diff --git "a/train.log" "b/train.log"
--- "a/train.log"
+++ "b/train.log"
@@ -53703,3 +53703,4242 @@ Eval results for step (60000 / 100000 | Eval Loss: 1.017992377281189 | Eval wer:
 
 60%|██████    | 3/5 [02:25<01:12, 36.08s/it]
 
 80%|████████  | 4/5 [02:25<00:22, 22.06s/it]
 
100%|██████████| 5/5 [02:26<00:00, 14.33s/it]
100%|██████████| 5/5 [02:26<00:00, 29.25s/it]
+
+
+
Evaluating eval...:   0%|          | 0/1900 [00:00<?, ?it/s]
+
+
Evaluating eval...:   0%|          | 1/1900 [00:03<1:51:36,  3.53s/it]
+
+
Evaluating eval...:   0%|          | 2/1900 [00:04<1:08:52,  2.18s/it]
+
+
Evaluating eval...:   0%|          | 3/1900 [00:06<56:09,  1.78s/it]  
+
+
Evaluating eval...:   0%|          | 4/1900 [00:07<49:40,  1.57s/it]
+
+
Evaluating eval...:   0%|          | 5/1900 [00:08<45:47,  1.45s/it]
+
+
Evaluating eval...:   0%|          | 6/1900 [00:09<42:51,  1.36s/it]
+
+
Evaluating eval...:   0%|          | 7/1900 [00:10<41:08,  1.30s/it]
+
+
Evaluating eval...:   0%|          | 8/1900 [00:12<39:52,  1.26s/it]
+
+
Evaluating eval...:   0%|          | 9/1900 [00:13<38:53,  1.23s/it]
+
+
Evaluating eval...:   1%|          | 10/1900 [00:14<38:36,  1.23s/it]
+
+
Evaluating eval...:   1%|          | 11/1900 [00:15<38:40,  1.23s/it]
+
+
Evaluating eval...:   1%|          | 12/1900 [00:16<38:08,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 13/1900 [00:18<38:04,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 14/1900 [00:19<37:42,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 15/1900 [00:20<37:32,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 16/1900 [00:21<37:25,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 17/1900 [00:22<37:26,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 18/1900 [00:24<37:14,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 19/1900 [00:25<36:46,  1.17s/it]
+
+
Evaluating eval...:   1%|          | 20/1900 [00:26<36:57,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 21/1900 [00:27<37:22,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 22/1900 [00:28<37:21,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 23/1900 [00:29<36:55,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 24/1900 [00:31<37:10,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 25/1900 [00:32<36:44,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 26/1900 [00:33<36:32,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 27/1900 [00:34<37:06,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 28/1900 [00:35<36:42,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 29/1900 [00:36<36:36,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 30/1900 [00:38<36:39,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 31/1900 [00:39<36:34,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 32/1900 [00:40<36:54,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 33/1900 [00:41<37:05,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 34/1900 [00:42<37:42,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 35/1900 [00:44<37:36,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 36/1900 [00:45<37:46,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 37/1900 [00:46<37:41,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 38/1900 [00:47<37:16,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 39/1900 [00:49<37:07,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 40/1900 [00:50<37:00,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 41/1900 [00:51<36:39,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 42/1900 [00:52<37:29,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 43/1900 [00:53<37:17,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 44/1900 [00:55<37:16,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 45/1900 [00:56<36:41,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 46/1900 [00:57<36:26,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 47/1900 [00:58<36:00,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 48/1900 [00:59<35:48,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 49/1900 [01:00<35:42,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 50/1900 [01:01<36:20,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 51/1900 [01:03<36:19,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 52/1900 [01:04<36:06,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 53/1900 [01:05<35:59,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 54/1900 [01:06<36:19,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 55/1900 [01:07<36:53,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 56/1900 [01:09<37:02,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 57/1900 [01:10<36:58,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 58/1900 [01:11<37:03,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 59/1900 [01:12<36:48,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 60/1900 [01:13<36:18,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 61/1900 [01:15<37:42,  1.23s/it]
+
+
Evaluating eval...:   3%|▎         | 62/1900 [01:16<37:13,  1.22s/it]
+
+
Evaluating eval...:   3%|▎         | 63/1900 [01:17<36:56,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 64/1900 [01:18<36:39,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 65/1900 [01:19<36:12,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 66/1900 [01:21<35:53,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 67/1900 [01:22<35:47,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 68/1900 [01:23<36:39,  1.20s/it]
+
+
Evaluating eval...:   4%|▎         | 69/1900 [01:24<36:06,  1.18s/it]
+
+
Evaluating eval...:   4%|▎         | 70/1900 [01:25<36:38,  1.20s/it]
+
+
Evaluating eval...:   4%|▎         | 71/1900 [01:27<36:26,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 72/1900 [01:28<36:45,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 73/1900 [01:29<36:33,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 74/1900 [01:30<36:27,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 75/1900 [01:31<36:07,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 76/1900 [01:33<36:09,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 77/1900 [01:34<36:13,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 78/1900 [01:35<36:01,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 79/1900 [01:36<36:06,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 80/1900 [01:37<36:00,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 81/1900 [01:38<35:48,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 82/1900 [01:40<36:38,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 83/1900 [01:41<37:17,  1.23s/it]
+
+
Evaluating eval...:   4%|▍         | 84/1900 [01:42<36:44,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 85/1900 [01:43<36:29,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 86/1900 [01:45<35:49,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 87/1900 [01:46<36:08,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 88/1900 [01:47<35:54,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 89/1900 [01:48<37:12,  1.23s/it]
+
+
Evaluating eval...:   5%|▍         | 90/1900 [01:49<36:45,  1.22s/it]
+
+
Evaluating eval...:   5%|▍         | 91/1900 [01:51<36:49,  1.22s/it]
+
+
Evaluating eval...:   5%|▍         | 92/1900 [01:52<36:15,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 93/1900 [01:53<35:59,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 94/1900 [01:54<35:30,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 95/1900 [01:55<35:07,  1.17s/it]
+
+
Evaluating eval...:   5%|▌         | 96/1900 [01:57<36:11,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 97/1900 [01:58<35:35,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 98/1900 [01:59<36:06,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 99/1900 [02:00<35:50,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 100/1900 [02:01<35:39,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 101/1900 [02:03<36:30,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 102/1900 [02:04<36:59,  1.23s/it]
+
+
Evaluating eval...:   5%|▌         | 103/1900 [02:05<36:35,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 104/1900 [02:06<36:11,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 105/1900 [02:07<35:51,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 106/1900 [02:09<35:17,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 107/1900 [02:10<35:39,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 108/1900 [02:11<35:15,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 109/1900 [02:12<35:29,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 110/1900 [02:13<35:11,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 111/1900 [02:15<35:27,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 112/1900 [02:16<36:12,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 113/1900 [02:17<35:43,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 114/1900 [02:18<35:15,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 115/1900 [02:19<35:06,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 116/1900 [02:20<34:40,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 117/1900 [02:22<34:40,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 118/1900 [02:23<35:09,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 119/1900 [02:24<35:00,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 120/1900 [02:25<35:27,  1.20s/it]
+
+
Evaluating eval...:   6%|▋         | 121/1900 [02:26<35:02,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 122/1900 [02:28<35:02,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 123/1900 [02:29<35:01,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 124/1900 [02:30<35:03,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 125/1900 [02:31<35:12,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 126/1900 [02:32<35:06,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 127/1900 [02:34<35:23,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 128/1900 [02:35<35:01,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 129/1900 [02:36<34:51,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 130/1900 [02:37<34:44,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 131/1900 [02:38<34:53,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 132/1900 [02:39<35:24,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 133/1900 [02:41<34:49,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 134/1900 [02:42<35:07,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 135/1900 [02:43<35:29,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 136/1900 [02:44<35:52,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 137/1900 [02:46<36:33,  1.24s/it]
+
+
Evaluating eval...:   7%|▋         | 138/1900 [02:47<36:14,  1.23s/it]
+
+
Evaluating eval...:   7%|▋         | 139/1900 [02:48<35:45,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 140/1900 [02:49<35:52,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 141/1900 [02:50<35:38,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 142/1900 [02:52<35:37,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 143/1900 [02:53<35:51,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 144/1900 [02:54<35:05,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 145/1900 [02:55<35:19,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 146/1900 [02:56<34:57,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 147/1900 [02:58<35:19,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 148/1900 [02:59<34:44,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 149/1900 [03:00<34:54,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 150/1900 [03:01<36:02,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 151/1900 [03:03<35:28,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 152/1900 [03:04<35:24,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 153/1900 [03:05<35:41,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 154/1900 [03:06<35:42,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 155/1900 [03:07<35:27,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 156/1900 [03:09<35:11,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 157/1900 [03:10<36:06,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 158/1900 [03:11<35:42,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 159/1900 [03:12<35:02,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 160/1900 [03:13<34:54,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 161/1900 [03:15<35:46,  1.23s/it]
+
+
Evaluating eval...:   9%|▊         | 162/1900 [03:16<35:05,  1.21s/it]
+
+
Evaluating eval...:   9%|▊         | 163/1900 [03:17<34:30,  1.19s/it]
+
+
Evaluating eval...:   9%|▊         | 164/1900 [03:18<34:53,  1.21s/it]
+
+
Evaluating eval...:   9%|▊         | 165/1900 [03:20<34:46,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 166/1900 [03:21<34:38,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 167/1900 [03:22<35:33,  1.23s/it]
+
+
Evaluating eval...:   9%|▉         | 168/1900 [03:23<34:52,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 169/1900 [03:24<34:56,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 170/1900 [03:26<34:39,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 171/1900 [03:27<34:32,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 172/1900 [03:28<34:51,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 173/1900 [03:29<34:59,  1.22s/it]
+
+
Evaluating eval...:   9%|▉         | 174/1900 [03:30<35:17,  1.23s/it]
+
+
Evaluating eval...:   9%|▉         | 175/1900 [03:32<34:35,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 176/1900 [03:33<34:01,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 177/1900 [03:34<35:58,  1.25s/it]
+
+
Evaluating eval...:   9%|▉         | 178/1900 [03:35<35:54,  1.25s/it]
+
+
Evaluating eval...:   9%|▉         | 179/1900 [03:37<35:10,  1.23s/it]
+
+
Evaluating eval...:   9%|▉         | 180/1900 [03:38<35:04,  1.22s/it]
+
+
Evaluating eval...:  10%|▉         | 181/1900 [03:39<34:43,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 182/1900 [03:40<35:25,  1.24s/it]
+
+
Evaluating eval...:  10%|▉         | 183/1900 [03:42<35:18,  1.23s/it]
+
+
Evaluating eval...:  10%|▉         | 184/1900 [03:43<34:42,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 185/1900 [03:44<34:30,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 186/1900 [03:45<34:02,  1.19s/it]
+
+
Evaluating eval...:  10%|▉         | 187/1900 [03:46<34:24,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 188/1900 [03:47<34:30,  1.21s/it]
+
+
Evaluating eval...:  10%|▉         | 189/1900 [03:49<34:02,  1.19s/it]
+
+
Evaluating eval...:  10%|█         | 190/1900 [03:50<33:59,  1.19s/it]
+
+
Evaluating eval...:  10%|█         | 191/1900 [03:51<33:42,  1.18s/it]
+
+
Evaluating eval...:  10%|█         | 192/1900 [03:52<34:35,  1.22s/it]
+
+
Evaluating eval...:  10%|█         | 193/1900 [03:54<35:35,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 194/1900 [03:55<35:18,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 195/1900 [03:56<35:26,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 196/1900 [03:57<35:06,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 197/1900 [03:59<35:44,  1.26s/it]
+
+
Evaluating eval...:  10%|█         | 198/1900 [04:00<35:53,  1.27s/it]
+
+
Evaluating eval...:  10%|█         | 199/1900 [04:01<35:08,  1.24s/it]
+
+
Evaluating eval...:  11%|█         | 200/1900 [04:02<34:27,  1.22s/it]
+
+
Evaluating eval...:  11%|█         | 201/1900 [04:03<33:53,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 202/1900 [04:05<33:28,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 203/1900 [04:06<33:26,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 204/1900 [04:07<33:29,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 205/1900 [04:08<33:42,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 206/1900 [04:09<33:40,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 207/1900 [04:11<34:10,  1.21s/it]
+
+
Evaluating eval...:  11%|█         | 208/1900 [04:12<33:40,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 209/1900 [04:13<33:29,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 210/1900 [04:14<33:13,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 211/1900 [04:15<33:39,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 212/1900 [04:16<33:26,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 213/1900 [04:18<34:13,  1.22s/it]
+
+
Evaluating eval...:  11%|█▏        | 214/1900 [04:19<34:11,  1.22s/it]
+
+
Evaluating eval...:  11%|█▏        | 215/1900 [04:20<33:59,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 216/1900 [04:21<33:51,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 217/1900 [04:23<33:46,  1.20s/it]
+
+
Evaluating eval...:  11%|█▏        | 218/1900 [04:24<34:25,  1.23s/it]
+
+
Evaluating eval...:  12%|█▏        | 219/1900 [04:25<34:00,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 220/1900 [04:26<34:14,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 221/1900 [04:27<34:08,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 222/1900 [04:29<33:56,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 223/1900 [04:30<33:19,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 224/1900 [04:31<32:59,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 225/1900 [04:32<32:50,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 226/1900 [04:33<32:56,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 227/1900 [04:34<32:46,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 228/1900 [04:36<33:25,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 229/1900 [04:37<32:54,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 230/1900 [04:38<33:04,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 231/1900 [04:39<33:23,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 232/1900 [04:40<33:01,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 233/1900 [04:42<32:59,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 234/1900 [04:43<32:58,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 235/1900 [04:44<33:15,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 236/1900 [04:45<33:56,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 237/1900 [04:47<34:06,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 238/1900 [04:48<34:09,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 239/1900 [04:49<34:26,  1.24s/it]
+
+
Evaluating eval...:  13%|█▎        | 240/1900 [04:50<33:42,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 241/1900 [04:51<33:18,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 242/1900 [04:53<33:21,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 243/1900 [04:54<32:55,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 244/1900 [04:55<32:46,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 245/1900 [04:56<33:20,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 246/1900 [04:57<33:24,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 247/1900 [04:59<33:07,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 248/1900 [05:00<33:19,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 249/1900 [05:01<32:48,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 250/1900 [05:02<33:19,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 251/1900 [05:04<33:52,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 252/1900 [05:05<33:22,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 253/1900 [05:06<33:55,  1.24s/it]
+
+
Evaluating eval...:  13%|█▎        | 254/1900 [05:07<33:34,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 255/1900 [05:08<33:19,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 256/1900 [05:10<33:06,  1.21s/it]
+
+
Evaluating eval...:  14%|█▎        | 257/1900 [05:11<32:35,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 258/1900 [05:12<32:25,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 259/1900 [05:13<32:26,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 260/1900 [05:14<32:25,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 261/1900 [05:15<32:29,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 262/1900 [05:17<32:09,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 263/1900 [05:18<32:18,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 264/1900 [05:19<32:09,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 265/1900 [05:20<32:17,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 266/1900 [05:21<32:12,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 267/1900 [05:23<32:14,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 268/1900 [05:24<32:09,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 269/1900 [05:25<32:07,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 270/1900 [05:26<31:54,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 271/1900 [05:27<31:36,  1.16s/it]
+
+
Evaluating eval...:  14%|█▍        | 272/1900 [05:28<32:01,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 273/1900 [05:30<32:11,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 274/1900 [05:31<32:08,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 275/1900 [05:32<32:11,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 276/1900 [05:33<32:31,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 277/1900 [05:34<32:08,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 278/1900 [05:36<31:47,  1.18s/it]
+
+
Evaluating eval...:  15%|█▍        | 279/1900 [05:37<32:28,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 280/1900 [05:38<32:48,  1.22s/it]
+
+
Evaluating eval...:  15%|█▍        | 281/1900 [05:39<32:52,  1.22s/it]
+
+
Evaluating eval...:  15%|█▍        | 282/1900 [05:40<32:32,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 283/1900 [05:42<32:25,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 284/1900 [05:43<32:24,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 285/1900 [05:44<32:06,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 286/1900 [05:45<32:46,  1.22s/it]
+
+
Evaluating eval...:  15%|█▌        | 287/1900 [05:47<32:38,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 288/1900 [05:48<33:57,  1.26s/it]
+
+
Evaluating eval...:  15%|█▌        | 289/1900 [05:49<33:15,  1.24s/it]
+
+
Evaluating eval...:  15%|█▌        | 290/1900 [05:50<32:43,  1.22s/it]
+
+
Evaluating eval...:  15%|█▌        | 291/1900 [05:51<32:24,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 292/1900 [05:53<32:17,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 293/1900 [05:54<31:53,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 294/1900 [05:55<31:37,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 295/1900 [05:56<31:47,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 296/1900 [05:57<32:06,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 297/1900 [05:59<32:19,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 298/1900 [06:00<32:49,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 299/1900 [06:01<32:22,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 300/1900 [06:02<32:24,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 301/1900 [06:04<32:56,  1.24s/it]
+
+
Evaluating eval...:  16%|█▌        | 302/1900 [06:05<32:25,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 303/1900 [06:06<32:02,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 304/1900 [06:07<31:35,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 305/1900 [06:08<31:38,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 306/1900 [06:09<31:38,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 307/1900 [06:11<31:28,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 308/1900 [06:12<31:24,  1.18s/it]
+
+
Evaluating eval...:  16%|█▋        | 309/1900 [06:13<31:25,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 310/1900 [06:14<31:54,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 311/1900 [06:15<32:09,  1.21s/it]
+
+
Evaluating eval...:  16%|█▋        | 312/1900 [06:17<32:07,  1.21s/it]
+
+
Evaluating eval...:  16%|█▋        | 313/1900 [06:18<31:52,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 314/1900 [06:19<31:46,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 315/1900 [06:20<31:51,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 316/1900 [06:21<31:35,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 317/1900 [06:23<31:52,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 318/1900 [06:24<31:27,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 319/1900 [06:25<31:37,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 320/1900 [06:26<31:37,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 321/1900 [06:27<31:09,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 322/1900 [06:29<31:15,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 323/1900 [06:30<31:26,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 324/1900 [06:31<31:02,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 325/1900 [06:32<31:08,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 326/1900 [06:33<30:57,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 327/1900 [06:35<30:51,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 328/1900 [06:36<31:25,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 329/1900 [06:37<31:07,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 330/1900 [06:38<31:28,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 331/1900 [06:40<32:24,  1.24s/it]
+
+
Evaluating eval...:  17%|█▋        | 332/1900 [06:41<32:25,  1.24s/it]
+
+
Evaluating eval...:  18%|█▊        | 333/1900 [06:42<32:25,  1.24s/it]
+
+
Evaluating eval...:  18%|█▊        | 334/1900 [06:43<31:39,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 335/1900 [06:44<31:02,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 336/1900 [06:45<31:00,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 337/1900 [06:47<30:52,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 338/1900 [06:48<31:25,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 339/1900 [06:49<31:46,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 340/1900 [06:50<31:32,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 341/1900 [06:52<31:50,  1.23s/it]
+
+
Evaluating eval...:  18%|█▊        | 342/1900 [06:53<31:17,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 343/1900 [06:54<31:10,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 344/1900 [06:55<31:06,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 345/1900 [06:56<31:16,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 346/1900 [06:58<30:56,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 347/1900 [06:59<31:03,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 348/1900 [07:00<30:35,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 349/1900 [07:01<30:19,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 350/1900 [07:02<30:24,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 351/1900 [07:03<30:53,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 352/1900 [07:05<31:06,  1.21s/it]
+
+
Evaluating eval...:  19%|█▊        | 353/1900 [07:06<31:38,  1.23s/it]
+
+
Evaluating eval...:  19%|█▊        | 354/1900 [07:07<31:23,  1.22s/it]
+
+
Evaluating eval...:  19%|█▊        | 355/1900 [07:08<31:54,  1.24s/it]
+
+
Evaluating eval...:  19%|█▊        | 356/1900 [07:10<31:45,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 357/1900 [07:11<31:10,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 358/1900 [07:12<31:20,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 359/1900 [07:13<31:02,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 360/1900 [07:14<31:03,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 361/1900 [07:16<30:41,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 362/1900 [07:17<31:22,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 363/1900 [07:18<31:00,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 364/1900 [07:19<30:38,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 365/1900 [07:20<30:36,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 366/1900 [07:22<30:13,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 367/1900 [07:23<31:14,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 368/1900 [07:24<31:55,  1.25s/it]
+
+
Evaluating eval...:  19%|█▉        | 369/1900 [07:25<31:36,  1.24s/it]
+
+
Evaluating eval...:  19%|█▉        | 370/1900 [07:27<31:07,  1.22s/it]
+
+
Evaluating eval...:  20%|█▉        | 371/1900 [07:28<30:50,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 372/1900 [07:29<30:31,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 373/1900 [07:30<30:25,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 374/1900 [07:31<30:04,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 375/1900 [07:32<29:49,  1.17s/it]
+
+
Evaluating eval...:  20%|█▉        | 376/1900 [07:34<30:09,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 377/1900 [07:35<31:12,  1.23s/it]
+
+
Evaluating eval...:  20%|█▉        | 378/1900 [07:36<31:33,  1.24s/it]
+
+
Evaluating eval...:  20%|█▉        | 379/1900 [07:38<31:05,  1.23s/it]
+
+
Evaluating eval...:  20%|██        | 380/1900 [07:39<30:55,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 381/1900 [07:40<30:57,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 382/1900 [07:41<31:06,  1.23s/it]
+
+
Evaluating eval...:  20%|██        | 383/1900 [07:42<30:32,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 384/1900 [07:44<30:18,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 385/1900 [07:45<30:06,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 386/1900 [07:46<30:27,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 387/1900 [07:47<30:16,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 388/1900 [07:48<30:11,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 389/1900 [07:50<30:13,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 390/1900 [07:51<30:13,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 391/1900 [07:52<30:20,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 392/1900 [07:53<29:53,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 393/1900 [07:54<29:35,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 394/1900 [07:55<29:41,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 395/1900 [07:57<29:30,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 396/1900 [07:58<30:08,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 397/1900 [07:59<30:14,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 398/1900 [08:00<29:52,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 399/1900 [08:01<30:15,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 400/1900 [08:03<30:11,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 401/1900 [08:04<30:05,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 402/1900 [08:05<29:46,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 403/1900 [08:06<29:58,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 404/1900 [08:08<30:06,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 405/1900 [08:09<30:20,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 406/1900 [08:10<29:56,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 407/1900 [08:11<29:52,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 408/1900 [08:12<30:29,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 409/1900 [08:14<30:26,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 410/1900 [08:15<30:04,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 411/1900 [08:16<30:09,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 412/1900 [08:17<29:34,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 413/1900 [08:18<30:06,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 414/1900 [08:20<29:50,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 415/1900 [08:21<29:16,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 416/1900 [08:22<29:07,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 417/1900 [08:23<29:56,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 418/1900 [08:24<29:38,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 419/1900 [08:26<29:17,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 420/1900 [08:27<29:45,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 421/1900 [08:28<29:43,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 422/1900 [08:29<29:30,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 423/1900 [08:30<29:55,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 424/1900 [08:32<29:54,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 425/1900 [08:33<30:06,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 426/1900 [08:34<30:10,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 427/1900 [08:35<29:54,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 428/1900 [08:36<29:21,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 429/1900 [08:38<29:25,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 430/1900 [08:39<29:03,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 431/1900 [08:40<29:08,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 432/1900 [08:41<29:36,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 433/1900 [08:42<29:27,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 434/1900 [08:44<30:24,  1.24s/it]
+
+
Evaluating eval...:  23%|██▎       | 435/1900 [08:45<29:48,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 436/1900 [08:46<29:57,  1.23s/it]
+
+
Evaluating eval...:  23%|██▎       | 437/1900 [08:47<29:15,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 438/1900 [08:49<28:57,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 439/1900 [08:50<29:13,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 440/1900 [08:51<29:02,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 441/1900 [08:52<28:52,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 442/1900 [08:53<28:33,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 443/1900 [08:54<28:55,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 444/1900 [08:56<28:55,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 445/1900 [08:57<29:04,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 446/1900 [08:58<29:02,  1.20s/it]
+
+
Evaluating eval...:  24%|██▎       | 447/1900 [08:59<28:41,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 448/1900 [09:00<28:35,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 449/1900 [09:02<28:31,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 450/1900 [09:03<28:29,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 451/1900 [09:04<28:43,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 452/1900 [09:05<28:26,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 453/1900 [09:06<29:03,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 454/1900 [09:08<29:14,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 455/1900 [09:09<29:08,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 456/1900 [09:10<29:11,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 457/1900 [09:11<29:18,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 458/1900 [09:12<29:07,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 459/1900 [09:14<28:36,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 460/1900 [09:15<28:23,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 461/1900 [09:16<28:42,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 462/1900 [09:17<28:38,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 463/1900 [09:18<28:27,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 464/1900 [09:20<28:36,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 465/1900 [09:21<28:33,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 466/1900 [09:22<28:14,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 467/1900 [09:23<28:19,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 468/1900 [09:24<28:38,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 469/1900 [09:26<28:33,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 470/1900 [09:27<28:27,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 471/1900 [09:28<28:23,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 472/1900 [09:29<28:53,  1.21s/it]
+
+
Evaluating eval...:  25%|██▍       | 473/1900 [09:30<28:25,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 474/1900 [09:31<28:12,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 475/1900 [09:33<28:17,  1.19s/it]
+
+
Evaluating eval...:  25%|██▌       | 476/1900 [09:34<28:01,  1.18s/it]
+
+
Evaluating eval...:  25%|██▌       | 477/1900 [09:35<28:43,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 478/1900 [09:36<28:50,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 479/1900 [09:38<29:02,  1.23s/it]
+
+
Evaluating eval...:  25%|██▌       | 480/1900 [09:39<28:41,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 481/1900 [09:40<29:27,  1.25s/it]
+
+
Evaluating eval...:  25%|██▌       | 482/1900 [09:41<28:45,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 483/1900 [09:42<28:23,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 484/1900 [09:44<28:49,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 485/1900 [09:45<28:20,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 486/1900 [09:46<28:02,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 487/1900 [09:47<28:05,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 488/1900 [09:48<28:26,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 489/1900 [09:50<28:25,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 490/1900 [09:51<28:15,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 491/1900 [09:52<28:23,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 492/1900 [09:53<28:21,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 493/1900 [09:55<28:33,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 494/1900 [09:56<28:24,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 495/1900 [09:57<28:11,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 496/1900 [09:58<28:17,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 497/1900 [09:59<28:25,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 498/1900 [10:01<28:50,  1.23s/it]
+
+
Evaluating eval...:  26%|██▋       | 499/1900 [10:02<28:41,  1.23s/it]
+
+
Evaluating eval...:  26%|██▋       | 500/1900 [10:03<28:34,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 501/1900 [10:04<28:33,  1.23s/it]
+
+
Evaluating eval...:  26%|██▋       | 502/1900 [10:06<28:35,  1.23s/it]
+
+
Evaluating eval...:  26%|██▋       | 503/1900 [10:07<28:55,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 504/1900 [10:08<29:07,  1.25s/it]
+
+
Evaluating eval...:  27%|██▋       | 505/1900 [10:09<29:07,  1.25s/it]
+
+
Evaluating eval...:  27%|██▋       | 506/1900 [10:11<28:40,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 507/1900 [10:12<28:20,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 508/1900 [10:13<28:20,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 509/1900 [10:14<28:50,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 510/1900 [10:15<28:20,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 511/1900 [10:17<27:58,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 512/1900 [10:18<27:50,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 513/1900 [10:19<27:31,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 514/1900 [10:20<27:26,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 515/1900 [10:21<27:44,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 516/1900 [10:23<27:49,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 517/1900 [10:24<27:39,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 518/1900 [10:25<28:20,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 519/1900 [10:26<28:32,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 520/1900 [10:27<28:03,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 521/1900 [10:29<28:16,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 522/1900 [10:30<28:05,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 523/1900 [10:31<27:57,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 524/1900 [10:32<27:45,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 525/1900 [10:34<27:26,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 526/1900 [10:35<27:32,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 527/1900 [10:36<27:58,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 528/1900 [10:37<28:01,  1.23s/it]
+
+
Evaluating eval...:  28%|██▊       | 529/1900 [10:38<28:09,  1.23s/it]
+
+
Evaluating eval...:  28%|██▊       | 530/1900 [10:40<27:42,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 531/1900 [10:41<27:42,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 532/1900 [10:42<28:14,  1.24s/it]
+
+
Evaluating eval...:  28%|██▊       | 533/1900 [10:43<27:47,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 534/1900 [10:45<27:34,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 535/1900 [10:46<27:13,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 536/1900 [10:47<27:23,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 537/1900 [10:48<27:33,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 538/1900 [10:49<27:34,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 539/1900 [10:51<27:28,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 540/1900 [10:52<27:13,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 541/1900 [10:53<26:58,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 542/1900 [10:54<27:20,  1.21s/it]
+
+
Evaluating eval...:  29%|██▊       | 543/1900 [10:55<26:54,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 544/1900 [10:57<26:56,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 545/1900 [10:58<27:40,  1.23s/it]
+
+
Evaluating eval...:  29%|██▊       | 546/1900 [10:59<27:32,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 547/1900 [11:00<27:37,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 548/1900 [11:02<27:54,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 549/1900 [11:03<27:44,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 550/1900 [11:04<27:39,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 551/1900 [11:05<27:22,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 552/1900 [11:06<27:50,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 553/1900 [11:08<27:30,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 554/1900 [11:09<27:06,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 555/1900 [11:10<26:51,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 556/1900 [11:11<26:58,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 557/1900 [11:12<26:43,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 558/1900 [11:14<26:49,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 559/1900 [11:15<26:32,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 560/1900 [11:16<26:55,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 561/1900 [11:17<26:44,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 562/1900 [11:18<26:46,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 563/1900 [11:20<27:13,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 564/1900 [11:21<27:48,  1.25s/it]
+
+
Evaluating eval...:  30%|██▉       | 565/1900 [11:22<27:35,  1.24s/it]
+
+
Evaluating eval...:  30%|██▉       | 566/1900 [11:23<27:49,  1.25s/it]
+
+
Evaluating eval...:  30%|██▉       | 567/1900 [11:25<27:33,  1.24s/it]
+
+
Evaluating eval...:  30%|██▉       | 568/1900 [11:26<27:32,  1.24s/it]
+
+
Evaluating eval...:  30%|██▉       | 569/1900 [11:27<27:22,  1.23s/it]
+
+
Evaluating eval...:  30%|███       | 570/1900 [11:28<27:55,  1.26s/it]
+
+
Evaluating eval...:  30%|███       | 571/1900 [11:30<27:07,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 572/1900 [11:31<26:54,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 573/1900 [11:32<27:02,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 574/1900 [11:33<26:51,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 575/1900 [11:34<26:32,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 576/1900 [11:36<26:47,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 577/1900 [11:37<26:48,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 578/1900 [11:38<26:48,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 579/1900 [11:39<26:42,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 580/1900 [11:40<26:29,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 581/1900 [11:42<26:11,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 582/1900 [11:44<33:16,  1.51s/it]
+
+
Evaluating eval...:  31%|███       | 583/1900 [11:45<30:54,  1.41s/it]
+
+
Evaluating eval...:  31%|███       | 584/1900 [11:46<29:20,  1.34s/it]
+
+
Evaluating eval...:  31%|███       | 585/1900 [11:47<28:21,  1.29s/it]
+
+
Evaluating eval...:  31%|███       | 586/1900 [11:49<27:59,  1.28s/it]
+
+
Evaluating eval...:  31%|███       | 587/1900 [11:50<27:10,  1.24s/it]
+
+
Evaluating eval...:  31%|███       | 588/1900 [11:51<26:34,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 589/1900 [11:52<26:33,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 590/1900 [11:53<26:28,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 591/1900 [11:55<26:19,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 592/1900 [11:56<26:28,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 593/1900 [11:57<26:15,  1.21s/it]
+
+
Evaluating eval...:  31%|███▏      | 594/1900 [11:58<26:33,  1.22s/it]
+
+
Evaluating eval...:  31%|███▏      | 595/1900 [11:59<26:11,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 596/1900 [12:01<26:15,  1.21s/it]
+
+
Evaluating eval...:  31%|███▏      | 597/1900 [12:02<26:34,  1.22s/it]
+
+
Evaluating eval...:  31%|███▏      | 598/1900 [12:03<26:14,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 599/1900 [12:04<26:07,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 600/1900 [12:05<26:09,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 601/1900 [12:07<26:05,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 602/1900 [12:08<25:40,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 603/1900 [12:09<25:33,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 604/1900 [12:10<25:42,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 605/1900 [12:11<25:55,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 606/1900 [12:13<26:21,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 607/1900 [12:14<25:49,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 608/1900 [12:15<26:16,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 609/1900 [12:16<26:26,  1.23s/it]
+
+
Evaluating eval...:  32%|███▏      | 610/1900 [12:18<26:00,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 611/1900 [12:19<25:37,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 612/1900 [12:20<25:49,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 613/1900 [12:21<25:41,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 614/1900 [12:22<26:15,  1.23s/it]
+
+
Evaluating eval...:  32%|███▏      | 615/1900 [12:24<25:55,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 616/1900 [12:25<25:38,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 617/1900 [12:26<25:25,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 618/1900 [12:27<25:10,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 619/1900 [12:28<25:57,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 620/1900 [12:30<25:40,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 621/1900 [12:31<25:43,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 622/1900 [12:32<25:38,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 623/1900 [12:33<25:46,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 624/1900 [12:34<26:14,  1.23s/it]
+
+
Evaluating eval...:  33%|███▎      | 625/1900 [12:36<26:14,  1.24s/it]
+
+
Evaluating eval...:  33%|███▎      | 626/1900 [12:37<25:47,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 627/1900 [12:38<25:23,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 628/1900 [12:39<25:13,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 629/1900 [12:40<25:39,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 630/1900 [12:42<25:41,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 631/1900 [12:43<25:51,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 632/1900 [12:44<25:25,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 633/1900 [12:45<25:10,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 634/1900 [12:46<24:46,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 635/1900 [12:48<24:45,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 636/1900 [12:49<24:56,  1.18s/it]
+
+
Evaluating eval...:  34%|███▎      | 637/1900 [12:50<25:06,  1.19s/it]
+
+
Evaluating eval...:  34%|███▎      | 638/1900 [12:51<25:47,  1.23s/it]
+
+
Evaluating eval...:  34%|███▎      | 639/1900 [12:53<26:24,  1.26s/it]
+
+
Evaluating eval...:  34%|███▎      | 640/1900 [12:54<26:41,  1.27s/it]
+
+
Evaluating eval...:  34%|███▎      | 641/1900 [12:55<26:13,  1.25s/it]
+
+
Evaluating eval...:  34%|███▍      | 642/1900 [12:56<26:00,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 643/1900 [12:58<26:07,  1.25s/it]
+
+
Evaluating eval...:  34%|███▍      | 644/1900 [12:59<25:43,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 645/1900 [13:00<25:43,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 646/1900 [13:01<25:55,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 647/1900 [13:02<25:34,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 648/1900 [13:04<25:14,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 649/1900 [13:05<25:25,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 650/1900 [13:06<25:35,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 651/1900 [13:07<25:37,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 652/1900 [13:09<25:03,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 653/1900 [13:10<24:42,  1.19s/it]
+
+
Evaluating eval...:  34%|███▍      | 654/1900 [13:11<24:58,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 655/1900 [13:12<24:45,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 656/1900 [13:13<24:37,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 657/1900 [13:14<24:30,  1.18s/it]
+
+
Evaluating eval...:  35%|███▍      | 658/1900 [13:16<24:57,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 659/1900 [13:17<24:59,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 660/1900 [13:18<24:41,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 661/1900 [13:19<24:41,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 662/1900 [13:21<25:00,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 663/1900 [13:22<25:08,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 664/1900 [13:23<24:59,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 665/1900 [13:24<24:48,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 666/1900 [13:25<24:45,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 667/1900 [13:27<25:55,  1.26s/it]
+
+
Evaluating eval...:  35%|███▌      | 668/1900 [13:28<25:18,  1.23s/it]
+
+
Evaluating eval...:  35%|███▌      | 669/1900 [13:29<24:54,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 670/1900 [13:30<24:43,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 671/1900 [13:31<24:49,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 672/1900 [13:33<24:38,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 673/1900 [13:34<24:38,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 674/1900 [13:35<24:35,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 675/1900 [13:36<24:24,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 676/1900 [13:37<24:16,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 677/1900 [13:39<24:09,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 678/1900 [13:40<24:28,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 679/1900 [13:41<24:08,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 680/1900 [13:42<24:36,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 681/1900 [13:44<25:05,  1.24s/it]
+
+
Evaluating eval...:  36%|███▌      | 682/1900 [13:45<24:57,  1.23s/it]
+
+
Evaluating eval...:  36%|███▌      | 683/1900 [13:46<25:07,  1.24s/it]
+
+
Evaluating eval...:  36%|███▌      | 684/1900 [13:47<24:36,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 685/1900 [13:48<24:14,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 686/1900 [13:50<24:37,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 687/1900 [13:51<24:12,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 688/1900 [13:52<23:55,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 689/1900 [13:53<23:48,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 690/1900 [13:54<23:54,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 691/1900 [13:55<24:00,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 692/1900 [13:57<23:42,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 693/1900 [13:58<23:46,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 694/1900 [13:59<23:55,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 695/1900 [14:00<24:08,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 696/1900 [14:01<24:14,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 697/1900 [14:03<24:02,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 698/1900 [14:04<24:07,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 699/1900 [14:05<24:27,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 700/1900 [14:06<24:00,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 701/1900 [14:07<23:59,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 702/1900 [14:09<24:01,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 703/1900 [14:10<23:35,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 704/1900 [14:11<24:26,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 705/1900 [14:12<24:14,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 706/1900 [14:14<24:02,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 707/1900 [14:15<23:38,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 708/1900 [14:16<24:12,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 709/1900 [14:17<24:03,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 710/1900 [14:18<23:48,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 711/1900 [14:20<24:17,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 712/1900 [14:21<24:23,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 713/1900 [14:22<24:35,  1.24s/it]
+
+
Evaluating eval...:  38%|███▊      | 714/1900 [14:23<24:02,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 715/1900 [14:24<23:45,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 716/1900 [14:26<23:33,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 717/1900 [14:27<23:23,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 718/1900 [14:28<23:29,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 719/1900 [14:29<23:27,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 720/1900 [14:30<23:24,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 721/1900 [14:32<23:45,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 722/1900 [14:33<23:39,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 723/1900 [14:34<23:49,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 724/1900 [14:35<23:47,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 725/1900 [14:36<23:32,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 726/1900 [14:38<23:37,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 727/1900 [14:39<23:27,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 728/1900 [14:40<23:54,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 729/1900 [14:41<23:32,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 730/1900 [14:43<23:54,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 731/1900 [14:44<23:46,  1.22s/it]
+
+
Evaluating eval...:  39%|███▊      | 732/1900 [14:45<23:36,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 733/1900 [14:46<23:32,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 734/1900 [14:47<23:22,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 735/1900 [14:49<23:09,  1.19s/it]
+
+
Evaluating eval...:  39%|███▊      | 736/1900 [14:50<23:15,  1.20s/it]
+
+
Evaluating eval...:  39%|███▉      | 737/1900 [14:51<23:08,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 738/1900 [14:52<23:22,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 739/1900 [14:53<23:04,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 740/1900 [14:55<23:04,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 741/1900 [14:56<23:34,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 742/1900 [14:57<23:32,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 743/1900 [14:58<23:33,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 744/1900 [14:59<23:28,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 745/1900 [15:01<23:34,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 746/1900 [15:02<23:27,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 747/1900 [15:03<23:46,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 748/1900 [15:04<23:29,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 749/1900 [15:06<23:29,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 750/1900 [15:07<23:14,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 751/1900 [15:08<23:15,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 752/1900 [15:09<23:27,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 753/1900 [15:11<23:28,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 754/1900 [15:12<23:06,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 755/1900 [15:13<22:48,  1.20s/it]
+
+
Evaluating eval...:  40%|███▉      | 756/1900 [15:14<23:17,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 757/1900 [15:15<23:07,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 758/1900 [15:17<23:19,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 759/1900 [15:18<23:17,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 760/1900 [15:19<23:22,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 761/1900 [15:20<23:01,  1.21s/it]
+
+
Evaluating eval...:  40%|████      | 762/1900 [15:21<22:35,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 763/1900 [15:23<22:23,  1.18s/it]
+
+
Evaluating eval...:  40%|████      | 764/1900 [15:24<22:21,  1.18s/it]
+
+
Evaluating eval...:  40%|████      | 765/1900 [15:25<22:40,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 766/1900 [15:26<22:50,  1.21s/it]
+
+
Evaluating eval...:  40%|████      | 767/1900 [15:27<23:17,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 768/1900 [15:29<23:42,  1.26s/it]
+
+
Evaluating eval...:  40%|████      | 769/1900 [15:30<23:24,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 770/1900 [15:31<22:53,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 771/1900 [15:32<22:49,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 772/1900 [15:34<22:55,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 773/1900 [15:35<22:44,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 774/1900 [15:36<22:30,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 775/1900 [15:37<23:02,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 776/1900 [15:38<22:56,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 777/1900 [15:40<22:59,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 778/1900 [15:41<22:40,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 779/1900 [15:42<22:29,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 780/1900 [15:43<23:11,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 781/1900 [15:45<22:54,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 782/1900 [15:46<23:09,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 783/1900 [15:47<23:03,  1.24s/it]
+
+
Evaluating eval...:  41%|████▏     | 784/1900 [15:48<22:51,  1.23s/it]
+
+
Evaluating eval...:  41%|████▏     | 785/1900 [15:49<22:38,  1.22s/it]
+
+
Evaluating eval...:  41%|████▏     | 786/1900 [15:51<22:26,  1.21s/it]
+
+
Evaluating eval...:  41%|████▏     | 787/1900 [15:52<22:25,  1.21s/it]
+
+
Evaluating eval...:  41%|████▏     | 788/1900 [15:53<22:19,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 789/1900 [15:54<22:25,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 790/1900 [15:55<22:18,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 791/1900 [15:57<22:28,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 792/1900 [15:58<22:41,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 793/1900 [15:59<22:22,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 794/1900 [16:00<22:10,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 795/1900 [16:02<22:01,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 796/1900 [16:03<21:45,  1.18s/it]
+
+
Evaluating eval...:  42%|████▏     | 797/1900 [16:04<21:41,  1.18s/it]
+
+
Evaluating eval...:  42%|████▏     | 798/1900 [16:05<21:38,  1.18s/it]
+
+
Evaluating eval...:  42%|████▏     | 799/1900 [16:06<21:37,  1.18s/it]
+
+
Evaluating eval...:  42%|████▏     | 800/1900 [16:07<22:12,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 801/1900 [16:09<22:03,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 802/1900 [16:10<21:41,  1.18s/it]
+
+
Evaluating eval...:  42%|████▏     | 803/1900 [16:11<21:54,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 804/1900 [16:12<21:43,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 805/1900 [16:13<21:58,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 806/1900 [16:15<21:49,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 807/1900 [16:16<21:44,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 808/1900 [16:17<22:19,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 809/1900 [16:18<22:26,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 810/1900 [16:20<22:16,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 811/1900 [16:21<22:01,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 812/1900 [16:22<22:01,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 813/1900 [16:23<21:38,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 814/1900 [16:24<21:41,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 815/1900 [16:26<21:34,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 816/1900 [16:27<21:34,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 817/1900 [16:28<21:24,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 818/1900 [16:29<21:33,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 819/1900 [16:30<21:28,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 820/1900 [16:31<21:27,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 821/1900 [16:33<21:13,  1.18s/it]
+
+
Evaluating eval...:  43%|████▎     | 822/1900 [16:34<21:17,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 823/1900 [16:35<21:33,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 824/1900 [16:36<21:24,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 825/1900 [16:37<21:13,  1.18s/it]
+
+
Evaluating eval...:  43%|████▎     | 826/1900 [16:39<21:26,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 827/1900 [16:40<21:23,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 828/1900 [16:41<21:29,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 829/1900 [16:42<21:11,  1.19s/it]
+
+
Evaluating eval...:  44%|████▎     | 830/1900 [16:43<21:21,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 831/1900 [16:45<21:05,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 832/1900 [16:46<21:06,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 833/1900 [16:47<21:13,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 834/1900 [16:48<20:57,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 835/1900 [16:49<21:19,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 836/1900 [16:51<21:20,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 837/1900 [16:52<21:08,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 838/1900 [16:53<20:53,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 839/1900 [16:54<20:47,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 840/1900 [16:55<20:59,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 841/1900 [16:57<21:18,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 842/1900 [16:58<21:11,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 843/1900 [16:59<21:08,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 844/1900 [17:00<20:48,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 845/1900 [17:01<20:47,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 846/1900 [17:03<21:13,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 847/1900 [17:04<20:54,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 848/1900 [17:05<20:52,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 849/1900 [17:06<20:46,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 850/1900 [17:07<20:56,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 851/1900 [17:08<20:47,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 852/1900 [17:10<21:08,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 853/1900 [17:11<20:53,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 854/1900 [17:12<20:55,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 855/1900 [17:13<20:55,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 856/1900 [17:14<20:44,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 857/1900 [17:16<20:39,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 858/1900 [17:17<20:51,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 859/1900 [17:18<20:47,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 860/1900 [17:19<20:49,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 861/1900 [17:21<21:13,  1.23s/it]
+
+
Evaluating eval...:  45%|████▌     | 862/1900 [17:22<21:04,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 863/1900 [17:23<20:37,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 864/1900 [17:24<20:24,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 865/1900 [17:25<20:13,  1.17s/it]
+
+
Evaluating eval...:  46%|████▌     | 866/1900 [17:26<20:12,  1.17s/it]
+
+
Evaluating eval...:  46%|████▌     | 867/1900 [17:28<20:27,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 868/1900 [17:29<20:53,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 869/1900 [17:30<20:30,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 870/1900 [17:31<20:36,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 871/1900 [17:32<20:42,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 872/1900 [17:34<20:31,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 873/1900 [17:35<20:24,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 874/1900 [17:36<20:38,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 875/1900 [17:37<20:37,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 876/1900 [17:38<20:24,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 877/1900 [17:40<20:05,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 878/1900 [17:41<20:29,  1.20s/it]
+
+
Evaluating eval...:  46%|████▋     | 879/1900 [17:42<20:16,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 880/1900 [17:43<20:04,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 881/1900 [17:44<19:53,  1.17s/it]
+
+
Evaluating eval...:  46%|████▋     | 882/1900 [17:45<20:06,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 883/1900 [17:47<20:24,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 884/1900 [17:48<20:20,  1.20s/it]
+
+
Evaluating eval...:  47%|███��▋     | 885/1900 [17:49<20:03,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 886/1900 [17:50<19:57,  1.18s/it]
+
+
Evaluating eval...:  47%|████▋     | 887/1900 [17:51<20:05,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 888/1900 [17:53<20:07,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 889/1900 [17:54<20:03,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 890/1900 [17:55<19:54,  1.18s/it]
+
+
Evaluating eval...:  47%|████▋     | 891/1900 [17:56<20:08,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 892/1900 [17:57<20:12,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 893/1900 [17:59<20:18,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 894/1900 [18:00<20:02,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 895/1900 [18:01<20:15,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 896/1900 [18:02<20:00,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 897/1900 [18:03<19:54,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 898/1900 [18:05<20:36,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 899/1900 [18:06<20:09,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 900/1900 [18:07<20:08,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 901/1900 [18:08<19:54,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 902/1900 [18:10<20:04,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 903/1900 [18:11<19:56,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 904/1900 [18:12<19:53,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 905/1900 [18:13<19:45,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 906/1900 [18:14<19:41,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 907/1900 [18:16<20:07,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 908/1900 [18:17<19:47,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 909/1900 [18:18<19:55,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 910/1900 [18:19<19:44,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 911/1900 [18:20<20:00,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 912/1900 [18:22<19:50,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 913/1900 [18:23<19:53,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 914/1900 [18:24<19:50,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 915/1900 [18:25<20:16,  1.24s/it]
+
+
Evaluating eval...:  48%|████▊     | 916/1900 [18:26<20:05,  1.23s/it]
+
+
Evaluating eval...:  48%|████▊     | 917/1900 [18:28<19:45,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 918/1900 [18:29<19:54,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 919/1900 [18:30<19:44,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 920/1900 [18:31<19:33,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 921/1900 [18:32<19:21,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 922/1900 [18:34<19:13,  1.18s/it]
+
+
Evaluating eval...:  49%|████▊     | 923/1900 [18:35<19:48,  1.22s/it]
+
+
Evaluating eval...:  49%|████▊     | 924/1900 [18:36<19:27,  1.20s/it]
+
+
Evaluating eval...:  49%|████▊     | 925/1900 [18:37<19:36,  1.21s/it]
+
+
Evaluating eval...:  49%|████▊     | 926/1900 [18:38<19:22,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 927/1900 [18:40<19:08,  1.18s/it]
+
+
Evaluating eval...:  49%|████▉     | 928/1900 [18:41<19:41,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 929/1900 [18:42<19:23,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 930/1900 [18:43<19:06,  1.18s/it]
+
+
Evaluating eval...:  49%|████▉     | 931/1900 [18:44<19:30,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 932/1900 [18:46<19:52,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 933/1900 [18:47<19:42,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 934/1900 [18:48<19:23,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 935/1900 [18:49<19:26,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 936/1900 [18:51<20:04,  1.25s/it]
+
+
Evaluating eval...:  49%|████▉     | 937/1900 [18:52<19:56,  1.24s/it]
+
+
Evaluating eval...:  49%|████▉     | 938/1900 [18:53<19:36,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 939/1900 [18:54<19:33,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 940/1900 [18:55<19:25,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 941/1900 [18:57<19:31,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 942/1900 [18:58<19:42,  1.23s/it]
+
+
Evaluating eval...:  50%|████▉     | 943/1900 [18:59<19:22,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 944/1900 [19:00<19:12,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 945/1900 [19:01<18:58,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 946/1900 [19:03<18:59,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 947/1900 [19:04<19:05,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 948/1900 [19:05<19:03,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 949/1900 [19:06<19:01,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 950/1900 [19:07<19:03,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 951/1900 [19:09<19:21,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 952/1900 [19:10<19:29,  1.23s/it]
+
+
Evaluating eval...:  50%|█████     | 953/1900 [19:11<19:05,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 954/1900 [19:12<18:54,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 955/1900 [19:14<18:53,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 956/1900 [19:15<18:44,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 957/1900 [19:16<18:37,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 958/1900 [19:17<18:44,  1.19s/it]
