diff --git "a/train.log" "b/train.log"
--- "a/train.log"
+++ "b/train.log"
@@ -15615,3 +15615,4229 @@ Eval results for step (15000 / 100000 | Eval Loss: 1.2628703117370605 | Eval wer
 
 60%|██████    | 3/5 [02:19<01:09, 34.56s/it]
 
 80%|████████  | 4/5 [02:19<00:21, 21.17s/it]
 
100%|██████████| 5/5 [02:20<00:00, 13.75s/it]
100%|██████████| 5/5 [02:20<00:00, 28.11s/it]
+
+
+
Evaluating eval...:   0%|          | 0/1900 [00:00<?, ?it/s]
+
+
Evaluating eval...:   0%|          | 1/1900 [00:03<1:48:09,  3.42s/it]
+
+
Evaluating eval...:   0%|          | 2/1900 [00:04<1:08:52,  2.18s/it]
+
+
Evaluating eval...:   0%|          | 3/1900 [00:05<55:41,  1.76s/it]  
+
+
Evaluating eval...:   0%|          | 4/1900 [00:07<48:51,  1.55s/it]
+
+
Evaluating eval...:   0%|          | 5/1900 [00:08<45:09,  1.43s/it]
+
+
Evaluating eval...:   0%|          | 6/1900 [00:09<42:40,  1.35s/it]
+
+
Evaluating eval...:   0%|          | 7/1900 [00:10<40:58,  1.30s/it]
+
+
Evaluating eval...:   0%|          | 8/1900 [00:11<39:36,  1.26s/it]
+
+
Evaluating eval...:   0%|          | 9/1900 [00:13<38:35,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 10/1900 [00:14<38:24,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 11/1900 [00:15<38:21,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 12/1900 [00:16<38:10,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 13/1900 [00:17<38:02,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 14/1900 [00:19<37:44,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 15/1900 [00:20<37:50,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 16/1900 [00:21<37:30,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 17/1900 [00:22<37:34,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 18/1900 [00:23<37:14,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 19/1900 [00:25<36:45,  1.17s/it]
+
+
Evaluating eval...:   1%|          | 20/1900 [00:26<36:58,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 21/1900 [00:27<37:26,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 22/1900 [00:28<37:10,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 23/1900 [00:29<36:43,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 24/1900 [00:30<36:56,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 25/1900 [00:32<36:32,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 26/1900 [00:33<36:10,  1.16s/it]
+
+
Evaluating eval...:   1%|▏         | 27/1900 [00:34<36:46,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 28/1900 [00:35<36:34,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 29/1900 [00:36<36:27,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 30/1900 [00:37<36:40,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 31/1900 [00:39<36:45,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 32/1900 [00:40<36:49,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 33/1900 [00:41<37:00,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 34/1900 [00:42<37:42,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 35/1900 [00:44<38:18,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 36/1900 [00:45<38:17,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 37/1900 [00:46<37:59,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 38/1900 [00:47<37:49,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 39/1900 [00:48<37:34,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 40/1900 [00:50<37:20,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 41/1900 [00:51<36:51,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 42/1900 [00:52<37:30,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 43/1900 [00:53<37:16,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 44/1900 [00:54<37:21,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 45/1900 [00:56<36:45,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 46/1900 [00:57<36:33,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 47/1900 [00:58<36:04,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 48/1900 [00:59<35:53,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 49/1900 [01:00<35:46,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 50/1900 [01:01<36:14,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 51/1900 [01:03<36:36,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 52/1900 [01:04<36:22,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 53/1900 [01:05<36:06,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 54/1900 [01:06<36:42,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 55/1900 [01:07<37:27,  1.22s/it]
+
+
Evaluating eval...:   3%|▎         | 56/1900 [01:09<37:20,  1.22s/it]
+
+
Evaluating eval...:   3%|▎         | 57/1900 [01:10<37:02,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 58/1900 [01:11<37:08,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 59/1900 [01:12<36:47,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 60/1900 [01:13<36:14,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 61/1900 [01:15<44:11,  1.44s/it]
+
+
Evaluating eval...:   3%|▎         | 62/1900 [01:17<41:40,  1.36s/it]
+
+
Evaluating eval...:   3%|▎         | 63/1900 [01:18<40:02,  1.31s/it]
+
+
Evaluating eval...:   3%|▎         | 64/1900 [01:19<38:42,  1.26s/it]
+
+
Evaluating eval...:   3%|▎         | 65/1900 [01:20<37:35,  1.23s/it]
+
+
Evaluating eval...:   3%|▎         | 66/1900 [01:21<36:54,  1.21s/it]
+
+
Evaluating eval...:   4%|▎         | 67/1900 [01:22<36:37,  1.20s/it]
+
+
Evaluating eval...:   4%|▎         | 68/1900 [01:24<37:47,  1.24s/it]
+
+
Evaluating eval...:   4%|▎         | 69/1900 [01:25<36:50,  1.21s/it]
+
+
Evaluating eval...:   4%|▎         | 70/1900 [01:26<37:03,  1.22s/it]
+
+
Evaluating eval...:   4%|▎         | 71/1900 [01:27<36:47,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 72/1900 [01:29<36:56,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 73/1900 [01:30<36:41,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 74/1900 [01:31<36:28,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 75/1900 [01:32<36:04,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 76/1900 [01:33<36:05,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 77/1900 [01:34<36:06,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 78/1900 [01:36<36:04,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 79/1900 [01:37<36:19,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 80/1900 [01:38<36:09,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 81/1900 [01:39<35:49,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 82/1900 [01:40<36:40,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 83/1900 [01:42<37:19,  1.23s/it]
+
+
Evaluating eval...:   4%|▍         | 84/1900 [01:43<36:43,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 85/1900 [01:44<36:24,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 86/1900 [01:45<35:44,  1.18s/it]
+
+
Evaluating eval...:   5%|▍         | 87/1900 [01:46<36:04,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 88/1900 [01:48<35:43,  1.18s/it]
+
+
Evaluating eval...:   5%|▍         | 89/1900 [01:50<45:05,  1.49s/it]
+
+
Evaluating eval...:   5%|▍         | 90/1900 [01:51<42:16,  1.40s/it]
+
+
Evaluating eval...:   5%|▍         | 91/1900 [01:52<40:41,  1.35s/it]
+
+
Evaluating eval...:   5%|▍         | 92/1900 [01:53<38:55,  1.29s/it]
+
+
Evaluating eval...:   5%|▍         | 93/1900 [01:55<37:44,  1.25s/it]
+
+
Evaluating eval...:   5%|▍         | 94/1900 [01:56<36:44,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 95/1900 [01:57<36:00,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 96/1900 [01:58<36:48,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 97/1900 [01:59<35:58,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 98/1900 [02:01<36:40,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 99/1900 [02:02<36:14,  1.21s/it]
+
+
Evaluating eval...:   5%|▌         | 100/1900 [02:03<35:57,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 101/1900 [02:04<36:38,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 102/1900 [02:05<36:57,  1.23s/it]
+
+
Evaluating eval...:   5%|▌         | 103/1900 [02:07<36:34,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 104/1900 [02:08<36:09,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 105/1900 [02:09<36:03,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 106/1900 [02:10<35:24,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 107/1900 [02:11<35:43,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 108/1900 [02:13<35:12,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 109/1900 [02:14<35:32,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 110/1900 [02:15<35:12,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 111/1900 [02:16<35:29,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 112/1900 [02:17<36:17,  1.22s/it]
+
+
Evaluating eval...:   6%|▌         | 113/1900 [02:19<35:52,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 114/1900 [02:20<35:23,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 115/1900 [02:21<35:08,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 116/1900 [02:22<34:41,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 117/1900 [02:23<34:53,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 118/1900 [02:24<35:13,  1.19s/it]
+
+
Evaluating eval...:   6%|▋         | 119/1900 [02:26<35:00,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 120/1900 [02:27<35:27,  1.20s/it]
+
+
Evaluating eval...:   6%|▋         | 121/1900 [02:28<35:02,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 122/1900 [02:29<35:06,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 123/1900 [02:30<35:01,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 124/1900 [02:32<35:19,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 125/1900 [02:33<35:27,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 126/1900 [02:34<35:46,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 127/1900 [02:35<35:51,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 128/1900 [02:36<35:19,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 129/1900 [02:38<34:54,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 130/1900 [02:39<34:44,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 131/1900 [02:40<34:56,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 132/1900 [02:41<35:25,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 133/1900 [02:42<34:47,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 134/1900 [02:43<34:56,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 135/1900 [02:45<35:19,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 136/1900 [02:46<35:44,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 137/1900 [02:47<36:10,  1.23s/it]
+
+
Evaluating eval...:   7%|▋         | 138/1900 [02:48<35:57,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 139/1900 [02:50<35:32,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 140/1900 [02:51<35:22,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 141/1900 [02:52<35:05,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 142/1900 [02:53<35:40,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 143/1900 [02:54<35:50,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 144/1900 [02:56<35:01,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 145/1900 [02:57<35:05,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 146/1900 [02:58<34:56,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 147/1900 [02:59<35:17,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 148/1900 [03:00<34:42,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 149/1900 [03:02<34:56,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 150/1900 [03:03<35:46,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 151/1900 [03:04<35:44,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 152/1900 [03:05<35:36,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 153/1900 [03:07<35:54,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 154/1900 [03:08<35:44,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 155/1900 [03:09<35:16,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 156/1900 [03:10<35:11,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 157/1900 [03:12<36:20,  1.25s/it]
+
+
Evaluating eval...:   8%|▊         | 158/1900 [03:13<35:46,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 159/1900 [03:14<34:57,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 160/1900 [03:15<34:43,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 161/1900 [03:16<35:35,  1.23s/it]
+
+
Evaluating eval...:   9%|▊         | 162/1900 [03:18<34:59,  1.21s/it]
+
+
Evaluating eval...:   9%|▊         | 163/1900 [03:19<34:26,  1.19s/it]
+
+
Evaluating eval...:   9%|▊         | 164/1900 [03:20<34:35,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 165/1900 [03:21<34:32,  1.19s/it]
+
+
Evaluating eval...:   9%|▊         | 166/1900 [03:22<34:31,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 167/1900 [03:24<35:15,  1.22s/it]
+
+
Evaluating eval...:   9%|▉         | 168/1900 [03:25<34:46,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 169/1900 [03:26<34:28,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 170/1900 [03:27<34:23,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 171/1900 [03:28<34:11,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 172/1900 [03:29<34:26,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 173/1900 [03:31<34:27,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 174/1900 [03:32<34:53,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 175/1900 [03:33<34:14,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 176/1900 [03:34<33:51,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 177/1900 [03:36<42:47,  1.49s/it]
+
+
Evaluating eval...:   9%|▉         | 178/1900 [03:38<40:28,  1.41s/it]
+
+
Evaluating eval...:   9%|▉         | 179/1900 [03:39<38:11,  1.33s/it]
+
+
Evaluating eval...:   9%|▉         | 180/1900 [03:40<36:57,  1.29s/it]
+
+
Evaluating eval...:  10%|▉         | 181/1900 [03:41<36:00,  1.26s/it]
+
+
Evaluating eval...:  10%|▉         | 182/1900 [03:43<44:16,  1.55s/it]
+
+
Evaluating eval...:  10%|▉         | 183/1900 [03:45<41:16,  1.44s/it]
+
+
Evaluating eval...:  10%|▉         | 184/1900 [03:46<38:52,  1.36s/it]
+
+
Evaluating eval...:  10%|▉         | 185/1900 [03:47<37:20,  1.31s/it]
+
+
Evaluating eval...:  10%|▉         | 186/1900 [03:48<36:01,  1.26s/it]
+
+
Evaluating eval...:  10%|▉         | 187/1900 [03:49<35:31,  1.24s/it]
+
+
Evaluating eval...:  10%|▉         | 188/1900 [03:51<35:14,  1.23s/it]
+
+
Evaluating eval...:  10%|▉         | 189/1900 [03:52<34:30,  1.21s/it]
+
+
Evaluating eval...:  10%|█         | 190/1900 [03:53<34:15,  1.20s/it]
+
+
Evaluating eval...:  10%|█         | 191/1900 [03:54<33:52,  1.19s/it]
+
+
Evaluating eval...:  10%|█         | 192/1900 [03:55<34:44,  1.22s/it]
+
+
Evaluating eval...:  10%|█         | 193/1900 [03:57<35:44,  1.26s/it]
+
+
Evaluating eval...:  10%|█         | 194/1900 [03:58<35:37,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 195/1900 [03:59<35:20,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 196/1900 [04:00<34:56,  1.23s/it]
+
+
Evaluating eval...:  10%|█         | 197/1900 [04:02<36:05,  1.27s/it]
+
+
Evaluating eval...:  10%|█         | 198/1900 [04:03<36:01,  1.27s/it]
+
+
Evaluating eval...:  10%|█         | 199/1900 [04:04<35:03,  1.24s/it]
+
+
Evaluating eval...:  11%|█         | 200/1900 [04:05<34:21,  1.21s/it]
+
+
Evaluating eval...:  11%|█         | 201/1900 [04:06<33:50,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 202/1900 [04:08<33:25,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 203/1900 [04:09<33:39,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 204/1900 [04:10<33:31,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 205/1900 [04:11<33:29,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 206/1900 [04:12<33:20,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 207/1900 [04:14<33:52,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 208/1900 [04:15<33:24,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 209/1900 [04:16<33:16,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 210/1900 [04:17<33:05,  1.17s/it]
+
+
Evaluating eval...:  11%|█         | 211/1900 [04:18<33:15,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 212/1900 [04:19<33:26,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 213/1900 [04:21<34:23,  1.22s/it]
+
+
Evaluating eval...:  11%|█▏        | 214/1900 [04:22<34:16,  1.22s/it]
+
+
Evaluating eval...:  11%|█▏        | 215/1900 [04:23<34:17,  1.22s/it]
+
+
Evaluating eval...:  11%|█▏        | 216/1900 [04:24<33:56,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 217/1900 [04:26<33:54,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 218/1900 [04:27<34:10,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 219/1900 [04:28<34:00,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 220/1900 [04:29<34:04,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 221/1900 [04:30<33:46,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 222/1900 [04:32<33:31,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 223/1900 [04:33<33:02,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 224/1900 [04:34<32:40,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 225/1900 [04:35<32:49,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 226/1900 [04:36<32:49,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 227/1900 [04:37<32:39,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 228/1900 [04:39<33:22,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 229/1900 [04:40<32:50,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 230/1900 [04:41<32:53,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 231/1900 [04:42<33:08,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 232/1900 [04:43<32:44,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 233/1900 [04:45<32:48,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 234/1900 [04:46<32:45,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 235/1900 [04:47<32:46,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 236/1900 [04:48<33:13,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 237/1900 [04:49<33:13,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 238/1900 [04:51<33:30,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 239/1900 [04:52<34:20,  1.24s/it]
+
+
Evaluating eval...:  13%|█▎        | 240/1900 [04:53<33:36,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 241/1900 [04:54<33:06,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 242/1900 [04:55<33:03,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 243/1900 [04:57<32:38,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 244/1900 [04:58<32:32,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 245/1900 [04:59<33:17,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 246/1900 [05:00<33:22,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 247/1900 [05:01<33:08,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 248/1900 [05:03<33:06,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 249/1900 [05:04<32:33,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 250/1900 [05:05<32:51,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 251/1900 [05:06<33:25,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 252/1900 [05:07<32:59,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 253/1900 [05:09<33:19,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 254/1900 [05:10<33:07,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 255/1900 [05:11<33:00,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 256/1900 [05:12<32:45,  1.20s/it]
+
+
Evaluating eval...:  14%|█▎        | 257/1900 [05:13<32:25,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 258/1900 [05:15<32:34,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 259/1900 [05:16<32:25,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 260/1900 [05:17<32:36,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 261/1900 [05:18<32:24,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 262/1900 [05:19<32:07,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 263/1900 [05:20<32:14,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 264/1900 [05:22<32:20,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 265/1900 [05:23<32:39,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 266/1900 [05:24<32:31,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 267/1900 [05:25<32:45,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 268/1900 [05:26<32:41,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 269/1900 [05:28<32:28,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 270/1900 [05:29<32:12,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 271/1900 [05:30<31:47,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 272/1900 [05:31<32:02,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 273/1900 [05:32<32:26,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 274/1900 [05:34<32:29,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 275/1900 [05:35<32:25,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 276/1900 [05:36<32:48,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 277/1900 [05:37<32:27,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 278/1900 [05:38<32:12,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 279/1900 [05:40<32:35,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 280/1900 [05:41<32:45,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 281/1900 [05:42<32:44,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 282/1900 [05:43<32:44,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 283/1900 [05:45<32:46,  1.22s/it]
+
+
Evaluating eval...:  15%|█▍        | 284/1900 [05:46<32:36,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 285/1900 [05:47<32:06,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 286/1900 [05:48<32:33,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 287/1900 [05:49<32:21,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 288/1900 [05:52<40:30,  1.51s/it]
+
+
Evaluating eval...:  15%|█▌        | 289/1900 [05:53<38:02,  1.42s/it]
+
+
Evaluating eval...:  15%|█▌        | 290/1900 [05:54<36:02,  1.34s/it]
+
+
Evaluating eval...:  15%|█▌        | 291/1900 [05:55<34:48,  1.30s/it]
+
+
Evaluating eval...:  15%|█▌        | 292/1900 [05:56<34:01,  1.27s/it]
+
+
Evaluating eval...:  15%|█▌        | 293/1900 [05:57<33:05,  1.24s/it]
+
+
Evaluating eval...:  15%|█▌        | 294/1900 [05:59<32:28,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 295/1900 [06:00<32:34,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 296/1900 [06:01<32:42,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 297/1900 [06:02<32:45,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 298/1900 [06:04<32:51,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 299/1900 [06:05<32:12,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 300/1900 [06:06<32:42,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 301/1900 [06:07<32:55,  1.24s/it]
+
+
Evaluating eval...:  16%|█▌        | 302/1900 [06:08<32:39,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 303/1900 [06:10<32:08,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 304/1900 [06:11<31:37,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 305/1900 [06:12<31:28,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 306/1900 [06:13<31:30,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 307/1900 [06:14<31:20,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 308/1900 [06:15<31:15,  1.18s/it]
+
+
Evaluating eval...:  16%|█▋        | 309/1900 [06:17<31:17,  1.18s/it]
+
+
Evaluating eval...:  16%|█▋        | 310/1900 [06:18<31:35,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 311/1900 [06:19<31:54,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 312/1900 [06:20<31:44,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 313/1900 [06:21<31:34,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 314/1900 [06:23<31:27,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 315/1900 [06:24<31:37,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 316/1900 [06:25<31:22,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 317/1900 [06:26<31:39,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 318/1900 [06:27<31:20,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 319/1900 [06:29<31:33,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 320/1900 [06:30<31:34,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 321/1900 [06:31<31:02,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 322/1900 [06:32<31:06,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 323/1900 [06:33<31:17,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 324/1900 [06:34<30:49,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 325/1900 [06:36<30:45,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 326/1900 [06:37<30:41,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 327/1900 [06:38<30:40,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 328/1900 [06:39<31:18,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 329/1900 [06:40<30:49,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 330/1900 [06:42<30:51,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 331/1900 [06:43<36:23,  1.39s/it]
+
+
Evaluating eval...:  17%|█▋        | 332/1900 [06:45<35:02,  1.34s/it]
+
+
Evaluating eval...:  18%|█▊        | 333/1900 [06:46<33:50,  1.30s/it]
+
+
Evaluating eval...:  18%|█▊        | 334/1900 [06:47<32:34,  1.25s/it]
+
+
Evaluating eval...:  18%|█▊        | 335/1900 [06:48<31:40,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 336/1900 [06:49<31:28,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 337/1900 [06:51<31:19,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 338/1900 [06:52<31:42,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 339/1900 [06:53<31:48,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 340/1900 [06:54<31:21,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 341/1900 [06:55<31:36,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 342/1900 [06:57<31:04,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 343/1900 [06:58<30:55,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 344/1900 [06:59<30:58,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 345/1900 [07:00<30:53,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 346/1900 [07:01<30:47,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 347/1900 [07:02<30:42,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 348/1900 [07:04<30:18,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 349/1900 [07:05<30:15,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 350/1900 [07:06<30:15,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 351/1900 [07:07<31:05,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 352/1900 [07:08<31:20,  1.21s/it]
+
+
Evaluating eval...:  19%|█▊        | 353/1900 [07:10<31:26,  1.22s/it]
+
+
Evaluating eval...:  19%|█▊        | 354/1900 [07:11<31:16,  1.21s/it]
+
+
Evaluating eval...:  19%|█▊        | 355/1900 [07:12<31:56,  1.24s/it]
+
+
Evaluating eval...:  19%|█▊        | 356/1900 [07:13<31:49,  1.24s/it]
+
+
Evaluating eval...:  19%|█▉        | 357/1900 [07:15<31:15,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 358/1900 [07:16<31:26,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 359/1900 [07:17<30:55,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 360/1900 [07:18<30:57,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 361/1900 [07:19<30:32,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 362/1900 [07:21<31:18,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 363/1900 [07:22<30:46,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 364/1900 [07:23<30:27,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 365/1900 [07:24<30:29,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 366/1900 [07:25<30:08,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 367/1900 [07:27<31:23,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 368/1900 [07:28<31:57,  1.25s/it]
+
+
Evaluating eval...:  19%|█▉        | 369/1900 [07:29<31:33,  1.24s/it]
+
+
Evaluating eval...:  19%|█▉        | 370/1900 [07:30<31:12,  1.22s/it]
+
+
Evaluating eval...:  20%|█▉        | 371/1900 [07:32<30:49,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 372/1900 [07:33<30:28,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 373/1900 [07:34<30:23,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 374/1900 [07:35<30:14,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 375/1900 [07:36<29:56,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 376/1900 [07:37<30:04,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 377/1900 [07:39<30:42,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 378/1900 [07:40<31:08,  1.23s/it]
+
+
Evaluating eval...:  20%|█▉        | 379/1900 [07:41<30:58,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 380/1900 [07:42<30:54,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 381/1900 [07:44<30:53,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 382/1900 [07:45<31:18,  1.24s/it]
+
+
Evaluating eval...:  20%|██        | 383/1900 [07:46<30:39,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 384/1900 [07:47<30:28,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 385/1900 [07:48<30:14,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 386/1900 [07:50<30:20,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 387/1900 [07:51<30:08,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 388/1900 [07:52<30:06,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 389/1900 [07:53<30:13,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 390/1900 [07:54<30:01,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 391/1900 [07:56<30:09,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 392/1900 [07:57<29:46,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 393/1900 [07:58<29:35,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 394/1900 [07:59<29:37,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 395/1900 [08:00<29:28,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 396/1900 [08:02<30:17,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 397/1900 [08:03<30:32,  1.22s/it]
+
+
Evaluating eval...:  21%|██        | 398/1900 [08:04<30:12,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 399/1900 [08:05<30:30,  1.22s/it]
+
+
Evaluating eval...:  21%|██        | 400/1900 [08:06<30:14,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 401/1900 [08:08<30:18,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 402/1900 [08:09<29:55,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 403/1900 [08:10<30:06,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 404/1900 [08:11<30:20,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 405/1900 [08:13<30:25,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 406/1900 [08:14<30:03,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 407/1900 [08:15<30:03,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 408/1900 [08:16<30:27,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 409/1900 [08:17<30:18,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 410/1900 [08:19<30:22,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 411/1900 [08:20<30:37,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 412/1900 [08:21<29:58,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 413/1900 [08:22<30:09,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 414/1900 [08:23<29:51,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 415/1900 [08:25<29:19,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 416/1900 [08:26<29:01,  1.17s/it]
+
+
Evaluating eval...:  22%|██▏       | 417/1900 [08:27<29:40,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 418/1900 [08:28<29:32,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 419/1900 [08:29<29:19,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 420/1900 [08:31<29:45,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 421/1900 [08:32<29:53,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 422/1900 [08:33<29:45,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 423/1900 [08:34<29:47,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 424/1900 [08:35<29:40,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 425/1900 [08:37<29:30,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 426/1900 [08:38<29:39,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 427/1900 [08:39<29:23,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 428/1900 [08:40<28:59,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 429/1900 [08:41<29:23,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 430/1900 [08:43<28:54,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 431/1900 [08:44<28:51,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 432/1900 [08:45<29:17,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 433/1900 [08:46<29:23,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 434/1900 [08:47<29:57,  1.23s/it]
+
+
Evaluating eval...:  23%|██▎       | 435/1900 [08:49<29:31,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 436/1900 [08:50<29:31,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 437/1900 [08:51<28:56,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 438/1900 [08:52<28:48,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 439/1900 [08:53<29:23,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 440/1900 [08:55<29:02,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 441/1900 [08:56<28:49,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 442/1900 [08:57<28:35,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 443/1900 [08:58<28:49,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 444/1900 [08:59<28:54,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 445/1900 [09:00<29:07,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 446/1900 [09:02<28:59,  1.20s/it]
+
+
Evaluating eval...:  24%|██▎       | 447/1900 [09:03<28:47,  1.19s/it]
+
+
Evaluating eval...:  24%|██▎       | 448/1900 [09:04<28:37,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 449/1900 [09:05<28:37,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 450/1900 [09:06<28:25,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 451/1900 [09:08<28:40,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 452/1900 [09:09<28:22,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 453/1900 [09:10<28:46,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 454/1900 [09:11<29:09,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 455/1900 [09:12<29:17,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 456/1900 [09:14<29:08,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 457/1900 [09:15<29:14,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 458/1900 [09:16<29:03,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 459/1900 [09:17<28:36,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 460/1900 [09:18<28:18,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 461/1900 [09:20<28:42,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 462/1900 [09:21<28:44,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 463/1900 [09:22<28:29,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 464/1900 [09:23<28:35,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 465/1900 [09:24<28:24,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 466/1900 [09:26<28:09,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 467/1900 [09:27<28:05,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 468/1900 [09:28<28:17,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 469/1900 [09:29<28:16,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 470/1900 [09:30<28:19,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 471/1900 [09:31<28:20,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 472/1900 [09:33<29:17,  1.23s/it]
+
+
Evaluating eval...:  25%|██▍       | 473/1900 [09:34<28:40,  1.21s/it]
+
+
Evaluating eval...:  25%|██▍       | 474/1900 [09:35<28:20,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 475/1900 [09:36<28:12,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 476/1900 [09:37<28:05,  1.18s/it]
+
+
Evaluating eval...:  25%|██▌       | 477/1900 [09:39<28:40,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 478/1900 [09:40<28:36,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 479/1900 [09:41<28:50,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 480/1900 [09:42<28:23,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 481/1900 [09:45<35:56,  1.52s/it]
+
+
Evaluating eval...:  25%|██▌       | 482/1900 [09:46<33:15,  1.41s/it]
+
+
Evaluating eval...:  25%|██▌       | 483/1900 [09:47<31:28,  1.33s/it]
+
+
Evaluating eval...:  25%|██▌       | 484/1900 [09:48<31:19,  1.33s/it]
+
+
Evaluating eval...:  26%|██▌       | 485/1900 [09:49<30:10,  1.28s/it]
+
+
Evaluating eval...:  26%|██▌       | 486/1900 [09:51<29:11,  1.24s/it]
+
+
Evaluating eval...:  26%|██▌       | 487/1900 [09:52<28:45,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 488/1900 [09:53<28:54,  1.23s/it]
+
+
Evaluating eval...:  26%|██▌       | 489/1900 [09:54<28:36,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 490/1900 [09:55<28:15,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 491/1900 [09:57<28:29,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 492/1900 [09:58<28:16,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 493/1900 [09:59<28:26,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 494/1900 [10:00<28:07,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 495/1900 [10:01<27:53,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 496/1900 [10:03<28:13,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 497/1900 [10:04<28:29,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 498/1900 [10:05<28:36,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 499/1900 [10:06<28:20,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 500/1900 [10:07<28:08,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 501/1900 [10:09<28:25,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 502/1900 [10:10<28:25,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 503/1900 [10:11<29:03,  1.25s/it]
+
+
Evaluating eval...:  27%|██▋       | 504/1900 [10:12<29:26,  1.27s/it]
+
+
Evaluating eval...:  27%|██▋       | 505/1900 [10:14<29:15,  1.26s/it]
+
+
Evaluating eval...:  27%|██▋       | 506/1900 [10:15<28:38,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 507/1900 [10:16<28:09,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 508/1900 [10:17<28:22,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 509/1900 [10:19<28:50,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 510/1900 [10:20<28:22,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 511/1900 [10:21<28:01,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 512/1900 [10:22<27:41,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 513/1900 [10:23<27:16,  1.18s/it]
+
+
Evaluating eval...:  27%|██▋       | 514/1900 [10:24<27:10,  1.18s/it]
+
+
Evaluating eval...:  27%|██▋       | 515/1900 [10:26<27:49,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 516/1900 [10:27<27:47,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 517/1900 [10:28<27:24,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 518/1900 [10:29<27:53,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 519/1900 [10:31<28:02,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 520/1900 [10:32<27:38,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 521/1900 [10:33<27:54,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 522/1900 [10:34<27:26,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 523/1900 [10:35<27:39,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 524/1900 [10:37<27:36,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 525/1900 [10:38<27:26,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 526/1900 [10:39<27:37,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 527/1900 [10:40<27:52,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 528/1900 [10:41<27:52,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 529/1900 [10:43<28:00,  1.23s/it]
+
+
Evaluating eval...:  28%|██▊       | 530/1900 [10:44<27:33,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 531/1900 [10:45<27:30,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 532/1900 [10:46<27:48,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 533/1900 [10:47<27:25,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 534/1900 [10:49<27:25,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 535/1900 [10:50<27:12,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 536/1900 [10:51<27:07,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 537/1900 [10:52<27:05,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 538/1900 [10:53<27:00,  1.19s/it]
+
+
Evaluating eval...:  28%|██▊       | 539/1900 [10:55<27:10,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 540/1900 [10:56<27:05,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 541/1900 [10:57<26:46,  1.18s/it]
+
+
Evaluating eval...:  29%|██▊       | 542/1900 [10:58<27:29,  1.21s/it]
+
+
Evaluating eval...:  29%|██▊       | 543/1900 [10:59<27:07,  1.20s/it]
+
+
Evaluating eval...:  29%|██▊       | 544/1900 [11:01<26:59,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 545/1900 [11:03<34:33,  1.53s/it]
+
+
Evaluating eval...:  29%|██▊       | 546/1900 [11:04<32:19,  1.43s/it]
+
+
Evaluating eval...:  29%|██▉       | 547/1900 [11:05<31:07,  1.38s/it]
+
+
Evaluating eval...:  29%|██▉       | 548/1900 [11:07<30:05,  1.34s/it]
+
+
Evaluating eval...:  29%|██▉       | 549/1900 [11:08<29:23,  1.31s/it]
+
+
Evaluating eval...:  29%|██▉       | 550/1900 [11:09<29:08,  1.30s/it]
+
+
Evaluating eval...:  29%|██▉       | 551/1900 [11:10<28:41,  1.28s/it]
+
+
Evaluating eval...:  29%|██▉       | 552/1900 [11:12<28:30,  1.27s/it]
+
+
Evaluating eval...:  29%|██▉       | 553/1900 [11:13<27:52,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 554/1900 [11:14<27:15,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 555/1900 [11:15<27:03,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 556/1900 [11:16<27:04,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 557/1900 [11:17<26:41,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 558/1900 [11:19<26:45,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 559/1900 [11:20<26:33,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 560/1900 [11:21<26:48,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 561/1900 [11:22<26:55,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 562/1900 [11:24<26:58,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 563/1900 [11:25<27:09,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 564/1900 [11:26<27:44,  1.25s/it]
+
+
Evaluating eval...:  30%|██▉       | 565/1900 [11:27<27:20,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 566/1900 [11:29<27:26,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 567/1900 [11:30<27:29,  1.24s/it]
+
+
Evaluating eval...:  30%|██▉       | 568/1900 [11:31<27:41,  1.25s/it]
+
+
Evaluating eval...:  30%|██▉       | 569/1900 [11:32<27:29,  1.24s/it]
+
+
Evaluating eval...:  30%|███       | 570/1900 [11:34<28:43,  1.30s/it]
+
+
Evaluating eval...:  30%|███       | 571/1900 [11:35<27:41,  1.25s/it]
+
+
Evaluating eval...:  30%|███       | 572/1900 [11:36<27:25,  1.24s/it]
+
+
Evaluating eval...:  30%|███       | 573/1900 [11:37<26:59,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 574/1900 [11:38<26:40,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 575/1900 [11:40<26:24,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 576/1900 [11:41<26:38,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 577/1900 [11:42<26:57,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 578/1900 [11:43<27:02,  1.23s/it]
+
+
Evaluating eval...:  30%|███       | 579/1900 [11:44<26:56,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 580/1900 [11:46<26:46,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 581/1900 [11:47<26:22,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 582/1900 [11:48<28:42,  1.31s/it]
+
+
Evaluating eval...:  31%|███       | 583/1900 [11:50<27:36,  1.26s/it]
+
+
Evaluating eval...:  31%|███       | 584/1900 [11:51<27:09,  1.24s/it]
+
+
Evaluating eval...:  31%|███       | 585/1900 [11:52<26:40,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 586/1900 [11:53<26:44,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 587/1900 [11:54<26:17,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 588/1900 [11:55<26:02,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 589/1900 [11:57<26:05,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 590/1900 [11:58<26:07,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 591/1900 [11:59<25:58,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 592/1900 [12:00<26:24,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 593/1900 [12:01<26:13,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 594/1900 [12:03<26:30,  1.22s/it]
+
+
Evaluating eval...:  31%|███▏      | 595/1900 [12:04<26:08,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 596/1900 [12:05<26:11,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 597/1900 [12:06<26:24,  1.22s/it]
+
+
Evaluating eval...:  31%|███▏      | 598/1900 [12:08<26:05,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 599/1900 [12:09<26:06,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 600/1900 [12:10<26:04,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 601/1900 [12:11<26:00,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 602/1900 [12:12<25:39,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 603/1900 [12:14<25:54,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 604/1900 [12:15<25:48,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 605/1900 [12:16<25:37,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 606/1900 [12:17<25:48,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 607/1900 [12:18<25:25,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 608/1900 [12:19<25:57,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 609/1900 [12:21<26:03,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 610/1900 [12:22<25:46,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 611/1900 [12:23<25:27,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 612/1900 [12:24<25:43,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 613/1900 [12:25<25:41,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 614/1900 [12:27<26:11,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 615/1900 [12:28<25:57,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 616/1900 [12:29<25:40,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 617/1900 [12:30<25:24,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 618/1900 [12:31<25:09,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 619/1900 [12:33<25:43,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 620/1900 [12:34<25:22,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 621/1900 [12:35<25:30,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 622/1900 [12:36<25:33,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 623/1900 [12:38<25:56,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 624/1900 [12:39<26:15,  1.24s/it]
+
+
Evaluating eval...:  33%|███▎      | 625/1900 [12:40<26:22,  1.24s/it]
+
+
Evaluating eval...:  33%|███▎      | 626/1900 [12:41<25:46,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 627/1900 [12:42<25:26,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 628/1900 [12:44<25:22,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 629/1900 [12:45<25:44,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 630/1900 [12:46<25:36,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 631/1900 [12:47<26:07,  1.23s/it]
+
+
Evaluating eval...:  33%|███▎      | 632/1900 [12:48<25:42,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 633/1900 [12:50<25:14,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 634/1900 [12:51<24:57,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 635/1900 [12:52<24:51,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 636/1900 [12:53<25:01,  1.19s/it]
+
+
Evaluating eval...:  34%|███▎      | 637/1900 [12:54<25:17,  1.20s/it]
+
+
Evaluating eval...:  34%|███▎      | 638/1900 [12:56<25:33,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 639/1900 [12:57<25:35,  1.22s/it]
+
+
Evaluating eval...:  34%|███▎      | 640/1900 [12:58<25:41,  1.22s/it]
+
+
Evaluating eval...:  34%|███▎      | 641/1900 [12:59<25:30,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 642/1900 [13:00<25:20,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 643/1900 [13:02<25:40,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 644/1900 [13:03<25:36,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 645/1900 [13:04<25:36,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 646/1900 [13:05<25:47,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 647/1900 [13:07<25:28,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 648/1900 [13:08<25:09,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 649/1900 [13:09<25:22,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 650/1900 [13:10<25:37,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 651/1900 [13:12<25:33,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 652/1900 [13:13<25:07,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 653/1900 [13:14<24:53,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 654/1900 [13:15<25:34,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 655/1900 [13:16<25:25,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 656/1900 [13:18<25:16,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 657/1900 [13:19<24:54,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 658/1900 [13:20<25:12,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 659/1900 [13:21<25:12,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 660/1900 [13:22<24:44,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 661/1900 [13:24<24:47,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 662/1900 [13:25<25:23,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 663/1900 [13:26<25:35,  1.24s/it]
+
+
Evaluating eval...:  35%|███▍      | 664/1900 [13:27<25:30,  1.24s/it]
+
+
Evaluating eval...:  35%|███▌      | 665/1900 [13:29<25:09,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 666/1900 [13:30<25:00,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 667/1900 [13:31<25:37,  1.25s/it]
+
+
Evaluating eval...:  35%|███▌      | 668/1900 [13:32<25:07,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 669/1900 [13:33<24:48,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 670/1900 [13:35<24:42,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 671/1900 [13:36<24:46,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 672/1900 [13:37<24:35,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 673/1900 [13:38<24:32,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 674/1900 [13:39<24:32,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 675/1900 [13:41<24:21,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 676/1900 [13:42<24:09,  1.18s/it]
+
+
Evaluating eval...:  36%|███▌      | 677/1900 [13:43<24:14,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 678/1900 [13:44<24:32,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 679/1900 [13:45<24:10,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 680/1900 [13:47<24:20,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 681/1900 [13:48<24:51,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 682/1900 [13:49<24:48,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 683/1900 [13:50<24:41,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 684/1900 [13:51<24:21,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 685/1900 [13:53<24:03,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 686/1900 [13:54<24:23,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 687/1900 [13:55<24:26,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 688/1900 [13:56<24:09,  1.20s/it]
+
+
Evaluating eval...:  36%|███▋      | 689/1900 [13:57<24:07,  1.20s/it]
+
+
Evaluating eval...:  36%|███▋      | 690/1900 [13:59<24:29,  1.21s/it]
+
+
Evaluating eval...:  36%|███▋      | 691/1900 [14:00<24:22,  1.21s/it]
+
+
Evaluating eval...:  36%|███▋      | 692/1900 [14:01<23:59,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 693/1900 [14:02<24:06,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 694/1900 [14:03<24:09,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 695/1900 [14:05<24:18,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 696/1900 [14:06<24:24,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 697/1900 [14:07<24:05,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 698/1900 [14:08<24:19,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 699/1900 [14:10<24:34,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 700/1900 [14:11<24:04,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 701/1900 [14:12<23:58,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 702/1900 [14:13<24:05,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 703/1900 [14:14<23:39,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 704/1900 [14:16<24:11,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 705/1900 [14:17<24:02,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 706/1900 [14:18<24:07,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 707/1900 [14:19<23:46,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 708/1900 [14:20<24:06,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 709/1900 [14:22<23:52,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 710/1900 [14:23<23:50,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 711/1900 [14:24<24:27,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 712/1900 [14:25<24:30,  1.24s/it]
+
+
Evaluating eval...:  38%|███▊      | 713/1900 [14:27<25:39,  1.30s/it]
+
+
Evaluating eval...:  38%|███▊      | 714/1900 [14:28<24:47,  1.25s/it]
+
+
Evaluating eval...:  38%|███▊      | 715/1900 [14:29<24:17,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 716/1900 [14:30<23:49,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 717/1900 [14:31<23:39,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 718/1900 [14:33<23:46,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 719/1900 [14:34<23:44,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 720/1900 [14:35<23:38,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 721/1900 [14:36<24:06,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 722/1900 [14:38<24:04,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 723/1900 [14:39<24:08,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 724/1900 [14:40<23:56,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 725/1900 [14:41<23:37,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 726/1900 [14:42<23:28,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 727/1900 [14:44<23:19,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 728/1900 [14:45<24:00,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 729/1900 [14:46<23:38,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 730/1900 [14:47<24:21,  1.25s/it]
+
+
Evaluating eval...:  38%|███▊      | 731/1900 [14:49<24:03,  1.24s/it]
+
+
Evaluating eval...:  39%|███▊      | 732/1900 [14:50<23:43,  1.22s/it]
+
+
Evaluating eval...:  39%|███▊      | 733/1900 [14:51<23:46,  1.22s/it]
+
+
Evaluating eval...:  39%|███▊      | 734/1900 [14:52<23:31,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 735/1900 [14:53<23:16,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 736/1900 [14:55<23:08,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 737/1900 [14:56<22:55,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 738/1900 [14:57<23:09,  1.20s/it]
+
+
Evaluating eval...:  39%|███▉      | 739/1900 [14:58<23:01,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 740/1900 [14:59<22:58,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 741/1900 [15:01<23:34,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 742/1900 [15:02<23:34,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 743/1900 [15:03<23:37,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 744/1900 [15:04<23:18,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 745/1900 [15:05<23:36,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 746/1900 [15:07<23:35,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 747/1900 [15:08<23:50,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 748/1900 [15:09<23:29,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 749/1900 [15:10<23:40,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 750/1900 [15:12<23:24,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 751/1900 [15:13<23:15,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 752/1900 [15:14<23:45,  1.24s/it]
+
+
Evaluating eval...:  40%|███▉      | 753/1900 [15:15<23:39,  1.24s/it]
+
+
Evaluating eval...:  40%|███▉      | 754/1900 [15:16<23:10,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 755/1900 [15:18<22:53,  1.20s/it]
+
+
Evaluating eval...:  40%|███▉      | 756/1900 [15:19<23:15,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 757/1900 [15:20<23:20,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 758/1900 [15:21<23:24,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 759/1900 [15:23<23:19,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 760/1900 [15:24<23:35,  1.24s/it]
+
+
Evaluating eval...:  40%|████      | 761/1900 [15:25<23:21,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 762/1900 [15:26<22:48,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 763/1900 [15:27<22:40,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 764/1900 [15:29<22:29,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 765/1900 [15:30<22:44,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 766/1900 [15:31<22:39,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 767/1900 [15:32<22:58,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 768/1900 [15:34<23:40,  1.25s/it]
+
+
Evaluating eval...:  40%|████      | 769/1900 [15:35<23:34,  1.25s/it]
+
+
Evaluating eval...:  41%|████      | 770/1900 [15:36<23:04,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 771/1900 [15:37<22:59,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 772/1900 [15:38<23:04,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 773/1900 [15:40<22:54,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 774/1900 [15:41<22:31,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 775/1900 [15:42<22:57,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 776/1900 [15:43<23:03,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 777/1900 [15:45<23:03,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 778/1900 [15:46<22:41,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 779/1900 [15:47<22:34,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 780/1900 [15:48<22:56,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 781/1900 [15:49<22:46,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 782/1900 [15:51<23:06,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 783/1900 [15:52<22:59,  1.24s/it]
+
+
Evaluating eval...:  41%|████▏     | 784/1900 [15:53<22:54,  1.23s/it]
+
+
Evaluating eval...:  41%|████▏     | 785/1900 [15:54<22:29,  1.21s/it]
+
+
Evaluating eval...:  41%|████▏     | 786/1900 [15:56<22:19,  1.20s/it]
+
+
Evaluating eval...:  41%|████▏     | 787/1900 [15:57<22:18,  1.20s/it]
+
+
Evaluating eval...:  41%|████▏     | 788/1900 [15:58<22:21,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 789/1900 [15:59<22:23,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 790/1900 [16:00<22:16,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 791/1900 [16:02<22:32,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 792/1900 [16:03<22:37,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 793/1900 [16:04<22:24,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 794/1900 [16:05<22:10,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 795/1900 [16:06<22:07,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 796/1900 [16:08<21:48,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 797/1900 [16:09<21:55,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 798/1900 [16:10<21:48,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 799/1900 [16:11<21:48,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 800/1900 [16:12<22:28,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 801/1900 [16:14<22:15,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 802/1900 [16:15<21:50,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 803/1900 [16:16<22:05,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 804/1900 [16:17<21:49,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 805/1900 [16:18<21:56,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 806/1900 [16:20<21:41,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 807/1900 [16:21<21:31,  1.18s/it]
+
+
Evaluating eval...:  43%|████▎     | 808/1900 [16:22<22:02,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 809/1900 [16:23<22:33,  1.24s/it]
+
+
Evaluating eval...:  43%|████▎     | 810/1900 [16:25<22:19,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 811/1900 [16:26<22:04,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 812/1900 [16:27<22:15,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 813/1900 [16:28<21:48,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 814/1900 [16:29<21:48,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 815/1900 [16:30<21:42,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 816/1900 [16:32<21:44,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 817/1900 [16:33<21:54,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 818/1900 [16:34<22:01,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 819/1900 [16:35<21:55,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 820/1900 [16:37<21:47,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 821/1900 [16:38<21:32,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 822/1900 [16:39<21:34,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 823/1900 [16:40<21:53,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 824/1900 [16:41<21:50,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 825/1900 [16:43<21:35,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 826/1900 [16:44<21:53,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 827/1900 [16:45<21:37,  1.21s/it]
+
+
Evaluating eval...:  44%|████▎     | 828/1900 [16:46<21:35,  1.21s/it]
+
+
Evaluating eval...:  44%|████▎     | 829/1900 [16:47<21:16,  1.19s/it]
+
+
Evaluating eval...:  44%|████▎     | 830/1900 [16:49<21:22,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 831/1900 [16:50<21:04,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 832/1900 [16:51<21:22,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 833/1900 [16:52<21:31,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 834/1900 [16:53<21:14,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 835/1900 [16:55<21:54,  1.23s/it]
+
+
Evaluating eval...:  44%|████▍     | 836/1900 [16:56<21:49,  1.23s/it]
+
+
Evaluating eval...:  44%|████▍     | 837/1900 [16:57<21:41,  1.22s/it]
+
+
Evaluating eval...:  44%|████▍     | 838/1900 [16:58<21:21,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 839/1900 [16:59<21:01,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 840/1900 [17:01<20:58,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 841/1900 [17:02<21:15,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 842/1900 [17:03<21:09,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 843/1900 [17:04<20:59,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 844/1900 [17:05<20:44,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 845/1900 [17:07<20:47,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 846/1900 [17:08<21:08,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 847/1900 [17:09<20:50,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 848/1900 [17:10<20:47,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 849/1900 [17:11<20:44,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 850/1900 [17:13<21:10,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 851/1900 [17:14<20:57,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 852/1900 [17:15<21:23,  1.23s/it]
+
+
Evaluating eval...:  45%|████▍     | 853/1900 [17:16<21:09,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 854/1900 [17:18<21:15,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 855/1900 [17:19<21:05,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 856/1900 [17:20<20:50,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 857/1900 [17:21<20:43,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 858/1900 [17:22<20:53,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 859/1900 [17:23<20:52,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 860/1900 [17:25<20:55,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 861/1900 [17:26<20:56,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 862/1900 [17:27<20:52,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 863/1900 [17:28<20:33,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 864/1900 [17:29<20:31,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 865/1900 [17:31<20:16,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 866/1900 [17:32<20:15,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 867/1900 [17:33<20:28,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 868/1900 [17:34<21:11,  1.23s/it]
+
+
Evaluating eval...:  46%|████▌     | 869/1900 [17:35<20:48,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 870/1900 [17:37<20:45,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 871/1900 [17:38<20:45,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 872/1900 [17:39<20:44,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 873/1900 [17:40<20:33,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 874/1900 [17:42<20:44,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 875/1900 [17:43<20:38,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 876/1900 [17:44<20:26,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 877/1900 [17:45<20:07,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 878/1900 [17:46<20:17,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 879/1900 [17:47<20:15,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 880/1900 [17:49<20:03,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 881/1900 [17:50<19:59,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 882/1900 [17:51<20:01,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 883/1900 [17:52<20:28,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 884/1900 [17:53<20:25,  1.21s/it]
+
+
Evaluating eval...:  47%|███��▋     | 885/1900 [17:55<20:19,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 886/1900 [17:56<20:02,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 887/1900 [17:57<20:05,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 888/1900 [17:58<20:11,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 889/1900 [17:59<20:09,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 890/1900 [18:01<19:57,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 891/1900 [18:02<20:08,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 892/1900 [18:03<20:18,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 893/1900 [18:04<20:23,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 894/1900 [18:05<20:07,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 895/1900 [18:07<20:20,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 896/1900 [18:08<20:08,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 897/1900 [18:09<19:57,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 898/1900 [18:10<20:32,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 899/1900 [18:11<20:05,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 900/1900 [18:13<20:25,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 901/1900 [18:14<20:05,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 902/1900 [18:15<20:08,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 903/1900 [18:16<20:05,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 904/1900 [18:18<20:07,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 905/1900 [18:19<19:57,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 906/1900 [18:20<19:52,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 907/1900 [18:21<20:02,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 908/1900 [18:22<19:52,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 909/1900 [18:24<19:48,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 910/1900 [18:25<19:37,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 911/1900 [18:26<19:51,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 912/1900 [18:27<19:44,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 913/1900 [18:28<19:54,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 914/1900 [18:30<20:01,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 915/1900 [18:31<20:21,  1.24s/it]
+
+
Evaluating eval...:  48%|████▊     | 916/1900 [18:32<20:01,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 917/1900 [18:33<19:45,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 918/1900 [18:35<19:59,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 919/1900 [18:36<20:00,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 920/1900 [18:37<19:43,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 921/1900 [18:38<19:24,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 922/1900 [18:39<19:13,  1.18s/it]
+
+
Evaluating eval...:  49%|████▊     | 923/1900 [18:41<19:51,  1.22s/it]
+
+
Evaluating eval...:  49%|████▊     | 924/1900 [18:42<19:26,  1.20s/it]
+
+
Evaluating eval...:  49%|████▊     | 925/1900 [18:43<19:41,  1.21s/it]
+
+
Evaluating eval...:  49%|████▊     | 926/1900 [18:44<19:26,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 927/1900 [18:45<19:10,  1.18s/it]
+
+
Evaluating eval...:  49%|████▉     | 928/1900 [18:46<19:23,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 929/1900 [18:48<19:07,  1.18s/it]
+
+
Evaluating eval...:  49%|████▉     | 930/1900 [18:49<18:55,  1.17s/it]
+
+
Evaluating eval...:  49%|████▉     | 931/1900 [18:50<19:19,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 932/1900 [18:51<19:48,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 933/1900 [18:53<19:46,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 934/1900 [18:54<19:29,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 935/1900 [18:55<19:35,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 936/1900 [18:56<19:51,  1.24s/it]
+
+
Evaluating eval...:  49%|████▉     | 937/1900 [18:57<19:42,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 938/1900 [18:59<19:30,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 939/1900 [19:00<19:27,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 940/1900 [19:01<19:30,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 941/1900 [19:02<19:33,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 942/1900 [19:04<19:55,  1.25s/it]
+
+
Evaluating eval...:  50%|████▉     | 943/1900 [19:05<19:32,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 944/1900 [19:06<19:19,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 945/1900 [19:07<19:00,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 946/1900 [19:08<19:01,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 947/1900 [19:10<19:14,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 948/1900 [19:11<19:02,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 949/1900 [19:12<19:01,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 950/1900 [19:13<18:53,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 951/1900 [19:14<19:18,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 952/1900 [19:16<19:31,  1.24s/it]
+
+
Evaluating eval...:  50%|█████     | 953/1900 [19:17<19:02,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 954/1900 [19:18<18:52,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 955/1900 [19:19<19:05,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 956/1900 [19:20<18:47,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 957/1900 [19:22<18:38,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 958/1900 [19:23<18:45,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 959/1900 [19:24<18:42,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 960/1900 [19:25<18:44,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 961/1900 [19:26<19:04,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 962/1900 [19:28<18:57,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 963/1900 [19:29<19:05,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 964/1900 [19:30<19:21,  1.24s/it]
+
+
Evaluating eval...:  51%|█████     | 965/1900 [19:31<19:12,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 966/1900 [19:32<18:46,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 967/1900 [19:34<18:31,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 968/1900 [19:35<18:23,  1.18s/it]
+
+
Evaluating eval...:  51%|█████     | 969/1900 [19:36<18:28,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 970/1900 [19:37<18:33,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 971/1900 [19:38<18:26,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 972/1900 [19:40<18:36,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 973/1900 [19:41<18:37,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 974/1900 [19:42<18:21,  1.19s/it]
+
+
Evaluating eval...:  51%|█████▏    | 975/1900 [19:43<18:39,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 976/1900 [19:44<18:41,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 977/1900 [19:46<18:24,  1.20s/it]
+
+
Evaluating eval...:  51%|█████▏    | 978/1900 [19:47<18:36,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 979/1900 [19:48<18:27,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 980/1900 [19:49<18:22,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 981/1900 [19:50<18:08,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 982/1900 [19:52<18:04,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 983/1900 [19:53<18:13,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 984/1900 [19:54<18:17,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 985/1900 [19:55<18:10,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 986/1900 [19:56<18:09,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 987/1900 [19:58<18:10,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 988/1900 [19:59<18:07,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 989/1900 [20:00<18:20,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 990/1900 [20:01<18:46,  1.24s/it]
+
+
Evaluating eval...:  52%|█████▏    | 991/1900 [20:03<18:30,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 992/1900 [20:04<18:18,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 993/1900 [20:05<18:27,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 994/1900 [20:06<18:10,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 995/1900 [20:07<18:26,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 996/1900 [20:09<18:06,  1.20s/it]
+
+
Evaluating eval...:  52%|████���▏    | 997/1900 [20:10<18:01,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 998/1900 [20:11<17:55,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 999/1900 [20:12<17:50,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1000/1900 [20:13<17:46,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1001/1900 [20:14<17:50,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1002/1900 [20:16<17:59,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1003/1900 [20:17<18:17,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1004/1900 [20:18<18:12,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1005/1900 [20:19<17:51,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1006/1900 [20:21<17:56,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1007/1900 [20:22<17:55,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1008/1900 [20:23<17:41,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1009/1900 [20:24<17:39,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1010/1900 [20:25<17:30,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1011/1900 [20:26<17:43,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1012/1900 [20:28<17:57,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1013/1900 [20:29<17:48,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1014/1900 [20:30<18:09,  1.23s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1015/1900 [20:31<17:52,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1016/1900 [20:33<18:09,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1017/1900 [20:34<18:04,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1018/1900 [20:35<18:02,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1019/1900 [20:36<18:38,  1.27s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1020/1900 [20:38<19:03,  1.30s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1021/1900 [20:39<18:39,  1.27s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1022/1900 [20:40<18:30,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1023/1900 [20:42<18:22,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1024/1900 [20:43<18:06,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1025/1900 [20:44<17:44,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1026/1900 [20:45<17:47,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1027/1900 [20:46<17:37,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1028/1900 [20:47<17:26,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1029/1900 [20:49<17:26,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1030/1900 [20:50<17:19,  1.19s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1031/1900 [20:51<17:42,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1032/1900 [20:52<17:32,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1033/1900 [20:53<17:13,  1.19s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1034/1900 [20:55<17:40,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1035/1900 [20:56<17:27,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1036/1900 [20:57<17:29,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1037/1900 [20:59<18:08,  1.26s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1038/1900 [21:00<17:51,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1039/1900 [21:01<17:45,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1040/1900 [21:02<17:36,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1041/1900 [21:03<17:29,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1042/1900 [21:05<17:32,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1043/1900 [21:06<17:20,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1044/1900 [21:07<17:13,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1045/1900 [21:08<16:55,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1046/1900 [21:09<16:51,  1.18s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1047/1900 [21:10<16:41,  1.17s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1048/1900 [21:12<16:40,  1.17s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1049/1900 [21:13<16:42,  1.18s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1050/1900 [21:14<17:07,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1051/1900 [21:15<17:14,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1052/1900 [21:17<17:11,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1053/1900 [21:18<17:09,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1054/1900 [21:19<16:59,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1055/1900 [21:20<16:42,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1056/1900 [21:21<16:59,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1057/1900 [21:23<17:23,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1058/1900 [21:24<17:19,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1059/1900 [21:25<16:53,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1060/1900 [21:26<16:41,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1061/1900 [21:27<16:36,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1062/1900 [21:29<16:33,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1063/1900 [21:30<16:41,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1064/1900 [21:31<17:01,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1065/1900 [21:32<16:59,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1066/1900 [21:33<16:46,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1067/1900 [21:35<16:50,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1068/1900 [21:36<16:39,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1069/1900 [21:37<16:43,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1070/1900 [21:38<16:44,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1071/1900 [21:40<17:00,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1072/1900 [21:41<16:56,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1073/1900 [21:42<16:38,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1074/1900 [21:43<16:33,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1075/1900 [21:44<16:39,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1076/1900 [21:46<16:40,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1077/1900 [21:47<16:39,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1078/1900 [21:48<16:16,  1.19s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1079/1900 [21:49<16:41,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1080/1900 [21:51<20:55,  1.53s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1081/1900 [21:53<19:36,  1.44s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1082/1900 [21:54<18:36,  1.36s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1083/1900 [21:55<18:05,  1.33s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1084/1900 [21:56<17:34,  1.29s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1085/1900 [21:58<17:12,  1.27s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1086/1900 [21:59<17:16,  1.27s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1087/1900 [22:00<17:03,  1.26s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1088/1900 [22:01<16:45,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1089/1900 [22:03<16:47,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1090/1900 [22:04<16:23,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1091/1900 [22:05<16:07,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1092/1900 [22:06<16:25,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1093/1900 [22:07<16:10,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1094/1900 [22:08<16:05,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1095/1900 [22:10<16:04,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1096/1900 [22:11<15:52,  1.18s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1097/1900 [22:12<15:40,  1.17s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1098/1900 [22:13<15:59,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1099/1900 [22:14<16:14,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1100/1900 [22:16<16:08,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1101/1900 [22:17<15:56,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1102/1900 [22:18<15:49,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1103/1900 [22:19<16:06,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1104/1900 [22:20<15:50,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1105/1900 [22:22<16:21,  1.23s/it]
+
+
Evaluating eval...:  58%|███���█▊    | 1106/1900 [22:23<16:22,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1107/1900 [22:24<16:21,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1108/1900 [22:25<16:20,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1109/1900 [22:27<16:13,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1110/1900 [22:28<15:56,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1111/1900 [22:29<16:17,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1112/1900 [22:30<16:06,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1113/1900 [22:32<16:05,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1114/1900 [22:33<16:01,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1115/1900 [22:34<15:53,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1116/1900 [22:35<15:49,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1117/1900 [22:36<15:40,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1118/1900 [22:38<15:32,  1.19s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1119/1900 [22:39<15:47,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1120/1900 [22:40<15:44,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1121/1900 [22:41<15:39,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1122/1900 [22:42<15:25,  1.19s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1123/1900 [22:44<15:43,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1124/1900 [22:45<15:43,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1125/1900 [22:46<15:33,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1126/1900 [22:47<15:31,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1127/1900 [22:48<15:38,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1128/1900 [22:50<15:44,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1129/1900 [22:51<15:28,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1130/1900 [22:52<15:18,  1.19s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1131/1900 [22:53<15:21,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1132/1900 [22:54<15:31,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1133/1900 [22:56<15:33,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1134/1900 [22:57<15:31,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1135/1900 [22:59<19:53,  1.56s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1136/1900 [23:00<18:24,  1.45s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1137/1900 [23:02<17:22,  1.37s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1138/1900 [23:03<16:55,  1.33s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1139/1900 [23:04<16:24,  1.29s/it]
+
+
Evaluating eval...:  60%|██████    | 1140/1900 [23:05<16:14,  1.28s/it]
+
+
Evaluating eval...:  60%|██████    | 1141/1900 [23:07<16:06,  1.27s/it]
+
+
Evaluating eval...:  60%|██████    | 1142/1900 [23:08<15:36,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1143/1900 [23:09<15:19,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1144/1900 [23:10<15:19,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1145/1900 [23:11<15:21,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1146/1900 [23:13<15:22,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1147/1900 [23:14<15:16,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1148/1900 [23:15<15:15,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1149/1900 [23:16<15:01,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1150/1900 [23:17<15:05,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1151/1900 [23:19<14:56,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1152/1900 [23:20<14:49,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1153/1900 [23:21<14:54,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1154/1900 [23:22<14:51,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1155/1900 [23:23<14:49,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1156/1900 [23:24<14:36,  1.18s/it]
+
+
Evaluating eval...:  61%|██████    | 1157/1900 [23:26<14:36,  1.18s/it]
+
+
Evaluating eval...:  61%|██████    | 1158/1900 [23:27<15:14,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1159/1900 [23:28<15:01,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1160/1900 [23:29<15:03,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1161/1900 [23:31<15:06,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1162/1900 [23:32<14:51,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1163/1900 [23:33<14:52,  1.21s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1164/1900 [23:34<14:37,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1165/1900 [23:35<14:35,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1166/1900 [23:37<14:41,  1.20s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1167/1900 [23:38<14:42,  1.20s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1168/1900 [23:39<14:45,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1169/1900 [23:40<14:40,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1170/1900 [23:42<14:48,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1171/1900 [23:43<14:50,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1172/1900 [23:44<14:54,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1173/1900 [23:45<14:45,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1174/1900 [23:46<14:31,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1175/1900 [23:48<15:05,  1.25s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1176/1900 [23:49<15:03,  1.25s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1177/1900 [23:50<14:43,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1178/1900 [23:51<14:30,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1179/1900 [23:52<14:28,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1180/1900 [23:54<14:29,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1181/1900 [23:55<14:14,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1182/1900 [23:56<14:23,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1183/1900 [23:57<14:40,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1184/1900 [23:59<14:43,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1185/1900 [24:00<14:36,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1186/1900 [24:01<14:46,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1187/1900 [24:02<14:32,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1188/1900 [24:03<14:21,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1189/1900 [24:05<14:16,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1190/1900 [24:06<14:04,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1191/1900 [24:07<14:10,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1192/1900 [24:08<14:22,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1193/1900 [24:09<14:14,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1194/1900 [24:11<14:30,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1195/1900 [24:12<14:21,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1196/1900 [24:13<14:11,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1197/1900 [24:14<14:14,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1198/1900 [24:16<14:07,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1199/1900 [24:17<14:21,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1200/1900 [24:18<14:16,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1201/1900 [24:19<14:03,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1202/1900 [24:20<13:53,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1203/1900 [24:22<14:02,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1204/1900 [24:23<14:04,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1205/1900 [24:24<14:02,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1206/1900 [24:25<14:11,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1207/1900 [24:26<14:02,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1208/1900 [24:28<13:54,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1209/1900 [24:29<13:49,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1210/1900 [24:30<14:01,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1211/1900 [24:31<14:03,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1212/1900 [24:33<14:00,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1213/1900 [24:34<13:49,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1214/1900 [24:35<13:43,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1215/1900 [24:36<13:32,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1216/1900 [24:37<13:40,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1217/1900 [24:39<13:53,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1218/1900 [24:40<14:05,  1.24s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1219/1900 [24:41<13:50,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1220/1900 [24:42<13:47,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1221/1900 [24:43<13:41,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1222/1900 [24:45<13:35,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1223/1900 [24:46<13:35,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1224/1900 [24:47<13:30,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1225/1900 [24:48<13:39,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1226/1900 [24:49<13:35,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1227/1900 [24:51<13:31,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1228/1900 [24:52<13:26,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1229/1900 [24:53<13:19,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1230/1900 [24:54<13:26,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1231/1900 [24:55<13:29,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1232/1900 [24:57<13:25,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1233/1900 [24:58<13:22,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1234/1900 [24:59<13:25,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1235/1900 [25:00<13:31,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1236/1900 [25:02<13:16,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1237/1900 [25:03<13:21,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1238/1900 [25:04<13:12,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1239/1900 [25:05<13:15,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1240/1900 [25:06<13:33,  1.23s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1241/1900 [25:08<13:18,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1242/1900 [25:09<13:11,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1243/1900 [25:10<13:29,  1.23s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1244/1900 [25:11<13:15,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1245/1900 [25:12<13:03,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1246/1900 [25:14<13:13,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1247/1900 [25:15<13:06,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1248/1900 [25:16<12:59,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1249/1900 [25:17<13:09,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1250/1900 [25:18<13:06,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1251/1900 [25:20<12:58,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1252/1900 [25:21<12:52,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1253/1900 [25:22<12:52,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1254/1900 [25:23<12:58,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1255/1900 [25:24<13:04,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1256/1900 [25:26<13:02,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1257/1900 [25:27<12:49,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1258/1900 [25:28<13:02,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1259/1900 [25:29<12:53,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1260/1900 [25:31<12:50,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1261/1900 [25:32<12:53,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1262/1900 [25:33<12:43,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1263/1900 [25:34<12:51,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1264/1900 [25:35<12:54,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1265/1900 [25:37<12:56,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1266/1900 [25:38<13:05,  1.24s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1267/1900 [25:39<12:55,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1268/1900 [25:40<12:44,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1269/1900 [25:41<12:45,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1270/1900 [25:43<12:38,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1271/1900 [25:44<12:42,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1272/1900 [25:45<12:35,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1273/1900 [25:46<12:29,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1274/1900 [25:47<12:33,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1275/1900 [25:49<12:29,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1276/1900 [25:50<12:30,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1277/1900 [25:51<12:27,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1278/1900 [25:52<12:18,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1279/1900 [25:53<12:20,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1280/1900 [25:55<12:14,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1281/1900 [25:56<12:06,  1.17s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1282/1900 [25:57<12:01,  1.17s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1283/1900 [25:58<12:04,  1.17s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1284/1900 [25:59<12:06,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1285/1900 [26:00<12:12,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1286/1900 [26:02<12:17,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1287/1900 [26:03<12:45,  1.25s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1288/1900 [26:04<12:35,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1289/1900 [26:05<12:23,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1290/1900 [26:07<12:16,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1291/1900 [26:08<12:11,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1292/1900 [26:09<12:12,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1293/1900 [26:10<12:11,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1294/1900 [26:11<12:17,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1295/1900 [26:13<12:10,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1296/1900 [26:14<12:11,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1297/1900 [26:15<12:00,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1298/1900 [26:16<12:02,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1299/1900 [26:17<12:06,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1300/1900 [26:19<12:11,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1301/1900 [26:20<12:13,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1302/1900 [26:21<12:02,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1303/1900 [26:22<12:03,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1304/1900 [26:24<12:01,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1305/1900 [26:25<11:55,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1306/1900 [26:26<11:56,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1307/1900 [26:27<11:47,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1308/1900 [26:28<11:47,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1309/1900 [26:30<11:46,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1310/1900 [26:31<11:40,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1311/1900 [26:32<11:41,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1312/1900 [26:33<11:40,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1313/1900 [26:34<11:46,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1314/1900 [26:35<11:37,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1315/1900 [26:37<11:37,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1316/1900 [26:38<11:44,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1317/1900 [26:39<11:40,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1318/1900 [26:40<11:49,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1319/1900 [26:42<11:46,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1320/1900 [26:43<11:34,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1321/1900 [26:44<12:02,  1.25s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1322/1900 [26:45<11:50,  1.23s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1323/1900 [26:46<11:44,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1324/1900 [26:48<11:34,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1325/1900 [26:49<11:24,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1326/1900 [26:50<11:24,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1327/1900 [26:51<11:20,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1328/1900 [26:52<11:30,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1329/1900 [26:54<11:21,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1330/1900 [26:55<11:28,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1331/1900 [26:56<11:28,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1332/1900 [26:57<11:25,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1333/1900 [26:58<11:24,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1334/1900 [27:00<11:23,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1335/1900 [27:01<11:17,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1336/1900 [27:02<11:14,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1337/1900 [27:03<11:18,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1338/1900 [27:04<11:15,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1339/1900 [27:06<11:09,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1340/1900 [27:07<11:08,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1341/1900 [27:08<11:00,  1.18s/it]
+
+
Evaluating eval...:  71%|███████   | 1342/1900 [27:09<11:08,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1343/1900 [27:10<11:03,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1344/1900 [27:12<11:05,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1345/1900 [27:13<11:16,  1.22s/it]
+
+
Evaluating eval...:  71%|███████   | 1346/1900 [27:14<11:33,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1347/1900 [27:15<11:19,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1348/1900 [27:17<11:05,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1349/1900 [27:19<14:02,  1.53s/it]
+
+
Evaluating eval...:  71%|███████   | 1350/1900 [27:20<13:09,  1.44s/it]
+
+
Evaluating eval...:  71%|███████   | 1351/1900 [27:21<12:41,  1.39s/it]
+
+
Evaluating eval...:  71%|███████   | 1352/1900 [27:23<12:17,  1.35s/it]
+
+
Evaluating eval...:  71%|███████   | 1353/1900 [27:24<12:03,  1.32s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1354/1900 [27:25<11:44,  1.29s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1355/1900 [27:26<11:28,  1.26s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1356/1900 [27:28<11:29,  1.27s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1357/1900 [27:29<11:19,  1.25s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1358/1900 [27:30<11:07,  1.23s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1359/1900 [27:31<11:05,  1.23s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1360/1900 [27:32<10:59,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1361/1900 [27:34<11:05,  1.24s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1362/1900 [27:35<10:52,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1363/1900 [27:36<11:00,  1.23s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1364/1900 [27:37<10:50,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1365/1900 [27:38<10:43,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1366/1900 [27:40<10:39,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1367/1900 [27:41<10:39,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1368/1900 [27:42<10:47,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1369/1900 [27:43<10:47,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1370/1900 [27:44<10:48,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1371/1900 [27:46<10:44,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1372/1900 [27:47<10:35,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1373/1900 [27:48<10:27,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1374/1900 [27:49<10:23,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1375/1900 [27:50<10:23,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1376/1900 [27:52<10:23,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1377/1900 [27:53<10:22,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1378/1900 [27:54<10:14,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1379/1900 [27:55<10:15,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1380/1900 [27:56<10:19,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1381/1900 [27:58<10:21,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1382/1900 [27:59<10:18,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1383/1900 [28:00<10:21,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1384/1900 [28:01<10:17,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1385/1900 [28:02<10:16,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1386/1900 [28:04<10:19,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1387/1900 [28:05<10:10,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1388/1900 [28:06<10:10,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1389/1900 [28:07<10:03,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1390/1900 [28:08<10:18,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1391/1900 [28:10<10:17,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1392/1900 [28:11<10:13,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1393/1900 [28:12<10:11,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1394/1900 [28:13<10:23,  1.23s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1395/1900 [28:14<10:19,  1.23s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1396/1900 [28:16<10:11,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1397/1900 [28:17<10:05,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1398/1900 [28:18<10:13,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1399/1900 [28:19<10:08,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1400/1900 [28:20<10:00,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1401/1900 [28:22<10:14,  1.23s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1402/1900 [28:23<10:00,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1403/1900 [28:24<09:53,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1404/1900 [28:25<09:50,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1405/1900 [28:26<09:43,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1406/1900 [28:28<09:43,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1407/1900 [28:29<09:48,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1408/1900 [28:30<09:59,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1409/1900 [28:31<09:59,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1410/1900 [28:33<09:54,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1411/1900 [28:34<09:51,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1412/1900 [28:35<09:47,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1413/1900 [28:36<09:44,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1414/1900 [28:37<09:41,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1415/1900 [28:38<09:39,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1416/1900 [28:40<09:33,  1.18s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1417/1900 [28:41<09:41,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1418/1900 [28:42<09:31,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1419/1900 [28:43<09:44,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1420/1900 [28:45<09:40,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1421/1900 [28:46<09:40,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1422/1900 [28:47<09:52,  1.24s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1423/1900 [28:48<09:42,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1424/1900 [28:49<09:40,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1425/1900 [28:51<09:35,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1426/1900 [28:52<09:32,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1427/1900 [28:53<09:31,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1428/1900 [28:54<09:35,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1429/1900 [28:55<09:33,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1430/1900 [28:57<09:29,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1431/1900 [28:58<09:36,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1432/1900 [29:00<12:09,  1.56s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1433/1900 [29:01<11:19,  1.45s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1434/1900 [29:03<10:41,  1.38s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1435/1900 [29:04<10:18,  1.33s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1436/1900 [29:05<10:06,  1.31s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1437/1900 [29:06<09:51,  1.28s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1438/1900 [29:08<09:37,  1.25s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1439/1900 [29:09<09:29,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1440/1900 [29:10<09:29,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1441/1900 [29:11<09:18,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1442/1900 [29:12<09:20,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1443/1900 [29:14<09:25,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1444/1900 [29:15<09:19,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1445/1900 [29:16<09:11,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1446/1900 [29:17<09:08,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1447/1900 [29:18<09:01,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1448/1900 [29:20<08:57,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1449/1900 [29:21<09:03,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1450/1900 [29:22<09:06,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1451/1900 [29:23<09:08,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1452/1900 [29:24<09:00,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1453/1900 [29:26<08:59,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1454/1900 [29:27<09:17,  1.25s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1455/1900 [29:28<09:13,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1456/1900 [29:30<09:16,  1.25s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1457/1900 [29:31<09:10,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1458/1900 [29:32<09:09,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1459/1900 [29:33<09:00,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1460/1900 [29:34<08:51,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1461/1900 [29:36<08:51,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1462/1900 [29:37<08:50,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1463/1900 [29:38<08:46,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1464/1900 [29:39<08:54,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1465/1900 [29:40<08:49,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1466/1900 [29:42<08:55,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1467/1900 [29:43<08:46,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1468/1900 [29:44<08:49,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1469/1900 [29:45<08:53,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1470/1900 [29:47<08:49,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1471/1900 [29:48<08:51,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1472/1900 [29:49<08:40,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1473/1900 [29:50<08:38,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1474/1900 [29:51<08:34,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1475/1900 [29:53<08:36,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1476/1900 [29:54<08:36,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1477/1900 [29:55<08:36,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1478/1900 [29:56<08:34,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1479/1900 [29:58<08:43,  1.24s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1480/1900 [29:59<08:31,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1481/1900 [30:00<08:33,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1482/1900 [30:01<08:27,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1483/1900 [30:02<08:20,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1484/1900 [30:04<08:22,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1485/1900 [30:05<08:24,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1486/1900 [30:06<08:20,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1487/1900 [30:07<08:28,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1488/1900 [30:09<08:17,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1489/1900 [30:10<08:11,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1490/1900 [30:11<08:12,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1491/1900 [30:12<08:07,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1492/1900 [30:13<08:11,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1493/1900 [30:14<08:09,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1494/1900 [30:16<08:06,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1495/1900 [30:17<08:04,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1496/1900 [30:18<07:56,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1497/1900 [30:19<07:53,  1.17s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1498/1900 [30:20<07:57,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1499/1900 [30:22<07:58,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1500/1900 [30:23<07:58,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1501/1900 [30:24<07:51,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1502/1900 [30:25<07:50,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1503/1900 [30:26<07:51,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1504/1900 [30:27<07:46,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1505/1900 [30:29<07:46,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1506/1900 [30:30<07:48,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1507/1900 [30:31<07:48,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1508/1900 [30:32<07:47,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1509/1900 [30:34<07:51,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1510/1900 [30:35<07:47,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1511/1900 [30:36<07:46,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1512/1900 [30:37<07:55,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1513/1900 [30:38<07:53,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1514/1900 [30:40<07:54,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1515/1900 [30:41<07:57,  1.24s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1516/1900 [30:42<07:54,  1.24s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1517/1900 [30:43<07:44,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1518/1900 [30:44<07:36,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1519/1900 [30:46<07:28,  1.18s/it]
+
+
Evaluating eval...:  80%|████████  | 1520/1900 [30:47<07:35,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1521/1900 [30:48<07:46,  1.23s/it]
+
+
Evaluating eval...:  80%|████████  | 1522/1900 [30:49<07:37,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1523/1900 [30:51<07:41,  1.22s/it]
+
+
Evaluating eval...:  80%|████████  | 1524/1900 [30:52<07:41,  1.23s/it]
+
+
Evaluating eval...:  80%|████████  | 1525/1900 [30:53<07:40,  1.23s/it]
+
+
Evaluating eval...:  80%|████████  | 1526/1900 [30:54<07:32,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1527/1900 [30:55<07:30,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1528/1900 [30:57<07:33,  1.22s/it]
+
+
Evaluating eval...:  80%|████████  | 1529/1900 [30:58<07:28,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1530/1900 [30:59<07:35,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1531/1900 [31:00<07:32,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1532/1900 [31:02<07:35,  1.24s/it]
+
+
Evaluating eval...:  81%|████████  | 1533/1900 [31:03<07:26,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1534/1900 [31:04<07:25,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1535/1900 [31:05<07:16,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1536/1900 [31:06<07:11,  1.18s/it]
+
+
Evaluating eval...:  81%|████████  | 1537/1900 [31:07<07:14,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1538/1900 [31:09<07:11,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1539/1900 [31:10<07:18,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1540/1900 [31:11<07:13,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1541/1900 [31:12<07:18,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1542/1900 [31:14<07:12,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1543/1900 [31:15<07:16,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1544/1900 [31:16<07:14,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1545/1900 [31:17<07:08,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1546/1900 [31:18<07:08,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1547/1900 [31:20<07:12,  1.23s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1548/1900 [31:21<07:08,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1549/1900 [31:22<07:00,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1550/1900 [31:23<07:05,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1551/1900 [31:25<07:03,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1552/1900 [31:26<06:55,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1553/1900 [31:27<06:53,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1554/1900 [31:28<06:54,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1555/1900 [31:29<06:54,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1556/1900 [31:31<07:08,  1.25s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1557/1900 [31:32<06:59,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1558/1900 [31:33<07:03,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1559/1900 [31:34<07:04,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1560/1900 [31:35<06:54,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1561/1900 [31:37<07:01,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1562/1900 [31:38<07:05,  1.26s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1563/1900 [31:39<07:04,  1.26s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1564/1900 [31:41<06:54,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1565/1900 [31:42<06:47,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1566/1900 [31:43<06:48,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1567/1900 [31:44<06:43,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1568/1900 [31:46<07:07,  1.29s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1569/1900 [31:47<07:02,  1.28s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1570/1900 [31:48<06:56,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1571/1900 [31:49<06:51,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1572/1900 [31:51<06:49,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1573/1900 [31:52<06:40,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1574/1900 [31:53<06:34,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1575/1900 [31:54<06:34,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1576/1900 [31:55<06:29,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1577/1900 [31:56<06:30,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1578/1900 [31:58<06:31,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1579/1900 [31:59<06:27,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1580/1900 [32:00<06:32,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1581/1900 [32:01<06:37,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1582/1900 [32:03<06:36,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1583/1900 [32:04<06:33,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1584/1900 [32:05<06:39,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1585/1900 [32:07<06:36,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1586/1900 [32:08<06:31,  1.25s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1587/1900 [32:09<06:21,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1588/1900 [32:10<06:15,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1589/1900 [32:11<06:14,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1590/1900 [32:12<06:14,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1591/1900 [32:14<06:19,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1592/1900 [32:15<06:11,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1593/1900 [32:16<06:13,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1594/1900 [32:17<06:18,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1595/1900 [32:19<06:16,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1596/1900 [32:20<06:17,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1597/1900 [32:21<06:15,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1598/1900 [32:22<06:06,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1599/1900 [32:23<05:59,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1600/1900 [32:25<05:56,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1601/1900 [32:26<05:54,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1602/1900 [32:27<05:55,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1603/1900 [32:28<05:54,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1604/1900 [32:29<05:59,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1605/1900 [32:31<05:53,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1606/1900 [32:32<05:53,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1607/1900 [32:33<05:52,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1608/1900 [32:34<05:52,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1609/1900 [32:36<06:00,  1.24s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1610/1900 [32:37<05:55,  1.23s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1611/1900 [32:38<05:47,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1612/1900 [32:39<05:40,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1613/1900 [32:40<05:35,  1.17s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1614/1900 [32:41<05:38,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1615/1900 [32:43<05:37,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1616/1900 [32:44<05:32,  1.17s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1617/1900 [32:45<05:36,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1618/1900 [32:46<05:37,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1619/1900 [32:47<05:40,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1620/1900 [32:49<05:41,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1621/1900 [32:50<05:36,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1622/1900 [32:51<05:29,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1623/1900 [32:52<05:29,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1624/1900 [32:53<05:26,  1.18s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1625/1900 [32:55<05:31,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1626/1900 [32:56<05:33,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1627/1900 [32:57<05:36,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1628/1900 [32:58<05:34,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1629/1900 [33:00<05:31,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1630/1900 [33:01<05:30,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1631/1900 [33:02<05:43,  1.28s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1632/1900 [33:03<05:35,  1.25s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1633/1900 [33:05<05:32,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1634/1900 [33:06<05:26,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1635/1900 [33:07<05:20,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1636/1900 [33:08<05:21,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1637/1900 [33:09<05:27,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1638/1900 [33:11<05:18,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1639/1900 [33:12<05:19,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1640/1900 [33:13<05:20,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1641/1900 [33:14<05:18,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1642/1900 [33:16<05:17,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1643/1900 [33:17<05:16,  1.23s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1644/1900 [33:18<05:08,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1645/1900 [33:19<05:03,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1646/1900 [33:20<05:05,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1647/1900 [33:22<05:03,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1648/1900 [33:23<05:02,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1649/1900 [33:24<04:59,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1650/1900 [33:25<05:02,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1651/1900 [33:26<04:56,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1652/1900 [33:27<04:53,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1653/1900 [33:29<04:51,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1654/1900 [33:30<04:52,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1655/1900 [33:31<04:59,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1656/1900 [33:32<04:58,  1.23s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1657/1900 [33:34<04:56,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1658/1900 [33:35<04:54,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1659/1900 [33:36<05:02,  1.26s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1660/1900 [33:37<04:58,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1661/1900 [33:39<04:59,  1.25s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1662/1900 [33:40<04:52,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1663/1900 [33:41<04:46,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1664/1900 [33:42<04:49,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1665/1900 [33:43<04:48,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1666/1900 [33:46<06:01,  1.55s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1667/1900 [33:47<05:39,  1.46s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1668/1900 [33:48<05:18,  1.37s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1669/1900 [33:49<05:05,  1.32s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1670/1900 [33:51<05:01,  1.31s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1671/1900 [33:52<04:56,  1.29s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1672/1900 [33:53<04:51,  1.28s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1673/1900 [33:55<04:53,  1.29s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1674/1900 [33:56<04:49,  1.28s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1675/1900 [33:57<04:43,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1676/1900 [33:58<04:38,  1.24s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1677/1900 [33:59<04:32,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1678/1900 [34:01<04:27,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1679/1900 [34:02<04:27,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1680/1900 [34:03<04:26,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1681/1900 [34:04<04:32,  1.25s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1682/1900 [34:05<04:26,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1683/1900 [34:07<04:25,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1684/1900 [34:08<04:21,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1685/1900 [34:09<04:18,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1686/1900 [34:10<04:20,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1687/1900 [34:12<04:19,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1688/1900 [34:13<04:19,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1689/1900 [34:14<04:15,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1690/1900 [34:15<04:12,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1691/1900 [34:16<04:13,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1692/1900 [34:18<04:09,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1693/1900 [34:19<04:10,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1694/1900 [34:20<04:11,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1695/1900 [34:21<04:09,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1696/1900 [34:22<04:06,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1697/1900 [34:24<04:07,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1698/1900 [34:25<04:08,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1699/1900 [34:26<04:03,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1700/1900 [34:27<04:03,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1701/1900 [34:29<04:09,  1.25s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1702/1900 [34:30<04:07,  1.25s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1703/1900 [34:31<04:03,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1704/1900 [34:32<03:58,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1705/1900 [34:33<03:54,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1706/1900 [34:35<03:56,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1707/1900 [34:36<03:53,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1708/1900 [34:37<03:55,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1709/1900 [34:38<03:52,  1.22s/it]
+
+
Evaluating eval...:  90%|█████████ | 1710/1900 [34:40<03:50,  1.21s/it]
+
+
Evaluating eval...:  90%|█████████ | 1711/1900 [34:41<03:45,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1712/1900 [34:42<03:43,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1713/1900 [34:43<03:40,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1714/1900 [34:44<03:38,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1715/1900 [34:45<03:40,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1716/1900 [34:47<03:38,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1717/1900 [34:49<04:40,  1.53s/it]
+
+
Evaluating eval...:  90%|█████████ | 1718/1900 [34:50<04:25,  1.46s/it]
+
+
Evaluating eval...:  90%|█████████ | 1719/1900 [34:51<04:09,  1.38s/it]
+
+
Evaluating eval...:  91%|█████████ | 1720/1900 [34:53<04:00,  1.33s/it]
+
+
Evaluating eval...:  91%|█████████ | 1721/1900 [34:54<03:51,  1.29s/it]
+
+
Evaluating eval...:  91%|█████████ | 1722/1900 [34:55<03:46,  1.27s/it]
+
+
Evaluating eval...:  91%|█████████ | 1723/1900 [34:56<03:39,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1724/1900 [34:58<03:40,  1.25s/it]
+
+
Evaluating eval...:  91%|█████████ | 1725/1900 [34:59<03:37,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1726/1900 [35:00<03:37,  1.25s/it]
+
+
Evaluating eval...:  91%|█████████ | 1727/1900 [35:01<03:36,  1.25s/it]
+
+
Evaluating eval...:  91%|█████████ | 1728/1900 [35:02<03:30,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1729/1900 [35:04<03:25,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1730/1900 [35:05<03:26,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1731/1900 [35:06<03:24,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1732/1900 [35:07<03:22,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1733/1900 [35:08<03:23,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1734/1900 [35:10<03:20,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1735/1900 [35:11<03:18,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1736/1900 [35:12<03:33,  1.30s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1737/1900 [35:14<03:25,  1.26s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1738/1900 [35:15<03:19,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1739/1900 [35:16<03:18,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1740/1900 [35:17<03:15,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1741/1900 [35:18<03:13,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1742/1900 [35:19<03:09,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1743/1900 [35:21<03:08,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1744/1900 [35:22<03:06,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1745/1900 [35:23<03:03,  1.18s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1746/1900 [35:24<03:07,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1747/1900 [35:25<03:05,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1748/1900 [35:27<03:03,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1749/1900 [35:28<03:02,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1750/1900 [35:29<03:03,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1751/1900 [35:30<03:01,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1752/1900 [35:32<03:00,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1753/1900 [35:33<02:56,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1754/1900 [35:34<02:54,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1755/1900 [35:35<02:55,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1756/1900 [35:36<02:53,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1757/1900 [35:38<02:55,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1758/1900 [35:39<02:53,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1759/1900 [35:40<02:49,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1760/1900 [35:41<02:46,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1761/1900 [35:42<02:47,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1762/1900 [35:44<02:47,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1763/1900 [35:45<02:44,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1764/1900 [35:46<02:48,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1765/1900 [35:47<02:48,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1766/1900 [35:49<02:46,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1767/1900 [35:50<02:43,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1768/1900 [35:51<02:42,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1769/1900 [35:52<02:41,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1770/1900 [35:54<02:42,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1771/1900 [35:55<02:39,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1772/1900 [35:56<02:37,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1773/1900 [35:57<02:38,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1774/1900 [35:59<02:35,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1775/1900 [36:00<02:36,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1776/1900 [36:01<02:33,  1.24s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1777/1900 [36:02<02:30,  1.23s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1778/1900 [36:03<02:29,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1779/1900 [36:05<02:25,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1780/1900 [36:06<02:23,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1781/1900 [36:07<02:20,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1782/1900 [36:08<02:22,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1783/1900 [36:09<02:22,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1784/1900 [36:11<02:20,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1785/1900 [36:12<02:16,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1786/1900 [36:13<02:14,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1787/1900 [36:14<02:13,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1788/1900 [36:15<02:11,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1789/1900 [36:16<02:09,  1.17s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1790/1900 [36:18<02:10,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1791/1900 [36:19<02:10,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1792/1900 [36:20<02:08,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1793/1900 [36:21<02:09,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1794/1900 [36:22<02:06,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1795/1900 [36:24<02:04,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1796/1900 [36:25<02:03,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1797/1900 [36:26<02:02,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1798/1900 [36:27<02:04,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1799/1900 [36:29<02:03,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1800/1900 [36:30<02:00,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1801/1900 [36:31<01:57,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1802/1900 [36:32<01:57,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1803/1900 [36:33<01:56,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1804/1900 [36:34<01:54,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1805/1900 [36:36<01:53,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1806/1900 [36:37<01:51,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1807/1900 [36:38<01:50,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1808/1900 [36:39<01:49,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1809/1900 [36:40<01:47,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1810/1900 [36:42<01:46,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1811/1900 [36:43<01:47,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1812/1900 [36:44<01:45,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1813/1900 [36:45<01:44,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1814/1900 [36:46<01:43,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1815/1900 [36:48<01:41,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1816/1900 [36:49<01:40,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1817/1900 [36:50<01:43,  1.24s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1818/1900 [36:51<01:40,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1819/1900 [36:53<01:37,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1820/1900 [36:54<01:36,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1821/1900 [36:55<01:35,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1822/1900 [36:56<01:34,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1823/1900 [36:57<01:32,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1824/1900 [36:59<01:30,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1825/1900 [37:00<01:29,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1826/1900 [37:01<01:29,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1827/1900 [37:02<01:29,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1828/1900 [37:03<01:28,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1829/1900 [37:05<01:29,  1.26s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1830/1900 [37:06<01:26,  1.24s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1831/1900 [37:07<01:23,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1832/1900 [37:08<01:21,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1833/1900 [37:09<01:19,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1834/1900 [37:11<01:18,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1835/1900 [37:12<01:17,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1836/1900 [37:13<01:16,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1837/1900 [37:14<01:16,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1838/1900 [37:16<01:17,  1.24s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1839/1900 [37:17<01:14,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1840/1900 [37:18<01:14,  1.24s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1841/1900 [37:19<01:12,  1.23s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1842/1900 [37:21<01:11,  1.23s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1843/1900 [37:22<01:09,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1844/1900 [37:23<01:07,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1845/1900 [37:24<01:05,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1846/1900 [37:25<01:05,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1847/1900 [37:26<01:03,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1848/1900 [37:28<01:02,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1849/1900 [37:29<01:01,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1850/1900 [37:30<00:59,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1851/1900 [37:31<00:59,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1852/1900 [37:32<00:57,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1853/1900 [37:34<00:56,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1854/1900 [37:35<00:54,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1855/1900 [37:36<00:54,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1856/1900 [37:37<00:52,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1857/1900 [37:38<00:51,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1858/1900 [37:40<00:50,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1859/1900 [37:41<00:49,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1860/1900 [37:42<00:48,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1861/1900 [37:43<00:46,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1862/1900 [37:44<00:45,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1863/1900 [37:46<00:44,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1864/1900 [37:47<00:42,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1865/1900 [37:48<00:41,  1.18s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1866/1900 [37:49<00:40,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1867/1900 [37:50<00:40,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1868/1900 [37:52<00:38,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1869/1900 [37:53<00:38,  1.23s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1870/1900 [37:54<00:36,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1871/1900 [37:55<00:35,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1872/1900 [37:57<00:34,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1873/1900 [37:58<00:33,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1874/1900 [37:59<00:31,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1875/1900 [38:00<00:30,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1876/1900 [38:02<00:29,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1877/1900 [38:03<00:27,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1878/1900 [38:04<00:26,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1879/1900 [38:05<00:25,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1880/1900 [38:06<00:23,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1881/1900 [38:07<00:22,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1882/1900 [38:09<00:21,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1883/1900 [38:10<00:21,  1.26s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1884/1900 [38:11<00:20,  1.28s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1885/1900 [38:13<00:18,  1.25s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1886/1900 [38:14<00:17,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1887/1900 [38:15<00:15,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1888/1900 [38:16<00:14,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1889/1900 [38:17<00:13,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1890/1900 [38:18<00:11,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1891/1900 [38:20<00:10,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1892/1900 [38:21<00:09,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1893/1900 [38:22<00:08,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1894/1900 [38:23<00:07,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1895/1900 [38:24<00:05,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1896/1900 [38:26<00:04,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1897/1900 [38:27<00:03,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1898/1900 [38:28<00:02,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1899/1900 [38:29<00:01,  1.19s/it]
+
+
Evaluating eval...: 100%|██████████| 1900/1900 [38:31<00:00,  1.31s/it]
Evaluating eval...: 100%|██████████| 1900/1900 [38:31<00:00,  1.22s/it]
+Eval results for step (20000 / 100000 | Eval Loss: 1.1917551755905151 | Eval wer: 30.284494602288703 | Eval wer_ortho: 33.84397528321318 |)
+
                                                                             
