<7:20:14,  1.70it/s]
Train steps ... :  55%|█████▍    | 54982/100000 [16:05:07<7:19:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54983/100000 [16:05:08<7:19:49,  1.71it/s]
Train steps ... :  55%|█████▍    | 54984/100000 [16:05:08<7:20:14,  1.70it/s]
Train steps ... :  55%|█████▍    | 54985/100000 [16:05:09<7:19:51,  1.71it/s]
Train steps ... :  55%|█████▍    | 54986/100000 [16:05:10<7:20:21,  1.70it/s]
Train steps ... :  55%|█████▍    | 54987/100000 [16:05:10<7:19:47,  1.71it/s]
Train steps ... :  55%|█████▍    | 54988/100000 [16:05:11<7:19:43,  1.71it/s]
Train steps ... :  55%|█████▍    | 54989/100000 [16:05:11<7:19:19,  1.71it/s]
Train steps ... :  55%|█████▍    | 54990/100000 [16:05:12<7:20:02,  1.70it/s]
Train steps ... :  55%|█████▍    | 54991/100000 [16:05:13<7:20:22,  1.70it/s]
Train steps ... :  55%|█████▍    | 54992/100000 [16:05:13<7:20:24,  1.70it/s]
Train steps ... :  55%|█████▍    | 54993/100000 [16:05:14<7:20:10,  1.70it/s]
Train steps ... :  55%|█████▍    | 54994/100000 [16:05:14<7:18:52,  1.71it/s]
Train steps ... :  55%|█████▍    | 54995/100000 [16:05:15<7:18:45,  1.71it/s]
Train steps ... :  55%|█████▍    | 54996/100000 [16:05:15<7:18:50,  1.71it/s]
Train steps ... :  55%|█████▍    | 54997/100000 [16:05:16<7:19:31,  1.71it/s]
Train steps ... :  55%|█████▍    | 54998/100000 [16:05:17<7:19:13,  1.71it/s]
Train steps ... :  55%|█████▍    | 54999/100000 [16:05:17<7:19:20,  1.71it/s]
Train steps ... :  55%|█████▌    | 55000/100000 [16:05:18<7:19:19,  1.71it/s]Step... (55000 / 100000 | Loss: 0.9918637275695801, Learning Rate: 4.522613065326633e-05)
+
                                                                             
Step... (55000 / 100000 | Loss: 0.6646056175231934, Learning Rate: 4.522613065326633e-05)
+
Train steps ... :  55%|█████▌    | 55000/100000 [16:05:18<7:19:19,  1.71it/s]06/18/2024 07:59:45 - INFO - accelerate.accelerator - Saving current state to ./checkpoint-55000-epoch-3
+06/18/2024 07:59:45 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/18/2024 07:59:48 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-55000-epoch-3/model.safetensors
+06/18/2024 07:59:48 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/18/2024 07:59:52 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-55000-epoch-3/model_1.safetensors
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Optimizer state saved in checkpoint-55000-epoch-3/optimizer.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Scheduler state saved in checkpoint-55000-epoch-3/scheduler.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in checkpoint-55000-epoch-3/sampler.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in checkpoint-55000-epoch-3/sampler_1.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 2 saved in checkpoint-55000-epoch-3/sampler_2.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 3 saved in checkpoint-55000-epoch-3/sampler_3.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 4 saved in checkpoint-55000-epoch-3/sampler_4.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 5 saved in checkpoint-55000-epoch-3/sampler_5.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 6 saved in checkpoint-55000-epoch-3/sampler_6.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 7 saved in checkpoint-55000-epoch-3/sampler_7.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 8 saved in checkpoint-55000-epoch-3/sampler_8.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 9 saved in checkpoint-55000-epoch-3/sampler_9.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 10 saved in checkpoint-55000-epoch-3/sampler_10.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 11 saved in checkpoint-55000-epoch-3/sampler_11.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 12 saved in checkpoint-55000-epoch-3/sampler_12.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Sampler state for dataloader 13 saved in checkpoint-55000-epoch-3/sampler_13.bin
+06/18/2024 07:59:53 - INFO - accelerate.checkpointing - Random states saved in checkpoint-55000-epoch-3/random_states_0.pkl
+06/18/2024 07:59:53 - INFO - __main__ - Deleting older checkpoint [checkpoint-30000-epoch-1] due to args.save_total_limit
+
+
  0%|          | 0/5 [00:00<?, ?it/s]
+
 20%|██        | 1/5 [01:45<07:00, 105.12s/it]
+
 40%|████      | 2/5 [02:18<03:09, 63.10s/it] 
+
 60%|██████    | 3/5 [02:19<01:09, 34.55s/it]
+
 80%|████████  | 4/5 [02:19<00:21, 21.15s/it]
+
100%|██████████| 5/5 [02:20<00:00, 13.75s/it]
100%|██████████| 5/5 [02:20<00:00, 28.12s/it]