+
+
Evaluating eval...:  50%|█████     | 959/1900 [19:18<18:36,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 960/1900 [19:19<18:38,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 961/1900 [19:21<19:06,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 962/1900 [19:22<18:47,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 963/1900 [19:23<18:56,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 964/1900 [19:24<19:14,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 965/1900 [19:26<19:06,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 966/1900 [19:27<18:41,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 967/1900 [19:28<18:26,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 968/1900 [19:29<18:29,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 969/1900 [19:30<18:42,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 970/1900 [19:32<18:50,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 971/1900 [19:33<18:38,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 972/1900 [19:34<18:57,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 973/1900 [19:35<18:36,  1.20s/it]
+
+
Evaluating eval...:  51%|█████▏    | 974/1900 [19:36<18:27,  1.20s/it]
+
+
Evaluating eval...:  51%|█████▏    | 975/1900 [19:38<18:49,  1.22s/it]
+
+
Evaluating eval...:  51%|█████▏    | 976/1900 [19:39<18:50,  1.22s/it]
+
+
Evaluating eval...:  51%|█████▏    | 977/1900 [19:40<18:29,  1.20s/it]
+
+
Evaluating eval...:  51%|█████▏    | 978/1900 [19:41<18:32,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 979/1900 [19:42<18:25,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 980/1900 [19:44<18:21,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 981/1900 [19:45<18:05,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 982/1900 [19:46<17:56,  1.17s/it]
+
+
Evaluating eval...:  52%|█████▏    | 983/1900 [19:47<18:08,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 984/1900 [19:48<18:10,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 985/1900 [19:50<18:11,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 986/1900 [19:51<18:03,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 987/1900 [19:52<18:06,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 988/1900 [19:53<17:58,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 989/1900 [19:54<18:08,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 990/1900 [19:56<18:37,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 991/1900 [19:57<18:23,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 992/1900 [19:58<18:11,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 993/1900 [19:59<18:10,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 994/1900 [20:00<17:59,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 995/1900 [20:02<18:16,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 996/1900 [20:03<18:01,  1.20s/it]
+
+
Evaluating eval...:  52%|████���▏    | 997/1900 [20:04<17:58,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 998/1900 [20:05<18:04,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 999/1900 [20:06<18:11,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1000/1900 [20:08<17:55,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1001/1900 [20:09<17:48,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1002/1900 [20:10<17:47,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1003/1900 [20:11<17:56,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1004/1900 [20:12<18:06,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1005/1900 [20:14<17:55,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1006/1900 [20:15<17:55,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1007/1900 [20:16<17:48,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1008/1900 [20:17<17:46,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1009/1900 [20:18<17:44,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1010/1900 [20:20<17:38,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1011/1900 [20:21<17:37,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1012/1900 [20:22<18:13,  1.23s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1013/1900 [20:23<17:50,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1014/1900 [20:24<18:05,  1.23s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1015/1900 [20:26<17:52,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1016/1900 [20:27<18:15,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1017/1900 [20:28<18:10,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1018/1900 [20:29<18:12,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1019/1900 [20:31<18:40,  1.27s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1020/1900 [20:32<18:31,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1021/1900 [20:33<18:18,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1022/1900 [20:35<18:29,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1023/1900 [20:36<18:14,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1024/1900 [20:37<18:05,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1025/1900 [20:38<17:44,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1026/1900 [20:39<17:54,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1027/1900 [20:41<17:45,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1028/1900 [20:42<17:34,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1029/1900 [20:43<17:28,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1030/1900 [20:44<17:25,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1031/1900 [20:45<17:49,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1032/1900 [20:47<17:41,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1033/1900 [20:48<17:27,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1034/1900 [20:49<18:01,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1035/1900 [20:50<17:39,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1036/1900 [20:52<17:40,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1037/1900 [20:53<17:50,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1038/1900 [20:54<17:40,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1039/1900 [20:55<17:42,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1040/1900 [20:56<17:29,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1041/1900 [20:58<17:30,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1042/1900 [20:59<17:32,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1043/1900 [21:00<17:16,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1044/1900 [21:01<17:16,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1045/1900 [21:03<17:08,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1046/1900 [21:04<17:02,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1047/1900 [21:05<16:55,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1048/1900 [21:06<17:05,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1049/1900 [21:07<17:13,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1050/1900 [21:09<17:33,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1051/1900 [21:10<17:29,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1052/1900 [21:11<17:25,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1053/1900 [21:12<17:17,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1054/1900 [21:13<17:10,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1055/1900 [21:15<16:54,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1056/1900 [21:16<17:26,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1057/1900 [21:17<17:53,  1.27s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1058/1900 [21:19<17:39,  1.26s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1059/1900 [21:20<17:09,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1060/1900 [21:21<16:50,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1061/1900 [21:22<16:38,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1062/1900 [21:23<16:35,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1063/1900 [21:24<16:46,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1064/1900 [21:26<17:00,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1065/1900 [21:27<17:02,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1066/1900 [21:28<16:50,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1067/1900 [21:29<17:04,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1068/1900 [21:31<16:53,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1069/1900 [21:32<16:58,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1070/1900 [21:33<16:53,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1071/1900 [21:34<17:02,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1072/1900 [21:36<17:04,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1073/1900 [21:37<16:44,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1074/1900 [21:38<16:39,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1075/1900 [21:39<16:40,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1076/1900 [21:40<16:51,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1077/1900 [21:42<16:42,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1078/1900 [21:43<16:20,  1.19s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1079/1900 [21:44<16:38,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1080/1900 [21:45<17:15,  1.26s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1081/1900 [21:47<17:03,  1.25s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1082/1900 [21:48<16:43,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1083/1900 [21:49<16:50,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1084/1900 [21:50<16:40,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1085/1900 [21:51<16:34,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1086/1900 [21:53<16:41,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1087/1900 [21:54<16:33,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1088/1900 [21:55<16:27,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1089/1900 [21:56<16:38,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1090/1900 [21:58<16:23,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1091/1900 [21:59<16:04,  1.19s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1092/1900 [22:00<16:21,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1093/1900 [22:01<16:08,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1094/1900 [22:02<16:04,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1095/1900 [22:03<16:00,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1096/1900 [22:05<15:48,  1.18s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1097/1900 [22:06<15:39,  1.17s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1098/1900 [22:07<15:59,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1099/1900 [22:08<16:22,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1100/1900 [22:10<16:12,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1101/1900 [22:11<16:02,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1102/1900 [22:12<15:48,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1103/1900 [22:13<16:04,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1104/1900 [22:14<15:48,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1105/1900 [22:16<16:24,  1.24s/it]
+
+
Evaluating eval...:  58%|███���█▊    | 1106/1900 [22:17<16:35,  1.25s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1107/1900 [22:18<16:31,  1.25s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1108/1900 [22:19<16:17,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1109/1900 [22:21<16:10,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1110/1900 [22:22<15:58,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1111/1900 [22:23<16:26,  1.25s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1112/1900 [22:24<16:09,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1113/1900 [22:25<16:14,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1114/1900 [22:27<16:04,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1115/1900 [22:28<16:03,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1116/1900 [22:29<16:20,  1.25s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1117/1900 [22:30<16:03,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1118/1900 [22:32<15:50,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1119/1900 [22:33<16:03,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1120/1900 [22:34<16:01,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1121/1900 [22:35<15:49,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1122/1900 [22:36<15:34,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1123/1900 [22:38<15:46,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1124/1900 [22:39<15:38,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1125/1900 [22:40<15:31,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1126/1900 [22:41<15:32,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1127/1900 [22:42<15:26,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1128/1900 [22:44<15:40,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1129/1900 [22:45<15:23,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1130/1900 [22:46<15:13,  1.19s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1131/1900 [22:47<15:24,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1132/1900 [22:48<15:24,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1133/1900 [22:50<15:29,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1134/1900 [22:51<15:20,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1135/1900 [22:52<15:50,  1.24s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1136/1900 [22:53<15:32,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1137/1900 [22:55<15:19,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1138/1900 [22:56<15:31,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1139/1900 [22:57<15:24,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1140/1900 [22:58<15:22,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1141/1900 [23:00<15:37,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1142/1900 [23:01<15:19,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1143/1900 [23:02<15:13,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1144/1900 [23:03<15:14,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1145/1900 [23:04<15:24,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1146/1900 [23:06<15:33,  1.24s/it]
+
+
Evaluating eval...:  60%|██████    | 1147/1900 [23:07<15:38,  1.25s/it]
+
+
Evaluating eval...:  60%|██████    | 1148/1900 [23:08<15:29,  1.24s/it]
+
+
Evaluating eval...:  60%|██████    | 1149/1900 [23:09<15:10,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1150/1900 [23:11<15:17,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1151/1900 [23:12<15:06,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1152/1900 [23:13<14:56,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1153/1900 [23:14<15:00,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1154/1900 [23:15<15:00,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1155/1900 [23:16<14:57,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1156/1900 [23:18<14:46,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1157/1900 [23:19<14:45,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1158/1900 [23:20<15:14,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1159/1900 [23:21<14:56,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1160/1900 [23:23<14:54,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1161/1900 [23:24<14:54,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1162/1900 [23:25<14:42,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1163/1900 [23:26<14:35,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1164/1900 [23:27<14:24,  1.17s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1165/1900 [23:28<14:27,  1.18s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1166/1900 [23:30<14:35,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1167/1900 [23:31<14:44,  1.21s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1168/1900 [23:32<14:41,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1169/1900 [23:33<14:35,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1170/1900 [23:35<14:47,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1171/1900 [23:36<14:54,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1172/1900 [23:37<14:43,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1173/1900 [23:38<14:35,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1174/1900 [23:39<14:28,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1175/1900 [23:41<14:46,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1176/1900 [23:42<14:53,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1177/1900 [23:43<14:35,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1178/1900 [23:44<14:19,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1179/1900 [23:45<14:22,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1180/1900 [23:47<14:29,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1181/1900 [23:48<14:18,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1182/1900 [23:49<14:27,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1183/1900 [23:50<14:33,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1184/1900 [23:52<14:47,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1185/1900 [23:53<14:47,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1186/1900 [23:54<14:58,  1.26s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1187/1900 [23:55<14:49,  1.25s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1188/1900 [23:57<14:42,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1189/1900 [23:58<14:35,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1190/1900 [23:59<14:24,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1191/1900 [24:00<14:37,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1192/1900 [24:01<14:36,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1193/1900 [24:03<14:23,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1194/1900 [24:04<14:31,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1195/1900 [24:05<14:24,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1196/1900 [24:06<14:18,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1197/1900 [24:08<14:28,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1198/1900 [24:09<14:17,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1199/1900 [24:10<14:22,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1200/1900 [24:11<14:13,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1201/1900 [24:12<14:00,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1202/1900 [24:14<13:51,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1203/1900 [24:15<14:07,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1204/1900 [24:16<14:16,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1205/1900 [24:17<14:12,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1206/1900 [24:19<14:19,  1.24s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1207/1900 [24:20<14:02,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1208/1900 [24:21<13:57,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1209/1900 [24:22<13:48,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1210/1900 [24:23<14:02,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1211/1900 [24:25<14:09,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1212/1900 [24:26<14:06,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1213/1900 [24:27<13:54,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1214/1900 [24:28<13:51,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1215/1900 [24:29<13:48,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1216/1900 [24:31<13:54,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1217/1900 [24:32<13:53,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1218/1900 [24:33<13:59,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1219/1900 [24:34<13:49,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1220/1900 [24:36<13:55,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1221/1900 [24:37<13:47,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1222/1900 [24:38<13:36,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1223/1900 [24:39<13:37,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1224/1900 [24:40<13:28,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1225/1900 [24:42<13:34,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1226/1900 [24:43<13:34,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1227/1900 [24:44<13:31,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1228/1900 [24:45<13:23,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1229/1900 [24:46<13:20,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1230/1900 [24:48<13:29,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1231/1900 [24:49<13:27,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1232/1900 [24:50<13:25,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1233/1900 [24:51<13:22,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1234/1900 [24:52<13:23,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1235/1900 [24:54<13:29,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1236/1900 [24:55<13:15,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1237/1900 [24:56<13:07,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1238/1900 [24:57<13:05,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1239/1900 [24:58<13:08,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1240/1900 [25:00<13:47,  1.25s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1241/1900 [25:01<13:31,  1.23s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1242/1900 [25:02<13:29,  1.23s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1243/1900 [25:03<13:47,  1.26s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1244/1900 [25:05<13:27,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1245/1900 [25:06<13:14,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1246/1900 [25:07<13:21,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1247/1900 [25:08<13:11,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1248/1900 [25:09<12:57,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1249/1900 [25:11<13:02,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1250/1900 [25:12<12:57,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1251/1900 [25:13<12:49,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1252/1900 [25:14<12:46,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1253/1900 [25:15<12:51,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1254/1900 [25:17<13:00,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1255/1900 [25:18<13:07,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1256/1900 [25:19<13:01,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1257/1900 [25:20<12:48,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1258/1900 [25:21<12:51,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1259/1900 [25:23<12:42,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1260/1900 [25:24<12:48,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1261/1900 [25:25<12:55,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1262/1900 [25:26<12:44,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1263/1900 [25:27<12:51,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1264/1900 [25:29<12:49,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1265/1900 [25:30<12:47,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1266/1900 [25:31<13:06,  1.24s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1267/1900 [25:32<12:57,  1.23s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1268/1900 [25:34<12:49,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1269/1900 [25:35<12:55,  1.23s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1270/1900 [25:36<12:48,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1271/1900 [25:37<12:49,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1272/1900 [25:38<12:42,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1273/1900 [25:40<12:37,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1274/1900 [25:41<12:35,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1275/1900 [25:42<12:30,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1276/1900 [25:43<12:31,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1277/1900 [25:44<12:32,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1278/1900 [25:46<12:23,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1279/1900 [25:47<12:21,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1280/1900 [25:48<12:17,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1281/1900 [25:49<12:10,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1282/1900 [25:50<12:08,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1283/1900 [25:52<12:10,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1284/1900 [25:53<12:11,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1285/1900 [25:54<12:13,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1286/1900 [25:55<12:20,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1287/1900 [25:57<12:40,  1.24s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1288/1900 [25:58<12:39,  1.24s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1289/1900 [25:59<12:26,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1290/1900 [26:00<12:22,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1291/1900 [26:01<12:15,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1292/1900 [26:03<12:16,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1293/1900 [26:04<12:17,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1294/1900 [26:05<12:25,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1295/1900 [26:06<12:16,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1296/1900 [26:07<12:16,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1297/1900 [26:09<12:05,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1298/1900 [26:10<12:03,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1299/1900 [26:11<12:00,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1300/1900 [26:12<12:10,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1301/1900 [26:13<12:13,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1302/1900 [26:15<12:11,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1303/1900 [26:16<12:17,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1304/1900 [26:17<12:18,  1.24s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1305/1900 [26:18<12:09,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1306/1900 [26:20<12:11,  1.23s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1307/1900 [26:21<12:02,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1308/1900 [26:22<12:02,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1309/1900 [26:23<12:01,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1310/1900 [26:25<12:00,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1311/1900 [26:26<12:08,  1.24s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1312/1900 [26:27<11:55,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1313/1900 [26:28<11:48,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1314/1900 [26:29<11:41,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1315/1900 [26:30<11:36,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1316/1900 [26:32<11:43,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1317/1900 [26:33<11:41,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1318/1900 [26:34<11:49,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1319/1900 [26:35<11:41,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1320/1900 [26:37<11:30,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1321/1900 [26:38<11:52,  1.23s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1322/1900 [26:39<11:44,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1323/1900 [26:40<11:44,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1324/1900 [26:41<11:39,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1325/1900 [26:43<11:30,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1326/1900 [26:44<11:29,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1327/1900 [26:45<11:26,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1328/1900 [26:46<11:39,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1329/1900 [26:47<11:29,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1330/1900 [26:49<11:30,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1331/1900 [26:50<11:25,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1332/1900 [26:51<11:21,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1333/1900 [26:52<11:19,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1334/1900 [26:53<11:23,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1335/1900 [26:55<11:20,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1336/1900 [26:56<11:19,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1337/1900 [26:57<11:25,  1.22s/it]
+
+
Evaluating eval...:  70%|███████   | 1338/1900 [26:58<11:20,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1339/1900 [27:00<11:15,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1340/1900 [27:01<11:12,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1341/1900 [27:02<11:06,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1342/1900 [27:03<11:15,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1343/1900 [27:04<11:08,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1344/1900 [27:06<11:06,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1345/1900 [27:07<11:17,  1.22s/it]
+
+
Evaluating eval...:  71%|███████   | 1346/1900 [27:08<11:38,  1.26s/it]
+
+
Evaluating eval...:  71%|███████   | 1347/1900 [27:09<11:24,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1348/1900 [27:10<11:07,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1349/1900 [27:12<11:32,  1.26s/it]
+
+
Evaluating eval...:  71%|███████   | 1350/1900 [27:13<11:23,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1351/1900 [27:14<11:22,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1352/1900 [27:16<11:19,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1353/1900 [27:17<11:23,  1.25s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1354/1900 [27:18<11:16,  1.24s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1355/1900 [27:19<11:07,  1.22s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1356/1900 [27:20<11:17,  1.25s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1357/1900 [27:22<11:05,  1.23s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1358/1900 [27:23<10:59,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1359/1900 [27:24<11:00,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1360/1900 [27:25<10:51,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1361/1900 [27:27<11:00,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1362/1900 [27:28<10:45,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1363/1900 [27:29<11:03,  1.24s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1364/1900 [27:30<10:51,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1365/1900 [27:31<10:41,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1366/1900 [27:32<10:32,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1367/1900 [27:34<10:33,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1368/1900 [27:35<10:40,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1369/1900 [27:36<10:46,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1370/1900 [27:37<10:44,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1371/1900 [27:39<10:42,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1372/1900 [27:40<10:34,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1373/1900 [27:41<10:27,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1374/1900 [27:42<10:30,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1375/1900 [27:43<10:27,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1376/1900 [27:45<10:29,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1377/1900 [27:46<10:30,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1378/1900 [27:47<10:23,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1379/1900 [27:48<10:24,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1380/1900 [27:49<10:26,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1381/1900 [27:51<10:31,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1382/1900 [27:52<10:22,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1383/1900 [27:53<10:24,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1384/1900 [27:54<10:18,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1385/1900 [27:55<10:20,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1386/1900 [27:57<10:23,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1387/1900 [27:58<10:14,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1388/1900 [27:59<10:13,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1389/1900 [28:00<10:07,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1390/1900 [28:01<10:23,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1391/1900 [28:03<10:19,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1392/1900 [28:04<10:16,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1393/1900 [28:05<10:10,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1394/1900 [28:06<10:23,  1.23s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1395/1900 [28:08<10:14,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1396/1900 [28:09<10:06,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1397/1900 [28:10<09:59,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1398/1900 [28:11<10:05,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1399/1900 [28:12<10:04,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1400/1900 [28:13<09:57,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1401/1900 [28:15<10:12,  1.23s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1402/1900 [28:16<09:57,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1403/1900 [28:17<09:49,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1404/1900 [28:18<09:49,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1405/1900 [28:19<09:43,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1406/1900 [28:21<09:45,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1407/1900 [28:22<09:50,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1408/1900 [28:23<10:00,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1409/1900 [28:24<09:56,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1410/1900 [28:26<09:51,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1411/1900 [28:27<09:51,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1412/1900 [28:28<09:48,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1413/1900 [28:29<09:45,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1414/1900 [28:30<09:45,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1415/1900 [28:32<09:41,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1416/1900 [28:33<09:34,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1417/1900 [28:34<09:35,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1418/1900 [28:35<09:30,  1.18s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1419/1900 [28:36<09:45,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1420/1900 [28:38<09:46,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1421/1900 [28:39<09:45,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1422/1900 [28:40<09:50,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1423/1900 [28:41<09:41,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1424/1900 [28:42<09:43,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1425/1900 [28:44<09:34,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1426/1900 [28:45<09:35,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1427/1900 [28:46<09:34,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1428/1900 [28:47<09:43,  1.24s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1429/1900 [28:49<09:38,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1430/1900 [28:50<09:32,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1431/1900 [28:51<09:37,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1432/1900 [28:52<09:56,  1.28s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1433/1900 [28:54<09:44,  1.25s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1434/1900 [28:55<09:34,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1435/1900 [28:56<09:29,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1436/1900 [28:57<09:29,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1437/1900 [28:58<09:22,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1438/1900 [29:00<09:16,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1439/1900 [29:01<09:12,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1440/1900 [29:02<09:17,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1441/1900 [29:03<09:12,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1442/1900 [29:05<09:23,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1443/1900 [29:06<09:32,  1.25s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1444/1900 [29:07<09:25,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1445/1900 [29:08<09:18,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1446/1900 [29:09<09:22,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1447/1900 [29:11<09:17,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1448/1900 [29:12<09:09,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1449/1900 [29:13<09:05,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1450/1900 [29:14<09:10,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1451/1900 [29:16<09:13,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1452/1900 [29:17<09:08,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1453/1900 [29:18<09:10,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1454/1900 [29:19<09:25,  1.27s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1455/1900 [29:21<09:19,  1.26s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1456/1900 [29:22<09:16,  1.25s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1457/1900 [29:23<09:09,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1458/1900 [29:24<09:09,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1459/1900 [29:25<08:56,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1460/1900 [29:27<08:48,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1461/1900 [29:28<08:48,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1462/1900 [29:29<08:49,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1463/1900 [29:30<08:45,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1464/1900 [29:32<08:48,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1465/1900 [29:33<08:48,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1466/1900 [29:34<08:54,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1467/1900 [29:35<08:48,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1468/1900 [29:36<08:44,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1469/1900 [29:38<08:43,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1470/1900 [29:39<08:36,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1471/1900 [29:40<08:40,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1472/1900 [29:41<08:32,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1473/1900 [29:42<08:33,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1474/1900 [29:44<08:33,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1475/1900 [29:45<08:36,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1476/1900 [29:46<08:36,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1477/1900 [29:47<08:34,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1478/1900 [29:48<08:32,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1479/1900 [29:50<08:40,  1.24s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1480/1900 [29:51<08:30,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1481/1900 [29:52<08:29,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1482/1900 [29:53<08:26,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1483/1900 [29:55<08:18,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1484/1900 [29:56<08:20,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1485/1900 [29:57<08:28,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1486/1900 [29:58<08:21,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1487/1900 [29:59<08:28,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1488/1900 [30:01<08:19,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1489/1900 [30:02<08:13,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1490/1900 [30:03<08:12,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1491/1900 [30:04<08:07,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1492/1900 [30:05<08:10,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1493/1900 [30:07<08:15,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1494/1900 [30:08<08:07,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1495/1900 [30:09<08:02,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1496/1900 [30:10<07:57,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1497/1900 [30:11<07:50,  1.17s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1498/1900 [30:13<08:03,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1499/1900 [30:14<08:09,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1500/1900 [30:15<08:08,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1501/1900 [30:16<08:00,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1502/1900 [30:17<07:57,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1503/1900 [30:19<07:56,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1504/1900 [30:20<07:53,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1505/1900 [30:21<07:53,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1506/1900 [30:22<07:57,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1507/1900 [30:23<07:50,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1508/1900 [30:25<07:56,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1509/1900 [30:26<07:56,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1510/1900 [30:27<07:48,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1511/1900 [30:28<07:50,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1512/1900 [30:30<07:59,  1.24s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1513/1900 [30:31<07:57,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1514/1900 [30:32<07:55,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1515/1900 [30:33<08:01,  1.25s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1516/1900 [30:35<08:01,  1.25s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1517/1900 [30:36<07:51,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1518/1900 [30:37<07:40,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1519/1900 [30:38<07:33,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1520/1900 [30:39<07:40,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1521/1900 [30:41<07:39,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1522/1900 [30:42<07:31,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1523/1900 [30:43<07:32,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1524/1900 [30:44<07:30,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1525/1900 [30:45<07:29,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1526/1900 [30:46<07:25,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1527/1900 [30:48<07:26,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1528/1900 [30:49<07:29,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1529/1900 [30:50<07:22,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1530/1900 [30:51<07:28,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1531/1900 [30:53<07:27,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1532/1900 [30:54<07:33,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1533/1900 [30:55<07:26,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1534/1900 [30:56<07:25,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1535/1900 [30:57<07:17,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1536/1900 [30:59<07:12,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1537/1900 [31:00<07:16,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1538/1900 [31:01<07:13,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1539/1900 [31:02<07:22,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1540/1900 [31:03<07:16,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1541/1900 [31:05<07:24,  1.24s/it]
+
+
Evaluating eval...:  81%|████████  | 1542/1900 [31:06<07:18,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1543/1900 [31:07<07:18,  1.23s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1544/1900 [31:08<07:15,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1545/1900 [31:10<07:08,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1546/1900 [31:11<07:09,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1547/1900 [31:12<07:11,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1548/1900 [31:13<07:05,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1549/1900 [31:14<07:00,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1550/1900 [31:16<07:07,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1551/1900 [31:17<07:06,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1552/1900 [31:18<07:00,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1553/1900 [31:19<06:58,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1554/1900 [31:20<06:57,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1555/1900 [31:22<06:54,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1556/1900 [31:23<07:03,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1557/1900 [31:24<06:57,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1558/1900 [31:25<07:01,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1559/1900 [31:27<07:03,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1560/1900 [31:28<06:53,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1561/1900 [31:29<06:57,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1562/1900 [31:30<06:58,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1563/1900 [31:32<06:57,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1564/1900 [31:33<06:50,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1565/1900 [31:34<06:48,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1566/1900 [31:35<06:47,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1567/1900 [31:36<06:46,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1568/1900 [31:38<06:59,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1569/1900 [31:39<07:01,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1570/1900 [31:40<06:57,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1571/1900 [31:42<06:49,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1572/1900 [31:43<06:52,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1573/1900 [31:44<06:43,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1574/1900 [31:45<06:39,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1575/1900 [31:46<06:39,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1576/1900 [31:48<06:32,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1577/1900 [31:49<06:35,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1578/1900 [31:50<06:33,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1579/1900 [31:51<06:30,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1580/1900 [31:53<06:34,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1581/1900 [31:54<06:43,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1582/1900 [31:55<06:43,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1583/1900 [31:56<06:41,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1584/1900 [31:58<06:42,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1585/1900 [31:59<06:41,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1586/1900 [32:00<06:34,  1.26s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1587/1900 [32:01<06:23,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1588/1900 [32:03<06:15,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1589/1900 [32:04<06:16,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1590/1900 [32:05<06:17,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1591/1900 [32:06<06:19,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1592/1900 [32:07<06:12,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1593/1900 [32:09<06:12,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1594/1900 [32:10<06:14,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1595/1900 [32:11<06:11,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1596/1900 [32:12<06:10,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1597/1900 [32:14<06:12,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1598/1900 [32:15<06:03,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1599/1900 [32:16<05:57,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1600/1900 [32:17<05:55,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1601/1900 [32:18<05:52,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1602/1900 [32:19<05:52,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1603/1900 [32:21<05:52,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1604/1900 [32:22<05:57,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1605/1900 [32:23<05:50,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1606/1900 [32:24<05:48,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1607/1900 [32:25<05:46,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1608/1900 [32:27<05:48,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1609/1900 [32:28<05:58,  1.23s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1610/1900 [32:29<05:52,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1611/1900 [32:30<05:46,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1612/1900 [32:31<05:41,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1613/1900 [32:32<05:36,  1.17s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1614/1900 [32:34<05:40,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1615/1900 [32:35<05:41,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1616/1900 [32:36<05:37,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1617/1900 [32:37<05:47,  1.23s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1618/1900 [32:39<05:46,  1.23s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1619/1900 [32:40<05:44,  1.23s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1620/1900 [32:41<05:41,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1621/1900 [32:42<05:38,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1622/1900 [32:43<05:31,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1623/1900 [32:45<05:29,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1624/1900 [32:46<05:25,  1.18s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1625/1900 [32:47<05:28,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1626/1900 [32:48<05:35,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1627/1900 [32:50<05:39,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1628/1900 [32:51<05:39,  1.25s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1629/1900 [32:52<05:36,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1630/1900 [32:53<05:31,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1631/1900 [32:55<05:42,  1.27s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1632/1900 [32:56<05:36,  1.26s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1633/1900 [32:57<05:32,  1.25s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1634/1900 [32:58<05:27,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1635/1900 [32:59<05:23,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1636/1900 [33:01<05:20,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1637/1900 [33:02<05:21,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1638/1900 [33:03<05:15,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1639/1900 [33:04<05:16,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1640/1900 [33:06<05:14,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1641/1900 [33:07<05:13,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1642/1900 [33:08<05:15,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1643/1900 [33:09<05:13,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1644/1900 [33:10<05:05,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1645/1900 [33:11<05:02,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1646/1900 [33:13<05:06,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1647/1900 [33:14<05:06,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1648/1900 [33:15<05:05,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1649/1900 [33:16<05:02,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1650/1900 [33:18<05:02,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1651/1900 [33:19<04:57,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1652/1900 [33:20<04:56,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1653/1900 [33:21<04:54,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1654/1900 [33:22<04:53,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1655/1900 [33:24<04:59,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1656/1900 [33:25<04:58,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1657/1900 [33:26<04:57,  1.23s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1658/1900 [33:27<04:55,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1659/1900 [33:29<05:00,  1.25s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1660/1900 [33:30<04:57,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1661/1900 [33:31<04:59,  1.25s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1662/1900 [33:32<04:52,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1663/1900 [33:33<04:46,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1664/1900 [33:35<04:45,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1665/1900 [33:36<04:46,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1666/1900 [33:37<04:54,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1667/1900 [33:38<04:52,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1668/1900 [33:40<04:46,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1669/1900 [33:41<04:43,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1670/1900 [33:42<04:41,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1671/1900 [33:43<04:37,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1672/1900 [33:45<04:37,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1673/1900 [33:46<04:40,  1.24s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1674/1900 [33:47<04:37,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1675/1900 [33:48<04:35,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1676/1900 [33:49<04:31,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1677/1900 [33:51<04:26,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1678/1900 [33:52<04:22,  1.18s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1679/1900 [33:53<04:22,  1.19s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1680/1900 [33:54<04:21,  1.19s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1681/1900 [33:55<04:21,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1682/1900 [33:56<04:19,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1683/1900 [33:58<04:20,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1684/1900 [33:59<04:18,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1685/1900 [34:00<04:14,  1.18s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1686/1900 [34:01<04:14,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1687/1900 [34:03<04:17,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1688/1900 [34:04<04:16,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1689/1900 [34:05<04:13,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1690/1900 [34:06<04:10,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1691/1900 [34:07<04:14,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1692/1900 [34:09<04:10,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1693/1900 [34:10<04:09,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1694/1900 [34:11<04:09,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1695/1900 [34:12<04:06,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1696/1900 [34:13<04:03,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1697/1900 [34:15<04:07,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1698/1900 [34:16<04:05,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1699/1900 [34:17<04:00,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1700/1900 [34:18<04:01,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1701/1900 [34:19<04:02,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1702/1900 [34:21<04:02,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1703/1900 [34:22<03:59,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1704/1900 [34:23<03:55,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1705/1900 [34:24<03:51,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1706/1900 [34:25<03:51,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1707/1900 [34:27<03:48,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1708/1900 [34:28<03:51,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1709/1900 [34:29<03:49,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1710/1900 [34:30<03:48,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1711/1900 [34:31<03:44,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1712/1900 [34:33<03:42,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1713/1900 [34:34<03:38,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1714/1900 [34:35<03:36,  1.16s/it]
+
+
Evaluating eval...:  90%|█████████ | 1715/1900 [34:36<03:39,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1716/1900 [34:37<03:38,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1717/1900 [34:39<03:45,  1.23s/it]
+
+
Evaluating eval...:  90%|█████████ | 1718/1900 [34:40<03:43,  1.23s/it]
+
+
Evaluating eval...:  90%|█████████ | 1719/1900 [34:41<03:39,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1720/1900 [34:42<03:39,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1721/1900 [34:43<03:35,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1722/1900 [34:45<03:36,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1723/1900 [34:46<03:31,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████ | 1724/1900 [34:47<03:37,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1725/1900 [34:48<03:35,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1726/1900 [34:50<03:35,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1727/1900 [34:51<03:34,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1728/1900 [34:52<03:30,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1729/1900 [34:53<03:25,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1730/1900 [34:54<03:27,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1731/1900 [34:56<03:23,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1732/1900 [34:57<03:21,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1733/1900 [34:58<03:21,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1734/1900 [34:59<03:17,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1735/1900 [35:00<03:16,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1736/1900 [35:02<03:15,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1737/1900 [35:03<03:14,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1738/1900 [35:04<03:13,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1739/1900 [35:05<03:13,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1740/1900 [35:06<03:12,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1741/1900 [35:08<03:11,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1742/1900 [35:09<03:07,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1743/1900 [35:10<03:07,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1744/1900 [35:11<03:06,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1745/1900 [35:12<03:03,  1.18s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1746/1900 [35:14<03:07,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1747/1900 [35:15<03:04,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1748/1900 [35:16<03:05,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1749/1900 [35:17<03:05,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1750/1900 [35:18<03:04,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1751/1900 [35:20<03:03,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1752/1900 [35:21<03:01,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1753/1900 [35:22<02:57,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1754/1900 [35:23<02:56,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1755/1900 [35:25<02:57,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1756/1900 [35:26<02:56,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1757/1900 [35:27<03:00,  1.26s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1758/1900 [35:28<02:55,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1759/1900 [35:29<02:51,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1760/1900 [35:31<02:47,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1761/1900 [35:32<02:45,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1762/1900 [35:33<02:44,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1763/1900 [35:34<02:42,  1.18s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1764/1900 [35:35<02:44,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1765/1900 [35:37<02:44,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1766/1900 [35:38<02:43,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1767/1900 [35:39<02:40,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1768/1900 [35:40<02:41,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1769/1900 [35:42<02:41,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1770/1900 [35:43<02:42,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1771/1900 [35:44<02:40,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1772/1900 [35:45<02:36,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1773/1900 [35:47<02:35,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1774/1900 [35:48<02:32,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1775/1900 [35:49<02:32,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1776/1900 [35:50<02:30,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1777/1900 [35:51<02:27,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1778/1900 [35:53<02:25,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1779/1900 [35:54<02:23,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1780/1900 [35:55<02:22,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1781/1900 [35:56<02:19,  1.17s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1782/1900 [35:57<02:20,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1783/1900 [35:58<02:21,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1784/1900 [36:00<02:19,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1785/1900 [36:01<02:16,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1786/1900 [36:02<02:14,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1787/1900 [36:03<02:13,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1788/1900 [36:04<02:12,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1789/1900 [36:06<02:10,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1790/1900 [36:07<02:11,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1791/1900 [36:08<02:09,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1792/1900 [36:09<02:08,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1793/1900 [36:10<02:09,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1794/1900 [36:12<02:06,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1795/1900 [36:13<02:05,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1796/1900 [36:14<02:03,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1797/1900 [36:15<02:03,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1798/1900 [36:16<02:04,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1799/1900 [36:18<02:02,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1800/1900 [36:19<02:01,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1801/1900 [36:20<01:57,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1802/1900 [36:21<01:57,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1803/1900 [36:22<01:57,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1804/1900 [36:24<01:54,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1805/1900 [36:25<01:52,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1806/1900 [36:26<01:51,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1807/1900 [36:27<01:50,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1808/1900 [36:28<01:49,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1809/1900 [36:29<01:47,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1810/1900 [36:31<01:47,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1811/1900 [36:32<01:46,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1812/1900 [36:33<01:45,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1813/1900 [36:34<01:44,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1814/1900 [36:35<01:42,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1815/1900 [36:37<01:40,  1.18s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1816/1900 [36:38<01:39,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1817/1900 [36:39<01:41,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1818/1900 [36:40<01:38,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1819/1900 [36:41<01:37,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1820/1900 [36:43<01:36,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1821/1900 [36:44<01:35,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1822/1900 [36:45<01:34,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1823/1900 [36:46<01:32,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1824/1900 [36:47<01:31,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1825/1900 [36:49<01:30,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1826/1900 [36:50<01:29,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1827/1900 [36:51<01:29,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1828/1900 [36:52<01:28,  1.24s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1829/1900 [36:54<01:29,  1.25s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1830/1900 [36:55<01:26,  1.24s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1831/1900 [36:56<01:23,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1832/1900 [36:57<01:21,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1833/1900 [36:58<01:19,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1834/1900 [37:00<01:19,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1835/1900 [37:01<01:17,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1836/1900 [37:02<01:16,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1837/1900 [37:03<01:17,  1.23s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1838/1900 [37:05<01:15,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1839/1900 [37:06<01:13,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1840/1900 [37:07<01:13,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1841/1900 [37:08<01:11,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1842/1900 [37:09<01:10,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1843/1900 [37:11<01:08,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1844/1900 [37:12<01:07,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1845/1900 [37:13<01:05,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1846/1900 [37:14<01:05,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1847/1900 [37:15<01:03,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1848/1900 [37:17<01:03,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1849/1900 [37:18<01:01,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1850/1900 [37:19<01:00,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1851/1900 [37:20<00:59,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1852/1900 [37:21<00:57,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1853/1900 [37:23<00:56,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1854/1900 [37:24<00:54,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1855/1900 [37:25<00:54,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1856/1900 [37:26<00:53,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1857/1900 [37:27<00:51,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1858/1900 [37:29<00:50,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1859/1900 [37:30<00:49,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1860/1900 [37:31<00:48,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1861/1900 [37:32<00:46,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1862/1900 [37:33<00:45,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1863/1900 [37:35<00:44,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1864/1900 [37:36<00:42,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1865/1900 [37:37<00:41,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1866/1900 [37:38<00:40,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1867/1900 [37:39<00:39,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1868/1900 [37:41<00:38,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1869/1900 [37:42<00:37,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1870/1900 [37:43<00:36,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1871/1900 [37:44<00:35,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1872/1900 [37:45<00:34,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1873/1900 [37:47<00:32,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1874/1900 [37:48<00:31,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1875/1900 [37:49<00:30,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1876/1900 [37:50<00:28,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1877/1900 [37:51<00:27,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1878/1900 [37:53<00:27,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1879/1900 [37:54<00:25,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1880/1900 [37:55<00:24,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1881/1900 [37:56<00:22,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1882/1900 [37:58<00:21,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1883/1900 [37:59<00:21,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1884/1900 [38:00<00:19,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1885/1900 [38:01<00:18,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1886/1900 [38:04<00:22,  1.61s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1887/1900 [38:05<00:19,  1.47s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1888/1900 [38:06<00:16,  1.39s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1889/1900 [38:07<00:14,  1.33s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1890/1900 [38:09<00:12,  1.28s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1891/1900 [38:10<00:11,  1.24s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1892/1900 [38:11<00:09,  1.23s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1893/1900 [38:12<00:08,  1.22s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1894/1900 [38:13<00:07,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1895/1900 [38:14<00:06,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1896/1900 [38:16<00:04,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1897/1900 [38:17<00:03,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1898/1900 [38:18<00:02,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1899/1900 [38:19<00:01,  1.20s/it]
+
+
Evaluating eval...: 100%|██████████| 1900/1900 [38:21<00:00,  1.31s/it]
Evaluating eval...: 100%|██████████| 1900/1900 [38:21<00:00,  1.21s/it]
+Eval results for step (65000 / 100000 | Eval Loss: 1.0027118921279907 | Eval wer: 25.634241120088696 | Eval wer_ortho: 28.889890147614146 |)
+
                                                                             