Eval results for step (20000 / 100000 | Eval Loss: 1.1917551755905151 | Eval wer: 30.284494602288703 | Eval wer_ortho: 33.84397528321318 |)
+
Train steps ... :  20%|██        | 20000/100000 [6:10:25<12:58:39,  1.71it/s]
Train steps ... :  20%|██        | 20001/100000 [6:10:26<16911:29:00, 761.03s/it]
Train steps ... :  20%|██        | 20002/100000 [6:10:26<11841:46:38, 532.89s/it]
Train steps ... :  20%|██        | 20003/100000 [6:10:27<8293:02:16, 373.20s/it] 
Train steps ... :  20%|██        | 20004/100000 [6:10:27<5808:56:21, 261.42s/it]
Train steps ... :  20%|██        | 20005/100000 [6:10:28<4070:06:00, 183.17s/it]
Train steps ... :  20%|██        | 20006/100000 [6:10:28<2852:55:22, 128.39s/it]
Train steps ... :  20%|██        | 20007/100000 [6:10:29<2000:55:26, 90.05s/it] 
Train steps ... :  20%|██        | 20008/100000 [6:10:30<1404:31:22, 63.21s/it]
Train steps ... :  20%|██        | 20009/100000 [6:10:30<987:03:21, 44.42s/it] 
Train steps ... :  20%|██        | 20010/100000 [6:10:31<694:49:37, 31.27s/it]
Train steps ... :  20%|██        | 20011/100000 [6:10:31<490:16:07, 22.07s/it]
Train steps ... :  20%|██        | 20012/100000 [6:10:32<347:04:13, 15.62s/it]
Train steps ... :  20%|██        | 20013/100000 [6:10:33<246:50:27, 11.11s/it]
Train steps ... :  20%|██        | 20014/100000 [6:10:33<176:42:06,  7.95s/it]
Train steps ... :  20%|██        | 20015/100000 [6:10:34<127:35:06,  5.74s/it]
Train steps ... :  20%|██        | 20016/100000 [6:10:34<93:11:38,  4.19s/it] 
Train steps ... :  20%|██        | 20017/100000 [6:10:35<69:07:35,  3.11s/it]
Train steps ... :  20%|██        | 20018/100000 [6:10:35<52:16:41,  2.35s/it]
Train steps ... :  20%|██        | 20019/100000 [6:10:36<40:29:28,  1.82s/it]
Train steps ... :  20%|██        | 20020/100000 [6:10:37<32:13:36,  1.45s/it]
Train steps ... :  20%|██        | 20021/100000 [6:10:37<26:26:55,  1.19s/it]
Train steps ... :  20%|██        | 20022/100000 [6:10:38<22:24:44,  1.01s/it]
Train steps ... :  20%|██        | 20023/100000 [6:10:38<19:34:52,  1.13it/s]
Train steps ... :  20%|██        | 20024/100000 [6:10:39<17:36:28,  1.26it/s]
Train steps ... :  20%|██        | 20025/100000 [6:10:40<16:12:40,  1.37it/s]Step... (20025 / 100000 | Loss: 0.9392538070678711, Learning Rate: 8.037688442211056e-05)
+
                                                                             
Step... (20025 / 100000 | Loss: 1.0178732872009277, Learning Rate: 8.037688442211056e-05)
+
Train steps ... :  20%|██        | 20025/100000 [6:10:40<16:12:40,  1.37it/s]
Train steps ... :  20%|██        | 20026/100000 [6:10:40<15:15:36,  1.46it/s]
Train steps ... :  20%|██        | 20027/100000 [6:10:41<14:34:17,  1.52it/s]
Train steps ... :  20%|██        | 20028/100000 [6:10:41<14:05:06,  1.58it/s]
Train steps ... :  20%|██        | 20029/100000 [6:10:42<13:45:39,  1.61it/s]
Train steps ... :  20%|██        | 20030/100000 [6:10:43<13:30:56,  1.64it/s]
Train steps ... :  20%|██        | 20031/100000 [6:10:43<13:20:32,  1.66it/s]
Train steps ... :  20%|██        | 20032/100000 [6:10:44<13:14:56,  1.68it/s]
Train steps ... :  20%|██        | 20033/100000 [6:10:44<13:09:54,  1.69it/s]
Train steps ... :  20%|██        | 20034/100000 [6:10:45<13:06:50,  1.69it/s]
Train steps ... :  20%|██        | 20035/100000 [6:10:45<13:04:11,  1.70it/s]
Train steps ... :  20%|██        | 20036/100000 [6:10:46<13:02:29,  1.70it/s]
Train steps ... :  20%|██        | 20037/100000 [6:10:47<13:01:41,  1.70it/s]
Train steps ... :  20%|██        | 20038/100000 [6:10:47<13:00:48,  1.71it/s]
Train steps ... :  20%|██        | 20039/100000 [6:10:48<13:00:21,  1.71it/s]
Train steps ... :  20%|██        | 20040/100000 [6:10:48<13:01:37,  1.71it/s]
Train steps ... :  20%|██        | 20041/100000 [6:10:49<13:03:33,  1.70it/s]
Train steps ... :  20%|██        | 20042/100000 [6:10:50<13:02:13,  1.70it/s]
Train steps ... :  20%|██        | 20043/100000 [6:10:50<13:00:33,  1.71it/s]
Train steps ... :  20%|██        | 20044/100000 [6:10:51<13:04:06,  1.70it/s]
Train steps ... :  20%|██        | 20045/100000 [6:10:51<13:01:24,  1.71it/s]
Train steps ... :  20%|██        | 20046/100000 [6:10:52<13:00:25,  1.71it/s]
Train steps ... :  20%|██        | 20047/100000 [6:10:52<12:59:46,  1.71it/s]
Train steps ... :  20%|██        | 20048/100000 [6:10:53<12:58:55,  1.71it/s]
Train steps ... :  20%|██        | 20049/100000 [6:10:54<12:59:04,  1.71it/s]
Train steps ... :  20%|██        | 20050/100000 [6:10:54<12:59:39,  1.71it/s]Step... (20050 / 100000 | Loss: 0.9382392764091492, Learning Rate: 8.035175879396985e-05)
+
                                                                             
Step... (20050 / 100000 | Loss: 1.0192642211914062, Learning Rate: 8.035175879396985e-05)
+
Train steps ... :  20%|██        | 20050/100000 [6:10:55<12:59:39,  1.71it/s]
Train steps ... :  20%|██        | 20051/100000 [6:10:55<13:00:01,  1.71it/s]
Train steps ... :  20%|██        | 20052/100000 [6:10:55<13:00:09,  1.71it/s]
Train steps ... :  20%|██        | 20053/100000 [6:10:56<12:59:55,  1.71it/s]
Train steps ... :  20%|██        | 20054/100000 [6:10:57<12:58:56,  1.71it/s]
Train steps ... :  20%|██        | 20055/100000 [6:10:57<12:58:15,  1.71it/s]
Train steps ... :  20%|██        | 20056/100000 [6:10:58<12:58:36,  1.71it/s]
Train steps ... :  20%|██        | 20057/100000 [6:10:58<12:58:09,  1.71it/s]
Train steps ... :  20%|██        | 20058/100000 [6:10:59<12:58:15,  1.71it/s]
Train steps ... :  20%|██        | 20059/100000 [6:10:59<12:58:20,  1.71it/s]
Train steps ... :  20%|██        | 20060/100000 [6:11:00<12:57:56,  1.71it/s]
Train steps ... :  20%|██        | 20061/100000 [6:11:01<12:59:32,  1.71it/s]
Train steps ... :  20%|██        | 20062/100000 [6:11:01<12:59:23,  1.71it/s]
Train steps ... :  20%|██        | 20063/100000 [6:11:02<12:59:19,  1.71it/s]
Train steps ... :  20%|██        | 20064/100000 [6:11:02<12:58:31,  1.71it/s]
Train steps ... :  20%|██        | 20065/100000 [6:11:03<12:57:59,  1.71it/s]
Train steps ... :  20%|██        | 20066/100000 [6:11:04<12:57:50,  1.71it/s]
Train steps ... :  20%|██        | 20067/100000 [6:11:04<12:58:49,  1.71it/s]
Train steps ... :  20%|██        | 20068/100000 [6:11:05<12:57:57,  1.71it/s]
Train steps ... :  20%|██        | 20069/100000 [6:11:05<12:57:53,  1.71it/s]
Train steps ... :  20%|██        | 20070/100000 [6:11:06<12:57:53,  1.71it/s]
Train steps ... :  20%|██        | 20071/100000 [6:11:06<12:57:41,  1.71it/s]
Train steps ... :  20%|██        | 20072/100000 [6:11:07<12:58:03,  1.71it/s]
Train steps ... :  20%|██        | 20073/100000 [6:11:08<12:58:39,  1.71it/s]
Train steps ... :  20%|██        | 20074/100000 [6:11:08<12:57:51,  1.71it/s]
Train steps ... :  20%|██        | 20075/100000 [6:11:09<12:58:52,  1.71it/s]Step... (20075 / 100000 | Loss: 1.1327205896377563, Learning Rate: 8.032663316582915e-05)
+
                                                                             
Step... (20075 / 100000 | Loss: 0.9030886888504028, Learning Rate: 8.032663316582915e-05)
+
Train steps ... :  20%|██        | 20075/100000 [6:11:09<12:58:52,  1.71it/s]
Train steps ... :  20%|██        | 20076/100000 [6:11:09<12:58:58,  1.71it/s]
Train steps ... :  20%|██        | 20077/100000 [6:11:10<12:58:58,  1.71it/s]
Train steps ... :  20%|██        | 20078/100000 [6:11:11<12:58:10,  1.71it/s]
Train steps ... :  20%|██        | 20079/100000 [6:11:11<12:57:35,  1.71it/s]
Train steps ... :  20%|██        | 20080/100000 [6:11:12<12:57:11,  1.71it/s]
Train steps ... :  20%|██        | 20081/100000 [6:11:12<12:57:27,  1.71it/s]
Train steps ... :  20%|██        | 20082/100000 [6:11:13<12:56:56,  1.71it/s]
Train steps ... :  20%|██        | 20083/100000 [6:11:13<12:57:14,  1.71it/s]
Train steps ... :  20%|██        | 20084/100000 [6:11:14<12:58:01,  1.71it/s]
Train steps ... :  20%|██        | 20085/100000 [6:11:15<12:57:33,  1.71it/s]
Train steps ... :  20%|██        | 20086/100000 [6:11:15<12:58:00,  1.71it/s]
Train steps ... :  20%|██        | 20087/100000 [6:11:16<12:58:48,  1.71it/s]
Train steps ... :  20%|██        | 20088/100000 [6:11:16<12:57:50,  1.71it/s]
Train steps ... :  20%|██        | 20089/100000 [6:11:17<12:57:18,  1.71it/s]
Train steps ... :  20%|██        | 20090/100000 [6:11:18<12:56:59,  1.71it/s]
Train steps ... :  20%|██        | 20091/100000 [6:11:18<12:57:56,  1.71it/s]
Train steps ... :  20%|██        | 20092/100000 [6:11:19<12:57:51,  1.71it/s]
Train steps ... :  20%|██        | 20093/100000 [6:11:19<12:57:29,  1.71it/s]
Train steps ... :  20%|██        | 20094/100000 [6:11:20<12:58:12,  1.71it/s]
Train steps ... :  20%|██        | 20095/100000 [6:11:21<12:57:48,  1.71it/s]
Train steps ... :  20%|██        | 20096/100000 [6:11:21<12:58:47,  1.71it/s]
Train steps ... :  20%|██        | 20097/100000 [6:11:22<12:58:39,  1.71it/s]
Train steps ... :  20%|██        | 20098/100000 [6:11:22<12:57:49,  1.71it/s]
Train steps ... :  20%|██        | 20099/100000 [6:11:23<12:57:49,  1.71it/s]
Train steps ... :  20%|██        | 20100/100000 [6:11:23<12:57:36,  1.71it/s]Step... (20100 / 100000 | Loss: 0.7651605606079102, Learning Rate: 8.030150753768845e-05)
+
                                                                             
Step... (20100 / 100000 | Loss: 0.8361247777938843, Learning Rate: 8.030150753768845e-05)
+
Train steps ... :  20%|██        | 20100/100000 [6:11:24<12:57:36,  1.71it/s]
Train steps ... :  20%|██        | 20101/100000 [6:11:24<12:57:55,  1.71it/s]
Train steps ... :  20%|██        | 20102/100000 [6:11:25<12:57:55,  1.71it/s]
Train steps ... :  20%|██        | 20103/100000 [6:11:25<12:58:04,  1.71it/s]
Train steps ... :  20%|██        | 20104/100000 [6:11:26<12:58:10,  1.71it/s]
Train steps ... :  20%|██        | 20105/100000 [6:11:26<12:58:23,  1.71it/s]
Train steps ... :  20%|██        | 20106/100000 [6:11:27<12:59:05,  1.71it/s]
Train steps ... :  20%|██        | 20107/100000 [6:11:28<13:00:09,  1.71it/s]
Train steps ... :  20%|██        | 20108/100000 [6:11:28<12:59:07,  1.71it/s]
Train steps ... :  20%|██        | 20109/100000 [6:11:29<12:58:23,  1.71it/s]
Train steps ... :  20%|██        | 20110/100000 [6:11:29<12:58:26,  1.71it/s]
Train steps ... :  20%|██        | 20111/100000 [6:11:30<12:58:19,  1.71it/s]
Train steps ... :  20%|██        | 20112/100000 [6:11:30<12:58:46,  1.71it/s]
Train steps ... :  20%|██        | 20113/100000 [6:11:31<12:58:00,  1.71it/s]
Train steps ... :  20%|██        | 20114/100000 [6:11:32<12:57:19,  1.71it/s]
Train steps ... :  20%|██        | 20115/100000 [6:11:32<12:56:49,  1.71it/s]
Train steps ... :  20%|██        | 20116/100000 [6:11:33<12:56:44,  1.71it/s]
Train steps ... :  20%|██        | 20117/100000 [6:11:33<12:57:30,  1.71it/s]
Train steps ... :  20%|██        | 20118/100000 [6:11:34<12:57:40,  1.71it/s]
Train steps ... :  20%|██        | 20119/100000 [6:11:35<12:57:23,  1.71it/s]
Train steps ... :  20%|██        | 20120/100000 [6:11:35<12:57:43,  1.71it/s]
Train steps ... :  20%|██        | 20121/100000 [6:11:36<12:58:16,  1.71it/s]
Train steps ... :  20%|██        | 20122/100000 [6:11:36<12:58:08,  1.71it/s]
Train steps ... :  20%|██        | 20123/100000 [6:11:37<12:57:50,  1.71it/s]
Train steps ... :  20%|██        | 20124/100000 [6:11:37<12:57:37,  1.71it/s]
Train steps ... :  20%|██        | 20125/100000 [6:11:38<12:57:36,  1.71it/s]Step... (20125 / 100000 | Loss: 0.9640218019485474, Learning Rate: 8.027638190954774e-05)
+
                                                                             
Step... (20125 / 100000 | Loss: 0.8395093679428101, Learning Rate: 8.027638190954774e-05)
+
Train steps ... :  20%|██        | 20125/100000 [6:11:38<12:57:36,  1.71it/s]
Train steps ... :  20%|██        | 20126/100000 [6:11:39<12:57:10,  1.71it/s]
Train steps ... :  20%|██        | 20127/100000 [6:11:39<12:57:07,  1.71it/s]
Train steps ... :  20%|██        | 20128/100000 [6:11:40<12:58:06,  1.71it/s]
Train steps ... :  20%|██        | 20129/100000 [6:11:40<12:57:33,  1.71it/s]
Train steps ... :  20%|██        | 20130/100000 [6:11:41<12:57:11,  1.71it/s]
Train steps ... :  20%|██        | 20131/100000 [6:11:42<12:57:23,  1.71it/s]
Train steps ... :  20%|██        | 20132/100000 [6:11:42<12:56:46,  1.71it/s]
Train steps ... :  20%|██        | 20133/100000 [6:11:43<12:56:48,  1.71it/s]
Train steps ... :  20%|██        | 20134/100000 [6:11:43<12:56:10,  1.71it/s]
Train steps ... :  20%|██        | 20135/100000 [6:11:44<12:55:53,  1.72it/s]
Train steps ... :  20%|██        | 20136/100000 [6:11:44<12:56:42,  1.71it/s]
Train steps ... :  20%|██        | 20137/100000 [6:11:45<12:56:20,  1.71it/s]
Train steps ... :  20%|██        | 20138/100000 [6:11:46<12:56:07,  1.71it/s]
Train steps ... :  20%|██        | 20139/100000 [6:11:46<12:56:15,  1.71it/s]
Train steps ... :  20%|██        | 20140/100000 [6:11:47<12:56:07,  1.71it/s]
Train steps ... :  20%|██        | 20141/100000 [6:11:47<12:56:05,  1.71it/s]
Train steps ... :  20%|██        | 20142/100000 [6:11:48<12:56:11,  1.71it/s]
Train steps ... :  20%|██        | 20143/100000 [6:11:49<12:56:29,  1.71it/s]
Train steps ... :  20%|██        | 20144/100000 [6:11:49<12:57:19,  1.71it/s]
Train steps ... :  20%|██        | 20145/100000 [6:11:50<12:56:58,  1.71it/s]
Train steps ... :  20%|██        | 20146/100000 [6:11:50<12:57:09,  1.71it/s]
Train steps ... :  20%|██        | 20147/100000 [6:11:51<12:58:12,  1.71it/s]
Train steps ... :  20%|██        | 20148/100000 [6:11:51<12:57:09,  1.71it/s]
Train steps ... :  20%|██        | 20149/100000 [6:11:52<12:57:25,  1.71it/s]
Train steps ... :  20%|██        | 20150/100000 [6:11:53<12:56:54,  1.71it/s]Step... (20150 / 100000 | Loss: 1.1868577003479004, Learning Rate: 8.025125628140704e-05)
+
                                                                             
Step... (20150 / 100000 | Loss: 0.9069689512252808, Learning Rate: 8.025125628140704e-05)
+
Train steps ... :  20%|██        | 20150/100000 [6:11:53<12:56:54,  1.71it/s]
Train steps ... :  20%|██        | 20151/100000 [6:11:53<12:57:26,  1.71it/s]
Train steps ... :  20%|██        | 20152/100000 [6:11:54<12:57:58,  1.71it/s]
Train steps ... :  20%|██        | 20153/100000 [6:11:54<12:57:26,  1.71it/s]
Train steps ... :  20%|██        | 20154/100000 [6:11:55<12:56:54,  1.71it/s]
Train steps ... :  20%|██        | 20155/100000 [6:11:56<12:57:36,  1.71it/s]
Train steps ... :  20%|██        | 20156/100000 [6:11:56<12:57:20,  1.71it/s]
Train steps ... :  20%|██        | 20157/100000 [6:11:57<12:58:18,  1.71it/s]
Train steps ... :  20%|██        | 20158/100000 [6:11:57<12:58:56,  1.71it/s]
Train steps ... :  20%|██        | 20159/100000 [6:11:58<12:57:50,  1.71it/s]
Train steps ... :  20%|██        | 20160/100000 [6:11:58<12:57:18,  1.71it/s]
Train steps ... :  20%|██        | 20161/100000 [6:11:59<12:57:10,  1.71it/s]
Train steps ... :  20%|██        | 20162/100000 [6:12:00<12:56:21,  1.71it/s]
Train steps ... :  20%|██        | 20163/100000 [6:12:00<12:57:22,  1.71it/s]
Train steps ... :  20%|██        | 20164/100000 [6:12:01<12:57:14,  1.71it/s]
Train steps ... :  20%|██        | 20165/100000 [6:12:01<12:57:37,  1.71it/s]
Train steps ... :  20%|██        | 20166/100000 [6:12:02<12:57:31,  1.71it/s]
Train steps ... :  20%|██        | 20167/100000 [6:12:03<12:57:47,  1.71it/s]
Train steps ... :  20%|██        | 20168/100000 [6:12:03<12:58:14,  1.71it/s]
Train steps ... :  20%|██        | 20169/100000 [6:12:04<12:57:54,  1.71it/s]
Train steps ... :  20%|██        | 20170/100000 [6:12:04<12:57:45,  1.71it/s]
Train steps ... :  20%|██        | 20171/100000 [6:12:05<12:57:50,  1.71it/s]
Train steps ... :  20%|██        | 20172/100000 [6:12:05<12:57:29,  1.71it/s]
Train steps ... :  20%|██        | 20173/100000 [6:12:06<12:56:19,  1.71it/s]
Train steps ... :  20%|██        | 20174/100000 [6:12:07<12:58:23,  1.71it/s]
Train steps ... :  20%|██        | 20175/100000 [6:12:07<12:56:45,  1.71it/s]Step... (20175 / 100000 | Loss: 0.7861303091049194, Learning Rate: 8.022613065326634e-05)
+
                                                                             
Step... (20175 / 100000 | Loss: 0.7190425395965576, Learning Rate: 8.022613065326634e-05)
+
Train steps ... :  20%|██        | 20175/100000 [6:12:08<12:56:45,  1.71it/s]
Train steps ... :  20%|██        | 20176/100000 [6:12:08<12:56:53,  1.71it/s]
Train steps ... :  20%|██        | 20177/100000 [6:12:08<12:56:41,  1.71it/s]
Train steps ... :  20%|██        | 20178/100000 [6:12:09<12:56:26,  1.71it/s]
Train steps ... :  20%|██        | 20179/100000 [6:12:10<12:57:25,  1.71it/s]
Train steps ... :  20%|██        | 20180/100000 [6:12:10<12:57:48,  1.71it/s]
Train steps ... :  20%|██        | 20181/100000 [6:12:11<12:58:03,  1.71it/s]
Train steps ... :  20%|██        | 20182/100000 [6:12:11<12:58:17,  1.71it/s]
Train steps ... :  20%|██        | 20183/100000 [6:12:12<12:56:47,  1.71it/s]
Train steps ... :  20%|██        | 20184/100000 [6:12:12<12:56:44,  1.71it/s]
Train steps ... :  20%|██        | 20185/100000 [6:12:13<12:56:58,  1.71it/s]
Train steps ... :  20%|██        | 20186/100000 [6:12:14<12:56:17,  1.71it/s]
Train steps ... :  20%|██        | 20187/100000 [6:12:14<12:56:13,  1.71it/s]
Train steps ... :  20%|██        | 20188/100000 [6:12:15<12:56:02,  1.71it/s]
Train steps ... :  20%|██        | 20189/100000 [6:12:15<12:55:48,  1.71it/s]
Train steps ... :  20%|██        | 20190/100000 [6:12:16<12:55:50,  1.71it/s]
Train steps ... :  20%|██        | 20191/100000 [6:12:17<12:55:50,  1.71it/s]
Train steps ... :  20%|██        | 20192/100000 [6:12:17<12:55:33,  1.72it/s]
Train steps ... :  20%|██        | 20193/100000 [6:12:18<12:56:29,  1.71it/s]
Train steps ... :  20%|██        | 20194/100000 [6:12:18<12:57:21,  1.71it/s]
Train steps ... :  20%|██        | 20195/100000 [6:12:19<12:57:54,  1.71it/s]
Train steps ... :  20%|██        | 20196/100000 [6:12:19<12:58:29,  1.71it/s]
Train steps ... :  20%|██        | 20197/100000 [6:12:20<12:58:20,  1.71it/s]
Train steps ... :  20%|██        | 20198/100000 [6:12:21<12:57:00,  1.71it/s]
Train steps ... :  20%|██        | 20199/100000 [6:12:21<12:56:41,  1.71it/s]
Train steps ... :  20%|██        | 20200/100000 [6:12:22<12:57:41,  1.71it/s]Step... (20200 / 100000 | Loss: 0.8251011371612549, Learning Rate: 8.020100502512563e-05)
+
                                                                             
Step... (20200 / 100000 | Loss: 0.9064726829528809, Learning Rate: 8.020100502512563e-05)
+
Train steps ... :  20%|██        | 20200/100000 [6:12:22<12:57:41,  1.71it/s]
Train steps ... :  20%|██        | 20201/100000 [6:12:22<12:56:30,  1.71it/s]
Train steps ... :  20%|██        | 20202/100000 [6:12:23<12:56:54,  1.71it/s]
Train steps ... :  20%|██        | 20203/100000 [6:12:24<12:55:46,  1.71it/s]
Train steps ... :  20%|██        | 20204/100000 [6:12:24<12:55:31,  1.71it/s]
Train steps ... :  20%|██        | 20205/100000 [6:12:25<12:55:30,  1.71it/s]
Train steps ... :  20%|██        | 20206/100000 [6:12:25<12:55:39,  1.71it/s]
Train steps ... :  20%|██        | 20207/100000 [6:12:26<12:56:31,  1.71it/s]
Train steps ... :  20%|██        | 20208/100000 [6:12:27<12:56:32,  1.71it/s]
Train steps ... :  20%|██        | 20209/100000 [6:12:27<12:56:35,  1.71it/s]
Train steps ... :  20%|██        | 20210/100000 [6:12:28<12:58:47,  1.71it/s]
Train steps ... :  20%|██        | 20211/100000 [6:12:28<12:57:13,  1.71it/s]
Train steps ... :  20%|██        | 20212/100000 [6:12:29<12:56:57,  1.71it/s]
Train steps ... :  20%|██        | 20213/100000 [6:12:29<12:56:21,  1.71it/s]
Train steps ... :  20%|██        | 20214/100000 [6:12:30<12:56:21,  1.71it/s]
Train steps ... :  20%|██        | 20215/100000 [6:12:31<12:55:43,  1.71it/s]
Train steps ... :  20%|██        | 20216/100000 [6:12:31<12:56:46,  1.71it/s]
Train steps ... :  20%|██        | 20217/100000 [6:12:32<12:58:28,  1.71it/s]
Train steps ... :  20%|██        | 20218/100000 [6:12:32<12:57:22,  1.71it/s]
Train steps ... :  20%|██        | 20219/100000 [6:12:33<12:58:36,  1.71it/s]
Train steps ... :  20%|██        | 20220/100000 [6:12:34<12:57:53,  1.71it/s]
Train steps ... :  20%|██        | 20221/100000 [6:12:34<12:58:32,  1.71it/s]
Train steps ... :  20%|██        | 20222/100000 [6:12:35<12:58:32,  1.71it/s]
Train steps ... :  20%|██        | 20223/100000 [6:12:35<12:58:34,  1.71it/s]
Train steps ... :  20%|██        | 20224/100000 [6:12:36<12:57:26,  1.71it/s]
Train steps ... :  20%|██        | 20225/100000 [6:12:36<12:56:22,  1.71it/s]Step... (20225 / 100000 | Loss: 0.8603885173797607, Learning Rate: 8.017587939698493e-05)
+
                                                                             
Step... (20225 / 100000 | Loss: 0.831610918045044, Learning Rate: 8.017587939698493e-05)
+
Train steps ... :  20%|██        | 20225/100000 [6:12:37<12:56:22,  1.71it/s]
Train steps ... :  20%|██        | 20226/100000 [6:12:37<12:57:27,  1.71it/s]
Train steps ... :  20%|██        | 20227/100000 [6:12:38<12:57:17,  1.71it/s]
Train steps ... :  20%|██        | 20228/100000 [6:12:38<12:56:36,  1.71it/s]
Train steps ... :  20%|██        | 20229/100000 [6:12:39<12:57:10,  1.71it/s]
Train steps ... :  20%|██        | 20230/100000 [6:12:39<12:56:24,  1.71it/s]
Train steps ... :  20%|██        | 20231/100000 [6:12:40<12:56:20,  1.71it/s]
Train steps ... :  20%|██        | 20232/100000 [6:12:41<12:56:23,  1.71it/s]
Train steps ... :  20%|██        | 20233/100000 [6:12:41<12:57:58,  1.71it/s]
Train steps ... :  20%|██        | 20234/100000 [6:12:42<12:56:45,  1.71it/s]
Train steps ... :  20%|██        | 20235/100000 [6:12:42<12:56:24,  1.71it/s]
Train steps ... :  20%|██        | 20236/100000 [6:12:43<12:56:03,  1.71it/s]
Train steps ... :  20%|██        | 20237/100000 [6:12:43<12:56:03,  1.71it/s]
Train steps ... :  20%|██        | 20238/100000 [6:12:44<12:56:06,  1.71it/s]
Train steps ... :  20%|██        | 20239/100000 [6:12:45<12:56:34,  1.71it/s]
Train steps ... :  20%|██        | 20240/100000 [6:12:45<12:56:24,  1.71it/s]
Train steps ... :  20%|██        | 20241/100000 [6:12:46<12:56:14,  1.71it/s]
Train steps ... :  20%|██        | 20242/100000 [6:12:46<12:56:24,  1.71it/s]
Train steps ... :  20%|██        | 20243/100000 [6:12:47<12:56:21,  1.71it/s]
Train steps ... :  20%|██        | 20244/100000 [6:12:48<12:56:22,  1.71it/s]
Train steps ... :  20%|██        | 20245/100000 [6:12:48<12:55:40,  1.71it/s]
Train steps ... :  20%|██        | 20246/100000 [6:12:49<12:56:42,  1.71it/s]
Train steps ... :  20%|██        | 20247/100000 [6:12:49<12:56:10,  1.71it/s]
Train steps ... :  20%|██        | 20248/100000 [6:12:50<12:56:35,  1.71it/s]
Train steps ... :  20%|██        | 20249/100000 [6:12:50<12:56:58,  1.71it/s]
Train steps ... :  20%|██        | 20250/100000 [6:12:51<12:56:03,  1.71it/s]Step... (20250 / 100000 | Loss: 1.3526242971420288, Learning Rate: 8.015075376884423e-05)
+
                                                                             
Step... (20250 / 100000 | Loss: 0.8739932775497437, Learning Rate: 8.015075376884423e-05)
+
Train steps ... :  20%|██        | 20250/100000 [6:12:51<12:56:03,  1.71it/s]
Train steps ... :  20%|██        | 20251/100000 [6:12:52<12:55:46,  1.71it/s]
Train steps ... :  20%|██        | 20252/100000 [6:12:52<12:55:54,  1.71it/s]
Train steps ... :  20%|██        | 20253/100000 [6:12:53<12:55:46,  1.71it/s]
Train steps ... :  20%|██        | 20254/100000 [6:12:53<12:55:27,  1.71it/s]
Train steps ... :  20%|██        | 20255/100000 [6:12:54<12:56:31,  1.71it/s]
Train steps ... :  20%|██        | 20256/100000 [6:12:55<12:56:28,  1.71it/s]
Train steps ... :  20%|██        | 20257/100000 [6:12:55<12:56:01,  1.71it/s]
Train steps ... :  20%|██        | 20258/100000 [6:12:56<12:55:35,  1.71it/s]
Train steps ... :  20%|██        | 20259/100000 [6:12:56<12:54:56,  1.71it/s]
Train steps ... :  20%|██        | 20260/100000 [6:12:57<12:55:02,  1.71it/s]
Train steps ... :  20%|██        | 20261/100000 [6:12:57<12:54:54,  1.72it/s]
Train steps ... :  20%|██        | 20262/100000 [6:12:58<12:54:51,  1.72it/s]
Train steps ... :  20%|██        | 20263/100000 [6:12:59<12:54:53,  1.72it/s]
Train steps ... :  20%|██        | 20264/100000 [6:12:59<12:55:12,  1.71it/s]
Train steps ... :  20%|██        | 20265/100000 [6:13:00<12:54:48,  1.72it/s]
Train steps ... :  20%|██        | 20266/100000 [6:13:00<12:55:25,  1.71it/s]
Train steps ... :  20%|██        | 20267/100000 [6:13:01<12:55:39,  1.71it/s]
Train steps ... :  20%|██        | 20268/100000 [6:13:02<12:55:21,  1.71it/s]
Train steps ... :  20%|██        | 20269/100000 [6:13:02<12:55:40,  1.71it/s]
Train steps ... :  20%|██        | 20270/100000 [6:13:03<12:55:35,  1.71it/s]
Train steps ... :  20%|██        | 20271/100000 [6:13:03<12:55:56,  1.71it/s]
Train steps ... :  20%|██        | 20272/100000 [6:13:04<12:55:50,  1.71it/s]
Train steps ... :  20%|██        | 20273/100000 [6:13:04<12:56:23,  1.71it/s]
Train steps ... :  20%|██        | 20274/100000 [6:13:05<12:57:14,  1.71it/s]
Train steps ... :  20%|██        | 20275/100000 [6:13:06<12:56:23,  1.71it/s]Step... (20275 / 100000 | Loss: 1.2142908573150635, Learning Rate: 8.012562814070352e-05)
+
                                                                             
Step... (20275 / 100000 | Loss: 1.1463093757629395, Learning Rate: 8.012562814070352e-05)
+
Train steps ... :  20%|██        | 20275/100000 [6:13:06<12:56:23,  1.71it/s]
Train steps ... :  20%|██        | 20276/100000 [6:13:06<12:56:45,  1.71it/s]
Train steps ... :  20%|██        | 20277/100000 [6:13:07<12:55:58,  1.71it/s]
Train steps ... :  20%|██        | 20278/100000 [6:13:07<12:55:37,  1.71it/s]
Train steps ... :  20%|██        | 20279/100000 [6:13:08<12:55:18,  1.71it/s]
Train steps ... :  20%|██        | 20280/100000 [6:13:09<12:56:00,  1.71it/s]
Train steps ... :  20%|██        | 20281/100000 [6:13:09<12:55:59,  1.71it/s]
Train steps ... :  20%|██        | 20282/100000 [6:13:10<12:56:58,  1.71it/s]
Train steps ... :  20%|██        | 20283/100000 [6:13:10<12:56:42,  1.71it/s]
Train steps ... :  20%|██        | 20284/100000 [6:13:11<12:56:43,  1.71it/s]
Train steps ... :  20%|██        | 20285/100000 [6:13:11<12:57:02,  1.71it/s]
Train steps ... :  20%|██        | 20286/100000 [6:13:12<12:56:51,  1.71it/s]
Train steps ... :  20%|██        | 20287/100000 [6:13:13<12:56:37,  1.71it/s]
Train steps ... :  20%|██        | 20288/100000 [6:13:13<12:56:50,  1.71it/s]
Train steps ... :  20%|██        | 20289/100000 [6:13:14<12:56:44,  1.71it/s]
Train steps ... :  20%|██        | 20290/100000 [6:13:14<12:57:10,  1.71it/s]
Train steps ... :  20%|██        | 20291/100000 [6:13:15<12:56:26,  1.71it/s]
Train steps ... :  20%|██        | 20292/100000 [6:13:16<12:55:39,  1.71it/s]
Train steps ... :  20%|██        | 20293/100000 [6:13:16<12:55:36,  1.71it/s]
Train steps ... :  20%|██        | 20294/100000 [6:13:17<12:55:32,  1.71it/s]
Train steps ... :  20%|██        | 20295/100000 [6:13:17<12:55:07,  1.71it/s]
Train steps ... :  20%|██        | 20296/100000 [6:13:18<12:57:09,  1.71it/s]
Train steps ... :  20%|██        | 20297/100000 [6:13:18<12:56:41,  1.71it/s]
Train steps ... :  20%|██        | 20298/100000 [6:13:19<12:55:38,  1.71it/s]
Train steps ... :  20%|██        | 20299/100000 [6:13:20<12:56:14,  1.71it/s]
Train steps ... :  20%|██        | 20300/100000 [6:13:20<12:56:00,  1.71it/s]Step... (20300 / 100000 | Loss: 1.1000878810882568, Learning Rate: 8.010050251256282e-05)
+
                                                                             
Step... (20300 / 100000 | Loss: 1.1347030401229858, Learning Rate: 8.010050251256282e-05)
+
Train steps ... :  20%|██        | 20300/100000 [6:13:21<12:56:00,  1.71it/s]
Train steps ... :  20%|██        | 20301/100000 [6:13:21<12:56:26,  1.71it/s]
Train steps ... :  20%|██        | 20302/100000 [6:13:21<12:55:35,  1.71it/s]
Train steps ... :  20%|██        | 20303/100000 [6:13:22<12:55:21,  1.71it/s]
Train steps ... :  20%|██        | 20304/100000 [6:13:23<12:55:29,  1.71it/s]
Train steps ... :  20%|██        | 20305/100000 [6:13:23<12:55:07,  1.71it/s]
Train steps ... :  20%|██        | 20306/100000 [6:13:24<12:55:32,  1.71it/s]
Train steps ... :  20%|██        | 20307/100000 [6:13:24<12:55:08,  1.71it/s]
Train steps ... :  20%|██        | 20308/100000 [6:13:25<12:54:39,  1.71it/s]
Train steps ... :  20%|██        | 20309/100000 [6:13:25<12:54:37,  1.71it/s]
Train steps ... :  20%|██        | 20310/100000 [6:13:26<12:55:05,  1.71it/s]
Train steps ... :  20%|██        | 20311/100000 [6:13:27<12:54:33,  1.71it/s]
Train steps ... :  20%|██        | 20312/100000 [6:13:27<12:54:59,  1.71it/s]
Train steps ... :  20%|██        | 20313/100000 [6:13:28<12:55:13,  1.71it/s]
Train steps ... :  20%|██        | 20314/100000 [6:13:28<12:54:53,  1.71it/s]
Train steps ... :  20%|██        | 20315/100000 [6:13:29<12:54:56,  1.71it/s]
Train steps ... :  20%|██        | 20316/100000 [6:13:30<12:55:12,  1.71it/s]
Train steps ... :  20%|██        | 20317/100000 [6:13:30<12:55:31,  1.71it/s]
Train steps ... :  20%|██        | 20318/100000 [6:13:31<12:55:18,  1.71it/s]
Train steps ... :  20%|██        | 20319/100000 [6:13:31<12:56:03,  1.71it/s]
Train steps ... :  20%|██        | 20320/100000 [6:13:32<12:55:53,  1.71it/s]
Train steps ... :  20%|██        | 20321/100000 [6:13:33<12:55:10,  1.71it/s]
Train steps ... :  20%|██        | 20322/100000 [6:13:33<12:55:10,  1.71it/s]
Train steps ... :  20%|██        | 20323/100000 [6:13:34<12:54:37,  1.71it/s]
Train steps ... :  20%|██        | 20324/100000 [6:13:34<12:54:21,  1.71it/s]
Train steps ... :  20%|██        | 20325/100000 [6:13:35<12:54:10,  1.72it/s]Step... (20325 / 100000 | Loss: 0.8512105345726013, Learning Rate: 8.007537688442212e-05)
+
                                                                             
Step... (20325 / 100000 | Loss: 0.785808801651001, Learning Rate: 8.007537688442212e-05)
+
Train steps ... :  20%|██        | 20325/100000 [6:13:35<12:54:10,  1.72it/s]
Train steps ... :  20%|██        | 20326/100000 [6:13:35<12:55:04,  1.71it/s]
Train steps ... :  20%|██        | 20327/100000 [6:13:36<12:54:59,  1.71it/s]
Train steps ... :  20%|██        | 20328/100000 [6:13:37<12:55:32,  1.71it/s]
Train steps ... :  20%|██        | 20329/100000 [6:13:37<12:55:04,  1.71it/s]
Train steps ... :  20%|██        | 20330/100000 [6:13:38<12:56:08,  1.71it/s]
Train steps ... :  20%|██        | 20331/100000 [6:13:38<12:55:23,  1.71it/s]
Train steps ... :  20%|██        | 20332/100000 [6:13:39<12:55:27,  1.71it/s]
Train steps ... :  20%|██        | 20333/100000 [6:13:40<12:54:44,  1.71it/s]
Train steps ... :  20%|██        | 20334/100000 [6:13:40<12:55:03,  1.71it/s]
Train steps ... :  20%|██        | 20335/100000 [6:13:41<12:54:52,  1.71it/s]
Train steps ... :  20%|██        | 20336/100000 [6:13:41<12:54:46,  1.71it/s]
Train steps ... :  20%|██        | 20337/100000 [6:13:42<12:54:05,  1.72it/s]
Train steps ... :  20%|██        | 20338/100000 [6:13:42<12:55:06,  1.71it/s]
Train steps ... :  20%|██        | 20339/100000 [6:13:43<12:54:38,  1.71it/s]
Train steps ... :  20%|██        | 20340/100000 [6:13:44<12:54:22,  1.71it/s]
Train steps ... :  20%|██        | 20341/100000 [6:13:44<12:54:02,  1.72it/s]
Train steps ... :  20%|██        | 20342/100000 [6:13:45<12:55:02,  1.71it/s]
Train steps ... :  20%|██        | 20343/100000 [6:13:45<12:54:48,  1.71it/s]
Train steps ... :  20%|██        | 20344/100000 [6:13:46<12:54:51,  1.71it/s]
Train steps ... :  20%|██        | 20345/100000 [6:13:47<12:55:31,  1.71it/s]
Train steps ... :  20%|██        | 20346/100000 [6:13:47<12:55:20,  1.71it/s]
Train steps ... :  20%|██        | 20347/100000 [6:13:48<12:55:46,  1.71it/s]
Train steps ... :  20%|██        | 20348/100000 [6:13:48<12:55:49,  1.71it/s]
Train steps ... :  20%|██        | 20349/100000 [6:13:49<12:55:24,  1.71it/s]
Train steps ... :  20%|██        | 20350/100000 [6:13:49<12:55:24,  1.71it/s]Step... (20350 / 100000 | Loss: 1.3406540155410767, Learning Rate: 8.00502512562814e-05)
+
                                                                             
Step... (20350 / 100000 | Loss: 0.7724142074584961, Learning Rate: 8.00502512562814e-05)
+
Train steps ... :  20%|██        | 20350/100000 [6:13:50<12:55:24,  1.71it/s]
Train steps ... :  20%|██        | 20351/100000 [6:13:50<12:55:45,  1.71it/s]
Train steps ... :  20%|██        | 20352/100000 [6:13:51<12:55:41,  1.71it/s]
Train steps ... :  20%|██        | 20353/100000 [6:13:51<12:55:17,  1.71it/s]
Train steps ... :  20%|██        | 20354/100000 [6:13:52<12:55:25,  1.71it/s]
Train steps ... :  20%|██        | 20355/100000 [6:13:52<12:56:08,  1.71it/s]
Train steps ... :  20%|██        | 20356/100000 [6:13:53<12:55:38,  1.71it/s]
Train steps ... :  20%|██        | 20357/100000 [6:13:54<12:55:25,  1.71it/s]
Train steps ... :  20%|██        | 20358/100000 [6:13:54<12:56:15,  1.71it/s]
Train steps ... :  20%|██        | 20359/100000 [6:13:55<12:56:49,  1.71it/s]
Train steps ... :  20%|██        | 20360/100000 [6:13:55<12:56:19,  1.71it/s]
Train steps ... :  20%|██        | 20361/100000 [6:13:56<12:56:12,  1.71it/s]
Train steps ... :  20%|██        | 20362/100000 [6:13:56<12:55:40,  1.71it/s]
Train steps ... :  20%|██        | 20363/100000 [6:13:57<12:56:00,  1.71it/s]
Train steps ... :  20%|██        | 20364/100000 [6:13:58<12:55:39,  1.71it/s]
Train steps ... :  20%|██        | 20365/100000 [6:13:58<12:55:28,  1.71it/s]
Train steps ... :  20%|██        | 20366/100000 [6:13:59<12:55:19,  1.71it/s]
Train steps ... :  20%|██        | 20367/100000 [6:13:59<12:54:56,  1.71it/s]
Train steps ... :  20%|██        | 20368/100000 [6:14:00<12:55:15,  1.71it/s]
Train steps ... :  20%|██        | 20369/100000 [6:14:01<12:55:05,  1.71it/s]
Train steps ... :  20%|██        | 20370/100000 [6:14:01<12:54:28,  1.71it/s]
Train steps ... :  20%|██        | 20371/100000 [6:14:02<12:54:19,  1.71it/s]
Train steps ... :  20%|██        | 20372/100000 [6:14:02<12:53:45,  1.72it/s]
Train steps ... :  20%|██        | 20373/100000 [6:14:03<12:53:52,  1.71it/s]
Train steps ... :  20%|██        | 20374/100000 [6:14:03<12:53:43,  1.72it/s]
Train steps ... :  20%|██        | 20375/100000 [6:14:04<12:53:53,  1.71it/s]Step... (20375 / 100000 | Loss: 0.8579944968223572, Learning Rate: 8.002512562814071e-05)
+
                                                                             
Step... (20375 / 100000 | Loss: 1.1056649684906006, Learning Rate: 8.002512562814071e-05)
+
Train steps ... :  20%|██        | 20375/100000 [6:14:04<12:53:53,  1.71it/s]
Train steps ... :  20%|██        | 20376/100000 [6:14:05<12:54:22,  1.71it/s]
Train steps ... :  20%|██        | 20377/100000 [6:14:05<12:54:28,  1.71it/s]
Train steps ... :  20%|██        | 20378/100000 [6:14:06<12:54:29,  1.71it/s]
Train steps ... :  20%|██        | 20379/100000 [6:14:06<12:54:44,  1.71it/s]
Train steps ... :  20%|██        | 20380/100000 [6:14:07<12:54:20,  1.71it/s]
Train steps ... :  20%|██        | 20381/100000 [6:14:08<12:54:36,  1.71it/s]
Train steps ... :  20%|██        | 20382/100000 [6:14:08<12:54:12,  1.71it/s]
Train steps ... :  20%|██        | 20383/100000 [6:14:09<12:54:21,  1.71it/s]
Train steps ... :  20%|██        | 20384/100000 [6:14:09<12:54:47,  1.71it/s]
Train steps ... :  20%|██        | 20385/100000 [6:14:10<12:54:34,  1.71it/s]
Train steps ... :  20%|██        | 20386/100000 [6:14:10<12:54:46,  1.71it/s]
Train steps ... :  20%|██        | 20387/100000 [6:14:11<12:55:28,  1.71it/s]
Train steps ... :  20%|██        | 20388/100000 [6:14:12<12:55:22,  1.71it/s]
Train steps ... :  20%|██        | 20389/100000 [6:14:12<12:54:56,  1.71it/s]
Train steps ... :  20%|██        | 20390/100000 [6:14:13<12:54:56,  1.71it/s]
Train steps ... :  20%|██        | 20391/100000 [6:14:13<12:54:11,  1.71it/s]
Train steps ... :  20%|██        | 20392/100000 [6:14:14<12:54:45,  1.71it/s]
Train steps ... :  20%|██        | 20393/100000 [6:14:15<12:54:41,  1.71it/s]
Train steps ... :  20%|██        | 20394/100000 [6:14:15<12:54:38,  1.71it/s]
Train steps ... :  20%|██        | 20395/100000 [6:14:16<12:55:09,  1.71it/s]
Train steps ... :  20%|██        | 20396/100000 [6:14:16<12:54:50,  1.71it/s]
Train steps ... :  20%|██        | 20397/100000 [6:14:17<12:54:32,  1.71it/s]
Train steps ... :  20%|██        | 20398/100000 [6:14:17<12:54:08,  1.71it/s]
Train steps ... :  20%|██        | 20399/100000 [6:14:18<12:54:13,  1.71it/s]
Train steps ... :  20%|██        | 20400/100000 [6:14:19<12:54:15,  1.71it/s]Step... (20400 / 100000 | Loss: 0.8392719030380249, Learning Rate: 8e-05)
+
                                                                             
Step... (20400 / 100000 | Loss: 0.9933385848999023, Learning Rate: 8e-05)
+
Train steps ... :  20%|██        | 20400/100000 [6:14:19<12:54:15,  1.71it/s]
Train steps ... :  20%|██        | 20401/100000 [6:14:19<12:54:24,  1.71it/s]
Train steps ... :  20%|██        | 20402/100000 [6:14:20<12:54:07,  1.71it/s]
Train steps ... :  20%|██        | 20403/100000 [6:14:20<12:54:09,  1.71it/s]
Train steps ... :  20%|██        | 20404/100000 [6:14:21<12:54:35,  1.71it/s]
Train steps ... :  20%|██        | 20405/100000 [6:14:22<12:54:17,  1.71it/s]
Train steps ... :  20%|██        | 20406/100000 [6:14:22<12:53:49,  1.71it/s]
Train steps ... :  20%|██        | 20407/100000 [6:14:23<12:53:57,  1.71it/s]
Train steps ... :  20%|██        | 20408/100000 [6:14:23<12:54:39,  1.71it/s]
Train steps ... :  20%|██        | 20409/100000 [6:14:24<12:53:55,  1.71it/s]
Train steps ... :  20%|██        | 20410/100000 [6:14:24<12:54:53,  1.71it/s]
Train steps ... :  20%|██        | 20411/100000 [6:14:25<12:55:35,  1.71it/s]
Train steps ... :  20%|██        | 20412/100000 [6:14:26<12:54:46,  1.71it/s]
Train steps ... :  20%|██        | 20413/100000 [6:14:26<12:54:42,  1.71it/s]
Train steps ... :  20%|██        | 20414/100000 [6:14:27<12:54:07,  1.71it/s]
Train steps ... :  20%|██        | 20415/100000 [6:14:27<12:54:22,  1.71it/s]
Train steps ... :  20%|██        | 20416/100000 [6:14:28<12:53:35,  1.71it/s]
Train steps ... :  20%|██        | 20417/100000 [6:14:29<12:53:45,  1.71it/s]
Train steps ... :  20%|██        | 20418/100000 [6:14:29<12:54:19,  1.71it/s]
Train steps ... :  20%|██        | 20419/100000 [6:14:30<12:54:39,  1.71it/s]
Train steps ... :  20%|██        | 20420/100000 [6:14:30<12:54:27,  1.71it/s]
Train steps ... :  20%|██        | 20421/100000 [6:14:31<12:54:18,  1.71it/s]
Train steps ... :  20%|██        | 20422/100000 [6:14:31<12:53:46,  1.71it/s]
Train steps ... :  20%|██        | 20423/100000 [6:14:32<12:53:39,  1.71it/s]
Train steps ... :  20%|██        | 20424/100000 [6:14:33<12:55:00,  1.71it/s]
Train steps ... :  20%|██        | 20425/100000 [6:14:33<12:54:50,  1.71it/s]Step... (20425 / 100000 | Loss: 0.8556100130081177, Learning Rate: 7.99748743718593e-05)
+
                                                                             
Step... (20425 / 100000 | Loss: 1.0319206714630127, Learning Rate: 7.99748743718593e-05)
+
Train steps ... :  20%|██        | 20425/100000 [6:14:34<12:54:50,  1.71it/s]
Train steps ... :  20%|██        | 20426/100000 [6:14:34<12:54:43,  1.71it/s]
Train steps ... :  20%|██        | 20427/100000 [6:14:34<12:54:08,  1.71it/s]
Train steps ... :  20%|██        | 20428/100000 [6:14:35<12:54:30,  1.71it/s]
Train steps ... :  20%|██        | 20429/100000 [6:14:36<12:55:11,  1.71it/s]
Train steps ... :  20%|██        | 20430/100000 [6:14:36<12:54:19,  1.71it/s]
Train steps ... :  20%|██        | 20431/100000 [6:14:37<12:54:01,  1.71it/s]
Train steps ... :  20%|██        | 20432/100000 [6:14:37<12:53:37,  1.71it/s]
Train steps ... :  20%|██        | 20433/100000 [6:14:38<12:53:43,  1.71it/s]
Train steps ... :  20%|██        | 20434/100000 [6:14:38<12:54:06,  1.71it/s]
Train steps ... :  20%|██        | 20435/100000 [6:14:39<12:54:00,  1.71it/s]
Train steps ... :  20%|██        | 20436/100000 [6:14:40<12:53:35,  1.71it/s]
Train steps ... :  20%|██        | 20437/100000 [6:14:40<12:54:22,  1.71it/s]
Train steps ... :  20%|██        | 20438/100000 [6:14:41<12:53:58,  1.71it/s]
Train steps ... :  20%|██        | 20439/100000 [6:14:41<12:54:26,  1.71it/s]
Train steps ... :  20%|██        | 20440/100000 [6:14:42<12:54:02,  1.71it/s]
Train steps ... :  20%|██        | 20441/100000 [6:14:43<12:53:41,  1.71it/s]
Train steps ... :  20%|██        | 20442/100000 [6:14:43<12:53:11,  1.71it/s]
Train steps ... :  20%|██        | 20443/100000 [6:14:44<12:53:25,  1.71it/s]
Train steps ... :  20%|██        | 20444/100000 [6:14:44<12:53:28,  1.71it/s]
Train steps ... :  20%|██        | 20445/100000 [6:14:45<12:53:46,  1.71it/s]
Train steps ... :  20%|██        | 20446/100000 [6:14:45<12:53:06,  1.72it/s]
Train steps ... :  20%|██        | 20447/100000 [6:14:46<12:53:29,  1.71it/s]
Train steps ... :  20%|██        | 20448/100000 [6:14:47<12:53:45,  1.71it/s]
Train steps ... :  20%|██        | 20449/100000 [6:14:47<12:53:32,  1.71it/s]
Train steps ... :  20%|██        | 20450/100000 [6:14:48<12:54:23,  1.71it/s]Step... (20450 / 100000 | Loss: 1.0363445281982422, Learning Rate: 7.99497487437186e-05)
+
                                                                             
Step... (20450 / 100000 | Loss: 0.886687159538269, Learning Rate: 7.99497487437186e-05)
+
Train steps ... :  20%|██        | 20450/100000 [6:14:48<12:54:23,  1.71it/s]
Train steps ... :  20%|██        | 20451/100000 [6:14:48<12:55:04,  1.71it/s]
Train steps ... :  20%|██        | 20452/100000 [6:14:49<12:54:19,  1.71it/s]
Train steps ... :  20%|██        | 20453/100000 [6:14:50<12:55:24,  1.71it/s]
Train steps ... :  20%|██        | 20454/100000 [6:14:50<12:54:53,  1.71it/s]
Train steps ... :  20%|██        | 20455/100000 [6:14:51<12:55:32,  1.71it/s]
Train steps ... :  20%|██        | 20456/100000 [6:14:51<12:55:15,  1.71it/s]
Train steps ... :  20%|██        | 20457/100000 [6:14:52<12:54:19,  1.71it/s]
Train steps ... :  20%|██        | 20458/100000 [6:14:52<12:53:37,  1.71it/s]
Train steps ... :  20%|██        | 20459/100000 [6:14:53<12:53:17,  1.71it/s]
Train steps ... :  20%|██        | 20460/100000 [6:14:54<12:53:34,  1.71it/s]
Train steps ... :  20%|██        | 20461/100000 [6:14:54<12:53:26,  1.71it/s]
Train steps ... :  20%|██        | 20462/100000 [6:14:55<12:52:50,  1.72it/s]
Train steps ... :  20%|██        | 20463/100000 [6:14:55<12:53:06,  1.71it/s]
Train steps ... :  20%|██        | 20464/100000 [6:14:56<12:54:04,  1.71it/s]
Train steps ... :  20%|██        | 20465/100000 [6:14:57<12:53:57,  1.71it/s]
Train steps ... :  20%|██        | 20466/100000 [6:14:57<12:54:40,  1.71it/s]
Train steps ... :  20%|██        | 20467/100000 [6:14:58<12:54:09,  1.71it/s]
Train steps ... :  20%|██        | 20468/100000 [6:14:58<12:53:44,  1.71it/s]
Train steps ... :  20%|██        | 20469/100000 [6:14:59<12:53:47,  1.71it/s]
Train steps ... :  20%|██        | 20470/100000 [6:14:59<12:53:36,  1.71it/s]
Train steps ... :  20%|██        | 20471/100000 [6:15:00<12:54:23,  1.71it/s]
Train steps ... :  20%|██        | 20472/100000 [6:15:01<12:54:31,  1.71it/s]
Train steps ... :  20%|██        | 20473/100000 [6:15:01<12:54:06,  1.71it/s]
Train steps ... :  20%|██        | 20474/100000 [6:15:02<12:54:02,  1.71it/s]
Train steps ... :  20%|██        | 20475/100000 [6:15:02<12:53:38,  1.71it/s]Step... (20475 / 100000 | Loss: 1.0591206550598145, Learning Rate: 7.99246231155779e-05)
+
                                                                             
Step... (20475 / 100000 | Loss: 1.2053210735321045, Learning Rate: 7.99246231155779e-05)
+
Train steps ... :  20%|██        | 20475/100000 [6:15:03<12:53:38,  1.71it/s]
Train steps ... :  20%|██        | 20476/100000 [6:15:03<12:54:32,  1.71it/s]
Train steps ... :  20%|██        | 20477/100000 [6:15:04<12:54:02,  1.71it/s]
Train steps ... :  20%|██        | 20478/100000 [6:15:04<12:53:28,  1.71it/s]
Train steps ... :  20%|██        | 20479/100000 [6:15:05<12:53:31,  1.71it/s]
Train steps ... :  20%|██        | 20480/100000 [6:15:05<12:54:09,  1.71it/s]
Train steps ... :  20%|██        | 20481/100000 [6:15:06<12:53:15,  1.71it/s]
Train steps ... :  20%|██        | 20482/100000 [6:15:07<12:53:13,  1.71it/s]
Train steps ... :  20%|██        | 20483/100000 [6:15:07<12:53:21,  1.71it/s]
Train steps ... :  20%|██        | 20484/100000 [6:15:08<12:53:35,  1.71it/s]
Train steps ... :  20%|██        | 20485/100000 [6:15:08<12:54:31,  1.71it/s]
Train steps ... :  20%|██        | 20486/100000 [6:15:09<12:54:09,  1.71it/s]
Train steps ... :  20%|██        | 20487/100000 [6:15:09<12:54:13,  1.71it/s]
Train steps ... :  20%|██        | 20488/100000 [6:15:10<12:54:30,  1.71it/s]
Train steps ... :  20%|██        | 20489/100000 [6:15:11<12:54:41,  1.71it/s]
Train steps ... :  20%|██        | 20490/100000 [6:15:11<12:54:12,  1.71it/s]
Train steps ... :  20%|██        | 20491/100000 [6:15:12<12:53:42,  1.71it/s]
Train steps ... :  20%|██        | 20492/100000 [6:15:12<12:53:19,  1.71it/s]
Train steps ... :  20%|██        | 20493/100000 [6:15:13<12:53:23,  1.71it/s]
Train steps ... :  20%|██        | 20494/100000 [6:15:14<12:53:11,  1.71it/s]
Train steps ... :  20%|██        | 20495/100000 [6:15:14<12:53:23,  1.71it/s]
Train steps ... :  20%|██        | 20496/100000 [6:15:15<12:53:04,  1.71it/s]
Train steps ... :  20%|██        | 20497/100000 [6:15:15<12:53:18,  1.71it/s]
Train steps ... :  20%|██        | 20498/100000 [6:15:16<12:53:02,  1.71it/s]
Train steps ... :  20%|██        | 20499/100000 [6:15:16<12:54:04,  1.71it/s]
Train steps ... :  20%|██        | 20500/100000 [6:15:17<12:53:46,  1.71it/s]Step... (20500 / 100000 | Loss: 0.8792425394058228, Learning Rate: 7.989949748743719e-05)
+
                                                                             
Step... (20500 / 100000 | Loss: 0.9676027894020081, Learning Rate: 7.989949748743719e-05)
+
Train steps ... :  20%|██        | 20500/100000 [6:15:17<12:53:46,  1.71it/s]
Train steps ... :  21%|██        | 20501/100000 [6:15:18<12:54:05,  1.71it/s]
Train steps ... :  21%|██        | 20502/100000 [6:15:18<12:54:19,  1.71it/s]
Train steps ... :  21%|██        | 20503/100000 [6:15:19<12:53:51,  1.71it/s]
Train steps ... :  21%|██        | 20504/100000 [6:15:19<12:53:32,  1.71it/s]
Train steps ... :  21%|██        | 20505/100000 [6:15:20<12:53:14,  1.71it/s]
Train steps ... :  21%|██        | 20506/100000 [6:15:21<12:53:08,  1.71it/s]
Train steps ... :  21%|██        | 20507/100000 [6:15:21<12:53:23,  1.71it/s]
Train steps ... :  21%|██        | 20508/100000 [6:15:22<12:53:16,  1.71it/s]
Train steps ... :  21%|██        | 20509/100000 [6:15:22<12:53:56,  1.71it/s]
Train steps ... :  21%|██        | 20510/100000 [6:15:23<12:53:44,  1.71it/s]
Train steps ... :  21%|██        | 20511/100000 [6:15:23<12:54:16,  1.71it/s]
Train steps ... :  21%|██        | 20512/100000 [6:15:24<12:53:56,  1.71it/s]
Train steps ... :  21%|██        | 20513/100000 [6:15:25<12:53:11,  1.71it/s]
Train steps ... :  21%|██        | 20514/100000 [6:15:25<12:53:14,  1.71it/s]
Train steps ... :  21%|██        | 20515/100000 [6:15:26<12:54:25,  1.71it/s]
Train steps ... :  21%|██        | 20516/100000 [6:15:26<12:54:04,  1.71it/s]
Train steps ... :  21%|██        | 20517/100000 [6:15:27<12:54:05,  1.71it/s]
Train steps ... :  21%|██        | 20518/100000 [6:15:28<12:53:31,  1.71it/s]
Train steps ... :  21%|██        | 20519/100000 [6:15:28<12:54:28,  1.71it/s]
Train steps ... :  21%|██        | 20520/100000 [6:15:29<12:54:05,  1.71it/s]
Train steps ... :  21%|██        | 20521/100000 [6:15:29<12:53:44,  1.71it/s]
Train steps ... :  21%|██        | 20522/100000 [6:15:30<12:53:39,  1.71it/s]
Train steps ... :  21%|██        | 20523/100000 [6:15:30<12:54:07,  1.71it/s]
Train steps ... :  21%|██        | 20524/100000 [6:15:31<12:54:15,  1.71it/s]
Train steps ... :  21%|██        | 20525/100000 [6:15:32<12:54:32,  1.71it/s]Step... (20525 / 100000 | Loss: 1.2148005962371826, Learning Rate: 7.987437185929648e-05)
+
                                                                             
Step... (20525 / 100000 | Loss: 1.0594584941864014, Learning Rate: 7.987437185929648e-05)
+
Train steps ... :  21%|██        | 20525/100000 [6:15:32<12:54:32,  1.71it/s]
Train steps ... :  21%|██        | 20526/100000 [6:15:32<12:53:44,  1.71it/s]
Train steps ... :  21%|██        | 20527/100000 [6:15:33<12:53:26,  1.71it/s]
Train steps ... :  21%|██        | 20528/100000 [6:15:33<12:54:13,  1.71it/s]
Train steps ... :  21%|██        | 20529/100000 [6:15:34<12:53:35,  1.71it/s]
Train steps ... :  21%|██        | 20530/100000 [6:15:35<12:53:49,  1.71it/s]
Train steps ... :  21%|██        | 20531/100000 [6:15:35<12:53:48,  1.71it/s]
Train steps ... :  21%|██        | 20532/100000 [6:15:36<12:53:50,  1.71it/s]
Train steps ... :  21%|██        | 20533/100000 [6:15:36<12:53:13,  1.71it/s]
Train steps ... :  21%|██        | 20534/100000 [6:15:37<12:53:04,  1.71it/s]
Train steps ... :  21%|██        | 20535/100000 [6:15:37<12:53:19,  1.71it/s]
Train steps ... :  21%|██        | 20536/100000 [6:15:38<12:52:33,  1.71it/s]
Train steps ... :  21%|██        | 20537/100000 [6:15:39<12:52:56,  1.71it/s]
Train steps ... :  21%|██        | 20538/100000 [6:15:39<12:53:45,  1.71it/s]
Train steps ... :  21%|██        | 20539/100000 [6:15:40<12:54:14,  1.71it/s]
Train steps ... :  21%|██        | 20540/100000 [6:15:40<12:53:40,  1.71it/s]
Train steps ... :  21%|██        | 20541/100000 [6:15:41<12:53:47,  1.71it/s]
Train steps ... :  21%|██        | 20542/100000 [6:15:42<12:53:35,  1.71it/s]
Train steps ... :  21%|██        | 20543/100000 [6:15:42<12:53:19,  1.71it/s]
Train steps ... :  21%|██        | 20544/100000 [6:15:43<12:53:12,  1.71it/s]
Train steps ... :  21%|██        | 20545/100000 [6:15:43<12:52:44,  1.71it/s]
Train steps ... :  21%|██        | 20546/100000 [6:15:44<12:52:41,  1.71it/s]
Train steps ... :  21%|██        | 20547/100000 [6:15:44<12:52:24,  1.71it/s]
Train steps ... :  21%|██        | 20548/100000 [6:15:45<12:52:23,  1.71it/s]
Train steps ... :  21%|██        | 20549/100000 [6:15:46<12:52:34,  1.71it/s]
Train steps ... :  21%|██        | 20550/100000 [6:15:46<12:53:00,  1.71it/s]Step... (20550 / 100000 | Loss: 1.1746349334716797, Learning Rate: 7.984924623115579e-05)
+
                                                                             
Step... (20550 / 100000 | Loss: 0.8435139656066895, Learning Rate: 7.984924623115579e-05)
+
Train steps ... :  21%|██        | 20550/100000 [6:15:47<12:53:00,  1.71it/s]
Train steps ... :  21%|██        | 20551/100000 [6:15:47<12:53:21,  1.71it/s]
Train steps ... :  21%|██        | 20552/100000 [6:15:47<12:54:05,  1.71it/s]
Train steps ... :  21%|██        | 20553/100000 [6:15:48<12:53:27,  1.71it/s]
Train steps ... :  21%|██        | 20554/100000 [6:15:49<12:53:36,  1.71it/s]
Train steps ... :  21%|██        | 20555/100000 [6:15:49<12:52:35,  1.71it/s]
Train steps ... :  21%|██        | 20556/100000 [6:15:50<12:53:22,  1.71it/s]
Train steps ... :  21%|██        | 20557/100000 [6:15:50<12:53:02,  1.71it/s]
Train steps ... :  21%|██        | 20558/100000 [6:15:51<12:52:49,  1.71it/s]
Train steps ... :  21%|██        | 20559/100000 [6:15:51<12:52:21,  1.71it/s]
Train steps ... :  21%|██        | 20560/100000 [6:15:52<12:52:27,  1.71it/s]
Train steps ... :  21%|██        | 20561/100000 [6:15:53<12:52:16,  1.71it/s]
Train steps ... :  21%|██        | 20562/100000 [6:15:53<12:52:52,  1.71it/s]
Train steps ... :  21%|██        | 20563/100000 [6:15:54<12:53:39,  1.71it/s]
Train steps ... :  21%|██        | 20564/100000 [6:15:54<12:52:59,  1.71it/s]
Train steps ... :  21%|██        | 20565/100000 [6:15:55<12:52:29,  1.71it/s]
Train steps ... :  21%|██        | 20566/100000 [6:15:56<12:52:58,  1.71it/s]
Train steps ... :  21%|██        | 20567/100000 [6:15:56<12:52:36,  1.71it/s]
Train steps ... :  21%|██        | 20568/100000 [6:15:57<12:53:16,  1.71it/s]
Train steps ... :  21%|██        | 20569/100000 [6:15:57<12:52:48,  1.71it/s]
Train steps ... :  21%|██        | 20570/100000 [6:15:58<12:52:43,  1.71it/s]
Train steps ... :  21%|██        | 20571/100000 [6:15:58<12:52:26,  1.71it/s]
Train steps ... :  21%|██        | 20572/100000 [6:15:59<12:52:41,  1.71it/s]
Train steps ... :  21%|██        | 20573/100000 [6:16:00<12:52:41,  1.71it/s]
Train steps ... :  21%|██        | 20574/100000 [6:16:00<12:52:18,  1.71it/s]
Train steps ... :  21%|██        | 20575/100000 [6:16:01<12:53:23,  1.71it/s]Step... (20575 / 100000 | Loss: 0.704805850982666, Learning Rate: 7.982412060301508e-05)
+
                                                                             
Step... (20575 / 100000 | Loss: 0.7654100656509399, Learning Rate: 7.982412060301508e-05)
+
Train steps ... :  21%|██        | 20575/100000 [6:16:01<12:53:23,  1.71it/s]
Train steps ... :  21%|██        | 20576/100000 [6:16:01<12:53:08,  1.71it/s]
Train steps ... :  21%|██        | 20577/100000 [6:16:02<12:52:48,  1.71it/s]
Train steps ... :  21%|██        | 20578/100000 [6:16:03<12:52:56,  1.71it/s]
Train steps ... :  21%|██        | 20579/100000 [6:16:03<12:52:55,  1.71it/s]
Train steps ... :  21%|██        | 20580/100000 [6:16:04<12:52:56,  1.71it/s]
Train steps ... :  21%|██        | 20581/100000 [6:16:04<12:53:12,  1.71it/s]
Train steps ... :  21%|██        | 20582/100000 [6:16:05<12:53:29,  1.71it/s]
Train steps ... :  21%|██        | 20583/100000 [6:16:05<12:53:45,  1.71it/s]
Train steps ... :  21%|██        | 20584/100000 [6:16:06<12:54:41,  1.71it/s]
Train steps ... :  21%|██        | 20585/100000 [6:16:07<12:54:15,  1.71it/s]
Train steps ... :  21%|██        | 20586/100000 [6:16:07<12:53:56,  1.71it/s]
Train steps ... :  21%|██        | 20587/100000 [6:16:08<12:53:40,  1.71it/s]
Train steps ... :  21%|██        | 20588/100000 [6:16:08<12:52:43,  1.71it/s]
Train steps ... :  21%|██        | 20589/100000 [6:16:09<12:52:18,  1.71it/s]
Train steps ... :  21%|██        | 20590/100000 [6:16:10<12:52:08,  1.71it/s]
Train steps ... :  21%|██        | 20591/100000 [6:16:10<12:52:24,  1.71it/s]
Train steps ... :  21%|██        | 20592/100000 [6:16:11<12:52:42,  1.71it/s]
Train steps ... :  21%|██        | 20593/100000 [6:16:11<12:53:15,  1.71it/s]
Train steps ... :  21%|██        | 20594/100000 [6:16:12<12:54:29,  1.71it/s]
Train steps ... :  21%|██        | 20595/100000 [6:16:12<12:53:40,  1.71it/s]
Train steps ... :  21%|██        | 20596/100000 [6:16:13<12:53:16,  1.71it/s]
Train steps ... :  21%|██        | 20597/100000 [6:16:14<12:53:12,  1.71it/s]
Train steps ... :  21%|██        | 20598/100000 [6:16:14<12:52:32,  1.71it/s]
Train steps ... :  21%|██        | 20599/100000 [6:16:15<12:52:23,  1.71it/s]
Train steps ... :  21%|██        | 20600/100000 [6:16:15<12:53:24,  1.71it/s]Step... (20600 / 100000 | Loss: 0.9405457973480225, Learning Rate: 7.979899497487438e-05)
+
                                                                             