Eval results for step (65000 / 100000 | Eval Loss: 1.0027118921279907 | Eval wer: 25.634241120088696 | Eval wer_ortho: 28.889890147614146 |)
+
Train steps ... :  65%|██████▌   | 65000/100000 [19:49:42<5:41:57,  1.71it/s]
Train steps ... :  65%|██████▌   | 65001/100000 [19:49:42<7424:00:46, 763.63s/it]
Train steps ... :  65%|██████▌   | 65002/100000 [19:49:43<5198:21:32, 534.72s/it]
Train steps ... :  65%|██████▌   | 65003/100000 [19:49:43<3640:27:14, 374.48s/it]
Train steps ... :  65%|██████▌   | 65004/100000 [19:49:44<2549:56:38, 262.31s/it]
Train steps ... :  65%|██████▌   | 65005/100000 [19:49:44<1786:36:55, 183.79s/it]
Train steps ... :  65%|██████▌   | 65006/100000 [19:49:45<1252:18:24, 128.83s/it]
Train steps ... :  65%|██████▌   | 65007/100000 [19:49:46<878:17:21, 90.36s/it]  
Train steps ... :  65%|██████▌   | 65008/100000 [19:49:46<616:29:42, 63.43s/it]
Train steps ... :  65%|██████▌   | 65009/100000 [19:49:47<433:14:10, 44.57s/it]
Train steps ... :  65%|██████▌   | 65010/100000 [19:49:47<304:58:03, 31.38s/it]
Train steps ... :  65%|██████▌   | 65011/100000 [19:49:48<215:10:14, 22.14s/it]
Train steps ... :  65%|██████▌   | 65012/100000 [19:49:49<152:19:34, 15.67s/it]
Train steps ... :  65%|██████▌   | 65013/100000 [19:49:49<108:19:55, 11.15s/it]
Train steps ... :  65%|██████▌   | 65014/100000 [19:49:50<77:31:59,  7.98s/it] 
Train steps ... :  65%|██████▌   | 65015/100000 [19:49:50<55:58:28,  5.76s/it]
Train steps ... :  65%|██████▌   | 65016/100000 [19:49:51<40:52:50,  4.21s/it]
Train steps ... :  65%|██████▌   | 65017/100000 [19:49:51<30:18:47,  3.12s/it]
Train steps ... :  65%|██████▌   | 65018/100000 [19:49:52<22:55:28,  2.36s/it]
Train steps ... :  65%|██████▌   | 65019/100000 [19:49:53<17:44:31,  1.83s/it]
Train steps ... :  65%|██████▌   | 65020/100000 [19:49:53<14:07:36,  1.45s/it]
Train steps ... :  65%|██████▌   | 65021/100000 [19:49:54<11:35:28,  1.19s/it]
Train steps ... :  65%|██████▌   | 65022/100000 [19:49:54<9:48:59,  1.01s/it] 
Train steps ... :  65%|██████▌   | 65023/100000 [19:49:55<8:34:47,  1.13it/s]
Train steps ... :  65%|██████▌   | 65024/100000 [19:49:56<7:42:18,  1.26it/s]
Train steps ... :  65%|██████▌   | 65025/100000 [19:49:56<7:05:36,  1.37it/s]Step... (65025 / 100000 | Loss: 0.9945952892303467, Learning Rate: 3.5150753768844224e-05)
+
                                                                             