Step... (20600 / 100000 | Loss: 0.957268476486206, Learning Rate: 7.979899497487438e-05)
+
Train steps ... :  21%|██        | 20600/100000 [6:16:16<12:53:24,  1.71it/s]
Train steps ... :  21%|██        | 20601/100000 [6:16:16<12:53:45,  1.71it/s]
Train steps ... :  21%|██        | 20602/100000 [6:16:17<12:53:19,  1.71it/s]
Train steps ... :  21%|██        | 20603/100000 [6:16:17<12:52:58,  1.71it/s]
Train steps ... :  21%|██        | 20604/100000 [6:16:18<12:54:56,  1.71it/s]
Train steps ... :  21%|██        | 20605/100000 [6:16:18<12:52:33,  1.71it/s]
Train steps ... :  21%|██        | 20606/100000 [6:16:19<12:55:04,  1.71it/s]
Train steps ... :  21%|██        | 20607/100000 [6:16:20<12:53:35,  1.71it/s]
Train steps ... :  21%|██        | 20608/100000 [6:16:20<12:53:29,  1.71it/s]
Train steps ... :  21%|██        | 20609/100000 [6:16:21<12:54:14,  1.71it/s]
Train steps ... :  21%|██        | 20610/100000 [6:16:21<12:53:38,  1.71it/s]
Train steps ... :  21%|██        | 20611/100000 [6:16:22<12:54:04,  1.71it/s]
Train steps ... :  21%|██        | 20612/100000 [6:16:22<12:53:14,  1.71it/s]
Train steps ... :  21%|██        | 20613/100000 [6:16:23<12:52:30,  1.71it/s]
Train steps ... :  21%|██        | 20614/100000 [6:16:24<12:52:32,  1.71it/s]
Train steps ... :  21%|██        | 20615/100000 [6:16:24<12:51:59,  1.71it/s]
Train steps ... :  21%|██        | 20616/100000 [6:16:25<12:52:17,  1.71it/s]
Train steps ... :  21%|██        | 20617/100000 [6:16:25<12:53:15,  1.71it/s]
Train steps ... :  21%|██        | 20618/100000 [6:16:26<12:52:42,  1.71it/s]
Train steps ... :  21%|██        | 20619/100000 [6:16:27<12:53:02,  1.71it/s]
Train steps ... :  21%|██        | 20620/100000 [6:16:27<12:52:44,  1.71it/s]
Train steps ... :  21%|██        | 20621/100000 [6:16:28<12:52:10,  1.71it/s]
Train steps ... :  21%|██        | 20622/100000 [6:16:28<12:53:11,  1.71it/s]
Train steps ... :  21%|██        | 20623/100000 [6:16:29<12:52:54,  1.71it/s]
Train steps ... :  21%|██        | 20624/100000 [6:16:29<12:52:35,  1.71it/s]
Train steps ... :  21%|██        | 20625/100000 [6:16:30<12:53:21,  1.71it/s]Step... (20625 / 100000 | Loss: 0.8681129217147827, Learning Rate: 7.977386934673368e-05)
+
                                                                             
Step... (20625 / 100000 | Loss: 0.9376604557037354, Learning Rate: 7.977386934673368e-05)
+
Train steps ... :  21%|██        | 20625/100000 [6:16:30<12:53:21,  1.71it/s]
Train steps ... :  21%|██        | 20626/100000 [6:16:31<12:53:18,  1.71it/s]
Train steps ... :  21%|██        | 20627/100000 [6:16:31<12:52:32,  1.71it/s]
Train steps ... :  21%|██        | 20628/100000 [6:16:32<12:53:12,  1.71it/s]
Train steps ... :  21%|██        | 20629/100000 [6:16:32<12:53:52,  1.71it/s]
Train steps ... :  21%|██        | 20630/100000 [6:16:33<12:53:12,  1.71it/s]
Train steps ... :  21%|██        | 20631/100000 [6:16:34<12:53:22,  1.71it/s]
Train steps ... :  21%|██        | 20632/100000 [6:16:34<12:52:44,  1.71it/s]
Train steps ... :  21%|██        | 20633/100000 [6:16:35<12:53:10,  1.71it/s]
Train steps ... :  21%|██        | 20634/100000 [6:16:35<12:53:29,  1.71it/s]
Train steps ... :  21%|██        | 20635/100000 [6:16:36<12:53:42,  1.71it/s]
Train steps ... :  21%|██        | 20636/100000 [6:16:36<12:53:45,  1.71it/s]
Train steps ... :  21%|██        | 20637/100000 [6:16:37<12:53:03,  1.71it/s]
Train steps ... :  21%|██        | 20638/100000 [6:16:38<12:52:58,  1.71it/s]
Train steps ... :  21%|██        | 20639/100000 [6:16:38<12:52:39,  1.71it/s]
Train steps ... :  21%|██        | 20640/100000 [6:16:39<12:52:17,  1.71it/s]
Train steps ... :  21%|██        | 20641/100000 [6:16:39<12:52:42,  1.71it/s]
Train steps ... :  21%|██        | 20642/100000 [6:16:40<12:52:06,  1.71it/s]
Train steps ... :  21%|██        | 20643/100000 [6:16:41<12:52:29,  1.71it/s]
Train steps ... :  21%|██        | 20644/100000 [6:16:41<12:52:53,  1.71it/s]
Train steps ... :  21%|██        | 20645/100000 [6:16:42<12:53:31,  1.71it/s]
Train steps ... :  21%|██        | 20646/100000 [6:16:42<12:56:05,  1.70it/s]
Train steps ... :  21%|██        | 20647/100000 [6:16:43<12:53:17,  1.71it/s]
Train steps ... :  21%|██        | 20648/100000 [6:16:43<12:53:53,  1.71it/s]
Train steps ... :  21%|██        | 20649/100000 [6:16:44<12:53:57,  1.71it/s]
Train steps ... :  21%|██        | 20650/100000 [6:16:45<12:53:50,  1.71it/s]Step... (20650 / 100000 | Loss: 0.8368181586265564, Learning Rate: 7.974874371859297e-05)
+
                                                                             
Step... (20650 / 100000 | Loss: 1.2342476844787598, Learning Rate: 7.974874371859297e-05)
+
Train steps ... :  21%|██        | 20650/100000 [6:16:45<12:53:50,  1.71it/s]
Train steps ... :  21%|██        | 20651/100000 [6:16:45<12:53:27,  1.71it/s]
Train steps ... :  21%|██        | 20652/100000 [6:16:46<12:52:49,  1.71it/s]
Train steps ... :  21%|██        | 20653/100000 [6:16:46<12:53:35,  1.71it/s]
Train steps ... :  21%|██        | 20654/100000 [6:16:47<12:53:33,  1.71it/s]
Train steps ... :  21%|██        | 20655/100000 [6:16:48<12:52:56,  1.71it/s]
Train steps ... :  21%|██        | 20656/100000 [6:16:48<12:53:07,  1.71it/s]
Train steps ... :  21%|██        | 20657/100000 [6:16:49<12:53:08,  1.71it/s]
Train steps ... :  21%|██        | 20658/100000 [6:16:49<12:56:36,  1.70it/s]
Train steps ... :  21%|██        | 20659/100000 [6:16:50<12:53:35,  1.71it/s]
Train steps ... :  21%|██        | 20660/100000 [6:16:50<12:52:55,  1.71it/s]
Train steps ... :  21%|██        | 20661/100000 [6:16:51<12:54:05,  1.71it/s]
Train steps ... :  21%|██        | 20662/100000 [6:16:52<12:54:18,  1.71it/s]
Train steps ... :  21%|██        | 20663/100000 [6:16:52<12:54:31,  1.71it/s]
Train steps ... :  21%|██        | 20664/100000 [6:16:53<12:52:42,  1.71it/s]
Train steps ... :  21%|██        | 20665/100000 [6:16:53<12:52:53,  1.71it/s]
Train steps ... :  21%|██        | 20666/100000 [6:16:54<12:52:34,  1.71it/s]
Train steps ... :  21%|██        | 20667/100000 [6:16:55<12:52:47,  1.71it/s]
Train steps ... :  21%|██        | 20668/100000 [6:16:55<12:53:46,  1.71it/s]
Train steps ... :  21%|██        | 20669/100000 [6:16:56<12:52:59,  1.71it/s]
Train steps ... :  21%|██        | 20670/100000 [6:16:56<12:53:45,  1.71it/s]
Train steps ... :  21%|██        | 20671/100000 [6:16:57<12:53:44,  1.71it/s]
Train steps ... :  21%|██        | 20672/100000 [6:16:58<12:53:34,  1.71it/s]
Train steps ... :  21%|██        | 20673/100000 [6:16:58<12:52:57,  1.71it/s]
Train steps ... :  21%|██        | 20674/100000 [6:16:59<12:52:48,  1.71it/s]
Train steps ... :  21%|██        | 20675/100000 [6:16:59<12:53:22,  1.71it/s]Step... (20675 / 100000 | Loss: 0.9596697092056274, Learning Rate: 7.972361809045227e-05)
+
                                                                             
Step... (20675 / 100000 | Loss: 0.8884670734405518, Learning Rate: 7.972361809045227e-05)
+
Train steps ... :  21%|██        | 20675/100000 [6:17:00<12:53:22,  1.71it/s]
Train steps ... :  21%|██        | 20676/100000 [6:17:00<12:54:35,  1.71it/s]
Train steps ... :  21%|██        | 20677/100000 [6:17:00<12:52:37,  1.71it/s]
Train steps ... :  21%|██        | 20678/100000 [6:17:01<12:57:11,  1.70it/s]
Train steps ... :  21%|██        | 20679/100000 [6:17:02<12:55:59,  1.70it/s]
Train steps ... :  21%|██        | 20680/100000 [6:17:02<12:55:54,  1.70it/s]
Train steps ... :  21%|██        | 20681/100000 [6:17:03<12:54:34,  1.71it/s]
Train steps ... :  21%|██        | 20682/100000 [6:17:03<12:54:39,  1.71it/s]
Train steps ... :  21%|██        | 20683/100000 [6:17:04<12:53:38,  1.71it/s]
Train steps ... :  21%|██        | 20684/100000 [6:17:05<12:53:13,  1.71it/s]
Train steps ... :  21%|██        | 20685/100000 [6:17:05<12:52:43,  1.71it/s]
Train steps ... :  21%|██        | 20686/100000 [6:17:06<12:53:08,  1.71it/s]
Train steps ... :  21%|██        | 20687/100000 [6:17:06<12:51:24,  1.71it/s]
Train steps ... :  21%|██        | 20688/100000 [6:17:07<12:52:18,  1.71it/s]
Train steps ... :  21%|██        | 20689/100000 [6:17:07<12:52:21,  1.71it/s]
Train steps ... :  21%|██        | 20690/100000 [6:17:08<12:52:30,  1.71it/s]
Train steps ... :  21%|██        | 20691/100000 [6:17:09<12:52:32,  1.71it/s]
Train steps ... :  21%|██        | 20692/100000 [6:17:09<12:52:25,  1.71it/s]
Train steps ... :  21%|██        | 20693/100000 [6:17:10<12:51:59,  1.71it/s]
Train steps ... :  21%|██        | 20694/100000 [6:17:10<12:51:37,  1.71it/s]
Train steps ... :  21%|██        | 20695/100000 [6:17:11<12:51:20,  1.71it/s]
Train steps ... :  21%|██        | 20696/100000 [6:17:12<12:51:43,  1.71it/s]
Train steps ... :  21%|██        | 20697/100000 [6:17:12<12:52:04,  1.71it/s]
Train steps ... :  21%|██        | 20698/100000 [6:17:13<12:52:02,  1.71it/s]
Train steps ... :  21%|██        | 20699/100000 [6:17:13<12:52:30,  1.71it/s]
Train steps ... :  21%|██        | 20700/100000 [6:17:14<12:52:06,  1.71it/s]Step... (20700 / 100000 | Loss: 0.799270749092102, Learning Rate: 7.969849246231155e-05)
+
                                                                             
Step... (20700 / 100000 | Loss: 0.7716310024261475, Learning Rate: 7.969849246231155e-05)
+
Train steps ... :  21%|██        | 20700/100000 [6:17:14<12:52:06,  1.71it/s]
Train steps ... :  21%|██        | 20701/100000 [6:17:14<12:51:52,  1.71it/s]
Train steps ... :  21%|██        | 20702/100000 [6:17:15<12:51:54,  1.71it/s]
Train steps ... :  21%|██        | 20703/100000 [6:17:16<12:51:41,  1.71it/s]
Train steps ... :  21%|██        | 20704/100000 [6:17:16<12:51:39,  1.71it/s]
Train steps ... :  21%|██        | 20705/100000 [6:17:17<12:52:04,  1.71it/s]
Train steps ... :  21%|██        | 20706/100000 [6:17:17<12:51:33,  1.71it/s]
Train steps ... :  21%|██        | 20707/100000 [6:17:18<12:51:33,  1.71it/s]
Train steps ... :  21%|██        | 20708/100000 [6:17:19<12:51:36,  1.71it/s]
Train steps ... :  21%|██        | 20709/100000 [6:17:19<12:51:19,  1.71it/s]
Train steps ... :  21%|██        | 20710/100000 [6:17:20<12:51:11,  1.71it/s]
Train steps ... :  21%|██        | 20711/100000 [6:17:20<12:51:29,  1.71it/s]
Train steps ... :  21%|██        | 20712/100000 [6:17:21<12:51:54,  1.71it/s]
Train steps ... :  21%|██        | 20713/100000 [6:17:21<12:52:00,  1.71it/s]
Train steps ... :  21%|██        | 20714/100000 [6:17:22<12:51:45,  1.71it/s]
Train steps ... :  21%|██        | 20715/100000 [6:17:23<12:52:30,  1.71it/s]
Train steps ... :  21%|██        | 20716/100000 [6:17:23<12:52:30,  1.71it/s]
Train steps ... :  21%|██        | 20717/100000 [6:17:24<12:52:34,  1.71it/s]
Train steps ... :  21%|██        | 20718/100000 [6:17:24<12:52:49,  1.71it/s]
Train steps ... :  21%|██        | 20719/100000 [6:17:25<12:52:29,  1.71it/s]
Train steps ... :  21%|██        | 20720/100000 [6:17:26<12:52:54,  1.71it/s]
Train steps ... :  21%|██        | 20721/100000 [6:17:26<12:52:51,  1.71it/s]
Train steps ... :  21%|██        | 20722/100000 [6:17:27<12:52:08,  1.71it/s]
Train steps ... :  21%|██        | 20723/100000 [6:17:27<12:52:31,  1.71it/s]
Train steps ... :  21%|██        | 20724/100000 [6:17:28<12:52:04,  1.71it/s]
Train steps ... :  21%|██        | 20725/100000 [6:17:28<12:51:54,  1.71it/s]Step... (20725 / 100000 | Loss: 0.995415449142456, Learning Rate: 7.967336683417086e-05)
+
                                                                             
Step... (20725 / 100000 | Loss: 0.9051423072814941, Learning Rate: 7.967336683417086e-05)
+
Train steps ... :  21%|██        | 20725/100000 [6:17:29<12:51:54,  1.71it/s]
Train steps ... :  21%|██        | 20726/100000 [6:17:29<12:51:50,  1.71it/s]
Train steps ... :  21%|██        | 20727/100000 [6:17:30<12:51:15,  1.71it/s]
Train steps ... :  21%|██        | 20728/100000 [6:17:30<12:51:30,  1.71it/s]
Train steps ... :  21%|██        | 20729/100000 [6:17:31<12:51:31,  1.71it/s]
Train steps ... :  21%|██        | 20730/100000 [6:17:31<12:51:40,  1.71it/s]
Train steps ... :  21%|██        | 20731/100000 [6:17:32<12:52:31,  1.71it/s]
Train steps ... :  21%|██        | 20732/100000 [6:17:33<12:51:51,  1.71it/s]
Train steps ... :  21%|██        | 20733/100000 [6:17:33<12:51:09,  1.71it/s]
Train steps ... :  21%|██        | 20734/100000 [6:17:34<12:52:54,  1.71it/s]
Train steps ... :  21%|██        | 20735/100000 [6:17:34<12:50:56,  1.71it/s]
Train steps ... :  21%|██        | 20736/100000 [6:17:35<12:52:06,  1.71it/s]
Train steps ... :  21%|██        | 20737/100000 [6:17:35<12:50:46,  1.71it/s]
Train steps ... :  21%|██        | 20738/100000 [6:17:36<12:50:41,  1.71it/s]
Train steps ... :  21%|██        | 20739/100000 [6:17:37<12:51:14,  1.71it/s]
Train steps ... :  21%|██        | 20740/100000 [6:17:37<12:52:19,  1.71it/s]
Train steps ... :  21%|██        | 20741/100000 [6:17:38<12:51:36,  1.71it/s]
Train steps ... :  21%|██        | 20742/100000 [6:17:38<12:52:18,  1.71it/s]
Train steps ... :  21%|██        | 20743/100000 [6:17:39<12:51:34,  1.71it/s]
Train steps ... :  21%|██        | 20744/100000 [6:17:40<12:51:29,  1.71it/s]
Train steps ... :  21%|██        | 20745/100000 [6:17:40<12:51:39,  1.71it/s]
Train steps ... :  21%|██        | 20746/100000 [6:17:41<12:51:22,  1.71it/s]
Train steps ... :  21%|██        | 20747/100000 [6:17:41<12:50:55,  1.71it/s]
Train steps ... :  21%|██        | 20748/100000 [6:17:42<12:51:44,  1.71it/s]
Train steps ... :  21%|██        | 20749/100000 [6:17:43<12:51:06,  1.71it/s]
Train steps ... :  21%|██        | 20750/100000 [6:17:43<12:50:59,  1.71it/s]Step... (20750 / 100000 | Loss: 1.0921752452850342, Learning Rate: 7.964824120603015e-05)
+
                                                                             
Step... (20750 / 100000 | Loss: 0.65499347448349, Learning Rate: 7.964824120603015e-05)
+
Train steps ... :  21%|██        | 20750/100000 [6:17:43<12:50:59,  1.71it/s]
Train steps ... :  21%|██        | 20751/100000 [6:17:44<12:52:41,  1.71it/s]
Train steps ... :  21%|██        | 20752/100000 [6:17:44<12:52:01,  1.71it/s]
Train steps ... :  21%|██        | 20753/100000 [6:17:45<12:52:47,  1.71it/s]
Train steps ... :  21%|██        | 20754/100000 [6:17:45<12:52:10,  1.71it/s]
Train steps ... :  21%|██        | 20755/100000 [6:17:46<12:52:55,  1.71it/s]
Train steps ... :  21%|██        | 20756/100000 [6:17:47<12:53:16,  1.71it/s]
Train steps ... :  21%|██        | 20757/100000 [6:17:47<12:53:08,  1.71it/s]
Train steps ... :  21%|██        | 20758/100000 [6:17:48<12:53:16,  1.71it/s]
Train steps ... :  21%|██        | 20759/100000 [6:17:48<12:52:09,  1.71it/s]
Train steps ... :  21%|██        | 20760/100000 [6:17:49<12:52:58,  1.71it/s]
Train steps ... :  21%|██        | 20761/100000 [6:17:50<12:51:53,  1.71it/s]
Train steps ... :  21%|██        | 20762/100000 [6:17:50<12:51:08,  1.71it/s]
Train steps ... :  21%|██        | 20763/100000 [6:17:51<12:51:04,  1.71it/s]
Train steps ... :  21%|██        | 20764/100000 [6:17:51<12:51:44,  1.71it/s]
Train steps ... :  21%|██        | 20765/100000 [6:17:52<12:52:02,  1.71it/s]
Train steps ... :  21%|██        | 20766/100000 [6:17:52<12:51:22,  1.71it/s]
Train steps ... :  21%|██        | 20767/100000 [6:17:53<12:51:48,  1.71it/s]
Train steps ... :  21%|██        | 20768/100000 [6:17:54<12:51:19,  1.71it/s]
Train steps ... :  21%|██        | 20769/100000 [6:17:54<12:50:55,  1.71it/s]
Train steps ... :  21%|██        | 20770/100000 [6:17:55<12:51:12,  1.71it/s]
Train steps ... :  21%|██        | 20771/100000 [6:17:55<12:51:57,  1.71it/s]
Train steps ... :  21%|██        | 20772/100000 [6:17:56<12:51:14,  1.71it/s]
Train steps ... :  21%|██        | 20773/100000 [6:17:57<12:51:22,  1.71it/s]
Train steps ... :  21%|██        | 20774/100000 [6:17:57<12:51:41,  1.71it/s]
Train steps ... :  21%|██        | 20775/100000 [6:17:58<12:51:46,  1.71it/s]Step... (20775 / 100000 | Loss: 0.9626421928405762, Learning Rate: 7.962311557788946e-05)
+
                                                                             
Step... (20775 / 100000 | Loss: 1.2113473415374756, Learning Rate: 7.962311557788946e-05)
+
Train steps ... :  21%|██        | 20775/100000 [6:17:58<12:51:46,  1.71it/s]
Train steps ... :  21%|██        | 20776/100000 [6:17:58<12:51:56,  1.71it/s]
Train steps ... :  21%|██        | 20777/100000 [6:17:59<12:51:23,  1.71it/s]
Train steps ... :  21%|██        | 20778/100000 [6:17:59<12:51:59,  1.71it/s]
Train steps ... :  21%|██        | 20779/100000 [6:18:00<12:51:29,  1.71it/s]
Train steps ... :  21%|██        | 20780/100000 [6:18:01<12:51:30,  1.71it/s]
Train steps ... :  21%|██        | 20781/100000 [6:18:01<12:52:16,  1.71it/s]
Train steps ... :  21%|██        | 20782/100000 [6:18:02<12:52:59,  1.71it/s]
Train steps ... :  21%|██        | 20783/100000 [6:18:02<12:52:37,  1.71it/s]
Train steps ... :  21%|██        | 20784/100000 [6:18:03<12:54:16,  1.71it/s]
Train steps ... :  21%|██        | 20785/100000 [6:18:04<12:53:29,  1.71it/s]
Train steps ... :  21%|██        | 20786/100000 [6:18:04<12:52:55,  1.71it/s]
Train steps ... :  21%|██        | 20787/100000 [6:18:05<12:52:29,  1.71it/s]
Train steps ... :  21%|██        | 20788/100000 [6:18:05<12:51:57,  1.71it/s]
Train steps ... :  21%|██        | 20789/100000 [6:18:06<12:52:43,  1.71it/s]
Train steps ... :  21%|██        | 20790/100000 [6:18:06<12:52:16,  1.71it/s]
Train steps ... :  21%|██        | 20791/100000 [6:18:07<12:52:46,  1.71it/s]
Train steps ... :  21%|██        | 20792/100000 [6:18:08<12:52:20,  1.71it/s]
Train steps ... :  21%|██        | 20793/100000 [6:18:08<12:52:26,  1.71it/s]
Train steps ... :  21%|██        | 20794/100000 [6:18:09<12:52:24,  1.71it/s]
Train steps ... :  21%|██        | 20795/100000 [6:18:09<12:51:54,  1.71it/s]
Train steps ... :  21%|██        | 20796/100000 [6:18:10<12:51:49,  1.71it/s]
Train steps ... :  21%|██        | 20797/100000 [6:18:11<12:51:26,  1.71it/s]
Train steps ... :  21%|██        | 20798/100000 [6:18:11<12:52:22,  1.71it/s]
Train steps ... :  21%|██        | 20799/100000 [6:18:12<12:51:02,  1.71it/s]
Train steps ... :  21%|██        | 20800/100000 [6:18:12<12:50:54,  1.71it/s]Step... (20800 / 100000 | Loss: 1.1720829010009766, Learning Rate: 7.959798994974875e-05)
+
                                                                             
Step... (20800 / 100000 | Loss: 0.8752936124801636, Learning Rate: 7.959798994974875e-05)
+
Train steps ... :  21%|██        | 20800/100000 [6:18:13<12:50:54,  1.71it/s]
Train steps ... :  21%|██        | 20801/100000 [6:18:13<12:51:04,  1.71it/s]
Train steps ... :  21%|██        | 20802/100000 [6:18:13<12:51:20,  1.71it/s]
Train steps ... :  21%|██        | 20803/100000 [6:18:14<12:51:59,  1.71it/s]
Train steps ... :  21%|██        | 20804/100000 [6:18:15<12:51:28,  1.71it/s]
Train steps ... :  21%|██        | 20805/100000 [6:18:15<12:51:49,  1.71it/s]
Train steps ... :  21%|██        | 20806/100000 [6:18:16<12:52:11,  1.71it/s]
Train steps ... :  21%|██        | 20807/100000 [6:18:16<12:52:07,  1.71it/s]
Train steps ... :  21%|██        | 20808/100000 [6:18:17<12:51:57,  1.71it/s]
Train steps ... :  21%|██        | 20809/100000 [6:18:18<12:52:04,  1.71it/s]
Train steps ... :  21%|██        | 20810/100000 [6:18:18<12:52:01,  1.71it/s]
Train steps ... :  21%|██        | 20811/100000 [6:18:19<12:51:18,  1.71it/s]
Train steps ... :  21%|██        | 20812/100000 [6:18:19<12:50:58,  1.71it/s]
Train steps ... :  21%|██        | 20813/100000 [6:18:20<12:51:11,  1.71it/s]
Train steps ... :  21%|██        | 20814/100000 [6:18:21<12:51:11,  1.71it/s]
Train steps ... :  21%|██        | 20815/100000 [6:18:21<12:51:07,  1.71it/s]
Train steps ... :  21%|██        | 20816/100000 [6:18:22<12:50:45,  1.71it/s]
Train steps ... :  21%|██        | 20817/100000 [6:18:22<12:51:20,  1.71it/s]
Train steps ... :  21%|██        | 20818/100000 [6:18:23<12:51:23,  1.71it/s]
Train steps ... :  21%|██        | 20819/100000 [6:18:23<12:50:48,  1.71it/s]
Train steps ... :  21%|██        | 20820/100000 [6:18:24<12:50:40,  1.71it/s]
Train steps ... :  21%|██        | 20821/100000 [6:18:25<12:51:45,  1.71it/s]
Train steps ... :  21%|██        | 20822/100000 [6:18:25<12:51:51,  1.71it/s]
Train steps ... :  21%|██        | 20823/100000 [6:18:26<12:51:20,  1.71it/s]
Train steps ... :  21%|██        | 20824/100000 [6:18:26<12:52:01,  1.71it/s]
Train steps ... :  21%|██        | 20825/100000 [6:18:27<12:53:17,  1.71it/s]Step... (20825 / 100000 | Loss: 1.2520153522491455, Learning Rate: 7.957286432160805e-05)
+
                                                                             
Step... (20825 / 100000 | Loss: 1.4954941272735596, Learning Rate: 7.957286432160805e-05)
+
Train steps ... :  21%|██        | 20825/100000 [6:18:27<12:53:17,  1.71it/s]
Train steps ... :  21%|██        | 20826/100000 [6:18:28<12:51:42,  1.71it/s]
Train steps ... :  21%|██        | 20827/100000 [6:18:28<12:50:32,  1.71it/s]
Train steps ... :  21%|██        | 20828/100000 [6:18:29<12:50:33,  1.71it/s]
Train steps ... :  21%|██        | 20829/100000 [6:18:29<12:51:30,  1.71it/s]
Train steps ... :  21%|██        | 20830/100000 [6:18:30<12:52:10,  1.71it/s]
Train steps ... :  21%|██        | 20831/100000 [6:18:30<12:50:46,  1.71it/s]
Train steps ... :  21%|██        | 20832/100000 [6:18:31<12:50:42,  1.71it/s]
Train steps ... :  21%|██        | 20833/100000 [6:18:32<12:52:09,  1.71it/s]
Train steps ... :  21%|██        | 20834/100000 [6:18:32<12:52:04,  1.71it/s]
Train steps ... :  21%|██        | 20835/100000 [6:18:33<12:50:23,  1.71it/s]
Train steps ... :  21%|██        | 20836/100000 [6:18:33<12:50:55,  1.71it/s]
Train steps ... :  21%|██        | 20837/100000 [6:18:34<12:50:50,  1.71it/s]
Train steps ... :  21%|██        | 20838/100000 [6:18:35<12:52:49,  1.71it/s]
Train steps ... :  21%|██        | 20839/100000 [6:18:35<12:52:19,  1.71it/s]
Train steps ... :  21%|██        | 20840/100000 [6:18:36<12:52:23,  1.71it/s]
Train steps ... :  21%|██        | 20841/100000 [6:18:36<12:52:42,  1.71it/s]
Train steps ... :  21%|██        | 20842/100000 [6:18:37<12:52:51,  1.71it/s]
Train steps ... :  21%|██        | 20843/100000 [6:18:37<12:51:59,  1.71it/s]
Train steps ... :  21%|██        | 20844/100000 [6:18:38<12:52:24,  1.71it/s]
Train steps ... :  21%|██        | 20845/100000 [6:18:39<12:51:34,  1.71it/s]
Train steps ... :  21%|██        | 20846/100000 [6:18:39<12:51:38,  1.71it/s]
Train steps ... :  21%|██        | 20847/100000 [6:18:40<12:51:48,  1.71it/s]
Train steps ... :  21%|██        | 20848/100000 [6:18:40<12:52:06,  1.71it/s]
Train steps ... :  21%|██        | 20849/100000 [6:18:41<12:51:33,  1.71it/s]
Train steps ... :  21%|██        | 20850/100000 [6:18:42<12:52:07,  1.71it/s]Step... (20850 / 100000 | Loss: 1.3815875053405762, Learning Rate: 7.954773869346735e-05)
+
                                                                             
Step... (20850 / 100000 | Loss: 0.9586275219917297, Learning Rate: 7.954773869346735e-05)
+
Train steps ... :  21%|██        | 20850/100000 [6:18:42<12:52:07,  1.71it/s]
Train steps ... :  21%|██        | 20851/100000 [6:18:42<12:52:32,  1.71it/s]
Train steps ... :  21%|██        | 20852/100000 [6:18:43<12:51:53,  1.71it/s]
Train steps ... :  21%|██        | 20853/100000 [6:18:43<12:51:38,  1.71it/s]
Train steps ... :  21%|██        | 20854/100000 [6:18:44<12:52:13,  1.71it/s]
Train steps ... :  21%|██        | 20855/100000 [6:18:45<12:55:22,  1.70it/s]
Train steps ... :  21%|██        | 20856/100000 [6:18:45<12:51:24,  1.71it/s]
Train steps ... :  21%|██        | 20857/100000 [6:18:46<12:50:46,  1.71it/s]
Train steps ... :  21%|██        | 20858/100000 [6:18:46<12:50:31,  1.71it/s]
Train steps ... :  21%|██        | 20859/100000 [6:18:47<12:51:32,  1.71it/s]
Train steps ... :  21%|██        | 20860/100000 [6:18:47<12:51:23,  1.71it/s]
Train steps ... :  21%|██        | 20861/100000 [6:18:48<12:50:26,  1.71it/s]
Train steps ... :  21%|██        | 20862/100000 [6:18:49<12:50:39,  1.71it/s]
Train steps ... :  21%|██        | 20863/100000 [6:18:49<12:50:15,  1.71it/s]
Train steps ... :  21%|██        | 20864/100000 [6:18:50<12:49:37,  1.71it/s]
Train steps ... :  21%|██        | 20865/100000 [6:18:50<12:50:57,  1.71it/s]
Train steps ... :  21%|██        | 20866/100000 [6:18:51<12:54:09,  1.70it/s]
Train steps ... :  21%|██        | 20867/100000 [6:18:52<12:52:15,  1.71it/s]
Train steps ... :  21%|██        | 20868/100000 [6:18:52<12:51:54,  1.71it/s]
Train steps ... :  21%|██        | 20869/100000 [6:18:53<12:52:15,  1.71it/s]
Train steps ... :  21%|██        | 20870/100000 [6:18:53<12:51:04,  1.71it/s]
Train steps ... :  21%|██        | 20871/100000 [6:18:54<12:52:34,  1.71it/s]
Train steps ... :  21%|██        | 20872/100000 [6:18:54<12:51:37,  1.71it/s]
Train steps ... :  21%|██        | 20873/100000 [6:18:55<12:52:10,  1.71it/s]
Train steps ... :  21%|██        | 20874/100000 [6:18:56<12:52:31,  1.71it/s]
Train steps ... :  21%|██        | 20875/100000 [6:18:56<12:51:42,  1.71it/s]Step... (20875 / 100000 | Loss: 1.6640312671661377, Learning Rate: 7.952261306532663e-05)
+
                                                                             
Step... (20875 / 100000 | Loss: 0.9878737926483154, Learning Rate: 7.952261306532663e-05)
+
Train steps ... :  21%|██        | 20875/100000 [6:18:57<12:51:42,  1.71it/s]
Train steps ... :  21%|██        | 20876/100000 [6:18:57<12:51:22,  1.71it/s]
Train steps ... :  21%|██        | 20877/100000 [6:18:57<12:51:28,  1.71it/s]
Train steps ... :  21%|██        | 20878/100000 [6:18:58<12:50:27,  1.71it/s]
Train steps ... :  21%|██        | 20879/100000 [6:18:59<12:50:02,  1.71it/s]
Train steps ... :  21%|██        | 20880/100000 [6:18:59<12:51:14,  1.71it/s]
Train steps ... :  21%|██        | 20881/100000 [6:19:00<12:50:48,  1.71it/s]
Train steps ... :  21%|██        | 20882/100000 [6:19:00<12:51:06,  1.71it/s]
Train steps ... :  21%|██        | 20883/100000 [6:19:01<12:51:32,  1.71it/s]
Train steps ... :  21%|██        | 20884/100000 [6:19:01<12:51:48,  1.71it/s]
Train steps ... :  21%|██        | 20885/100000 [6:19:02<12:50:58,  1.71it/s]
Train steps ... :  21%|██        | 20886/100000 [6:19:03<12:50:36,  1.71it/s]
Train steps ... :  21%|██        | 20887/100000 [6:19:03<12:51:08,  1.71it/s]
Train steps ... :  21%|██        | 20888/100000 [6:19:04<12:51:15,  1.71it/s]
Train steps ... :  21%|██        | 20889/100000 [6:19:04<12:50:35,  1.71it/s]
Train steps ... :  21%|██        | 20890/100000 [6:19:05<12:51:30,  1.71it/s]
Train steps ... :  21%|��█        | 20891/100000 [6:19:06<12:50:55,  1.71it/s]
Train steps ... :  21%|██        | 20892/100000 [6:19:06<12:50:20,  1.71it/s]
Train steps ... :  21%|██        | 20893/100000 [6:19:07<12:52:09,  1.71it/s]
Train steps ... :  21%|██        | 20894/100000 [6:19:07<12:52:22,  1.71it/s]
Train steps ... :  21%|██        | 20895/100000 [6:19:08<12:52:13,  1.71it/s]
Train steps ... :  21%|██        | 20896/100000 [6:19:08<12:51:29,  1.71it/s]
Train steps ... :  21%|██        | 20897/100000 [6:19:09<12:52:53,  1.71it/s]
Train steps ... :  21%|██        | 20898/100000 [6:19:10<12:53:03,  1.71it/s]
Train steps ... :  21%|██        | 20899/100000 [6:19:10<12:51:56,  1.71it/s]
Train steps ... :  21%|██        | 20900/100000 [6:19:11<12:52:04,  1.71it/s]Step... (20900 / 100000 | Loss: 0.8461540937423706, Learning Rate: 7.949748743718594e-05)
+
                                                                             
Step... (20900 / 100000 | Loss: 1.4692381620407104, Learning Rate: 7.949748743718594e-05)
+
Train steps ... :  21%|██        | 20900/100000 [6:19:11<12:52:04,  1.71it/s]
Train steps ... :  21%|██        | 20901/100000 [6:19:11<12:52:09,  1.71it/s]
Train steps ... :  21%|██        | 20902/100000 [6:19:12<12:52:01,  1.71it/s]
Train steps ... :  21%|██        | 20903/100000 [6:19:13<12:51:19,  1.71it/s]
Train steps ... :  21%|██        | 20904/100000 [6:19:13<12:52:29,  1.71it/s]
Train steps ... :  21%|██        | 20905/100000 [6:19:14<12:51:59,  1.71it/s]
Train steps ... :  21%|██        | 20906/100000 [6:19:14<12:50:50,  1.71it/s]
Train steps ... :  21%|██        | 20907/100000 [6:19:15<12:53:06,  1.71it/s]
Train steps ... :  21%|██        | 20908/100000 [6:19:16<12:51:23,  1.71it/s]
Train steps ... :  21%|██        | 20909/100000 [6:19:16<12:51:29,  1.71it/s]
Train steps ... :  21%|██        | 20910/100000 [6:19:17<12:51:14,  1.71it/s]
Train steps ... :  21%|██        | 20911/100000 [6:19:17<12:50:06,  1.71it/s]
Train steps ... :  21%|██        | 20912/100000 [6:19:18<12:50:26,  1.71it/s]
Train steps ... :  21%|██        | 20913/100000 [6:19:18<12:50:59,  1.71it/s]
Train steps ... :  21%|██        | 20914/100000 [6:19:19<12:50:58,  1.71it/s]
Train steps ... :  21%|██        | 20915/100000 [6:19:20<12:50:55,  1.71it/s]
Train steps ... :  21%|██        | 20916/100000 [6:19:20<12:50:49,  1.71it/s]
Train steps ... :  21%|██        | 20917/100000 [6:19:21<12:50:57,  1.71it/s]
Train steps ... :  21%|██        | 20918/100000 [6:19:21<12:49:50,  1.71it/s]
Train steps ... :  21%|██        | 20919/100000 [6:19:22<12:49:53,  1.71it/s]
Train steps ... :  21%|██        | 20920/100000 [6:19:23<12:51:48,  1.71it/s]
Train steps ... :  21%|██        | 20921/100000 [6:19:23<12:50:59,  1.71it/s]
Train steps ... :  21%|██        | 20922/100000 [6:19:24<12:50:54,  1.71it/s]
Train steps ... :  21%|██        | 20923/100000 [6:19:24<12:51:39,  1.71it/s]
Train steps ... :  21%|██        | 20924/100000 [6:19:25<12:51:09,  1.71it/s]
Train steps ... :  21%|██        | 20925/100000 [6:19:25<12:54:52,  1.70it/s]Step... (20925 / 100000 | Loss: 0.8028380870819092, Learning Rate: 7.947236180904522e-05)
+
                                                                             
Step... (20925 / 100000 | Loss: 0.8583966493606567, Learning Rate: 7.947236180904522e-05)
+
Train steps ... :  21%|██        | 20925/100000 [6:19:26<12:54:52,  1.70it/s]
Train steps ... :  21%|██        | 20926/100000 [6:19:26<12:53:12,  1.70it/s]
Train steps ... :  21%|██        | 20927/100000 [6:19:27<12:52:12,  1.71it/s]
Train steps ... :  21%|██        | 20928/100000 [6:19:27<12:52:44,  1.71it/s]
Train steps ... :  21%|██        | 20929/100000 [6:19:28<12:51:20,  1.71it/s]
Train steps ... :  21%|██        | 20930/100000 [6:19:28<12:50:39,  1.71it/s]
Train steps ... :  21%|██        | 20931/100000 [6:19:29<12:50:26,  1.71it/s]
Train steps ... :  21%|██        | 20932/100000 [6:19:30<12:50:25,  1.71it/s]
Train steps ... :  21%|██        | 20933/100000 [6:19:30<12:50:16,  1.71it/s]
Train steps ... :  21%|██        | 20934/100000 [6:19:31<12:49:47,  1.71it/s]
Train steps ... :  21%|██        | 20935/100000 [6:19:31<12:50:16,  1.71it/s]
Train steps ... :  21%|██        | 20936/100000 [6:19:32<12:50:12,  1.71it/s]
Train steps ... :  21%|██        | 20937/100000 [6:19:32<12:50:14,  1.71it/s]
Train steps ... :  21%|██        | 20938/100000 [6:19:33<12:49:28,  1.71it/s]
Train steps ... :  21%|██        | 20939/100000 [6:19:34<12:50:53,  1.71it/s]
Train steps ... :  21%|██        | 20940/100000 [6:19:34<12:51:41,  1.71it/s]
Train steps ... :  21%|██        | 20941/100000 [6:19:35<12:52:06,  1.71it/s]
Train steps ... :  21%|██        | 20942/100000 [6:19:35<12:51:12,  1.71it/s]
Train steps ... :  21%|██        | 20943/100000 [6:19:36<12:50:41,  1.71it/s]
Train steps ... :  21%|██        | 20944/100000 [6:19:37<12:51:19,  1.71it/s]
Train steps ... :  21%|██        | 20945/100000 [6:19:37<12:50:22,  1.71it/s]
Train steps ... :  21%|██        | 20946/100000 [6:19:38<12:50:03,  1.71it/s]
Train steps ... :  21%|██        | 20947/100000 [6:19:38<12:50:51,  1.71it/s]
Train steps ... :  21%|██        | 20948/100000 [6:19:39<12:50:18,  1.71it/s]
Train steps ... :  21%|██        | 20949/100000 [6:19:39<12:50:02,  1.71it/s]
Train steps ... :  21%|██        | 20950/100000 [6:19:40<12:50:24,  1.71it/s]Step... (20950 / 100000 | Loss: 1.14037024974823, Learning Rate: 7.944723618090453e-05)
+
                                                                             
Step... (20950 / 100000 | Loss: 1.0694669485092163, Learning Rate: 7.944723618090453e-05)
+
Train steps ... :  21%|██        | 20950/100000 [6:19:40<12:50:24,  1.71it/s]
Train steps ... :  21%|██        | 20951/100000 [6:19:41<12:50:34,  1.71it/s]
Train steps ... :  21%|██        | 20952/100000 [6:19:41<12:50:02,  1.71it/s]
Train steps ... :  21%|██        | 20953/100000 [6:19:42<12:51:47,  1.71it/s]
Train steps ... :  21%|██        | 20954/100000 [6:19:42<12:50:23,  1.71it/s]
Train steps ... :  21%|██        | 20955/100000 [6:19:43<12:51:16,  1.71it/s]
Train steps ... :  21%|██        | 20956/100000 [6:19:44<12:50:45,  1.71it/s]
Train steps ... :  21%|██        | 20957/100000 [6:19:44<12:51:39,  1.71it/s]
Train steps ... :  21%|██        | 20958/100000 [6:19:45<12:51:34,  1.71it/s]
Train steps ... :  21%|██        | 20959/100000 [6:19:45<12:50:50,  1.71it/s]
Train steps ... :  21%|██        | 20960/100000 [6:19:46<12:50:43,  1.71it/s]
Train steps ... :  21%|██        | 20961/100000 [6:19:47<12:51:30,  1.71it/s]
Train steps ... :  21%|██        | 20962/100000 [6:19:47<12:53:08,  1.70it/s]
Train steps ... :  21%|██        | 20963/100000 [6:19:48<12:51:31,  1.71it/s]
Train steps ... :  21%|██        | 20964/100000 [6:19:48<12:51:35,  1.71it/s]
Train steps ... :  21%|██        | 20965/100000 [6:19:49<12:50:28,  1.71it/s]
Train steps ... :  21%|██        | 20966/100000 [6:19:49<12:50:10,  1.71it/s]
Train steps ... :  21%|██        | 20967/100000 [6:19:50<12:49:57,  1.71it/s]
Train steps ... :  21%|██        | 20968/100000 [6:19:51<12:51:05,  1.71it/s]
Train steps ... :  21%|██        | 20969/100000 [6:19:51<12:50:14,  1.71it/s]
Train steps ... :  21%|██        | 20970/100000 [6:19:52<12:50:36,  1.71it/s]
Train steps ... :  21%|██        | 20971/100000 [6:19:52<12:50:05,  1.71it/s]
Train steps ... :  21%|██        | 20972/100000 [6:19:53<12:49:52,  1.71it/s]
Train steps ... :  21%|██        | 20973/100000 [6:19:54<12:51:10,  1.71it/s]
Train steps ... :  21%|██        | 20974/100000 [6:19:54<12:52:44,  1.70it/s]
Train steps ... :  21%|██        | 20975/100000 [6:19:55<12:50:02,  1.71it/s]Step... (20975 / 100000 | Loss: 0.9500733613967896, Learning Rate: 7.942211055276382e-05)
+
                                                                             
Step... (20975 / 100000 | Loss: 1.4034066200256348, Learning Rate: 7.942211055276382e-05)
+
Train steps ... :  21%|██        | 20975/100000 [6:19:55<12:50:02,  1.71it/s]
Train steps ... :  21%|██        | 20976/100000 [6:19:55<12:52:27,  1.71it/s]
Train steps ... :  21%|██        | 20977/100000 [6:19:56<12:51:05,  1.71it/s]
Train steps ... :  21%|██        | 20978/100000 [6:19:56<12:52:11,  1.71it/s]
Train steps ... :  21%|██        | 20979/100000 [6:19:57<12:51:30,  1.71it/s]
Train steps ... :  21%|██        | 20980/100000 [6:19:58<12:50:11,  1.71it/s]
Train steps ... :  21%|██        | 20981/100000 [6:19:58<12:51:52,  1.71it/s]
Train steps ... :  21%|██        | 20982/100000 [6:19:59<12:50:27,  1.71it/s]
Train steps ... :  21%|██        | 20983/100000 [6:19:59<12:49:28,  1.71it/s]
Train steps ... :  21%|██        | 20984/100000 [6:20:00<12:50:38,  1.71it/s]
Train steps ... :  21%|██        | 20985/100000 [6:20:01<12:50:15,  1.71it/s]
Train steps ... :  21%|██        | 20986/100000 [6:20:01<12:50:13,  1.71it/s]
Train steps ... :  21%|██        | 20987/100000 [6:20:02<12:50:35,  1.71it/s]
Train steps ... :  21%|██        | 20988/100000 [6:20:02<12:49:30,  1.71it/s]
Train steps ... :  21%|██        | 20989/100000 [6:20:03<12:50:11,  1.71it/s]
Train steps ... :  21%|██        | 20990/100000 [6:20:03<12:50:10,  1.71it/s]
Train steps ... :  21%|██        | 20991/100000 [6:20:04<12:49:04,  1.71it/s]
Train steps ... :  21%|██        | 20992/100000 [6:20:05<12:51:56,  1.71it/s]
Train steps ... :  21%|██        | 20993/100000 [6:20:05<12:50:32,  1.71it/s]
Train steps ... :  21%|██        | 20994/100000 [6:20:06<12:50:15,  1.71it/s]
Train steps ... :  21%|██        | 20995/100000 [6:20:06<12:49:31,  1.71it/s]
Train steps ... :  21%|██        | 20996/100000 [6:20:07<12:51:05,  1.71it/s]
Train steps ... :  21%|██        | 20997/100000 [6:20:08<12:51:06,  1.71it/s]
Train steps ... :  21%|██        | 20998/100000 [6:20:08<12:50:47,  1.71it/s]
Train steps ... :  21%|██        | 20999/100000 [6:20:09<12:51:09,  1.71it/s]
Train steps ... :  21%|██        | 21000/100000 [6:20:09<12:50:56,  1.71it/s]Step... (21000 / 100000 | Loss: 1.0079635381698608, Learning Rate: 7.939698492462313e-05)
+
                                                                             
Step... (21000 / 100000 | Loss: 1.0201412439346313, Learning Rate: 7.939698492462313e-05)
+
Train steps ... :  21%|██        | 21000/100000 [6:20:10<12:50:56,  1.71it/s]
Train steps ... :  21%|██        | 21001/100000 [6:20:10<12:50:08,  1.71it/s]
Train steps ... :  21%|██        | 21002/100000 [6:20:11<12:49:05,  1.71it/s]
Train steps ... :  21%|██        | 21003/100000 [6:20:11<12:50:26,  1.71it/s]
Train steps ... :  21%|██        | 21004/100000 [6:20:12<12:48:29,  1.71it/s]
Train steps ... :  21%|██        | 21005/100000 [6:20:12<12:49:08,  1.71it/s]
Train steps ... :  21%|██        | 21006/100000 [6:20:13<12:49:17,  1.71it/s]
Train steps ... :  21%|██        | 21007/100000 [6:20:13<12:50:11,  1.71it/s]
Train steps ... :  21%|██        | 21008/100000 [6:20:14<12:50:06,  1.71it/s]
Train steps ... :  21%|██        | 21009/100000 [6:20:15<12:49:16,  1.71it/s]
Train steps ... :  21%|██        | 21010/100000 [6:20:15<12:49:47,  1.71it/s]
Train steps ... :  21%|██        | 21011/100000 [6:20:16<12:50:16,  1.71it/s]
Train steps ... :  21%|██        | 21012/100000 [6:20:16<12:49:20,  1.71it/s]
Train steps ... :  21%|██        | 21013/100000 [6:20:17<12:49:42,  1.71it/s]
Train steps ... :  21%|██        | 21014/100000 [6:20:18<12:51:14,  1.71it/s]
Train steps ... :  21%|██        | 21015/100000 [6:20:18<12:52:06,  1.70it/s]
Train steps ... :  21%|██        | 21016/100000 [6:20:19<12:49:58,  1.71it/s]
Train steps ... :  21%|██        | 21017/100000 [6:20:19<12:50:36,  1.71it/s]
Train steps ... :  21%|██        | 21018/100000 [6:20:20<12:50:51,  1.71it/s]
Train steps ... :  21%|██        | 21019/100000 [6:20:20<12:51:12,  1.71it/s]
Train steps ... :  21%|██        | 21020/100000 [6:20:21<12:50:20,  1.71it/s]
Train steps ... :  21%|██        | 21021/100000 [6:20:22<12:52:14,  1.70it/s]
Train steps ... :  21%|██        | 21022/100000 [6:20:22<12:51:01,  1.71it/s]
Train steps ... :  21%|██        | 21023/100000 [6:20:23<12:52:12,  1.70it/s]
Train steps ... :  21%|██        | 21024/100000 [6:20:23<12:53:47,  1.70it/s]
Train steps ... :  21%|██        | 21025/100000 [6:20:24<12:52:06,  1.70it/s]Step... (21025 / 100000 | Loss: 1.2761976718902588, Learning Rate: 7.937185929648242e-05)
+
                                                                             
Step... (21025 / 100000 | Loss: 0.7538670897483826, Learning Rate: 7.937185929648242e-05)
+
Train steps ... :  21%|██        | 21025/100000 [6:20:24<12:52:06,  1.70it/s]
Train steps ... :  21%|██        | 21026/100000 [6:20:25<12:50:32,  1.71it/s]
Train steps ... :  21%|██        | 21027/100000 [6:20:25<12:50:19,  1.71it/s]
Train steps ... :  21%|██        | 21028/100000 [6:20:26<12:50:16,  1.71it/s]
Train steps ... :  21%|██        | 21029/100000 [6:20:26<12:55:19,  1.70it/s]
Train steps ... :  21%|██        | 21030/100000 [6:20:27<12:54:00,  1.70it/s]
Train steps ... :  21%|██        | 21031/100000 [6:20:27<12:51:52,  1.71it/s]
Train steps ... :  21%|██        | 21032/100000 [6:20:28<12:51:17,  1.71it/s]
Train steps ... :  21%|██        | 21033/100000 [6:20:29<12:51:44,  1.71it/s]
Train steps ... :  21%|██        | 21034/100000 [6:20:29<12:50:11,  1.71it/s]
Train steps ... :  21%|██        | 21035/100000 [6:20:30<12:50:18,  1.71it/s]
Train steps ... :  21%|██        | 21036/100000 [6:20:30<12:49:13,  1.71it/s]
Train steps ... :  21%|██        | 21037/100000 [6:20:31<12:49:08,  1.71it/s]
Train steps ... :  21%|██        | 21038/100000 [6:20:32<12:49:17,  1.71it/s]
Train steps ... :  21%|██        | 21039/100000 [6:20:32<12:49:28,  1.71it/s]
Train steps ... :  21%|██        | 21040/100000 [6:20:33<12:49:04,  1.71it/s]
Train steps ... :  21%|██        | 21041/100000 [6:20:33<12:50:12,  1.71it/s]
Train steps ... :  21%|██        | 21042/100000 [6:20:34<12:49:40,  1.71it/s]
Train steps ... :  21%|██        | 21043/100000 [6:20:35<12:49:54,  1.71it/s]
Train steps ... :  21%|██        | 21044/100000 [6:20:35<12:51:01,  1.71it/s]
Train steps ... :  21%|██        | 21045/100000 [6:20:36<12:50:42,  1.71it/s]
Train steps ... :  21%|██        | 21046/100000 [6:20:36<12:51:17,  1.71it/s]
Train steps ... :  21%|██        | 21047/100000 [6:20:37<12:49:14,  1.71it/s]
Train steps ... :  21%|██        | 21048/100000 [6:20:37<12:51:20,  1.71it/s]
Train steps ... :  21%|██        | 21049/100000 [6:20:38<12:48:54,  1.71it/s]
Train steps ... :  21%|██        | 21050/100000 [6:20:39<12:49:40,  1.71it/s]Step... (21050 / 100000 | Loss: 0.7711610794067383, Learning Rate: 7.93467336683417e-05)
+
                                                                             
Step... (21050 / 100000 | Loss: 0.7255771160125732, Learning Rate: 7.93467336683417e-05)
+
Train steps ... :  21%|██        | 21050/100000 [6:20:39<12:49:40,  1.71it/s]
Train steps ... :  21%|██        | 21051/100000 [6:20:39<12:49:30,  1.71it/s]
Train steps ... :  21%|██        | 21052/100000 [6:20:40<12:49:51,  1.71it/s]
Train steps ... :  21%|██        | 21053/100000 [6:20:40<12:49:33,  1.71it/s]
Train steps ... :  21%|██        | 21054/100000 [6:20:41<12:48:49,  1.71it/s]
Train steps ... :  21%|██        | 21055/100000 [6:20:42<12:51:13,  1.71it/s]
Train steps ... :  21%|██        | 21056/100000 [6:20:42<12:49:08,  1.71it/s]
Train steps ... :  21%|██        | 21057/100000 [6:20:43<12:48:58,  1.71it/s]
Train steps ... :  21%|██        | 21058/100000 [6:20:43<12:48:57,  1.71it/s]
Train steps ... :  21%|██        | 21059/100000 [6:20:44<12:48:42,  1.71it/s]
Train steps ... :  21%|██        | 21060/100000 [6:20:44<12:48:41,  1.71it/s]
Train steps ... :  21%|██        | 21061/100000 [6:20:45<12:50:42,  1.71it/s]
Train steps ... :  21%|██        | 21062/100000 [6:20:46<12:49:25,  1.71it/s]
Train steps ... :  21%|██        | 21063/100000 [6:20:46<12:49:49,  1.71it/s]
Train steps ... :  21%|██        | 21064/100000 [6:20:47<12:50:18,  1.71it/s]
Train steps ... :  21%|██        | 21065/100000 [6:20:47<12:49:26,  1.71it/s]
Train steps ... :  21%|██        | 21066/100000 [6:20:48<12:49:27,  1.71it/s]
Train steps ... :  21%|██        | 21067/100000 [6:20:49<12:49:34,  1.71it/s]
Train steps ... :  21%|██        | 21068/100000 [6:20:49<12:49:06,  1.71it/s]
Train steps ... :  21%|██        | 21069/100000 [6:20:50<12:49:10,  1.71it/s]
Train steps ... :  21%|██        | 21070/100000 [6:20:50<12:50:01,  1.71it/s]
Train steps ... :  21%|██        | 21071/100000 [6:20:51<12:49:53,  1.71it/s]
Train steps ... :  21%|██        | 21072/100000 [6:20:51<12:49:51,  1.71it/s]
Train steps ... :  21%|██        | 21073/100000 [6:20:52<12:49:26,  1.71it/s]
Train steps ... :  21%|██        | 21074/100000 [6:20:53<12:49:04,  1.71it/s]
Train steps ... :  21%|██        | 21075/100000 [6:20:53<12:48:31,  1.71it/s]Step... (21075 / 100000 | Loss: 0.8693599700927734, Learning Rate: 7.932160804020102e-05)
+
                                                                             
Step... (21075 / 100000 | Loss: 0.9255092144012451, Learning Rate: 7.932160804020102e-05)
+
Train steps ... :  21%|██        | 21075/100000 [6:20:54<12:48:31,  1.71it/s]
Train steps ... :  21%|██        | 21076/100000 [6:20:54<12:49:12,  1.71it/s]
Train steps ... :  21%|██        | 21077/100000 [6:20:54<12:48:26,  1.71it/s]
Train steps ... :  21%|██        | 21078/100000 [6:20:55<12:48:28,  1.71it/s]
Train steps ... :  21%|██        | 21079/100000 [6:20:56<12:48:12,  1.71it/s]
Train steps ... :  21%|██        | 21080/100000 [6:20:56<12:48:36,  1.71it/s]
Train steps ... :  21%|██        | 21081/100000 [6:20:57<12:49:04,  1.71it/s]
Train steps ... :  21%|██        | 21082/100000 [6:20:57<12:49:21,  1.71it/s]
Train steps ... :  21%|██        | 21083/100000 [6:20:58<12:49:18,  1.71it/s]
Train steps ... :  21%|██        | 21084/100000 [6:20:58<12:49:26,  1.71it/s]
Train steps ... :  21%|██        | 21085/100000 [6:20:59<12:49:49,  1.71it/s]
Train steps ... :  21%|██        | 21086/100000 [6:21:00<12:49:43,  1.71it/s]
Train steps ... :  21%|██        | 21087/100000 [6:21:00<12:49:49,  1.71it/s]
Train steps ... :  21%|██        | 21088/100000 [6:21:01<12:48:42,  1.71it/s]
Train steps ... :  21%|██        | 21089/100000 [6:21:01<12:48:12,  1.71it/s]
Train steps ... :  21%|██        | 21090/100000 [6:21:02<12:48:59,  1.71it/s]
Train steps ... :  21%|██        | 21091/100000 [6:21:03<12:48:30,  1.71it/s]
Train steps ... :  21%|██        | 21092/100000 [6:21:03<12:49:07,  1.71it/s]
Train steps ... :  21%|██        | 21093/100000 [6:21:04<12:48:46,  1.71it/s]
Train steps ... :  21%|██        | 21094/100000 [6:21:04<12:48:19,  1.71it/s]
Train steps ... :  21%|██        | 21095/100000 [6:21:05<12:48:11,  1.71it/s]
Train steps ... :  21%|██        | 21096/100000 [6:21:06<12:48:09,  1.71it/s]
Train steps ... :  21%|██        | 21097/100000 [6:21:06<12:48:14,  1.71it/s]
Train steps ... :  21%|██        | 21098/100000 [6:21:07<12:48:16,  1.71it/s]
Train steps ... :  21%|██        | 21099/100000 [6:21:07<12:48:51,  1.71it/s]
Train steps ... :  21%|██        | 21100/100000 [6:21:08<12:48:33,  1.71it/s]Step... (21100 / 100000 | Loss: 0.8187243342399597, Learning Rate: 7.92964824120603e-05)
+
                                                                             
Step... (21100 / 100000 | Loss: 1.0847673416137695, Learning Rate: 7.92964824120603e-05)
+
Train steps ... :  21%|██        | 21100/100000 [6:21:08<12:48:33,  1.71it/s]
Train steps ... :  21%|██        | 21101/100000 [6:21:08<12:49:11,  1.71it/s]
Train steps ... :  21%|██        | 21102/100000 [6:21:09<12:48:58,  1.71it/s]
Train steps ... :  21%|██        | 21103/100000 [6:21:10<12:49:14,  1.71it/s]
Train steps ... :  21%|██        | 21104/100000 [6:21:10<12:48:56,  1.71it/s]
Train steps ... :  21%|██        | 21105/100000 [6:21:11<12:48:55,  1.71it/s]
Train steps ... :  21%|██        | 21106/100000 [6:21:11<12:49:05,  1.71it/s]
Train steps ... :  21%|██        | 21107/100000 [6:21:12<12:48:45,  1.71it/s]
Train steps ... :  21%|██        | 21108/100000 [6:21:13<12:49:18,  1.71it/s]
Train steps ... :  21%|██        | 21109/100000 [6:21:13<12:48:36,  1.71it/s]
Train steps ... :  21%|██        | 21110/100000 [6:21:14<12:49:18,  1.71it/s]
Train steps ... :  21%|██        | 21111/100000 [6:21:14<12:48:40,  1.71it/s]
Train steps ... :  21%|██        | 21112/100000 [6:21:15<12:48:52,  1.71it/s]
Train steps ... :  21%|██        | 21113/100000 [6:21:15<12:48:44,  1.71it/s]
Train steps ... :  21%|██        | 21114/100000 [6:21:16<12:50:07,  1.71it/s]
Train steps ... :  21%|██        | 21115/100000 [6:21:17<12:49:15,  1.71it/s]
Train steps ... :  21%|██        | 21116/100000 [6:21:17<12:47:39,  1.71it/s]
Train steps ... :  21%|██        | 21117/100000 [6:21:18<12:50:48,  1.71it/s]
Train steps ... :  21%|██        | 21118/100000 [6:21:18<12:48:15,  1.71it/s]
Train steps ... :  21%|██        | 21119/100000 [6:21:19<12:48:00,  1.71it/s]
Train steps ... :  21%|██        | 21120/100000 [6:21:20<12:48:52,  1.71it/s]
Train steps ... :  21%|██        | 21121/100000 [6:21:20<12:48:35,  1.71it/s]
Train steps ... :  21%|██        | 21122/100000 [6:21:21<12:47:57,  1.71it/s]
Train steps ... :  21%|██        | 21123/100000 [6:21:21<12:48:26,  1.71it/s]
Train steps ... :  21%|██        | 21124/100000 [6:21:22<12:48:55,  1.71it/s]
Train steps ... :  21%|██        | 21125/100000 [6:21:22<12:48:24,  1.71it/s]Step... (21125 / 100000 | Loss: 0.9107370376586914, Learning Rate: 7.927135678391961e-05)
+
                                                                             
Step... (21125 / 100000 | Loss: 0.7646253705024719, Learning Rate: 7.927135678391961e-05)
+
Train steps ... :  21%|██        | 21125/100000 [6:21:23<12:48:24,  1.71it/s]
Train steps ... :  21%|██        | 21126/100000 [6:21:23<12:48:50,  1.71it/s]
Train steps ... :  21%|██        | 21127/100000 [6:21:24<12:48:43,  1.71it/s]
Train steps ... :  21%|██        | 21128/100000 [6:21:24<12:47:50,  1.71it/s]
Train steps ... :  21%|██        | 21129/100000 [6:21:25<12:47:55,  1.71it/s]
Train steps ... :  21%|██        | 21130/100000 [6:21:25<12:47:57,  1.71it/s]
Train steps ... :  21%|██        | 21131/100000 [6:21:26<12:47:58,  1.71it/s]
Train steps ... :  21%|██        | 21132/100000 [6:21:27<12:49:14,  1.71it/s]
Train steps ... :  21%|██        | 21133/100000 [6:21:27<12:47:34,  1.71it/s]
Train steps ... :  21%|██        | 21134/100000 [6:21:28<12:47:52,  1.71it/s]
Train steps ... :  21%|██        | 21135/100000 [6:21:28<12:47:30,  1.71it/s]
Train steps ... :  21%|██        | 21136/100000 [6:21:29<12:47:43,  1.71it/s]
Train steps ... :  21%|██        | 21137/100000 [6:21:29<12:48:30,  1.71it/s]
Train steps ... :  21%|██        | 21138/100000 [6:21:30<12:49:29,  1.71it/s]
Train steps ... :  21%|██        | 21139/100000 [6:21:31<12:49:28,  1.71it/s]
Train steps ... :  21%|██        | 21140/100000 [6:21:31<12:49:06,  1.71it/s]
Train steps ... :  21%|██        | 21141/100000 [6:21:32<12:48:31,  1.71it/s]
Train steps ... :  21%|██        | 21142/100000 [6:21:32<12:48:56,  1.71it/s]
Train steps ... :  21%|██        | 21143/100000 [6:21:33<12:48:07,  1.71it/s]
Train steps ... :  21%|██        | 21144/100000 [6:21:34<12:47:49,  1.71it/s]
Train steps ... :  21%|██        | 21145/100000 [6:21:34<12:47:54,  1.71it/s]
Train steps ... :  21%|██        | 21146/100000 [6:21:35<12:48:58,  1.71it/s]
Train steps ... :  21%|██        | 21147/100000 [6:21:35<12:47:35,  1.71it/s]
Train steps ... :  21%|██        | 21148/100000 [6:21:36<12:47:55,  1.71it/s]
Train steps ... :  21%|██        | 21149/100000 [6:21:36<12:48:11,  1.71it/s]
Train steps ... :  21%|██        | 21150/100000 [6:21:37<12:48:21,  1.71it/s]Step... (21150 / 100000 | Loss: 1.0583215951919556, Learning Rate: 7.924623115577889e-05)
+
                                                                             
Step... (21150 / 100000 | Loss: 0.8947384357452393, Learning Rate: 7.924623115577889e-05)
+
Train steps ... :  21%|██        | 21150/100000 [6:21:37<12:48:21,  1.71it/s]
Train steps ... :  21%|██        | 21151/100000 [6:21:38<12:49:05,  1.71it/s]
Train steps ... :  21%|██        | 21152/100000 [6:21:38<12:48:12,  1.71it/s]
Train steps ... :  21%|██        | 21153/100000 [6:21:39<12:48:52,  1.71it/s]
Train steps ... :  21%|██        | 21154/100000 [6:21:39<12:49:03,  1.71it/s]
Train steps ... :  21%|██        | 21155/100000 [6:21:40<12:49:07,  1.71it/s]
Train steps ... :  21%|██        | 21156/100000 [6:21:41<12:48:51,  1.71it/s]
Train steps ... :  21%|██        | 21157/100000 [6:21:41<12:48:12,  1.71it/s]
Train steps ... :  21%|██        | 21158/100000 [6:21:42<12:48:19,  1.71it/s]
Train steps ... :  21%|██        | 21159/100000 [6:21:42<12:47:59,  1.71it/s]
Train steps ... :  21%|██        | 21160/100000 [6:21:43<12:48:26,  1.71it/s]
Train steps ... :  21%|██        | 21161/100000 [6:21:44<12:48:35,  1.71it/s]
Train steps ... :  21%|██        | 21162/100000 [6:21:44<12:49:36,  1.71it/s]
Train steps ... :  21%|██        | 21163/100000 [6:21:45<12:49:31,  1.71it/s]
Train steps ... :  21%|██        | 21164/100000 [6:21:45<12:48:47,  1.71it/s]
Train steps ... :  21%|██        | 21165/100000 [6:21:46<12:48:16,  1.71it/s]
Train steps ... :  21%|██        | 21166/100000 [6:21:46<12:49:14,  1.71it/s]
Train steps ... :  21%|██        | 21167/100000 [6:21:47<12:48:35,  1.71it/s]
Train steps ... :  21%|██        | 21168/100000 [6:21:48<12:48:53,  1.71it/s]
Train steps ... :  21%|██        | 21169/100000 [6:21:48<12:48:11,  1.71it/s]
Train steps ... :  21%|██        | 21170/100000 [6:21:49<12:48:25,  1.71it/s]
Train steps ... :  21%|██        | 21171/100000 [6:21:49<12:49:06,  1.71it/s]
Train steps ... :  21%|██        | 21172/100000 [6:21:50<12:49:23,  1.71it/s]
Train steps ... :  21%|██        | 21173/100000 [6:21:51<12:48:20,  1.71it/s]
Train steps ... :  21%|██        | 21174/100000 [6:21:51<12:47:57,  1.71it/s]
Train steps ... :  21%|██        | 21175/100000 [6:21:52<12:47:41,  1.71it/s]Step... (21175 / 100000 | Loss: 1.213146686553955, Learning Rate: 7.92211055276382e-05)
+
                                                                             
Step... (21175 / 100000 | Loss: 0.7648752927780151, Learning Rate: 7.92211055276382e-05)
+
Train steps ... :  21%|██        | 21175/100000 [6:21:52<12:47:41,  1.71it/s]
Train steps ... :  21%|██        | 21176/100000 [6:21:52<12:47:54,  1.71it/s]
Train steps ... :  21%|██        | 21177/100000 [6:21:53<12:47:16,  1.71it/s]
Train steps ... :  21%|██        | 21178/100000 [6:21:53<12:47:34,  1.71it/s]
Train steps ... :  21%|██        | 21179/100000 [6:21:54<12:47:29,  1.71it/s]
Train steps ... :  21%|██        | 21180/100000 [6:21:55<12:47:24,  1.71it/s]
Train steps ... :  21%|██        | 21181/100000 [6:21:55<12:49:07,  1.71it/s]
Train steps ... :  21%|██        | 21182/100000 [6:21:56<12:48:31,  1.71it/s]
Train steps ... :  21%|██        | 21183/100000 [6:21:56<12:48:24,  1.71it/s]
Train steps ... :  21%|██        | 21184/100000 [6:21:57<12:48:37,  1.71it/s]
Train steps ... :  21%|██        | 21185/100000 [6:21:58<12:48:11,  1.71it/s]
Train steps ... :  21%|██        | 21186/100000 [6:21:58<12:48:37,  1.71it/s]
Train steps ... :  21%|██        | 21187/100000 [6:21:59<12:48:05,  1.71it/s]
Train steps ... :  21%|██        | 21188/100000 [6:21:59<12:48:39,  1.71it/s]
Train steps ... :  21%|██        | 21189/100000 [6:22:00<12:48:01,  1.71it/s]
Train steps ... :  21%|██        | 21190/100000 [6:22:00<12:48:11,  1.71it/s]
Train steps ... :  21%|██        | 21191/100000 [6:22:01<12:48:30,  1.71it/s]
Train steps ... :  21%|██        | 21192/100000 [6:22:02<12:48:40,  1.71it/s]
Train steps ... :  21%|██        | 21193/100000 [6:22:02<12:48:53,  1.71it/s]
Train steps ... :  21%|██        | 21194/100000 [6:22:03<12:47:52,  1.71it/s]
Train steps ... :  21%|██        | 21195/100000 [6:22:03<12:51:01,  1.70it/s]
Train steps ... :  21%|██        | 21196/100000 [6:22:04<12:50:36,  1.70it/s]
Train steps ... :  21%|██        | 21197/100000 [6:22:05<12:49:10,  1.71it/s]
Train steps ... :  21%|██        | 21198/100000 [6:22:05<12:48:31,  1.71it/s]
Train steps ... :  21%|██        | 21199/100000 [6:22:06<12:48:46,  1.71it/s]
Train steps ... :  21%|██        | 21200/100000 [6:22:06<12:48:09,  1.71it/s]Step... (21200 / 100000 | Loss: 0.9236801266670227, Learning Rate: 7.91959798994975e-05)
+
                                                                             
Step... (21200 / 100000 | Loss: 1.203514814376831, Learning Rate: 7.91959798994975e-05)
+
Train steps ... :  21%|██        | 21200/100000 [6:22:07<12:48:09,  1.71it/s]
Train steps ... :  21%|██        | 21201/100000 [6:22:07<12:48:39,  1.71it/s]
Train steps ... :  21%|██        | 21202/100000 [6:22:08<12:48:20,  1.71it/s]
Train steps ... :  21%|██        | 21203/100000 [6:22:08<12:48:20,  1.71it/s]
Train steps ... :  21%|██        | 21204/100000 [6:22:09<12:48:14,  1.71it/s]
Train steps ... :  21%|██        | 21205/100000 [6:22:09<12:48:15,  1.71it/s]
Train steps ... :  21%|██        | 21206/100000 [6:22:10<12:48:06,  1.71it/s]
Train steps ... :  21%|██        | 21207/100000 [6:22:10<12:48:00,  1.71it/s]
Train steps ... :  21%|██        | 21208/100000 [6:22:11<12:48:38,  1.71it/s]
Train steps ... :  21%|██        | 21209/100000 [6:22:12<12:48:17,  1.71it/s]
Train steps ... :  21%|██        | 21210/100000 [6:22:12<12:49:24,  1.71it/s]
Train steps ... :  21%|██        | 21211/100000 [6:22:13<12:49:04,  1.71it/s]
Train steps ... :  21%|██        | 21212/100000 [6:22:13<12:48:03,  1.71it/s]
Train steps ... :  21%|██        | 21213/100000 [6:22:14<12:47:25,  1.71it/s]
Train steps ... :  21%|██        | 21214/100000 [6:22:15<12:47:02,  1.71it/s]
Train steps ... :  21%|██        | 21215/100000 [6:22:15<12:47:34,  1.71it/s]
Train steps ... :  21%|██        | 21216/100000 [6:22:16<12:47:47,  1.71it/s]
Train steps ... :  21%|██        | 21217/100000 [6:22:16<12:47:54,  1.71it/s]
Train steps ... :  21%|██        | 21218/100000 [6:22:17<12:48:22,  1.71it/s]
Train steps ... :  21%|██        | 21219/100000 [6:22:17<12:48:30,  1.71it/s]
Train steps ... :  21%|██        | 21220/100000 [6:22:18<12:47:37,  1.71it/s]
Train steps ... :  21%|██        | 21221/100000 [6:22:19<12:48:24,  1.71it/s]
Train steps ... :  21%|██        | 21222/100000 [6:22:19<12:48:11,  1.71it/s]
Train steps ... :  21%|██        | 21223/100000 [6:22:20<12:49:03,  1.71it/s]
Train steps ... :  21%|██        | 21224/100000 [6:22:20<12:47:57,  1.71it/s]
Train steps ... :  21%|██        | 21225/100000 [6:22:21<12:47:44,  1.71it/s]Step... (21225 / 100000 | Loss: 0.9889585375785828, Learning Rate: 7.917085427135678e-05)
+
                                                                             
Step... (21225 / 100000 | Loss: 1.005425214767456, Learning Rate: 7.917085427135678e-05)
+
Train steps ... :  21%|██        | 21225/100000 [6:22:21<12:47:44,  1.71it/s]
Train steps ... :  21%|██        | 21226/100000 [6:22:22<12:47:42,  1.71it/s]
Train steps ... :  21%|██        | 21227/100000 [6:22:22<12:47:10,  1.71it/s]
Train steps ... :  21%|██        | 21228/100000 [6:22:23<12:47:13,  1.71it/s]
Train steps ... :  21%|██        | 21229/100000 [6:22:23<12:47:56,  1.71it/s]
Train steps ... :  21%|██        | 21230/100000 [6:22:24<12:47:42,  1.71it/s]
Train steps ... :  21%|██        | 21231/100000 [6:22:24<12:48:36,  1.71it/s]
Train steps ... :  21%|██        | 21232/100000 [6:22:25<12:48:46,  1.71it/s]
Train steps ... :  21%|██        | 21233/100000 [6:22:26<12:48:05,  1.71it/s]
Train steps ... :  21%|██        | 21234/100000 [6:22:26<12:47:46,  1.71it/s]
Train steps ... :  21%|██        | 21235/100000 [6:22:27<12:48:26,  1.71it/s]
Train steps ... :  21%|██        | 21236/100000 [6:22:27<12:48:26,  1.71it/s]
Train steps ... :  21%|██        | 21237/100000 [6:22:28<12:48:10,  1.71it/s]
Train steps ... :  21%|██        | 21238/100000 [6:22:29<12:47:43,  1.71it/s]
Train steps ... :  21%|██        | 21239/100000 [6:22:29<12:47:02,  1.71it/s]
Train steps ... :  21%|██        | 21240/100000 [6:22:30<12:47:00,  1.71it/s]
Train steps ... :  21%|██        | 21241/100000 [6:22:30<12:47:18,  1.71it/s]
Train steps ... :  21%|██        | 21242/100000 [6:22:31<12:48:05,  1.71it/s]
Train steps ... :  21%|██        | 21243/100000 [6:22:31<12:49:04,  1.71it/s]
Train steps ... :  21%|██        | 21244/100000 [6:22:32<12:47:25,  1.71it/s]
Train steps ... :  21%|██        | 21245/100000 [6:22:33<12:46:50,  1.71it/s]
Train steps ... :  21%|██        | 21246/100000 [6:22:33<12:47:26,  1.71it/s]
Train steps ... :  21%|██        | 21247/100000 [6:22:34<12:47:14,  1.71it/s]
Train steps ... :  21%|██        | 21248/100000 [6:22:34<12:48:41,  1.71it/s]
Train steps ... :  21%|██        | 21249/100000 [6:22:35<12:48:20,  1.71it/s]
Train steps ... :  21%|██▏       | 21250/100000 [6:22:36<12:47:25,  1.71it/s]Step... (21250 / 100000 | Loss: 0.9959968328475952, Learning Rate: 7.914572864321609e-05)
+
                                                                             
Step... (21250 / 100000 | Loss: 1.104618787765503, Learning Rate: 7.914572864321609e-05)
+
Train steps ... :  21%|██▏       | 21250/100000 [6:22:36<12:47:25,  1.71it/s]
Train steps ... :  21%|██▏       | 21251/100000 [6:22:36<12:47:18,  1.71it/s]
Train steps ... :  21%|██▏       | 21252/100000 [6:22:37<12:47:50,  1.71it/s]
Train steps ... :  21%|██▏       | 21253/100000 [6:22:37<12:47:33,  1.71it/s]
Train steps ... :  21%|██▏       | 21254/100000 [6:22:38<12:47:38,  1.71it/s]
Train steps ... :  21%|██▏       | 21255/100000 [6:22:39<12:47:04,  1.71it/s]
Train steps ... :  21%|██▏       | 21256/100000 [6:22:39<12:47:37,  1.71it/s]
Train steps ... :  21%|██▏       | 21257/100000 [6:22:40<12:47:51,  1.71it/s]
Train steps ... :  21%|██▏       | 21258/100000 [6:22:40<12:47:21,  1.71it/s]
Train steps ... :  21%|██▏       | 21259/100000 [6:22:41<12:47:43,  1.71it/s]
Train steps ... :  21%|██▏       | 21260/100000 [6:22:41<12:47:33,  1.71it/s]
Train steps ... :  21%|██▏       | 21261/100000 [6:22:42<12:47:53,  1.71it/s]
Train steps ... :  21%|██▏       | 21262/100000 [6:22:43<12:49:31,  1.71it/s]
Train steps ... :  21%|██▏       | 21263/100000 [6:22:43<12:47:38,  1.71it/s]
Train steps ... :  21%|██▏       | 21264/100000 [6:22:44<12:47:50,  1.71it/s]
Train steps ... :  21%|██▏       | 21265/100000 [6:22:44<12:47:43,  1.71it/s]
Train steps ... :  21%|██▏       | 21266/100000 [6:22:45<12:47:23,  1.71it/s]
Train steps ... :  21%|██▏       | 21267/100000 [6:22:46<12:47:22,  1.71it/s]
Train steps ... :  21%|██▏       | 21268/100000 [6:22:46<12:47:51,  1.71it/s]
Train steps ... :  21%|██▏       | 21269/100000 [6:22:47<12:47:39,  1.71it/s]
Train steps ... :  21%|██▏       | 21270/100000 [6:22:47<12:47:46,  1.71it/s]
Train steps ... :  21%|██▏       | 21271/100000 [6:22:48<12:47:45,  1.71it/s]
Train steps ... :  21%|██▏       | 21272/100000 [6:22:48<12:48:40,  1.71it/s]
Train steps ... :  21%|██▏       | 21273/100000 [6:22:49<12:48:55,  1.71it/s]
Train steps ... :  21%|██▏       | 21274/100000 [6:22:50<12:48:08,  1.71it/s]
Train steps ... :  21%|██▏       | 21275/100000 [6:22:50<12:47:44,  1.71it/s]Step... (21275 / 100000 | Loss: 1.050773024559021, Learning Rate: 7.912060301507537e-05)
+
                                                                             
Step... (21275 / 100000 | Loss: 1.1080085039138794, Learning Rate: 7.912060301507537e-05)
+
Train steps ... :  21%|██▏       | 21275/100000 [6:22:51<12:47:44,  1.71it/s]
Train steps ... :  21%|██▏       | 21276/100000 [6:22:51<12:49:25,  1.71it/s]
Train steps ... :  21%|██▏       | 21277/100000 [6:22:51<12:48:14,  1.71it/s]
Train steps ... :  21%|██▏       | 21278/100000 [6:22:52<12:48:26,  1.71it/s]
Train steps ... :  21%|██▏       | 21279/100000 [6:22:53<12:47:52,  1.71it/s]
Train steps ... :  21%|██▏       | 21280/100000 [6:22:53<12:47:55,  1.71it/s]
Train steps ... :  21%|██▏       | 21281/100000 [6:22:54<12:47:00,  1.71it/s]
Train steps ... :  21%|██▏       | 21282/100000 [6:22:54<12:46:51,  1.71it/s]
Train steps ... :  21%|██▏       | 21283/100000 [6:22:55<12:47:08,  1.71it/s]
Train steps ... :  21%|██▏       | 21284/100000 [6:22:55<12:46:41,  1.71it/s]
Train steps ... :  21%|██▏       | 21285/100000 [6:22:56<12:47:46,  1.71it/s]
Train steps ... :  21%|██▏       | 21286/100000 [6:22:57<12:47:05,  1.71it/s]
Train steps ... :  21%|██▏       | 21287/100000 [6:22:57<12:47:37,  1.71it/s]
Train steps ... :  21%|██▏       | 21288/100000 [6:22:58<12:47:29,  1.71it/s]
Train steps ... :  21%|██▏       | 21289/100000 [6:22:58<12:46:56,  1.71it/s]
Train steps ... :  21%|██▏       | 21290/100000 [6:22:59<12:46:54,  1.71it/s]
Train steps ... :  21%|██▏       | 21291/100000 [6:23:00<12:46:44,  1.71it/s]
Train steps ... :  21%|██▏       | 21292/100000 [6:23:00<12:46:43,  1.71it/s]
Train steps ... :  21%|██▏       | 21293/100000 [6:23:01<12:48:03,  1.71it/s]
Train steps ... :  21%|██▏       | 21294/100000 [6:23:01<12:48:45,  1.71it/s]
Train steps ... :  21%|██▏       | 21295/100000 [6:23:02<12:47:25,  1.71it/s]
Train steps ... :  21%|██▏       | 21296/100000 [6:23:02<12:47:31,  1.71it/s]
Train steps ... :  21%|██▏       | 21297/100000 [6:23:03<12:47:02,  1.71it/s]
Train steps ... :  21%|██▏       | 21298/100000 [6:23:04<12:47:12,  1.71it/s]
Train steps ... :  21%|██▏       | 21299/100000 [6:23:04<12:46:54,  1.71it/s]
Train steps ... :  21%|██▏       | 21300/100000 [6:23:05<12:46:03,  1.71it/s]Step... (21300 / 100000 | Loss: 1.2278459072113037, Learning Rate: 7.909547738693468e-05)
+
                                                                             
Step... (21300 / 100000 | Loss: 1.1781576871871948, Learning Rate: 7.909547738693468e-05)
+
Train steps ... :  21%|██▏       | 21300/100000 [6:23:05<12:46:03,  1.71it/s]
Train steps ... :  21%|██▏       | 21301/100000 [6:23:05<12:46:30,  1.71it/s]
Train steps ... :  21%|██▏       | 21302/100000 [6:23:06<12:46:10,  1.71it/s]
Train steps ... :  21%|██▏       | 21303/100000 [6:23:07<12:46:13,  1.71it/s]
Train steps ... :  21%|██▏       | 21304/100000 [6:23:07<12:46:26,  1.71it/s]
Train steps ... :  21%|██▏       | 21305/100000 [6:23:08<12:46:13,  1.71it/s]
Train steps ... :  21%|██▏       | 21306/100000 [6:23:08<12:45:59,  1.71it/s]
Train steps ... :  21%|██▏       | 21307/100000 [6:23:09<12:46:33,  1.71it/s]
Train steps ... :  21%|██▏       | 21308/100000 [6:23:10<12:46:32,  1.71it/s]
Train steps ... :  21%|██▏       | 21309/100000 [6:23:10<12:47:00,  1.71it/s]
Train steps ... :  21%|██▏       | 21310/100000 [6:23:11<12:47:36,  1.71it/s]
Train steps ... :  21%|██▏       | 21311/100000 [6:23:11<12:46:43,  1.71it/s]
Train steps ... :  21%|██▏       | 21312/100000 [6:23:12<12:47:13,  1.71it/s]
Train steps ... :  21%|██▏       | 21313/100000 [6:23:12<12:46:22,  1.71it/s]
Train steps ... :  21%|██▏       | 21314/100000 [6:23:13<12:47:11,  1.71it/s]
Train steps ... :  21%|██▏       | 21315/100000 [6:23:14<12:46:32,  1.71it/s]
Train steps ... :  21%|██▏       | 21316/100000 [6:23:14<12:46:12,  1.71it/s]
Train steps ... :  21%|██▏       | 21317/100000 [6:23:15<12:46:00,  1.71it/s]
Train steps ... :  21%|██▏       | 21318/100000 [6:23:15<12:45:55,  1.71it/s]
Train steps ... :  21%|██▏       | 21319/100000 [6:23:16<12:46:09,  1.71it/s]
Train steps ... :  21%|██▏       | 21320/100000 [6:23:17<12:46:59,  1.71it/s]
Train steps ... :  21%|██▏       | 21321/100000 [6:23:17<12:46:09,  1.71it/s]
Train steps ... :  21%|██▏       | 21322/100000 [6:23:18<12:46:15,  1.71it/s]
Train steps ... :  21%|██▏       | 21323/100000 [6:23:18<12:47:22,  1.71it/s]
Train steps ... :  21%|██▏       | 21324/100000 [6:23:19<12:47:01,  1.71it/s]
Train steps ... :  21%|██▏       | 21325/100000 [6:23:19<12:46:17,  1.71it/s]Step... (21325 / 100000 | Loss: 1.1211042404174805, Learning Rate: 7.907035175879397e-05)
+
                                                                             
Step... (21325 / 100000 | Loss: 0.8838163614273071, Learning Rate: 7.907035175879397e-05)
+
Train steps ... :  21%|██▏       | 21325/100000 [6:23:20<12:46:17,  1.71it/s]
Train steps ... :  21%|██▏       | 21326/100000 [6:23:20<12:46:28,  1.71it/s]
Train steps ... :  21%|██▏       | 21327/100000 [6:23:21<12:45:32,  1.71it/s]
Train steps ... :  21%|██▏       | 21328/100000 [6:23:21<12:45:40,  1.71it/s]
Train steps ... :  21%|██▏       | 21329/100000 [6:23:22<12:46:12,  1.71it/s]
Train steps ... :  21%|██▏       | 21330/100000 [6:23:22<12:45:41,  1.71it/s]
Train steps ... :  21%|██▏       | 21331/100000 [6:23:23<12:46:29,  1.71it/s]
Train steps ... :  21%|██▏       | 21332/100000 [6:23:24<12:46:16,  1.71it/s]
Train steps ... :  21%|██▏       | 21333/100000 [6:23:24<12:46:49,  1.71it/s]
Train steps ... :  21%|██▏       | 21334/100000 [6:23:25<12:46:18,  1.71it/s]
Train steps ... :  21%|██▏       | 21335/100000 [6:23:25<12:46:06,  1.71it/s]
Train steps ... :  21%|██▏       | 21336/100000 [6:23:26<12:47:17,  1.71it/s]
Train steps ... :  21%|██▏       | 21337/100000 [6:23:26<12:46:11,  1.71it/s]
Train steps ... :  21%|██▏       | 21338/100000 [6:23:27<12:45:34,  1.71it/s]
Train steps ... :  21%|██▏       | 21339/100000 [6:23:28<12:45:38,  1.71it/s]
Train steps ... :  21%|██▏       | 21340/100000 [6:23:28<12:45:42,  1.71it/s]
Train steps ... :  21%|██▏       | 21341/100000 [6:23:29<12:46:49,  1.71it/s]
Train steps ... :  21%|██▏       | 21342/100000 [6:23:29<12:45:55,  1.71it/s]
Train steps ... :  21%|██▏       | 21343/100000 [6:23:30<12:46:21,  1.71it/s]
Train steps ... :  21%|██▏       | 21344/100000 [6:23:31<12:46:20,  1.71it/s]
Train steps ... :  21%|██▏       | 21345/100000 [6:23:31<12:46:37,  1.71it/s]
Train steps ... :  21%|██▏       | 21346/100000 [6:23:32<12:47:25,  1.71it/s]
Train steps ... :  21%|██▏       | 21347/100000 [6:23:32<12:47:16,  1.71it/s]
Train steps ... :  21%|██▏       | 21348/100000 [6:23:33<12:46:46,  1.71it/s]
Train steps ... :  21%|██▏       | 21349/100000 [6:23:33<12:46:44,  1.71it/s]
Train steps ... :  21%|██▏       | 21350/100000 [6:23:34<12:46:08,  1.71it/s]Step... (21350 / 100000 | Loss: 0.8816248178482056, Learning Rate: 7.904522613065328e-05)
+
                                                                             
Step... (21350 / 100000 | Loss: 1.1502740383148193, Learning Rate: 7.904522613065328e-05)
+
Train steps ... :  21%|██▏       | 21350/100000 [6:23:34<12:46:08,  1.71it/s]
Train steps ... :  21%|██▏       | 21351/100000 [6:23:35<12:46:11,  1.71it/s]
Train steps ... :  21%|██▏       | 21352/100000 [6:23:35<12:46:00,  1.71it/s]
Train steps ... :  21%|██▏       | 21353/100000 [6:23:36<12:46:36,  1.71it/s]
Train steps ... :  21%|██▏       | 21354/100000 [6:23:36<12:47:36,  1.71it/s]
Train steps ... :  21%|██▏       | 21355/100000 [6:23:37<12:47:31,  1.71it/s]
Train steps ... :  21%|██▏       | 21356/100000 [6:23:38<12:46:53,  1.71it/s]
Train steps ... :  21%|██▏       | 21357/100000 [6:23:38<12:46:56,  1.71it/s]
Train steps ... :  21%|██▏       | 21358/100000 [6:23:39<12:47:13,  1.71it/s]
Train steps ... :  21%|██▏       | 21359/100000 [6:23:39<12:47:58,  1.71it/s]
Train steps ... :  21%|██▏       | 21360/100000 [6:23:40<12:47:52,  1.71it/s]
Train steps ... :  21%|██▏       | 21361/100000 [6:23:41<12:48:24,  1.71it/s]
Train steps ... :  21%|██▏       | 21362/100000 [6:23:41<12:49:35,  1.70it/s]
Train steps ... :  21%|██▏       | 21363/100000 [6:23:42<12:49:58,  1.70it/s]
Train steps ... :  21%|██▏       | 21364/100000 [6:23:42<12:48:25,  1.71it/s]
Train steps ... :  21%|██▏       | 21365/100000 [6:23:43<12:49:27,  1.70it/s]
Train steps ... :  21%|██▏       | 21366/100000 [6:23:43<12:48:09,  1.71it/s]
Train steps ... :  21%|██▏       | 21367/100000 [6:23:44<12:47:30,  1.71it/s]
Train steps ... :  21%|██▏       | 21368/100000 [6:23:45<12:48:01,  1.71it/s]
Train steps ... :  21%|██▏       | 21369/100000 [6:23:45<12:47:41,  1.71it/s]
Train steps ... :  21%|██▏       | 21370/100000 [6:23:46<12:47:33,  1.71it/s]
Train steps ... :  21%|██▏       | 21371/100000 [6:23:46<12:47:59,  1.71it/s]
Train steps ... :  21%|██▏       | 21372/100000 [6:23:47<12:48:47,  1.70it/s]
Train steps ... :  21%|██▏       | 21373/100000 [6:23:48<12:48:53,  1.70it/s]
Train steps ... :  21%|██▏       | 21374/100000 [6:23:48<12:48:27,  1.71it/s]
Train steps ... :  21%|██▏       | 21375/100000 [6:23:49<12:48:00,  1.71it/s]Step... (21375 / 100000 | Loss: 1.0780339241027832, Learning Rate: 7.902010050251256e-05)
+
                                                                             
Step... (21375 / 100000 | Loss: 1.1168043613433838, Learning Rate: 7.902010050251256e-05)
+
Train steps ... :  21%|██▏       | 21375/100000 [6:23:49<12:48:00,  1.71it/s]
Train steps ... :  21%|██▏       | 21376/100000 [6:23:49<12:48:35,  1.70it/s]
Train steps ... :  21%|██▏       | 21377/100000 [6:23:50<12:48:05,  1.71it/s]
Train steps ... :  21%|██▏       | 21378/100000 [6:23:50<12:47:54,  1.71it/s]
Train steps ... :  21%|██▏       | 21379/100000 [6:23:51<12:49:30,  1.70it/s]
Train steps ... :  21%|██▏       | 21380/100000 [6:23:52<12:48:26,  1.71it/s]
Train steps ... :  21%|██▏       | 21381/100000 [6:23:52<12:48:32,  1.70it/s]
Train steps ... :  21%|██▏       | 21382/100000 [6:23:53<12:48:00,  1.71it/s]
Train steps ... :  21%|██▏       | 21383/100000 [6:23:53<12:48:06,  1.71it/s]
Train steps ... :  21%|██▏       | 21384/100000 [6:23:54<12:48:22,  1.71it/s]
Train steps ... :  21%|██▏       | 21385/100000 [6:23:55<12:48:41,  1.70it/s]
Train steps ... :  21%|██▏       | 21386/100000 [6:23:55<12:49:22,  1.70it/s]
Train steps ... :  21%|██▏       | 21387/100000 [6:23:56<12:48:20,  1.71it/s]
Train steps ... :  21%|██▏       | 21388/100000 [6:23:56<12:49:27,  1.70it/s]
Train steps ... :  21%|██▏       | 21389/100000 [6:23:57<12:49:39,  1.70it/s]
Train steps ... :  21%|██▏       | 21390/100000 [6:23:58<12:49:41,  1.70it/s]
Train steps ... :  21%|██▏       | 21391/100000 [6:23:58<12:49:16,  1.70it/s]
Train steps ... :  21%|██▏       | 21392/100000 [6:23:59<12:49:02,  1.70it/s]
Train steps ... :  21%|██▏       | 21393/100000 [6:23:59<12:48:17,  1.71it/s]
Train steps ... :  21%|██▏       | 21394/100000 [6:24:00<12:47:20,  1.71it/s]
Train steps ... :  21%|██▏       | 21395/100000 [6:24:00<12:47:53,  1.71it/s]
Train steps ... :  21%|██▏       | 21396/100000 [6:24:01<12:47:20,  1.71it/s]
Train steps ... :  21%|██▏       | 21397/100000 [6:24:02<12:46:53,  1.71it/s]
Train steps ... :  21%|██▏       | 21398/100000 [6:24:02<12:46:54,  1.71it/s]
Train steps ... :  21%|██▏       | 21399/100000 [6:24:03<12:47:20,  1.71it/s]
Train steps ... :  21%|██▏       | 21400/100000 [6:24:03<12:50:09,  1.70it/s]Step... (21400 / 100000 | Loss: 0.941879391670227, Learning Rate: 7.899497487437186e-05)
+
                                                                             
Step... (21400 / 100000 | Loss: 1.0880799293518066, Learning Rate: 7.899497487437186e-05)
+
Train steps ... :  21%|██▏       | 21400/100000 [6:24:04<12:50:09,  1.70it/s]
Train steps ... :  21%|██▏       | 21401/100000 [6:24:04<12:50:01,  1.70it/s]
Train steps ... :  21%|██▏       | 21402/100000 [6:24:05<12:48:03,  1.71it/s]
Train steps ... :  21%|██▏       | 21403/100000 [6:24:05<12:47:30,  1.71it/s]
Train steps ... :  21%|██▏       | 21404/100000 [6:24:06<12:48:23,  1.70it/s]
Train steps ... :  21%|██▏       | 21405/100000 [6:24:06<12:48:04,  1.71it/s]
Train steps ... :  21%|██▏       | 21406/100000 [6:24:07<12:47:07,  1.71it/s]
Train steps ... :  21%|██▏       | 21407/100000 [6:24:07<12:48:57,  1.70it/s]
Train steps ... :  21%|██▏       | 21408/100000 [6:24:08<12:47:49,  1.71it/s]
Train steps ... :  21%|██▏       | 21409/100000 [6:24:09<12:47:15,  1.71it/s]
Train steps ... :  21%|██▏       | 21410/100000 [6:24:09<12:46:29,  1.71it/s]
Train steps ... :  21%|██▏       | 21411/100000 [6:24:10<12:45:54,  1.71it/s]
Train steps ... :  21%|██▏       | 21412/100000 [6:24:10<12:46:21,  1.71it/s]
Train steps ... :  21%|██▏       | 21413/100000 [6:24:11<12:45:50,  1.71it/s]
Train steps ... :  21%|██▏       | 21414/100000 [6:24:12<12:45:46,  1.71it/s]
Train steps ... :  21%|██▏       | 21415/100000 [6:24:12<12:45:54,  1.71it/s]
Train steps ... :  21%|██▏       | 21416/100000 [6:24:13<12:45:39,  1.71it/s]
Train steps ... :  21%|██▏       | 21417/100000 [6:24:13<12:46:22,  1.71it/s]
Train steps ... :  21%|██▏       | 21418/100000 [6:24:14<12:45:50,  1.71it/s]
Train steps ... :  21%|██▏       | 21419/100000 [6:24:14<12:45:30,  1.71it/s]
Train steps ... :  21%|██▏       | 21420/100000 [6:24:15<12:47:25,  1.71it/s]
Train steps ... :  21%|██▏       | 21421/100000 [6:24:16<12:47:20,  1.71it/s]
Train steps ... :  21%|██▏       | 21422/100000 [6:24:16<12:47:53,  1.71it/s]
Train steps ... :  21%|██▏       | 21423/100000 [6:24:17<12:47:13,  1.71it/s]
Train steps ... :  21%|██▏       | 21424/100000 [6:24:17<12:46:41,  1.71it/s]
Train steps ... :  21%|██▏       | 21425/100000 [6:24:18<12:45:47,  1.71it/s]Step... (21425 / 100000 | Loss: 0.8957284688949585, Learning Rate: 7.896984924623117e-05)
+
                                                                             
Step... (21425 / 100000 | Loss: 1.1859928369522095, Learning Rate: 7.896984924623117e-05)
+
Train steps ... :  21%|██▏       | 21425/100000 [6:24:18<12:45:47,  1.71it/s]
Train steps ... :  21%|██▏       | 21426/100000 [6:24:19<12:45:49,  1.71it/s]
Train steps ... :  21%|██▏       | 21427/100000 [6:24:19<12:45:25,  1.71it/s]
Train steps ... :  21%|██▏       | 21428/100000 [6:24:20<12:46:14,  1.71it/s]
Train steps ... :  21%|██▏       | 21429/100000 [6:24:20<12:45:42,  1.71it/s]
Train steps ... :  21%|██▏       | 21430/100000 [6:24:21<12:45:24,  1.71it/s]
Train steps ... :  21%|██▏       | 21431/100000 [6:24:22<12:45:06,  1.71it/s]
Train steps ... :  21%|██▏       | 21432/100000 [6:24:22<12:45:17,  1.71it/s]
Train steps ... :  21%|██▏       | 21433/100000 [6:24:23<12:45:57,  1.71it/s]
Train steps ... :  21%|██▏       | 21434/100000 [6:24:23<12:46:29,  1.71it/s]
Train steps ... :  21%|██▏       | 21435/100000 [6:24:24<12:45:18,  1.71it/s]
Train steps ... :  21%|██▏       | 21436/100000 [6:24:24<12:46:05,  1.71it/s]
Train steps ... :  21%|██▏       | 21437/100000 [6:24:25<12:47:36,  1.71it/s]
Train steps ... :  21%|██▏       | 21438/100000 [6:24:26<12:45:34,  1.71it/s]
Train steps ... :  21%|██▏       | 21439/100000 [6:24:26<12:45:31,  1.71it/s]
Train steps ... :  21%|██▏       | 21440/100000 [6:24:27<12:45:06,  1.71it/s]
Train steps ... :  21%|██▏       | 21441/100000 [6:24:27<12:44:43,  1.71it/s]
Train steps ... :  21%|██▏       | 21442/100000 [6:24:28<12:44:35,  1.71it/s]
Train steps ... :  21%|██▏       | 21443/100000 [6:24:29<12:44:27,  1.71it/s]
Train steps ... :  21%|██▏       | 21444/100000 [6:24:29<12:44:44,  1.71it/s]
Train steps ... :  21%|██▏       | 21445/100000 [6:24:30<12:45:14,  1.71it/s]
Train steps ... :  21%|██▏       | 21446/100000 [6:24:30<12:46:13,  1.71it/s]
Train steps ... :  21%|██▏       | 21447/100000 [6:24:31<12:45:33,  1.71it/s]
Train steps ... :  21%|██▏       | 21448/100000 [6:24:31<12:45:53,  1.71it/s]
Train steps ... :  21%|██▏       | 21449/100000 [6:24:32<12:46:12,  1.71it/s]
Train steps ... :  21%|██▏       | 21450/100000 [6:24:33<12:45:18,  1.71it/s]Step... (21450 / 100000 | Loss: 1.2763895988464355, Learning Rate: 7.894472361809045e-05)
+
                                                                             
Step... (21450 / 100000 | Loss: 1.0786539316177368, Learning Rate: 7.894472361809045e-05)
+
Train steps ... :  21%|██▏       | 21450/100000 [6:24:33<12:45:18,  1.71it/s]
Train steps ... :  21%|██▏       | 21451/100000 [6:24:33<12:46:23,  1.71it/s]
Train steps ... :  21%|██▏       | 21452/100000 [6:24:34<12:46:17,  1.71it/s]
Train steps ... :  21%|██▏       | 21453/100000 [6:24:34<12:45:59,  1.71it/s]
Train steps ... :  21%|██▏       | 21454/100000 [6:24:35<12:47:01,  1.71it/s]
Train steps ... :  21%|██▏       | 21455/100000 [6:24:36<12:47:00,  1.71it/s]
Train steps ... :  21%|██▏       | 21456/100000 [6:24:36<12:46:58,  1.71it/s]
Train steps ... :  21%|██▏       | 21457/100000 [6:24:37<12:47:12,  1.71it/s]
Train steps ... :  21%|██▏       | 21458/100000 [6:24:37<12:47:10,  1.71it/s]
Train steps ... :  21%|██▏       | 21459/100000 [6:24:38<12:46:51,  1.71it/s]
Train steps ... :  21%|██▏       | 21460/100000 [6:24:38<12:47:28,  1.71it/s]
Train steps ... :  21%|██▏       | 21461/100000 [6:24:39<12:46:25,  1.71it/s]
Train steps ... :  21%|██▏       | 21462/100000 [6:24:40<12:46:35,  1.71it/s]
Train steps ... :  21%|██▏       | 21463/100000 [6:24:40<12:46:18,  1.71it/s]
Train steps ... :  21%|██▏       | 21464/100000 [6:24:41<12:46:23,  1.71it/s]
Train steps ... :  21%|██▏       | 21465/100000 [6:24:41<12:46:25,  1.71it/s]
Train steps ... :  21%|██▏       | 21466/100000 [6:24:42<12:46:19,  1.71it/s]
Train steps ... :  21%|██▏       | 21467/100000 [6:24:43<12:45:25,  1.71it/s]
Train steps ... :  21%|██▏       | 21468/100000 [6:24:43<12:46:09,  1.71it/s]
Train steps ... :  21%|██▏       | 21469/100000 [6:24:44<12:46:04,  1.71it/s]
Train steps ... :  21%|██▏       | 21470/100000 [6:24:44<12:45:30,  1.71it/s]
Train steps ... :  21%|██▏       | 21471/100000 [6:24:45<12:45:47,  1.71it/s]
Train steps ... :  21%|██▏       | 21472/100000 [6:24:46<12:46:21,  1.71it/s]
Train steps ... :  21%|██▏       | 21473/100000 [6:24:46<12:45:29,  1.71it/s]
Train steps ... :  21%|██▏       | 21474/100000 [6:24:47<12:44:50,  1.71it/s]
Train steps ... :  21%|██▏       | 21475/100000 [6:24:47<12:45:41,  1.71it/s]Step... (21475 / 100000 | Loss: 0.9754245281219482, Learning Rate: 7.891959798994976e-05)
+
                                                                             
Step... (21475 / 100000 | Loss: 0.9343414306640625, Learning Rate: 7.891959798994976e-05)
+
Train steps ... :  21%|██▏       | 21475/100000 [6:24:48<12:45:41,  1.71it/s]
Train steps ... :  21%|██▏       | 21476/100000 [6:24:48<12:45:56,  1.71it/s]
Train steps ... :  21%|██▏       | 21477/100000 [6:24:48<12:47:19,  1.71it/s]
Train steps ... :  21%|██▏       | 21478/100000 [6:24:49<12:48:07,  1.70it/s]
Train steps ... :  21%|██▏       | 21479/100000 [6:24:50<12:47:09,  1.71it/s]
Train steps ... :  21%|██▏       | 21480/100000 [6:24:50<12:47:05,  1.71it/s]
Train steps ... :  21%|██▏       | 21481/100000 [6:24:51<12:46:41,  1.71it/s]
Train steps ... :  21%|██▏       | 21482/100000 [6:24:51<12:45:24,  1.71it/s]
Train steps ... :  21%|██▏       | 21483/100000 [6:24:52<12:45:54,  1.71it/s]
Train steps ... :  21%|██▏       | 21484/100000 [6:24:53<12:45:16,  1.71it/s]
Train steps ... :  21%|██▏       | 21485/100000 [6:24:53<12:45:28,  1.71it/s]
Train steps ... :  21%|██▏       | 21486/100000 [6:24:54<12:44:56,  1.71it/s]
Train steps ... :  21%|██▏       | 21487/100000 [6:24:54<12:44:37,  1.71it/s]
Train steps ... :  21%|██▏       | 21488/100000 [6:24:55<12:44:35,  1.71it/s]
Train steps ... :  21%|██▏       | 21489/100000 [6:24:55<12:44:32,  1.71it/s]
Train steps ... :  21%|██▏       | 21490/100000 [6:24:56<12:44:54,  1.71it/s]
Train steps ... :  21%|██▏       | 21491/100000 [6:24:57<12:45:02,  1.71it/s]
Train steps ... :  21%|██▏       | 21492/100000 [6:24:57<12:45:39,  1.71it/s]
Train steps ... :  21%|██▏       | 21493/100000 [6:24:58<12:45:58,  1.71it/s]
Train steps ... :  21%|██▏       | 21494/100000 [6:24:58<12:46:24,  1.71it/s]
Train steps ... :  21%|██▏       | 21495/100000 [6:24:59<12:45:43,  1.71it/s]
Train steps ... :  21%|██▏       | 21496/100000 [6:25:00<12:45:34,  1.71it/s]
Train steps ... :  21%|██▏       | 21497/100000 [6:25:00<12:45:33,  1.71it/s]
Train steps ... :  21%|██▏       | 21498/100000 [6:25:01<12:45:22,  1.71it/s]
Train steps ... :  21%|██▏       | 21499/100000 [6:25:01<12:45:16,  1.71it/s]
Train steps ... :  22%|██▏       | 21500/100000 [6:25:02<12:44:58,  1.71it/s]Step... (21500 / 100000 | Loss: 1.4025251865386963, Learning Rate: 7.889447236180904e-05)
+
                                                                             
Step... (21500 / 100000 | Loss: 0.7851412296295166, Learning Rate: 7.889447236180904e-05)
+
Train steps ... :  22%|██▏       | 21500/100000 [6:25:02<12:44:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21501/100000 [6:25:02<12:45:06,  1.71it/s]
Train steps ... :  22%|██▏       | 21502/100000 [6:25:03<12:43:57,  1.71it/s]
Train steps ... :  22%|██▏       | 21503/100000 [6:25:04<12:44:11,  1.71it/s]
Train steps ... :  22%|██▏       | 21504/100000 [6:25:04<12:44:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21505/100000 [6:25:05<12:43:50,  1.71it/s]
Train steps ... :  22%|██▏       | 21506/100000 [6:25:05<12:44:21,  1.71it/s]
Train steps ... :  22%|██▏       | 21507/100000 [6:25:06<12:45:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21508/100000 [6:25:07<12:44:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21509/100000 [6:25:07<12:46:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21510/100000 [6:25:08<12:44:51,  1.71it/s]
Train steps ... :  22%|██▏       | 21511/100000 [6:25:08<12:45:07,  1.71it/s]
Train steps ... :  22%|██▏       | 21512/100000 [6:25:09<12:44:59,  1.71it/s]
Train steps ... :  22%|██▏       | 21513/100000 [6:25:09<12:44:35,  1.71it/s]
Train steps ... :  22%|██▏       | 21514/100000 [6:25:10<12:44:56,  1.71it/s]
Train steps ... :  22%|██▏       | 21515/100000 [6:25:11<12:46:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21516/100000 [6:25:11<12:44:31,  1.71it/s]
Train steps ... :  22%|██▏       | 21517/100000 [6:25:12<12:45:49,  1.71it/s]
Train steps ... :  22%|██▏       | 21518/100000 [6:25:12<12:44:51,  1.71it/s]
Train steps ... :  22%|██▏       | 21519/100000 [6:25:13<12:44:52,  1.71it/s]
Train steps ... :  22%|██▏       | 21520/100000 [6:25:14<12:45:08,  1.71it/s]
Train steps ... :  22%|██▏       | 21521/100000 [6:25:14<12:44:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21522/100000 [6:25:15<12:44:54,  1.71it/s]
Train steps ... :  22%|██▏       | 21523/100000 [6:25:15<12:45:10,  1.71it/s]
Train steps ... :  22%|██▏       | 21524/100000 [6:25:16<12:44:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21525/100000 [6:25:17<12:44:32,  1.71it/s]Step... (21525 / 100000 | Loss: 1.186198115348816, Learning Rate: 7.886934673366835e-05)
+
                                                                             
Step... (21525 / 100000 | Loss: 0.9263048768043518, Learning Rate: 7.886934673366835e-05)
+
Train steps ... :  22%|██▏       | 21525/100000 [6:25:17<12:44:32,  1.71it/s]
Train steps ... :  22%|██▏       | 21526/100000 [6:25:17<12:44:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21527/100000 [6:25:18<12:45:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21528/100000 [6:25:18<12:45:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21529/100000 [6:25:19<12:44:40,  1.71it/s]
Train steps ... :  22%|██▏       | 21530/100000 [6:25:19<12:44:35,  1.71it/s]
Train steps ... :  22%|██▏       | 21531/100000 [6:25:20<12:43:57,  1.71it/s]
Train steps ... :  22%|██▏       | 21532/100000 [6:25:21<12:45:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21533/100000 [6:25:21<12:45:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21534/100000 [6:25:22<12:44:46,  1.71it/s]
Train steps ... :  22%|██▏       | 21535/100000 [6:25:22<12:45:18,  1.71it/s]
Train steps ... :  22%|██▏       | 21536/100000 [6:25:23<12:44:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21537/100000 [6:25:24<12:44:07,  1.71it/s]
Train steps ... :  22%|██▏       | 21538/100000 [6:25:24<12:44:31,  1.71it/s]
Train steps ... :  22%|██▏       | 21539/100000 [6:25:25<12:44:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21540/100000 [6:25:25<12:44:06,  1.71it/s]
Train steps ... :  22%|██▏       | 21541/100000 [6:25:26<12:44:22,  1.71it/s]
Train steps ... :  22%|██▏       | 21542/100000 [6:25:26<12:44:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21543/100000 [6:25:27<12:45:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21544/100000 [6:25:28<12:45:31,  1.71it/s]
Train steps ... :  22%|██▏       | 21545/100000 [6:25:28<12:44:23,  1.71it/s]
Train steps ... :  22%|██▏       | 21546/100000 [6:25:29<12:44:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21547/100000 [6:25:29<12:44:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21548/100000 [6:25:30<12:44:47,  1.71it/s]
Train steps ... :  22%|██▏       | 21549/100000 [6:25:31<12:44:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21550/100000 [6:25:31<12:43:50,  1.71it/s]Step... (21550 / 100000 | Loss: 1.278397798538208, Learning Rate: 7.884422110552764e-05)
+
                                                                             
Step... (21550 / 100000 | Loss: 0.8743199706077576, Learning Rate: 7.884422110552764e-05)
+
Train steps ... :  22%|██▏       | 21550/100000 [6:25:31<12:43:50,  1.71it/s]
Train steps ... :  22%|██▏       | 21551/100000 [6:25:32<12:43:53,  1.71it/s]
Train steps ... :  22%|██▏       | 21552/100000 [6:25:32<12:43:12,  1.71it/s]
Train steps ... :  22%|██▏       | 21553/100000 [6:25:33<12:43:43,  1.71it/s]
Train steps ... :  22%|██▏       | 21554/100000 [6:25:33<12:43:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21555/100000 [6:25:34<12:43:51,  1.71it/s]
Train steps ... :  22%|██▏       | 21556/100000 [6:25:35<12:43:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21557/100000 [6:25:35<12:44:34,  1.71it/s]
Train steps ... :  22%|██▏       | 21558/100000 [6:25:36<12:43:55,  1.71it/s]
Train steps ... :  22%|██▏       | 21559/100000 [6:25:36<12:43:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21560/100000 [6:25:37<12:44:13,  1.71it/s]
Train steps ... :  22%|██▏       | 21561/100000 [6:25:38<12:43:51,  1.71it/s]
Train steps ... :  22%|██▏       | 21562/100000 [6:25:38<12:44:19,  1.71it/s]
Train steps ... :  22%|██▏       | 21563/100000 [6:25:39<12:44:06,  1.71it/s]
Train steps ... :  22%|██▏       | 21564/100000 [6:25:39<12:44:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21565/100000 [6:25:40<12:44:17,  1.71it/s]
Train steps ... :  22%|██▏       | 21566/100000 [6:25:40<12:43:54,  1.71it/s]
Train steps ... :  22%|██▏       | 21567/100000 [6:25:41<12:43:26,  1.71it/s]
Train steps ... :  22%|██▏       | 21568/100000 [6:25:42<12:43:35,  1.71it/s]
Train steps ... :  22%|██▏       | 21569/100000 [6:25:42<12:44:11,  1.71it/s]
Train steps ... :  22%|██▏       | 21570/100000 [6:25:43<12:44:16,  1.71it/s]
Train steps ... :  22%|██▏       | 21571/100000 [6:25:43<12:44:28,  1.71it/s]
Train steps ... :  22%|██▏       | 21572/100000 [6:25:44<12:44:26,  1.71it/s]
Train steps ... :  22%|██▏       | 21573/100000 [6:25:45<12:43:31,  1.71it/s]
Train steps ... :  22%|██▏       | 21574/100000 [6:25:45<12:43:54,  1.71it/s]
Train steps ... :  22%|██▏       | 21575/100000 [6:25:46<12:43:34,  1.71it/s]Step... (21575 / 100000 | Loss: 1.106321930885315, Learning Rate: 7.881909547738693e-05)
+
                                                                             
Step... (21575 / 100000 | Loss: 0.6903216242790222, Learning Rate: 7.881909547738693e-05)
+
Train steps ... :  22%|██▏       | 21575/100000 [6:25:46<12:43:34,  1.71it/s]
Train steps ... :  22%|██▏       | 21576/100000 [6:25:46<12:44:19,  1.71it/s]
Train steps ... :  22%|██▏       | 21577/100000 [6:25:47<12:45:06,  1.71it/s]
Train steps ... :  22%|██▏       | 21578/100000 [6:25:47<12:44:20,  1.71it/s]
Train steps ... :  22%|██▏       | 21579/100000 [6:25:48<12:44:31,  1.71it/s]
Train steps ... :  22%|██▏       | 21580/100000 [6:25:49<12:46:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21581/100000 [6:25:49<12:44:47,  1.71it/s]
Train steps ... :  22%|██▏       | 21582/100000 [6:25:50<12:44:10,  1.71it/s]
Train steps ... :  22%|██▏       | 21583/100000 [6:25:50<12:43:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21584/100000 [6:25:51<12:44:10,  1.71it/s]
Train steps ... :  22%|██▏       | 21585/100000 [6:25:52<12:43:23,  1.71it/s]
Train steps ... :  22%|██▏       | 21586/100000 [6:25:52<12:44:20,  1.71it/s]
Train steps ... :  22%|██▏       | 21587/100000 [6:25:53<12:43:20,  1.71it/s]
Train steps ... :  22%|██▏       | 21588/100000 [6:25:53<12:43:09,  1.71it/s]
Train steps ... :  22%|██▏       | 21589/100000 [6:25:54<12:43:04,  1.71it/s]
Train steps ... :  22%|██▏       | 21590/100000 [6:25:55<12:42:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21591/100000 [6:25:55<12:43:36,  1.71it/s]
Train steps ... :  22%|██▏       | 21592/100000 [6:25:56<12:43:22,  1.71it/s]
Train steps ... :  22%|██▏       | 21593/100000 [6:25:56<12:43:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21594/100000 [6:25:57<12:44:27,  1.71it/s]
Train steps ... :  22%|██▏       | 21595/100000 [6:25:57<12:44:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21596/100000 [6:25:58<12:43:35,  1.71it/s]
Train steps ... :  22%|██▏       | 21597/100000 [6:25:59<12:43:01,  1.71it/s]
Train steps ... :  22%|██▏       | 21598/100000 [6:25:59<12:43:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21599/100000 [6:26:00<12:43:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21600/100000 [6:26:00<12:43:30,  1.71it/s]Step... (21600 / 100000 | Loss: 0.9607187509536743, Learning Rate: 7.879396984924623e-05)
+
                                                                             
Step... (21600 / 100000 | Loss: 1.0166311264038086, Learning Rate: 7.879396984924623e-05)
+
Train steps ... :  22%|██▏       | 21600/100000 [6:26:01<12:43:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21601/100000 [6:26:01<12:43:42,  1.71it/s]
Train steps ... :  22%|██▏       | 21602/100000 [6:26:02<12:42:38,  1.71it/s]
Train steps ... :  22%|██▏       | 21603/100000 [6:26:02<12:42:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21604/100000 [6:26:03<12:42:34,  1.71it/s]
Train steps ... :  22%|██▏       | 21605/100000 [6:26:03<12:43:01,  1.71it/s]
Train steps ... :  22%|██▏       | 21606/100000 [6:26:04<12:42:43,  1.71it/s]
Train steps ... :  22%|██▏       | 21607/100000 [6:26:04<12:42:51,  1.71it/s]
Train steps ... :  22%|██▏       | 21608/100000 [6:26:05<12:42:43,  1.71it/s]
Train steps ... :  22%|██▏       | 21609/100000 [6:26:06<12:42:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21610/100000 [6:26:06<12:42:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21611/100000 [6:26:07<12:43:59,  1.71it/s]
Train steps ... :  22%|██▏       | 21612/100000 [6:26:07<12:43:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21613/100000 [6:26:08<12:43:46,  1.71it/s]
Train steps ... :  22%|██▏       | 21614/100000 [6:26:09<12:43:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21615/100000 [6:26:09<12:43:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21616/100000 [6:26:10<12:42:50,  1.71it/s]
Train steps ... :  22%|██▏       | 21617/100000 [6:26:10<12:42:36,  1.71it/s]
Train steps ... :  22%|██▏       | 21618/100000 [6:26:11<12:42:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21619/100000 [6:26:11<12:42:48,  1.71it/s]
Train steps ... :  22%|██▏       | 21620/100000 [6:26:12<12:42:28,  1.71it/s]
Train steps ... :  22%|██▏       | 21621/100000 [6:26:13<12:44:23,  1.71it/s]
Train steps ... :  22%|██▏       | 21622/100000 [6:26:13<12:43:47,  1.71it/s]
Train steps ... :  22%|██▏       | 21623/100000 [6:26:14<12:43:15,  1.71it/s]
Train steps ... :  22%|██▏       | 21624/100000 [6:26:14<12:44:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21625/100000 [6:26:15<12:43:39,  1.71it/s]Step... (21625 / 100000 | Loss: 1.0017445087432861, Learning Rate: 7.876884422110553e-05)
+
                                                                             
Step... (21625 / 100000 | Loss: 1.007224678993225, Learning Rate: 7.876884422110553e-05)
+
Train steps ... :  22%|██▏       | 21625/100000 [6:26:15<12:43:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21626/100000 [6:26:16<12:44:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21627/100000 [6:26:16<12:43:48,  1.71it/s]
Train steps ... :  22%|██▏       | 21628/100000 [6:26:17<12:43:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21629/100000 [6:26:17<12:42:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21630/100000 [6:26:18<12:43:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21631/100000 [6:26:18<12:42:53,  1.71it/s]
Train steps ... :  22%|██▏       | 21632/100000 [6:26:19<12:42:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21633/100000 [6:26:20<12:43:20,  1.71it/s]
Train steps ... :  22%|██▏       | 21634/100000 [6:26:20<12:43:53,  1.71it/s]
Train steps ... :  22%|██▏       | 21635/100000 [6:26:21<12:43:43,  1.71it/s]
Train steps ... :  22%|██▏       | 21636/100000 [6:26:21<12:43:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21637/100000 [6:26:22<12:43:18,  1.71it/s]
Train steps ... :  22%|██▏       | 21638/100000 [6:26:23<12:43:34,  1.71it/s]
Train steps ... :  22%|██▏       | 21639/100000 [6:26:23<12:43:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21640/100000 [6:26:24<12:42:57,  1.71it/s]
Train steps ... :  22%|██▏       | 21641/100000 [6:26:24<12:43:04,  1.71it/s]
Train steps ... :  22%|██▏       | 21642/100000 [6:26:25<12:42:54,  1.71it/s]
Train steps ... :  22%|██▏       | 21643/100000 [6:26:25<12:43:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21644/100000 [6:26:26<12:43:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21645/100000 [6:26:27<12:43:18,  1.71it/s]
Train steps ... :  22%|██▏       | 21646/100000 [6:26:27<12:43:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21647/100000 [6:26:28<12:43:11,  1.71it/s]
Train steps ... :  22%|██▏       | 21648/100000 [6:26:28<12:43:57,  1.71it/s]
Train steps ... :  22%|██▏       | 21649/100000 [6:26:29<12:43:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21650/100000 [6:26:30<12:43:53,  1.71it/s]Step... (21650 / 100000 | Loss: 0.801194429397583, Learning Rate: 7.874371859296484e-05)
+
                                                                             
Step... (21650 / 100000 | Loss: 1.2321627140045166, Learning Rate: 7.874371859296484e-05)
+
Train steps ... :  22%|██▏       | 21650/100000 [6:26:30<12:43:53,  1.71it/s]
Train steps ... :  22%|██▏       | 21651/100000 [6:26:30<12:44:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21652/100000 [6:26:31<12:43:16,  1.71it/s]
Train steps ... :  22%|██▏       | 21653/100000 [6:26:31<12:44:20,  1.71it/s]
Train steps ... :  22%|██▏       | 21654/100000 [6:26:32<12:43:26,  1.71it/s]
Train steps ... :  22%|██▏       | 21655/100000 [6:26:32<12:43:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21656/100000 [6:26:33<12:42:55,  1.71it/s]
Train steps ... :  22%|██▏       | 21657/100000 [6:26:34<12:42:57,  1.71it/s]
Train steps ... :  22%|██▏       | 21658/100000 [6:26:34<12:43:09,  1.71it/s]
Train steps ... :  22%|██▏       | 21659/100000 [6:26:35<12:43:47,  1.71it/s]
Train steps ... :  22%|██▏       | 21660/100000 [6:26:35<12:43:07,  1.71it/s]
Train steps ... :  22%|██▏       | 21661/100000 [6:26:36<12:42:35,  1.71it/s]
Train steps ... :  22%|██▏       | 21662/100000 [6:26:37<12:42:26,  1.71it/s]
Train steps ... :  22%|██▏       | 21663/100000 [6:26:37<12:41:59,  1.71it/s]
Train steps ... :  22%|██▏       | 21664/100000 [6:26:38<12:42:13,  1.71it/s]
Train steps ... :  22%|██▏       | 21665/100000 [6:26:38<12:41:37,  1.71it/s]
Train steps ... :  22%|██▏       | 21666/100000 [6:26:39<12:42:26,  1.71it/s]
Train steps ... :  22%|██▏       | 21667/100000 [6:26:40<12:42:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21668/100000 [6:26:40<12:42:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21669/100000 [6:26:41<12:42:15,  1.71it/s]
Train steps ... :  22%|██▏       | 21670/100000 [6:26:41<12:42:28,  1.71it/s]
Train steps ... :  22%|██▏       | 21671/100000 [6:26:42<12:42:33,  1.71it/s]
Train steps ... :  22%|██▏       | 21672/100000 [6:26:42<12:42:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21673/100000 [6:26:43<12:42:40,  1.71it/s]
Train steps ... :  22%|██▏       | 21674/100000 [6:26:44<12:42:11,  1.71it/s]
Train steps ... :  22%|██▏       | 21675/100000 [6:26:44<12:42:00,  1.71it/s]Step... (21675 / 100000 | Loss: 0.6744142770767212, Learning Rate: 7.871859296482412e-05)
+
                                                                             
Step... (21675 / 100000 | Loss: 0.8192905187606812, Learning Rate: 7.871859296482412e-05)
+
Train steps ... :  22%|██▏       | 21675/100000 [6:26:45<12:42:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21676/100000 [6:26:45<12:42:12,  1.71it/s]
Train steps ... :  22%|██▏       | 21677/100000 [6:26:45<12:42:10,  1.71it/s]
Train steps ... :  22%|██▏       | 21678/100000 [6:26:46<12:41:37,  1.71it/s]
Train steps ... :  22%|██▏       | 21679/100000 [6:26:47<12:41:35,  1.71it/s]
Train steps ... :  22%|██▏       | 21680/100000 [6:26:47<12:42:50,  1.71it/s]
Train steps ... :  22%|██▏       | 21681/100000 [6:26:48<12:45:19,  1.71it/s]
Train steps ... :  22%|██▏       | 21682/100000 [6:26:48<12:42:27,  1.71it/s]
Train steps ... :  22%|���█▏       | 21683/100000 [6:26:49<12:42:50,  1.71it/s]
Train steps ... :  22%|██▏       | 21684/100000 [6:26:49<12:42:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21685/100000 [6:26:50<12:43:28,  1.71it/s]
Train steps ... :  22%|██▏       | 21686/100000 [6:26:51<12:44:09,  1.71it/s]
Train steps ... :  22%|██▏       | 21687/100000 [6:26:51<12:43:15,  1.71it/s]
Train steps ... :  22%|██▏       | 21688/100000 [6:26:52<12:43:06,  1.71it/s]
Train steps ... :  22%|██▏       | 21689/100000 [6:26:52<12:42:56,  1.71it/s]
Train steps ... :  22%|██▏       | 21690/100000 [6:26:53<12:42:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21691/100000 [6:26:54<12:43:08,  1.71it/s]
Train steps ... :  22%|██▏       | 21692/100000 [6:26:54<12:43:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21693/100000 [6:26:55<12:42:32,  1.71it/s]
Train steps ... :  22%|██▏       | 21694/100000 [6:26:55<12:42:33,  1.71it/s]
Train steps ... :  22%|██▏       | 21695/100000 [6:26:56<12:42:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21696/100000 [6:26:56<12:43:42,  1.71it/s]
Train steps ... :  22%|██▏       | 21697/100000 [6:26:57<12:43:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21698/100000 [6:26:58<12:43:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21699/100000 [6:26:58<12:42:20,  1.71it/s]
Train steps ... :  22%|██▏       | 21700/100000 [6:26:59<12:42:00,  1.71it/s]Step... (21700 / 100000 | Loss: 0.7638759613037109, Learning Rate: 7.869346733668343e-05)
+
                                                                             
Step... (21700 / 100000 | Loss: 1.028124213218689, Learning Rate: 7.869346733668343e-05)
+
Train steps ... :  22%|██▏       | 21700/100000 [6:26:59<12:42:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21701/100000 [6:26:59<12:42:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21702/100000 [6:27:00<12:42:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21703/100000 [6:27:01<12:42:06,  1.71it/s]
Train steps ... :  22%|██▏       | 21704/100000 [6:27:01<12:41:54,  1.71it/s]
Train steps ... :  22%|██▏       | 21705/100000 [6:27:02<12:42:26,  1.71it/s]
Train steps ... :  22%|██▏       | 21706/100000 [6:27:02<12:42:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21707/100000 [6:27:03<12:42:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21708/100000 [6:27:03<12:42:27,  1.71it/s]
Train steps ... :  22%|██▏       | 21709/100000 [6:27:04<12:42:40,  1.71it/s]
Train steps ... :  22%|██▏       | 21710/100000 [6:27:05<12:42:51,  1.71it/s]
Train steps ... :  22%|██▏       | 21711/100000 [6:27:05<12:42:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21712/100000 [6:27:06<12:42:33,  1.71it/s]
Train steps ... :  22%|██▏       | 21713/100000 [6:27:06<12:42:49,  1.71it/s]
Train steps ... :  22%|██▏       | 21714/100000 [6:27:07<12:42:50,  1.71it/s]
Train steps ... :  22%|██▏       | 21715/100000 [6:27:08<12:43:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21716/100000 [6:27:08<12:42:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21717/100000 [6:27:09<12:42:43,  1.71it/s]
Train steps ... :  22%|██▏       | 21718/100000 [6:27:09<12:42:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21719/100000 [6:27:10<12:42:06,  1.71it/s]
Train steps ... :  22%|██▏       | 21720/100000 [6:27:10<12:41:40,  1.71it/s]
Train steps ... :  22%|██▏       | 21721/100000 [6:27:11<12:41:31,  1.71it/s]
Train steps ... :  22%|██▏       | 21722/100000 [6:27:12<12:41:42,  1.71it/s]
Train steps ... :  22%|██▏       | 21723/100000 [6:27:12<12:42:09,  1.71it/s]
Train steps ... :  22%|██▏       | 21724/100000 [6:27:13<12:42:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21725/100000 [6:27:13<12:41:59,  1.71it/s]Step... (21725 / 100000 | Loss: 0.9169961214065552, Learning Rate: 7.866834170854271e-05)
+
                                                                             
Step... (21725 / 100000 | Loss: 1.019108772277832, Learning Rate: 7.866834170854271e-05)
+
Train steps ... :  22%|██▏       | 21725/100000 [6:27:14<12:41:59,  1.71it/s]
Train steps ... :  22%|██▏       | 21726/100000 [6:27:14<12:42:17,  1.71it/s]
Train steps ... :  22%|██▏       | 21727/100000 [6:27:15<12:41:38,  1.71it/s]
Train steps ... :  22%|██▏       | 21728/100000 [6:27:15<12:41:47,  1.71it/s]
Train steps ... :  22%|██▏       | 21729/100000 [6:27:16<12:41:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21730/100000 [6:27:16<12:43:13,  1.71it/s]
Train steps ... :  22%|██▏       | 21731/100000 [6:27:17<12:42:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21732/100000 [6:27:17<12:42:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21733/100000 [6:27:18<12:42:35,  1.71it/s]
Train steps ... :  22%|██▏       | 21734/100000 [6:27:19<12:43:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21735/100000 [6:27:19<12:41:57,  1.71it/s]
Train steps ... :  22%|██▏       | 21736/100000 [6:27:20<12:41:52,  1.71it/s]
Train steps ... :  22%|██▏       | 21737/100000 [6:27:20<12:41:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21738/100000 [6:27:21<12:41:22,  1.71it/s]
Train steps ... :  22%|██▏       | 21739/100000 [6:27:22<12:42:06,  1.71it/s]
Train steps ... :  22%|██▏       | 21740/100000 [6:27:22<12:41:49,  1.71it/s]
Train steps ... :  22%|██▏       | 21741/100000 [6:27:23<12:41:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21742/100000 [6:27:23<12:41:23,  1.71it/s]
Train steps ... :  22%|██▏       | 21743/100000 [6:27:24<12:41:36,  1.71it/s]
Train steps ... :  22%|██▏       | 21744/100000 [6:27:24<12:41:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21745/100000 [6:27:25<12:41:07,  1.71it/s]
Train steps ... :  22%|██▏       | 21746/100000 [6:27:26<12:41:40,  1.71it/s]
Train steps ... :  22%|██▏       | 21747/100000 [6:27:26<12:41:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21748/100000 [6:27:27<12:41:51,  1.71it/s]
Train steps ... :  22%|██▏       | 21749/100000 [6:27:27<12:43:38,  1.71it/s]
Train steps ... :  22%|██▏       | 21750/100000 [6:27:28<12:42:47,  1.71it/s]Step... (21750 / 100000 | Loss: 0.9458447694778442, Learning Rate: 7.864321608040201e-05)
+
                                                                             
Step... (21750 / 100000 | Loss: 1.263321876525879, Learning Rate: 7.864321608040201e-05)
+
Train steps ... :  22%|██▏       | 21750/100000 [6:27:28<12:42:47,  1.71it/s]
Train steps ... :  22%|██▏       | 21751/100000 [6:27:29<12:42:57,  1.71it/s]
Train steps ... :  22%|██▏       | 21752/100000 [6:27:29<12:43:45,  1.71it/s]
Train steps ... :  22%|██▏       | 21753/100000 [6:27:30<12:43:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21754/100000 [6:27:30<12:42:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21755/100000 [6:27:31<12:42:49,  1.71it/s]
Train steps ... :  22%|██▏       | 21756/100000 [6:27:32<12:41:59,  1.71it/s]
Train steps ... :  22%|██▏       | 21757/100000 [6:27:32<12:43:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21758/100000 [6:27:33<12:43:12,  1.71it/s]
Train steps ... :  22%|██▏       | 21759/100000 [6:27:33<12:42:40,  1.71it/s]
Train steps ... :  22%|██▏       | 21760/100000 [6:27:34<12:42:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21761/100000 [6:27:34<12:42:16,  1.71it/s]
Train steps ... :  22%|██▏       | 21762/100000 [6:27:35<12:42:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21763/100000 [6:27:36<12:42:27,  1.71it/s]
Train steps ... :  22%|██▏       | 21764/100000 [6:27:36<12:42:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21765/100000 [6:27:37<12:42:32,  1.71it/s]
Train steps ... :  22%|██▏       | 21766/100000 [6:27:37<12:43:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21767/100000 [6:27:38<12:41:26,  1.71it/s]
Train steps ... :  22%|██▏       | 21768/100000 [6:27:39<12:42:12,  1.71it/s]
Train steps ... :  22%|██▏       | 21769/100000 [6:27:39<12:42:56,  1.71it/s]
Train steps ... :  22%|██▏       | 21770/100000 [6:27:40<12:42:36,  1.71it/s]
Train steps ... :  22%|██▏       | 21771/100000 [6:27:40<12:42:07,  1.71it/s]
Train steps ... :  22%|██▏       | 21772/100000 [6:27:41<12:41:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21773/100000 [6:27:41<12:43:32,  1.71it/s]
Train steps ... :  22%|██▏       | 21774/100000 [6:27:42<12:43:42,  1.71it/s]
Train steps ... :  22%|██▏       | 21775/100000 [6:27:43<12:43:46,  1.71it/s]Step... (21775 / 100000 | Loss: 0.8442423343658447, Learning Rate: 7.861809045226131e-05)
+
                                                                             
Step... (21775 / 100000 | Loss: 1.0215893983840942, Learning Rate: 7.861809045226131e-05)
+
Train steps ... :  22%|██▏       | 21775/100000 [6:27:43<12:43:46,  1.71it/s]
Train steps ... :  22%|██▏       | 21776/100000 [6:27:43<12:43:31,  1.71it/s]
Train steps ... :  22%|██▏       | 21777/100000 [6:27:44<12:42:23,  1.71it/s]
Train steps ... :  22%|██▏       | 21778/100000 [6:27:44<12:41:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21779/100000 [6:27:45<12:41:19,  1.71it/s]
Train steps ... :  22%|██▏       | 21780/100000 [6:27:46<12:41:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21781/100000 [6:27:46<12:41:28,  1.71it/s]
Train steps ... :  22%|██▏       | 21782/100000 [6:27:47<12:41:33,  1.71it/s]
Train steps ... :  22%|██▏       | 21783/100000 [6:27:47<12:42:47,  1.71it/s]
Train steps ... :  22%|██▏       | 21784/100000 [6:27:48<12:42:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21785/100000 [6:27:48<12:41:20,  1.71it/s]
Train steps ... :  22%|██▏       | 21786/100000 [6:27:49<12:41:22,  1.71it/s]
Train steps ... :  22%|██▏       | 21787/100000 [6:27:50<12:41:21,  1.71it/s]
Train steps ... :  22%|██▏       | 21788/100000 [6:27:50<12:42:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21789/100000 [6:27:51<12:41:49,  1.71it/s]
Train steps ... :  22%|██▏       | 21790/100000 [6:27:51<12:41:13,  1.71it/s]
Train steps ... :  22%|██▏       | 21791/100000 [6:27:52<12:41:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21792/100000 [6:27:53<12:42:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21793/100000 [6:27:53<12:43:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21794/100000 [6:27:54<12:43:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21795/100000 [6:27:54<12:43:04,  1.71it/s]
Train steps ... :  22%|██▏       | 21796/100000 [6:27:55<12:43:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21797/100000 [6:27:55<12:42:22,  1.71it/s]
Train steps ... :  22%|██▏       | 21798/100000 [6:27:56<12:41:52,  1.71it/s]
Train steps ... :  22%|██▏       | 21799/100000 [6:27:57<12:42:23,  1.71it/s]
Train steps ... :  22%|██▏       | 21800/100000 [6:27:57<12:41:52,  1.71it/s]Step... (21800 / 100000 | Loss: 0.8020404577255249, Learning Rate: 7.85929648241206e-05)
+
                                                                             
Step... (21800 / 100000 | Loss: 0.9121211767196655, Learning Rate: 7.85929648241206e-05)
+
Train steps ... :  22%|██▏       | 21800/100000 [6:27:58<12:41:52,  1.71it/s]
Train steps ... :  22%|██▏       | 21801/100000 [6:27:58<12:42:38,  1.71it/s]
Train steps ... :  22%|██▏       | 21802/100000 [6:27:58<12:41:40,  1.71it/s]
Train steps ... :  22%|██▏       | 21803/100000 [6:27:59<12:41:18,  1.71it/s]
Train steps ... :  22%|██▏       | 21804/100000 [6:28:00<12:41:10,  1.71it/s]
Train steps ... :  22%|██▏       | 21805/100000 [6:28:00<12:41:11,  1.71it/s]
Train steps ... :  22%|██▏       | 21806/100000 [6:28:01<12:42:02,  1.71it/s]
Train steps ... :  22%|██▏       | 21807/100000 [6:28:01<12:41:16,  1.71it/s]
Train steps ... :  22%|██▏       | 21808/100000 [6:28:02<12:41:57,  1.71it/s]
Train steps ... :  22%|██▏       | 21809/100000 [6:28:03<12:41:37,  1.71it/s]
Train steps ... :  22%|██▏       | 21810/100000 [6:28:03<12:42:04,  1.71it/s]
Train steps ... :  22%|██▏       | 21811/100000 [6:28:04<12:41:40,  1.71it/s]
Train steps ... :  22%|██▏       | 21812/100000 [6:28:04<12:41:01,  1.71it/s]
Train steps ... :  22%|██▏       | 21813/100000 [6:28:05<12:41:35,  1.71it/s]
Train steps ... :  22%|██▏       | 21814/100000 [6:28:05<12:42:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21815/100000 [6:28:06<12:42:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21816/100000 [6:28:07<12:41:19,  1.71it/s]
Train steps ... :  22%|██▏       | 21817/100000 [6:28:07<12:41:23,  1.71it/s]
Train steps ... :  22%|██▏       | 21818/100000 [6:28:08<12:42:26,  1.71it/s]
Train steps ... :  22%|██▏       | 21819/100000 [6:28:08<12:42:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21820/100000 [6:28:09<12:43:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21821/100000 [6:28:10<12:43:52,  1.71it/s]
Train steps ... :  22%|██▏       | 21822/100000 [6:28:10<12:42:48,  1.71it/s]
Train steps ... :  22%|██▏       | 21823/100000 [6:28:11<12:42:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21824/100000 [6:28:11<12:41:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21825/100000 [6:28:12<12:41:44,  1.71it/s]Step... (21825 / 100000 | Loss: 0.8192112445831299, Learning Rate: 7.856783919597991e-05)
+
                                                                             
Step... (21825 / 100000 | Loss: 0.8120445013046265, Learning Rate: 7.856783919597991e-05)
+
Train steps ... :  22%|██▏       | 21825/100000 [6:28:12<12:41:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21826/100000 [6:28:12<12:41:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21827/100000 [6:28:13<12:42:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21828/100000 [6:28:14<12:42:15,  1.71it/s]
Train steps ... :  22%|██▏       | 21829/100000 [6:28:14<12:41:45,  1.71it/s]
Train steps ... :  22%|██▏       | 21830/100000 [6:28:15<12:41:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21831/100000 [6:28:15<12:40:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21832/100000 [6:28:16<12:42:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21833/100000 [6:28:17<12:42:49,  1.71it/s]
Train steps ... :  22%|██▏       | 21834/100000 [6:28:17<12:43:27,  1.71it/s]
Train steps ... :  22%|██▏       | 21835/100000 [6:28:18<12:43:13,  1.71it/s]
Train steps ... :  22%|██▏       | 21836/100000 [6:28:18<12:44:14,  1.70it/s]
Train steps ... :  22%|██▏       | 21837/100000 [6:28:19<12:43:28,  1.71it/s]
Train steps ... :  22%|██▏       | 21838/100000 [6:28:19<12:43:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21839/100000 [6:28:20<12:43:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21840/100000 [6:28:21<12:42:12,  1.71it/s]
Train steps ... :  22%|██▏       | 21841/100000 [6:28:21<12:42:07,  1.71it/s]
Train steps ... :  22%|██▏       | 21842/100000 [6:28:22<12:42:04,  1.71it/s]
Train steps ... :  22%|██▏       | 21843/100000 [6:28:22<12:42:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21844/100000 [6:28:23<12:42:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21845/100000 [6:28:24<12:43:04,  1.71it/s]
Train steps ... :  22%|██▏       | 21846/100000 [6:28:24<12:41:56,  1.71it/s]
Train steps ... :  22%|██▏       | 21847/100000 [6:28:25<12:42:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21848/100000 [6:28:25<12:42:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21849/100000 [6:28:26<12:41:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21850/100000 [6:28:26<12:41:51,  1.71it/s]Step... (21850 / 100000 | Loss: 1.2083851099014282, Learning Rate: 7.85427135678392e-05)
+
                                                                             
Step... (21850 / 100000 | Loss: 0.9465850591659546, Learning Rate: 7.85427135678392e-05)
+
Train steps ... :  22%|██▏       | 21850/100000 [6:28:27<12:41:51,  1.71it/s]
Train steps ... :  22%|██▏       | 21851/100000 [6:28:27<12:41:37,  1.71it/s]
Train steps ... :  22%|██▏       | 21852/100000 [6:28:28<12:41:24,  1.71it/s]
Train steps ... :  22%|██▏       | 21853/100000 [6:28:28<12:41:37,  1.71it/s]
Train steps ... :  22%|██▏       | 21854/100000 [6:28:29<12:40:46,  1.71it/s]
Train steps ... :  22%|██▏       | 21855/100000 [6:28:29<12:40:38,  1.71it/s]
Train steps ... :  22%|██▏       | 21856/100000 [6:28:30<12:40:32,  1.71it/s]
Train steps ... :  22%|██▏       | 21857/100000 [6:28:31<12:40:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21858/100000 [6:28:31<12:40:12,  1.71it/s]
Train steps ... :  22%|██▏       | 21859/100000 [6:28:32<12:40:21,  1.71it/s]
Train steps ... :  22%|██▏       | 21860/100000 [6:28:32<12:40:50,  1.71it/s]
Train steps ... :  22%|██▏       | 21861/100000 [6:28:33<12:40:21,  1.71it/s]
Train steps ... :  22%|██▏       | 21862/100000 [6:28:34<12:40:48,  1.71it/s]
Train steps ... :  22%|██▏       | 21863/100000 [6:28:34<12:40:46,  1.71it/s]
Train steps ... :  22%|██▏       | 21864/100000 [6:28:35<12:41:46,  1.71it/s]
Train steps ... :  22%|██▏       | 21865/100000 [6:28:35<12:40:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21866/100000 [6:28:36<12:42:02,  1.71it/s]
Train steps ... :  22%|██▏       | 21867/100000 [6:28:36<12:44:12,  1.70it/s]
Train steps ... :  22%|██▏       | 21868/100000 [6:28:37<12:42:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21869/100000 [6:28:38<12:42:10,  1.71it/s]
Train steps ... :  22%|██▏       | 21870/100000 [6:28:38<12:41:42,  1.71it/s]
Train steps ... :  22%|██▏       | 21871/100000 [6:28:39<12:41:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21872/100000 [6:28:39<12:41:08,  1.71it/s]
Train steps ... :  22%|██▏       | 21873/100000 [6:28:40<12:41:33,  1.71it/s]
Train steps ... :  22%|██▏       | 21874/100000 [6:28:41<12:39:53,  1.71it/s]
Train steps ... :  22%|██▏       | 21875/100000 [6:28:41<12:40:43,  1.71it/s]Step... (21875 / 100000 | Loss: 0.9325259923934937, Learning Rate: 7.85175879396985e-05)
+
                                                                             
Step... (21875 / 100000 | Loss: 0.845201849937439, Learning Rate: 7.85175879396985e-05)
+
Train steps ... :  22%|██▏       | 21875/100000 [6:28:41<12:40:43,  1.71it/s]
Train steps ... :  22%|██▏       | 21876/100000 [6:28:42<12:41:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21877/100000 [6:28:42<12:41:15,  1.71it/s]
Train steps ... :  22%|██▏       | 21878/100000 [6:28:43<12:42:01,  1.71it/s]
Train steps ... :  22%|██▏       | 21879/100000 [6:28:43<12:42:09,  1.71it/s]
Train steps ... :  22%|██▏       | 21880/100000 [6:28:44<12:42:08,  1.71it/s]
Train steps ... :  22%|██▏       | 21881/100000 [6:28:45<12:41:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21882/100000 [6:28:45<12:42:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21883/100000 [6:28:46<12:42:12,  1.71it/s]
Train steps ... :  22%|██▏       | 21884/100000 [6:28:46<12:42:48,  1.71it/s]
Train steps ... :  22%|██▏       | 21885/100000 [6:28:47<12:42:05,  1.71it/s]
Train steps ... :  22%|██▏       | 21886/100000 [6:28:48<12:41:32,  1.71it/s]
Train steps ... :  22%|██▏       | 21887/100000 [6:28:48<12:40:53,  1.71it/s]
Train steps ... :  22%|██▏       | 21888/100000 [6:28:49<12:43:04,  1.71it/s]
Train steps ... :  22%|██▏       | 21889/100000 [6:28:49<12:41:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21890/100000 [6:28:50<12:41:40,  1.71it/s]
Train steps ... :  22%|██▏       | 21891/100000 [6:28:50<12:41:18,  1.71it/s]
Train steps ... :  22%|██▏       | 21892/100000 [6:28:51<12:40:47,  1.71it/s]
Train steps ... :  22%|██▏       | 21893/100000 [6:28:52<12:40:22,  1.71it/s]
Train steps ... :  22%|██���       | 21894/100000 [6:28:52<12:40:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21895/100000 [6:28:53<12:39:37,  1.71it/s]
Train steps ... :  22%|██▏       | 21896/100000 [6:28:53<12:39:52,  1.71it/s]
Train steps ... :  22%|██▏       | 21897/100000 [6:28:54<12:40:16,  1.71it/s]
Train steps ... :  22%|██▏       | 21898/100000 [6:28:55<12:41:19,  1.71it/s]
Train steps ... :  22%|██▏       | 21899/100000 [6:28:55<12:40:57,  1.71it/s]
Train steps ... :  22%|██▏       | 21900/100000 [6:28:56<12:40:29,  1.71it/s]Step... (21900 / 100000 | Loss: 0.898025393486023, Learning Rate: 7.849246231155779e-05)
+
                                                                             
Step... (21900 / 100000 | Loss: 0.8260594010353088, Learning Rate: 7.849246231155779e-05)
+
Train steps ... :  22%|██▏       | 21900/100000 [6:28:56<12:40:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21901/100000 [6:28:56<12:41:04,  1.71it/s]
Train steps ... :  22%|██▏       | 21902/100000 [6:28:57<12:40:40,  1.71it/s]
Train steps ... :  22%|██▏       | 21903/100000 [6:28:57<12:41:08,  1.71it/s]
Train steps ... :  22%|██▏       | 21904/100000 [6:28:58<12:41:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21905/100000 [6:28:59<12:41:07,  1.71it/s]
Train steps ... :  22%|██▏       | 21906/100000 [6:28:59<12:40:49,  1.71it/s]
Train steps ... :  22%|██▏       | 21907/100000 [6:29:00<12:41:17,  1.71it/s]
Train steps ... :  22%|██▏       | 21908/100000 [6:29:00<12:40:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21909/100000 [6:29:01<12:39:53,  1.71it/s]
Train steps ... :  22%|██▏       | 21910/100000 [6:29:02<12:40:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21911/100000 [6:29:02<12:40:27,  1.71it/s]
Train steps ... :  22%|██▏       | 21912/100000 [6:29:03<12:40:31,  1.71it/s]
Train steps ... :  22%|██▏       | 21913/100000 [6:29:03<12:42:19,  1.71it/s]
Train steps ... :  22%|██▏       | 21914/100000 [6:29:04<12:40:15,  1.71it/s]
Train steps ... :  22%|██▏       | 21915/100000 [6:29:04<12:39:54,  1.71it/s]
Train steps ... :  22%|██▏       | 21916/100000 [6:29:05<12:39:59,  1.71it/s]
Train steps ... :  22%|██▏       | 21917/100000 [6:29:06<12:39:36,  1.71it/s]
Train steps ... :  22%|██▏       | 21918/100000 [6:29:06<12:39:50,  1.71it/s]
Train steps ... :  22%|██▏       | 21919/100000 [6:29:07<12:40:10,  1.71it/s]
Train steps ... :  22%|██▏       | 21920/100000 [6:29:07<12:39:47,  1.71it/s]
Train steps ... :  22%|██▏       | 21921/100000 [6:29:08<12:40:18,  1.71it/s]
Train steps ... :  22%|██▏       | 21922/100000 [6:29:09<12:39:34,  1.71it/s]
Train steps ... :  22%|██▏       | 21923/100000 [6:29:09<12:39:09,  1.71it/s]
Train steps ... :  22%|██▏       | 21924/100000 [6:29:10<12:40:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21925/100000 [6:29:10<12:40:45,  1.71it/s]Step... (21925 / 100000 | Loss: 0.9805576801300049, Learning Rate: 7.846733668341709e-05)
+
                                                                             
Step... (21925 / 100000 | Loss: 0.9172903895378113, Learning Rate: 7.846733668341709e-05)
+
Train steps ... :  22%|██▏       | 21925/100000 [6:29:11<12:40:45,  1.71it/s]
Train steps ... :  22%|██▏       | 21926/100000 [6:29:11<12:40:16,  1.71it/s]
Train steps ... :  22%|██▏       | 21927/100000 [6:29:11<12:39:54,  1.71it/s]
Train steps ... :  22%|██▏       | 21928/100000 [6:29:12<12:40:01,  1.71it/s]
Train steps ... :  22%|██▏       | 21929/100000 [6:29:13<12:39:32,  1.71it/s]
Train steps ... :  22%|██▏       | 21930/100000 [6:29:13<12:40:21,  1.71it/s]
Train steps ... :  22%|██▏       | 21931/100000 [6:29:14<12:41:02,  1.71it/s]
Train steps ... :  22%|██▏       | 21932/100000 [6:29:14<12:41:35,  1.71it/s]
Train steps ... :  22%|██▏       | 21933/100000 [6:29:15<12:40:47,  1.71it/s]
Train steps ... :  22%|██▏       | 21934/100000 [6:29:16<12:40:26,  1.71it/s]
Train steps ... :  22%|██▏       | 21935/100000 [6:29:16<12:39:52,  1.71it/s]
Train steps ... :  22%|██▏       | 21936/100000 [6:29:17<12:39:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21937/100000 [6:29:17<12:40:17,  1.71it/s]
Train steps ... :  22%|██▏       | 21938/100000 [6:29:18<12:39:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21939/100000 [6:29:19<12:40:02,  1.71it/s]
Train steps ... :  22%|██▏       | 21940/100000 [6:29:19<12:39:32,  1.71it/s]
Train steps ... :  22%|██▏       | 21941/100000 [6:29:20<12:40:46,  1.71it/s]
Train steps ... :  22%|██▏       | 21942/100000 [6:29:20<12:40:01,  1.71it/s]
Train steps ... :  22%|██▏       | 21943/100000 [6:29:21<12:40:07,  1.71it/s]
Train steps ... :  22%|██▏       | 21944/100000 [6:29:21<12:40:09,  1.71it/s]
Train steps ... :  22%|██▏       | 21945/100000 [6:29:22<12:39:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21946/100000 [6:29:23<12:40:07,  1.71it/s]
Train steps ... :  22%|██▏       | 21947/100000 [6:29:23<12:39:42,  1.71it/s]
Train steps ... :  22%|██▏       | 21948/100000 [6:29:24<12:39:58,  1.71it/s]
Train steps ... :  22%|██▏       | 21949/100000 [6:29:24<12:40:36,  1.71it/s]
Train steps ... :  22%|██▏       | 21950/100000 [6:29:25<12:40:16,  1.71it/s]Step... (21950 / 100000 | Loss: 1.0449728965759277, Learning Rate: 7.844221105527638e-05)
+
                                                                             
Step... (21950 / 100000 | Loss: 0.8921677470207214, Learning Rate: 7.844221105527638e-05)
+
Train steps ... :  22%|██▏       | 21950/100000 [6:29:25<12:40:16,  1.71it/s]
Train steps ... :  22%|██▏       | 21951/100000 [6:29:26<12:40:19,  1.71it/s]
Train steps ... :  22%|██▏       | 21952/100000 [6:29:26<12:40:15,  1.71it/s]
Train steps ... :  22%|██▏       | 21953/100000 [6:29:27<12:39:15,  1.71it/s]
Train steps ... :  22%|██▏       | 21954/100000 [6:29:27<12:39:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21955/100000 [6:29:28<12:39:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21956/100000 [6:29:28<12:39:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21957/100000 [6:29:29<12:39:51,  1.71it/s]
Train steps ... :  22%|██▏       | 21958/100000 [6:29:30<12:39:53,  1.71it/s]
Train steps ... :  22%|██▏       | 21959/100000 [6:29:30<12:40:15,  1.71it/s]
Train steps ... :  22%|██▏       | 21960/100000 [6:29:31<12:40:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21961/100000 [6:29:31<12:39:51,  1.71it/s]
Train steps ... :  22%|██▏       | 21962/100000 [6:29:32<12:41:13,  1.71it/s]
Train steps ... :  22%|██▏       | 21963/100000 [6:29:33<12:39:49,  1.71it/s]
Train steps ... :  22%|██▏       | 21964/100000 [6:29:33<12:40:26,  1.71it/s]
Train steps ... :  22%|██▏       | 21965/100000 [6:29:34<12:39:39,  1.71it/s]
Train steps ... :  22%|██▏       | 21966/100000 [6:29:34<12:40:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21967/100000 [6:29:35<12:40:14,  1.71it/s]
Train steps ... :  22%|██▏       | 21968/100000 [6:29:35<12:40:04,  1.71it/s]
Train steps ... :  22%|██▏       | 21969/100000 [6:29:36<12:40:11,  1.71it/s]
Train steps ... :  22%|██▏       | 21970/100000 [6:29:37<12:39:43,  1.71it/s]
Train steps ... :  22%|██▏       | 21971/100000 [6:29:37<12:40:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21972/100000 [6:29:38<12:42:29,  1.71it/s]
Train steps ... :  22%|██▏       | 21973/100000 [6:29:38<12:41:31,  1.71it/s]
Train steps ... :  22%|██▏       | 21974/100000 [6:29:39<12:42:45,  1.70it/s]
Train steps ... :  22%|██▏       | 21975/100000 [6:29:40<12:41:25,  1.71it/s]Step... (21975 / 100000 | Loss: 1.0849303007125854, Learning Rate: 7.841708542713568e-05)
+
                                                                             
Step... (21975 / 100000 | Loss: 0.7864855527877808, Learning Rate: 7.841708542713568e-05)
+
Train steps ... :  22%|██▏       | 21975/100000 [6:29:40<12:41:25,  1.71it/s]
Train steps ... :  22%|██▏       | 21976/100000 [6:29:40<12:41:19,  1.71it/s]
Train steps ... :  22%|██▏       | 21977/100000 [6:29:41<12:40:42,  1.71it/s]
Train steps ... :  22%|██▏       | 21978/100000 [6:29:41<12:40:12,  1.71it/s]
Train steps ... :  22%|██▏       | 21979/100000 [6:29:42<12:40:18,  1.71it/s]
Train steps ... :  22%|██▏       | 21980/100000 [6:29:42<12:39:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21981/100000 [6:29:43<12:39:11,  1.71it/s]
Train steps ... :  22%|██▏       | 21982/100000 [6:29:44<12:39:44,  1.71it/s]
Train steps ... :  22%|██▏       | 21983/100000 [6:29:44<12:38:48,  1.71it/s]
Train steps ... :  22%|██▏       | 21984/100000 [6:29:45<12:39:54,  1.71it/s]
Train steps ... :  22%|██▏       | 21985/100000 [6:29:45<12:39:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21986/100000 [6:29:46<12:41:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21987/100000 [6:29:47<12:39:21,  1.71it/s]
Train steps ... :  22%|██▏       | 21988/100000 [6:29:47<12:39:33,  1.71it/s]
Train steps ... :  22%|██▏       | 21989/100000 [6:29:48<12:41:15,  1.71it/s]
Train steps ... :  22%|██▏       | 21990/100000 [6:29:48<12:42:00,  1.71it/s]
Train steps ... :  22%|██▏       | 21991/100000 [6:29:49<12:39:37,  1.71it/s]
Train steps ... :  22%|██▏       | 21992/100000 [6:29:49<12:39:41,  1.71it/s]
Train steps ... :  22%|██▏       | 21993/100000 [6:29:50<12:40:30,  1.71it/s]
Train steps ... :  22%|██▏       | 21994/100000 [6:29:51<12:39:53,  1.71it/s]
Train steps ... :  22%|██▏       | 21995/100000 [6:29:51<12:39:08,  1.71it/s]
Train steps ... :  22%|██▏       | 21996/100000 [6:29:52<12:39:03,  1.71it/s]
Train steps ... :  22%|██▏       | 21997/100000 [6:29:52<12:38:49,  1.71it/s]
Train steps ... :  22%|██▏       | 21998/100000 [6:29:53<12:38:35,  1.71it/s]
Train steps ... :  22%|██▏       | 21999/100000 [6:29:54<12:38:44,  1.71it/s]
Train steps ... :  22%|██▏       | 22000/100000 [6:29:54<12:39:13,  1.71it/s]Step... (22000 / 100000 | Loss: 1.1823945045471191, Learning Rate: 7.839195979899498e-05)
+
                                                                             
Step... (22000 / 100000 | Loss: 1.0635530948638916, Learning Rate: 7.839195979899498e-05)
+
Train steps ... :  22%|██▏       | 22000/100000 [6:29:54<12:39:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22001/100000 [6:29:55<12:39:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22002/100000 [6:29:55<12:38:42,  1.71it/s]
Train steps ... :  22%|██▏       | 22003/100000 [6:29:56<12:38:32,  1.71it/s]
Train steps ... :  22%|██▏       | 22004/100000 [6:29:57<12:39:15,  1.71it/s]
Train steps ... :  22%|██▏       | 22005/100000 [6:29:57<12:39:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22006/100000 [6:29:58<12:38:58,  1.71it/s]
Train steps ... :  22%|██▏       | 22007/100000 [6:29:58<12:39:06,  1.71it/s]
Train steps ... :  22%|██▏       | 22008/100000 [6:29:59<12:38:36,  1.71it/s]
Train steps ... :  22%|██▏       | 22009/100000 [6:29:59<12:40:02,  1.71it/s]
Train steps ... :  22%|██▏       | 22010/100000 [6:30:00<12:39:35,  1.71it/s]
Train steps ... :  22%|██▏       | 22011/100000 [6:30:01<12:39:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22012/100000 [6:30:01<12:39:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22013/100000 [6:30:02<12:38:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22014/100000 [6:30:02<12:38:35,  1.71it/s]
Train steps ... :  22%|██▏       | 22015/100000 [6:30:03<12:38:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22016/100000 [6:30:04<12:39:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22017/100000 [6:30:04<12:39:59,  1.71it/s]
Train steps ... :  22%|██▏       | 22018/100000 [6:30:05<12:39:34,  1.71it/s]
Train steps ... :  22%|██▏       | 22019/100000 [6:30:05<12:39:35,  1.71it/s]
Train steps ... :  22%|██▏       | 22020/100000 [6:30:06<12:39:20,  1.71it/s]
Train steps ... :  22%|██▏       | 22021/100000 [6:30:06<12:39:59,  1.71it/s]
Train steps ... :  22%|██▏       | 22022/100000 [6:30:07<12:39:34,  1.71it/s]
Train steps ... :  22%|██▏       | 22023/100000 [6:30:08<12:39:28,  1.71it/s]
Train steps ... :  22%|██▏       | 22024/100000 [6:30:08<12:40:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22025/100000 [6:30:09<12:39:26,  1.71it/s]Step... (22025 / 100000 | Loss: 0.8452292680740356, Learning Rate: 7.836683417085427e-05)
+
                                                                             
Step... (22025 / 100000 | Loss: 0.7718006372451782, Learning Rate: 7.836683417085427e-05)
+
Train steps ... :  22%|██▏       | 22025/100000 [6:30:09<12:39:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22026/100000 [6:30:09<12:39:30,  1.71it/s]
Train steps ... :  22%|██▏       | 22027/100000 [6:30:10<12:39:36,  1.71it/s]
Train steps ... :  22%|██▏       | 22028/100000 [6:30:11<12:40:28,  1.71it/s]
Train steps ... :  22%|██▏       | 22029/100000 [6:30:11<12:39:31,  1.71it/s]
Train steps ... :  22%|██▏       | 22030/100000 [6:30:12<12:39:19,  1.71it/s]
Train steps ... :  22%|██▏       | 22031/100000 [6:30:12<12:39:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22032/100000 [6:30:13<12:39:46,  1.71it/s]
Train steps ... :  22%|██▏       | 22033/100000 [6:30:13<12:39:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22034/100000 [6:30:14<12:40:31,  1.71it/s]
Train steps ... :  22%|██▏       | 22035/100000 [6:30:15<12:40:42,  1.71it/s]
Train steps ... :  22%|██▏       | 22036/100000 [6:30:15<12:40:00,  1.71it/s]
Train steps ... :  22%|██▏       | 22037/100000 [6:30:16<12:39:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22038/100000 [6:30:16<12:43:32,  1.70it/s]
Train steps ... :  22%|██▏       | 22039/100000 [6:30:17<12:41:00,  1.71it/s]
Train steps ... :  22%|██▏       | 22040/100000 [6:30:18<12:40:29,  1.71it/s]
Train steps ... :  22%|██▏       | 22041/100000 [6:30:18<12:39:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22042/100000 [6:30:19<12:40:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22043/100000 [6:30:19<12:40:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22044/100000 [6:30:20<12:41:04,  1.71it/s]
Train steps ... :  22%|██▏       | 22045/100000 [6:30:20<12:40:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22046/100000 [6:30:21<12:39:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22047/100000 [6:30:22<12:39:27,  1.71it/s]
Train steps ... :  22%|██▏       | 22048/100000 [6:30:22<12:40:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22049/100000 [6:30:23<12:40:16,  1.71it/s]
Train steps ... :  22%|██▏       | 22050/100000 [6:30:23<12:39:57,  1.71it/s]Step... (22050 / 100000 | Loss: 1.1217472553253174, Learning Rate: 7.834170854271357e-05)
+
                                                                             