Step... (65025 / 100000 | Loss: 0.7216123342514038, Learning Rate: 3.5150753768844224e-05)
+
Train steps ... :  65%|██████▌   | 65025/100000 [19:49:56<7:05:36,  1.37it/s]
Train steps ... :  65%|██████▌   | 65026/100000 [19:49:57<6:40:12,  1.46it/s]
Train steps ... :  65%|██████▌   | 65027/100000 [19:49:57<6:22:39,  1.52it/s]
Train steps ... :  65%|██████▌   | 65028/100000 [19:49:58<6:09:52,  1.58it/s]
Train steps ... :  65%|██████▌   | 65029/100000 [19:49:59<6:01:30,  1.61it/s]
Train steps ... :  65%|██████▌   | 65030/100000 [19:49:59<5:55:02,  1.64it/s]
Train steps ... :  65%|██████▌   | 65031/100000 [19:50:00<5:50:26,  1.66it/s]
Train steps ... :  65%|██████▌   | 65032/100000 [19:50:00<5:47:25,  1.68it/s]
Train steps ... :  65%|██████▌   | 65033/100000 [19:50:01<5:45:10,  1.69it/s]
Train steps ... :  65%|██████▌   | 65034/100000 [19:50:01<5:44:11,  1.69it/s]
Train steps ... :  65%|██████▌   | 65035/100000 [19:50:02<5:42:46,  1.70it/s]
Train steps ... :  65%|██████▌   | 65036/100000 [19:50:03<5:42:14,  1.70it/s]
Train steps ... :  65%|██████▌   | 65037/100000 [19:50:03<5:41:45,  1.71it/s]
Train steps ... :  65%|██████▌   | 65038/100000 [19:50:04<5:41:05,  1.71it/s]
Train steps ... :  65%|██████▌   | 65039/100000 [19:50:04<5:40:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65040/100000 [19:50:05<5:40:24,  1.71it/s]
Train steps ... :  65%|██████▌   | 65041/100000 [19:50:06<5:40:20,  1.71it/s]
Train steps ... :  65%|██████▌   | 65042/100000 [19:50:06<5:40:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65043/100000 [19:50:07<5:40:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65044/100000 [19:50:07<5:40:07,  1.71it/s]
Train steps ... :  65%|██████▌   | 65045/100000 [19:50:08<5:40:27,  1.71it/s]
Train steps ... :  65%|██████▌   | 65046/100000 [19:50:08<5:40:49,  1.71it/s]
Train steps ... :  65%|██████▌   | 65047/100000 [19:50:09<5:40:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65048/100000 [19:50:10<5:41:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65049/100000 [19:50:10<5:41:02,  1.71it/s]
Train steps ... :  65%|██████▌   | 65050/100000 [19:50:11<5:41:39,  1.70it/s]Step... (65050 / 100000 | Loss: 0.7352002859115601, Learning Rate: 3.512562814070352e-05)
+
                                                                             