Step... (22050 / 100000 | Loss: 1.091805100440979, Learning Rate: 7.834170854271357e-05)
+
Train steps ... :  22%|██▏       | 22050/100000 [6:30:24<12:39:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22051/100000 [6:30:24<12:40:44,  1.71it/s]
Train steps ... :  22%|██▏       | 22052/100000 [6:30:25<12:40:55,  1.71it/s]
Train steps ... :  22%|██▏       | 22053/100000 [6:30:25<12:40:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22054/100000 [6:30:26<12:39:49,  1.71it/s]
Train steps ... :  22%|██▏       | 22055/100000 [6:30:26<12:39:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22056/100000 [6:30:27<12:40:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22057/100000 [6:30:27<12:39:55,  1.71it/s]
Train steps ... :  22%|██▏       | 22058/100000 [6:30:28<12:39:41,  1.71it/s]
Train steps ... :  22%|██▏       | 22059/100000 [6:30:29<12:40:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22060/100000 [6:30:29<12:39:10,  1.71it/s]
Train steps ... :  22%|██▏       | 22061/100000 [6:30:30<12:39:03,  1.71it/s]
Train steps ... :  22%|██▏       | 22062/100000 [6:30:30<12:39:02,  1.71it/s]
Train steps ... :  22%|██▏       | 22063/100000 [6:30:31<12:38:54,  1.71it/s]
Train steps ... :  22%|██▏       | 22064/100000 [6:30:32<12:38:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22065/100000 [6:30:32<12:38:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22066/100000 [6:30:33<12:39:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22067/100000 [6:30:33<12:39:42,  1.71it/s]
Train steps ... :  22%|██▏       | 22068/100000 [6:30:34<12:39:48,  1.71it/s]
Train steps ... :  22%|██▏       | 22069/100000 [6:30:35<12:39:19,  1.71it/s]
Train steps ... :  22%|██▏       | 22070/100000 [6:30:35<12:39:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22071/100000 [6:30:36<12:39:42,  1.71it/s]
Train steps ... :  22%|██▏       | 22072/100000 [6:30:36<12:39:54,  1.71it/s]
Train steps ... :  22%|██▏       | 22073/100000 [6:30:37<12:38:27,  1.71it/s]
Train steps ... :  22%|██▏       | 22074/100000 [6:30:37<12:40:33,  1.71it/s]
Train steps ... :  22%|██▏       | 22075/100000 [6:30:38<12:40:00,  1.71it/s]Step... (22075 / 100000 | Loss: 0.9666452407836914, Learning Rate: 7.831658291457287e-05)
+
                                                                             
Step... (22075 / 100000 | Loss: 0.6234397292137146, Learning Rate: 7.831658291457287e-05)
+
Train steps ... :  22%|██▏       | 22075/100000 [6:30:38<12:40:00,  1.71it/s]
Train steps ... :  22%|██▏       | 22076/100000 [6:30:39<12:39:27,  1.71it/s]
Train steps ... :  22%|██▏       | 22077/100000 [6:30:39<12:38:47,  1.71it/s]
Train steps ... :  22%|██▏       | 22078/100000 [6:30:40<12:39:20,  1.71it/s]
Train steps ... :  22%|██▏       | 22079/100000 [6:30:40<12:39:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22080/100000 [6:30:41<12:39:08,  1.71it/s]
Train steps ... :  22%|██▏       | 22081/100000 [6:30:42<12:38:55,  1.71it/s]
Train steps ... :  22%|██▏       | 22082/100000 [6:30:42<12:39:10,  1.71it/s]
Train steps ... :  22%|██▏       | 22083/100000 [6:30:43<12:39:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22084/100000 [6:30:43<12:41:22,  1.71it/s]
Train steps ... :  22%|██▏       | 22085/100000 [6:30:44<12:40:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22086/100000 [6:30:44<12:40:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22087/100000 [6:30:45<12:39:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22088/100000 [6:30:46<12:39:07,  1.71it/s]
Train steps ... :  22%|██▏       | 22089/100000 [6:30:46<12:38:59,  1.71it/s]
Train steps ... :  22%|██▏       | 22090/100000 [6:30:47<12:38:30,  1.71it/s]
Train steps ... :  22%|██▏       | 22091/100000 [6:30:47<12:38:00,  1.71it/s]
Train steps ... :  22%|██▏       | 22092/100000 [6:30:48<12:38:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22093/100000 [6:30:49<12:38:34,  1.71it/s]
Train steps ... :  22%|██▏       | 22094/100000 [6:30:49<12:38:48,  1.71it/s]
Train steps ... :  22%|██▏       | 22095/100000 [6:30:50<12:38:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22096/100000 [6:30:50<12:38:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22097/100000 [6:30:51<12:38:07,  1.71it/s]
Train steps ... :  22%|██▏       | 22098/100000 [6:30:51<12:38:44,  1.71it/s]
Train steps ... :  22%|██▏       | 22099/100000 [6:30:52<12:39:19,  1.71it/s]
Train steps ... :  22%|██▏       | 22100/100000 [6:30:53<12:40:05,  1.71it/s]Step... (22100 / 100000 | Loss: 1.0403587818145752, Learning Rate: 7.829145728643216e-05)
+
                                                                             
Step... (22100 / 100000 | Loss: 0.865020215511322, Learning Rate: 7.829145728643216e-05)
+
Train steps ... :  22%|██▏       | 22100/100000 [6:30:53<12:40:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22101/100000 [6:30:53<12:39:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22102/100000 [6:30:54<12:39:20,  1.71it/s]
Train steps ... :  22%|██▏       | 22103/100000 [6:30:54<12:38:58,  1.71it/s]
Train steps ... :  22%|██▏       | 22104/100000 [6:30:55<12:39:36,  1.71it/s]
Train steps ... :  22%|██▏       | 22105/100000 [6:30:56<12:39:01,  1.71it/s]
Train steps ... :  22%|██▏       | 22106/100000 [6:30:56<12:39:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22107/100000 [6:30:57<12:39:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22108/100000 [6:30:57<12:38:54,  1.71it/s]
Train steps ... :  22%|██▏       | 22109/100000 [6:30:58<12:39:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22110/100000 [6:30:58<12:39:16,  1.71it/s]
Train steps ... :  22%|██▏       | 22111/100000 [6:30:59<12:40:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22112/100000 [6:31:00<12:39:27,  1.71it/s]
Train steps ... :  22%|██▏       | 22113/100000 [6:31:00<12:39:36,  1.71it/s]
Train steps ... :  22%|██▏       | 22114/100000 [6:31:01<12:38:56,  1.71it/s]
Train steps ... :  22%|██▏       | 22115/100000 [6:31:01<12:38:15,  1.71it/s]
Train steps ... :  22%|██▏       | 22116/100000 [6:31:02<12:38:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22117/100000 [6:31:03<12:38:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22118/100000 [6:31:03<12:38:00,  1.71it/s]
Train steps ... :  22%|██▏       | 22119/100000 [6:31:04<12:38:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22120/100000 [6:31:04<12:37:54,  1.71it/s]
Train steps ... :  22%|██▏       | 22121/100000 [6:31:05<12:37:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22122/100000 [6:31:05<12:37:53,  1.71it/s]
Train steps ... :  22%|██▏       | 22123/100000 [6:31:06<12:42:14,  1.70it/s]
Train steps ... :  22%|██▏       | 22124/100000 [6:31:07<12:40:15,  1.71it/s]
Train steps ... :  22%|██▏       | 22125/100000 [6:31:07<12:39:26,  1.71it/s]Step... (22125 / 100000 | Loss: 1.1322669982910156, Learning Rate: 7.826633165829146e-05)
+
                                                                             
Step... (22125 / 100000 | Loss: 0.9749542474746704, Learning Rate: 7.826633165829146e-05)
+
Train steps ... :  22%|██▏       | 22125/100000 [6:31:08<12:39:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22126/100000 [6:31:08<12:39:54,  1.71it/s]
Train steps ... :  22%|██▏       | 22127/100000 [6:31:08<12:40:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22128/100000 [6:31:09<12:38:47,  1.71it/s]
Train steps ... :  22%|██▏       | 22129/100000 [6:31:10<12:39:00,  1.71it/s]
Train steps ... :  22%|██▏       | 22130/100000 [6:31:10<12:39:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22131/100000 [6:31:11<12:38:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22132/100000 [6:31:11<12:38:18,  1.71it/s]
Train steps ... :  22%|██▏       | 22133/100000 [6:31:12<12:38:19,  1.71it/s]
Train steps ... :  22%|██▏       | 22134/100000 [6:31:13<12:37:46,  1.71it/s]
Train steps ... :  22%|██▏       | 22135/100000 [6:31:13<12:39:04,  1.71it/s]
Train steps ... :  22%|██▏       | 22136/100000 [6:31:14<12:38:25,  1.71it/s]
Train steps ... :  22%|██▏       | 22137/100000 [6:31:14<12:38:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22138/100000 [6:31:15<12:38:08,  1.71it/s]
Train steps ... :  22%|██▏       | 22139/100000 [6:31:15<12:37:40,  1.71it/s]
Train steps ... :  22%|██▏       | 22140/100000 [6:31:16<12:37:15,  1.71it/s]
Train steps ... :  22%|██▏       | 22141/100000 [6:31:17<12:38:18,  1.71it/s]
Train steps ... :  22%|██▏       | 22142/100000 [6:31:17<12:38:51,  1.71it/s]
Train steps ... :  22%|██▏       | 22143/100000 [6:31:18<12:39:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22144/100000 [6:31:18<12:39:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22145/100000 [6:31:19<12:40:15,  1.71it/s]
Train steps ... :  22%|██▏       | 22146/100000 [6:31:20<12:39:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22147/100000 [6:31:20<12:38:48,  1.71it/s]
Train steps ... :  22%|██▏       | 22148/100000 [6:31:21<12:38:51,  1.71it/s]
Train steps ... :  22%|██▏       | 22149/100000 [6:31:21<12:37:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22150/100000 [6:31:22<12:37:37,  1.71it/s]Step... (22150 / 100000 | Loss: 0.8435255289077759, Learning Rate: 7.824120603015076e-05)
+
                                                                             
Step... (22150 / 100000 | Loss: 0.9772441387176514, Learning Rate: 7.824120603015076e-05)
+
Train steps ... :  22%|██▏       | 22150/100000 [6:31:22<12:37:37,  1.71it/s]
Train steps ... :  22%|██▏       | 22151/100000 [6:31:22<12:38:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22152/100000 [6:31:23<12:37:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22153/100000 [6:31:24<12:37:17,  1.71it/s]
Train steps ... :  22%|██▏       | 22154/100000 [6:31:24<12:37:39,  1.71it/s]
Train steps ... :  22%|██▏       | 22155/100000 [6:31:25<12:37:27,  1.71it/s]
Train steps ... :  22%|██▏       | 22156/100000 [6:31:25<12:37:09,  1.71it/s]
Train steps ... :  22%|██▏       | 22157/100000 [6:31:26<12:37:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22158/100000 [6:31:27<12:39:39,  1.71it/s]
Train steps ... :  22%|██▏       | 22159/100000 [6:31:27<12:38:09,  1.71it/s]
Train steps ... :  22%|██▏       | 22160/100000 [6:31:28<12:39:06,  1.71it/s]
Train steps ... :  22%|██▏       | 22161/100000 [6:31:28<12:39:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22162/100000 [6:31:29<12:38:29,  1.71it/s]
Train steps ... :  22%|██▏       | 22163/100000 [6:31:29<12:38:46,  1.71it/s]
Train steps ... :  22%|██▏       | 22164/100000 [6:31:30<12:38:58,  1.71it/s]
Train steps ... :  22%|██▏       | 22165/100000 [6:31:31<12:38:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22166/100000 [6:31:31<12:38:36,  1.71it/s]
Train steps ... :  22%|██▏       | 22167/100000 [6:31:32<12:38:53,  1.71it/s]
Train steps ... :  22%|██▏       | 22168/100000 [6:31:32<12:39:02,  1.71it/s]
Train steps ... :  22%|██▏       | 22169/100000 [6:31:33<12:38:17,  1.71it/s]
Train steps ... :  22%|██▏       | 22170/100000 [6:31:34<12:38:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22171/100000 [6:31:34<12:38:27,  1.71it/s]
Train steps ... :  22%|██▏       | 22172/100000 [6:31:35<12:38:17,  1.71it/s]
Train steps ... :  22%|██▏       | 22173/100000 [6:31:35<12:37:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22174/100000 [6:31:36<12:38:37,  1.71it/s]
Train steps ... :  22%|██▏       | 22175/100000 [6:31:36<12:38:10,  1.71it/s]Step... (22175 / 100000 | Loss: 0.9358765482902527, Learning Rate: 7.821608040201005e-05)
+
                                                                             
Step... (22175 / 100000 | Loss: 1.1234654188156128, Learning Rate: 7.821608040201005e-05)
+
Train steps ... :  22%|██▏       | 22175/100000 [6:31:37<12:38:10,  1.71it/s]
Train steps ... :  22%|██▏       | 22176/100000 [6:31:37<12:40:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22177/100000 [6:31:38<12:38:09,  1.71it/s]
Train steps ... :  22%|██▏       | 22178/100000 [6:31:38<12:37:56,  1.71it/s]
Train steps ... :  22%|██▏       | 22179/100000 [6:31:39<12:37:56,  1.71it/s]
Train steps ... :  22%|██▏       | 22180/100000 [6:31:39<12:38:58,  1.71it/s]
Train steps ... :  22%|██▏       | 22181/100000 [6:31:40<12:37:56,  1.71it/s]
Train steps ... :  22%|██▏       | 22182/100000 [6:31:41<12:38:04,  1.71it/s]
Train steps ... :  22%|██▏       | 22183/100000 [6:31:41<12:37:28,  1.71it/s]
Train steps ... :  22%|██▏       | 22184/100000 [6:31:42<12:37:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22185/100000 [6:31:42<12:37:49,  1.71it/s]
Train steps ... :  22%|██▏       | 22186/100000 [6:31:43<12:37:53,  1.71it/s]
Train steps ... :  22%|██▏       | 22187/100000 [6:31:44<12:41:12,  1.70it/s]
Train steps ... :  22%|██▏       | 22188/100000 [6:31:44<12:39:03,  1.71it/s]
Train steps ... :  22%|██▏       | 22189/100000 [6:31:45<12:38:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22190/100000 [6:31:45<12:37:54,  1.71it/s]
Train steps ... :  22%|██▏       | 22191/100000 [6:31:46<12:37:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22192/100000 [6:31:46<12:38:16,  1.71it/s]
Train steps ... :  22%|██▏       | 22193/100000 [6:31:47<12:38:37,  1.71it/s]
Train steps ... :  22%|██▏       | 22194/100000 [6:31:48<12:37:30,  1.71it/s]
Train steps ... :  22%|██▏       | 22195/100000 [6:31:48<12:38:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22196/100000 [6:31:49<12:37:47,  1.71it/s]
Train steps ... :  22%|██▏       | 22197/100000 [6:31:49<12:38:37,  1.71it/s]
Train steps ... :  22%|██▏       | 22198/100000 [6:31:50<12:38:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22199/100000 [6:31:51<12:38:37,  1.71it/s]
Train steps ... :  22%|██▏       | 22200/100000 [6:31:51<12:39:25,  1.71it/s]Step... (22200 / 100000 | Loss: 1.525654673576355, Learning Rate: 7.819095477386935e-05)
+
                                                                             
Step... (22200 / 100000 | Loss: 0.7573925256729126, Learning Rate: 7.819095477386935e-05)
+
Train steps ... :  22%|██▏       | 22200/100000 [6:31:51<12:39:25,  1.71it/s]
Train steps ... :  22%|██▏       | 22201/100000 [6:31:52<12:39:53,  1.71it/s]
Train steps ... :  22%|██▏       | 22202/100000 [6:31:52<12:39:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22203/100000 [6:31:53<12:38:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22204/100000 [6:31:53<12:37:55,  1.71it/s]
Train steps ... :  22%|██▏       | 22205/100000 [6:31:54<12:38:04,  1.71it/s]
Train steps ... :  22%|██▏       | 22206/100000 [6:31:55<12:37:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22207/100000 [6:31:55<12:37:35,  1.71it/s]
Train steps ... :  22%|██▏       | 22208/100000 [6:31:56<12:37:22,  1.71it/s]
Train steps ... :  22%|██▏       | 22209/100000 [6:31:56<12:37:35,  1.71it/s]
Train steps ... :  22%|██▏       | 22210/100000 [6:31:57<12:37:39,  1.71it/s]
Train steps ... :  22%|██▏       | 22211/100000 [6:31:58<12:37:28,  1.71it/s]
Train steps ... :  22%|██▏       | 22212/100000 [6:31:58<12:38:01,  1.71it/s]
Train steps ... :  22%|██▏       | 22213/100000 [6:31:59<12:37:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22214/100000 [6:31:59<12:37:15,  1.71it/s]
Train steps ... :  22%|██▏       | 22215/100000 [6:32:00<12:37:01,  1.71it/s]
Train steps ... :  22%|██▏       | 22216/100000 [6:32:00<12:37:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22217/100000 [6:32:01<12:37:40,  1.71it/s]
Train steps ... :  22%|██▏       | 22218/100000 [6:32:02<12:37:18,  1.71it/s]
Train steps ... :  22%|██▏       | 22219/100000 [6:32:02<12:38:03,  1.71it/s]
Train steps ... :  22%|██▏       | 22220/100000 [6:32:03<12:37:56,  1.71it/s]
Train steps ... :  22%|██▏       | 22221/100000 [6:32:03<12:37:18,  1.71it/s]
Train steps ... :  22%|██▏       | 22222/100000 [6:32:04<12:37:14,  1.71it/s]
Train steps ... :  22%|██▏       | 22223/100000 [6:32:05<12:37:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22224/100000 [6:32:05<12:37:25,  1.71it/s]
Train steps ... :  22%|██▏       | 22225/100000 [6:32:06<12:36:59,  1.71it/s]Step... (22225 / 100000 | Loss: 1.0908409357070923, Learning Rate: 7.816582914572865e-05)
+
                                                                             
Step... (22225 / 100000 | Loss: 0.9027966260910034, Learning Rate: 7.816582914572865e-05)
+
Train steps ... :  22%|██▏       | 22225/100000 [6:32:06<12:36:59,  1.71it/s]
Train steps ... :  22%|██▏       | 22226/100000 [6:32:06<12:37:27,  1.71it/s]
Train steps ... :  22%|██▏       | 22227/100000 [6:32:07<12:38:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22228/100000 [6:32:07<12:37:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22229/100000 [6:32:08<12:37:20,  1.71it/s]
Train steps ... :  22%|██▏       | 22230/100000 [6:32:09<12:37:58,  1.71it/s]
Train steps ... :  22%|██▏       | 22231/100000 [6:32:09<12:37:46,  1.71it/s]
Train steps ... :  22%|██▏       | 22232/100000 [6:32:10<12:37:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22233/100000 [6:32:10<12:37:49,  1.71it/s]
Train steps ... :  22%|██▏       | 22234/100000 [6:32:11<12:38:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22235/100000 [6:32:12<12:38:15,  1.71it/s]
Train steps ... :  22%|██▏       | 22236/100000 [6:32:12<12:38:02,  1.71it/s]
Train steps ... :  22%|██▏       | 22237/100000 [6:32:13<12:38:41,  1.71it/s]
Train steps ... :  22%|██▏       | 22238/100000 [6:32:13<12:37:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22239/100000 [6:32:14<12:37:22,  1.71it/s]
Train steps ... :  22%|██▏       | 22240/100000 [6:32:14<12:37:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22241/100000 [6:32:15<12:37:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22242/100000 [6:32:16<12:37:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22243/100000 [6:32:16<12:37:58,  1.71it/s]
Train steps ... :  22%|██▏       | 22244/100000 [6:32:17<12:37:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22245/100000 [6:32:17<12:37:30,  1.71it/s]
Train steps ... :  22%|██▏       | 22246/100000 [6:32:18<12:38:10,  1.71it/s]
Train steps ... :  22%|██▏       | 22247/100000 [6:32:19<12:37:32,  1.71it/s]
Train steps ... :  22%|██▏       | 22248/100000 [6:32:19<12:37:34,  1.71it/s]
Train steps ... :  22%|██▏       | 22249/100000 [6:32:20<12:37:22,  1.71it/s]
Train steps ... :  22%|██▏       | 22250/100000 [6:32:20<12:38:18,  1.71it/s]Step... (22250 / 100000 | Loss: 0.7585623860359192, Learning Rate: 7.814070351758794e-05)
+
                                                                             
Step... (22250 / 100000 | Loss: 1.0239014625549316, Learning Rate: 7.814070351758794e-05)
+
Train steps ... :  22%|██▏       | 22250/100000 [6:32:21<12:38:18,  1.71it/s]
Train steps ... :  22%|██▏       | 22251/100000 [6:32:21<12:37:58,  1.71it/s]
Train steps ... :  22%|██▏       | 22252/100000 [6:32:22<12:37:25,  1.71it/s]
Train steps ... :  22%|██▏       | 22253/100000 [6:32:22<12:37:07,  1.71it/s]
Train steps ... :  22%|██▏       | 22254/100000 [6:32:23<12:36:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22255/100000 [6:32:23<12:36:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22256/100000 [6:32:24<12:36:29,  1.71it/s]
Train steps ... :  22%|██▏       | 22257/100000 [6:32:24<12:36:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22258/100000 [6:32:25<12:37:20,  1.71it/s]
Train steps ... :  22%|██▏       | 22259/100000 [6:32:26<12:38:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22260/100000 [6:32:26<12:37:59,  1.71it/s]
Train steps ... :  22%|██▏       | 22261/100000 [6:32:27<12:37:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22262/100000 [6:32:27<12:37:33,  1.71it/s]
Train steps ... :  22%|██▏       | 22263/100000 [6:32:28<12:37:30,  1.71it/s]
Train steps ... :  22%|██▏       | 22264/100000 [6:32:29<12:36:59,  1.71it/s]
Train steps ... :  22%|██▏       | 22265/100000 [6:32:29<12:36:56,  1.71it/s]
Train steps ... :  22%|██▏       | 22266/100000 [6:32:30<12:37:06,  1.71it/s]
Train steps ... :  22%|██▏       | 22267/100000 [6:32:30<12:37:14,  1.71it/s]
Train steps ... :  22%|██▏       | 22268/100000 [6:32:31<12:36:32,  1.71it/s]
Train steps ... :  22%|██▏       | 22269/100000 [6:32:31<12:37:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22270/100000 [6:32:32<12:38:06,  1.71it/s]
Train steps ... :  22%|██▏       | 22271/100000 [6:32:33<12:38:47,  1.71it/s]
Train steps ... :  22%|██▏       | 22272/100000 [6:32:33<12:37:59,  1.71it/s]
Train steps ... :  22%|██▏       | 22273/100000 [6:32:34<12:38:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22274/100000 [6:32:34<12:38:09,  1.71it/s]
Train steps ... :  22%|██▏       | 22275/100000 [6:32:35<12:38:40,  1.71it/s]Step... (22275 / 100000 | Loss: 0.8413459062576294, Learning Rate: 7.811557788944724e-05)
+
                                                                             
Step... (22275 / 100000 | Loss: 1.2987679243087769, Learning Rate: 7.811557788944724e-05)
+
Train steps ... :  22%|██▏       | 22275/100000 [6:32:35<12:38:40,  1.71it/s]
Train steps ... :  22%|██▏       | 22276/100000 [6:32:36<12:38:19,  1.71it/s]
Train steps ... :  22%|██▏       | 22277/100000 [6:32:36<12:37:48,  1.71it/s]
Train steps ... :  22%|██▏       | 22278/100000 [6:32:37<12:37:31,  1.71it/s]
Train steps ... :  22%|██▏       | 22279/100000 [6:32:37<12:38:03,  1.71it/s]
Train steps ... :  22%|██▏       | 22280/100000 [6:32:38<12:36:33,  1.71it/s]
Train steps ... :  22%|██▏       | 22281/100000 [6:32:38<12:38:08,  1.71it/s]
Train steps ... :  22%|██▏       | 22282/100000 [6:32:39<12:37:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22283/100000 [6:32:40<12:37:01,  1.71it/s]
Train steps ... :  22%|██▏       | 22284/100000 [6:32:40<12:37:02,  1.71it/s]
Train steps ... :  22%|██▏       | 22285/100000 [6:32:41<12:36:33,  1.71it/s]
Train steps ... :  22%|██▏       | 22286/100000 [6:32:41<12:36:43,  1.71it/s]
Train steps ... :  22%|██▏       | 22287/100000 [6:32:42<12:36:54,  1.71it/s]
Train steps ... :  22%|██▏       | 22288/100000 [6:32:43<12:36:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22289/100000 [6:32:43<12:36:25,  1.71it/s]
Train steps ... :  22%|██▏       | 22290/100000 [6:32:44<12:37:09,  1.71it/s]
Train steps ... :  22%|██▏       | 22291/100000 [6:32:44<12:37:01,  1.71it/s]
Train steps ... :  22%|██▏       | 22292/100000 [6:32:45<12:36:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22293/100000 [6:32:45<12:36:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22294/100000 [6:32:46<12:37:56,  1.71it/s]
Train steps ... :  22%|██▏       | 22295/100000 [6:32:47<12:37:06,  1.71it/s]
Train steps ... :  22%|██▏       | 22296/100000 [6:32:47<12:39:43,  1.70it/s]
Train steps ... :  22%|██▏       | 22297/100000 [6:32:48<12:38:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22298/100000 [6:32:48<12:37:30,  1.71it/s]
Train steps ... :  22%|██▏       | 22299/100000 [6:32:49<12:38:06,  1.71it/s]
Train steps ... :  22%|██▏       | 22300/100000 [6:32:50<12:37:29,  1.71it/s]Step... (22300 / 100000 | Loss: 0.7189918756484985, Learning Rate: 7.809045226130654e-05)
+
                                                                             
Step... (22300 / 100000 | Loss: 1.0269315242767334, Learning Rate: 7.809045226130654e-05)
+
Train steps ... :  22%|██▏       | 22300/100000 [6:32:50<12:37:29,  1.71it/s]
Train steps ... :  22%|██▏       | 22301/100000 [6:32:50<12:37:43,  1.71it/s]
Train steps ... :  22%|██▏       | 22302/100000 [6:32:51<12:36:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22303/100000 [6:32:51<12:37:18,  1.71it/s]
Train steps ... :  22%|██▏       | 22304/100000 [6:32:52<12:36:53,  1.71it/s]
Train steps ... :  22%|██▏       | 22305/100000 [6:32:52<12:36:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22306/100000 [6:32:53<12:37:27,  1.71it/s]
Train steps ... :  22%|██▏       | 22307/100000 [6:32:54<12:36:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22308/100000 [6:32:54<12:36:32,  1.71it/s]
Train steps ... :  22%|██▏       | 22309/100000 [6:32:55<12:36:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22310/100000 [6:32:55<12:37:36,  1.71it/s]
Train steps ... :  22%|██▏       | 22311/100000 [6:32:56<12:35:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22312/100000 [6:32:57<12:36:55,  1.71it/s]
Train steps ... :  22%|██▏       | 22313/100000 [6:32:57<12:36:35,  1.71it/s]
Train steps ... :  22%|██▏       | 22314/100000 [6:32:58<12:36:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22315/100000 [6:32:58<12:36:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22316/100000 [6:32:59<12:37:43,  1.71it/s]
Train steps ... :  22%|██▏       | 22317/100000 [6:33:00<12:38:31,  1.71it/s]
Train steps ... :  22%|██▏       | 22318/100000 [6:33:00<12:37:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22319/100000 [6:33:01<12:37:09,  1.71it/s]
Train steps ... :  22%|██▏       | 22320/100000 [6:33:01<12:36:48,  1.71it/s]
Train steps ... :  22%|██▏       | 22321/100000 [6:33:02<12:36:20,  1.71it/s]
Train steps ... :  22%|██▏       | 22322/100000 [6:33:02<12:37:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22323/100000 [6:33:03<12:37:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22324/100000 [6:33:04<12:37:15,  1.71it/s]
Train steps ... :  22%|██▏       | 22325/100000 [6:33:04<12:37:46,  1.71it/s]Step... (22325 / 100000 | Loss: 0.9960604906082153, Learning Rate: 7.806532663316583e-05)
+
                                                                             
Step... (22325 / 100000 | Loss: 0.6975178718566895, Learning Rate: 7.806532663316583e-05)
+
Train steps ... :  22%|██▏       | 22325/100000 [6:33:05<12:37:46,  1.71it/s]
Train steps ... :  22%|██▏       | 22326/100000 [6:33:05<12:37:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22327/100000 [6:33:05<12:36:37,  1.71it/s]
Train steps ... :  22%|██▏       | 22328/100000 [6:33:06<12:36:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22329/100000 [6:33:07<12:38:29,  1.71it/s]
Train steps ... :  22%|██▏       | 22330/100000 [6:33:07<12:37:55,  1.71it/s]
Train steps ... :  22%|██▏       | 22331/100000 [6:33:08<12:38:10,  1.71it/s]
Train steps ... :  22%|██▏       | 22332/100000 [6:33:08<12:36:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22333/100000 [6:33:09<12:36:56,  1.71it/s]
Train steps ... :  22%|██▏       | 22334/100000 [6:33:09<12:36:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22335/100000 [6:33:10<12:36:22,  1.71it/s]
Train steps ... :  22%|██▏       | 22336/100000 [6:33:11<12:37:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22337/100000 [6:33:11<12:36:18,  1.71it/s]
Train steps ... :  22%|██▏       | 22338/100000 [6:33:12<12:36:32,  1.71it/s]
Train steps ... :  22%|██▏       | 22339/100000 [6:33:12<12:35:53,  1.71it/s]
Train steps ... :  22%|██▏       | 22340/100000 [6:33:13<12:36:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22341/100000 [6:33:14<12:36:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22342/100000 [6:33:14<12:35:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22343/100000 [6:33:15<12:36:04,  1.71it/s]
Train steps ... :  22%|██▏       | 22344/100000 [6:33:15<12:36:36,  1.71it/s]
Train steps ... :  22%|██▏       | 22345/100000 [6:33:16<12:36:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22346/100000 [6:33:16<12:36:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22347/100000 [6:33:17<12:36:33,  1.71it/s]
Train steps ... :  22%|██▏       | 22348/100000 [6:33:18<12:36:03,  1.71it/s]
Train steps ... :  22%|██▏       | 22349/100000 [6:33:18<12:35:39,  1.71it/s]
Train steps ... :  22%|██▏       | 22350/100000 [6:33:19<12:36:17,  1.71it/s]Step... (22350 / 100000 | Loss: 1.0657384395599365, Learning Rate: 7.804020100502513e-05)
+
                                                                             
Step... (22350 / 100000 | Loss: 0.9615559577941895, Learning Rate: 7.804020100502513e-05)
+
Train steps ... :  22%|██▏       | 22350/100000 [6:33:19<12:36:17,  1.71it/s]
Train steps ... :  22%|██▏       | 22351/100000 [6:33:19<12:36:34,  1.71it/s]
Train steps ... :  22%|██▏       | 22352/100000 [6:33:20<12:36:41,  1.71it/s]
Train steps ... :  22%|██▏       | 22353/100000 [6:33:21<12:36:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22354/100000 [6:33:21<12:36:56,  1.71it/s]
Train steps ... :  22%|██▏       | 22355/100000 [6:33:22<12:36:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22356/100000 [6:33:22<12:37:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22357/100000 [6:33:23<12:36:10,  1.71it/s]
Train steps ... :  22%|██▏       | 22358/100000 [6:33:23<12:36:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22359/100000 [6:33:24<12:36:21,  1.71it/s]
Train steps ... :  22%|██▏       | 22360/100000 [6:33:25<12:37:01,  1.71it/s]
Train steps ... :  22%|██▏       | 22361/100000 [6:33:25<12:36:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22362/100000 [6:33:26<12:37:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22363/100000 [6:33:26<12:36:36,  1.71it/s]
Train steps ... :  22%|██▏       | 22364/100000 [6:33:27<12:36:17,  1.71it/s]
Train steps ... :  22%|██▏       | 22365/100000 [6:33:28<12:37:24,  1.71it/s]
Train steps ... :  22%|██▏       | 22366/100000 [6:33:28<12:36:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22367/100000 [6:33:29<12:36:51,  1.71it/s]
Train steps ... :  22%|██▏       | 22368/100000 [6:33:29<12:35:53,  1.71it/s]
Train steps ... :  22%|██▏       | 22369/100000 [6:33:30<12:36:37,  1.71it/s]
Train steps ... :  22%|██▏       | 22370/100000 [6:33:30<12:36:14,  1.71it/s]
Train steps ... :  22%|██▏       | 22371/100000 [6:33:31<12:36:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22372/100000 [6:33:32<12:36:07,  1.71it/s]
Train steps ... :  22%|██▏       | 22373/100000 [6:33:32<12:36:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22374/100000 [6:33:33<12:36:20,  1.71it/s]
Train steps ... :  22%|██▏       | 22375/100000 [6:33:33<12:36:16,  1.71it/s]Step... (22375 / 100000 | Loss: 1.241912841796875, Learning Rate: 7.801507537688443e-05)
+
                                                                             
Step... (22375 / 100000 | Loss: 1.0408965349197388, Learning Rate: 7.801507537688443e-05)
+
Train steps ... :  22%|██▏       | 22375/100000 [6:33:34<12:36:16,  1.71it/s]
Train steps ... :  22%|██▏       | 22376/100000 [6:33:34<12:36:39,  1.71it/s]
Train steps ... :  22%|██▏       | 22377/100000 [6:33:35<12:36:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22378/100000 [6:33:35<12:36:46,  1.71it/s]
Train steps ... :  22%|██▏       | 22379/100000 [6:33:36<12:36:32,  1.71it/s]
Train steps ... :  22%|██▏       | 22380/100000 [6:33:36<12:36:03,  1.71it/s]
Train steps ... :  22%|██▏       | 22381/100000 [6:33:37<12:36:07,  1.71it/s]
Train steps ... :  22%|██▏       | 22382/100000 [6:33:38<12:35:51,  1.71it/s]
Train steps ... :  22%|██▏       | 22383/100000 [6:33:38<12:35:51,  1.71it/s]
Train steps ... :  22%|██▏       | 22384/100000 [6:33:39<12:35:49,  1.71it/s]
Train steps ... :  22%|██▏       | 22385/100000 [6:33:39<12:36:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22386/100000 [6:33:40<12:35:34,  1.71it/s]
Train steps ... :  22%|██▏       | 22387/100000 [6:33:40<12:35:29,  1.71it/s]
Train steps ... :  22%|██▏       | 22388/100000 [6:33:41<12:35:34,  1.71it/s]
Train steps ... :  22%|██▏       | 22389/100000 [6:33:42<12:36:46,  1.71it/s]
Train steps ... :  22%|██▏       | 22390/100000 [6:33:42<12:35:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22391/100000 [6:33:43<12:35:25,  1.71it/s]
Train steps ... :  22%|██▏       | 22392/100000 [6:33:43<12:34:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22393/100000 [6:33:44<12:35:00,  1.71it/s]
Train steps ... :  22%|██▏       | 22394/100000 [6:33:45<12:35:01,  1.71it/s]
Train steps ... :  22%|██▏       | 22395/100000 [6:33:45<12:35:14,  1.71it/s]
Train steps ... :  22%|██▏       | 22396/100000 [6:33:46<12:36:04,  1.71it/s]
Train steps ... :  22%|██▏       | 22397/100000 [6:33:46<12:35:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22398/100000 [6:33:47<12:36:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22399/100000 [6:33:47<12:35:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22400/100000 [6:33:48<12:35:52,  1.71it/s]Step... (22400 / 100000 | Loss: 1.2989102602005005, Learning Rate: 7.798994974874372e-05)
+
                                                                             
Step... (22400 / 100000 | Loss: 0.9642370939254761, Learning Rate: 7.798994974874372e-05)
+
Train steps ... :  22%|██▏       | 22400/100000 [6:33:48<12:35:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22401/100000 [6:33:49<12:35:58,  1.71it/s]
Train steps ... :  22%|██▏       | 22402/100000 [6:33:49<12:36:01,  1.71it/s]
Train steps ... :  22%|██▏       | 22403/100000 [6:33:50<12:35:44,  1.71it/s]
Train steps ... :  22%|██▏       | 22404/100000 [6:33:50<12:35:14,  1.71it/s]
Train steps ... :  22%|██▏       | 22405/100000 [6:33:51<12:35:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22406/100000 [6:33:52<12:35:34,  1.71it/s]
Train steps ... :  22%|██▏       | 22407/100000 [6:33:52<12:36:04,  1.71it/s]
Train steps ... :  22%|██▏       | 22408/100000 [6:33:53<12:36:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22409/100000 [6:33:53<12:37:19,  1.71it/s]
Train steps ... :  22%|██▏       | 22410/100000 [6:33:54<12:36:46,  1.71it/s]
Train steps ... :  22%|██▏       | 22411/100000 [6:33:54<12:37:43,  1.71it/s]
Train steps ... :  22%|██▏       | 22412/100000 [6:33:55<12:36:55,  1.71it/s]
Train steps ... :  22%|██▏       | 22413/100000 [6:33:56<12:36:39,  1.71it/s]
Train steps ... :  22%|██▏       | 22414/100000 [6:33:56<12:36:58,  1.71it/s]
Train steps ... :  22%|██▏       | 22415/100000 [6:33:57<12:36:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22416/100000 [6:33:57<12:36:15,  1.71it/s]
Train steps ... :  22%|██▏       | 22417/100000 [6:33:58<12:35:54,  1.71it/s]
Train steps ... :  22%|██▏       | 22418/100000 [6:33:59<12:36:08,  1.71it/s]
Train steps ... :  22%|██▏       | 22419/100000 [6:33:59<12:35:42,  1.71it/s]
Train steps ... :  22%|██▏       | 22420/100000 [6:34:00<12:35:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22421/100000 [6:34:00<12:36:28,  1.71it/s]
Train steps ... :  22%|██▏       | 22422/100000 [6:34:01<12:36:19,  1.71it/s]
Train steps ... :  22%|██▏       | 22423/100000 [6:34:01<12:35:39,  1.71it/s]
Train steps ... :  22%|██▏       | 22424/100000 [6:34:02<12:35:48,  1.71it/s]
Train steps ... :  22%|██▏       | 22425/100000 [6:34:03<12:37:11,  1.71it/s]Step... (22425 / 100000 | Loss: 0.9123727083206177, Learning Rate: 7.796482412060302e-05)
+
                                                                             
Step... (22425 / 100000 | Loss: 0.8849239349365234, Learning Rate: 7.796482412060302e-05)
+
Train steps ... :  22%|██▏       | 22425/100000 [6:34:03<12:37:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22426/100000 [6:34:03<12:37:35,  1.71it/s]
Train steps ... :  22%|██▏       | 22427/100000 [6:34:04<12:36:22,  1.71it/s]
Train steps ... :  22%|██▏       | 22428/100000 [6:34:04<12:35:56,  1.71it/s]
Train steps ... :  22%|██▏       | 22429/100000 [6:34:05<12:35:44,  1.71it/s]
Train steps ... :  22%|██▏       | 22430/100000 [6:34:06<12:36:01,  1.71it/s]
Train steps ... :  22%|██▏       | 22431/100000 [6:34:06<12:35:49,  1.71it/s]
Train steps ... :  22%|██▏       | 22432/100000 [6:34:07<12:38:35,  1.70it/s]
Train steps ... :  22%|██▏       | 22433/100000 [6:34:07<12:35:55,  1.71it/s]
Train steps ... :  22%|██▏       | 22434/100000 [6:34:08<12:36:37,  1.71it/s]
Train steps ... :  22%|██▏       | 22435/100000 [6:34:09<12:36:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22436/100000 [6:34:09<12:35:47,  1.71it/s]
Train steps ... :  22%|██▏       | 22437/100000 [6:34:10<12:35:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22438/100000 [6:34:10<12:36:03,  1.71it/s]
Train steps ... :  22%|██▏       | 22439/100000 [6:34:11<12:36:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22440/100000 [6:34:11<12:36:05,  1.71it/s]
Train steps ... :  22%|██▏       | 22441/100000 [6:34:12<12:35:31,  1.71it/s]
Train steps ... :  22%|██▏       | 22442/100000 [6:34:13<12:36:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22443/100000 [6:34:13<12:36:41,  1.71it/s]
Train steps ... :  22%|██▏       | 22444/100000 [6:34:14<12:36:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22445/100000 [6:34:14<12:36:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22446/100000 [6:34:15<12:36:39,  1.71it/s]
Train steps ... :  22%|██▏       | 22447/100000 [6:34:16<12:37:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22448/100000 [6:34:16<12:37:06,  1.71it/s]
Train steps ... :  22%|██▏       | 22449/100000 [6:34:17<12:36:26,  1.71it/s]
Train steps ... :  22%|██▏       | 22450/100000 [6:34:17<12:36:50,  1.71it/s]Step... (22450 / 100000 | Loss: 0.7994601726531982, Learning Rate: 7.793969849246232e-05)
+
                                                                             
Step... (22450 / 100000 | Loss: 1.053167462348938, Learning Rate: 7.793969849246232e-05)
+
Train steps ... :  22%|██▏       | 22450/100000 [6:34:18<12:36:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22451/100000 [6:34:18<12:38:11,  1.70it/s]
Train steps ... :  22%|██▏       | 22452/100000 [6:34:18<12:37:10,  1.71it/s]
Train steps ... :  22%|██▏       | 22453/100000 [6:34:19<12:36:43,  1.71it/s]
Train steps ... :  22%|██▏       | 22454/100000 [6:34:20<12:36:06,  1.71it/s]
Train steps ... :  22%|██▏       | 22455/100000 [6:34:20<12:35:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22456/100000 [6:34:21<12:35:33,  1.71it/s]
Train steps ... :  22%|██▏       | 22457/100000 [6:34:21<12:35:30,  1.71it/s]
Train steps ... :  22%|██▏       | 22458/100000 [6:34:22<12:35:29,  1.71it/s]
Train steps ... :  22%|██▏       | 22459/100000 [6:34:23<12:35:14,  1.71it/s]
Train steps ... :  22%|██▏       | 22460/100000 [6:34:23<12:35:16,  1.71it/s]
Train steps ... :  22%|██▏       | 22461/100000 [6:34:24<12:34:25,  1.71it/s]
Train steps ... :  22%|██▏       | 22462/100000 [6:34:24<12:34:09,  1.71it/s]
Train steps ... :  22%|██▏       | 22463/100000 [6:34:25<12:34:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22464/100000 [6:34:25<12:35:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22465/100000 [6:34:26<12:35:48,  1.71it/s]
Train steps ... :  22%|██▏       | 22466/100000 [6:34:27<12:35:37,  1.71it/s]
Train steps ... :  22%|██▏       | 22467/100000 [6:34:27<12:35:47,  1.71it/s]
Train steps ... :  22%|██▏       | 22468/100000 [6:34:28<12:36:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22469/100000 [6:34:28<12:35:52,  1.71it/s]
Train steps ... :  22%|██▏       | 22470/100000 [6:34:29<12:37:40,  1.71it/s]
Train steps ... :  22%|██▏       | 22471/100000 [6:34:30<12:35:49,  1.71it/s]
Train steps ... :  22%|██▏       | 22472/100000 [6:34:30<12:35:48,  1.71it/s]
Train steps ... :  22%|██▏       | 22473/100000 [6:34:31<12:35:14,  1.71it/s]
Train steps ... :  22%|██▏       | 22474/100000 [6:34:31<12:36:07,  1.71it/s]
Train steps ... :  22%|██▏       | 22475/100000 [6:34:32<12:36:17,  1.71it/s]Step... (22475 / 100000 | Loss: 1.0293512344360352, Learning Rate: 7.791457286432161e-05)
+
                                                                             
Step... (22475 / 100000 | Loss: 0.9874007701873779, Learning Rate: 7.791457286432161e-05)
+
Train steps ... :  22%|██▏       | 22475/100000 [6:34:32<12:36:17,  1.71it/s]
Train steps ... :  22%|██▏       | 22476/100000 [6:34:32<12:35:57,  1.71it/s]
Train steps ... :  22%|██▏       | 22477/100000 [6:34:33<12:36:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22478/100000 [6:34:34<12:35:38,  1.71it/s]
Train steps ... :  22%|██▏       | 22479/100000 [6:34:34<12:35:20,  1.71it/s]
Train steps ... :  22%|██▏       | 22480/100000 [6:34:35<12:36:00,  1.71it/s]
Train steps ... :  22%|██▏       | 22481/100000 [6:34:35<12:35:23,  1.71it/s]
Train steps ... :  22%|██▏       | 22482/100000 [6:34:36<12:36:20,  1.71it/s]
Train steps ... :  22%|██▏       | 22483/100000 [6:34:37<12:36:14,  1.71it/s]
Train steps ... :  22%|██▏       | 22484/100000 [6:34:37<12:35:53,  1.71it/s]
Train steps ... :  22%|██▏       | 22485/100000 [6:34:38<12:36:03,  1.71it/s]
Train steps ... :  22%|██▏       | 22486/100000 [6:34:38<12:35:44,  1.71it/s]
Train steps ... :  22%|██▏       | 22487/100000 [6:34:39<12:35:11,  1.71it/s]
Train steps ... :  22%|██▏       | 22488/100000 [6:34:40<12:35:03,  1.71it/s]
Train steps ... :  22%|██▏       | 22489/100000 [6:34:40<12:35:07,  1.71it/s]
Train steps ... :  22%|██▏       | 22490/100000 [6:34:41<12:36:00,  1.71it/s]
Train steps ... :  22%|██▏       | 22491/100000 [6:34:41<12:35:50,  1.71it/s]
Train steps ... :  22%|██▏       | 22492/100000 [6:34:42<12:35:12,  1.71it/s]
Train steps ... :  22%|██▏       | 22493/100000 [6:34:42<12:35:13,  1.71it/s]
Train steps ... :  22%|██▏       | 22494/100000 [6:34:43<12:36:00,  1.71it/s]
Train steps ... :  22%|██▏       | 22495/100000 [6:34:44<12:35:07,  1.71it/s]
Train steps ... :  22%|██▏       | 22496/100000 [6:34:44<12:34:45,  1.71it/s]
Train steps ... :  22%|██▏       | 22497/100000 [6:34:45<12:34:28,  1.71it/s]
Train steps ... :  22%|██▏       | 22498/100000 [6:34:45<12:34:39,  1.71it/s]
Train steps ... :  22%|██▏       | 22499/100000 [6:34:46<12:35:46,  1.71it/s]
Train steps ... :  22%|██▎       | 22500/100000 [6:34:47<12:35:00,  1.71it/s]Step... (22500 / 100000 | Loss: 0.7232595682144165, Learning Rate: 7.788944723618091e-05)
+
                                                                             
Step... (22500 / 100000 | Loss: 0.737823486328125, Learning Rate: 7.788944723618091e-05)
+
Train steps ... :  22%|██▎       | 22500/100000 [6:34:47<12:35:00,  1.71it/s]
Train steps ... :  23%|██▎       | 22501/100000 [6:34:47<12:35:46,  1.71it/s]
Train steps ... :  23%|██▎       | 22502/100000 [6:34:48<12:35:00,  1.71it/s]
Train steps ... :  23%|██▎       | 22503/100000 [6:34:48<12:35:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22504/100000 [6:34:49<12:35:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22505/100000 [6:34:49<12:35:17,  1.71it/s]
Train steps ... :  23%|██▎       | 22506/100000 [6:34:50<12:35:19,  1.71it/s]
Train steps ... :  23%|██▎       | 22507/100000 [6:34:51<12:34:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22508/100000 [6:34:51<12:34:46,  1.71it/s]
Train steps ... :  23%|██▎       | 22509/100000 [6:34:52<12:35:18,  1.71it/s]
Train steps ... :  23%|██▎       | 22510/100000 [6:34:52<12:34:37,  1.71it/s]
Train steps ... :  23%|██▎       | 22511/100000 [6:34:53<12:34:33,  1.71it/s]
Train steps ... :  23%|██▎       | 22512/100000 [6:34:54<12:34:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22513/100000 [6:34:54<12:34:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22514/100000 [6:34:55<12:34:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22515/100000 [6:34:55<12:35:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22516/100000 [6:34:56<12:35:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22517/100000 [6:34:56<12:35:04,  1.71it/s]
Train steps ... :  23%|██▎       | 22518/100000 [6:34:57<12:35:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22519/100000 [6:34:58<12:35:44,  1.71it/s]
Train steps ... :  23%|██▎       | 22520/100000 [6:34:58<12:35:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22521/100000 [6:34:59<12:35:53,  1.71it/s]
Train steps ... :  23%|██▎       | 22522/100000 [6:34:59<12:36:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22523/100000 [6:35:00<12:36:24,  1.71it/s]
Train steps ... :  23%|██▎       | 22524/100000 [6:35:01<12:35:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22525/100000 [6:35:01<12:35:33,  1.71it/s]Step... (22525 / 100000 | Loss: 1.1204943656921387, Learning Rate: 7.78643216080402e-05)
+
                                                                             
Step... (22525 / 100000 | Loss: 0.9242497086524963, Learning Rate: 7.78643216080402e-05)
+
Train steps ... :  23%|██▎       | 22525/100000 [6:35:01<12:35:33,  1.71it/s]
Train steps ... :  23%|██▎       | 22526/100000 [6:35:02<12:35:07,  1.71it/s]
Train steps ... :  23%|██▎       | 22527/100000 [6:35:02<12:36:21,  1.71it/s]
Train steps ... :  23%|██▎       | 22528/100000 [6:35:03<12:35:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22529/100000 [6:35:03<12:35:09,  1.71it/s]
Train steps ... :  23%|██▎       | 22530/100000 [6:35:04<12:37:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22531/100000 [6:35:05<12:36:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22532/100000 [6:35:05<12:35:53,  1.71it/s]
Train steps ... :  23%|██▎       | 22533/100000 [6:35:06<12:35:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22534/100000 [6:35:06<12:36:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22535/100000 [6:35:07<12:35:36,  1.71it/s]
Train steps ... :  23%|██▎       | 22536/100000 [6:35:08<12:36:00,  1.71it/s]
Train steps ... :  23%|██▎       | 22537/100000 [6:35:08<12:34:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22538/100000 [6:35:09<12:35:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22539/100000 [6:35:09<12:34:24,  1.71it/s]
Train steps ... :  23%|██▎       | 22540/100000 [6:35:10<12:34:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22541/100000 [6:35:11<12:34:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22542/100000 [6:35:11<12:34:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22543/100000 [6:35:12<12:34:47,  1.71it/s]
Train steps ... :  23%|██▎       | 22544/100000 [6:35:12<12:34:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22545/100000 [6:35:13<12:35:30,  1.71it/s]
Train steps ... :  23%|██▎       | 22546/100000 [6:35:13<12:35:20,  1.71it/s]
Train steps ... :  23%|██▎       | 22547/100000 [6:35:14<12:34:54,  1.71it/s]
Train steps ... :  23%|██▎       | 22548/100000 [6:35:15<12:35:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22549/100000 [6:35:15<12:34:43,  1.71it/s]
Train steps ... :  23%|██▎       | 22550/100000 [6:35:16<12:35:02,  1.71it/s]Step... (22550 / 100000 | Loss: 0.728348970413208, Learning Rate: 7.78391959798995e-05)
+
                                                                             
Step... (22550 / 100000 | Loss: 0.9293402433395386, Learning Rate: 7.78391959798995e-05)
+
Train steps ... :  23%|██▎       | 22550/100000 [6:35:16<12:35:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22551/100000 [6:35:16<12:34:30,  1.71it/s]
Train steps ... :  23%|██▎       | 22552/100000 [6:35:17<12:35:17,  1.71it/s]
Train steps ... :  23%|██▎       | 22553/100000 [6:35:18<12:34:30,  1.71it/s]
Train steps ... :  23%|██▎       | 22554/100000 [6:35:18<12:35:34,  1.71it/s]
Train steps ... :  23%|██▎       | 22555/100000 [6:35:19<12:34:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22556/100000 [6:35:19<12:34:10,  1.71it/s]
Train steps ... :  23%|██▎       | 22557/100000 [6:35:20<12:34:17,  1.71it/s]
Train steps ... :  23%|██▎       | 22558/100000 [6:35:20<12:34:05,  1.71it/s]
Train steps ... :  23%|██▎       | 22559/100000 [6:35:21<12:35:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22560/100000 [6:35:22<12:34:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22561/100000 [6:35:22<12:35:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22562/100000 [6:35:23<12:34:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22563/100000 [6:35:23<12:35:14,  1.71it/s]
Train steps ... :  23%|██▎       | 22564/100000 [6:35:24<12:34:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22565/100000 [6:35:25<12:34:27,  1.71it/s]
Train steps ... :  23%|██▎       | 22566/100000 [6:35:25<12:34:40,  1.71it/s]
Train steps ... :  23%|██▎       | 22567/100000 [6:35:26<12:34:35,  1.71it/s]
Train steps ... :  23%|██▎       | 22568/100000 [6:35:26<12:35:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22569/100000 [6:35:27<12:35:15,  1.71it/s]
Train steps ... :  23%|██▎       | 22570/100000 [6:35:27<12:35:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22571/100000 [6:35:28<12:36:08,  1.71it/s]
Train steps ... :  23%|██▎       | 22572/100000 [6:35:29<12:34:46,  1.71it/s]
Train steps ... :  23%|██▎       | 22573/100000 [6:35:29<12:35:03,  1.71it/s]
Train steps ... :  23%|██▎       | 22574/100000 [6:35:30<12:35:05,  1.71it/s]
Train steps ... :  23%|██▎       | 22575/100000 [6:35:30<12:34:21,  1.71it/s]Step... (22575 / 100000 | Loss: 1.561206579208374, Learning Rate: 7.78140703517588e-05)
+
                                                                             
Step... (22575 / 100000 | Loss: 0.959479570388794, Learning Rate: 7.78140703517588e-05)
+
Train steps ... :  23%|██▎       | 22575/100000 [6:35:31<12:34:21,  1.71it/s]
Train steps ... :  23%|██▎       | 22576/100000 [6:35:31<12:35:06,  1.71it/s]
Train steps ... :  23%|██▎       | 22577/100000 [6:35:32<12:34:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22578/100000 [6:35:32<12:34:19,  1.71it/s]
Train steps ... :  23%|██▎       | 22579/100000 [6:35:33<12:36:15,  1.71it/s]
Train steps ... :  23%|██▎       | 22580/100000 [6:35:33<12:34:27,  1.71it/s]
Train steps ... :  23%|██▎       | 22581/100000 [6:35:34<12:34:40,  1.71it/s]
Train steps ... :  23%|██▎       | 22582/100000 [6:35:34<12:34:03,  1.71it/s]
Train steps ... :  23%|██▎       | 22583/100000 [6:35:35<12:33:56,  1.71it/s]
Train steps ... :  23%|██▎       | 22584/100000 [6:35:36<12:34:55,  1.71it/s]
Train steps ... :  23%|██▎       | 22585/100000 [6:35:36<12:34:09,  1.71it/s]
Train steps ... :  23%|██▎       | 22586/100000 [6:35:37<12:35:18,  1.71it/s]
Train steps ... :  23%|██▎       | 22587/100000 [6:35:37<12:34:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22588/100000 [6:35:38<12:35:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22589/100000 [6:35:39<12:35:00,  1.71it/s]
Train steps ... :  23%|██▎       | 22590/100000 [6:35:39<12:34:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22591/100000 [6:35:40<12:33:55,  1.71it/s]
Train steps ... :  23%|██▎       | 22592/100000 [6:35:40<12:33:36,  1.71it/s]
Train steps ... :  23%|██▎       | 22593/100000 [6:35:41<12:34:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22594/100000 [6:35:42<12:34:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22595/100000 [6:35:42<12:34:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22596/100000 [6:35:43<12:35:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22597/100000 [6:35:43<12:35:24,  1.71it/s]
Train steps ... :  23%|██▎       | 22598/100000 [6:35:44<12:34:10,  1.71it/s]
Train steps ... :  23%|██▎       | 22599/100000 [6:35:44<12:35:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22600/100000 [6:35:45<12:35:43,  1.71it/s]Step... (22600 / 100000 | Loss: 1.1325490474700928, Learning Rate: 7.77889447236181e-05)
+
                                                                             
Step... (22600 / 100000 | Loss: 1.219534158706665, Learning Rate: 7.77889447236181e-05)
+
Train steps ... :  23%|██▎       | 22600/100000 [6:35:45<12:35:43,  1.71it/s]
Train steps ... :  23%|██▎       | 22601/100000 [6:35:46<12:35:20,  1.71it/s]
Train steps ... :  23%|██▎       | 22602/100000 [6:35:46<12:34:45,  1.71it/s]
Train steps ... :  23%|██▎       | 22603/100000 [6:35:47<12:34:55,  1.71it/s]
Train steps ... :  23%|██▎       | 22604/100000 [6:35:47<12:35:04,  1.71it/s]
Train steps ... :  23%|██▎       | 22605/100000 [6:35:48<12:34:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22606/100000 [6:35:49<12:34:58,  1.71it/s]
Train steps ... :  23%|██▎       | 22607/100000 [6:35:49<12:34:33,  1.71it/s]
Train steps ... :  23%|██▎       | 22608/100000 [6:35:50<12:35:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22609/100000 [6:35:50<12:35:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22610/100000 [6:35:51<12:35:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22611/100000 [6:35:51<12:34:51,  1.71it/s]
Train steps ... :  23%|██▎       | 22612/100000 [6:35:52<12:34:56,  1.71it/s]
Train steps ... :  23%|██▎       | 22613/100000 [6:35:53<12:34:27,  1.71it/s]
Train steps ... :  23%|██▎       | 22614/100000 [6:35:53<12:34:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22615/100000 [6:35:54<12:34:27,  1.71it/s]
Train steps ... :  23%|██▎       | 22616/100000 [6:35:54<12:34:05,  1.71it/s]
Train steps ... :  23%|██▎       | 22617/100000 [6:35:55<12:34:36,  1.71it/s]
Train steps ... :  23%|██▎       | 22618/100000 [6:35:56<12:37:18,  1.70it/s]
Train steps ... :  23%|██▎       | 22619/100000 [6:35:56<12:35:19,  1.71it/s]
Train steps ... :  23%|██▎       | 22620/100000 [6:35:57<12:35:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22621/100000 [6:35:57<12:36:28,  1.70it/s]
Train steps ... :  23%|██▎       | 22622/100000 [6:35:58<12:35:28,  1.71it/s]
Train steps ... :  23%|██▎       | 22623/100000 [6:35:58<12:34:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22624/100000 [6:35:59<12:34:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22625/100000 [6:36:00<12:34:12,  1.71it/s]Step... (22625 / 100000 | Loss: 0.8815897703170776, Learning Rate: 7.776381909547739e-05)
+
                                                                             
Step... (22625 / 100000 | Loss: 1.2292118072509766, Learning Rate: 7.776381909547739e-05)
+
Train steps ... :  23%|██▎       | 22625/100000 [6:36:00<12:34:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22626/100000 [6:36:00<12:33:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22627/100000 [6:36:01<12:33:09,  1.71it/s]
Train steps ... :  23%|██▎       | 22628/100000 [6:36:01<12:33:55,  1.71it/s]
Train steps ... :  23%|██▎       | 22629/100000 [6:36:02<12:33:14,  1.71it/s]
Train steps ... :  23%|██▎       | 22630/100000 [6:36:03<12:34:21,  1.71it/s]
Train steps ... :  23%|██▎       | 22631/100000 [6:36:03<12:34:08,  1.71it/s]
Train steps ... :  23%|██▎       | 22632/100000 [6:36:04<12:34:06,  1.71it/s]
Train steps ... :  23%|██▎       | 22633/100000 [6:36:04<12:34:21,  1.71it/s]
Train steps ... :  23%|██▎       | 22634/100000 [6:36:05<12:33:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22635/100000 [6:36:05<12:34:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22636/100000 [6:36:06<12:34:17,  1.71it/s]
Train steps ... :  23%|██▎       | 22637/100000 [6:36:07<12:34:36,  1.71it/s]
Train steps ... :  23%|██▎       | 22638/100000 [6:36:07<12:33:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22639/100000 [6:36:08<12:34:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22640/100000 [6:36:08<12:34:34,  1.71it/s]
Train steps ... :  23%|██▎       | 22641/100000 [6:36:09<12:34:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22642/100000 [6:36:10<12:34:05,  1.71it/s]
Train steps ... :  23%|██▎       | 22643/100000 [6:36:10<12:34:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22644/100000 [6:36:11<12:34:11,  1.71it/s]
Train steps ... :  23%|██▎       | 22645/100000 [6:36:11<12:33:47,  1.71it/s]
Train steps ... :  23%|██▎       | 22646/100000 [6:36:12<12:33:46,  1.71it/s]
Train steps ... :  23%|██▎       | 22647/100000 [6:36:13<12:33:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22648/100000 [6:36:13<12:33:08,  1.71it/s]
Train steps ... :  23%|██▎       | 22649/100000 [6:36:14<12:33:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22650/100000 [6:36:14<12:33:40,  1.71it/s]Step... (22650 / 100000 | Loss: 0.898928165435791, Learning Rate: 7.773869346733669e-05)
+
                                                                             
Step... (22650 / 100000 | Loss: 0.8873871564865112, Learning Rate: 7.773869346733669e-05)
+
Train steps ... :  23%|██▎       | 22650/100000 [6:36:15<12:33:40,  1.71it/s]
Train steps ... :  23%|██▎       | 22651/100000 [6:36:15<12:33:45,  1.71it/s]
Train steps ... :  23%|██▎       | 22652/100000 [6:36:15<12:33:14,  1.71it/s]
Train steps ... :  23%|██▎       | 22653/100000 [6:36:16<12:34:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22654/100000 [6:36:17<12:35:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22655/100000 [6:36:17<12:34:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22656/100000 [6:36:18<12:35:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22657/100000 [6:36:18<12:34:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22658/100000 [6:36:19<12:33:18,  1.71it/s]
Train steps ... :  23%|██▎       | 22659/100000 [6:36:20<12:33:03,  1.71it/s]
Train steps ... :  23%|██▎       | 22660/100000 [6:36:20<12:33:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22661/100000 [6:36:21<12:33:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22662/100000 [6:36:21<12:33:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22663/100000 [6:36:22<12:33:11,  1.71it/s]
Train steps ... :  23%|██▎       | 22664/100000 [6:36:22<12:32:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22665/100000 [6:36:23<12:32:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22666/100000 [6:36:24<12:33:48,  1.71it/s]
Train steps ... :  23%|██▎       | 22667/100000 [6:36:24<12:33:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22668/100000 [6:36:25<12:33:20,  1.71it/s]
Train steps ... :  23%|██▎       | 22669/100000 [6:36:25<12:33:04,  1.71it/s]
Train steps ... :  23%|██▎       | 22670/100000 [6:36:26<12:33:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22671/100000 [6:36:27<12:34:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22672/100000 [6:36:27<12:34:19,  1.71it/s]
Train steps ... :  23%|██▎       | 22673/100000 [6:36:28<12:33:47,  1.71it/s]
Train steps ... :  23%|██▎       | 22674/100000 [6:36:28<12:35:08,  1.71it/s]
Train steps ... :  23%|██▎       | 22675/100000 [6:36:29<12:33:36,  1.71it/s]Step... (22675 / 100000 | Loss: 0.7849072813987732, Learning Rate: 7.771356783919599e-05)
+
                                                                             
Step... (22675 / 100000 | Loss: 1.0681300163269043, Learning Rate: 7.771356783919599e-05)
+
Train steps ... :  23%|██▎       | 22675/100000 [6:36:29<12:33:36,  1.71it/s]
Train steps ... :  23%|██▎       | 22676/100000 [6:36:29<12:34:40,  1.71it/s]
Train steps ... :  23%|██▎       | 22677/100000 [6:36:30<12:34:34,  1.71it/s]
Train steps ... :  23%|██▎       | 22678/100000 [6:36:31<12:34:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22679/100000 [6:36:31<12:33:44,  1.71it/s]
Train steps ... :  23%|██▎       | 22680/100000 [6:36:32<12:33:13,  1.71it/s]
Train steps ... :  23%|██▎       | 22681/100000 [6:36:32<12:32:45,  1.71it/s]
Train steps ... :  23%|██▎       | 22682/100000 [6:36:33<12:32:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22683/100000 [6:36:34<12:32:45,  1.71it/s]
Train steps ... :  23%|██▎       | 22684/100000 [6:36:34<12:33:06,  1.71it/s]
Train steps ... :  23%|██▎       | 22685/100000 [6:36:35<12:32:25,  1.71it/s]
Train steps ... :  23%|██▎       | 22686/100000 [6:36:35<12:33:33,  1.71it/s]
Train steps ... :  23%|██▎       | 22687/100000 [6:36:36<12:32:44,  1.71it/s]
Train steps ... :  23%|██▎       | 22688/100000 [6:36:36<12:33:17,  1.71it/s]
Train steps ... :  23%|██▎       | 22689/100000 [6:36:37<12:34:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22690/100000 [6:36:38<12:34:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22691/100000 [6:36:38<12:33:22,  1.71it/s]
Train steps ... :  23%|██▎       | 22692/100000 [6:36:39<12:33:33,  1.71it/s]
Train steps ... :  23%|██▎       | 22693/100000 [6:36:39<12:35:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22694/100000 [6:36:40<12:34:48,  1.71it/s]
Train steps ... :  23%|██▎       | 22695/100000 [6:36:41<12:33:54,  1.71it/s]
Train steps ... :  23%|██▎       | 22696/100000 [6:36:41<12:33:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22697/100000 [6:36:42<12:33:14,  1.71it/s]
Train steps ... :  23%|██▎       | 22698/100000 [6:36:42<12:33:56,  1.71it/s]
Train steps ... :  23%|██▎       | 22699/100000 [6:36:43<12:34:27,  1.71it/s]
Train steps ... :  23%|██▎       | 22700/100000 [6:36:44<12:34:26,  1.71it/s]Step... (22700 / 100000 | Loss: 0.9689501523971558, Learning Rate: 7.768844221105528e-05)
+
                                                                             
Step... (22700 / 100000 | Loss: 0.738939642906189, Learning Rate: 7.768844221105528e-05)
+
Train steps ... :  23%|██▎       | 22700/100000 [6:36:44<12:34:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22701/100000 [6:36:44<12:34:33,  1.71it/s]
Train steps ... :  23%|██▎       | 22702/100000 [6:36:45<12:33:44,  1.71it/s]
Train steps ... :  23%|██▎       | 22703/100000 [6:36:45<12:34:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22704/100000 [6:36:46<12:34:44,  1.71it/s]
Train steps ... :  23%|██▎       | 22705/100000 [6:36:46<12:33:19,  1.71it/s]
Train steps ... :  23%|██▎       | 22706/100000 [6:36:47<12:33:27,  1.71it/s]
Train steps ... :  23%|██▎       | 22707/100000 [6:36:48<12:33:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22708/100000 [6:36:48<12:32:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22709/100000 [6:36:49<12:32:46,  1.71it/s]
Train steps ... :  23%|██▎       | 22710/100000 [6:36:49<12:33:18,  1.71it/s]
Train steps ... :  23%|██▎       | 22711/100000 [6:36:50<12:33:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22712/100000 [6:36:51<12:32:49,  1.71it/s]
Train steps ... :  23%|██▎       | 22713/100000 [6:36:51<12:32:37,  1.71it/s]
Train steps ... :  23%|██▎       | 22714/100000 [6:36:52<12:33:06,  1.71it/s]
Train steps ... :  23%|██▎       | 22715/100000 [6:36:52<12:32:35,  1.71it/s]
Train steps ... :  23%|██▎       | 22716/100000 [6:36:53<12:33:08,  1.71it/s]
Train steps ... :  23%|██▎       | 22717/100000 [6:36:53<12:33:00,  1.71it/s]
Train steps ... :  23%|██▎       | 22718/100000 [6:36:54<12:32:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22719/100000 [6:36:55<12:32:25,  1.71it/s]
Train steps ... :  23%|██▎       | 22720/100000 [6:36:55<12:34:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22721/100000 [6:36:56<12:32:30,  1.71it/s]
Train steps ... :  23%|██▎       | 22722/100000 [6:36:56<12:33:13,  1.71it/s]
Train steps ... :  23%|██▎       | 22723/100000 [6:36:57<12:32:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22724/100000 [6:36:58<12:32:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22725/100000 [6:36:58<12:33:36,  1.71it/s]Step... (22725 / 100000 | Loss: 1.0362187623977661, Learning Rate: 7.766331658291458e-05)
+
                                                                             
Step... (22725 / 100000 | Loss: 1.086386799812317, Learning Rate: 7.766331658291458e-05)
+
Train steps ... :  23%|██▎       | 22725/100000 [6:36:58<12:33:36,  1.71it/s]
Train steps ... :  23%|██▎       | 22726/100000 [6:36:59<12:33:07,  1.71it/s]
Train steps ... :  23%|██▎       | 22727/100000 [6:36:59<12:33:07,  1.71it/s]
Train steps ... :  23%|██▎       | 22728/100000 [6:37:00<12:33:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22729/100000 [6:37:00<12:32:55,  1.71it/s]
Train steps ... :  23%|██▎       | 22730/100000 [6:37:01<12:33:32,  1.71it/s]
Train steps ... :  23%|██▎       | 22731/100000 [6:37:02<12:33:18,  1.71it/s]
Train steps ... :  23%|██▎       | 22732/100000 [6:37:02<12:32:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22733/100000 [6:37:03<12:32:34,  1.71it/s]
Train steps ... :  23%|██▎       | 22734/100000 [6:37:03<12:32:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22735/100000 [6:37:04<12:33:10,  1.71it/s]
Train steps ... :  23%|██▎       | 22736/100000 [6:37:05<12:33:08,  1.71it/s]
Train steps ... :  23%|██▎       | 22737/100000 [6:37:05<12:33:10,  1.71it/s]
Train steps ... :  23%|██▎       | 22738/100000 [6:37:06<12:33:28,  1.71it/s]
Train steps ... :  23%|██▎       | 22739/100000 [6:37:06<12:32:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22740/100000 [6:37:07<12:34:30,  1.71it/s]
Train steps ... :  23%|██▎       | 22741/100000 [6:37:07<12:32:54,  1.71it/s]
Train steps ... :  23%|██▎       | 22742/100000 [6:37:08<12:33:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22743/100000 [6:37:09<12:33:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22744/100000 [6:37:09<12:32:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22745/100000 [6:37:10<12:32:18,  1.71it/s]
Train steps ... :  23%|██▎       | 22746/100000 [6:37:10<12:32:55,  1.71it/s]
Train steps ... :  23%|██▎       | 22747/100000 [6:37:11<12:32:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22748/100000 [6:37:12<12:33:06,  1.71it/s]
Train steps ... :  23%|██▎       | 22749/100000 [6:37:12<12:32:20,  1.71it/s]
Train steps ... :  23%|██▎       | 22750/100000 [6:37:13<12:32:09,  1.71it/s]Step... (22750 / 100000 | Loss: 1.181980848312378, Learning Rate: 7.763819095477388e-05)
+
                                                                             
Step... (22750 / 100000 | Loss: 0.7350860238075256, Learning Rate: 7.763819095477388e-05)
+
Train steps ... :  23%|██▎       | 22750/100000 [6:37:13<12:32:09,  1.71it/s]
Train steps ... :  23%|██▎       | 22751/100000 [6:37:13<12:32:32,  1.71it/s]
Train steps ... :  23%|██▎       | 22752/100000 [6:37:14<12:32:08,  1.71it/s]
Train steps ... :  23%|██▎       | 22753/100000 [6:37:15<12:32:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22754/100000 [6:37:15<12:32:28,  1.71it/s]
Train steps ... :  23%|██▎       | 22755/100000 [6:37:16<12:32:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22756/100000 [6:37:16<12:32:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22757/100000 [6:37:17<12:32:09,  1.71it/s]
Train steps ... :  23%|██▎       | 22758/100000 [6:37:17<12:31:45,  1.71it/s]
Train steps ... :  23%|██▎       | 22759/100000 [6:37:18<12:32:08,  1.71it/s]
Train steps ... :  23%|██▎       | 22760/100000 [6:37:19<12:31:49,  1.71it/s]
Train steps ... :  23%|██▎       | 22761/100000 [6:37:19<12:31:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22762/100000 [6:37:20<12:31:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22763/100000 [6:37:20<12:32:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22764/100000 [6:37:21<12:32:58,  1.71it/s]
Train steps ... :  23%|██▎       | 22765/100000 [6:37:22<12:32:14,  1.71it/s]
Train steps ... :  23%|██▎       | 22766/100000 [6:37:22<12:32:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22767/100000 [6:37:23<12:32:13,  1.71it/s]
Train steps ... :  23%|██▎       | 22768/100000 [6:37:23<12:31:51,  1.71it/s]
Train steps ... :  23%|██▎       | 22769/100000 [6:37:24<12:32:17,  1.71it/s]
Train steps ... :  23%|██▎       | 22770/100000 [6:37:24<12:31:45,  1.71it/s]
Train steps ... :  23%|██▎       | 22771/100000 [6:37:25<12:32:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22772/100000 [6:37:26<12:32:03,  1.71it/s]
Train steps ... :  23%|██▎       | 22773/100000 [6:37:26<12:31:40,  1.71it/s]
Train steps ... :  23%|██▎       | 22774/100000 [6:37:27<12:33:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22775/100000 [6:37:27<12:34:39,  1.71it/s]Step... (22775 / 100000 | Loss: 0.8187071084976196, Learning Rate: 7.761306532663317e-05)
+
                                                                             
Step... (22775 / 100000 | Loss: 0.8490391969680786, Learning Rate: 7.761306532663317e-05)
+
Train steps ... :  23%|██▎       | 22775/100000 [6:37:28<12:34:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22776/100000 [6:37:28<12:33:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22777/100000 [6:37:29<12:34:18,  1.71it/s]
Train steps ... :  23%|██▎       | 22778/100000 [6:37:29<12:33:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22779/100000 [6:37:30<12:34:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22780/100000 [6:37:30<12:32:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22781/100000 [6:37:31<12:32:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22782/100000 [6:37:31<12:31:54,  1.71it/s]
Train steps ... :  23%|██▎       | 22783/100000 [6:37:32<12:31:49,  1.71it/s]
Train steps ... :  23%|██▎       | 22784/100000 [6:37:33<12:31:43,  1.71it/s]
Train steps ... :  23%|██▎       | 22785/100000 [6:37:33<12:31:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22786/100000 [6:37:34<12:32:18,  1.71it/s]
Train steps ... :  23%|██▎       | 22787/100000 [6:37:34<12:32:06,  1.71it/s]
Train steps ... :  23%|██▎       | 22788/100000 [6:37:35<12:32:36,  1.71it/s]
Train steps ... :  23%|██▎       | 22789/100000 [6:37:36<12:32:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22790/100000 [6:37:36<12:32:24,  1.71it/s]
Train steps ... :  23%|██▎       | 22791/100000 [6:37:37<12:34:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22792/100000 [6:37:37<12:31:09,  1.71it/s]
Train steps ... :  23%|██▎       | 22793/100000 [6:37:38<12:32:32,  1.71it/s]
Train steps ... :  23%|██▎       | 22794/100000 [6:37:38<12:31:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22795/100000 [6:37:39<12:31:07,  1.71it/s]
Train steps ... :  23%|██▎       | 22796/100000 [6:37:40<12:31:00,  1.71it/s]
Train steps ... :  23%|██▎       | 22797/100000 [6:37:40<12:31:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22798/100000 [6:37:41<12:31:47,  1.71it/s]
Train steps ... :  23%|██▎       | 22799/100000 [6:37:41<12:32:37,  1.71it/s]
Train steps ... :  23%|██▎       | 22800/100000 [6:37:42<12:32:23,  1.71it/s]Step... (22800 / 100000 | Loss: 0.8612502813339233, Learning Rate: 7.758793969849247e-05)
+
                                                                             
Step... (22800 / 100000 | Loss: 1.0911915302276611, Learning Rate: 7.758793969849247e-05)
+
Train steps ... :  23%|██▎       | 22800/100000 [6:37:42<12:32:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22801/100000 [6:37:43<12:32:34,  1.71it/s]
Train steps ... :  23%|██▎       | 22802/100000 [6:37:43<12:31:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22803/100000 [6:37:44<12:32:17,  1.71it/s]
Train steps ... :  23%|██▎       | 22804/100000 [6:37:44<12:31:34,  1.71it/s]
Train steps ... :  23%|██▎       | 22805/100000 [6:37:45<12:31:32,  1.71it/s]
Train steps ... :  23%|██▎       | 22806/100000 [6:37:45<12:31:03,  1.71it/s]
Train steps ... :  23%|██▎       | 22807/100000 [6:37:46<12:31:32,  1.71it/s]
Train steps ... :  23%|██▎       | 22808/100000 [6:37:47<12:32:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22809/100000 [6:37:47<12:33:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22810/100000 [6:37:48<12:33:17,  1.71it/s]
Train steps ... :  23%|██▎       | 22811/100000 [6:37:48<12:34:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22812/100000 [6:37:49<12:33:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22813/100000 [6:37:50<12:32:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22814/100000 [6:37:50<12:32:44,  1.71it/s]
Train steps ... :  23%|██▎       | 22815/100000 [6:37:51<12:32:45,  1.71it/s]
Train steps ... :  23%|██▎       | 22816/100000 [6:37:51<12:32:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22817/100000 [6:37:52<12:32:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22818/100000 [6:37:53<12:33:45,  1.71it/s]
Train steps ... :  23%|██▎       | 22819/100000 [6:37:53<12:33:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22820/100000 [6:37:54<12:32:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22821/100000 [6:37:54<12:32:05,  1.71it/s]
Train steps ... :  23%|██▎       | 22822/100000 [6:37:55<12:31:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22823/100000 [6:37:55<12:31:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22824/100000 [6:37:56<12:31:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22825/100000 [6:37:57<12:31:56,  1.71it/s]Step... (22825 / 100000 | Loss: 0.8923661708831787, Learning Rate: 7.756281407035177e-05)
+
                                                                             
Step... (22825 / 100000 | Loss: 0.7947975397109985, Learning Rate: 7.756281407035177e-05)
+
Train steps ... :  23%|██▎       | 22825/100000 [6:37:57<12:31:56,  1.71it/s]
Train steps ... :  23%|██▎       | 22826/100000 [6:37:57<12:32:21,  1.71it/s]
Train steps ... :  23%|██▎       | 22827/100000 [6:37:58<12:32:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22828/100000 [6:37:58<12:32:07,  1.71it/s]
Train steps ... :  23%|██▎       | 22829/100000 [6:37:59<12:32:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22830/100000 [6:38:00<12:33:05,  1.71it/s]
Train steps ... :  23%|██▎       | 22831/100000 [6:38:00<12:32:24,  1.71it/s]
Train steps ... :  23%|██▎       | 22832/100000 [6:38:01<12:31:49,  1.71it/s]
Train steps ... :  23%|██▎       | 22833/100000 [6:38:01<12:31:51,  1.71it/s]
Train steps ... :  23%|██▎       | 22834/100000 [6:38:02<12:31:43,  1.71it/s]
Train steps ... :  23%|██▎       | 22835/100000 [6:38:02<12:32:04,  1.71it/s]
Train steps ... :  23%|██▎       | 22836/100000 [6:38:03<12:31:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22837/100000 [6:38:04<12:31:35,  1.71it/s]
Train steps ... :  23%|██▎       | 22838/100000 [6:38:04<12:31:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22839/100000 [6:38:05<12:30:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22840/100000 [6:38:05<12:32:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22841/100000 [6:38:06<12:32:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22842/100000 [6:38:07<12:32:10,  1.71it/s]
Train steps ... :  23%|██▎       | 22843/100000 [6:38:07<12:33:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22844/100000 [6:38:08<12:32:55,  1.71it/s]
Train steps ... :  23%|██▎       | 22845/100000 [6:38:08<12:32:32,  1.71it/s]
Train steps ... :  23%|██▎       | 22846/100000 [6:38:09<12:32:32,  1.71it/s]
Train steps ... :  23%|██▎       | 22847/100000 [6:38:09<12:32:25,  1.71it/s]
Train steps ... :  23%|██▎       | 22848/100000 [6:38:10<12:32:19,  1.71it/s]
Train steps ... :  23%|██▎       | 22849/100000 [6:38:11<12:31:34,  1.71it/s]
Train steps ... :  23%|██▎       | 22850/100000 [6:38:11<12:32:31,  1.71it/s]Step... (22850 / 100000 | Loss: 0.9662520289421082, Learning Rate: 7.753768844221105e-05)
+
                                                                             
Step... (22850 / 100000 | Loss: 0.8806779384613037, Learning Rate: 7.753768844221105e-05)
+
Train steps ... :  23%|██▎       | 22850/100000 [6:38:12<12:32:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22851/100000 [6:38:12<12:32:28,  1.71it/s]
Train steps ... :  23%|██▎       | 22852/100000 [6:38:12<12:31:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22853/100000 [6:38:13<12:31:27,  1.71it/s]
Train steps ... :  23%|██▎       | 22854/100000 [6:38:14<12:31:22,  1.71it/s]
Train steps ... :  23%|██▎       | 22855/100000 [6:38:14<12:31:35,  1.71it/s]
Train steps ... :  23%|██▎       | 22856/100000 [6:38:15<12:31:34,  1.71it/s]
Train steps ... :  23%|██▎       | 22857/100000 [6:38:15<12:31:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22858/100000 [6:38:16<12:32:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22859/100000 [6:38:16<12:32:22,  1.71it/s]
Train steps ... :  23%|██▎       | 22860/100000 [6:38:17<12:31:34,  1.71it/s]
Train steps ... :  23%|██▎       | 22861/100000 [6:38:18<12:31:46,  1.71it/s]
Train steps ... :  23%|██▎       | 22862/100000 [6:38:18<12:31:06,  1.71it/s]
Train steps ... :  23%|██▎       | 22863/100000 [6:38:19<12:31:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22864/100000 [6:38:19<12:31:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22865/100000 [6:38:20<12:31:00,  1.71it/s]
Train steps ... :  23%|██▎       | 22866/100000 [6:38:21<12:30:44,  1.71it/s]
Train steps ... :  23%|██▎       | 22867/100000 [6:38:21<12:30:44,  1.71it/s]
Train steps ... :  23%|██▎       | 22868/100000 [6:38:22<12:30:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22869/100000 [6:38:22<12:32:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22870/100000 [6:38:23<12:31:10,  1.71it/s]
Train steps ... :  23%|██▎       | 22871/100000 [6:38:24<12:31:24,  1.71it/s]
Train steps ... :  23%|██▎       | 22872/100000 [6:38:24<12:31:09,  1.71it/s]
Train steps ... :  23%|██▎       | 22873/100000 [6:38:25<12:31:03,  1.71it/s]
Train steps ... :  23%|██▎       | 22874/100000 [6:38:25<12:30:51,  1.71it/s]
Train steps ... :  23%|██▎       | 22875/100000 [6:38:26<12:31:41,  1.71it/s]Step... (22875 / 100000 | Loss: 0.82452392578125, Learning Rate: 7.751256281407036e-05)
+
                                                                             
Step... (22875 / 100000 | Loss: 0.9094220399856567, Learning Rate: 7.751256281407036e-05)
+
Train steps ... :  23%|██▎       | 22875/100000 [6:38:26<12:31:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22876/100000 [6:38:26<12:31:44,  1.71it/s]
Train steps ... :  23%|██▎       | 22877/100000 [6:38:27<12:30:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22878/100000 [6:38:28<12:32:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22879/100000 [6:38:28<12:32:25,  1.71it/s]
Train steps ... :  23%|██▎       | 22880/100000 [6:38:29<12:32:37,  1.71it/s]
Train steps ... :  23%|██▎       | 22881/100000 [6:38:29<12:32:51,  1.71it/s]
Train steps ... :  23%|██▎       | 22882/100000 [6:38:30<12:31:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22883/100000 [6:38:31<12:31:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22884/100000 [6:38:31<12:31:08,  1.71it/s]
Train steps ... :  23%|██▎       | 22885/100000 [6:38:32<12:30:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22886/100000 [6:38:32<12:30:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22887/100000 [6:38:33<12:30:55,  1.71it/s]
Train steps ... :  23%|██▎       | 22888/100000 [6:38:33<12:31:22,  1.71it/s]
Train steps ... :  23%|██▎       | 22889/100000 [6:38:34<12:31:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22890/100000 [6:38:35<12:32:10,  1.71it/s]
Train steps ... :  23%|██▎       | 22891/100000 [6:38:35<12:32:15,  1.71it/s]
Train steps ... :  23%|██▎       | 22892/100000 [6:38:36<12:31:14,  1.71it/s]
Train steps ... :  23%|██▎       | 22893/100000 [6:38:36<12:33:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22894/100000 [6:38:37<12:32:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22895/100000 [6:38:38<12:31:37,  1.71it/s]
Train steps ... :  23%|██▎       | 22896/100000 [6:38:38<12:31:53,  1.71it/s]
Train steps ... :  23%|██▎       | 22897/100000 [6:38:39<12:31:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22898/100000 [6:38:39<12:31:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22899/100000 [6:38:40<12:30:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22900/100000 [6:38:40<12:30:13,  1.71it/s]Step... (22900 / 100000 | Loss: 0.7045605182647705, Learning Rate: 7.748743718592966e-05)
+
                                                                             
Step... (22900 / 100000 | Loss: 0.8575975298881531, Learning Rate: 7.748743718592966e-05)
+
Train steps ... :  23%|██▎       | 22900/100000 [6:38:41<12:30:13,  1.71it/s]
Train steps ... :  23%|██▎       | 22901/100000 [6:38:41<12:30:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22902/100000 [6:38:42<12:31:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22903/100000 [6:38:42<12:31:43,  1.71it/s]
Train steps ... :  23%|██▎       | 22904/100000 [6:38:43<12:31:49,  1.71it/s]
Train steps ... :  23%|██▎       | 22905/100000 [6:38:43<12:30:55,  1.71it/s]
Train steps ... :  23%|██▎       | 22906/100000 [6:38:44<12:31:36,  1.71it/s]
Train steps ... :  23%|██▎       | 22907/100000 [6:38:45<12:32:10,  1.71it/s]
Train steps ... :  23%|██▎       | 22908/100000 [6:38:45<12:31:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22909/100000 [6:38:46<12:31:35,  1.71it/s]
Train steps ... :  23%|██▎       | 22910/100000 [6:38:46<12:31:51,  1.71it/s]
Train steps ... :  23%|██▎       | 22911/100000 [6:38:47<12:31:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22912/100000 [6:38:47<12:31:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22913/100000 [6:38:48<12:30:54,  1.71it/s]
Train steps ... :  23%|██▎       | 22914/100000 [6:38:49<12:32:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22915/100000 [6:38:49<12:30:27,  1.71it/s]
Train steps ... :  23%|██▎       | 22916/100000 [6:38:50<12:31:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22917/100000 [6:38:50<12:30:39,  1.71it/s]
Train steps ... :  23%|██▎       | 22918/100000 [6:38:51<12:31:28,  1.71it/s]
Train steps ... :  23%|██▎       | 22919/100000 [6:38:52<12:33:20,  1.71it/s]
Train steps ... :  23%|██▎       | 22920/100000 [6:38:52<12:31:22,  1.71it/s]
Train steps ... :  23%|██▎       | 22921/100000 [6:38:53<12:31:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22922/100000 [6:38:53<12:31:15,  1.71it/s]
Train steps ... :  23%|██▎       | 22923/100000 [6:38:54<12:31:49,  1.71it/s]
Train steps ... :  23%|██▎       | 22924/100000 [6:38:55<12:30:52,  1.71it/s]
Train steps ... :  23%|██▎       | 22925/100000 [6:38:55<12:30:31,  1.71it/s]Step... (22925 / 100000 | Loss: 1.272028923034668, Learning Rate: 7.746231155778895e-05)
+
                                                                             
Step... (22925 / 100000 | Loss: 0.7665361166000366, Learning Rate: 7.746231155778895e-05)
+
Train steps ... :  23%|██▎       | 22925/100000 [6:38:55<12:30:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22926/100000 [6:38:56<12:30:29,  1.71it/s]
Train steps ... :  23%|██▎       | 22927/100000 [6:38:56<12:30:25,  1.71it/s]
Train steps ... :  23%|██▎       | 22928/100000 [6:38:57<12:31:28,  1.71it/s]
Train steps ... :  23%|██▎       | 22929/100000 [6:38:57<12:30:58,  1.71it/s]
Train steps ... :  23%|██▎       | 22930/100000 [6:38:58<12:30:32,  1.71it/s]
Train steps ... :  23%|██▎       | 22931/100000 [6:38:59<12:30:33,  1.71it/s]
Train steps ... :  23%|██▎       | 22932/100000 [6:38:59<12:30:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22933/100000 [6:39:00<12:30:33,  1.71it/s]
Train steps ... :  23%|██▎       | 22934/100000 [6:39:00<12:30:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22935/100000 [6:39:01<12:30:37,  1.71it/s]
Train steps ... :  23%|██▎       | 22936/100000 [6:39:02<12:30:33,  1.71it/s]
Train steps ... :  23%|██▎       | 22937/100000 [6:39:02<12:30:04,  1.71it/s]
Train steps ... :  23%|██▎       | 22938/100000 [6:39:03<12:30:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22939/100000 [6:39:03<12:31:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22940/100000 [6:39:04<12:30:02,  1.71it/s]
Train steps ... :  23%|██▎       | 22941/100000 [6:39:04<12:31:42,  1.71it/s]
Train steps ... :  23%|██▎       | 22942/100000 [6:39:05<12:31:05,  1.71it/s]
Train steps ... :  23%|██▎       | 22943/100000 [6:39:06<12:30:56,  1.71it/s]
Train steps ... :  23%|██▎       | 22944/100000 [6:39:06<12:31:34,  1.71it/s]
Train steps ... :  23%|██▎       | 22945/100000 [6:39:07<12:30:21,  1.71it/s]
Train steps ... :  23%|██▎       | 22946/100000 [6:39:07<12:30:58,  1.71it/s]
Train steps ... :  23%|██▎       | 22947/100000 [6:39:08<12:32:30,  1.71it/s]
Train steps ... :  23%|██▎       | 22948/100000 [6:39:09<12:30:28,  1.71it/s]
Train steps ... :  23%|██▎       | 22949/100000 [6:39:09<12:30:08,  1.71it/s]
Train steps ... :  23%|██▎       | 22950/100000 [6:39:10<12:29:58,  1.71it/s]Step... (22950 / 100000 | Loss: 1.0674934387207031, Learning Rate: 7.743718592964825e-05)
+
                                                                             
Step... (22950 / 100000 | Loss: 0.7074738144874573, Learning Rate: 7.743718592964825e-05)
+
Train steps ... :  23%|██▎       | 22950/100000 [6:39:10<12:29:58,  1.71it/s]
Train steps ... :  23%|██▎       | 22951/100000 [6:39:10<12:30:15,  1.71it/s]
Train steps ... :  23%|██▎       | 22952/100000 [6:39:11<12:30:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22953/100000 [6:39:11<12:30:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22954/100000 [6:39:12<12:30:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22955/100000 [6:39:13<12:30:16,  1.71it/s]
Train steps ... :  23%|██▎       | 22956/100000 [6:39:13<12:30:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22957/100000 [6:39:14<12:30:43,  1.71it/s]
Train steps ... :  23%|██▎       | 22958/100000 [6:39:14<12:30:23,  1.71it/s]
Train steps ... :  23%|██▎       | 22959/100000 [6:39:15<12:30:09,  1.71it/s]
Train steps ... :  23%|██▎       | 22960/100000 [6:39:16<12:31:25,  1.71it/s]
Train steps ... :  23%|██▎       | 22961/100000 [6:39:16<12:30:30,  1.71it/s]
Train steps ... :  23%|██▎       | 22962/100000 [6:39:17<12:31:28,  1.71it/s]
Train steps ... :  23%|██▎       | 22963/100000 [6:39:17<12:30:47,  1.71it/s]
Train steps ... :  23%|██▎       | 22964/100000 [6:39:18<12:31:26,  1.71it/s]
Train steps ... :  23%|██▎       | 22965/100000 [6:39:18<12:31:40,  1.71it/s]
Train steps ... :  23%|██▎       | 22966/100000 [6:39:19<12:30:47,  1.71it/s]
Train steps ... :  23%|██▎       | 22967/100000 [6:39:20<12:30:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22968/100000 [6:39:20<12:30:17,  1.71it/s]
Train steps ... :  23%|██▎       | 22969/100000 [6:39:21<12:29:57,  1.71it/s]
Train steps ... :  23%|██▎       | 22970/100000 [6:39:21<12:30:03,  1.71it/s]
Train steps ... :  23%|██▎       | 22971/100000 [6:39:22<12:30:51,  1.71it/s]
Train steps ... :  23%|██▎       | 22972/100000 [6:39:23<12:30:50,  1.71it/s]
Train steps ... :  23%|██▎       | 22973/100000 [6:39:23<12:30:21,  1.71it/s]
Train steps ... :  23%|██▎       | 22974/100000 [6:39:24<12:30:33,  1.71it/s]
Train steps ... :  23%|██▎       | 22975/100000 [6:39:24<12:30:18,  1.71it/s]Step... (22975 / 100000 | Loss: 0.9212612509727478, Learning Rate: 7.741206030150754e-05)
+
                                                                             
Step... (22975 / 100000 | Loss: 0.7165900468826294, Learning Rate: 7.741206030150754e-05)
+
Train steps ... :  23%|██▎       | 22975/100000 [6:39:25<12:30:18,  1.71it/s]
Train steps ... :  23%|██▎       | 22976/100000 [6:39:25<12:30:24,  1.71it/s]
Train steps ... :  23%|██▎       | 22977/100000 [6:39:25<12:30:18,  1.71it/s]
Train steps ... :  23%|██▎       | 22978/100000 [6:39:26<12:30:11,  1.71it/s]
Train steps ... :  23%|██▎       | 22979/100000 [6:39:27<12:30:49,  1.71it/s]
Train steps ... :  23%|██▎       | 22980/100000 [6:39:27<12:32:01,  1.71it/s]
Train steps ... :  23%|██▎       | 22981/100000 [6:39:28<12:31:35,  1.71it/s]
Train steps ... :  23%|██▎       | 22982/100000 [6:39:28<12:30:40,  1.71it/s]
Train steps ... :  23%|██▎       | 22983/100000 [6:39:29<12:32:41,  1.71it/s]
Train steps ... :  23%|██▎       | 22984/100000 [6:39:30<12:31:27,  1.71it/s]
Train steps ... :  23%|██▎       | 22985/100000 [6:39:30<12:31:37,  1.71it/s]
Train steps ... :  23%|██▎       | 22986/100000 [6:39:31<12:30:38,  1.71it/s]
Train steps ... :  23%|██▎       | 22987/100000 [6:39:31<12:29:59,  1.71it/s]
Train steps ... :  23%|██▎       | 22988/100000 [6:39:32<12:29:49,  1.71it/s]
Train steps ... :  23%|██▎       | 22989/100000 [6:39:33<12:30:30,  1.71it/s]
Train steps ... :  23%|██▎       | 22990/100000 [6:39:33<12:31:00,  1.71it/s]
Train steps ... :  23%|██▎       | 22991/100000 [6:39:34<12:30:56,  1.71it/s]
Train steps ... :  23%|██▎       | 22992/100000 [6:39:34<12:30:54,  1.71it/s]
Train steps ... :  23%|██▎       | 22993/100000 [6:39:35<12:32:06,  1.71it/s]
Train steps ... :  23%|██▎       | 22994/100000 [6:39:35<12:31:03,  1.71it/s]
Train steps ... :  23%|██▎       | 22995/100000 [6:39:36<12:31:12,  1.71it/s]
Train steps ... :  23%|██▎       | 22996/100000 [6:39:37<12:31:31,  1.71it/s]
Train steps ... :  23%|██▎       | 22997/100000 [6:39:37<12:31:43,  1.71it/s]
Train steps ... :  23%|██▎       | 22998/100000 [6:39:38<12:31:20,  1.71it/s]
Train steps ... :  23%|██▎       | 22999/100000 [6:39:38<12:31:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23000/100000 [6:39:39<12:32:08,  1.71it/s]Step... (23000 / 100000 | Loss: 0.9654857516288757, Learning Rate: 7.738693467336684e-05)
+
                                                                             
Step... (23000 / 100000 | Loss: 0.7743905782699585, Learning Rate: 7.738693467336684e-05)
+
Train steps ... :  23%|██▎       | 23000/100000 [6:39:39<12:32:08,  1.71it/s]
Train steps ... :  23%|██▎       | 23001/100000 [6:39:40<12:31:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23002/100000 [6:39:40<12:30:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23003/100000 [6:39:41<12:29:59,  1.71it/s]
Train steps ... :  23%|██▎       | 23004/100000 [6:39:41<12:29:49,  1.71it/s]
Train steps ... :  23%|██▎       | 23005/100000 [6:39:42<12:29:59,  1.71it/s]
Train steps ... :  23%|██▎       | 23006/100000 [6:39:42<12:30:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23007/100000 [6:39:43<12:29:35,  1.71it/s]
Train steps ... :  23%|██▎       | 23008/100000 [6:39:44<12:30:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23009/100000 [6:39:44<12:29:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23010/100000 [6:39:45<12:29:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23011/100000 [6:39:45<12:29:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23012/100000 [6:39:46<12:29:44,  1.71it/s]
Train steps ... :  23%|██▎       | 23013/100000 [6:39:47<12:29:35,  1.71it/s]
Train steps ... :  23%|██▎       | 23014/100000 [6:39:47<12:30:22,  1.71it/s]
Train steps ... :  23%|██▎       | 23015/100000 [6:39:48<12:30:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23016/100000 [6:39:48<12:30:16,  1.71it/s]
Train steps ... :  23%|██▎       | 23017/100000 [6:39:49<12:30:18,  1.71it/s]
Train steps ... :  23%|██▎       | 23018/100000 [6:39:49<12:30:00,  1.71it/s]
Train steps ... :  23%|██▎       | 23019/100000 [6:39:50<12:30:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23020/100000 [6:39:51<12:31:31,  1.71it/s]
Train steps ... :  23%|██▎       | 23021/100000 [6:39:51<12:30:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23022/100000 [6:39:52<12:31:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23023/100000 [6:39:52<12:30:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23024/100000 [6:39:53<12:31:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23025/100000 [6:39:54<12:30:36,  1.71it/s]Step... (23025 / 100000 | Loss: 0.8180453777313232, Learning Rate: 7.736180904522612e-05)
+
                                                                             
Step... (23025 / 100000 | Loss: 1.2730730772018433, Learning Rate: 7.736180904522612e-05)
+
Train steps ... :  23%|██▎       | 23025/100000 [6:39:54<12:30:36,  1.71it/s]
Train steps ... :  23%|██▎       | 23026/100000 [6:39:54<12:30:43,  1.71it/s]
Train steps ... :  23%|██▎       | 23027/100000 [6:39:55<12:30:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23028/100000 [6:39:55<12:30:36,  1.71it/s]
Train steps ... :  23%|██▎       | 23029/100000 [6:39:56<12:30:10,  1.71it/s]
Train steps ... :  23%|██▎       | 23030/100000 [6:39:56<12:29:40,  1.71it/s]
Train steps ... :  23%|██▎       | 23031/100000 [6:39:57<12:29:19,  1.71it/s]
Train steps ... :  23%|██▎       | 23032/100000 [6:39:58<12:29:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23033/100000 [6:39:58<12:29:30,  1.71it/s]
Train steps ... :  23%|██▎       | 23034/100000 [6:39:59<12:29:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23035/100000 [6:39:59<12:29:53,  1.71it/s]
Train steps ... :  23%|██▎       | 23036/100000 [6:40:00<12:29:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23037/100000 [6:40:01<12:29:23,  1.71it/s]
Train steps ... :  23%|██▎       | 23038/100000 [6:40:01<12:30:11,  1.71it/s]
Train steps ... :  23%|██▎       | 23039/100000 [6:40:02<12:29:31,  1.71it/s]
Train steps ... :  23%|██▎       | 23040/100000 [6:40:02<12:29:31,  1.71it/s]
Train steps ... :  23%|██▎       | 23041/100000 [6:40:03<12:29:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23042/100000 [6:40:04<12:29:30,  1.71it/s]
Train steps ... :  23%|██▎       | 23043/100000 [6:40:04<12:29:15,  1.71it/s]
Train steps ... :  23%|██▎       | 23044/100000 [6:40:05<12:29:00,  1.71it/s]
Train steps ... :  23%|██▎       | 23045/100000 [6:40:05<12:29:40,  1.71it/s]
Train steps ... :  23%|██▎       | 23046/100000 [6:40:06<12:29:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23047/100000 [6:40:06<12:30:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23048/100000 [6:40:07<12:30:13,  1.71it/s]
Train steps ... :  23%|██▎       | 23049/100000 [6:40:08<12:29:44,  1.71it/s]
Train steps ... :  23%|██▎       | 23050/100000 [6:40:08<12:29:12,  1.71it/s]Step... (23050 / 100000 | Loss: 0.9016166925430298, Learning Rate: 7.733668341708543e-05)
+
                                                                             
Step... (23050 / 100000 | Loss: 1.0017777681350708, Learning Rate: 7.733668341708543e-05)
+
Train steps ... :  23%|██▎       | 23050/100000 [6:40:09<12:29:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23051/100000 [6:40:09<12:29:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23052/100000 [6:40:09<12:28:31,  1.71it/s]
Train steps ... :  23%|██▎       | 23053/100000 [6:40:10<12:28:31,  1.71it/s]
Train steps ... :  23%|██▎       | 23054/100000 [6:40:11<12:28:37,  1.71it/s]
Train steps ... :  23%|██▎       | 23055/100000 [6:40:11<12:30:11,  1.71it/s]
Train steps ... :  23%|██▎       | 23056/100000 [6:40:12<12:30:27,  1.71it/s]
Train steps ... :  23%|██▎       | 23057/100000 [6:40:12<12:30:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23058/100000 [6:40:13<12:29:54,  1.71it/s]
Train steps ... :  23%|██▎       | 23059/100000 [6:40:13<12:29:49,  1.71it/s]
Train steps ... :  23%|██▎       | 23060/100000 [6:40:14<12:29:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23061/100000 [6:40:15<12:28:41,  1.71it/s]
Train steps ... :  23%|██▎       | 23062/100000 [6:40:15<12:28:54,  1.71it/s]
Train steps ... :  23%|██▎       | 23063/100000 [6:40:16<12:28:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23064/100000 [6:40:16<12:28:57,  1.71it/s]
Train steps ... :  23%|██▎       | 23065/100000 [6:40:17<12:28:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23066/100000 [6:40:18<12:29:08,  1.71it/s]
Train steps ... :  23%|██▎       | 23067/100000 [6:40:18<12:28:40,  1.71it/s]
Train steps ... :  23%|██▎       | 23068/100000 [6:40:19<12:28:39,  1.71it/s]
Train steps ... :  23%|██▎       | 23069/100000 [6:40:19<12:29:53,  1.71it/s]
Train steps ... :  23%|██▎       | 23070/100000 [6:40:20<12:28:57,  1.71it/s]
Train steps ... :  23%|██▎       | 23071/100000 [6:40:20<12:28:23,  1.71it/s]
Train steps ... :  23%|██▎       | 23072/100000 [6:40:21<12:29:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23073/100000 [6:40:22<12:30:33,  1.71it/s]
Train steps ... :  23%|██▎       | 23074/100000 [6:40:22<12:29:40,  1.71it/s]
Train steps ... :  23%|██▎       | 23075/100000 [6:40:23<12:29:52,  1.71it/s]Step... (23075 / 100000 | Loss: 0.93133944272995, Learning Rate: 7.731155778894472e-05)
+
                                                                             
Step... (23075 / 100000 | Loss: 0.8245190382003784, Learning Rate: 7.731155778894472e-05)
+
Train steps ... :  23%|██▎       | 23075/100000 [6:40:23<12:29:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23076/100000 [6:40:23<12:29:32,  1.71it/s]
Train steps ... :  23%|██▎       | 23077/100000 [6:40:24<12:29:00,  1.71it/s]
Train steps ... :  23%|██▎       | 23078/100000 [6:40:25<12:28:57,  1.71it/s]
Train steps ... :  23%|██▎       | 23079/100000 [6:40:25<12:28:41,  1.71it/s]
Train steps ... :  23%|██▎       | 23080/100000 [6:40:26<12:28:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23081/100000 [6:40:26<12:29:11,  1.71it/s]
Train steps ... :  23%|██▎       | 23082/100000 [6:40:27<12:30:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23083/100000 [6:40:27<12:31:51,  1.71it/s]
Train steps ... :  23%|██▎       | 23084/100000 [6:40:28<12:29:30,  1.71it/s]
Train steps ... :  23%|██▎       | 23085/100000 [6:40:29<12:30:29,  1.71it/s]
Train steps ... :  23%|██▎       | 23086/100000 [6:40:29<12:29:36,  1.71it/s]
Train steps ... :  23%|██▎       | 23087/100000 [6:40:30<12:30:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23088/100000 [6:40:30<12:29:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23089/100000 [6:40:31<12:29:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23090/100000 [6:40:32<12:29:16,  1.71it/s]
Train steps ... :  23%|██▎       | 23091/100000 [6:40:32<12:28:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23092/100000 [6:40:33<12:29:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23093/100000 [6:40:33<12:28:31,  1.71it/s]
Train steps ... :  23%|██▎       | 23094/100000 [6:40:34<12:28:21,  1.71it/s]
Train steps ... :  23%|██▎       | 23095/100000 [6:40:34<12:28:09,  1.71it/s]
Train steps ... :  23%|██▎       | 23096/100000 [6:40:35<12:29:18,  1.71it/s]
Train steps ... :  23%|██▎       | 23097/100000 [6:40:36<12:31:18,  1.71it/s]
Train steps ... :  23%|██▎       | 23098/100000 [6:40:36<12:30:02,  1.71it/s]
Train steps ... :  23%|██▎       | 23099/100000 [6:40:37<12:30:13,  1.71it/s]
Train steps ... :  23%|██▎       | 23100/100000 [6:40:37<12:29:26,  1.71it/s]Step... (23100 / 100000 | Loss: 0.9099173545837402, Learning Rate: 7.728643216080403e-05)
+
                                                                             
Step... (23100 / 100000 | Loss: 1.1678671836853027, Learning Rate: 7.728643216080403e-05)
+
Train steps ... :  23%|██▎       | 23100/100000 [6:40:38<12:29:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23101/100000 [6:40:38<12:29:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23102/100000 [6:40:39<12:28:37,  1.71it/s]
Train steps ... :  23%|██▎       | 23103/100000 [6:40:39<12:28:44,  1.71it/s]
Train steps ... :  23%|██▎       | 23104/100000 [6:40:40<12:29:10,  1.71it/s]
Train steps ... :  23%|██▎       | 23105/100000 [6:40:40<12:28:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23106/100000 [6:40:41<12:29:15,  1.71it/s]
Train steps ... :  23%|██▎       | 23107/100000 [6:40:41<12:29:08,  1.71it/s]
Train steps ... :  23%|██▎       | 23108/100000 [6:40:42<12:29:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23109/100000 [6:40:43<12:29:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23110/100000 [6:40:43<12:28:55,  1.71it/s]
Train steps ... :  23%|██▎       | 23111/100000 [6:40:44<12:28:54,  1.71it/s]
Train steps ... :  23%|██▎       | 23112/100000 [6:40:44<12:28:39,  1.71it/s]
Train steps ... :  23%|██▎       | 23113/100000 [6:40:45<12:28:35,  1.71it/s]
Train steps ... :  23%|██▎       | 23114/100000 [6:40:46<12:30:13,  1.71it/s]
Train steps ... :  23%|██▎       | 23115/100000 [6:40:46<12:30:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23116/100000 [6:40:47<12:29:39,  1.71it/s]
Train steps ... :  23%|██▎       | 23117/100000 [6:40:47<12:29:53,  1.71it/s]
Train steps ... :  23%|██▎       | 23118/100000 [6:40:48<12:28:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23119/100000 [6:40:49<12:28:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23120/100000 [6:40:49<12:29:51,  1.71it/s]
Train steps ... :  23%|██▎       | 23121/100000 [6:40:50<12:29:11,  1.71it/s]
Train steps ... :  23%|██▎       | 23122/100000 [6:40:50<12:29:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23123/100000 [6:40:51<12:30:01,  1.71it/s]
Train steps ... :  23%|██▎       | 23124/100000 [6:40:51<12:28:50,  1.71it/s]
Train steps ... :  23%|██▎       | 23125/100000 [6:40:52<12:28:29,  1.71it/s]Step... (23125 / 100000 | Loss: 0.923648476600647, Learning Rate: 7.726130653266332e-05)
+
                                                                             
Step... (23125 / 100000 | Loss: 0.9306179285049438, Learning Rate: 7.726130653266332e-05)
+
Train steps ... :  23%|██▎       | 23125/100000 [6:40:52<12:28:29,  1.71it/s]
Train steps ... :  23%|██▎       | 23126/100000 [6:40:53<12:29:06,  1.71it/s]
Train steps ... :  23%|██▎       | 23127/100000 [6:40:53<12:28:43,  1.71it/s]
Train steps ... :  23%|██▎       | 23128/100000 [6:40:54<12:28:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23129/100000 [6:40:54<12:29:30,  1.71it/s]
Train steps ... :  23%|██▎       | 23130/100000 [6:40:55<12:27:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23131/100000 [6:40:56<12:29:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23132/100000 [6:40:56<12:29:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23133/100000 [6:40:57<12:29:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23134/100000 [6:40:57<12:28:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23135/100000 [6:40:58<12:28:15,  1.71it/s]
Train steps ... :  23%|██▎       | 23136/100000 [6:40:58<12:29:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23137/100000 [6:40:59<12:28:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23138/100000 [6:41:00<12:28:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23139/100000 [6:41:00<12:29:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23140/100000 [6:41:01<12:28:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23141/100000 [6:41:01<12:28:13,  1.71it/s]
Train steps ... :  23%|██▎       | 23142/100000 [6:41:02<12:28:06,  1.71it/s]
Train steps ... :  23%|██▎       | 23143/100000 [6:41:03<12:28:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23144/100000 [6:41:03<12:28:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23145/100000 [6:41:04<12:27:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23146/100000 [6:41:04<12:29:06,  1.71it/s]
Train steps ... :  23%|██▎       | 23147/100000 [6:41:05<12:28:34,  1.71it/s]
Train steps ... :  23%|██▎       | 23148/100000 [6:41:05<12:28:47,  1.71it/s]
Train steps ... :  23%|██▎       | 23149/100000 [6:41:06<12:29:50,  1.71it/s]
Train steps ... :  23%|██▎       | 23150/100000 [6:41:07<12:29:03,  1.71it/s]Step... (23150 / 100000 | Loss: 1.2086519002914429, Learning Rate: 7.723618090452262e-05)
+
                                                                             
Step... (23150 / 100000 | Loss: 0.9794008731842041, Learning Rate: 7.723618090452262e-05)
+
Train steps ... :  23%|██▎       | 23150/100000 [6:41:07<12:29:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23151/100000 [6:41:07<12:29:23,  1.71it/s]
Train steps ... :  23%|██▎       | 23152/100000 [6:41:08<12:29:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23153/100000 [6:41:08<12:29:16,  1.71it/s]
Train steps ... :  23%|██▎       | 23154/100000 [6:41:09<12:28:36,  1.71it/s]
Train steps ... :  23%|██▎       | 23155/100000 [6:41:10<12:29:10,  1.71it/s]
Train steps ... :  23%|██▎       | 23156/100000 [6:41:10<12:28:45,  1.71it/s]
Train steps ... :  23%|██▎       | 23157/100000 [6:41:11<12:28:49,  1.71it/s]
Train steps ... :  23%|██▎       | 23158/100000 [6:41:11<12:28:25,  1.71it/s]
Train steps ... :  23%|██▎       | 23159/100000 [6:41:12<12:28:31,  1.71it/s]
Train steps ... :  23%|██▎       | 23160/100000 [6:41:12<12:28:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23161/100000 [6:41:13<12:28:16,  1.71it/s]
Train steps ... :  23%|██▎       | 23162/100000 [6:41:14<12:28:25,  1.71it/s]
Train steps ... :  23%|██▎       | 23163/100000 [6:41:14<12:28:45,  1.71it/s]
Train steps ... :  23%|██▎       | 23164/100000 [6:41:15<12:28:08,  1.71it/s]
Train steps ... :  23%|██▎       | 23165/100000 [6:41:15<12:28:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23166/100000 [6:41:16<12:27:57,  1.71it/s]
Train steps ... :  23%|██▎       | 23167/100000 [6:41:17<12:27:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23168/100000 [6:41:17<12:28:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23169/100000 [6:41:18<12:31:09,  1.70it/s]
Train steps ... :  23%|██▎       | 23170/100000 [6:41:18<12:29:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23171/100000 [6:41:19<12:28:40,  1.71it/s]
Train steps ... :  23%|██▎       | 23172/100000 [6:41:19<12:28:16,  1.71it/s]
Train steps ... :  23%|██▎       | 23173/100000 [6:41:20<12:29:15,  1.71it/s]
Train steps ... :  23%|██▎       | 23174/100000 [6:41:21<12:29:16,  1.71it/s]
Train steps ... :  23%|██▎       | 23175/100000 [6:41:21<12:28:49,  1.71it/s]Step... (23175 / 100000 | Loss: 0.9991200566291809, Learning Rate: 7.721105527638192e-05)
+
                                                                             
Step... (23175 / 100000 | Loss: 1.2525107860565186, Learning Rate: 7.721105527638192e-05)
+
Train steps ... :  23%|██▎       | 23175/100000 [6:41:22<12:28:49,  1.71it/s]
Train steps ... :  23%|██▎       | 23176/100000 [6:41:22<12:29:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23177/100000 [6:41:22<12:28:36,  1.71it/s]
Train steps ... :  23%|██▎       | 23178/100000 [6:41:23<12:28:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23179/100000 [6:41:24<12:27:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23180/100000 [6:41:24<12:27:53,  1.71it/s]
Train steps ... :  23%|██▎       | 23181/100000 [6:41:25<12:27:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23182/100000 [6:41:25<12:27:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23183/100000 [6:41:26<12:28:21,  1.71it/s]
Train steps ... :  23%|██▎       | 23184/100000 [6:41:27<12:27:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23185/100000 [6:41:27<12:28:22,  1.71it/s]
Train steps ... :  23%|██▎       | 23186/100000 [6:41:28<12:29:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23187/100000 [6:41:28<12:28:43,  1.71it/s]
Train steps ... :  23%|██▎       | 23188/100000 [6:41:29<12:29:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23189/100000 [6:41:29<12:28:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23190/100000 [6:41:30<12:28:24,  1.71it/s]
Train steps ... :  23%|██▎       | 23191/100000 [6:41:31<12:28:24,  1.71it/s]
Train steps ... :  23%|██▎       | 23192/100000 [6:41:31<12:28:15,  1.71it/s]
Train steps ... :  23%|██▎       | 23193/100000 [6:41:32<12:28:06,  1.71it/s]
Train steps ... :  23%|██▎       | 23194/100000 [6:41:32<12:29:02,  1.71it/s]
Train steps ... :  23%|██▎       | 23195/100000 [6:41:33<12:29:06,  1.71it/s]
Train steps ... :  23%|██▎       | 23196/100000 [6:41:34<12:28:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23197/100000 [6:41:34<12:29:36,  1.71it/s]
Train steps ... :  23%|██▎       | 23198/100000 [6:41:35<12:28:18,  1.71it/s]
Train steps ... :  23%|██▎       | 23199/100000 [6:41:35<12:28:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23200/100000 [6:41:36<12:29:01,  1.71it/s]Step... (23200 / 100000 | Loss: 0.7828170657157898, Learning Rate: 7.71859296482412e-05)
+
                                                                             
Step... (23200 / 100000 | Loss: 1.1892616748809814, Learning Rate: 7.71859296482412e-05)
+
Train steps ... :  23%|██▎       | 23200/100000 [6:41:36<12:29:01,  1.71it/s]
Train steps ... :  23%|██▎       | 23201/100000 [6:41:36<12:30:52,  1.70it/s]
Train steps ... :  23%|██▎       | 23202/100000 [6:41:37<12:31:07,  1.70it/s]
Train steps ... :  23%|██▎       | 23203/100000 [6:41:38<12:30:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23204/100000 [6:41:38<12:29:25,  1.71it/s]
Train steps ... :  23%|██▎       | 23205/100000 [6:41:39<12:29:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23206/100000 [6:41:39<12:28:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23207/100000 [6:41:40<12:28:22,  1.71it/s]
Train steps ... :  23%|██▎       | 23208/100000 [6:41:41<12:29:02,  1.71it/s]
Train steps ... :  23%|██▎       | 23209/100000 [6:41:41<12:28:30,  1.71it/s]
Train steps ... :  23%|██▎       | 23210/100000 [6:41:42<12:28:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23211/100000 [6:41:42<12:27:59,  1.71it/s]
Train steps ... :  23%|██▎       | 23212/100000 [6:41:43<12:27:29,  1.71it/s]
Train steps ... :  23%|██▎       | 23213/100000 [6:41:43<12:28:23,  1.71it/s]
Train steps ... :  23%|██▎       | 23214/100000 [6:41:44<12:27:13,  1.71it/s]
Train steps ... :  23%|██▎       | 23215/100000 [6:41:45<12:27:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23216/100000 [6:41:45<12:27:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23217/100000 [6:41:46<12:27:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23218/100000 [6:41:46<12:28:09,  1.71it/s]
Train steps ... :  23%|██▎       | 23219/100000 [6:41:47<12:28:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23220/100000 [6:41:48<12:27:55,  1.71it/s]
Train steps ... :  23%|██▎       | 23221/100000 [6:41:48<12:28:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23222/100000 [6:41:49<12:28:34,  1.71it/s]
Train steps ... :  23%|██▎       | 23223/100000 [6:41:49<12:27:50,  1.71it/s]
Train steps ... :  23%|██▎       | 23224/100000 [6:41:50<12:28:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23225/100000 [6:41:50<12:28:15,  1.71it/s]Step... (23225 / 100000 | Loss: 1.1657154560089111, Learning Rate: 7.716080402010051e-05)
+
                                                                             
Step... (23225 / 100000 | Loss: 0.8753844499588013, Learning Rate: 7.716080402010051e-05)
+
Train steps ... :  23%|██▎       | 23225/100000 [6:41:51<12:28:15,  1.71it/s]
Train steps ... :  23%|██▎       | 23226/100000 [6:41:51<12:27:59,  1.71it/s]
Train steps ... :  23%|██▎       | 23227/100000 [6:41:52<12:28:06,  1.71it/s]
Train steps ... :  23%|██▎       | 23228/100000 [6:41:52<12:29:04,  1.71it/s]
Train steps ... :  23%|██▎       | 23229/100000 [6:41:53<12:28:54,  1.71it/s]
Train steps ... :  23%|██▎       | 23230/100000 [6:41:53<12:29:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23231/100000 [6:41:54<12:28:36,  1.71it/s]
Train steps ... :  23%|██▎       | 23232/100000 [6:41:55<12:28:23,  1.71it/s]
Train steps ... :  23%|██▎       | 23233/100000 [6:41:55<12:28:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23234/100000 [6:41:56<12:27:36,  1.71it/s]
Train steps ... :  23%|██▎       | 23235/100000 [6:41:56<12:28:02,  1.71it/s]
Train steps ... :  23%|██▎       | 23236/100000 [6:41:57<12:27:47,  1.71it/s]
Train steps ... :  23%|██▎       | 23237/100000 [6:41:58<12:28:08,  1.71it/s]
Train steps ... :  23%|██▎       | 23238/100000 [6:41:58<12:28:04,  1.71it/s]
Train steps ... :  23%|██▎       | 23239/100000 [6:41:59<12:29:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23240/100000 [6:41:59<12:29:16,  1.71it/s]
Train steps ... :  23%|██▎       | 23241/100000 [6:42:00<12:28:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23242/100000 [6:42:00<12:28:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23243/100000 [6:42:01<12:29:09,  1.71it/s]
Train steps ... :  23%|██▎       | 23244/100000 [6:42:02<12:28:44,  1.71it/s]
Train steps ... :  23%|██▎       | 23245/100000 [6:42:02<12:27:32,  1.71it/s]
Train steps ... :  23%|██▎       | 23246/100000 [6:42:03<12:27:19,  1.71it/s]
Train steps ... :  23%|██▎       | 23247/100000 [6:42:03<12:28:06,  1.71it/s]
Train steps ... :  23%|██▎       | 23248/100000 [6:42:04<12:28:08,  1.71it/s]
Train steps ... :  23%|██▎       | 23249/100000 [6:42:05<12:27:32,  1.71it/s]
Train steps ... :  23%|██▎       | 23250/100000 [6:42:05<12:27:27,  1.71it/s]Step... (23250 / 100000 | Loss: 0.6066478490829468, Learning Rate: 7.71356783919598e-05)
+
                                                                             
Step... (23250 / 100000 | Loss: 1.4648782014846802, Learning Rate: 7.71356783919598e-05)
+
Train steps ... :  23%|██▎       | 23250/100000 [6:42:05<12:27:27,  1.71it/s]
Train steps ... :  23%|██▎       | 23251/100000 [6:42:06<12:27:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23252/100000 [6:42:06<12:27:40,  1.71it/s]
Train steps ... :  23%|██▎       | 23253/100000 [6:42:07<12:28:36,  1.71it/s]
Train steps ... :  23%|██▎       | 23254/100000 [6:42:07<12:28:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23255/100000 [6:42:08<12:27:54,  1.71it/s]
Train steps ... :  23%|██▎       | 23256/100000 [6:42:09<12:27:28,  1.71it/s]
Train steps ... :  23%|██▎       | 23257/100000 [6:42:09<12:27:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23258/100000 [6:42:10<12:27:32,  1.71it/s]
Train steps ... :  23%|██▎       | 23259/100000 [6:42:10<12:27:25,  1.71it/s]
Train steps ... :  23%|██▎       | 23260/100000 [6:42:11<12:28:02,  1.71it/s]
Train steps ... :  23%|██▎       | 23261/100000 [6:42:12<12:29:44,  1.71it/s]
Train steps ... :  23%|██▎       | 23262/100000 [6:42:12<12:29:11,  1.71it/s]
Train steps ... :  23%|██▎       | 23263/100000 [6:42:13<12:28:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23264/100000 [6:42:13<12:28:55,  1.71it/s]
Train steps ... :  23%|██▎       | 23265/100000 [6:42:14<12:28:35,  1.71it/s]
Train steps ... :  23%|██▎       | 23266/100000 [6:42:14<12:27:54,  1.71it/s]
Train steps ... :  23%|██▎       | 23267/100000 [6:42:15<12:26:57,  1.71it/s]
Train steps ... :  23%|██▎       | 23268/100000 [6:42:16<12:27:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23269/100000 [6:42:16<12:27:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23270/100000 [6:42:17<12:28:21,  1.71it/s]
Train steps ... :  23%|██▎       | 23271/100000 [6:42:17<12:28:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23272/100000 [6:42:18<12:28:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23273/100000 [6:42:19<12:27:30,  1.71it/s]
Train steps ... :  23%|██▎       | 23274/100000 [6:42:19<12:28:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23275/100000 [6:42:20<12:28:58,  1.71it/s]Step... (23275 / 100000 | Loss: 1.2655153274536133, Learning Rate: 7.71105527638191e-05)
+
                                                                             
Step... (23275 / 100000 | Loss: 0.7373475432395935, Learning Rate: 7.71105527638191e-05)
+
Train steps ... :  23%|██▎       | 23275/100000 [6:42:20<12:28:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23276/100000 [6:42:20<12:28:25,  1.71it/s]
Train steps ... :  23%|██▎       | 23277/100000 [6:42:21<12:28:08,  1.71it/s]
Train steps ... :  23%|██▎       | 23278/100000 [6:42:21<12:27:33,  1.71it/s]
Train steps ... :  23%|██▎       | 23279/100000 [6:42:22<12:26:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23280/100000 [6:42:23<12:26:33,  1.71it/s]
Train steps ... :  23%|██▎       | 23281/100000 [6:42:23<12:26:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23282/100000 [6:42:24<12:26:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23283/100000 [6:42:24<12:27:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23284/100000 [6:42:25<12:26:41,  1.71it/s]
Train steps ... :  23%|██▎       | 23285/100000 [6:42:26<12:27:32,  1.71it/s]
Train steps ... :  23%|██▎       | 23286/100000 [6:42:26<12:30:45,  1.70it/s]
Train steps ... :  23%|██▎       | 23287/100000 [6:42:27<12:29:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23288/100000 [6:42:27<12:28:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23289/100000 [6:42:28<12:27:50,  1.71it/s]
Train steps ... :  23%|██▎       | 23290/100000 [6:42:29<12:29:10,  1.71it/s]
Train steps ... :  23%|██▎       | 23291/100000 [6:42:29<12:28:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23292/100000 [6:42:30<12:27:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23293/100000 [6:42:30<12:27:30,  1.71it/s]
Train steps ... :  23%|██▎       | 23294/100000 [6:42:31<12:27:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23295/100000 [6:42:31<12:27:33,  1.71it/s]
Train steps ... :  23%|██▎       | 23296/100000 [6:42:32<12:26:51,  1.71it/s]
Train steps ... :  23%|██▎       | 23297/100000 [6:42:33<12:26:41,  1.71it/s]
Train steps ... :  23%|██▎       | 23298/100000 [6:42:33<12:25:54,  1.71it/s]
Train steps ... :  23%|██▎       | 23299/100000 [6:42:34<12:26:34,  1.71it/s]
Train steps ... :  23%|██▎       | 23300/100000 [6:42:34<12:26:43,  1.71it/s]Step... (23300 / 100000 | Loss: 1.0863635540008545, Learning Rate: 7.70854271356784e-05)
+
                                                                             
Step... (23300 / 100000 | Loss: 0.8110690116882324, Learning Rate: 7.70854271356784e-05)
+
Train steps ... :  23%|██▎       | 23300/100000 [6:42:35<12:26:43,  1.71it/s]
Train steps ... :  23%|██▎       | 23301/100000 [6:42:35<12:27:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23302/100000 [6:42:36<12:28:39,  1.71it/s]
Train steps ... :  23%|██▎       | 23303/100000 [6:42:36<12:27:45,  1.71it/s]
Train steps ... :  23%|██▎       | 23304/100000 [6:42:37<12:27:25,  1.71it/s]
Train steps ... :  23%|██▎       | 23305/100000 [6:42:37<12:27:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23306/100000 [6:42:38<12:27:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23307/100000 [6:42:38<12:27:00,  1.71it/s]
Train steps ... :  23%|██▎       | 23308/100000 [6:42:39<12:26:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23309/100000 [6:42:40<12:26:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23310/100000 [6:42:40<12:26:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23311/100000 [6:42:41<12:26:00,  1.71it/s]
Train steps ... :  23%|██▎       | 23312/100000 [6:42:41<12:26:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23313/100000 [6:42:42<12:26:44,  1.71it/s]
Train steps ... :  23%|██▎       | 23314/100000 [6:42:43<12:26:10,  1.71it/s]
Train steps ... :  23%|██▎       | 23315/100000 [6:42:43<12:26:28,  1.71it/s]
Train steps ... :  23%|██▎       | 23316/100000 [6:42:44<12:26:40,  1.71it/s]
Train steps ... :  23%|██▎       | 23317/100000 [6:42:44<12:27:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23318/100000 [6:42:45<12:26:27,  1.71it/s]
Train steps ... :  23%|██▎       | 23319/100000 [6:42:45<12:26:06,  1.71it/s]
Train steps ... :  23%|██▎       | 23320/100000 [6:42:46<12:26:59,  1.71it/s]
Train steps ... :  23%|██▎       | 23321/100000 [6:42:47<12:26:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23322/100000 [6:42:47<12:28:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23323/100000 [6:42:48<12:27:25,  1.71it/s]
Train steps ... :  23%|██▎       | 23324/100000 [6:42:48<12:26:54,  1.71it/s]
Train steps ... :  23%|██▎       | 23325/100000 [6:42:49<12:26:18,  1.71it/s]Step... (23325 / 100000 | Loss: 1.211654543876648, Learning Rate: 7.70603015075377e-05)
+
                                                                             
Step... (23325 / 100000 | Loss: 0.8153536915779114, Learning Rate: 7.70603015075377e-05)
+
Train steps ... :  23%|██▎       | 23325/100000 [6:42:49<12:26:18,  1.71it/s]
Train steps ... :  23%|██▎       | 23326/100000 [6:42:50<12:27:11,  1.71it/s]
Train steps ... :  23%|██▎       | 23327/100000 [6:42:50<12:27:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23328/100000 [6:42:51<12:28:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23329/100000 [6:42:51<12:28:25,  1.71it/s]
Train steps ... :  23%|██▎       | 23330/100000 [6:42:52<12:27:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23331/100000 [6:42:52<12:27:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23332/100000 [6:42:53<12:26:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23333/100000 [6:42:54<12:26:35,  1.71it/s]
Train steps ... :  23%|██▎       | 23334/100000 [6:42:54<12:26:28,  1.71it/s]
Train steps ... :  23%|██▎       | 23335/100000 [6:42:55<12:26:40,  1.71it/s]
Train steps ... :  23%|██▎       | 23336/100000 [6:42:55<12:26:34,  1.71it/s]
Train steps ... :  23%|██▎       | 23337/100000 [6:42:56<12:26:47,  1.71it/s]
Train steps ... :  23%|██▎       | 23338/100000 [6:42:57<12:27:35,  1.71it/s]
Train steps ... :  23%|██▎       | 23339/100000 [6:42:57<12:27:53,  1.71it/s]
Train steps ... :  23%|██▎       | 23340/100000 [6:42:58<12:27:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23341/100000 [6:42:58<12:27:00,  1.71it/s]
Train steps ... :  23%|██▎       | 23342/100000 [6:42:59<12:27:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23343/100000 [6:42:59<12:26:31,  1.71it/s]
Train steps ... :  23%|██▎       | 23344/100000 [6:43:00<12:26:02,  1.71it/s]
Train steps ... :  23%|██▎       | 23345/100000 [6:43:01<12:25:59,  1.71it/s]
Train steps ... :  23%|██▎       | 23346/100000 [6:43:01<12:25:41,  1.71it/s]
Train steps ... :  23%|██▎       | 23347/100000 [6:43:02<12:26:37,  1.71it/s]
Train steps ... :  23%|██▎       | 23348/100000 [6:43:02<12:26:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23349/100000 [6:43:03<12:26:34,  1.71it/s]
Train steps ... :  23%|██▎       | 23350/100000 [6:43:04<12:26:46,  1.71it/s]Step... (23350 / 100000 | Loss: 0.9838812351226807, Learning Rate: 7.7035175879397e-05)
+
                                                                             
Step... (23350 / 100000 | Loss: 1.0354348421096802, Learning Rate: 7.7035175879397e-05)
+
Train steps ... :  23%|██▎       | 23350/100000 [6:43:04<12:26:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23351/100000 [6:43:04<12:28:22,  1.71it/s]
Train steps ... :  23%|██▎       | 23352/100000 [6:43:05<12:27:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23353/100000 [6:43:05<12:29:01,  1.71it/s]
Train steps ... :  23%|██▎       | 23354/100000 [6:43:06<12:26:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23355/100000 [6:43:07<12:28:00,  1.71it/s]
Train steps ... :  23%|██▎       | 23356/100000 [6:43:07<12:27:37,  1.71it/s]
Train steps ... :  23%|██▎       | 23357/100000 [6:43:08<12:30:30,  1.70it/s]
Train steps ... :  23%|██▎       | 23358/100000 [6:43:08<12:28:35,  1.71it/s]
Train steps ... :  23%|██▎       | 23359/100000 [6:43:09<12:27:30,  1.71it/s]
Train steps ... :  23%|██▎       | 23360/100000 [6:43:09<12:26:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23361/100000 [6:43:10<12:26:32,  1.71it/s]
Train steps ... :  23%|██▎       | 23362/100000 [6:43:11<12:26:23,  1.71it/s]
Train steps ... :  23%|██▎       | 23363/100000 [6:43:11<12:27:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23364/100000 [6:43:12<12:26:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23365/100000 [6:43:12<12:26:59,  1.71it/s]
Train steps ... :  23%|██▎       | 23366/100000 [6:43:13<12:27:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23367/100000 [6:43:14<12:26:10,  1.71it/s]
Train steps ... :  23%|██▎       | 23368/100000 [6:43:14<12:26:29,  1.71it/s]
Train steps ... :  23%|██▎       | 23369/100000 [6:43:15<12:26:45,  1.71it/s]
Train steps ... :  23%|██▎       | 23370/100000 [6:43:15<12:29:17,  1.70it/s]
Train steps ... :  23%|██▎       | 23371/100000 [6:43:16<12:29:16,  1.70it/s]
Train steps ... :  23%|██▎       | 23372/100000 [6:43:16<12:28:59,  1.71it/s]
Train steps ... :  23%|██▎       | 23373/100000 [6:43:17<12:28:45,  1.71it/s]
Train steps ... :  23%|██▎       | 23374/100000 [6:43:18<12:27:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23375/100000 [6:43:18<12:28:20,  1.71it/s]Step... (23375 / 100000 | Loss: 1.0469845533370972, Learning Rate: 7.701005025125628e-05)
+
                                                                             
Step... (23375 / 100000 | Loss: 0.8776382207870483, Learning Rate: 7.701005025125628e-05)
+
Train steps ... :  23%|██▎       | 23375/100000 [6:43:19<12:28:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23376/100000 [6:43:19<12:27:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23377/100000 [6:43:19<12:26:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23378/100000 [6:43:20<12:27:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23379/100000 [6:43:21<12:27:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23380/100000 [6:43:21<12:26:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23381/100000 [6:43:22<12:27:08,  1.71it/s]
Train steps ... :  23%|██▎       | 23382/100000 [6:43:22<12:26:28,  1.71it/s]
Train steps ... :  23%|██▎       | 23383/100000 [6:43:23<12:26:43,  1.71it/s]
Train steps ... :  23%|██▎       | 23384/100000 [6:43:23<12:26:15,  1.71it/s]
Train steps ... :  23%|██▎       | 23385/100000 [6:43:24<12:26:20,  1.71it/s]
Train steps ... :  23%|██▎       | 23386/100000 [6:43:25<12:25:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23387/100000 [6:43:25<12:25:57,  1.71it/s]
Train steps ... :  23%|██▎       | 23388/100000 [6:43:26<12:25:32,  1.71it/s]
Train steps ... :  23%|██▎       | 23389/100000 [6:43:26<12:25:40,  1.71it/s]
Train steps ... :  23%|██▎       | 23390/100000 [6:43:27<12:26:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23391/100000 [6:43:28<12:25:32,  1.71it/s]
Train steps ... :  23%|██▎       | 23392/100000 [6:43:28<12:25:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23393/100000 [6:43:29<12:25:43,  1.71it/s]
Train steps ... :  23%|██▎       | 23394/100000 [6:43:29<12:26:01,  1.71it/s]
Train steps ... :  23%|██▎       | 23395/100000 [6:43:30<12:27:44,  1.71it/s]
Train steps ... :  23%|██▎       | 23396/100000 [6:43:30<12:26:23,  1.71it/s]
Train steps ... :  23%|██▎       | 23397/100000 [6:43:31<12:26:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23398/100000 [6:43:32<12:25:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23399/100000 [6:43:32<12:25:35,  1.71it/s]
Train steps ... :  23%|██▎       | 23400/100000 [6:43:33<12:26:45,  1.71it/s]Step... (23400 / 100000 | Loss: 0.8358213901519775, Learning Rate: 7.698492462311559e-05)
+
                                                                             
Step... (23400 / 100000 | Loss: 1.3033078908920288, Learning Rate: 7.698492462311559e-05)
+
Train steps ... :  23%|██▎       | 23400/100000 [6:43:33<12:26:45,  1.71it/s]
Train steps ... :  23%|██▎       | 23401/100000 [6:43:33<12:27:06,  1.71it/s]
Train steps ... :  23%|██▎       | 23402/100000 [6:43:34<12:26:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23403/100000 [6:43:35<12:26:15,  1.71it/s]
Train steps ... :  23%|██▎       | 23404/100000 [6:43:35<12:26:04,  1.71it/s]
Train steps ... :  23%|██▎       | 23405/100000 [6:43:36<12:26:40,  1.71it/s]
Train steps ... :  23%|██▎       | 23406/100000 [6:43:36<12:27:10,  1.71it/s]
Train steps ... :  23%|██▎       | 23407/100000 [6:43:37<12:26:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23408/100000 [6:43:38<12:25:24,  1.71it/s]
Train steps ... :  23%|██▎       | 23409/100000 [6:43:38<12:25:16,  1.71it/s]
Train steps ... :  23%|██▎       | 23410/100000 [6:43:39<12:26:08,  1.71it/s]
Train steps ... :  23%|██▎       | 23411/100000 [6:43:39<12:26:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23412/100000 [6:43:40<12:26:45,  1.71it/s]
Train steps ... :  23%|██▎       | 23413/100000 [6:43:40<12:26:41,  1.71it/s]
Train steps ... :  23%|██▎       | 23414/100000 [6:43:41<12:26:10,  1.71it/s]
Train steps ... :  23%|██▎       | 23415/100000 [6:43:42<12:26:24,  1.71it/s]
Train steps ... :  23%|██▎       | 23416/100000 [6:43:42<12:26:04,  1.71it/s]
Train steps ... :  23%|██▎       | 23417/100000 [6:43:43<12:26:29,  1.71it/s]
Train steps ... :  23%|██▎       | 23418/100000 [6:43:43<12:26:29,  1.71it/s]
Train steps ... :  23%|██▎       | 23419/100000 [6:43:44<12:26:34,  1.71it/s]
Train steps ... :  23%|██▎       | 23420/100000 [6:43:45<12:25:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23421/100000 [6:43:45<12:25:46,  1.71it/s]
Train steps ... :  23%|██▎       | 23422/100000 [6:43:46<12:26:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23423/100000 [6:43:46<12:27:27,  1.71it/s]
Train steps ... :  23%|██▎       | 23424/100000 [6:43:47<12:26:29,  1.71it/s]
Train steps ... :  23%|██▎       | 23425/100000 [6:43:47<12:26:01,  1.71it/s]Step... (23425 / 100000 | Loss: 0.7068166136741638, Learning Rate: 7.695979899497487e-05)
+
                                                                             
Step... (23425 / 100000 | Loss: 0.9638409614562988, Learning Rate: 7.695979899497487e-05)
+
Train steps ... :  23%|██▎       | 23425/100000 [6:43:48<12:26:01,  1.71it/s]
Train steps ... :  23%|██▎       | 23426/100000 [6:43:48<12:27:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23427/100000 [6:43:49<12:27:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23428/100000 [6:43:49<12:26:44,  1.71it/s]
Train steps ... :  23%|██▎       | 23429/100000 [6:43:50<12:27:11,  1.71it/s]
Train steps ... :  23%|██▎       | 23430/100000 [6:43:50<12:27:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23431/100000 [6:43:51<12:26:23,  1.71it/s]
Train steps ... :  23%|██▎       | 23432/100000 [6:43:52<12:26:12,  1.71it/s]
Train steps ... :  23%|██▎       | 23433/100000 [6:43:52<12:25:55,  1.71it/s]
Train steps ... :  23%|██▎       | 23434/100000 [6:43:53<12:25:25,  1.71it/s]
Train steps ... :  23%|██▎       | 23435/100000 [6:43:53<12:25:24,  1.71it/s]
Train steps ... :  23%|██▎       | 23436/100000 [6:43:54<12:26:13,  1.71it/s]
Train steps ... :  23%|██▎       | 23437/100000 [6:43:54<12:25:26,  1.71it/s]
Train steps ... :  23%|██▎       | 23438/100000 [6:43:55<12:24:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23439/100000 [6:43:56<12:25:29,  1.71it/s]
Train steps ... :  23%|██▎       | 23440/100000 [6:43:56<12:24:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23441/100000 [6:43:57<12:25:53,  1.71it/s]
Train steps ... :  23%|██▎       | 23442/100000 [6:43:57<12:26:55,  1.71it/s]
Train steps ... :  23%|██▎       | 23443/100000 [6:43:58<12:26:17,  1.71it/s]
Train steps ... :  23%|██▎       | 23444/100000 [6:43:59<12:27:07,  1.71it/s]
Train steps ... :  23%|██▎       | 23445/100000 [6:43:59<12:26:49,  1.71it/s]
Train steps ... :  23%|██▎       | 23446/100000 [6:44:00<12:25:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23447/100000 [6:44:00<12:25:15,  1.71it/s]
Train steps ... :  23%|██▎       | 23448/100000 [6:44:01<12:25:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23449/100000 [6:44:01<12:25:03,  1.71it/s]
Train steps ... :  23%|██▎       | 23450/100000 [6:44:02<12:25:45,  1.71it/s]Step... (23450 / 100000 | Loss: 0.8597567081451416, Learning Rate: 7.693467336683418e-05)
+
                                                                             
Step... (23450 / 100000 | Loss: 0.9173182845115662, Learning Rate: 7.693467336683418e-05)
+
Train steps ... :  23%|██▎       | 23450/100000 [6:44:02<12:25:45,  1.71it/s]
Train steps ... :  23%|██▎       | 23451/100000 [6:44:03<12:25:47,  1.71it/s]
Train steps ... :  23%|██▎       | 23452/100000 [6:44:03<12:25:45,  1.71it/s]
Train steps ... :  23%|██▎       | 23453/100000 [6:44:04<12:26:27,  1.71it/s]
Train steps ... :  23%|██▎       | 23454/100000 [6:44:04<12:25:49,  1.71it/s]
Train steps ... :  23%|██▎       | 23455/100000 [6:44:05<12:26:43,  1.71it/s]
Train steps ... :  23%|██▎       | 23456/100000 [6:44:06<12:26:54,  1.71it/s]
Train steps ... :  23%|██▎       | 23457/100000 [6:44:06<12:26:13,  1.71it/s]
Train steps ... :  23%|██▎       | 23458/100000 [6:44:07<12:26:22,  1.71it/s]
Train steps ... :  23%|██▎       | 23459/100000 [6:44:07<12:26:08,  1.71it/s]
Train steps ... :  23%|██▎       | 23460/100000 [6:44:08<12:25:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23461/100000 [6:44:08<12:24:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23462/100000 [6:44:09<12:25:34,  1.71it/s]
Train steps ... :  23%|██▎       | 23463/100000 [6:44:10<12:25:09,  1.71it/s]
Train steps ... :  23%|██▎       | 23464/100000 [6:44:10<12:27:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23465/100000 [6:44:11<12:25:27,  1.71it/s]
Train steps ... :  23%|██▎       | 23466/100000 [6:44:11<12:27:24,  1.71it/s]
Train steps ... :  23%|██▎       | 23467/100000 [6:44:12<12:26:48,  1.71it/s]
Train steps ... :  23%|██▎       | 23468/100000 [6:44:13<12:26:28,  1.71it/s]
Train steps ... :  23%|██▎       | 23469/100000 [6:44:13<12:25:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23470/100000 [6:44:14<12:25:57,  1.71it/s]
Train steps ... :  23%|██▎       | 23471/100000 [6:44:14<12:25:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23472/100000 [6:44:15<12:24:56,  1.71it/s]
Train steps ... :  23%|██▎       | 23473/100000 [6:44:16<12:25:02,  1.71it/s]
Train steps ... :  23%|██▎       | 23474/100000 [6:44:16<12:24:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23475/100000 [6:44:17<12:25:31,  1.71it/s]Step... (23475 / 100000 | Loss: 1.0768840312957764, Learning Rate: 7.690954773869346e-05)
+
                                                                             
Step... (23475 / 100000 | Loss: 0.8695204854011536, Learning Rate: 7.690954773869346e-05)
+
Train steps ... :  23%|██▎       | 23475/100000 [6:44:17<12:25:31,  1.71it/s]
Train steps ... :  23%|██▎       | 23476/100000 [6:44:17<12:28:06,  1.70it/s]
Train steps ... :  23%|██▎       | 23477/100000 [6:44:18<12:25:18,  1.71it/s]
Train steps ... :  23%|██▎       | 23478/100000 [6:44:18<12:24:42,  1.71it/s]
Train steps ... :  23%|██▎       | 23479/100000 [6:44:19<12:24:38,  1.71it/s]
Train steps ... :  23%|██▎       | 23480/100000 [6:44:20<12:24:36,  1.71it/s]
Train steps ... :  23%|██▎       | 23481/100000 [6:44:20<12:24:58,  1.71it/s]
Train steps ... :  23%|██▎       | 23482/100000 [6:44:21<12:26:57,  1.71it/s]
Train steps ... :  23%|██▎       | 23483/100000 [6:44:21<12:27:10,  1.71it/s]
Train steps ... :  23%|██▎       | 23484/100000 [6:44:22<12:27:10,  1.71it/s]
Train steps ... :  23%|██▎       | 23485/100000 [6:44:23<12:26:52,  1.71it/s]
Train steps ... :  23%|██▎       | 23486/100000 [6:44:23<12:28:05,  1.70it/s]
Train steps ... :  23%|██▎       | 23487/100000 [6:44:24<12:25:35,  1.71it/s]
Train steps ... :  23%|██▎       | 23488/100000 [6:44:24<12:25:44,  1.71it/s]
Train steps ... :  23%|██▎       | 23489/100000 [6:44:25<12:25:37,  1.71it/s]
Train steps ... :  23%|██▎       | 23490/100000 [6:44:25<12:26:14,  1.71it/s]
Train steps ... :  23%|██▎       | 23491/100000 [6:44:26<12:25:29,  1.71it/s]
Train steps ... :  23%|██▎       | 23492/100000 [6:44:27<12:26:11,  1.71it/s]
Train steps ... :  23%|██▎       | 23493/100000 [6:44:27<12:25:27,  1.71it/s]
Train steps ... :  23%|██▎       | 23494/100000 [6:44:28<12:25:05,  1.71it/s]
Train steps ... :  23%|██▎       | 23495/100000 [6:44:28<12:24:50,  1.71it/s]
Train steps ... :  23%|██▎       | 23496/100000 [6:44:29<12:25:06,  1.71it/s]
Train steps ... :  23%|██▎       | 23497/100000 [6:44:30<12:25:09,  1.71it/s]
Train steps ... :  23%|██▎       | 23498/100000 [6:44:30<12:24:49,  1.71it/s]
Train steps ... :  23%|██▎       | 23499/100000 [6:44:31<12:24:49,  1.71it/s]
Train steps ... :  24%|██▎       | 23500/100000 [6:44:31<12:24:31,  1.71it/s]Step... (23500 / 100000 | Loss: 0.8556240797042847, Learning Rate: 7.688442211055277e-05)
+
                                                                             
Step... (23500 / 100000 | Loss: 0.9775276184082031, Learning Rate: 7.688442211055277e-05)
+
Train steps ... :  24%|██▎       | 23500/100000 [6:44:32<12:24:31,  1.71it/s]
Train steps ... :  24%|██▎       | 23501/100000 [6:44:32<12:25:15,  1.71it/s]
Train steps ... :  24%|██▎       | 23502/100000 [6:44:32<12:24:44,  1.71it/s]
Train steps ... :  24%|██▎       | 23503/100000 [6:44:33<12:24:38,  1.71it/s]
Train steps ... :  24%|██▎       | 23504/100000 [6:44:34<12:24:22,  1.71it/s]
Train steps ... :  24%|██▎       | 23505/100000 [6:44:34<12:24:36,  1.71it/s]
Train steps ... :  24%|██▎       | 23506/100000 [6:44:35<12:24:10,  1.71it/s]
Train steps ... :  24%|██▎       | 23507/100000 [6:44:35<12:26:52,  1.71it/s]
Train steps ... :  24%|██▎       | 23508/100000 [6:44:36<12:25:01,  1.71it/s]
Train steps ... :  24%|██▎       | 23509/100000 [6:44:37<12:24:45,  1.71it/s]
Train steps ... :  24%|██▎       | 23510/100000 [6:44:37<12:25:09,  1.71it/s]
Train steps ... :  24%|██▎       | 23511/100000 [6:44:38<12:24:48,  1.71it/s]
Train steps ... :  24%|██▎       | 23512/100000 [6:44:38<12:24:40,  1.71it/s]
Train steps ... :  24%|██▎       | 23513/100000 [6:44:39<12:23:58,  1.71it/s]
Train steps ... :  24%|██▎       | 23514/100000 [6:44:39<12:25:37,  1.71it/s]
Train steps ... :  24%|██▎       | 23515/100000 [6:44:40<12:23:54,  1.71it/s]
Train steps ... :  24%|██▎       | 23516/100000 [6:44:41<12:23:18,  1.71it/s]
Train steps ... :  24%|██▎       | 23517/100000 [6:44:41<12:23:53,  1.71it/s]
Train steps ... :  24%|██▎       | 23518/100000 [6:44:42<12:23:46,  1.71it/s]
Train steps ... :  24%|██▎       | 23519/100000 [6:44:42<12:24:22,  1.71it/s]
Train steps ... :  24%|██▎       | 23520/100000 [6:44:43<12:24:14,  1.71it/s]
Train steps ... :  24%|██▎       | 23521/100000 [6:44:44<12:24:07,  1.71it/s]
Train steps ... :  24%|██▎       | 23522/100000 [6:44:44<12:24:17,  1.71it/s]
Train steps ... :  24%|██▎       | 23523/100000 [6:44:45<12:23:44,  1.71it/s]
Train steps ... :  24%|██▎       | 23524/100000 [6:44:45<12:24:10,  1.71it/s]
Train steps ... :  24%|██▎       | 23525/100000 [6:44:46<12:25:10,  1.71it/s]Step... (23525 / 100000 | Loss: 1.01644766330719, Learning Rate: 7.685929648241207e-05)
+
                                                                             
Step... (23525 / 100000 | Loss: 0.724001407623291, Learning Rate: 7.685929648241207e-05)
+
Train steps ... :  24%|██▎       | 23525/100000 [6:44:46<12:25:10,  1.71it/s]
Train steps ... :  24%|██▎       | 23526/100000 [6:44:46<12:25:03,  1.71it/s]
Train steps ... :  24%|██▎       | 23527/100000 [6:44:47<12:25:22,  1.71it/s]
Train steps ... :  24%|██▎       | 23528/100000 [6:44:48<12:25:20,  1.71it/s]
Train steps ... :  24%|██▎       | 23529/100000 [6:44:48<12:26:11,  1.71it/s]
Train steps ... :  24%|██▎       | 23530/100000 [6:44:49<12:25:22,  1.71it/s]
Train steps ... :  24%|██▎       | 23531/100000 [6:44:49<12:25:34,  1.71it/s]
Train steps ... :  24%|██▎       | 23532/100000 [6:44:50<12:25:00,  1.71it/s]
Train steps ... :  24%|██▎       | 23533/100000 [6:44:51<12:24:57,  1.71it/s]
Train steps ... :  24%|██▎       | 23534/100000 [6:44:51<12:24:55,  1.71it/s]
Train steps ... :  24%|██▎       | 23535/100000 [6:44:52<12:24:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23536/100000 [6:44:52<12:24:04,  1.71it/s]
Train steps ... :  24%|██▎       | 23537/100000 [6:44:53<12:24:31,  1.71it/s]
Train steps ... :  24%|██▎       | 23538/100000 [6:44:54<12:24:16,  1.71it/s]
Train steps ... :  24%|██▎       | 23539/100000 [6:44:54<12:24:25,  1.71it/s]
Train steps ... :  24%|██▎       | 23540/100000 [6:44:55<12:25:05,  1.71it/s]
Train steps ... :  24%|██▎       | 23541/100000 [6:44:55<12:24:36,  1.71it/s]
Train steps ... :  24%|██▎       | 23542/100000 [6:44:56<12:24:25,  1.71it/s]
Train steps ... :  24%|██▎       | 23543/100000 [6:44:56<12:23:35,  1.71it/s]
Train steps ... :  24%|██▎       | 23544/100000 [6:44:57<12:24:19,  1.71it/s]
Train steps ... :  24%|██▎       | 23545/100000 [6:44:58<12:24:18,  1.71it/s]
Train steps ... :  24%|██▎       | 23546/100000 [6:44:58<12:24:15,  1.71it/s]
Train steps ... :  24%|██▎       | 23547/100000 [6:44:59<12:24:59,  1.71it/s]
Train steps ... :  24%|██▎       | 23548/100000 [6:44:59<12:24:45,  1.71it/s]
Train steps ... :  24%|██▎       | 23549/100000 [6:45:00<12:25:06,  1.71it/s]
Train steps ... :  24%|██▎       | 23550/100000 [6:45:01<12:24:37,  1.71it/s]Step... (23550 / 100000 | Loss: 0.9061241745948792, Learning Rate: 7.683417085427135e-05)
+
                                                                             
Step... (23550 / 100000 | Loss: 0.858729362487793, Learning Rate: 7.683417085427135e-05)
+
Train steps ... :  24%|██▎       | 23550/100000 [6:45:01<12:24:37,  1.71it/s]
Train steps ... :  24%|██▎       | 23551/100000 [6:45:01<12:25:55,  1.71it/s]
Train steps ... :  24%|██▎       | 23552/100000 [6:45:02<12:26:07,  1.71it/s]
Train steps ... :  24%|██▎       | 23553/100000 [6:45:02<12:25:35,  1.71it/s]
Train steps ... :  24%|██▎       | 23554/100000 [6:45:03<12:24:37,  1.71it/s]
Train steps ... :  24%|██▎       | 23555/100000 [6:45:03<12:24:29,  1.71it/s]
Train steps ... :  24%|██▎       | 23556/100000 [6:45:04<12:24:07,  1.71it/s]
Train steps ... :  24%|██▎       | 23557/100000 [6:45:05<12:24:17,  1.71it/s]
Train steps ... :  24%|██▎       | 23558/100000 [6:45:05<12:24:23,  1.71it/s]
Train steps ... :  24%|██▎       | 23559/100000 [6:45:06<12:24:50,  1.71it/s]
Train steps ... :  24%|██▎       | 23560/100000 [6:45:06<12:25:25,  1.71it/s]
Train steps ... :  24%|██▎       | 23561/100000 [6:45:07<12:27:04,  1.71it/s]
Train steps ... :  24%|██▎       | 23562/100000 [6:45:08<12:26:51,  1.71it/s]
Train steps ... :  24%|██▎       | 23563/100000 [6:45:08<12:25:57,  1.71it/s]
Train steps ... :  24%|██▎       | 23564/100000 [6:45:09<12:25:32,  1.71it/s]
Train steps ... :  24%|██▎       | 23565/100000 [6:45:09<12:25:15,  1.71it/s]
Train steps ... :  24%|██▎       | 23566/100000 [6:45:10<12:24:55,  1.71it/s]
Train steps ... :  24%|██▎       | 23567/100000 [6:45:10<12:25:26,  1.71it/s]
Train steps ... :  24%|██▎       | 23568/100000 [6:45:11<12:25:49,  1.71it/s]
Train steps ... :  24%|██▎       | 23569/100000 [6:45:12<12:25:05,  1.71it/s]
Train steps ... :  24%|██▎       | 23570/100000 [6:45:12<12:26:00,  1.71it/s]
Train steps ... :  24%|██▎       | 23571/100000 [6:45:13<12:25:02,  1.71it/s]
Train steps ... :  24%|██▎       | 23572/100000 [6:45:13<12:25:14,  1.71it/s]
Train steps ... :  24%|██▎       | 23573/100000 [6:45:14<12:25:34,  1.71it/s]
Train steps ... :  24%|██▎       | 23574/100000 [6:45:15<12:24:30,  1.71it/s]
Train steps ... :  24%|██▎       | 23575/100000 [6:45:15<12:24:18,  1.71it/s]Step... (23575 / 100000 | Loss: 0.9865756034851074, Learning Rate: 7.680904522613066e-05)
+
                                                                             
Step... (23575 / 100000 | Loss: 0.8560261726379395, Learning Rate: 7.680904522613066e-05)
+
Train steps ... :  24%|██▎       | 23575/100000 [6:45:15<12:24:18,  1.71it/s]
Train steps ... :  24%|██▎       | 23576/100000 [6:45:16<12:25:18,  1.71it/s]
Train steps ... :  24%|██▎       | 23577/100000 [6:45:16<12:24:56,  1.71it/s]
Train steps ... :  24%|██▎       | 23578/100000 [6:45:17<12:24:56,  1.71it/s]
Train steps ... :  24%|██▎       | 23579/100000 [6:45:17<12:25:31,  1.71it/s]
Train steps ... :  24%|██▎       | 23580/100000 [6:45:18<12:25:12,  1.71it/s]
Train steps ... :  24%|██▎       | 23581/100000 [6:45:19<12:24:32,  1.71it/s]
Train steps ... :  24%|██▎       | 23582/100000 [6:45:19<12:24:41,  1.71it/s]
Train steps ... :  24%|██▎       | 23583/100000 [6:45:20<12:26:17,  1.71it/s]
Train steps ... :  24%|██▎       | 23584/100000 [6:45:20<12:26:36,  1.71it/s]
Train steps ... :  24%|██▎       | 23585/100000 [6:45:21<12:25:16,  1.71it/s]
Train steps ... :  24%|██▎       | 23586/100000 [6:45:22<12:24:52,  1.71it/s]
Train steps ... :  24%|██▎       | 23587/100000 [6:45:22<12:24:51,  1.71it/s]
Train steps ... :  24%|██▎       | 23588/100000 [6:45:23<12:24:13,  1.71it/s]
Train steps ... :  24%|██▎       | 23589/100000 [6:45:23<12:24:20,  1.71it/s]
Train steps ... :  24%|██▎       | 23590/100000 [6:45:24<12:24:26,  1.71it/s]
Train steps ... :  24%|██▎       | 23591/100000 [6:45:25<12:24:35,  1.71it/s]
Train steps ... :  24%|██▎       | 23592/100000 [6:45:25<12:25:36,  1.71it/s]
Train steps ... :  24%|██▎       | 23593/100000 [6:45:26<12:25:02,  1.71it/s]
Train steps ... :  24%|██▎       | 23594/100000 [6:45:26<12:25:35,  1.71it/s]
Train steps ... :  24%|██▎       | 23595/100000 [6:45:27<12:26:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23596/100000 [6:45:27<12:25:57,  1.71it/s]
Train steps ... :  24%|██▎       | 23597/100000 [6:45:28<12:25:11,  1.71it/s]
Train steps ... :  24%|██▎       | 23598/100000 [6:45:29<12:24:17,  1.71it/s]
Train steps ... :  24%|██▎       | 23599/100000 [6:45:29<12:24:11,  1.71it/s]
Train steps ... :  24%|██▎       | 23600/100000 [6:45:30<12:24:16,  1.71it/s]Step... (23600 / 100000 | Loss: 1.0750412940979004, Learning Rate: 7.678391959798995e-05)
+
                                                                             
Step... (23600 / 100000 | Loss: 1.2295432090759277, Learning Rate: 7.678391959798995e-05)
+
Train steps ... :  24%|██▎       | 23600/100000 [6:45:30<12:24:16,  1.71it/s]
Train steps ... :  24%|██▎       | 23601/100000 [6:45:30<12:24:40,  1.71it/s]
Train steps ... :  24%|██▎       | 23602/100000 [6:45:31<12:24:30,  1.71it/s]
Train steps ... :  24%|██▎       | 23603/100000 [6:45:32<12:24:16,  1.71it/s]
Train steps ... :  24%|██▎       | 23604/100000 [6:45:32<12:25:18,  1.71it/s]
Train steps ... :  24%|██▎       | 23605/100000 [6:45:33<12:25:52,  1.71it/s]
Train steps ... :  24%|██▎       | 23606/100000 [6:45:33<12:25:00,  1.71it/s]
Train steps ... :  24%|██▎       | 23607/100000 [6:45:34<12:25:57,  1.71it/s]
Train steps ... :  24%|██▎       | 23608/100000 [6:45:34<12:26:11,  1.71it/s]
Train steps ... :  24%|██▎       | 23609/100000 [6:45:35<12:25:50,  1.71it/s]
Train steps ... :  24%|██▎       | 23610/100000 [6:45:36<12:25:13,  1.71it/s]
Train steps ... :  24%|██▎       | 23611/100000 [6:45:36<12:25:25,  1.71it/s]
Train steps ... :  24%|██▎       | 23612/100000 [6:45:37<12:24:26,  1.71it/s]
Train steps ... :  24%|██▎       | 23613/100000 [6:45:37<12:24:18,  1.71it/s]
Train steps ... :  24%|██▎       | 23614/100000 [6:45:38<12:24:32,  1.71it/s]
Train steps ... :  24%|██▎       | 23615/100000 [6:45:39<12:25:00,  1.71it/s]
Train steps ... :  24%|██▎       | 23616/100000 [6:45:39<12:24:32,  1.71it/s]
Train steps ... :  24%|██▎       | 23617/100000 [6:45:40<12:24:48,  1.71it/s]
Train steps ... :  24%|██▎       | 23618/100000 [6:45:40<12:24:54,  1.71it/s]
Train steps ... :  24%|██▎       | 23619/100000 [6:45:41<12:24:20,  1.71it/s]
Train steps ... :  24%|██▎       | 23620/100000 [6:45:41<12:23:56,  1.71it/s]
Train steps ... :  24%|██▎       | 23621/100000 [6:45:42<12:23:01,  1.71it/s]
Train steps ... :  24%|██▎       | 23622/100000 [6:45:43<12:23:02,  1.71it/s]
Train steps ... :  24%|██▎       | 23623/100000 [6:45:43<12:23:56,  1.71it/s]
Train steps ... :  24%|██▎       | 23624/100000 [6:45:44<12:23:29,  1.71it/s]
Train steps ... :  24%|██▎       | 23625/100000 [6:45:44<12:23:37,  1.71it/s]Step... (23625 / 100000 | Loss: 0.8618956804275513, Learning Rate: 7.675879396984926e-05)
+
                                                                             