Step... (65050 / 100000 | Loss: 0.6708692312240601, Learning Rate: 3.512562814070352e-05)
+
Train steps ... :  65%|██████▌   | 65050/100000 [19:50:11<5:41:39,  1.70it/s]
Train steps ... :  65%|██████▌   | 65051/100000 [19:50:11<5:41:05,  1.71it/s]
Train steps ... :  65%|██████▌   | 65052/100000 [19:50:12<5:40:45,  1.71it/s]
Train steps ... :  65%|██████▌   | 65053/100000 [19:50:13<5:41:05,  1.71it/s]
Train steps ... :  65%|██████▌   | 65054/100000 [19:50:13<5:40:45,  1.71it/s]
Train steps ... :  65%|██████▌   | 65055/100000 [19:50:14<5:40:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65056/100000 [19:50:14<5:40:13,  1.71it/s]
Train steps ... :  65%|██████▌   | 65057/100000 [19:50:15<5:40:13,  1.71it/s]
Train steps ... :  65%|██████▌   | 65058/100000 [19:50:15<5:40:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65059/100000 [19:50:16<5:40:16,  1.71it/s]
Train steps ... :  65%|██████▌   | 65060/100000 [19:50:17<5:40:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65061/100000 [19:50:17<5:40:18,  1.71it/s]
Train steps ... :  65%|██████▌   | 65062/100000 [19:50:18<5:40:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65063/100000 [19:50:18<5:40:31,  1.71it/s]
Train steps ... :  65%|██████▌   | 65064/100000 [19:50:19<5:40:40,  1.71it/s]
Train steps ... :  65%|██████▌   | 65065/100000 [19:50:20<5:40:41,  1.71it/s]
Train steps ... :  65%|██████▌   | 65066/100000 [19:50:20<5:40:39,  1.71it/s]
Train steps ... :  65%|██████▌   | 65067/100000 [19:50:21<5:40:20,  1.71it/s]
Train steps ... :  65%|██████▌   | 65068/100000 [19:50:21<5:40:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65069/100000 [19:50:22<5:40:03,  1.71it/s]
Train steps ... :  65%|██████▌   | 65070/100000 [19:50:22<5:39:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65071/100000 [19:50:23<5:40:13,  1.71it/s]
Train steps ... :  65%|██████▌   | 65072/100000 [19:50:24<5:40:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65073/100000 [19:50:24<5:40:07,  1.71it/s]
Train steps ... :  65%|██████▌   | 65074/100000 [19:50:25<5:39:59,  1.71it/s]
Train steps ... :  65%|██████▌   | 65075/100000 [19:50:25<5:39:55,  1.71it/s]Step... (65075 / 100000 | Loss: 0.7022529244422913, Learning Rate: 3.510050251256282e-05)
+
                                                                             