Step... (23625 / 100000 | Loss: 0.9103225469589233, Learning Rate: 7.675879396984926e-05)
+
Train steps ... :  24%|██▎       | 23625/100000 [6:45:45<12:23:37,  1.71it/s]
Train steps ... :  24%|██▎       | 23626/100000 [6:45:45<12:24:12,  1.71it/s]
Train steps ... :  24%|██▎       | 23627/100000 [6:45:46<12:23:35,  1.71it/s]
Train steps ... :  24%|██▎       | 23628/100000 [6:45:46<12:23:29,  1.71it/s]
Train steps ... :  24%|██▎       | 23629/100000 [6:45:47<12:23:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23630/100000 [6:45:47<12:23:03,  1.71it/s]
Train steps ... :  24%|██▎       | 23631/100000 [6:45:48<12:23:16,  1.71it/s]
Train steps ... :  24%|██▎       | 23632/100000 [6:45:48<12:23:12,  1.71it/s]
Train steps ... :  24%|██▎       | 23633/100000 [6:45:49<12:23:11,  1.71it/s]
Train steps ... :  24%|██▎       | 23634/100000 [6:45:50<12:24:10,  1.71it/s]
Train steps ... :  24%|██▎       | 23635/100000 [6:45:50<12:24:31,  1.71it/s]
Train steps ... :  24%|██▎       | 23636/100000 [6:45:51<12:23:51,  1.71it/s]
Train steps ... :  24%|██▎       | 23637/100000 [6:45:51<12:24:28,  1.71it/s]
Train steps ... :  24%|██▎       | 23638/100000 [6:45:52<12:23:41,  1.71it/s]
Train steps ... :  24%|██▎       | 23639/100000 [6:45:53<12:24:24,  1.71it/s]
Train steps ... :  24%|██▎       | 23640/100000 [6:45:53<12:24:50,  1.71it/s]
Train steps ... :  24%|██▎       | 23641/100000 [6:45:54<12:23:57,  1.71it/s]
Train steps ... :  24%|██▎       | 23642/100000 [6:45:54<12:24:48,  1.71it/s]
Train steps ... :  24%|██▎       | 23643/100000 [6:45:55<12:24:00,  1.71it/s]
Train steps ... :  24%|██▎       | 23644/100000 [6:45:55<12:24:33,  1.71it/s]
Train steps ... :  24%|██▎       | 23645/100000 [6:45:56<12:24:17,  1.71it/s]
Train steps ... :  24%|██▎       | 23646/100000 [6:45:57<12:24:02,  1.71it/s]
Train steps ... :  24%|██▎       | 23647/100000 [6:45:57<12:23:05,  1.71it/s]
Train steps ... :  24%|██▎       | 23648/100000 [6:45:58<12:23:04,  1.71it/s]
Train steps ... :  24%|██▎       | 23649/100000 [6:45:58<12:22:46,  1.71it/s]
Train steps ... :  24%|██▎       | 23650/100000 [6:45:59<12:23:22,  1.71it/s]Step... (23650 / 100000 | Loss: 1.0035696029663086, Learning Rate: 7.673366834170854e-05)
+
                                                                             
Step... (23650 / 100000 | Loss: 1.0787068605422974, Learning Rate: 7.673366834170854e-05)
+
Train steps ... :  24%|██▎       | 23650/100000 [6:45:59<12:23:22,  1.71it/s]
Train steps ... :  24%|██▎       | 23651/100000 [6:46:00<12:22:57,  1.71it/s]
Train steps ... :  24%|██▎       | 23652/100000 [6:46:00<12:22:41,  1.71it/s]
Train steps ... :  24%|██▎       | 23653/100000 [6:46:01<12:23:52,  1.71it/s]
Train steps ... :  24%|██▎       | 23654/100000 [6:46:01<12:23:13,  1.71it/s]
Train steps ... :  24%|██▎       | 23655/100000 [6:46:02<12:22:58,  1.71it/s]
Train steps ... :  24%|██▎       | 23656/100000 [6:46:03<12:23:01,  1.71it/s]
Train steps ... :  24%|██▎       | 23657/100000 [6:46:03<12:23:09,  1.71it/s]
Train steps ... :  24%|██▎       | 23658/100000 [6:46:04<12:22:28,  1.71it/s]
Train steps ... :  24%|██▎       | 23659/100000 [6:46:04<12:22:39,  1.71it/s]
Train steps ... :  24%|██▎       | 23660/100000 [6:46:05<12:22:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23661/100000 [6:46:05<12:22:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23662/100000 [6:46:06<12:22:43,  1.71it/s]
Train steps ... :  24%|██▎       | 23663/100000 [6:46:07<12:22:51,  1.71it/s]
Train steps ... :  24%|██▎       | 23664/100000 [6:46:07<12:23:11,  1.71it/s]
Train steps ... :  24%|██▎       | 23665/100000 [6:46:08<12:23:08,  1.71it/s]
Train steps ... :  24%|██▎       | 23666/100000 [6:46:08<12:24:08,  1.71it/s]
Train steps ... :  24%|██▎       | 23667/100000 [6:46:09<12:24:39,  1.71it/s]
Train steps ... :  24%|██▎       | 23668/100000 [6:46:10<12:23:40,  1.71it/s]
Train steps ... :  24%|██▎       | 23669/100000 [6:46:10<12:23:37,  1.71it/s]
Train steps ... :  24%|██▎       | 23670/100000 [6:46:11<12:22:58,  1.71it/s]
Train steps ... :  24%|██▎       | 23671/100000 [6:46:11<12:22:13,  1.71it/s]
Train steps ... :  24%|██▎       | 23672/100000 [6:46:12<12:23:37,  1.71it/s]
Train steps ... :  24%|██▎       | 23673/100000 [6:46:12<12:24:09,  1.71it/s]
Train steps ... :  24%|██▎       | 23674/100000 [6:46:13<12:23:04,  1.71it/s]
Train steps ... :  24%|██▎       | 23675/100000 [6:46:14<12:23:56,  1.71it/s]Step... (23675 / 100000 | Loss: 0.7675723433494568, Learning Rate: 7.670854271356785e-05)
+
                                                                             
Step... (23675 / 100000 | Loss: 0.9836010932922363, Learning Rate: 7.670854271356785e-05)
+
Train steps ... :  24%|██▎       | 23675/100000 [6:46:14<12:23:56,  1.71it/s]
Train steps ... :  24%|██▎       | 23676/100000 [6:46:14<12:23:42,  1.71it/s]
Train steps ... :  24%|██▎       | 23677/100000 [6:46:15<12:23:31,  1.71it/s]
Train steps ... :  24%|██▎       | 23678/100000 [6:46:15<12:22:50,  1.71it/s]
Train steps ... :  24%|██▎       | 23679/100000 [6:46:16<12:22:49,  1.71it/s]
Train steps ... :  24%|██▎       | 23680/100000 [6:46:17<12:22:39,  1.71it/s]
Train steps ... :  24%|██▎       | 23681/100000 [6:46:17<12:22:34,  1.71it/s]
Train steps ... :  24%|██▎       | 23682/100000 [6:46:18<12:23:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23683/100000 [6:46:18<12:23:03,  1.71it/s]
Train steps ... :  24%|██▎       | 23684/100000 [6:46:19<12:23:18,  1.71it/s]
Train steps ... :  24%|██▎       | 23685/100000 [6:46:19<12:23:08,  1.71it/s]
Train steps ... :  24%|██▎       | 23686/100000 [6:46:20<12:22:48,  1.71it/s]
Train steps ... :  24%|██▎       | 23687/100000 [6:46:21<12:23:05,  1.71it/s]
Train steps ... :  24%|██▎       | 23688/100000 [6:46:21<12:22:48,  1.71it/s]
Train steps ... :  24%|██▎       | 23689/100000 [6:46:22<12:23:09,  1.71it/s]
Train steps ... :  24%|██▎       | 23690/100000 [6:46:22<12:23:29,  1.71it/s]
Train steps ... :  24%|██▎       | 23691/100000 [6:46:23<12:24:24,  1.71it/s]
Train steps ... :  24%|██▎       | 23692/100000 [6:46:24<12:23:43,  1.71it/s]
Train steps ... :  24%|██▎       | 23693/100000 [6:46:24<12:23:11,  1.71it/s]
Train steps ... :  24%|██▎       | 23694/100000 [6:46:25<12:23:04,  1.71it/s]
Train steps ... :  24%|██▎       | 23695/100000 [6:46:25<12:23:43,  1.71it/s]
Train steps ... :  24%|██▎       | 23696/100000 [6:46:26<12:23:42,  1.71it/s]
Train steps ... :  24%|██▎       | 23697/100000 [6:46:26<12:24:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23698/100000 [6:46:27<12:24:08,  1.71it/s]
Train steps ... :  24%|██▎       | 23699/100000 [6:46:28<12:23:20,  1.71it/s]
Train steps ... :  24%|██▎       | 23700/100000 [6:46:28<12:22:55,  1.71it/s]Step... (23700 / 100000 | Loss: 0.901107907295227, Learning Rate: 7.668341708542713e-05)
+
                                                                             
Step... (23700 / 100000 | Loss: 0.8108240962028503, Learning Rate: 7.668341708542713e-05)
+
Train steps ... :  24%|██▎       | 23700/100000 [6:46:29<12:22:55,  1.71it/s]
Train steps ... :  24%|██▎       | 23701/100000 [6:46:29<12:24:09,  1.71it/s]
Train steps ... :  24%|██▎       | 23702/100000 [6:46:29<12:23:08,  1.71it/s]
Train steps ... :  24%|██▎       | 23703/100000 [6:46:30<12:23:32,  1.71it/s]
Train steps ... :  24%|██▎       | 23704/100000 [6:46:31<12:23:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23705/100000 [6:46:31<12:23:10,  1.71it/s]
Train steps ... :  24%|██▎       | 23706/100000 [6:46:32<12:22:55,  1.71it/s]
Train steps ... :  24%|██▎       | 23707/100000 [6:46:32<12:23:27,  1.71it/s]
Train steps ... :  24%|██▎       | 23708/100000 [6:46:33<12:22:37,  1.71it/s]
Train steps ... :  24%|██▎       | 23709/100000 [6:46:33<12:22:52,  1.71it/s]
Train steps ... :  24%|██▎       | 23710/100000 [6:46:34<12:23:36,  1.71it/s]
Train steps ... :  24%|██▎       | 23711/100000 [6:46:35<12:23:04,  1.71it/s]
Train steps ... :  24%|██▎       | 23712/100000 [6:46:35<12:23:27,  1.71it/s]
Train steps ... :  24%|██▎       | 23713/100000 [6:46:36<12:23:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23714/100000 [6:46:36<12:22:49,  1.71it/s]
Train steps ... :  24%|██▎       | 23715/100000 [6:46:37<12:22:34,  1.71it/s]
Train steps ... :  24%|██▎       | 23716/100000 [6:46:38<12:22:38,  1.71it/s]
Train steps ... :  24%|██▎       | 23717/100000 [6:46:38<12:22:33,  1.71it/s]
Train steps ... :  24%|██▎       | 23718/100000 [6:46:39<12:22:32,  1.71it/s]
Train steps ... :  24%|██▎       | 23719/100000 [6:46:39<12:22:00,  1.71it/s]
Train steps ... :  24%|██▎       | 23720/100000 [6:46:40<12:22:10,  1.71it/s]
Train steps ... :  24%|██▎       | 23721/100000 [6:46:40<12:22:08,  1.71it/s]
Train steps ... :  24%|██▎       | 23722/100000 [6:46:41<12:23:06,  1.71it/s]
Train steps ... :  24%|██▎       | 23723/100000 [6:46:42<12:23:35,  1.71it/s]
Train steps ... :  24%|██▎       | 23724/100000 [6:46:42<12:24:24,  1.71it/s]
Train steps ... :  24%|██▎       | 23725/100000 [6:46:43<12:23:27,  1.71it/s]Step... (23725 / 100000 | Loss: 1.0808799266815186, Learning Rate: 7.665829145728643e-05)
+
                                                                             
Step... (23725 / 100000 | Loss: 0.6897779107093811, Learning Rate: 7.665829145728643e-05)
+
Train steps ... :  24%|██▎       | 23725/100000 [6:46:43<12:23:27,  1.71it/s]
Train steps ... :  24%|██▎       | 23726/100000 [6:46:43<12:23:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23727/100000 [6:46:44<12:23:57,  1.71it/s]
Train steps ... :  24%|██▎       | 23728/100000 [6:46:45<12:23:03,  1.71it/s]
Train steps ... :  24%|██▎       | 23729/100000 [6:46:45<12:22:52,  1.71it/s]
Train steps ... :  24%|██▎       | 23730/100000 [6:46:46<12:23:13,  1.71it/s]
Train steps ... :  24%|██▎       | 23731/100000 [6:46:46<12:23:04,  1.71it/s]
Train steps ... :  24%|██▎       | 23732/100000 [6:46:47<12:23:36,  1.71it/s]
Train steps ... :  24%|██▎       | 23733/100000 [6:46:48<12:23:21,  1.71it/s]
Train steps ... :  24%|██▎       | 23734/100000 [6:46:48<12:23:28,  1.71it/s]
Train steps ... :  24%|██▎       | 23735/100000 [6:46:49<12:23:39,  1.71it/s]
Train steps ... :  24%|██▎       | 23736/100000 [6:46:49<12:23:00,  1.71it/s]
Train steps ... :  24%|██▎       | 23737/100000 [6:46:50<12:23:03,  1.71it/s]
Train steps ... :  24%|██▎       | 23738/100000 [6:46:50<12:22:30,  1.71it/s]
Train steps ... :  24%|██▎       | 23739/100000 [6:46:51<12:22:40,  1.71it/s]
Train steps ... :  24%|██▎       | 23740/100000 [6:46:52<12:23:07,  1.71it/s]
Train steps ... :  24%|██▎       | 23741/100000 [6:46:52<12:23:25,  1.71it/s]
Train steps ... :  24%|██▎       | 23742/100000 [6:46:53<12:22:41,  1.71it/s]
Train steps ... :  24%|██▎       | 23743/100000 [6:46:53<12:22:26,  1.71it/s]
Train steps ... :  24%|██▎       | 23744/100000 [6:46:54<12:22:55,  1.71it/s]
Train steps ... :  24%|██▎       | 23745/100000 [6:46:55<12:22:52,  1.71it/s]
Train steps ... :  24%|██▎       | 23746/100000 [6:46:55<12:23:33,  1.71it/s]
Train steps ... :  24%|██▎       | 23747/100000 [6:46:56<12:23:02,  1.71it/s]
Train steps ... :  24%|██▎       | 23748/100000 [6:46:56<12:23:22,  1.71it/s]
Train steps ... :  24%|██▎       | 23749/100000 [6:46:57<12:23:00,  1.71it/s]
Train steps ... :  24%|██▍       | 23750/100000 [6:46:57<12:22:50,  1.71it/s]Step... (23750 / 100000 | Loss: 0.754440426826477, Learning Rate: 7.663316582914574e-05)
+
                                                                             
Step... (23750 / 100000 | Loss: 1.6104626655578613, Learning Rate: 7.663316582914574e-05)
+
Train steps ... :  24%|██▍       | 23750/100000 [6:46:58<12:22:50,  1.71it/s]
Train steps ... :  24%|██▍       | 23751/100000 [6:46:58<12:23:32,  1.71it/s]
Train steps ... :  24%|██▍       | 23752/100000 [6:46:59<12:23:29,  1.71it/s]
Train steps ... :  24%|██▍       | 23753/100000 [6:46:59<12:22:41,  1.71it/s]
Train steps ... :  24%|██▍       | 23754/100000 [6:47:00<12:24:00,  1.71it/s]
Train steps ... :  24%|██▍       | 23755/100000 [6:47:00<12:23:59,  1.71it/s]
Train steps ... :  24%|██▍       | 23756/100000 [6:47:01<12:23:20,  1.71it/s]
Train steps ... :  24%|██▍       | 23757/100000 [6:47:02<12:22:33,  1.71it/s]
Train steps ... :  24%|██▍       | 23758/100000 [6:47:02<12:22:11,  1.71it/s]
Train steps ... :  24%|██▍       | 23759/100000 [6:47:03<12:21:50,  1.71it/s]
Train steps ... :  24%|██▍       | 23760/100000 [6:47:03<12:22:39,  1.71it/s]
Train steps ... :  24%|██▍       | 23761/100000 [6:47:04<12:23:11,  1.71it/s]
Train steps ... :  24%|██▍       | 23762/100000 [6:47:04<12:22:27,  1.71it/s]
Train steps ... :  24%|██▍       | 23763/100000 [6:47:05<12:22:12,  1.71it/s]
Train steps ... :  24%|██▍       | 23764/100000 [6:47:06<12:22:17,  1.71it/s]
Train steps ... :  24%|██▍       | 23765/100000 [6:47:06<12:23:16,  1.71it/s]
Train steps ... :  24%|██▍       | 23766/100000 [6:47:07<12:21:53,  1.71it/s]
Train steps ... :  24%|██▍       | 23767/100000 [6:47:07<12:22:43,  1.71it/s]
Train steps ... :  24%|██▍       | 23768/100000 [6:47:08<12:24:03,  1.71it/s]
Train steps ... :  24%|██▍       | 23769/100000 [6:47:09<12:23:57,  1.71it/s]
Train steps ... :  24%|██▍       | 23770/100000 [6:47:09<12:22:17,  1.71it/s]
Train steps ... :  24%|██▍       | 23771/100000 [6:47:10<12:22:51,  1.71it/s]
Train steps ... :  24%|██▍       | 23772/100000 [6:47:10<12:22:57,  1.71it/s]
Train steps ... :  24%|██▍       | 23773/100000 [6:47:11<12:23:10,  1.71it/s]
Train steps ... :  24%|██▍       | 23774/100000 [6:47:11<12:22:33,  1.71it/s]
Train steps ... :  24%|██▍       | 23775/100000 [6:47:12<12:23:00,  1.71it/s]Step... (23775 / 100000 | Loss: 1.2133290767669678, Learning Rate: 7.660804020100502e-05)
+
                                                                             
Step... (23775 / 100000 | Loss: 0.736013650894165, Learning Rate: 7.660804020100502e-05)
+
Train steps ... :  24%|██▍       | 23775/100000 [6:47:12<12:23:00,  1.71it/s]
Train steps ... :  24%|██▍       | 23776/100000 [6:47:13<12:23:39,  1.71it/s]
Train steps ... :  24%|██▍       | 23777/100000 [6:47:13<12:23:12,  1.71it/s]
Train steps ... :  24%|██▍       | 23778/100000 [6:47:14<12:22:54,  1.71it/s]
Train steps ... :  24%|██▍       | 23779/100000 [6:47:14<12:21:55,  1.71it/s]
Train steps ... :  24%|██▍       | 23780/100000 [6:47:15<12:21:43,  1.71it/s]
Train steps ... :  24%|██▍       | 23781/100000 [6:47:16<12:21:10,  1.71it/s]
Train steps ... :  24%|██▍       | 23782/100000 [6:47:16<12:21:23,  1.71it/s]
Train steps ... :  24%|██▍       | 23783/100000 [6:47:17<12:21:58,  1.71it/s]
Train steps ... :  24%|██▍       | 23784/100000 [6:47:17<12:22:13,  1.71it/s]
Train steps ... :  24%|██▍       | 23785/100000 [6:47:18<12:23:37,  1.71it/s]
Train steps ... :  24%|██▍       | 23786/100000 [6:47:18<12:24:15,  1.71it/s]
Train steps ... :  24%|██▍       | 23787/100000 [6:47:19<12:23:30,  1.71it/s]
Train steps ... :  24%|██▍       | 23788/100000 [6:47:20<12:22:38,  1.71it/s]
Train steps ... :  24%|██▍       | 23789/100000 [6:47:20<12:21:56,  1.71it/s]
Train steps ... :  24%|██▍       | 23790/100000 [6:47:21<12:21:55,  1.71it/s]
Train steps ... :  24%|██▍       | 23791/100000 [6:47:21<12:22:14,  1.71it/s]
Train steps ... :  24%|██▍       | 23792/100000 [6:47:22<12:22:30,  1.71it/s]
Train steps ... :  24%|██▍       | 23793/100000 [6:47:23<12:22:35,  1.71it/s]
Train steps ... :  24%|██▍       | 23794/100000 [6:47:23<12:22:22,  1.71it/s]
Train steps ... :  24%|██▍       | 23795/100000 [6:47:24<12:23:10,  1.71it/s]
Train steps ... :  24%|██▍       | 23796/100000 [6:47:24<12:22:42,  1.71it/s]
Train steps ... :  24%|██▍       | 23797/100000 [6:47:25<12:22:09,  1.71it/s]
Train steps ... :  24%|██▍       | 23798/100000 [6:47:26<12:21:30,  1.71it/s]
Train steps ... :  24%|██▍       | 23799/100000 [6:47:26<12:22:39,  1.71it/s]
Train steps ... :  24%|██▍       | 23800/100000 [6:47:27<12:23:24,  1.71it/s]Step... (23800 / 100000 | Loss: 1.0207442045211792, Learning Rate: 7.658291457286433e-05)
+
                                                                             
Step... (23800 / 100000 | Loss: 1.0081838369369507, Learning Rate: 7.658291457286433e-05)
+
Train steps ... :  24%|██▍       | 23800/100000 [6:47:27<12:23:24,  1.71it/s]
Train steps ... :  24%|██▍       | 23801/100000 [6:47:27<12:23:37,  1.71it/s]
Train steps ... :  24%|██▍       | 23802/100000 [6:47:28<12:23:46,  1.71it/s]
Train steps ... :  24%|██▍       | 23803/100000 [6:47:28<12:23:00,  1.71it/s]
Train steps ... :  24%|██▍       | 23804/100000 [6:47:29<12:22:32,  1.71it/s]
Train steps ... :  24%|██▍       | 23805/100000 [6:47:30<12:23:04,  1.71it/s]
Train steps ... :  24%|██▍       | 23806/100000 [6:47:30<12:22:10,  1.71it/s]
Train steps ... :  24%|██▍       | 23807/100000 [6:47:31<12:22:19,  1.71it/s]
Train steps ... :  24%|██▍       | 23808/100000 [6:47:31<12:21:23,  1.71it/s]
Train steps ... :  24%|██▍       | 23809/100000 [6:47:32<12:22:04,  1.71it/s]
Train steps ... :  24%|██▍       | 23810/100000 [6:47:33<12:21:59,  1.71it/s]
Train steps ... :  24%|██▍       | 23811/100000 [6:47:33<12:21:25,  1.71it/s]
Train steps ... :  24%|██▍       | 23812/100000 [6:47:34<12:21:45,  1.71it/s]
Train steps ... :  24%|██▍       | 23813/100000 [6:47:34<12:21:53,  1.71it/s]
Train steps ... :  24%|██▍       | 23814/100000 [6:47:35<12:21:48,  1.71it/s]
Train steps ... :  24%|██▍       | 23815/100000 [6:47:35<12:21:28,  1.71it/s]
Train steps ... :  24%|██▍       | 23816/100000 [6:47:36<12:21:56,  1.71it/s]
Train steps ... :  24%|██▍       | 23817/100000 [6:47:37<12:23:08,  1.71it/s]
Train steps ... :  24%|██▍       | 23818/100000 [6:47:37<12:23:33,  1.71it/s]
Train steps ... :  24%|██▍       | 23819/100000 [6:47:38<12:23:02,  1.71it/s]
Train steps ... :  24%|██▍       | 23820/100000 [6:47:38<12:22:07,  1.71it/s]
Train steps ... :  24%|██▍       | 23821/100000 [6:47:39<12:21:47,  1.71it/s]
Train steps ... :  24%|██▍       | 23822/100000 [6:47:40<12:22:22,  1.71it/s]
Train steps ... :  24%|██▍       | 23823/100000 [6:47:40<12:22:48,  1.71it/s]
Train steps ... :  24%|██▍       | 23824/100000 [6:47:41<12:22:05,  1.71it/s]
Train steps ... :  24%|██▍       | 23825/100000 [6:47:41<12:21:23,  1.71it/s]Step... (23825 / 100000 | Loss: 0.9657829999923706, Learning Rate: 7.655778894472362e-05)
+
                                                                             
Step... (23825 / 100000 | Loss: 1.362546443939209, Learning Rate: 7.655778894472362e-05)
+
Train steps ... :  24%|██▍       | 23825/100000 [6:47:42<12:21:23,  1.71it/s]
Train steps ... :  24%|██▍       | 23826/100000 [6:47:42<12:22:43,  1.71it/s]
Train steps ... :  24%|██▍       | 23827/100000 [6:47:42<12:22:42,  1.71it/s]
Train steps ... :  24%|██▍       | 23828/100000 [6:47:43<12:22:06,  1.71it/s]
Train steps ... :  24%|██▍       | 23829/100000 [6:47:44<12:22:30,  1.71it/s]
Train steps ... :  24%|██▍       | 23830/100000 [6:47:44<12:22:03,  1.71it/s]
Train steps ... :  24%|██▍       | 23831/100000 [6:47:45<12:21:43,  1.71it/s]
Train steps ... :  24%|██▍       | 23832/100000 [6:47:45<12:22:31,  1.71it/s]
Train steps ... :  24%|██▍       | 23833/100000 [6:47:46<12:24:55,  1.70it/s]
Train steps ... :  24%|██▍       | 23834/100000 [6:47:47<12:22:20,  1.71it/s]
Train steps ... :  24%|██▍       | 23835/100000 [6:47:47<12:22:22,  1.71it/s]
Train steps ... :  24%|██▍       | 23836/100000 [6:47:48<12:24:39,  1.70it/s]
Train steps ... :  24%|██▍       | 23837/100000 [6:47:48<12:25:42,  1.70it/s]
Train steps ... :  24%|██▍       | 23838/100000 [6:47:49<12:24:59,  1.70it/s]
Train steps ... :  24%|██▍       | 23839/100000 [6:47:49<12:24:01,  1.71it/s]
Train steps ... :  24%|██▍       | 23840/100000 [6:47:50<12:24:42,  1.70it/s]
Train steps ... :  24%|██▍       | 23841/100000 [6:47:51<12:24:05,  1.71it/s]
Train steps ... :  24%|██▍       | 23842/100000 [6:47:51<12:24:22,  1.71it/s]
Train steps ... :  24%|██▍       | 23843/100000 [6:47:52<12:23:37,  1.71it/s]
Train steps ... :  24%|██▍       | 23844/100000 [6:47:52<12:23:11,  1.71it/s]
Train steps ... :  24%|██▍       | 23845/100000 [6:47:53<12:22:30,  1.71it/s]
Train steps ... :  24%|██▍       | 23846/100000 [6:47:54<12:22:52,  1.71it/s]
Train steps ... :  24%|██▍       | 23847/100000 [6:47:54<12:23:02,  1.71it/s]
Train steps ... :  24%|██▍       | 23848/100000 [6:47:55<12:23:00,  1.71it/s]
Train steps ... :  24%|██▍       | 23849/100000 [6:47:55<12:22:13,  1.71it/s]
Train steps ... :  24%|██▍       | 23850/100000 [6:47:56<12:21:40,  1.71it/s]Step... (23850 / 100000 | Loss: 0.9226722717285156, Learning Rate: 7.653266331658291e-05)
+
                                                                             
Step... (23850 / 100000 | Loss: 0.816177487373352, Learning Rate: 7.653266331658291e-05)
+
Train steps ... :  24%|██▍       | 23850/100000 [6:47:56<12:21:40,  1.71it/s]
Train steps ... :  24%|██▍       | 23851/100000 [6:47:57<12:21:43,  1.71it/s]
Train steps ... :  24%|██▍       | 23852/100000 [6:47:57<12:21:53,  1.71it/s]
Train steps ... :  24%|██▍       | 23853/100000 [6:47:58<12:21:05,  1.71it/s]
Train steps ... :  24%|██▍       | 23854/100000 [6:47:58<12:21:31,  1.71it/s]
Train steps ... :  24%|██▍       | 23855/100000 [6:47:59<12:21:18,  1.71it/s]
Train steps ... :  24%|██▍       | 23856/100000 [6:47:59<12:22:45,  1.71it/s]
Train steps ... :  24%|██▍       | 23857/100000 [6:48:00<12:21:40,  1.71it/s]
Train steps ... :  24%|██▍       | 23858/100000 [6:48:01<12:21:58,  1.71it/s]
Train steps ... :  24%|██▍       | 23859/100000 [6:48:01<12:21:47,  1.71it/s]
Train steps ... :  24%|██▍       | 23860/100000 [6:48:02<12:22:27,  1.71it/s]
Train steps ... :  24%|██▍       | 23861/100000 [6:48:02<12:22:51,  1.71it/s]
Train steps ... :  24%|██▍       | 23862/100000 [6:48:03<12:23:05,  1.71it/s]
Train steps ... :  24%|██▍       | 23863/100000 [6:48:04<12:22:10,  1.71it/s]
Train steps ... :  24%|██▍       | 23864/100000 [6:48:04<12:23:32,  1.71it/s]
Train steps ... :  24%|██▍       | 23865/100000 [6:48:05<12:22:47,  1.71it/s]
Train steps ... :  24%|██▍       | 23866/100000 [6:48:05<12:22:10,  1.71it/s]
Train steps ... :  24%|██▍       | 23867/100000 [6:48:06<12:22:26,  1.71it/s]
Train steps ... :  24%|██▍       | 23868/100000 [6:48:06<12:21:48,  1.71it/s]
Train steps ... :  24%|██▍       | 23869/100000 [6:48:07<12:22:00,  1.71it/s]
Train steps ... :  24%|██▍       | 23870/100000 [6:48:08<12:21:56,  1.71it/s]
Train steps ... :  24%|██▍       | 23871/100000 [6:48:08<12:21:09,  1.71it/s]
Train steps ... :  24%|██▍       | 23872/100000 [6:48:09<12:21:28,  1.71it/s]
Train steps ... :  24%|██▍       | 23873/100000 [6:48:09<12:21:04,  1.71it/s]
Train steps ... :  24%|██▍       | 23874/100000 [6:48:10<12:21:30,  1.71it/s]
Train steps ... :  24%|██▍       | 23875/100000 [6:48:11<12:20:57,  1.71it/s]Step... (23875 / 100000 | Loss: 0.9671965837478638, Learning Rate: 7.650753768844221e-05)
+
                                                                             
Step... (23875 / 100000 | Loss: 1.5341626405715942, Learning Rate: 7.650753768844221e-05)
+
Train steps ... :  24%|██▍       | 23875/100000 [6:48:11<12:20:57,  1.71it/s]
Train steps ... :  24%|██▍       | 23876/100000 [6:48:11<12:21:07,  1.71it/s]
Train steps ... :  24%|██▍       | 23877/100000 [6:48:12<12:21:14,  1.71it/s]
Train steps ... :  24%|██▍       | 23878/100000 [6:48:12<12:21:00,  1.71it/s]
Train steps ... :  24%|██▍       | 23879/100000 [6:48:13<12:21:20,  1.71it/s]
Train steps ... :  24%|██▍       | 23880/100000 [6:48:13<12:21:21,  1.71it/s]
Train steps ... :  24%|██▍       | 23881/100000 [6:48:14<12:21:06,  1.71it/s]
Train steps ... :  24%|██▍       | 23882/100000 [6:48:15<12:22:03,  1.71it/s]
Train steps ... :  24%|██▍       | 23883/100000 [6:48:15<12:23:29,  1.71it/s]
Train steps ... :  24%|██▍       | 23884/100000 [6:48:16<12:21:30,  1.71it/s]
Train steps ... :  24%|██▍       | 23885/100000 [6:48:16<12:24:03,  1.70it/s]
Train steps ... :  24%|██▍       | 23886/100000 [6:48:17<12:21:50,  1.71it/s]
Train steps ... :  24%|██▍       | 23887/100000 [6:48:18<12:22:38,  1.71it/s]
Train steps ... :  24%|██▍       | 23888/100000 [6:48:18<12:23:25,  1.71it/s]
Train steps ... :  24%|██▍       | 23889/100000 [6:48:19<12:21:46,  1.71it/s]
Train steps ... :  24%|██▍       | 23890/100000 [6:48:19<12:22:49,  1.71it/s]
Train steps ... :  24%|██▍       | 23891/100000 [6:48:20<12:22:16,  1.71it/s]
Train steps ... :  24%|██▍       | 23892/100000 [6:48:20<12:21:58,  1.71it/s]
Train steps ... :  24%|██▍       | 23893/100000 [6:48:21<12:21:59,  1.71it/s]
Train steps ... :  24%|██▍       | 23894/100000 [6:48:22<12:21:33,  1.71it/s]
Train steps ... :  24%|██▍       | 23895/100000 [6:48:22<12:20:48,  1.71it/s]
Train steps ... :  24%|██▍       | 23896/100000 [6:48:23<12:20:23,  1.71it/s]
Train steps ... :  24%|██▍       | 23897/100000 [6:48:23<12:21:03,  1.71it/s]
Train steps ... :  24%|██▍       | 23898/100000 [6:48:24<12:21:00,  1.71it/s]
Train steps ... :  24%|██▍       | 23899/100000 [6:48:25<12:22:16,  1.71it/s]
Train steps ... :  24%|██▍       | 23900/100000 [6:48:25<12:21:46,  1.71it/s]Step... (23900 / 100000 | Loss: 1.1410279273986816, Learning Rate: 7.64824120603015e-05)
+
                                                                             
Step... (23900 / 100000 | Loss: 1.4746557474136353, Learning Rate: 7.64824120603015e-05)
+
Train steps ... :  24%|██▍       | 23900/100000 [6:48:25<12:21:46,  1.71it/s]
Train steps ... :  24%|██▍       | 23901/100000 [6:48:26<12:21:50,  1.71it/s]
Train steps ... :  24%|██▍       | 23902/100000 [6:48:26<12:22:59,  1.71it/s]
Train steps ... :  24%|██▍       | 23903/100000 [6:48:27<12:21:26,  1.71it/s]
Train steps ... :  24%|██▍       | 23904/100000 [6:48:28<12:21:27,  1.71it/s]
Train steps ... :  24%|██▍       | 23905/100000 [6:48:28<12:22:47,  1.71it/s]
Train steps ... :  24%|██▍       | 23906/100000 [6:48:29<12:23:55,  1.70it/s]
Train steps ... :  24%|██▍       | 23907/100000 [6:48:29<12:23:13,  1.71it/s]
Train steps ... :  24%|██▍       | 23908/100000 [6:48:30<12:22:46,  1.71it/s]
Train steps ... :  24%|██▍       | 23909/100000 [6:48:30<12:22:03,  1.71it/s]
Train steps ... :  24%|██▍       | 23910/100000 [6:48:31<12:23:07,  1.71it/s]
Train steps ... :  24%|██▍       | 23911/100000 [6:48:32<12:22:43,  1.71it/s]
Train steps ... :  24%|██▍       | 23912/100000 [6:48:32<12:22:37,  1.71it/s]
Train steps ... :  24%|██▍       | 23913/100000 [6:48:33<12:22:07,  1.71it/s]
Train steps ... :  24%|██▍       | 23914/100000 [6:48:33<12:22:34,  1.71it/s]
Train steps ... :  24%|██▍       | 23915/100000 [6:48:34<12:22:27,  1.71it/s]
Train steps ... :  24%|██▍       | 23916/100000 [6:48:35<12:22:06,  1.71it/s]
Train steps ... :  24%|██▍       | 23917/100000 [6:48:35<12:21:05,  1.71it/s]
Train steps ... :  24%|██▍       | 23918/100000 [6:48:36<12:21:41,  1.71it/s]
Train steps ... :  24%|██▍       | 23919/100000 [6:48:36<12:20:35,  1.71it/s]
Train steps ... :  24%|██▍       | 23920/100000 [6:48:37<12:21:46,  1.71it/s]
Train steps ... :  24%|██▍       | 23921/100000 [6:48:37<12:21:32,  1.71it/s]
Train steps ... :  24%|██▍       | 23922/100000 [6:48:38<12:22:48,  1.71it/s]
Train steps ... :  24%|██▍       | 23923/100000 [6:48:39<12:22:20,  1.71it/s]
Train steps ... :  24%|██▍       | 23924/100000 [6:48:39<12:21:55,  1.71it/s]
Train steps ... :  24%|██▍       | 23925/100000 [6:48:40<12:23:59,  1.70it/s]Step... (23925 / 100000 | Loss: 1.0005682706832886, Learning Rate: 7.645728643216082e-05)
+
                                                                             
Step... (23925 / 100000 | Loss: 1.0606906414031982, Learning Rate: 7.645728643216082e-05)
+
Train steps ... :  24%|██▍       | 23925/100000 [6:48:40<12:23:59,  1.70it/s]
Train steps ... :  24%|██▍       | 23926/100000 [6:48:40<12:23:48,  1.70it/s]
Train steps ... :  24%|██▍       | 23927/100000 [6:48:41<12:24:23,  1.70it/s]
Train steps ... :  24%|██▍       | 23928/100000 [6:48:42<12:25:07,  1.70it/s]
Train steps ... :  24%|██▍       | 23929/100000 [6:48:42<12:23:54,  1.70it/s]
Train steps ... :  24%|██▍       | 23930/100000 [6:48:43<12:23:00,  1.71it/s]
Train steps ... :  24%|██▍       | 23931/100000 [6:48:43<12:22:28,  1.71it/s]
Train steps ... :  24%|██▍       | 23932/100000 [6:48:44<12:21:35,  1.71it/s]
Train steps ... :  24%|██▍       | 23933/100000 [6:48:44<12:22:15,  1.71it/s]
Train steps ... :  24%|██▍       | 23934/100000 [6:48:45<12:22:42,  1.71it/s]
Train steps ... :  24%|██��       | 23935/100000 [6:48:46<12:22:19,  1.71it/s]
Train steps ... :  24%|██▍       | 23936/100000 [6:48:46<12:22:56,  1.71it/s]
Train steps ... :  24%|██▍       | 23937/100000 [6:48:47<12:23:10,  1.71it/s]
Train steps ... :  24%|██▍       | 23938/100000 [6:48:47<12:22:40,  1.71it/s]
Train steps ... :  24%|██▍       | 23939/100000 [6:48:48<12:21:06,  1.71it/s]
Train steps ... :  24%|██▍       | 23940/100000 [6:48:49<12:24:27,  1.70it/s]
Train steps ... :  24%|██▍       | 23941/100000 [6:48:49<12:23:50,  1.70it/s]
Train steps ... :  24%|██▍       | 23942/100000 [6:48:50<12:25:34,  1.70it/s]
Train steps ... :  24%|██▍       | 23943/100000 [6:48:50<12:23:57,  1.70it/s]
Train steps ... :  24%|██▍       | 23944/100000 [6:48:51<12:23:07,  1.71it/s]
Train steps ... :  24%|██▍       | 23945/100000 [6:48:52<12:24:21,  1.70it/s]
Train steps ... :  24%|██▍       | 23946/100000 [6:48:52<12:23:47,  1.70it/s]
Train steps ... :  24%|██▍       | 23947/100000 [6:48:53<12:22:14,  1.71it/s]
Train steps ... :  24%|██▍       | 23948/100000 [6:48:53<12:21:31,  1.71it/s]
Train steps ... :  24%|██▍       | 23949/100000 [6:48:54<12:20:41,  1.71it/s]
Train steps ... :  24%|██▍       | 23950/100000 [6:48:54<12:20:25,  1.71it/s]Step... (23950 / 100000 | Loss: 0.852142870426178, Learning Rate: 7.64321608040201e-05)
+
                                                                             
Step... (23950 / 100000 | Loss: 0.9663822650909424, Learning Rate: 7.64321608040201e-05)
+
Train steps ... :  24%|██▍       | 23950/100000 [6:48:55<12:20:25,  1.71it/s]
Train steps ... :  24%|██▍       | 23951/100000 [6:48:55<12:23:17,  1.71it/s]
Train steps ... :  24%|██▍       | 23952/100000 [6:48:56<12:21:39,  1.71it/s]
Train steps ... :  24%|██▍       | 23953/100000 [6:48:56<12:21:25,  1.71it/s]
Train steps ... :  24%|██▍       | 23954/100000 [6:48:57<12:22:40,  1.71it/s]
Train steps ... :  24%|██▍       | 23955/100000 [6:48:57<12:22:07,  1.71it/s]
Train steps ... :  24%|██▍       | 23956/100000 [6:48:58<12:21:16,  1.71it/s]
Train steps ... :  24%|██▍       | 23957/100000 [6:48:59<12:23:14,  1.71it/s]
Train steps ... :  24%|██▍       | 23958/100000 [6:48:59<12:23:07,  1.71it/s]
Train steps ... :  24%|██▍       | 23959/100000 [6:49:00<12:22:11,  1.71it/s]
Train steps ... :  24%|██▍       | 23960/100000 [6:49:00<12:22:05,  1.71it/s]
Train steps ... :  24%|██▍       | 23961/100000 [6:49:01<12:21:03,  1.71it/s]
Train steps ... :  24%|██▍       | 23962/100000 [6:49:01<12:20:58,  1.71it/s]
Train steps ... :  24%|██▍       | 23963/100000 [6:49:02<12:20:31,  1.71it/s]
Train steps ... :  24%|██▍       | 23964/100000 [6:49:03<12:21:24,  1.71it/s]
Train steps ... :  24%|██▍       | 23965/100000 [6:49:03<12:20:56,  1.71it/s]
Train steps ... :  24%|██▍       | 23966/100000 [6:49:04<12:20:49,  1.71it/s]
Train steps ... :  24%|██▍       | 23967/100000 [6:49:04<12:22:10,  1.71it/s]
Train steps ... :  24%|██▍       | 23968/100000 [6:49:05<12:22:13,  1.71it/s]
Train steps ... :  24%|██▍       | 23969/100000 [6:49:06<12:23:15,  1.70it/s]
Train steps ... :  24%|██▍       | 23970/100000 [6:49:06<12:22:29,  1.71it/s]
Train steps ... :  24%|██▍       | 23971/100000 [6:49:07<12:22:15,  1.71it/s]
Train steps ... :  24%|██▍       | 23972/100000 [6:49:07<12:23:17,  1.70it/s]
Train steps ... :  24%|██▍       | 23973/100000 [6:49:08<12:21:51,  1.71it/s]
Train steps ... :  24%|██▍       | 23974/100000 [6:49:09<12:21:48,  1.71it/s]
Train steps ... :  24%|██▍       | 23975/100000 [6:49:09<12:21:37,  1.71it/s]Step... (23975 / 100000 | Loss: 1.158046841621399, Learning Rate: 7.640703517587941e-05)
+
                                                                             
Step... (23975 / 100000 | Loss: 0.9821901321411133, Learning Rate: 7.640703517587941e-05)
+
Train steps ... :  24%|██▍       | 23975/100000 [6:49:09<12:21:37,  1.71it/s]
Train steps ... :  24%|██▍       | 23976/100000 [6:49:10<12:21:12,  1.71it/s]
Train steps ... :  24%|██▍       | 23977/100000 [6:49:10<12:20:53,  1.71it/s]
Train steps ... :  24%|██▍       | 23978/100000 [6:49:11<12:21:31,  1.71it/s]
Train steps ... :  24%|██▍       | 23979/100000 [6:49:11<12:21:09,  1.71it/s]
Train steps ... :  24%|██▍       | 23980/100000 [6:49:12<12:20:16,  1.71it/s]
Train steps ... :  24%|██▍       | 23981/100000 [6:49:13<12:20:28,  1.71it/s]
Train steps ... :  24%|██▍       | 23982/100000 [6:49:13<12:19:50,  1.71it/s]
Train steps ... :  24%|██▍       | 23983/100000 [6:49:14<12:20:29,  1.71it/s]
Train steps ... :  24%|██▍       | 23984/100000 [6:49:14<12:20:25,  1.71it/s]
Train steps ... :  24%|██▍       | 23985/100000 [6:49:15<12:20:05,  1.71it/s]
Train steps ... :  24%|██▍       | 23986/100000 [6:49:16<12:19:47,  1.71it/s]
Train steps ... :  24%|██▍       | 23987/100000 [6:49:16<12:19:36,  1.71it/s]
Train steps ... :  24%|██▍       | 23988/100000 [6:49:17<12:19:58,  1.71it/s]
Train steps ... :  24%|██▍       | 23989/100000 [6:49:17<12:20:11,  1.71it/s]
Train steps ... :  24%|██▍       | 23990/100000 [6:49:18<12:20:42,  1.71it/s]
Train steps ... :  24%|██▍       | 23991/100000 [6:49:18<12:21:03,  1.71it/s]
Train steps ... :  24%|██▍       | 23992/100000 [6:49:19<12:21:09,  1.71it/s]
Train steps ... :  24%|██▍       | 23993/100000 [6:49:20<12:21:13,  1.71it/s]
Train steps ... :  24%|██▍       | 23994/100000 [6:49:20<12:20:48,  1.71it/s]
Train steps ... :  24%|██▍       | 23995/100000 [6:49:21<12:20:16,  1.71it/s]
Train steps ... :  24%|██▍       | 23996/100000 [6:49:21<12:20:03,  1.71it/s]
Train steps ... :  24%|██▍       | 23997/100000 [6:49:22<12:20:21,  1.71it/s]
Train steps ... :  24%|██▍       | 23998/100000 [6:49:23<12:20:40,  1.71it/s]
Train steps ... :  24%|██▍       | 23999/100000 [6:49:23<12:20:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24000/100000 [6:49:24<12:20:09,  1.71it/s]Step... (24000 / 100000 | Loss: 0.7770604491233826, Learning Rate: 7.638190954773869e-05)
+
                                                                             
Step... (24000 / 100000 | Loss: 0.5804320573806763, Learning Rate: 7.638190954773869e-05)
+
Train steps ... :  24%|██▍       | 24000/100000 [6:49:24<12:20:09,  1.71it/s]
Train steps ... :  24%|██▍       | 24001/100000 [6:49:24<12:20:20,  1.71it/s]
Train steps ... :  24%|██▍       | 24002/100000 [6:49:25<12:21:01,  1.71it/s]
Train steps ... :  24%|██▍       | 24003/100000 [6:49:25<12:21:55,  1.71it/s]
Train steps ... :  24%|██▍       | 24004/100000 [6:49:26<12:21:19,  1.71it/s]
Train steps ... :  24%|██▍       | 24005/100000 [6:49:27<12:21:14,  1.71it/s]
Train steps ... :  24%|██▍       | 24006/100000 [6:49:27<12:21:31,  1.71it/s]
Train steps ... :  24%|██▍       | 24007/100000 [6:49:28<12:21:11,  1.71it/s]
Train steps ... :  24%|██▍       | 24008/100000 [6:49:28<12:21:01,  1.71it/s]
Train steps ... :  24%|██▍       | 24009/100000 [6:49:29<12:21:27,  1.71it/s]
Train steps ... :  24%|██▍       | 24010/100000 [6:49:30<12:20:11,  1.71it/s]
Train steps ... :  24%|██▍       | 24011/100000 [6:49:30<12:20:36,  1.71it/s]
Train steps ... :  24%|██▍       | 24012/100000 [6:49:31<12:21:24,  1.71it/s]
Train steps ... :  24%|██▍       | 24013/100000 [6:49:31<12:21:27,  1.71it/s]
Train steps ... :  24%|██▍       | 24014/100000 [6:49:32<12:20:40,  1.71it/s]
Train steps ... :  24%|██▍       | 24015/100000 [6:49:32<12:20:13,  1.71it/s]
Train steps ... :  24%|██▍       | 24016/100000 [6:49:33<12:20:31,  1.71it/s]
Train steps ... :  24%|██▍       | 24017/100000 [6:49:34<12:19:56,  1.71it/s]
Train steps ... :  24%|██▍       | 24018/100000 [6:49:34<12:20:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24019/100000 [6:49:35<12:19:44,  1.71it/s]
Train steps ... :  24%|██▍       | 24020/100000 [6:49:35<12:19:46,  1.71it/s]
Train steps ... :  24%|██▍       | 24021/100000 [6:49:36<12:21:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24022/100000 [6:49:37<12:22:30,  1.71it/s]
Train steps ... :  24%|██▍       | 24023/100000 [6:49:37<12:20:18,  1.71it/s]
Train steps ... :  24%|██▍       | 24024/100000 [6:49:38<12:21:02,  1.71it/s]
Train steps ... :  24%|██▍       | 24025/100000 [6:49:38<12:20:06,  1.71it/s]Step... (24025 / 100000 | Loss: 0.7946523427963257, Learning Rate: 7.635678391959799e-05)
+
                                                                             
Step... (24025 / 100000 | Loss: 0.6687437295913696, Learning Rate: 7.635678391959799e-05)
+
Train steps ... :  24%|██▍       | 24025/100000 [6:49:39<12:20:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24026/100000 [6:49:39<12:21:01,  1.71it/s]
Train steps ... :  24%|██▍       | 24027/100000 [6:49:39<12:20:03,  1.71it/s]
Train steps ... :  24%|██▍       | 24028/100000 [6:49:40<12:20:20,  1.71it/s]
Train steps ... :  24%|██▍       | 24029/100000 [6:49:41<12:19:47,  1.71it/s]
Train steps ... :  24%|██▍       | 24030/100000 [6:49:41<12:19:39,  1.71it/s]
Train steps ... :  24%|██▍       | 24031/100000 [6:49:42<12:19:41,  1.71it/s]
Train steps ... :  24%|██▍       | 24032/100000 [6:49:42<12:19:35,  1.71it/s]
Train steps ... :  24%|██▍       | 24033/100000 [6:49:43<12:19:25,  1.71it/s]
Train steps ... :  24%|██▍       | 24034/100000 [6:49:44<12:19:42,  1.71it/s]
Train steps ... :  24%|██▍       | 24035/100000 [6:49:44<12:20:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24036/100000 [6:49:45<12:20:18,  1.71it/s]
Train steps ... :  24%|██▍       | 24037/100000 [6:49:45<12:21:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24038/100000 [6:49:46<12:20:23,  1.71it/s]
Train steps ... :  24%|██▍       | 24039/100000 [6:49:47<12:20:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24040/100000 [6:49:47<12:19:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24041/100000 [6:49:48<12:20:28,  1.71it/s]
Train steps ... :  24%|██▍       | 24042/100000 [6:49:48<12:20:57,  1.71it/s]
Train steps ... :  24%|██▍       | 24043/100000 [6:49:49<12:20:32,  1.71it/s]
Train steps ... :  24%|██▍       | 24044/100000 [6:49:49<12:19:42,  1.71it/s]
Train steps ... :  24%|██▍       | 24045/100000 [6:49:50<12:18:55,  1.71it/s]
Train steps ... :  24%|██▍       | 24046/100000 [6:49:51<12:19:36,  1.71it/s]
Train steps ... :  24%|██▍       | 24047/100000 [6:49:51<12:20:09,  1.71it/s]
Train steps ... :  24%|██▍       | 24048/100000 [6:49:52<12:20:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24049/100000 [6:49:52<12:19:09,  1.71it/s]
Train steps ... :  24%|██▍       | 24050/100000 [6:49:53<12:18:59,  1.71it/s]Step... (24050 / 100000 | Loss: 0.9838467836380005, Learning Rate: 7.633165829145729e-05)
+
                                                                             
Step... (24050 / 100000 | Loss: 0.6789649724960327, Learning Rate: 7.633165829145729e-05)
+
Train steps ... :  24%|██▍       | 24050/100000 [6:49:53<12:18:59,  1.71it/s]
Train steps ... :  24%|██▍       | 24051/100000 [6:49:54<12:19:23,  1.71it/s]
Train steps ... :  24%|██▍       | 24052/100000 [6:49:54<12:19:13,  1.71it/s]
Train steps ... :  24%|██▍       | 24053/100000 [6:49:55<12:19:39,  1.71it/s]
Train steps ... :  24%|██▍       | 24054/100000 [6:49:55<12:20:01,  1.71it/s]
Train steps ... :  24%|██▍       | 24055/100000 [6:49:56<12:19:34,  1.71it/s]
Train steps ... :  24%|██▍       | 24056/100000 [6:49:56<12:19:38,  1.71it/s]
Train steps ... :  24%|██▍       | 24057/100000 [6:49:57<12:20:11,  1.71it/s]
Train steps ... :  24%|██▍       | 24058/100000 [6:49:58<12:20:56,  1.71it/s]
Train steps ... :  24%|██▍       | 24059/100000 [6:49:58<12:20:07,  1.71it/s]
Train steps ... :  24%|██▍       | 24060/100000 [6:49:59<12:19:39,  1.71it/s]
Train steps ... :  24%|██▍       | 24061/100000 [6:49:59<12:19:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24062/100000 [6:50:00<12:19:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24063/100000 [6:50:01<12:19:10,  1.71it/s]
Train steps ... :  24%|██▍       | 24064/100000 [6:50:01<12:18:42,  1.71it/s]
Train steps ... :  24%|██▍       | 24065/100000 [6:50:02<12:19:16,  1.71it/s]
Train steps ... :  24%|██▍       | 24066/100000 [6:50:02<12:19:12,  1.71it/s]
Train steps ... :  24%|██▍       | 24067/100000 [6:50:03<12:20:11,  1.71it/s]
Train steps ... :  24%|██▍       | 24068/100000 [6:50:03<12:19:09,  1.71it/s]
Train steps ... :  24%|██▍       | 24069/100000 [6:50:04<12:18:53,  1.71it/s]
Train steps ... :  24%|██▍       | 24070/100000 [6:50:05<12:19:19,  1.71it/s]
Train steps ... :  24%|██▍       | 24071/100000 [6:50:05<12:19:31,  1.71it/s]
Train steps ... :  24%|██▍       | 24072/100000 [6:50:06<12:19:24,  1.71it/s]
Train steps ... :  24%|██▍       | 24073/100000 [6:50:06<12:23:43,  1.70it/s]
Train steps ... :  24%|██▍       | 24074/100000 [6:50:07<12:21:07,  1.71it/s]
Train steps ... :  24%|██▍       | 24075/100000 [6:50:08<12:20:58,  1.71it/s]Step... (24075 / 100000 | Loss: 1.1476244926452637, Learning Rate: 7.630653266331658e-05)
+
                                                                             
Step... (24075 / 100000 | Loss: 0.6760756373405457, Learning Rate: 7.630653266331658e-05)
+
Train steps ... :  24%|██▍       | 24075/100000 [6:50:08<12:20:58,  1.71it/s]
Train steps ... :  24%|██▍       | 24076/100000 [6:50:08<12:21:07,  1.71it/s]
Train steps ... :  24%|██▍       | 24077/100000 [6:50:09<12:21:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24078/100000 [6:50:09<12:21:46,  1.71it/s]
Train steps ... :  24%|██▍       | 24079/100000 [6:50:10<12:20:47,  1.71it/s]
Train steps ... :  24%|██▍       | 24080/100000 [6:50:10<12:20:52,  1.71it/s]
Train steps ... :  24%|██▍       | 24081/100000 [6:50:11<12:20:49,  1.71it/s]
Train steps ... :  24%|██▍       | 24082/100000 [6:50:12<12:19:53,  1.71it/s]
Train steps ... :  24%|██▍       | 24083/100000 [6:50:12<12:19:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24084/100000 [6:50:13<12:19:18,  1.71it/s]
Train steps ... :  24%|██▍       | 24085/100000 [6:50:13<12:19:13,  1.71it/s]
Train steps ... :  24%|██▍       | 24086/100000 [6:50:14<12:18:55,  1.71it/s]
Train steps ... :  24%|██▍       | 24087/100000 [6:50:15<12:19:44,  1.71it/s]
Train steps ... :  24%|██▍       | 24088/100000 [6:50:15<12:19:19,  1.71it/s]
Train steps ... :  24%|██▍       | 24089/100000 [6:50:16<12:19:24,  1.71it/s]
Train steps ... :  24%|██▍       | 24090/100000 [6:50:16<12:19:33,  1.71it/s]
Train steps ... :  24%|██▍       | 24091/100000 [6:50:17<12:21:10,  1.71it/s]
Train steps ... :  24%|██▍       | 24092/100000 [6:50:18<12:21:20,  1.71it/s]
Train steps ... :  24%|██▍       | 24093/100000 [6:50:18<12:22:29,  1.70it/s]
Train steps ... :  24%|██▍       | 24094/100000 [6:50:19<12:22:37,  1.70it/s]
Train steps ... :  24%|██▍       | 24095/100000 [6:50:19<12:21:48,  1.71it/s]
Train steps ... :  24%|██▍       | 24096/100000 [6:50:20<12:21:12,  1.71it/s]
Train steps ... :  24%|██▍       | 24097/100000 [6:50:20<12:20:27,  1.71it/s]
Train steps ... :  24%|██▍       | 24098/100000 [6:50:21<12:20:35,  1.71it/s]
Train steps ... :  24%|██▍       | 24099/100000 [6:50:22<12:20:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24100/100000 [6:50:22<12:20:24,  1.71it/s]Step... (24100 / 100000 | Loss: 0.983979344367981, Learning Rate: 7.628140703517588e-05)
+
                                                                             
Step... (24100 / 100000 | Loss: 0.9710196256637573, Learning Rate: 7.628140703517588e-05)
+
Train steps ... :  24%|██▍       | 24100/100000 [6:50:23<12:20:24,  1.71it/s]
Train steps ... :  24%|██▍       | 24101/100000 [6:50:23<12:19:56,  1.71it/s]
Train steps ... :  24%|██▍       | 24102/100000 [6:50:23<12:19:30,  1.71it/s]
Train steps ... :  24%|██▍       | 24103/100000 [6:50:24<12:19:07,  1.71it/s]
Train steps ... :  24%|██▍       | 24104/100000 [6:50:25<12:19:55,  1.71it/s]
Train steps ... :  24%|██▍       | 24105/100000 [6:50:25<12:19:29,  1.71it/s]
Train steps ... :  24%|██▍       | 24106/100000 [6:50:26<12:20:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24107/100000 [6:50:26<12:20:16,  1.71it/s]
Train steps ... :  24%|██▍       | 24108/100000 [6:50:27<12:19:46,  1.71it/s]
Train steps ... :  24%|██▍       | 24109/100000 [6:50:27<12:19:29,  1.71it/s]
Train steps ... :  24%|██▍       | 24110/100000 [6:50:28<12:20:02,  1.71it/s]
Train steps ... :  24%|██▍       | 24111/100000 [6:50:29<12:20:38,  1.71it/s]
Train steps ... :  24%|██▍       | 24112/100000 [6:50:29<12:20:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24113/100000 [6:50:30<12:20:23,  1.71it/s]
Train steps ... :  24%|██▍       | 24114/100000 [6:50:30<12:20:12,  1.71it/s]
Train steps ... :  24%|██▍       | 24115/100000 [6:50:31<12:19:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24116/100000 [6:50:32<12:20:22,  1.71it/s]
Train steps ... :  24%|██▍       | 24117/100000 [6:50:32<12:20:47,  1.71it/s]
Train steps ... :  24%|██▍       | 24118/100000 [6:50:33<12:20:36,  1.71it/s]
Train steps ... :  24%|██▍       | 24119/100000 [6:50:33<12:21:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24120/100000 [6:50:34<12:20:56,  1.71it/s]
Train steps ... :  24%|██▍       | 24121/100000 [6:50:34<12:21:36,  1.71it/s]
Train steps ... :  24%|██▍       | 24122/100000 [6:50:35<12:22:00,  1.70it/s]
Train steps ... :  24%|██▍       | 24123/100000 [6:50:36<12:21:23,  1.71it/s]
Train steps ... :  24%|██▍       | 24124/100000 [6:50:36<12:22:04,  1.70it/s]
Train steps ... :  24%|██▍       | 24125/100000 [6:50:37<12:21:00,  1.71it/s]Step... (24125 / 100000 | Loss: 1.2667930126190186, Learning Rate: 7.625628140703518e-05)
+
                                                                             
Step... (24125 / 100000 | Loss: 0.9546635150909424, Learning Rate: 7.625628140703518e-05)
+
Train steps ... :  24%|██▍       | 24125/100000 [6:50:37<12:21:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24126/100000 [6:50:37<12:20:29,  1.71it/s]
Train steps ... :  24%|██▍       | 24127/100000 [6:50:38<12:21:02,  1.71it/s]
Train steps ... :  24%|██▍       | 24128/100000 [6:50:39<12:20:18,  1.71it/s]
Train steps ... :  24%|██▍       | 24129/100000 [6:50:39<12:20:57,  1.71it/s]
Train steps ... :  24%|██▍       | 24130/100000 [6:50:40<12:19:34,  1.71it/s]
Train steps ... :  24%|██▍       | 24131/100000 [6:50:40<12:20:47,  1.71it/s]
Train steps ... :  24%|██▍       | 24132/100000 [6:50:41<12:19:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24133/100000 [6:50:42<12:22:41,  1.70it/s]
Train steps ... :  24%|██▍       | 24134/100000 [6:50:42<12:21:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24135/100000 [6:50:43<12:20:33,  1.71it/s]
Train steps ... :  24%|██▍       | 24136/100000 [6:50:43<12:21:30,  1.71it/s]
Train steps ... :  24%|██▍       | 24137/100000 [6:50:44<12:20:23,  1.71it/s]
Train steps ... :  24%|██▍       | 24138/100000 [6:50:44<12:20:01,  1.71it/s]
Train steps ... :  24%|██▍       | 24139/100000 [6:50:45<12:20:30,  1.71it/s]
Train steps ... :  24%|██▍       | 24140/100000 [6:50:46<12:20:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24141/100000 [6:50:46<12:20:12,  1.71it/s]
Train steps ... :  24%|██▍       | 24142/100000 [6:50:47<12:22:31,  1.70it/s]
Train steps ... :  24%|██▍       | 24143/100000 [6:50:47<12:20:36,  1.71it/s]
Train steps ... :  24%|██▍       | 24144/100000 [6:50:48<12:21:44,  1.70it/s]
Train steps ... :  24%|██▍       | 24145/100000 [6:50:49<12:20:07,  1.71it/s]
Train steps ... :  24%|██▍       | 24146/100000 [6:50:49<12:20:08,  1.71it/s]
Train steps ... :  24%|██▍       | 24147/100000 [6:50:50<12:18:59,  1.71it/s]
Train steps ... :  24%|██▍       | 24148/100000 [6:50:50<12:19:14,  1.71it/s]
Train steps ... :  24%|██▍       | 24149/100000 [6:50:51<12:21:22,  1.71it/s]
Train steps ... :  24%|██▍       | 24150/100000 [6:50:51<12:20:44,  1.71it/s]Step... (24150 / 100000 | Loss: 0.8655149340629578, Learning Rate: 7.623115577889449e-05)
+
                                                                             
Step... (24150 / 100000 | Loss: 1.1254855394363403, Learning Rate: 7.623115577889449e-05)
+
Train steps ... :  24%|██▍       | 24150/100000 [6:50:52<12:20:44,  1.71it/s]
Train steps ... :  24%|██▍       | 24151/100000 [6:50:52<12:21:02,  1.71it/s]
Train steps ... :  24%|██▍       | 24152/100000 [6:50:53<12:20:39,  1.71it/s]
Train steps ... :  24%|██▍       | 24153/100000 [6:50:53<12:19:57,  1.71it/s]
Train steps ... :  24%|██▍       | 24154/100000 [6:50:54<12:20:44,  1.71it/s]
Train steps ... :  24%|██▍       | 24155/100000 [6:50:54<12:20:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24156/100000 [6:50:55<12:20:42,  1.71it/s]
Train steps ... :  24%|██▍       | 24157/100000 [6:50:56<12:19:11,  1.71it/s]
Train steps ... :  24%|██▍       | 24158/100000 [6:50:56<12:19:41,  1.71it/s]
Train steps ... :  24%|██▍       | 24159/100000 [6:50:57<12:21:34,  1.70it/s]
Train steps ... :  24%|██▍       | 24160/100000 [6:50:57<12:21:34,  1.70it/s]
Train steps ... :  24%|██▍       | 24161/100000 [6:50:58<12:21:44,  1.70it/s]
Train steps ... :  24%|██▍       | 24162/100000 [6:50:59<12:19:45,  1.71it/s]
Train steps ... :  24%|██▍       | 24163/100000 [6:50:59<12:20:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24164/100000 [6:51:00<12:20:10,  1.71it/s]
Train steps ... :  24%|██▍       | 24165/100000 [6:51:00<12:19:35,  1.71it/s]
Train steps ... :  24%|██▍       | 24166/100000 [6:51:01<12:20:01,  1.71it/s]
Train steps ... :  24%|██▍       | 24167/100000 [6:51:01<12:19:14,  1.71it/s]
Train steps ... :  24%|██▍       | 24168/100000 [6:51:02<12:21:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24169/100000 [6:51:03<12:18:43,  1.71it/s]
Train steps ... :  24%|██▍       | 24170/100000 [6:51:03<12:20:11,  1.71it/s]
Train steps ... :  24%|██▍       | 24171/100000 [6:51:04<12:20:10,  1.71it/s]
Train steps ... :  24%|██▍       | 24172/100000 [6:51:04<12:18:24,  1.71it/s]
Train steps ... :  24%|██▍       | 24173/100000 [6:51:05<12:18:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24174/100000 [6:51:06<12:19:20,  1.71it/s]
Train steps ... :  24%|██▍       | 24175/100000 [6:51:06<12:20:40,  1.71it/s]Step... (24175 / 100000 | Loss: 0.9719386696815491, Learning Rate: 7.620603015075377e-05)
+
                                                                             
Step... (24175 / 100000 | Loss: 0.8690699338912964, Learning Rate: 7.620603015075377e-05)
+
Train steps ... :  24%|██▍       | 24175/100000 [6:51:06<12:20:40,  1.71it/s]
Train steps ... :  24%|██▍       | 24176/100000 [6:51:07<12:20:30,  1.71it/s]
Train steps ... :  24%|██▍       | 24177/100000 [6:51:07<12:19:30,  1.71it/s]
Train steps ... :  24%|██▍       | 24178/100000 [6:51:08<12:21:48,  1.70it/s]
Train steps ... :  24%|██▍       | 24179/100000 [6:51:08<12:20:10,  1.71it/s]
Train steps ... :  24%|██▍       | 24180/100000 [6:51:09<12:20:11,  1.71it/s]
Train steps ... :  24%|██▍       | 24181/100000 [6:51:10<12:18:57,  1.71it/s]
Train steps ... :  24%|██▍       | 24182/100000 [6:51:10<12:19:25,  1.71it/s]
Train steps ... :  24%|██▍       | 24183/100000 [6:51:11<12:21:20,  1.70it/s]
Train steps ... :  24%|██▍       | 24184/100000 [6:51:11<12:21:51,  1.70it/s]
Train steps ... :  24%|██▍       | 24185/100000 [6:51:12<12:20:12,  1.71it/s]
Train steps ... :  24%|██▍       | 24186/100000 [6:51:13<12:21:24,  1.70it/s]
Train steps ... :  24%|██▍       | 24187/100000 [6:51:13<12:20:46,  1.71it/s]
Train steps ... :  24%|██▍       | 24188/100000 [6:51:14<12:19:37,  1.71it/s]
Train steps ... :  24%|██▍       | 24189/100000 [6:51:14<12:18:36,  1.71it/s]
Train steps ... :  24%|██▍       | 24190/100000 [6:51:15<12:20:26,  1.71it/s]
Train steps ... :  24%|██▍       | 24191/100000 [6:51:15<12:19:08,  1.71it/s]
Train steps ... :  24%|██▍       | 24192/100000 [6:51:16<12:19:27,  1.71it/s]
Train steps ... :  24%|██▍       | 24193/100000 [6:51:17<12:19:44,  1.71it/s]
Train steps ... :  24%|██▍       | 24194/100000 [6:51:17<12:19:56,  1.71it/s]
Train steps ... :  24%|██▍       | 24195/100000 [6:51:18<12:19:08,  1.71it/s]
Train steps ... :  24%|██▍       | 24196/100000 [6:51:18<12:18:40,  1.71it/s]
Train steps ... :  24%|██▍       | 24197/100000 [6:51:19<12:18:52,  1.71it/s]
Train steps ... :  24%|██▍       | 24198/100000 [6:51:20<12:19:09,  1.71it/s]
Train steps ... :  24%|██▍       | 24199/100000 [6:51:20<12:19:42,  1.71it/s]
Train steps ... :  24%|██▍       | 24200/100000 [6:51:21<12:19:06,  1.71it/s]Step... (24200 / 100000 | Loss: 0.8609551787376404, Learning Rate: 7.618090452261307e-05)
+
                                                                             
Step... (24200 / 100000 | Loss: 0.805305540561676, Learning Rate: 7.618090452261307e-05)
+
Train steps ... :  24%|██▍       | 24200/100000 [6:51:21<12:19:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24201/100000 [6:51:21<12:19:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24202/100000 [6:51:22<12:20:12,  1.71it/s]
Train steps ... :  24%|██▍       | 24203/100000 [6:51:23<12:19:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24204/100000 [6:51:23<12:18:17,  1.71it/s]
Train steps ... :  24%|██▍       | 24205/100000 [6:51:24<12:18:53,  1.71it/s]
Train steps ... :  24%|██▍       | 24206/100000 [6:51:24<12:21:04,  1.70it/s]
Train steps ... :  24%|██▍       | 24207/100000 [6:51:25<12:20:41,  1.71it/s]
Train steps ... :  24%|██▍       | 24208/100000 [6:51:25<12:23:47,  1.70it/s]
Train steps ... :  24%|██▍       | 24209/100000 [6:51:26<12:21:11,  1.70it/s]
Train steps ... :  24%|██▍       | 24210/100000 [6:51:27<12:21:41,  1.70it/s]
Train steps ... :  24%|██▍       | 24211/100000 [6:51:27<12:22:41,  1.70it/s]
Train steps ... :  24%|██▍       | 24212/100000 [6:51:28<12:23:15,  1.70it/s]
Train steps ... :  24%|██▍       | 24213/100000 [6:51:28<12:23:03,  1.70it/s]
Train steps ... :  24%|██▍       | 24214/100000 [6:51:29<12:23:47,  1.70it/s]
Train steps ... :  24%|██▍       | 24215/100000 [6:51:30<12:25:02,  1.70it/s]
Train steps ... :  24%|██▍       | 24216/100000 [6:51:30<12:21:30,  1.70it/s]
Train steps ... :  24%|██▍       | 24217/100000 [6:51:31<12:23:33,  1.70it/s]
Train steps ... :  24%|██▍       | 24218/100000 [6:51:31<12:23:33,  1.70it/s]
Train steps ... :  24%|██▍       | 24219/100000 [6:51:32<12:22:14,  1.70it/s]
Train steps ... :  24%|██▍       | 24220/100000 [6:51:32<12:21:23,  1.70it/s]
Train steps ... :  24%|██▍       | 24221/100000 [6:51:33<12:20:55,  1.70it/s]
Train steps ... :  24%|██▍       | 24222/100000 [6:51:34<12:20:42,  1.71it/s]
Train steps ... :  24%|██▍       | 24223/100000 [6:51:34<12:20:50,  1.70it/s]
Train steps ... :  24%|██▍       | 24224/100000 [6:51:35<12:21:05,  1.70it/s]
Train steps ... :  24%|██▍       | 24225/100000 [6:51:35<12:22:20,  1.70it/s]Step... (24225 / 100000 | Loss: 0.8131205439567566, Learning Rate: 7.615577889447236e-05)
+
                                                                             
Step... (24225 / 100000 | Loss: 1.4351637363433838, Learning Rate: 7.615577889447236e-05)
+
Train steps ... :  24%|██▍       | 24225/100000 [6:51:36<12:22:20,  1.70it/s]
Train steps ... :  24%|██▍       | 24226/100000 [6:51:36<12:19:46,  1.71it/s]
Train steps ... :  24%|██▍       | 24227/100000 [6:51:37<12:22:46,  1.70it/s]
Train steps ... :  24%|██▍       | 24228/100000 [6:51:37<12:18:52,  1.71it/s]
Train steps ... :  24%|██▍       | 24229/100000 [6:51:38<12:18:58,  1.71it/s]
Train steps ... :  24%|██▍       | 24230/100000 [6:51:38<12:19:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24231/100000 [6:51:39<12:18:13,  1.71it/s]
Train steps ... :  24%|██▍       | 24232/100000 [6:51:40<12:18:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24233/100000 [6:51:40<12:18:42,  1.71it/s]
Train steps ... :  24%|██▍       | 24234/100000 [6:51:41<12:18:13,  1.71it/s]
Train steps ... :  24%|██▍       | 24235/100000 [6:51:41<12:19:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24236/100000 [6:51:42<12:18:07,  1.71it/s]
Train steps ... :  24%|██▍       | 24237/100000 [6:51:42<12:19:15,  1.71it/s]
Train steps ... :  24%|██▍       | 24238/100000 [6:51:43<12:18:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24239/100000 [6:51:44<12:18:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24240/100000 [6:51:44<12:18:47,  1.71it/s]
Train steps ... :  24%|██▍       | 24241/100000 [6:51:45<12:18:24,  1.71it/s]
Train steps ... :  24%|██▍       | 24242/100000 [6:51:45<12:18:38,  1.71it/s]
Train steps ... :  24%|██▍       | 24243/100000 [6:51:46<12:18:35,  1.71it/s]
Train steps ... :  24%|██▍       | 24244/100000 [6:51:47<12:19:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24245/100000 [6:51:47<12:18:37,  1.71it/s]
Train steps ... :  24%|██▍       | 24246/100000 [6:51:48<12:18:50,  1.71it/s]
Train steps ... :  24%|██▍       | 24247/100000 [6:51:48<12:19:40,  1.71it/s]
Train steps ... :  24%|██▍       | 24248/100000 [6:51:49<12:18:46,  1.71it/s]
Train steps ... :  24%|██▍       | 24249/100000 [6:51:49<12:18:33,  1.71it/s]
Train steps ... :  24%|██▍       | 24250/100000 [6:51:50<12:18:52,  1.71it/s]Step... (24250 / 100000 | Loss: 0.909528374671936, Learning Rate: 7.613065326633166e-05)
+
                                                                             
Step... (24250 / 100000 | Loss: 0.8356572389602661, Learning Rate: 7.613065326633166e-05)
+
Train steps ... :  24%|██▍       | 24250/100000 [6:51:50<12:18:52,  1.71it/s]
Train steps ... :  24%|██▍       | 24251/100000 [6:51:51<12:19:17,  1.71it/s]
Train steps ... :  24%|██▍       | 24252/100000 [6:51:51<12:22:59,  1.70it/s]
Train steps ... :  24%|██▍       | 24253/100000 [6:51:52<12:20:24,  1.71it/s]
Train steps ... :  24%|██▍       | 24254/100000 [6:51:52<12:20:52,  1.70it/s]
Train steps ... :  24%|██▍       | 24255/100000 [6:51:53<12:21:12,  1.70it/s]
Train steps ... :  24%|██▍       | 24256/100000 [6:51:54<12:22:09,  1.70it/s]
Train steps ... :  24%|██▍       | 24257/100000 [6:51:54<12:19:53,  1.71it/s]
Train steps ... :  24%|██▍       | 24258/100000 [6:51:55<12:19:14,  1.71it/s]
Train steps ... :  24%|██▍       | 24259/100000 [6:51:55<12:19:44,  1.71it/s]
Train steps ... :  24%|██▍       | 24260/100000 [6:51:56<12:20:45,  1.70it/s]
Train steps ... :  24%|██▍       | 24261/100000 [6:51:57<12:20:08,  1.71it/s]
Train steps ... :  24%|██▍       | 24262/100000 [6:51:57<12:19:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24263/100000 [6:51:58<12:19:28,  1.71it/s]
Train steps ... :  24%|██▍       | 24264/100000 [6:51:58<12:20:11,  1.71it/s]
Train steps ... :  24%|██▍       | 24265/100000 [6:51:59<12:19:43,  1.71it/s]
Train steps ... :  24%|██▍       | 24266/100000 [6:51:59<12:19:48,  1.71it/s]
Train steps ... :  24%|██▍       | 24267/100000 [6:52:00<12:20:40,  1.70it/s]
Train steps ... :  24%|██▍       | 24268/100000 [6:52:01<12:21:19,  1.70it/s]
Train steps ... :  24%|██▍       | 24269/100000 [6:52:01<12:20:53,  1.70it/s]
Train steps ... :  24%|██▍       | 24270/100000 [6:52:02<12:19:22,  1.71it/s]
Train steps ... :  24%|██▍       | 24271/100000 [6:52:02<12:19:14,  1.71it/s]
Train steps ... :  24%|██▍       | 24272/100000 [6:52:03<12:21:47,  1.70it/s]
Train steps ... :  24%|██▍       | 24273/100000 [6:52:04<12:21:16,  1.70it/s]
Train steps ... :  24%|██▍       | 24274/100000 [6:52:04<12:19:35,  1.71it/s]
Train steps ... :  24%|██▍       | 24275/100000 [6:52:05<12:20:32,  1.70it/s]Step... (24275 / 100000 | Loss: 0.8507226705551147, Learning Rate: 7.610552763819096e-05)
+
                                                                             
Step... (24275 / 100000 | Loss: 1.110766053199768, Learning Rate: 7.610552763819096e-05)
+
Train steps ... :  24%|██▍       | 24275/100000 [6:52:05<12:20:32,  1.70it/s]
Train steps ... :  24%|██▍       | 24276/100000 [6:52:05<12:20:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24277/100000 [6:52:06<12:20:30,  1.70it/s]
Train steps ... :  24%|██▍       | 24278/100000 [6:52:06<12:20:37,  1.70it/s]
Train steps ... :  24%|██▍       | 24279/100000 [6:52:07<12:21:02,  1.70it/s]
Train steps ... :  24%|██▍       | 24280/100000 [6:52:08<12:19:45,  1.71it/s]
Train steps ... :  24%|██▍       | 24281/100000 [6:52:08<12:19:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24282/100000 [6:52:09<12:18:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24283/100000 [6:52:09<12:19:10,  1.71it/s]
Train steps ... :  24%|██▍       | 24284/100000 [6:52:10<12:18:46,  1.71it/s]
Train steps ... :  24%|██▍       | 24285/100000 [6:52:11<12:18:27,  1.71it/s]
Train steps ... :  24%|██▍       | 24286/100000 [6:52:11<12:19:24,  1.71it/s]
Train steps ... :  24%|██▍       | 24287/100000 [6:52:12<12:19:39,  1.71it/s]
Train steps ... :  24%|██▍       | 24288/100000 [6:52:12<12:19:47,  1.71it/s]
Train steps ... :  24%|██▍       | 24289/100000 [6:52:13<12:18:57,  1.71it/s]
Train steps ... :  24%|██▍       | 24290/100000 [6:52:14<12:19:55,  1.71it/s]
Train steps ... :  24%|██▍       | 24291/100000 [6:52:14<12:20:20,  1.70it/s]
Train steps ... :  24%|██▍       | 24292/100000 [6:52:15<12:18:16,  1.71it/s]
Train steps ... :  24%|██▍       | 24293/100000 [6:52:15<12:19:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24294/100000 [6:52:16<12:19:24,  1.71it/s]
Train steps ... :  24%|██▍       | 24295/100000 [6:52:16<12:18:32,  1.71it/s]
Train steps ... :  24%|██▍       | 24296/100000 [6:52:17<12:17:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24297/100000 [6:52:18<12:17:23,  1.71it/s]
Train steps ... :  24%|██▍       | 24298/100000 [6:52:18<12:17:03,  1.71it/s]
Train steps ... :  24%|██▍       | 24299/100000 [6:52:19<12:17:33,  1.71it/s]
Train steps ... :  24%|██▍       | 24300/100000 [6:52:19<12:16:44,  1.71it/s]Step... (24300 / 100000 | Loss: 0.7206546068191528, Learning Rate: 7.608040201005025e-05)
+
                                                                             
Step... (24300 / 100000 | Loss: 0.8040058612823486, Learning Rate: 7.608040201005025e-05)
+
Train steps ... :  24%|██▍       | 24300/100000 [6:52:20<12:16:44,  1.71it/s]
Train steps ... :  24%|██▍       | 24301/100000 [6:52:20<12:17:17,  1.71it/s]
Train steps ... :  24%|██▍       | 24302/100000 [6:52:21<12:17:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24303/100000 [6:52:21<12:17:28,  1.71it/s]
Train steps ... :  24%|██▍       | 24304/100000 [6:52:22<12:17:39,  1.71it/s]
Train steps ... :  24%|██▍       | 24305/100000 [6:52:22<12:17:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24306/100000 [6:52:23<12:18:02,  1.71it/s]
Train steps ... :  24%|██▍       | 24307/100000 [6:52:23<12:21:36,  1.70it/s]
Train steps ... :  24%|██▍       | 24308/100000 [6:52:24<12:20:03,  1.70it/s]
Train steps ... :  24%|██▍       | 24309/100000 [6:52:25<12:21:13,  1.70it/s]
Train steps ... :  24%|██▍       | 24310/100000 [6:52:25<12:19:59,  1.70it/s]
Train steps ... :  24%|██▍       | 24311/100000 [6:52:26<12:20:16,  1.70it/s]
Train steps ... :  24%|██▍       | 24312/100000 [6:52:26<12:20:07,  1.70it/s]
Train steps ... :  24%|██▍       | 24313/100000 [6:52:27<12:19:57,  1.70it/s]
Train steps ... :  24%|██▍       | 24314/100000 [6:52:28<12:19:37,  1.71it/s]
Train steps ... :  24%|██▍       | 24315/100000 [6:52:28<12:18:33,  1.71it/s]
Train steps ... :  24%|██▍       | 24316/100000 [6:52:29<12:20:14,  1.70it/s]
Train steps ... :  24%|██▍       | 24317/100000 [6:52:29<12:18:20,  1.71it/s]
Train steps ... :  24%|██▍       | 24318/100000 [6:52:30<12:18:08,  1.71it/s]
Train steps ... :  24%|██▍       | 24319/100000 [6:52:30<12:18:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24320/100000 [6:52:31<12:18:42,  1.71it/s]
Train steps ... :  24%|██▍       | 24321/100000 [6:52:32<12:19:16,  1.71it/s]
Train steps ... :  24%|██▍       | 24322/100000 [6:52:32<12:18:50,  1.71it/s]
Train steps ... :  24%|██▍       | 24323/100000 [6:52:33<12:17:22,  1.71it/s]
Train steps ... :  24%|██▍       | 24324/100000 [6:52:33<12:16:49,  1.71it/s]
Train steps ... :  24%|██▍       | 24325/100000 [6:52:34<12:17:47,  1.71it/s]Step... (24325 / 100000 | Loss: 0.7762709259986877, Learning Rate: 7.605527638190955e-05)
+
                                                                             