Step... (65075 / 100000 | Loss: 0.555611789226532, Learning Rate: 3.510050251256282e-05)
+
Train steps ... :  65%|██████▌   | 65075/100000 [19:50:26<5:39:55,  1.71it/s]
Train steps ... :  65%|██████▌   | 65076/100000 [19:50:26<5:40:13,  1.71it/s]
Train steps ... :  65%|██████▌   | 65077/100000 [19:50:27<5:39:54,  1.71it/s]
Train steps ... :  65%|██████▌   | 65078/100000 [19:50:27<5:39:50,  1.71it/s]
Train steps ... :  65%|██████▌   | 65079/100000 [19:50:28<5:40:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65080/100000 [19:50:28<5:39:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65081/100000 [19:50:29<5:40:25,  1.71it/s]
Train steps ... :  65%|██████▌   | 65082/100000 [19:50:29<5:40:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65083/100000 [19:50:30<5:40:26,  1.71it/s]
Train steps ... :  65%|██████▌   | 65084/100000 [19:50:31<5:40:49,  1.71it/s]
Train steps ... :  65%|██████▌   | 65085/100000 [19:50:31<5:40:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65086/100000 [19:50:32<5:40:21,  1.71it/s]
Train steps ... :  65%|██████▌   | 65087/100000 [19:50:32<5:40:04,  1.71it/s]
Train steps ... :  65%|██████▌   | 65088/100000 [19:50:33<5:40:27,  1.71it/s]
Train steps ... :  65%|██████▌   | 65089/100000 [19:50:34<5:40:32,  1.71it/s]
Train steps ... :  65%|██████▌   | 65090/100000 [19:50:34<5:39:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65091/100000 [19:50:35<5:40:03,  1.71it/s]
Train steps ... :  65%|██████▌   | 65092/100000 [19:50:35<5:40:47,  1.71it/s]
Train steps ... :  65%|██████▌   | 65093/100000 [19:50:36<5:41:04,  1.71it/s]
Train steps ... :  65%|██████▌   | 65094/100000 [19:50:37<5:40:23,  1.71it/s]
Train steps ... :  65%|██████▌   | 65095/100000 [19:50:37<5:39:58,  1.71it/s]
Train steps ... :  65%|██████▌   | 65096/100000 [19:50:38<5:40:03,  1.71it/s]
Train steps ... :  65%|██████▌   | 65097/100000 [19:50:38<5:39:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65098/100000 [19:50:39<5:40:13,  1.71it/s]
Train steps ... :  65%|██████▌   | 65099/100000 [19:50:39<5:40:02,  1.71it/s]
Train steps ... :  65%|██████▌   | 65100/100000 [19:50:40<5:39:55,  1.71it/s]Step... (65100 / 100000 | Loss: 0.771933376789093, Learning Rate: 3.5075376884422114e-05)
+
                                                                             
Step... (65100 / 100000 | Loss: 0.8650752305984497, Learning Rate: 3.5075376884422114e-05)
+
Train steps ... :  65%|██████▌   | 65100/100000 [19:50:40<5:39:55,  1.71it/s]
Train steps ... :  65%|██████▌   | 65101/100000 [19:50:41<5:39:55,  1.71it/s]
Train steps ... :  65%|██████▌   | 65102/100000 [19:50:41<5:39:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65103/100000 [19:50:42<5:39:44,  1.71it/s]
Train steps ... :  65%|██████▌   | 65104/100000 [19:50:42<5:39:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65105/100000 [19:50:43<5:39:43,  1.71it/s]
Train steps ... :  65%|██████▌   | 65106/100000 [19:50:44<5:39:34,  1.71it/s]
Train steps ... :  65%|██████▌   | 65107/100000 [19:50:44<5:39:28,  1.71it/s]
Train steps ... :  65%|██████▌   | 65108/100000 [19:50:45<5:39:44,  1.71it/s]
Train steps ... :  65%|██████▌   | 65109/100000 [19:50:45<5:40:24,  1.71it/s]
Train steps ... :  65%|██████▌   | 65110/100000 [19:50:46<5:40:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65111/100000 [19:50:46<5:40:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65112/100000 [19:50:47<5:40:07,  1.71it/s]
Train steps ... :  65%|██████▌   | 65113/100000 [19:50:48<5:40:16,  1.71it/s]
Train steps ... :  65%|██████▌   | 65114/100000 [19:50:48<5:40:08,  1.71it/s]
Train steps ... :  65%|██████▌   | 65115/100000 [19:50:49<5:39:48,  1.71it/s]
Train steps ... :  65%|██████▌   | 65116/100000 [19:50:49<5:40:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65117/100000 [19:50:50<5:39:43,  1.71it/s]
Train steps ... :  65%|██████▌   | 65118/100000 [19:50:51<5:39:24,  1.71it/s]
Train steps ... :  65%|██████▌   | 65119/100000 [19:50:51<5:39:23,  1.71it/s]
Train steps ... :  65%|██████▌   | 65120/100000 [19:50:52<5:39:16,  1.71it/s]
Train steps ... :  65%|██████▌   | 65121/100000 [19:50:52<5:39:20,  1.71it/s]
Train steps ... :  65%|██████▌   | 65122/100000 [19:50:53<5:39:26,  1.71it/s]
Train steps ... :  65%|██████▌   | 65123/100000 [19:50:53<5:39:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65124/100000 [19:50:54<5:39:49,  1.71it/s]
Train steps ... :  65%|██████▌   | 65125/100000 [19:50:55<5:39:40,  1.71it/s]Step... (65125 / 100000 | Loss: 0.9922420978546143, Learning Rate: 3.505025125628141e-05)
+
                                                                             
Step... (65125 / 100000 | Loss: 0.8386441469192505, Learning Rate: 3.505025125628141e-05)
+
Train steps ... :  65%|██████▌   | 65125/100000 [19:50:55<5:39:40,  1.71it/s]
Train steps ... :  65%|██████▌   | 65126/100000 [19:50:55<5:40:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65127/100000 [19:50:56<5:39:57,  1.71it/s]
Train steps ... :  65%|██████▌   | 65128/100000 [19:50:56<5:39:40,  1.71it/s]
Train steps ... :  65%|██████▌   | 65129/100000 [19:50:57<5:39:31,  1.71it/s]
Train steps ... :  65%|██████▌   | 65130/100000 [19:50:58<5:39:37,  1.71it/s]
Train steps ... :  65%|██████▌   | 65131/100000 [19:50:58<5:39:58,  1.71it/s]
Train steps ... :  65%|██████▌   | 65132/100000 [19:50:59<5:39:31,  1.71it/s]
Train steps ... :  65%|██████▌   | 65133/100000 [19:50:59<5:39:42,  1.71it/s]
Train steps ... :  65%|██████▌   | 65134/100000 [19:51:00<5:39:43,  1.71it/s]
Train steps ... :  65%|██████▌   | 65135/100000 [19:51:00<5:39:44,  1.71it/s]
Train steps ... :  65%|██████▌   | 65136/100000 [19:51:01<5:39:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65137/100000 [19:51:02<5:39:12,  1.71it/s]
Train steps ... :  65%|██████▌   | 65138/100000 [19:51:02<5:39:20,  1.71it/s]
Train steps ... :  65%|██████▌   | 65139/100000 [19:51:03<5:39:23,  1.71it/s]
Train steps ... :  65%|██████▌   | 65140/100000 [19:51:03<5:39:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65141/100000 [19:51:04<5:39:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65142/100000 [19:51:05<5:39:40,  1.71it/s]
Train steps ... :  65%|██████▌   | 65143/100000 [19:51:05<5:39:23,  1.71it/s]
Train steps ... :  65%|██████▌   | 65144/100000 [19:51:06<5:39:30,  1.71it/s]
Train steps ... :  65%|██████▌   | 65145/100000 [19:51:06<5:39:18,  1.71it/s]
Train steps ... :  65%|██████▌   | 65146/100000 [19:51:07<5:39:18,  1.71it/s]
Train steps ... :  65%|██████▌   | 65147/100000 [19:51:07<5:39:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65148/100000 [19:51:08<5:39:20,  1.71it/s]
Train steps ... :  65%|██████▌   | 65149/100000 [19:51:09<5:39:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65150/100000 [19:51:09<5:39:30,  1.71it/s]Step... (65150 / 100000 | Loss: 0.6646852493286133, Learning Rate: 3.50251256281407e-05)
+
                                                                             