Step... (24325 / 100000 | Loss: 1.0850309133529663, Learning Rate: 7.605527638190955e-05)
+
Train steps ... :  24%|██▍       | 24325/100000 [6:52:34<12:17:47,  1.71it/s]
Train steps ... :  24%|██▍       | 24326/100000 [6:52:35<12:17:35,  1.71it/s]
Train steps ... :  24%|██▍       | 24327/100000 [6:52:35<12:20:26,  1.70it/s]
Train steps ... :  24%|██▍       | 24328/100000 [6:52:36<12:19:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24329/100000 [6:52:36<12:20:07,  1.70it/s]
Train steps ... :  24%|██▍       | 24330/100000 [6:52:37<12:17:19,  1.71it/s]
Train steps ... :  24%|██▍       | 24331/100000 [6:52:38<12:18:55,  1.71it/s]
Train steps ... :  24%|██▍       | 24332/100000 [6:52:38<12:19:11,  1.71it/s]
Train steps ... :  24%|██▍       | 24333/100000 [6:52:39<12:17:31,  1.71it/s]
Train steps ... :  24%|██▍       | 24334/100000 [6:52:39<12:17:26,  1.71it/s]
Train steps ... :  24%|██▍       | 24335/100000 [6:52:40<12:16:46,  1.71it/s]
Train steps ... :  24%|██▍       | 24336/100000 [6:52:40<12:17:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24337/100000 [6:52:41<12:20:03,  1.70it/s]
Train steps ... :  24%|██▍       | 24338/100000 [6:52:42<12:22:47,  1.70it/s]
Train steps ... :  24%|██▍       | 24339/100000 [6:52:42<12:20:46,  1.70it/s]
Train steps ... :  24%|██▍       | 24340/100000 [6:52:43<12:20:14,  1.70it/s]
Train steps ... :  24%|██▍       | 24341/100000 [6:52:43<12:20:35,  1.70it/s]
Train steps ... :  24%|██▍       | 24342/100000 [6:52:44<12:19:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24343/100000 [6:52:45<12:16:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24344/100000 [6:52:45<12:17:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24345/100000 [6:52:46<12:17:45,  1.71it/s]
Train steps ... :  24%|██▍       | 24346/100000 [6:52:46<12:19:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24347/100000 [6:52:47<12:18:08,  1.71it/s]
Train steps ... :  24%|██▍       | 24348/100000 [6:52:47<12:18:45,  1.71it/s]
Train steps ... :  24%|██▍       | 24349/100000 [6:52:48<12:18:01,  1.71it/s]
Train steps ... :  24%|██▍       | 24350/100000 [6:52:49<12:18:52,  1.71it/s]Step... (24350 / 100000 | Loss: 1.0501643419265747, Learning Rate: 7.603015075376885e-05)
+
                                                                             
Step... (24350 / 100000 | Loss: 1.0340635776519775, Learning Rate: 7.603015075376885e-05)
+
Train steps ... :  24%|██▍       | 24350/100000 [6:52:49<12:18:52,  1.71it/s]
Train steps ... :  24%|██▍       | 24351/100000 [6:52:49<12:18:28,  1.71it/s]
Train steps ... :  24%|██▍       | 24352/100000 [6:52:50<12:19:19,  1.71it/s]
Train steps ... :  24%|██▍       | 24353/100000 [6:52:50<12:19:58,  1.70it/s]
Train steps ... :  24%|██▍       | 24354/100000 [6:52:51<12:19:10,  1.71it/s]
Train steps ... :  24%|██▍       | 24355/100000 [6:52:52<12:19:49,  1.70it/s]
Train steps ... :  24%|██▍       | 24356/100000 [6:52:52<12:24:29,  1.69it/s]
Train steps ... :  24%|██▍       | 24357/100000 [6:52:53<12:20:30,  1.70it/s]
Train steps ... :  24%|██▍       | 24358/100000 [6:52:53<12:21:15,  1.70it/s]
Train steps ... :  24%|██▍       | 24359/100000 [6:52:54<12:20:06,  1.70it/s]
Train steps ... :  24%|██▍       | 24360/100000 [6:52:55<12:20:58,  1.70it/s]
Train steps ... :  24%|██▍       | 24361/100000 [6:52:55<12:21:35,  1.70it/s]
Train steps ... :  24%|██▍       | 24362/100000 [6:52:56<12:20:18,  1.70it/s]
Train steps ... :  24%|██▍       | 24363/100000 [6:52:56<12:20:07,  1.70it/s]
Train steps ... :  24%|██▍       | 24364/100000 [6:52:57<12:18:35,  1.71it/s]
Train steps ... :  24%|██▍       | 24365/100000 [6:52:57<12:17:57,  1.71it/s]
Train steps ... :  24%|██▍       | 24366/100000 [6:52:58<12:19:31,  1.70it/s]
Train steps ... :  24%|██▍       | 24367/100000 [6:52:59<12:17:52,  1.71it/s]
Train steps ... :  24%|██▍       | 24368/100000 [6:52:59<12:17:26,  1.71it/s]
Train steps ... :  24%|██▍       | 24369/100000 [6:53:00<12:17:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24370/100000 [6:53:00<12:17:07,  1.71it/s]
Train steps ... :  24%|██▍       | 24371/100000 [6:53:01<12:17:43,  1.71it/s]
Train steps ... :  24%|██▍       | 24372/100000 [6:53:02<12:16:44,  1.71it/s]
Train steps ... :  24%|██▍       | 24373/100000 [6:53:02<12:16:30,  1.71it/s]
Train steps ... :  24%|██▍       | 24374/100000 [6:53:03<12:16:26,  1.71it/s]
Train steps ... :  24%|██▍       | 24375/100000 [6:53:03<12:17:51,  1.71it/s]Step... (24375 / 100000 | Loss: 1.354477882385254, Learning Rate: 7.600502512562814e-05)
+
                                                                             
Step... (24375 / 100000 | Loss: 0.8398449420928955, Learning Rate: 7.600502512562814e-05)
+
Train steps ... :  24%|██▍       | 24375/100000 [6:53:04<12:17:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24376/100000 [6:53:04<12:18:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24377/100000 [6:53:04<12:19:43,  1.70it/s]
Train steps ... :  24%|██▍       | 24378/100000 [6:53:05<12:20:28,  1.70it/s]
Train steps ... :  24%|██▍       | 24379/100000 [6:53:06<12:19:19,  1.70it/s]
Train steps ... :  24%|██▍       | 24380/100000 [6:53:06<12:18:50,  1.71it/s]
Train steps ... :  24%|██▍       | 24381/100000 [6:53:07<12:18:45,  1.71it/s]
Train steps ... :  24%|██▍       | 24382/100000 [6:53:07<12:18:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24383/100000 [6:53:08<12:18:32,  1.71it/s]
Train steps ... :  24%|██▍       | 24384/100000 [6:53:09<12:18:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24385/100000 [6:53:09<12:17:41,  1.71it/s]
Train steps ... :  24%|██▍       | 24386/100000 [6:53:10<12:18:16,  1.71it/s]
Train steps ... :  24%|██▍       | 24387/100000 [6:53:10<12:17:33,  1.71it/s]
Train steps ... :  24%|██▍       | 24388/100000 [6:53:11<12:17:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24389/100000 [6:53:12<12:17:49,  1.71it/s]
Train steps ... :  24%|██▍       | 24390/100000 [6:53:12<12:17:45,  1.71it/s]
Train steps ... :  24%|██▍       | 24391/100000 [6:53:13<12:19:21,  1.70it/s]
Train steps ... :  24%|██▍       | 24392/100000 [6:53:13<12:17:21,  1.71it/s]
Train steps ... :  24%|██▍       | 24393/100000 [6:53:14<12:17:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24394/100000 [6:53:14<12:18:01,  1.71it/s]
Train steps ... :  24%|██▍       | 24395/100000 [6:53:15<12:19:15,  1.70it/s]
Train steps ... :  24%|██▍       | 24396/100000 [6:53:16<12:18:48,  1.71it/s]
Train steps ... :  24%|██▍       | 24397/100000 [6:53:16<12:18:27,  1.71it/s]
Train steps ... :  24%|██▍       | 24398/100000 [6:53:17<12:18:45,  1.71it/s]
Train steps ... :  24%|██▍       | 24399/100000 [6:53:17<12:18:59,  1.71it/s]
Train steps ... :  24%|██▍       | 24400/100000 [6:53:18<12:20:07,  1.70it/s]Step... (24400 / 100000 | Loss: 1.1232810020446777, Learning Rate: 7.597989949748744e-05)
+
                                                                             
Step... (24400 / 100000 | Loss: 0.9674120545387268, Learning Rate: 7.597989949748744e-05)
+
Train steps ... :  24%|██▍       | 24400/100000 [6:53:18<12:20:07,  1.70it/s]
Train steps ... :  24%|██▍       | 24401/100000 [6:53:19<12:17:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24402/100000 [6:53:19<12:18:31,  1.71it/s]
Train steps ... :  24%|██▍       | 24403/100000 [6:53:20<12:18:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24404/100000 [6:53:20<12:18:40,  1.71it/s]
Train steps ... :  24%|██▍       | 24405/100000 [6:53:21<12:18:39,  1.71it/s]
Train steps ... :  24%|██▍       | 24406/100000 [6:53:21<12:17:26,  1.71it/s]
Train steps ... :  24%|██▍       | 24407/100000 [6:53:22<12:19:15,  1.70it/s]
Train steps ... :  24%|██▍       | 24408/100000 [6:53:23<12:16:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24409/100000 [6:53:23<12:16:38,  1.71it/s]
Train steps ... :  24%|██▍       | 24410/100000 [6:53:24<12:15:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24411/100000 [6:53:24<12:15:26,  1.71it/s]
Train steps ... :  24%|██▍       | 24412/100000 [6:53:25<12:15:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24413/100000 [6:53:26<12:17:47,  1.71it/s]
Train steps ... :  24%|██▍       | 24414/100000 [6:53:26<12:15:39,  1.71it/s]
Train steps ... :  24%|██▍       | 24415/100000 [6:53:27<12:17:42,  1.71it/s]
Train steps ... :  24%|██▍       | 24416/100000 [6:53:27<12:17:37,  1.71it/s]
Train steps ... :  24%|██▍       | 24417/100000 [6:53:28<12:18:28,  1.71it/s]
Train steps ... :  24%|██▍       | 24418/100000 [6:53:28<12:17:20,  1.71it/s]
Train steps ... :  24%|██▍       | 24419/100000 [6:53:29<12:17:35,  1.71it/s]
Train steps ... :  24%|██▍       | 24420/100000 [6:53:30<12:18:32,  1.71it/s]
Train steps ... :  24%|██▍       | 24421/100000 [6:53:30<12:17:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24422/100000 [6:53:31<12:17:27,  1.71it/s]
Train steps ... :  24%|██▍       | 24423/100000 [6:53:31<12:16:22,  1.71it/s]
Train steps ... :  24%|██▍       | 24424/100000 [6:53:32<12:16:45,  1.71it/s]
Train steps ... :  24%|██▍       | 24425/100000 [6:53:33<12:17:54,  1.71it/s]Step... (24425 / 100000 | Loss: 0.9051287174224854, Learning Rate: 7.595477386934674e-05)
+
                                                                             
Step... (24425 / 100000 | Loss: 1.6293964385986328, Learning Rate: 7.595477386934674e-05)
+
Train steps ... :  24%|██▍       | 24425/100000 [6:53:33<12:17:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24426/100000 [6:53:33<12:19:07,  1.70it/s]
Train steps ... :  24%|██▍       | 24427/100000 [6:53:34<12:18:25,  1.71it/s]
Train steps ... :  24%|██▍       | 24428/100000 [6:53:34<12:16:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24429/100000 [6:53:35<12:18:43,  1.70it/s]
Train steps ... :  24%|██▍       | 24430/100000 [6:53:36<12:18:52,  1.70it/s]
Train steps ... :  24%|██▍       | 24431/100000 [6:53:36<12:19:21,  1.70it/s]
Train steps ... :  24%|██▍       | 24432/100000 [6:53:37<12:18:50,  1.70it/s]
Train steps ... :  24%|██▍       | 24433/100000 [6:53:37<12:20:08,  1.70it/s]
Train steps ... :  24%|██▍       | 24434/100000 [6:53:38<12:18:02,  1.71it/s]
Train steps ... :  24%|██▍       | 24435/100000 [6:53:38<12:19:05,  1.70it/s]
Train steps ... :  24%|██▍       | 24436/100000 [6:53:39<12:17:27,  1.71it/s]
Train steps ... :  24%|██▍       | 24437/100000 [6:53:40<12:17:22,  1.71it/s]
Train steps ... :  24%|██▍       | 24438/100000 [6:53:40<12:20:30,  1.70it/s]
Train steps ... :  24%|██▍       | 24439/100000 [6:53:41<12:16:50,  1.71it/s]
Train steps ... :  24%|██▍       | 24440/100000 [6:53:41<12:18:13,  1.71it/s]
Train steps ... :  24%|██▍       | 24441/100000 [6:53:42<12:17:25,  1.71it/s]
Train steps ... :  24%|██▍       | 24442/100000 [6:53:43<12:18:06,  1.71it/s]
Train steps ... :  24%|██▍       | 24443/100000 [6:53:43<12:17:31,  1.71it/s]
Train steps ... :  24%|██▍       | 24444/100000 [6:53:44<12:18:34,  1.71it/s]
Train steps ... :  24%|██▍       | 24445/100000 [6:53:44<12:17:21,  1.71it/s]
Train steps ... :  24%|██▍       | 24446/100000 [6:53:45<12:17:51,  1.71it/s]
Train steps ... :  24%|██▍       | 24447/100000 [6:53:45<12:17:30,  1.71it/s]
Train steps ... :  24%|██▍       | 24448/100000 [6:53:46<12:17:13,  1.71it/s]
Train steps ... :  24%|██▍       | 24449/100000 [6:53:47<12:17:54,  1.71it/s]
Train steps ... :  24%|██▍       | 24450/100000 [6:53:47<12:18:59,  1.70it/s]Step... (24450 / 100000 | Loss: 0.809866726398468, Learning Rate: 7.592964824120603e-05)
+
                                                                             
Step... (24450 / 100000 | Loss: 1.0488777160644531, Learning Rate: 7.592964824120603e-05)
+
Train steps ... :  24%|██▍       | 24450/100000 [6:53:48<12:18:59,  1.70it/s]
Train steps ... :  24%|██▍       | 24451/100000 [6:53:48<12:18:00,  1.71it/s]
Train steps ... :  24%|██▍       | 24452/100000 [6:53:48<12:18:25,  1.71it/s]
Train steps ... :  24%|██▍       | 24453/100000 [6:53:49<12:17:50,  1.71it/s]
Train steps ... :  24%|██▍       | 24454/100000 [6:53:50<12:18:36,  1.70it/s]
Train steps ... :  24%|██▍       | 24455/100000 [6:53:50<12:21:31,  1.70it/s]
Train steps ... :  24%|██▍       | 24456/100000 [6:53:51<12:19:12,  1.70it/s]
Train steps ... :  24%|██▍       | 24457/100000 [6:53:51<12:18:35,  1.70it/s]
Train steps ... :  24%|██▍       | 24458/100000 [6:53:52<12:16:55,  1.71it/s]
Train steps ... :  24%|██▍       | 24459/100000 [6:53:53<12:17:33,  1.71it/s]
Train steps ... :  24%|██▍       | 24460/100000 [6:53:53<12:17:37,  1.71it/s]
Train steps ... :  24%|██▍       | 24461/100000 [6:53:54<12:18:16,  1.71it/s]
Train steps ... :  24%|██▍       | 24462/100000 [6:53:54<12:17:38,  1.71it/s]
Train steps ... :  24%|██▍       | 24463/100000 [6:53:55<12:17:31,  1.71it/s]
Train steps ... :  24%|██▍       | 24464/100000 [6:53:55<12:17:43,  1.71it/s]
Train steps ... :  24%|██▍       | 24465/100000 [6:53:56<12:18:52,  1.70it/s]
Train steps ... :  24%|██▍       | 24466/100000 [6:53:57<12:18:40,  1.70it/s]
Train steps ... :  24%|██▍       | 24467/100000 [6:53:57<12:18:13,  1.71it/s]
Train steps ... :  24%|██▍       | 24468/100000 [6:53:58<12:18:38,  1.70it/s]
Train steps ... :  24%|██▍       | 24469/100000 [6:53:58<12:18:30,  1.70it/s]
Train steps ... :  24%|██▍       | 24470/100000 [6:53:59<12:18:22,  1.70it/s]
Train steps ... :  24%|██▍       | 24471/100000 [6:54:00<12:17:28,  1.71it/s]
Train steps ... :  24%|██▍       | 24472/100000 [6:54:00<12:16:33,  1.71it/s]
Train steps ... :  24%|██▍       | 24473/100000 [6:54:01<12:16:26,  1.71it/s]
Train steps ... :  24%|██▍       | 24474/100000 [6:54:01<12:17:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24475/100000 [6:54:02<12:17:11,  1.71it/s]Step... (24475 / 100000 | Loss: 1.1166203022003174, Learning Rate: 7.590452261306533e-05)
+
                                                                             
Step... (24475 / 100000 | Loss: 0.9053014516830444, Learning Rate: 7.590452261306533e-05)
+
Train steps ... :  24%|██▍       | 24475/100000 [6:54:02<12:17:11,  1.71it/s]
Train steps ... :  24%|██▍       | 24476/100000 [6:54:02<12:17:04,  1.71it/s]
Train steps ... :  24%|██▍       | 24477/100000 [6:54:03<12:16:03,  1.71it/s]
Train steps ... :  24%|██▍       | 24478/100000 [6:54:04<12:18:25,  1.70it/s]
Train steps ... :  24%|██▍       | 24479/100000 [6:54:04<12:19:03,  1.70it/s]
Train steps ... :  24%|██▍       | 24480/100000 [6:54:05<12:16:53,  1.71it/s]
Train steps ... :  24%|██▍       | 24481/100000 [6:54:05<12:16:42,  1.71it/s]
Train steps ... :  24%|██▍       | 24482/100000 [6:54:06<12:18:35,  1.70it/s]
Train steps ... :  24%|██▍       | 24483/100000 [6:54:07<12:17:25,  1.71it/s]
Train steps ... :  24%|██▍       | 24484/100000 [6:54:07<12:15:58,  1.71it/s]
Train steps ... :  24%|██▍       | 24485/100000 [6:54:08<12:16:47,  1.71it/s]
Train steps ... :  24%|██▍       | 24486/100000 [6:54:08<12:19:03,  1.70it/s]
Train steps ... :  24%|██▍       | 24487/100000 [6:54:09<12:16:05,  1.71it/s]
Train steps ... :  24%|██▍       | 24488/100000 [6:54:10<12:17:07,  1.71it/s]
Train steps ... :  24%|██▍       | 24489/100000 [6:54:10<12:16:50,  1.71it/s]
Train steps ... :  24%|██▍       | 24490/100000 [6:54:11<12:16:38,  1.71it/s]
Train steps ... :  24%|██▍       | 24491/100000 [6:54:11<12:18:34,  1.70it/s]
Train steps ... :  24%|██▍       | 24492/100000 [6:54:12<12:16:07,  1.71it/s]
Train steps ... :  24%|██▍       | 24493/100000 [6:54:12<12:16:12,  1.71it/s]
Train steps ... :  24%|██▍       | 24494/100000 [6:54:13<12:16:02,  1.71it/s]
Train steps ... :  24%|██▍       | 24495/100000 [6:54:14<12:17:13,  1.71it/s]
Train steps ... :  24%|██▍       | 24496/100000 [6:54:14<12:16:07,  1.71it/s]
Train steps ... :  24%|██▍       | 24497/100000 [6:54:15<12:17:01,  1.71it/s]
Train steps ... :  24%|██▍       | 24498/100000 [6:54:15<12:17:12,  1.71it/s]
Train steps ... :  24%|██▍       | 24499/100000 [6:54:16<12:16:08,  1.71it/s]
Train steps ... :  24%|██▍       | 24500/100000 [6:54:17<12:17:08,  1.71it/s]Step... (24500 / 100000 | Loss: 0.7941638231277466, Learning Rate: 7.587939698492463e-05)
+
                                                                             
Step... (24500 / 100000 | Loss: 0.9541068077087402, Learning Rate: 7.587939698492463e-05)
+
Train steps ... :  24%|██▍       | 24500/100000 [6:54:17<12:17:08,  1.71it/s]
Train steps ... :  25%|██▍       | 24501/100000 [6:54:17<12:17:46,  1.71it/s]
Train steps ... :  25%|██▍       | 24502/100000 [6:54:18<12:17:17,  1.71it/s]
Train steps ... :  25%|██▍       | 24503/100000 [6:54:18<12:16:55,  1.71it/s]
Train steps ... :  25%|██▍       | 24504/100000 [6:54:19<12:16:37,  1.71it/s]
Train steps ... :  25%|██▍       | 24505/100000 [6:54:19<12:16:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24506/100000 [6:54:20<12:16:59,  1.71it/s]
Train steps ... :  25%|██▍       | 24507/100000 [6:54:21<12:17:16,  1.71it/s]
Train steps ... :  25%|██▍       | 24508/100000 [6:54:21<12:16:59,  1.71it/s]
Train steps ... :  25%|██▍       | 24509/100000 [6:54:22<12:17:09,  1.71it/s]
Train steps ... :  25%|██▍       | 24510/100000 [6:54:22<12:19:54,  1.70it/s]
Train steps ... :  25%|██▍       | 24511/100000 [6:54:23<12:16:56,  1.71it/s]
Train steps ... :  25%|██▍       | 24512/100000 [6:54:24<12:16:38,  1.71it/s]
Train steps ... :  25%|██▍       | 24513/100000 [6:54:24<12:16:37,  1.71it/s]
Train steps ... :  25%|██▍       | 24514/100000 [6:54:25<12:15:47,  1.71it/s]
Train steps ... :  25%|██▍       | 24515/100000 [6:54:25<12:15:22,  1.71it/s]
Train steps ... :  25%|██▍       | 24516/100000 [6:54:26<12:15:17,  1.71it/s]
Train steps ... :  25%|██▍       | 24517/100000 [6:54:27<12:15:16,  1.71it/s]
Train steps ... :  25%|██▍       | 24518/100000 [6:54:27<12:16:00,  1.71it/s]
Train steps ... :  25%|██▍       | 24519/100000 [6:54:28<12:17:31,  1.71it/s]
Train steps ... :  25%|██▍       | 24520/100000 [6:54:28<12:16:35,  1.71it/s]
Train steps ... :  25%|██▍       | 24521/100000 [6:54:29<12:16:28,  1.71it/s]
Train steps ... :  25%|██▍       | 24522/100000 [6:54:29<12:16:36,  1.71it/s]
Train steps ... :  25%|██▍       | 24523/100000 [6:54:30<12:18:57,  1.70it/s]
Train steps ... :  25%|██▍       | 24524/100000 [6:54:31<12:16:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24525/100000 [6:54:31<12:16:00,  1.71it/s]Step... (24525 / 100000 | Loss: 0.8415974974632263, Learning Rate: 7.585427135678392e-05)
+
                                                                             
Step... (24525 / 100000 | Loss: 0.7013616561889648, Learning Rate: 7.585427135678392e-05)
+
Train steps ... :  25%|██▍       | 24525/100000 [6:54:32<12:16:00,  1.71it/s]
Train steps ... :  25%|██▍       | 24526/100000 [6:54:32<12:16:50,  1.71it/s]
Train steps ... :  25%|██▍       | 24527/100000 [6:54:32<12:16:03,  1.71it/s]
Train steps ... :  25%|██▍       | 24528/100000 [6:54:33<12:16:40,  1.71it/s]
Train steps ... :  25%|██▍       | 24529/100000 [6:54:34<12:15:43,  1.71it/s]
Train steps ... :  25%|██▍       | 24530/100000 [6:54:34<12:18:26,  1.70it/s]
Train steps ... :  25%|██▍       | 24531/100000 [6:54:35<12:15:39,  1.71it/s]
Train steps ... :  25%|██▍       | 24532/100000 [6:54:35<12:15:20,  1.71it/s]
Train steps ... :  25%|██▍       | 24533/100000 [6:54:36<12:17:24,  1.71it/s]
Train steps ... :  25%|██▍       | 24534/100000 [6:54:36<12:16:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24535/100000 [6:54:37<12:16:36,  1.71it/s]
Train steps ... :  25%|██▍       | 24536/100000 [6:54:38<12:16:23,  1.71it/s]
Train steps ... :  25%|██▍       | 24537/100000 [6:54:38<12:17:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24538/100000 [6:54:39<12:18:27,  1.70it/s]
Train steps ... :  25%|██▍       | 24539/100000 [6:54:39<12:15:26,  1.71it/s]
Train steps ... :  25%|██▍       | 24540/100000 [6:54:40<12:18:25,  1.70it/s]
Train steps ... :  25%|██▍       | 24541/100000 [6:54:41<12:18:06,  1.70it/s]
Train steps ... :  25%|██▍       | 24542/100000 [6:54:41<12:17:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24543/100000 [6:54:42<12:17:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24544/100000 [6:54:42<12:15:50,  1.71it/s]
Train steps ... :  25%|██▍       | 24545/100000 [6:54:43<12:15:36,  1.71it/s]
Train steps ... :  25%|██▍       | 24546/100000 [6:54:43<12:16:32,  1.71it/s]
Train steps ... :  25%|██▍       | 24547/100000 [6:54:44<12:15:25,  1.71it/s]
Train steps ... :  25%|██▍       | 24548/100000 [6:54:45<12:16:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24549/100000 [6:54:45<12:16:33,  1.71it/s]
Train steps ... :  25%|██▍       | 24550/100000 [6:54:46<12:15:50,  1.71it/s]Step... (24550 / 100000 | Loss: 0.8139214515686035, Learning Rate: 7.582914572864322e-05)
+
                                                                             
Step... (24550 / 100000 | Loss: 0.9838447570800781, Learning Rate: 7.582914572864322e-05)
+
Train steps ... :  25%|██▍       | 24550/100000 [6:54:46<12:15:50,  1.71it/s]
Train steps ... :  25%|██▍       | 24551/100000 [6:54:46<12:17:04,  1.71it/s]
Train steps ... :  25%|██▍       | 24552/100000 [6:54:47<12:18:32,  1.70it/s]
Train steps ... :  25%|██▍       | 24553/100000 [6:54:48<12:17:26,  1.71it/s]
Train steps ... :  25%|██▍       | 24554/100000 [6:54:48<12:17:36,  1.70it/s]
Train steps ... :  25%|██▍       | 24555/100000 [6:54:49<12:17:28,  1.71it/s]
Train steps ... :  25%|██▍       | 24556/100000 [6:54:49<12:18:07,  1.70it/s]
Train steps ... :  25%|██▍       | 24557/100000 [6:54:50<12:17:23,  1.71it/s]
Train steps ... :  25%|██▍       | 24558/100000 [6:54:51<12:18:15,  1.70it/s]
Train steps ... :  25%|██▍       | 24559/100000 [6:54:51<12:17:25,  1.71it/s]
Train steps ... :  25%|██▍       | 24560/100000 [6:54:52<12:18:05,  1.70it/s]
Train steps ... :  25%|██▍       | 24561/100000 [6:54:52<12:16:46,  1.71it/s]
Train steps ... :  25%|██▍       | 24562/100000 [6:54:53<12:18:56,  1.70it/s]
Train steps ... :  25%|██▍       | 24563/100000 [6:54:53<12:17:08,  1.71it/s]
Train steps ... :  25%|██▍       | 24564/100000 [6:54:54<12:16:38,  1.71it/s]
Train steps ... :  25%|██▍       | 24565/100000 [6:54:55<12:17:48,  1.70it/s]
Train steps ... :  25%|██▍       | 24566/100000 [6:54:55<12:17:45,  1.70it/s]
Train steps ... :  25%|██▍       | 24567/100000 [6:54:56<12:17:25,  1.70it/s]
Train steps ... :  25%|██▍       | 24568/100000 [6:54:56<12:17:13,  1.71it/s]
Train steps ... :  25%|██▍       | 24569/100000 [6:54:57<12:15:46,  1.71it/s]
Train steps ... :  25%|██▍       | 24570/100000 [6:54:58<12:17:38,  1.70it/s]
Train steps ... :  25%|██▍       | 24571/100000 [6:54:58<12:16:36,  1.71it/s]
Train steps ... :  25%|██▍       | 24572/100000 [6:54:59<12:15:37,  1.71it/s]
Train steps ... :  25%|██▍       | 24573/100000 [6:54:59<12:15:25,  1.71it/s]
Train steps ... :  25%|██▍       | 24574/100000 [6:55:00<12:14:36,  1.71it/s]
Train steps ... :  25%|██▍       | 24575/100000 [6:55:00<12:14:13,  1.71it/s]Step... (24575 / 100000 | Loss: 0.7746714353561401, Learning Rate: 7.580402010050252e-05)
+
                                                                             
Step... (24575 / 100000 | Loss: 0.7966964244842529, Learning Rate: 7.580402010050252e-05)
+
Train steps ... :  25%|██▍       | 24575/100000 [6:55:01<12:14:13,  1.71it/s]
Train steps ... :  25%|██▍       | 24576/100000 [6:55:01<12:15:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24577/100000 [6:55:02<12:16:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24578/100000 [6:55:02<12:15:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24579/100000 [6:55:03<12:14:41,  1.71it/s]
Train steps ... :  25%|██▍       | 24580/100000 [6:55:03<12:16:15,  1.71it/s]
Train steps ... :  25%|██▍       | 24581/100000 [6:55:04<12:18:01,  1.70it/s]
Train steps ... :  25%|██▍       | 24582/100000 [6:55:05<12:16:33,  1.71it/s]
Train steps ... :  25%|██▍       | 24583/100000 [6:55:05<12:20:13,  1.70it/s]
Train steps ... :  25%|██▍       | 24584/100000 [6:55:06<12:18:16,  1.70it/s]
Train steps ... :  25%|██▍       | 24585/100000 [6:55:06<12:18:25,  1.70it/s]
Train steps ... :  25%|██▍       | 24586/100000 [6:55:07<12:17:33,  1.70it/s]
Train steps ... :  25%|██▍       | 24587/100000 [6:55:08<12:20:28,  1.70it/s]
Train steps ... :  25%|██▍       | 24588/100000 [6:55:08<12:18:48,  1.70it/s]
Train steps ... :  25%|██▍       | 24589/100000 [6:55:09<12:19:31,  1.70it/s]
Train steps ... :  25%|██▍       | 24590/100000 [6:55:09<12:17:15,  1.70it/s]
Train steps ... :  25%|██▍       | 24591/100000 [6:55:10<12:19:01,  1.70it/s]
Train steps ... :  25%|██▍       | 24592/100000 [6:55:10<12:20:09,  1.70it/s]
Train steps ... :  25%|██▍       | 24593/100000 [6:55:11<12:17:50,  1.70it/s]
Train steps ... :  25%|██▍       | 24594/100000 [6:55:12<12:18:00,  1.70it/s]
Train steps ... :  25%|██▍       | 24595/100000 [6:55:12<12:17:33,  1.70it/s]
Train steps ... :  25%|██▍       | 24596/100000 [6:55:13<12:20:01,  1.70it/s]
Train steps ... :  25%|██▍       | 24597/100000 [6:55:13<12:18:15,  1.70it/s]
Train steps ... :  25%|██▍       | 24598/100000 [6:55:14<12:18:51,  1.70it/s]
Train steps ... :  25%|██▍       | 24599/100000 [6:55:15<12:16:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24600/100000 [6:55:15<12:17:30,  1.70it/s]Step... (24600 / 100000 | Loss: 0.707149088382721, Learning Rate: 7.577889447236181e-05)
+
                                                                             
Step... (24600 / 100000 | Loss: 0.8112066984176636, Learning Rate: 7.577889447236181e-05)
+
Train steps ... :  25%|██▍       | 24600/100000 [6:55:15<12:17:30,  1.70it/s]
Train steps ... :  25%|██▍       | 24601/100000 [6:55:16<12:20:11,  1.70it/s]
Train steps ... :  25%|██▍       | 24602/100000 [6:55:16<12:18:04,  1.70it/s]
Train steps ... :  25%|██▍       | 24603/100000 [6:55:17<12:17:21,  1.70it/s]
Train steps ... :  25%|██▍       | 24604/100000 [6:55:18<12:17:44,  1.70it/s]
Train steps ... :  25%|██▍       | 24605/100000 [6:55:18<12:17:25,  1.70it/s]
Train steps ... :  25%|██▍       | 24606/100000 [6:55:19<12:18:40,  1.70it/s]
Train steps ... :  25%|██▍       | 24607/100000 [6:55:19<12:17:43,  1.70it/s]
Train steps ... :  25%|██▍       | 24608/100000 [6:55:20<12:18:34,  1.70it/s]
Train steps ... :  25%|██▍       | 24609/100000 [6:55:20<12:17:39,  1.70it/s]
Train steps ... :  25%|██▍       | 24610/100000 [6:55:21<12:18:21,  1.70it/s]
Train steps ... :  25%|██▍       | 24611/100000 [6:55:22<12:16:56,  1.71it/s]
Train steps ... :  25%|██▍       | 24612/100000 [6:55:22<12:16:19,  1.71it/s]
Train steps ... :  25%|██▍       | 24613/100000 [6:55:23<12:17:39,  1.70it/s]
Train steps ... :  25%|██▍       | 24614/100000 [6:55:23<12:17:10,  1.70it/s]
Train steps ... :  25%|██▍       | 24615/100000 [6:55:24<12:17:52,  1.70it/s]
Train steps ... :  25%|██▍       | 24616/100000 [6:55:25<12:17:58,  1.70it/s]
Train steps ... :  25%|██▍       | 24617/100000 [6:55:25<12:15:56,  1.71it/s]
Train steps ... :  25%|██▍       | 24618/100000 [6:55:26<12:18:17,  1.70it/s]
Train steps ... :  25%|██▍       | 24619/100000 [6:55:26<12:15:32,  1.71it/s]
Train steps ... :  25%|██▍       | 24620/100000 [6:55:27<12:15:36,  1.71it/s]
Train steps ... :  25%|██▍       | 24621/100000 [6:55:27<12:16:55,  1.70it/s]
Train steps ... :  25%|██▍       | 24622/100000 [6:55:28<12:16:51,  1.70it/s]
Train steps ... :  25%|██▍       | 24623/100000 [6:55:29<12:15:53,  1.71it/s]
Train steps ... :  25%|██▍       | 24624/100000 [6:55:29<12:15:49,  1.71it/s]
Train steps ... :  25%|██▍       | 24625/100000 [6:55:30<12:16:34,  1.71it/s]Step... (24625 / 100000 | Loss: 1.08270263671875, Learning Rate: 7.575376884422111e-05)
+
                                                                             
Step... (24625 / 100000 | Loss: 1.0180010795593262, Learning Rate: 7.575376884422111e-05)
+
Train steps ... :  25%|██▍       | 24625/100000 [6:55:30<12:16:34,  1.71it/s]
Train steps ... :  25%|██▍       | 24626/100000 [6:55:30<12:16:57,  1.70it/s]
Train steps ... :  25%|██▍       | 24627/100000 [6:55:31<12:16:13,  1.71it/s]
Train steps ... :  25%|██▍       | 24628/100000 [6:55:32<12:16:50,  1.70it/s]
Train steps ... :  25%|██▍       | 24629/100000 [6:55:32<12:15:51,  1.71it/s]
Train steps ... :  25%|██▍       | 24630/100000 [6:55:33<12:17:21,  1.70it/s]
Train steps ... :  25%|██▍       | 24631/100000 [6:55:33<12:17:30,  1.70it/s]
Train steps ... :  25%|██▍       | 24632/100000 [6:55:34<12:17:22,  1.70it/s]
Train steps ... :  25%|██▍       | 24633/100000 [6:55:35<12:16:38,  1.71it/s]
Train steps ... :  25%|██▍       | 24634/100000 [6:55:35<12:17:32,  1.70it/s]
Train steps ... :  25%|██▍       | 24635/100000 [6:55:36<12:16:08,  1.71it/s]
Train steps ... :  25%|██▍       | 24636/100000 [6:55:36<12:15:32,  1.71it/s]
Train steps ... :  25%|██▍       | 24637/100000 [6:55:37<12:17:22,  1.70it/s]
Train steps ... :  25%|██▍       | 24638/100000 [6:55:37<12:15:22,  1.71it/s]
Train steps ... :  25%|██▍       | 24639/100000 [6:55:38<12:15:24,  1.71it/s]
Train steps ... :  25%|██▍       | 24640/100000 [6:55:39<12:15:16,  1.71it/s]
Train steps ... :  25%|██▍       | 24641/100000 [6:55:39<12:14:46,  1.71it/s]
Train steps ... :  25%|██▍       | 24642/100000 [6:55:40<12:15:15,  1.71it/s]
Train steps ... :  25%|██▍       | 24643/100000 [6:55:40<12:14:17,  1.71it/s]
Train steps ... :  25%|██▍       | 24644/100000 [6:55:41<12:16:41,  1.70it/s]
Train steps ... :  25%|██▍       | 24645/100000 [6:55:42<12:15:56,  1.71it/s]
Train steps ... :  25%|██▍       | 24646/100000 [6:55:42<12:15:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24647/100000 [6:55:43<12:16:07,  1.71it/s]
Train steps ... :  25%|██▍       | 24648/100000 [6:55:43<12:15:34,  1.71it/s]
Train steps ... :  25%|██▍       | 24649/100000 [6:55:44<12:14:53,  1.71it/s]
Train steps ... :  25%|██▍       | 24650/100000 [6:55:44<12:15:39,  1.71it/s]Step... (24650 / 100000 | Loss: 1.1575584411621094, Learning Rate: 7.57286432160804e-05)
+
                                                                             
Step... (24650 / 100000 | Loss: 1.2523276805877686, Learning Rate: 7.57286432160804e-05)
+
Train steps ... :  25%|██▍       | 24650/100000 [6:55:45<12:15:39,  1.71it/s]
Train steps ... :  25%|██▍       | 24651/100000 [6:55:45<12:16:14,  1.71it/s]
Train steps ... :  25%|██▍       | 24652/100000 [6:55:46<12:15:03,  1.71it/s]
Train steps ... :  25%|██▍       | 24653/100000 [6:55:46<12:15:06,  1.71it/s]
Train steps ... :  25%|██▍       | 24654/100000 [6:55:47<12:17:13,  1.70it/s]
Train steps ... :  25%|██▍       | 24655/100000 [6:55:47<12:14:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24656/100000 [6:55:48<12:14:56,  1.71it/s]
Train steps ... :  25%|██▍       | 24657/100000 [6:55:49<12:14:56,  1.71it/s]
Train steps ... :  25%|██▍       | 24658/100000 [6:55:49<12:17:38,  1.70it/s]
Train steps ... :  25%|██▍       | 24659/100000 [6:55:50<12:16:05,  1.71it/s]
Train steps ... :  25%|██▍       | 24660/100000 [6:55:50<12:16:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24661/100000 [6:55:51<12:15:01,  1.71it/s]
Train steps ... :  25%|██▍       | 24662/100000 [6:55:52<12:16:32,  1.70it/s]
Train steps ... :  25%|██▍       | 24663/100000 [6:55:52<12:16:32,  1.70it/s]
Train steps ... :  25%|██▍       | 24664/100000 [6:55:53<12:15:59,  1.71it/s]
Train steps ... :  25%|██▍       | 24665/100000 [6:55:53<12:16:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24666/100000 [6:55:54<12:16:19,  1.71it/s]
Train steps ... :  25%|██▍       | 24667/100000 [6:55:54<12:15:19,  1.71it/s]
Train steps ... :  25%|██▍       | 24668/100000 [6:55:55<12:15:24,  1.71it/s]
Train steps ... :  25%|██▍       | 24669/100000 [6:55:56<12:14:56,  1.71it/s]
Train steps ... :  25%|██▍       | 24670/100000 [6:55:56<12:14:30,  1.71it/s]
Train steps ... :  25%|██▍       | 24671/100000 [6:55:57<12:13:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24672/100000 [6:55:57<12:14:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24673/100000 [6:55:58<12:14:59,  1.71it/s]
Train steps ... :  25%|██▍       | 24674/100000 [6:55:59<12:13:05,  1.71it/s]
Train steps ... :  25%|██▍       | 24675/100000 [6:55:59<12:13:12,  1.71it/s]Step... (24675 / 100000 | Loss: 0.8021987676620483, Learning Rate: 7.57035175879397e-05)
+
                                                                             
Step... (24675 / 100000 | Loss: 0.8983321189880371, Learning Rate: 7.57035175879397e-05)
+
Train steps ... :  25%|██▍       | 24675/100000 [6:55:59<12:13:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24676/100000 [6:56:00<12:15:52,  1.71it/s]
Train steps ... :  25%|██▍       | 24677/100000 [6:56:00<12:15:43,  1.71it/s]
Train steps ... :  25%|██▍       | 24678/100000 [6:56:01<12:15:24,  1.71it/s]
Train steps ... :  25%|██▍       | 24679/100000 [6:56:01<12:15:46,  1.71it/s]
Train steps ... :  25%|██▍       | 24680/100000 [6:56:02<12:15:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24681/100000 [6:56:03<12:15:53,  1.71it/s]
Train steps ... :  25%|██▍       | 24682/100000 [6:56:03<12:15:33,  1.71it/s]
Train steps ... :  25%|██▍       | 24683/100000 [6:56:04<12:15:25,  1.71it/s]
Train steps ... :  25%|██▍       | 24684/100000 [6:56:04<12:15:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24685/100000 [6:56:05<12:14:28,  1.71it/s]
Train steps ... :  25%|██▍       | 24686/100000 [6:56:06<12:16:23,  1.70it/s]
Train steps ... :  25%|██▍       | 24687/100000 [6:56:06<12:14:46,  1.71it/s]
Train steps ... :  25%|██▍       | 24688/100000 [6:56:07<12:15:26,  1.71it/s]
Train steps ... :  25%|██▍       | 24689/100000 [6:56:07<12:15:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24690/100000 [6:56:08<12:16:40,  1.70it/s]
Train steps ... :  25%|██▍       | 24691/100000 [6:56:09<12:15:36,  1.71it/s]
Train steps ... :  25%|██▍       | 24692/100000 [6:56:09<12:15:11,  1.71it/s]
Train steps ... :  25%|██▍       | 24693/100000 [6:56:10<12:14:57,  1.71it/s]
Train steps ... :  25%|██▍       | 24694/100000 [6:56:10<12:14:41,  1.71it/s]
Train steps ... :  25%|██▍       | 24695/100000 [6:56:11<12:14:39,  1.71it/s]
Train steps ... :  25%|██▍       | 24696/100000 [6:56:11<12:14:43,  1.71it/s]
Train steps ... :  25%|██▍       | 24697/100000 [6:56:12<12:14:59,  1.71it/s]
Train steps ... :  25%|██▍       | 24698/100000 [6:56:13<12:15:17,  1.71it/s]
Train steps ... :  25%|██▍       | 24699/100000 [6:56:13<12:14:59,  1.71it/s]
Train steps ... :  25%|██▍       | 24700/100000 [6:56:14<12:14:54,  1.71it/s]Step... (24700 / 100000 | Loss: 0.8496579527854919, Learning Rate: 7.5678391959799e-05)
+
                                                                             
Step... (24700 / 100000 | Loss: 0.9212912321090698, Learning Rate: 7.5678391959799e-05)
+
Train steps ... :  25%|██▍       | 24700/100000 [6:56:14<12:14:54,  1.71it/s]
Train steps ... :  25%|██▍       | 24701/100000 [6:56:14<12:16:38,  1.70it/s]
Train steps ... :  25%|██▍       | 24702/100000 [6:56:15<12:14:27,  1.71it/s]
Train steps ... :  25%|██▍       | 24703/100000 [6:56:16<12:15:25,  1.71it/s]
Train steps ... :  25%|██▍       | 24704/100000 [6:56:16<12:14:22,  1.71it/s]
Train steps ... :  25%|██▍       | 24705/100000 [6:56:17<12:14:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24706/100000 [6:56:17<12:14:35,  1.71it/s]
Train steps ... :  25%|██▍       | 24707/100000 [6:56:18<12:14:06,  1.71it/s]
Train steps ... :  25%|██▍       | 24708/100000 [6:56:18<12:13:34,  1.71it/s]
Train steps ... :  25%|██▍       | 24709/100000 [6:56:19<12:14:56,  1.71it/s]
Train steps ... :  25%|██▍       | 24710/100000 [6:56:20<12:14:27,  1.71it/s]
Train steps ... :  25%|██▍       | 24711/100000 [6:56:20<12:14:55,  1.71it/s]
Train steps ... :  25%|██▍       | 24712/100000 [6:56:21<12:14:21,  1.71it/s]
Train steps ... :  25%|██▍       | 24713/100000 [6:56:21<12:14:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24714/100000 [6:56:22<12:15:11,  1.71it/s]
Train steps ... :  25%|██▍       | 24715/100000 [6:56:23<12:15:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24716/100000 [6:56:23<12:14:31,  1.71it/s]
Train steps ... :  25%|██▍       | 24717/100000 [6:56:24<12:14:23,  1.71it/s]
Train steps ... :  25%|██▍       | 24718/100000 [6:56:24<12:16:16,  1.70it/s]
Train steps ... :  25%|██▍       | 24719/100000 [6:56:25<12:13:53,  1.71it/s]
Train steps ... :  25%|██▍       | 24720/100000 [6:56:25<12:13:32,  1.71it/s]
Train steps ... :  25%|██▍       | 24721/100000 [6:56:26<12:14:19,  1.71it/s]
Train steps ... :  25%|██▍       | 24722/100000 [6:56:27<12:15:59,  1.70it/s]
Train steps ... :  25%|██▍       | 24723/100000 [6:56:27<12:15:46,  1.71it/s]
Train steps ... :  25%|██▍       | 24724/100000 [6:56:28<12:15:50,  1.70it/s]
Train steps ... :  25%|██▍       | 24725/100000 [6:56:28<12:14:18,  1.71it/s]Step... (24725 / 100000 | Loss: 0.9627296924591064, Learning Rate: 7.56532663316583e-05)
+
                                                                             
Step... (24725 / 100000 | Loss: 1.2380484342575073, Learning Rate: 7.56532663316583e-05)
+
Train steps ... :  25%|██▍       | 24725/100000 [6:56:29<12:14:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24726/100000 [6:56:29<12:15:03,  1.71it/s]
Train steps ... :  25%|██▍       | 24727/100000 [6:56:30<12:14:26,  1.71it/s]
Train steps ... :  25%|██▍       | 24728/100000 [6:56:30<12:14:41,  1.71it/s]
Train steps ... :  25%|██▍       | 24729/100000 [6:56:31<12:14:49,  1.71it/s]
Train steps ... :  25%|██▍       | 24730/100000 [6:56:31<12:13:49,  1.71it/s]
Train steps ... :  25%|██▍       | 24731/100000 [6:56:32<12:14:16,  1.71it/s]
Train steps ... :  25%|██▍       | 24732/100000 [6:56:33<12:13:37,  1.71it/s]
Train steps ... :  25%|██▍       | 24733/100000 [6:56:33<12:14:25,  1.71it/s]
Train steps ... :  25%|██▍       | 24734/100000 [6:56:34<12:14:28,  1.71it/s]
Train steps ... :  25%|██▍       | 24735/100000 [6:56:34<12:14:29,  1.71it/s]
Train steps ... :  25%|██▍       | 24736/100000 [6:56:35<12:14:43,  1.71it/s]
Train steps ... :  25%|██▍       | 24737/100000 [6:56:35<12:13:48,  1.71it/s]
Train steps ... :  25%|██▍       | 24738/100000 [6:56:36<12:13:50,  1.71it/s]
Train steps ... :  25%|██▍       | 24739/100000 [6:56:37<12:14:14,  1.71it/s]
Train steps ... :  25%|██▍       | 24740/100000 [6:56:37<12:14:08,  1.71it/s]
Train steps ... :  25%|██▍       | 24741/100000 [6:56:38<12:14:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24742/100000 [6:56:38<12:14:07,  1.71it/s]
Train steps ... :  25%|██▍       | 24743/100000 [6:56:39<12:13:41,  1.71it/s]
Train steps ... :  25%|██▍       | 24744/100000 [6:56:40<12:15:54,  1.70it/s]
Train steps ... :  25%|██▍       | 24745/100000 [6:56:40<12:15:17,  1.71it/s]
Train steps ... :  25%|██▍       | 24746/100000 [6:56:41<12:15:16,  1.71it/s]
Train steps ... :  25%|██▍       | 24747/100000 [6:56:41<12:14:25,  1.71it/s]
Train steps ... :  25%|██▍       | 24748/100000 [6:56:42<12:14:37,  1.71it/s]
Train steps ... :  25%|██▍       | 24749/100000 [6:56:42<12:14:31,  1.71it/s]
Train steps ... :  25%|██▍       | 24750/100000 [6:56:43<12:16:13,  1.70it/s]Step... (24750 / 100000 | Loss: 1.5566380023956299, Learning Rate: 7.562814070351759e-05)
+
                                                                             
Step... (24750 / 100000 | Loss: 0.7694822549819946, Learning Rate: 7.562814070351759e-05)
+
Train steps ... :  25%|██▍       | 24750/100000 [6:56:43<12:16:13,  1.70it/s]
Train steps ... :  25%|██▍       | 24751/100000 [6:56:44<12:14:25,  1.71it/s]
Train steps ... :  25%|██▍       | 24752/100000 [6:56:44<12:14:14,  1.71it/s]
Train steps ... :  25%|██▍       | 24753/100000 [6:56:45<12:14:07,  1.71it/s]
Train steps ... :  25%|██▍       | 24754/100000 [6:56:45<12:13:48,  1.71it/s]
Train steps ... :  25%|██▍       | 24755/100000 [6:56:46<12:13:36,  1.71it/s]
Train steps ... :  25%|██▍       | 24756/100000 [6:56:47<12:13:46,  1.71it/s]
Train steps ... :  25%|██▍       | 24757/100000 [6:56:47<12:12:52,  1.71it/s]
Train steps ... :  25%|██▍       | 24758/100000 [6:56:48<12:13:56,  1.71it/s]
Train steps ... :  25%|██▍       | 24759/100000 [6:56:48<12:14:53,  1.71it/s]
Train steps ... :  25%|██▍       | 24760/100000 [6:56:49<12:15:30,  1.70it/s]
Train steps ... :  25%|██▍       | 24761/100000 [6:56:49<12:14:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24762/100000 [6:56:50<12:15:15,  1.71it/s]
Train steps ... :  25%|██▍       | 24763/100000 [6:56:51<12:14:34,  1.71it/s]
Train steps ... :  25%|██▍       | 24764/100000 [6:56:51<12:15:42,  1.70it/s]
Train steps ... :  25%|██▍       | 24765/100000 [6:56:52<12:15:38,  1.70it/s]
Train steps ... :  25%|██▍       | 24766/100000 [6:56:52<12:14:51,  1.71it/s]
Train steps ... :  25%|██▍       | 24767/100000 [6:56:53<12:14:39,  1.71it/s]
Train steps ... :  25%|██▍       | 24768/100000 [6:56:54<12:14:24,  1.71it/s]
Train steps ... :  25%|██▍       | 24769/100000 [6:56:54<12:13:38,  1.71it/s]
Train steps ... :  25%|██▍       | 24770/100000 [6:56:55<12:15:39,  1.70it/s]
Train steps ... :  25%|██▍       | 24771/100000 [6:56:55<12:16:28,  1.70it/s]
Train steps ... :  25%|██▍       | 24772/100000 [6:56:56<12:15:09,  1.71it/s]
Train steps ... :  25%|██▍       | 24773/100000 [6:56:57<12:16:09,  1.70it/s]
Train steps ... :  25%|██▍       | 24774/100000 [6:56:57<12:14:52,  1.71it/s]
Train steps ... :  25%|██▍       | 24775/100000 [6:56:58<12:14:29,  1.71it/s]Step... (24775 / 100000 | Loss: 1.5649998188018799, Learning Rate: 7.560301507537689e-05)
+
                                                                             
Step... (24775 / 100000 | Loss: 0.786985456943512, Learning Rate: 7.560301507537689e-05)
+
Train steps ... :  25%|██▍       | 24775/100000 [6:56:58<12:14:29,  1.71it/s]
Train steps ... :  25%|██▍       | 24776/100000 [6:56:58<12:15:13,  1.71it/s]
Train steps ... :  25%|██▍       | 24777/100000 [6:56:59<12:15:35,  1.70it/s]
Train steps ... :  25%|██▍       | 24778/100000 [6:56:59<12:14:47,  1.71it/s]
Train steps ... :  25%|██▍       | 24779/100000 [6:57:00<12:16:41,  1.70it/s]
Train steps ... :  25%|██▍       | 24780/100000 [6:57:01<12:15:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24781/100000 [6:57:01<12:15:37,  1.70it/s]
Train steps ... :  25%|██▍       | 24782/100000 [6:57:02<12:15:19,  1.70it/s]
Train steps ... :  25%|██▍       | 24783/100000 [6:57:02<12:16:24,  1.70it/s]
Train steps ... :  25%|██▍       | 24784/100000 [6:57:03<12:16:28,  1.70it/s]
Train steps ... :  25%|██▍       | 24785/100000 [6:57:04<12:16:18,  1.70it/s]
Train steps ... :  25%|██▍       | 24786/100000 [6:57:04<12:15:06,  1.71it/s]
Train steps ... :  25%|██▍       | 24787/100000 [6:57:05<12:16:18,  1.70it/s]
Train steps ... :  25%|██▍       | 24788/100000 [6:57:05<12:15:23,  1.70it/s]
Train steps ... :  25%|██▍       | 24789/100000 [6:57:06<12:14:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24790/100000 [6:57:07<12:14:04,  1.71it/s]
Train steps ... :  25%|██▍       | 24791/100000 [6:57:07<12:13:39,  1.71it/s]
Train steps ... :  25%|██▍       | 24792/100000 [6:57:08<12:12:36,  1.71it/s]
Train steps ... :  25%|██▍       | 24793/100000 [6:57:08<12:13:14,  1.71it/s]
Train steps ... :  25%|██▍       | 24794/100000 [6:57:09<12:14:06,  1.71it/s]
Train steps ... :  25%|██▍       | 24795/100000 [6:57:09<12:13:24,  1.71it/s]
Train steps ... :  25%|██▍       | 24796/100000 [6:57:10<12:13:15,  1.71it/s]
Train steps ... :  25%|██▍       | 24797/100000 [6:57:11<12:14:35,  1.71it/s]
Train steps ... :  25%|██▍       | 24798/100000 [6:57:11<12:14:08,  1.71it/s]
Train steps ... :  25%|██▍       | 24799/100000 [6:57:12<12:13:40,  1.71it/s]
Train steps ... :  25%|██▍       | 24800/100000 [6:57:12<12:13:40,  1.71it/s]Step... (24800 / 100000 | Loss: 0.8843810558319092, Learning Rate: 7.557788944723618e-05)
+
                                                                             
Step... (24800 / 100000 | Loss: 0.9009883999824524, Learning Rate: 7.557788944723618e-05)
+
Train steps ... :  25%|██▍       | 24800/100000 [6:57:13<12:13:40,  1.71it/s]
Train steps ... :  25%|██▍       | 24801/100000 [6:57:13<12:14:09,  1.71it/s]
Train steps ... :  25%|██▍       | 24802/100000 [6:57:14<12:13:34,  1.71it/s]
Train steps ... :  25%|██▍       | 24803/100000 [6:57:14<12:15:52,  1.70it/s]
Train steps ... :  25%|██▍       | 24804/100000 [6:57:15<12:17:04,  1.70it/s]
Train steps ... :  25%|██▍       | 24805/100000 [6:57:15<12:14:59,  1.71it/s]
Train steps ... :  25%|██▍       | 24806/100000 [6:57:16<12:13:51,  1.71it/s]
Train steps ... :  25%|██▍       | 24807/100000 [6:57:16<12:13:15,  1.71it/s]
Train steps ... :  25%|██▍       | 24808/100000 [6:57:17<12:13:21,  1.71it/s]
Train steps ... :  25%|██▍       | 24809/100000 [6:57:18<12:13:07,  1.71it/s]
Train steps ... :  25%|██▍       | 24810/100000 [6:57:18<12:13:24,  1.71it/s]
Train steps ... :  25%|██▍       | 24811/100000 [6:57:19<12:13:17,  1.71it/s]
Train steps ... :  25%|██▍       | 24812/100000 [6:57:19<12:13:44,  1.71it/s]
Train steps ... :  25%|██▍       | 24813/100000 [6:57:20<12:14:19,  1.71it/s]
Train steps ... :  25%|██▍       | 24814/100000 [6:57:21<12:13:55,  1.71it/s]
Train steps ... :  25%|██▍       | 24815/100000 [6:57:21<12:13:23,  1.71it/s]
Train steps ... :  25%|██▍       | 24816/100000 [6:57:22<12:14:15,  1.71it/s]
Train steps ... :  25%|██▍       | 24817/100000 [6:57:22<12:13:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24818/100000 [6:57:23<12:14:31,  1.71it/s]
Train steps ... :  25%|██▍       | 24819/100000 [6:57:23<12:13:13,  1.71it/s]
Train steps ... :  25%|██▍       | 24820/100000 [6:57:24<12:13:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24821/100000 [6:57:25<12:11:46,  1.71it/s]
Train steps ... :  25%|██▍       | 24822/100000 [6:57:25<12:11:50,  1.71it/s]
Train steps ... :  25%|██▍       | 24823/100000 [6:57:26<12:15:57,  1.70it/s]
Train steps ... :  25%|██▍       | 24824/100000 [6:57:26<12:13:14,  1.71it/s]
Train steps ... :  25%|██▍       | 24825/100000 [6:57:27<12:13:53,  1.71it/s]Step... (24825 / 100000 | Loss: 0.8083592057228088, Learning Rate: 7.555276381909548e-05)
+
                                                                             
Step... (24825 / 100000 | Loss: 1.0572986602783203, Learning Rate: 7.555276381909548e-05)
+
Train steps ... :  25%|██▍       | 24825/100000 [6:57:27<12:13:53,  1.71it/s]
Train steps ... :  25%|██▍       | 24826/100000 [6:57:28<12:13:39,  1.71it/s]
Train steps ... :  25%|██▍       | 24827/100000 [6:57:28<12:14:32,  1.71it/s]
Train steps ... :  25%|██▍       | 24828/100000 [6:57:29<12:13:41,  1.71it/s]
Train steps ... :  25%|██▍       | 24829/100000 [6:57:29<12:13:34,  1.71it/s]
Train steps ... :  25%|██▍       | 24830/100000 [6:57:30<12:13:11,  1.71it/s]
Train steps ... :  25%|██▍       | 24831/100000 [6:57:31<12:13:23,  1.71it/s]
Train steps ... :  25%|██▍       | 24832/100000 [6:57:31<12:14:03,  1.71it/s]
Train steps ... :  25%|██▍       | 24833/100000 [6:57:32<12:13:50,  1.71it/s]
Train steps ... :  25%|██▍       | 24834/100000 [6:57:32<12:13:35,  1.71it/s]
Train steps ... :  25%|██▍       | 24835/100000 [6:57:33<12:14:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24836/100000 [6:57:33<12:14:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24837/100000 [6:57:34<12:14:39,  1.71it/s]
Train steps ... :  25%|██▍       | 24838/100000 [6:57:35<12:13:34,  1.71it/s]
Train steps ... :  25%|██▍       | 24839/100000 [6:57:35<12:14:04,  1.71it/s]
Train steps ... :  25%|██▍       | 24840/100000 [6:57:36<12:14:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24841/100000 [6:57:36<12:15:14,  1.70it/s]
Train steps ... :  25%|██▍       | 24842/100000 [6:57:37<12:15:51,  1.70it/s]
Train steps ... :  25%|██▍       | 24843/100000 [6:57:38<12:14:57,  1.70it/s]
Train steps ... :  25%|██▍       | 24844/100000 [6:57:38<12:15:16,  1.70it/s]
Train steps ... :  25%|██▍       | 24845/100000 [6:57:39<12:14:54,  1.70it/s]
Train steps ... :  25%|██▍       | 24846/100000 [6:57:39<12:14:05,  1.71it/s]
Train steps ... :  25%|██▍       | 24847/100000 [6:57:40<12:14:21,  1.71it/s]
Train steps ... :  25%|██▍       | 24848/100000 [6:57:40<12:14:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24849/100000 [6:57:41<12:14:29,  1.71it/s]
Train steps ... :  25%|██▍       | 24850/100000 [6:57:42<12:15:40,  1.70it/s]Step... (24850 / 100000 | Loss: 0.8717447519302368, Learning Rate: 7.552763819095478e-05)
+
                                                                             
Step... (24850 / 100000 | Loss: 0.9052634239196777, Learning Rate: 7.552763819095478e-05)
+
Train steps ... :  25%|██▍       | 24850/100000 [6:57:42<12:15:40,  1.70it/s]
Train steps ... :  25%|██▍       | 24851/100000 [6:57:42<12:15:39,  1.70it/s]
Train steps ... :  25%|██▍       | 24852/100000 [6:57:43<12:15:14,  1.70it/s]
Train steps ... :  25%|██▍       | 24853/100000 [6:57:43<12:13:34,  1.71it/s]
Train steps ... :  25%|██▍       | 24854/100000 [6:57:44<12:13:24,  1.71it/s]
Train steps ... :  25%|██▍       | 24855/100000 [6:57:45<12:13:58,  1.71it/s]
Train steps ... :  25%|██▍       | 24856/100000 [6:57:45<12:13:53,  1.71it/s]
Train steps ... :  25%|██▍       | 24857/100000 [6:57:46<12:15:20,  1.70it/s]
Train steps ... :  25%|██▍       | 24858/100000 [6:57:46<12:15:01,  1.70it/s]
Train steps ... :  25%|██▍       | 24859/100000 [6:57:47<12:13:31,  1.71it/s]
Train steps ... :  25%|██▍       | 24860/100000 [6:57:48<12:14:30,  1.70it/s]
Train steps ... :  25%|██▍       | 24861/100000 [6:57:48<12:14:17,  1.71it/s]
Train steps ... :  25%|██▍       | 24862/100000 [6:57:49<12:13:33,  1.71it/s]
Train steps ... :  25%|██▍       | 24863/100000 [6:57:49<12:13:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24864/100000 [6:57:50<12:13:14,  1.71it/s]
Train steps ... :  25%|██▍       | 24865/100000 [6:57:50<12:13:49,  1.71it/s]
Train steps ... :  25%|██▍       | 24866/100000 [6:57:51<12:13:37,  1.71it/s]
Train steps ... :  25%|██▍       | 24867/100000 [6:57:52<12:16:10,  1.70it/s]
Train steps ... :  25%|██▍       | 24868/100000 [6:57:52<12:15:13,  1.70it/s]
Train steps ... :  25%|██▍       | 24869/100000 [6:57:53<12:14:29,  1.70it/s]
Train steps ... :  25%|██▍       | 24870/100000 [6:57:53<12:14:16,  1.71it/s]
Train steps ... :  25%|██▍       | 24871/100000 [6:57:54<12:15:43,  1.70it/s]
Train steps ... :  25%|██▍       | 24872/100000 [6:57:55<12:17:08,  1.70it/s]
Train steps ... :  25%|██▍       | 24873/100000 [6:57:55<12:14:46,  1.70it/s]
Train steps ... :  25%|██▍       | 24874/100000 [6:57:56<12:15:01,  1.70it/s]
Train steps ... :  25%|██▍       | 24875/100000 [6:57:56<12:14:03,  1.71it/s]Step... (24875 / 100000 | Loss: 1.0123485326766968, Learning Rate: 7.550251256281407e-05)
+
                                                                             
Step... (24875 / 100000 | Loss: 1.0152063369750977, Learning Rate: 7.550251256281407e-05)
+
Train steps ... :  25%|██▍       | 24875/100000 [6:57:57<12:14:03,  1.71it/s]
Train steps ... :  25%|██▍       | 24876/100000 [6:57:57<12:13:30,  1.71it/s]
Train steps ... :  25%|██▍       | 24877/100000 [6:57:57<12:13:25,  1.71it/s]
Train steps ... :  25%|██▍       | 24878/100000 [6:57:58<12:13:30,  1.71it/s]
Train steps ... :  25%|██▍       | 24879/100000 [6:57:59<12:12:19,  1.71it/s]
Train steps ... :  25%|██▍       | 24880/100000 [6:57:59<12:12:48,  1.71it/s]
Train steps ... :  25%|██▍       | 24881/100000 [6:58:00<12:14:03,  1.71it/s]
Train steps ... :  25%|██▍       | 24882/100000 [6:58:00<12:13:22,  1.71it/s]
Train steps ... :  25%|██▍       | 24883/100000 [6:58:01<12:14:04,  1.71it/s]
Train steps ... :  25%|██▍       | 24884/100000 [6:58:02<12:12:47,  1.71it/s]
Train steps ... :  25%|██▍       | 24885/100000 [6:58:02<12:13:13,  1.71it/s]
Train steps ... :  25%|██▍       | 24886/100000 [6:58:03<12:13:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24887/100000 [6:58:03<12:12:49,  1.71it/s]
Train steps ... :  25%|██▍       | 24888/100000 [6:58:04<12:14:45,  1.70it/s]
Train steps ... :  25%|██▍       | 24889/100000 [6:58:05<12:13:50,  1.71it/s]
Train steps ... :  25%|██▍       | 24890/100000 [6:58:05<12:14:24,  1.70it/s]
Train steps ... :  25%|██▍       | 24891/100000 [6:58:06<12:13:13,  1.71it/s]
Train steps ... :  25%|██▍       | 24892/100000 [6:58:06<12:14:16,  1.70it/s]
Train steps ... :  25%|██▍       | 24893/100000 [6:58:07<12:14:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24894/100000 [6:58:07<12:14:16,  1.70it/s]
Train steps ... :  25%|██▍       | 24895/100000 [6:58:08<12:13:29,  1.71it/s]
Train steps ... :  25%|██▍       | 24896/100000 [6:58:09<12:13:30,  1.71it/s]
Train steps ... :  25%|██▍       | 24897/100000 [6:58:09<12:12:57,  1.71it/s]
Train steps ... :  25%|██▍       | 24898/100000 [6:58:10<12:12:34,  1.71it/s]
Train steps ... :  25%|██▍       | 24899/100000 [6:58:10<12:11:55,  1.71it/s]
Train steps ... :  25%|██▍       | 24900/100000 [6:58:11<12:12:07,  1.71it/s]Step... (24900 / 100000 | Loss: 0.7811367511749268, Learning Rate: 7.547738693467337e-05)
+
                                                                             
Step... (24900 / 100000 | Loss: 0.6935492753982544, Learning Rate: 7.547738693467337e-05)
+
Train steps ... :  25%|██▍       | 24900/100000 [6:58:11<12:12:07,  1.71it/s]
Train steps ... :  25%|██▍       | 24901/100000 [6:58:12<12:12:44,  1.71it/s]
Train steps ... :  25%|██▍       | 24902/100000 [6:58:12<12:13:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24903/100000 [6:58:13<12:13:37,  1.71it/s]
Train steps ... :  25%|██▍       | 24904/100000 [6:58:13<12:13:46,  1.71it/s]
Train steps ... :  25%|██▍       | 24905/100000 [6:58:14<12:14:25,  1.70it/s]
Train steps ... :  25%|██▍       | 24906/100000 [6:58:14<12:12:50,  1.71it/s]
Train steps ... :  25%|██▍       | 24907/100000 [6:58:15<12:13:44,  1.71it/s]
Train steps ... :  25%|██▍       | 24908/100000 [6:58:16<12:13:34,  1.71it/s]
Train steps ... :  25%|██▍       | 24909/100000 [6:58:16<12:12:53,  1.71it/s]
Train steps ... :  25%|██▍       | 24910/100000 [6:58:17<12:13:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24911/100000 [6:58:17<12:13:00,  1.71it/s]
Train steps ... :  25%|██▍       | 24912/100000 [6:58:18<12:13:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24913/100000 [6:58:19<12:11:45,  1.71it/s]
Train steps ... :  25%|██▍       | 24914/100000 [6:58:19<12:12:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24915/100000 [6:58:20<12:13:13,  1.71it/s]
Train steps ... :  25%|██▍       | 24916/100000 [6:58:20<12:12:00,  1.71it/s]
Train steps ... :  25%|██▍       | 24917/100000 [6:58:21<12:12:26,  1.71it/s]
Train steps ... :  25%|██▍       | 24918/100000 [6:58:22<12:12:24,  1.71it/s]
Train steps ... :  25%|██▍       | 24919/100000 [6:58:22<12:11:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24920/100000 [6:58:23<12:11:52,  1.71it/s]
Train steps ... :  25%|██▍       | 24921/100000 [6:58:23<12:12:06,  1.71it/s]
Train steps ... :  25%|██▍       | 24922/100000 [6:58:24<12:11:32,  1.71it/s]
Train steps ... :  25%|██▍       | 24923/100000 [6:58:24<12:12:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24924/100000 [6:58:25<12:13:01,  1.71it/s]
Train steps ... :  25%|██▍       | 24925/100000 [6:58:26<12:13:23,  1.71it/s]Step... (24925 / 100000 | Loss: 0.8601844310760498, Learning Rate: 7.545226130653267e-05)
+
                                                                             
Step... (24925 / 100000 | Loss: 0.9196078777313232, Learning Rate: 7.545226130653267e-05)
+
Train steps ... :  25%|██▍       | 24925/100000 [6:58:26<12:13:23,  1.71it/s]
Train steps ... :  25%|██▍       | 24926/100000 [6:58:26<12:13:00,  1.71it/s]
Train steps ... :  25%|██▍       | 24927/100000 [6:58:27<12:12:07,  1.71it/s]
Train steps ... :  25%|██▍       | 24928/100000 [6:58:27<12:13:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24929/100000 [6:58:28<12:12:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24930/100000 [6:58:29<12:14:49,  1.70it/s]
Train steps ... :  25%|██▍       | 24931/100000 [6:58:29<12:13:28,  1.71it/s]
Train steps ... :  25%|██▍       | 24932/100000 [6:58:30<12:14:04,  1.70it/s]
Train steps ... :  25%|██▍       | 24933/100000 [6:58:30<12:12:49,  1.71it/s]
Train steps ... :  25%|██▍       | 24934/100000 [6:58:31<12:12:45,  1.71it/s]
Train steps ... :  25%|██▍       | 24935/100000 [6:58:31<12:12:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24936/100000 [6:58:32<12:12:30,  1.71it/s]
Train steps ... :  25%|██▍       | 24937/100000 [6:58:33<12:12:03,  1.71it/s]
Train steps ... :  25%|██▍       | 24938/100000 [6:58:33<12:12:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24939/100000 [6:58:34<12:13:09,  1.71it/s]
Train steps ... :  25%|██▍       | 24940/100000 [6:58:34<12:13:13,  1.71it/s]
Train steps ... :  25%|██▍       | 24941/100000 [6:58:35<12:14:24,  1.70it/s]
Train steps ... :  25%|██▍       | 24942/100000 [6:58:36<12:12:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24943/100000 [6:58:36<12:12:13,  1.71it/s]
Train steps ... :  25%|██▍       | 24944/100000 [6:58:37<12:12:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24945/100000 [6:58:37<12:12:04,  1.71it/s]
Train steps ... :  25%|██▍       | 24946/100000 [6:58:38<12:12:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24947/100000 [6:58:38<12:10:58,  1.71it/s]
Train steps ... :  25%|██▍       | 24948/100000 [6:58:39<12:11:43,  1.71it/s]
Train steps ... :  25%|██▍       | 24949/100000 [6:58:40<12:12:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24950/100000 [6:58:40<12:12:47,  1.71it/s]Step... (24950 / 100000 | Loss: 1.2458415031433105, Learning Rate: 7.542713567839196e-05)
+
                                                                             
Step... (24950 / 100000 | Loss: 0.9435670971870422, Learning Rate: 7.542713567839196e-05)
+
Train steps ... :  25%|██▍       | 24950/100000 [6:58:41<12:12:47,  1.71it/s]
Train steps ... :  25%|██▍       | 24951/100000 [6:58:41<12:13:14,  1.71it/s]
Train steps ... :  25%|██▍       | 24952/100000 [6:58:41<12:12:54,  1.71it/s]
Train steps ... :  25%|██▍       | 24953/100000 [6:58:42<12:12:57,  1.71it/s]
Train steps ... :  25%|██▍       | 24954/100000 [6:58:43<12:12:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24955/100000 [6:58:43<12:13:49,  1.70it/s]
Train steps ... :  25%|██▍       | 24956/100000 [6:58:44<12:12:41,  1.71it/s]
Train steps ... :  25%|██▍       | 24957/100000 [6:58:44<12:12:14,  1.71it/s]
Train steps ... :  25%|██▍       | 24958/100000 [6:58:45<12:13:14,  1.71it/s]
Train steps ... :  25%|██▍       | 24959/100000 [6:58:46<12:11:44,  1.71it/s]
Train steps ... :  25%|██▍       | 24960/100000 [6:58:46<12:12:30,  1.71it/s]
Train steps ... :  25%|██▍       | 24961/100000 [6:58:47<12:11:02,  1.71it/s]
Train steps ... :  25%|██▍       | 24962/100000 [6:58:47<12:11:56,  1.71it/s]
Train steps ... :  25%|██▍       | 24963/100000 [6:58:48<12:13:04,  1.71it/s]
Train steps ... :  25%|██▍       | 24964/100000 [6:58:48<12:11:33,  1.71it/s]
Train steps ... :  25%|██▍       | 24965/100000 [6:58:49<12:11:25,  1.71it/s]
Train steps ... :  25%|██▍       | 24966/100000 [6:58:50<12:11:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24967/100000 [6:58:50<12:11:59,  1.71it/s]
Train steps ... :  25%|██▍       | 24968/100000 [6:58:51<12:12:20,  1.71it/s]
Train steps ... :  25%|██▍       | 24969/100000 [6:58:51<12:12:44,  1.71it/s]
Train steps ... :  25%|██▍       | 24970/100000 [6:58:52<12:13:18,  1.71it/s]
Train steps ... :  25%|██▍       | 24971/100000 [6:58:53<12:11:42,  1.71it/s]
Train steps ... :  25%|██▍       | 24972/100000 [6:58:53<12:11:10,  1.71it/s]
Train steps ... :  25%|██▍       | 24973/100000 [6:58:54<12:11:12,  1.71it/s]
Train steps ... :  25%|██▍       | 24974/100000 [6:58:54<12:10:57,  1.71it/s]
Train steps ... :  25%|██▍       | 24975/100000 [6:58:55<12:12:55,  1.71it/s]Step... (24975 / 100000 | Loss: 0.7608084678649902, Learning Rate: 7.540201005025126e-05)
+
                                                                             
Step... (24975 / 100000 | Loss: 0.8659267425537109, Learning Rate: 7.540201005025126e-05)
+
Train steps ... :  25%|██▍       | 24975/100000 [6:58:55<12:12:55,  1.71it/s]
Train steps ... :  25%|██▍       | 24976/100000 [6:58:55<12:12:58,  1.71it/s]
Train steps ... :  25%|██▍       | 24977/100000 [6:58:56<12:13:39,  1.70it/s]
Train steps ... :  25%|██▍       | 24978/100000 [6:58:57<12:13:30,  1.70it/s]
Train steps ... :  25%|██▍       | 24979/100000 [6:58:57<12:15:01,  1.70it/s]
Train steps ... :  25%|██▍       | 24980/100000 [6:58:58<12:15:58,  1.70it/s]
Train steps ... :  25%|██▍       | 24981/100000 [6:58:58<12:13:28,  1.70it/s]
Train steps ... :  25%|██▍       | 24982/100000 [6:58:59<12:13:09,  1.71it/s]
Train steps ... :  25%|██▍       | 24983/100000 [6:59:00<12:13:16,  1.71it/s]
Train steps ... :  25%|██▍       | 24984/100000 [6:59:00<12:14:10,  1.70it/s]
Train steps ... :  25%|██▍       | 24985/100000 [6:59:01<12:13:07,  1.71it/s]
Train steps ... :  25%|██▍       | 24986/100000 [6:59:01<12:14:38,  1.70it/s]
Train steps ... :  25%|██▍       | 24987/100000 [6:59:02<12:13:30,  1.70it/s]
Train steps ... :  25%|██▍       | 24988/100000 [6:59:03<12:15:05,  1.70it/s]
Train steps ... :  25%|██▍       | 24989/100000 [6:59:03<12:12:40,  1.71it/s]
Train steps ... :  25%|██▍       | 24990/100000 [6:59:04<12:13:37,  1.70it/s]
Train steps ... :  25%|██▍       | 24991/100000 [6:59:04<12:17:03,  1.70it/s]
Train steps ... :  25%|██▍       | 24992/100000 [6:59:05<12:15:46,  1.70it/s]
Train steps ... :  25%|██▍       | 24993/100000 [6:59:05<12:14:02,  1.70it/s]
Train steps ... :  25%|██▍       | 24994/100000 [6:59:06<12:15:27,  1.70it/s]
Train steps ... :  25%|██▍       | 24995/100000 [6:59:07<12:15:14,  1.70it/s]
Train steps ... :  25%|██▍       | 24996/100000 [6:59:07<12:16:19,  1.70it/s]
Train steps ... :  25%|██▍       | 24997/100000 [6:59:08<12:14:00,  1.70it/s]
Train steps ... :  25%|██▍       | 24998/100000 [6:59:08<12:14:35,  1.70it/s]
Train steps ... :  25%|██▍       | 24999/100000 [6:59:09<12:14:08,  1.70it/s]
Train steps ... :  25%|██▌       | 25000/100000 [6:59:10<12:14:29,  1.70it/s]Step... (25000 / 100000 | Loss: 1.053762435913086, Learning Rate: 7.537688442211056e-05)
+
                                                                             
Step... (25000 / 100000 | Loss: 1.1949880123138428, Learning Rate: 7.537688442211056e-05)
+
Train steps ... :  25%|██▌       | 25000/100000 [6:59:10<12:14:29,  1.70it/s]06/17/2024 22:53:37 - INFO - accelerate.accelerator - Saving current state to ./checkpoint-25000-epoch-1
+06/17/2024 22:53:37 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/17/2024 22:53:40 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-25000-epoch-1/model.safetensors
+06/17/2024 22:53:40 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/17/2024 22:53:44 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-25000-epoch-1/model_1.safetensors
+06/17/2024 22:53:44 - INFO - accelerate.checkpointing - Optimizer state saved in checkpoint-25000-epoch-1/optimizer.bin
+06/17/2024 22:53:44 - INFO - accelerate.checkpointing - Scheduler state saved in checkpoint-25000-epoch-1/scheduler.bin
+06/17/2024 22:53:44 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in checkpoint-25000-epoch-1/sampler.bin
+06/17/2024 22:53:44 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in checkpoint-25000-epoch-1/sampler_1.bin
+06/17/2024 22:53:44 - INFO - accelerate.checkpointing - Sampler state for dataloader 2 saved in checkpoint-25000-epoch-1/sampler_2.bin
+06/17/2024 22:53:44 - INFO - accelerate.checkpointing - Sampler state for dataloader 3 saved in checkpoint-25000-epoch-1/sampler_3.bin
+06/17/2024 22:53:44 - INFO - accelerate.checkpointing - Sampler state for dataloader 4 saved in checkpoint-25000-epoch-1/sampler_4.bin
+06/17/2024 22:53:44 - INFO - accelerate.checkpointing - Sampler state for dataloader 5 saved in checkpoint-25000-epoch-1/sampler_5.bin
+06/17/2024 22:53:44 - INFO - accelerate.checkpointing - Random states saved in checkpoint-25000-epoch-1/random_states_0.pkl
+
+
  0%|          | 0/5 [00:00<?, ?it/s]
+
 20%|██        | 1/5 [01:45<07:02, 105.50s/it]
+
 40%|████      | 2/5 [02:19<03:10, 63.39s/it] 
+
 60%|██████    | 3/5 [02:20<01:09, 34.72s/it]
+
 80%|████████  | 4/5 [02:20<00:21, 21.30s/it]
+
100%|██████████| 5/5 [02:21<00:00, 13.82s/it]
100%|██████████| 5/5 [02:21<00:00, 28.26s/it]