Step... (65150 / 100000 | Loss: 0.6477423906326294, Learning Rate: 3.50251256281407e-05)
+
Train steps ... :  65%|██████▌   | 65150/100000 [19:51:10<5:39:30,  1.71it/s]
Train steps ... :  65%|██████▌   | 65151/100000 [19:51:10<5:40:00,  1.71it/s]
Train steps ... :  65%|██████▌   | 65152/100000 [19:51:10<5:39:32,  1.71it/s]
Train steps ... :  65%|██████▌   | 65153/100000 [19:51:11<5:39:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65154/100000 [19:51:12<5:39:04,  1.71it/s]
Train steps ... :  65%|██████▌   | 65155/100000 [19:51:12<5:39:07,  1.71it/s]
Train steps ... :  65%|██████▌   | 65156/100000 [19:51:13<5:39:09,  1.71it/s]
Train steps ... :  65%|██████▌   | 65157/100000 [19:51:13<5:39:05,  1.71it/s]
Train steps ... :  65%|██████▌   | 65158/100000 [19:51:14<5:39:02,  1.71it/s]
Train steps ... :  65%|██████▌   | 65159/100000 [19:51:14<5:38:54,  1.71it/s]
Train steps ... :  65%|██████▌   | 65160/100000 [19:51:15<5:39:07,  1.71it/s]
Train steps ... :  65%|██████▌   | 65161/100000 [19:51:16<5:39:08,  1.71it/s]
Train steps ... :  65%|██████▌   | 65162/100000 [19:51:16<5:39:20,  1.71it/s]
Train steps ... :  65%|██████▌   | 65163/100000 [19:51:17<5:39:09,  1.71it/s]
Train steps ... :  65%|██████▌   | 65164/100000 [19:51:17<5:39:21,  1.71it/s]
Train steps ... :  65%|██████▌   | 65165/100000 [19:51:18<5:40:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65166/100000 [19:51:19<5:39:54,  1.71it/s]
Train steps ... :  65%|██████▌   | 65167/100000 [19:51:19<5:39:32,  1.71it/s]
Train steps ... :  65%|██████▌   | 65168/100000 [19:51:20<5:39:24,  1.71it/s]
Train steps ... :  65%|██████▌   | 65169/100000 [19:51:20<5:39:46,  1.71it/s]
Train steps ... :  65%|██████▌   | 65170/100000 [19:51:21<5:39:24,  1.71it/s]
Train steps ... :  65%|██████▌   | 65171/100000 [19:51:22<5:39:32,  1.71it/s]
Train steps ... :  65%|██████▌   | 65172/100000 [19:51:22<5:39:03,  1.71it/s]
Train steps ... :  65%|██████▌   | 65173/100000 [19:51:23<5:38:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65174/100000 [19:51:23<5:39:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65175/100000 [19:51:24<5:39:17,  1.71it/s]Step... (65175 / 100000 | Loss: 0.5940853357315063, Learning Rate: 3.5e-05)
+
                                                                             
Step... (65175 / 100000 | Loss: 0.8000319004058838, Learning Rate: 3.5e-05)
+
Train steps ... :  65%|██████▌   | 65175/100000 [19:51:24<5:39:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65176/100000 [19:51:24<5:39:30,  1.71it/s]
Train steps ... :  65%|██████▌   | 65177/100000 [19:51:25<5:39:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65178/100000 [19:51:26<5:39:39,  1.71it/s]
Train steps ... :  65%|██████▌   | 65179/100000 [19:51:26<5:40:15,  1.71it/s]
Train steps ... :  65%|██████▌   | 65180/100000 [19:51:27<5:40:01,  1.71it/s]
Train steps ... :  65%|██████▌   | 65181/100000 [19:51:27<5:39:31,  1.71it/s]
Train steps ... :  65%|██████▌   | 65182/100000 [19:51:28<5:39:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65183/100000 [19:51:29<5:39:26,  1.71it/s]
Train steps ... :  65%|██████▌   | 65184/100000 [19:51:29<5:39:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65185/100000 [19:51:30<5:39:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65186/100000 [19:51:30<5:39:30,  1.71it/s]
Train steps ... :  65%|██████▌   | 65187/100000 [19:51:31<5:39:47,  1.71it/s]
Train steps ... :  65%|██████▌   | 65188/100000 [19:51:31<5:39:42,  1.71it/s]
Train steps ... :  65%|██████▌   | 65189/100000 [19:51:32<5:39:14,  1.71it/s]
Train steps ... :  65%|██████▌   | 65190/100000 [19:51:33<5:39:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65191/100000 [19:51:33<5:39:10,  1.71it/s]
Train steps ... :  65%|██████▌   | 65192/100000 [19:51:34<5:39:10,  1.71it/s]
Train steps ... :  65%|██████▌   | 65193/100000 [19:51:34<5:38:52,  1.71it/s]
Train steps ... :  65%|██████▌   | 65194/100000 [19:51:35<5:38:49,  1.71it/s]
Train steps ... :  65%|██████▌   | 65195/100000 [19:51:36<5:39:12,  1.71it/s]
Train steps ... :  65%|██████▌   | 65196/100000 [19:51:36<5:39:00,  1.71it/s]
Train steps ... :  65%|██████▌   | 65197/100000 [19:51:37<5:39:00,  1.71it/s]
Train steps ... :  65%|██████▌   | 65198/100000 [19:51:37<5:38:53,  1.71it/s]
Train steps ... :  65%|██████▌   | 65199/100000 [19:51:38<5:39:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65200/100000 [19:51:38<5:39:08,  1.71it/s]Step... (65200 / 100000 | Loss: 0.9958220720291138, Learning Rate: 3.49748743718593e-05)
+
                                                                             
Step... (65200 / 100000 | Loss: 0.7145507335662842, Learning Rate: 3.49748743718593e-05)
+
Train steps ... :  65%|██████▌   | 65200/100000 [19:51:39<5:39:08,  1.71it/s]
Train steps ... :  65%|██████▌   | 65201/100000 [19:51:39<5:39:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65202/100000 [19:51:40<5:39:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65203/100000 [19:51:40<5:39:04,  1.71it/s]
Train steps ... :  65%|██████▌   | 65204/100000 [19:51:41<5:38:55,  1.71it/s]
Train steps ... :  65%|██████▌   | 65205/100000 [19:51:41<5:39:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65206/100000 [19:51:42<5:39:25,  1.71it/s]
Train steps ... :  65%|██████▌   | 65207/100000 [19:51:43<5:40:05,  1.71it/s]
Train steps ... :  65%|██████▌   | 65208/100000 [19:51:43<5:39:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65209/100000 [19:51:44<5:39:38,  1.71it/s]
Train steps ... :  65%|██████▌   | 65210/100000 [19:51:44<5:39:14,  1.71it/s]
Train steps ... :  65%|██████▌   | 65211/100000 [19:51:45<5:39:08,  1.71it/s]
Train steps ... :  65%|██████▌   | 65212/100000 [19:51:45<5:39:09,  1.71it/s]
Train steps ... :  65%|██████▌   | 65213/100000 [19:51:46<5:39:09,  1.71it/s]
Train steps ... :  65%|██████▌   | 65214/100000 [19:51:47<5:38:54,  1.71it/s]
Train steps ... :  65%|██████▌   | 65215/100000 [19:51:47<5:39:08,  1.71it/s]
Train steps ... :  65%|██████▌   | 65216/100000 [19:51:48<5:39:46,  1.71it/s]
Train steps ... :  65%|██████▌   | 65217/100000 [19:51:48<5:39:21,  1.71it/s]
Train steps ... :  65%|██████▌   | 65218/100000 [19:51:49<5:39:21,  1.71it/s]
Train steps ... :  65%|██████▌   | 65219/100000 [19:51:50<5:38:59,  1.71it/s]
Train steps ... :  65%|██████▌   | 65220/100000 [19:51:50<5:39:07,  1.71it/s]
Train steps ... :  65%|██████▌   | 65221/100000 [19:51:51<5:38:54,  1.71it/s]
Train steps ... :  65%|██████▌   | 65222/100000 [19:51:51<5:38:42,  1.71it/s]
Train steps ... :  65%|██████▌   | 65223/100000 [19:51:52<5:38:55,  1.71it/s]
Train steps ... :  65%|██████▌   | 65224/100000 [19:51:53<5:39:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65225/100000 [19:51:53<5:39:03,  1.71it/s]Step... (65225 / 100000 | Loss: 0.5504133105278015, Learning Rate: 3.49497487437186e-05)
+
                                                                             
Step... (65225 / 100000 | Loss: 0.8552618622779846, Learning Rate: 3.49497487437186e-05)
+
Train steps ... :  65%|██████▌   | 65225/100000 [19:51:53<5:39:03,  1.71it/s]
Train steps ... :  65%|██████▌   | 65226/100000 [19:51:54<5:39:14,  1.71it/s]
Train steps ... :  65%|██████▌   | 65227/100000 [19:51:54<5:39:00,  1.71it/s]
Train steps ... :  65%|██████▌   | 65228/100000 [19:51:55<5:39:01,  1.71it/s]
Train steps ... :  65%|██████▌   | 65229/100000 [19:51:55<5:39:04,  1.71it/s]
Train steps ... :  65%|██████▌   | 65230/100000 [19:51:56<5:39:08,  1.71it/s]
Train steps ... :  65%|██████▌   | 65231/100000 [19:51:57<5:38:51,  1.71it/s]
Train steps ... :  65%|██████▌   | 65232/100000 [19:51:57<5:38:44,  1.71it/s]
Train steps ... :  65%|██████▌   | 65233/100000 [19:51:58<5:39:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65234/100000 [19:51:58<5:39:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65235/100000 [19:51:59<5:38:54,  1.71it/s]
Train steps ... :  65%|██████▌   | 65236/100000 [19:52:00<5:38:46,  1.71it/s]
Train steps ... :  65%|██████▌   | 65237/100000 [19:52:00<5:38:49,  1.71it/s]
Train steps ... :  65%|██████▌   | 65238/100000 [19:52:01<5:38:34,  1.71it/s]
Train steps ... :  65%|██████▌   | 65239/100000 [19:52:01<5:38:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65240/100000 [19:52:02<5:38:53,  1.71it/s]
Train steps ... :  65%|██████▌   | 65241/100000 [19:52:02<5:38:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65242/100000 [19:52:03<5:39:20,  1.71it/s]
Train steps ... :  65%|██████▌   | 65243/100000 [19:52:04<5:38:49,  1.71it/s]
Train steps ... :  65%|██████▌   | 65244/100000 [19:52:04<5:38:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65245/100000 [19:52:05<5:38:46,  1.71it/s]
Train steps ... :  65%|██████▌   | 65246/100000 [19:52:05<5:38:58,  1.71it/s]
Train steps ... :  65%|██████▌   | 65247/100000 [19:52:06<5:39:03,  1.71it/s]
Train steps ... :  65%|██████▌   | 65248/100000 [19:52:07<5:38:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65249/100000 [19:52:07<5:39:32,  1.71it/s]
Train steps ... :  65%|██████▌   | 65250/100000 [19:52:08<5:38:33,  1.71it/s]Step... (65250 / 100000 | Loss: 0.7264801263809204, Learning Rate: 3.4924623115577894e-05)
+
                                                                             
Step... (65250 / 100000 | Loss: 0.6922319531440735, Learning Rate: 3.4924623115577894e-05)
+
Train steps ... :  65%|██████▌   | 65250/100000 [19:52:08<5:38:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65251/100000 [19:52:08<5:38:51,  1.71it/s]
Train steps ... :  65%|██████▌   | 65252/100000 [19:52:09<5:38:43,  1.71it/s]
Train steps ... :  65%|██████▌   | 65253/100000 [19:52:09<5:38:38,  1.71it/s]
Train steps ... :  65%|██████▌   | 65254/100000 [19:52:10<5:38:25,  1.71it/s]
Train steps ... :  65%|██████▌   | 65255/100000 [19:52:11<5:38:14,  1.71it/s]
Train steps ... :  65%|██████▌   | 65256/100000 [19:52:11<5:38:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65257/100000 [19:52:12<5:38:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65258/100000 [19:52:12<5:38:34,  1.71it/s]
Train steps ... :  65%|██████▌   | 65259/100000 [19:52:13<5:38:25,  1.71it/s]
Train steps ... :  65%|██████▌   | 65260/100000 [19:52:14<5:38:36,  1.71it/s]
Train steps ... :  65%|██████▌   | 65261/100000 [19:52:14<5:38:51,  1.71it/s]
Train steps ... :  65%|██████▌   | 65262/100000 [19:52:15<5:38:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65263/100000 [19:52:15<5:38:39,  1.71it/s]
Train steps ... :  65%|██████▌   | 65264/100000 [19:52:16<5:38:45,  1.71it/s]
Train steps ... :  65%|██████▌   | 65265/100000 [19:52:16<5:38:42,  1.71it/s]
Train steps ... :  65%|██████▌   | 65266/100000 [19:52:17<5:38:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65267/100000 [19:52:18<5:38:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65268/100000 [19:52:18<5:38:34,  1.71it/s]
Train steps ... :  65%|██████▌   | 65269/100000 [19:52:19<5:38:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65270/100000 [19:52:19<5:38:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65271/100000 [19:52:20<5:39:43,  1.70it/s]
Train steps ... :  65%|██████▌   | 65272/100000 [19:52:21<5:38:58,  1.71it/s]
Train steps ... :  65%|██████▌   | 65273/100000 [19:52:21<5:38:53,  1.71it/s]
Train steps ... :  65%|██████▌   | 65274/100000 [19:52:22<5:38:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65275/100000 [19:52:22<5:38:35,  1.71it/s]Step... (65275 / 100000 | Loss: 0.6275578737258911, Learning Rate: 3.489949748743719e-05)
+
                                                                             
Step... (65275 / 100000 | Loss: 0.8410693407058716, Learning Rate: 3.489949748743719e-05)
+
Train steps ... :  65%|██████▌   | 65275/100000 [19:52:23<5:38:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65276/100000 [19:52:23<5:38:45,  1.71it/s]
Train steps ... :  65%|██████▌   | 65277/100000 [19:52:24<5:38:25,  1.71it/s]
Train steps ... :  65%|██████▌   | 65278/100000 [19:52:24<5:38:07,  1.71it/s]
Train steps ... :  65%|██████▌   | 65279/100000 [19:52:25<5:38:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65280/100000 [19:52:25<5:38:15,  1.71it/s]
Train steps ... :  65%|██████▌   | 65281/100000 [19:52:26<5:38:14,  1.71it/s]
Train steps ... :  65%|██████▌   | 65282/100000 [19:52:26<5:38:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65283/100000 [19:52:27<5:38:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65284/100000 [19:52:28<5:38:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65285/100000 [19:52:28<5:38:16,  1.71it/s]
Train steps ... :  65%|██████▌   | 65286/100000 [19:52:29<5:38:18,  1.71it/s]
Train steps ... :  65%|██████▌   | 65287/100000 [19:52:29<5:38:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65288/100000 [19:52:30<5:37:53,  1.71it/s]
Train steps ... :  65%|██████▌   | 65289/100000 [19:52:31<5:38:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65290/100000 [19:52:31<5:38:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65291/100000 [19:52:32<5:37:57,  1.71it/s]
Train steps ... :  65%|██████▌   | 65292/100000 [19:52:32<5:38:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65293/100000 [19:52:33<5:38:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65294/100000 [19:52:33<5:38:10,  1.71it/s]
Train steps ... :  65%|██████▌   | 65295/100000 [19:52:34<5:38:05,  1.71it/s]
Train steps ... :  65%|██████▌   | 65296/100000 [19:52:35<5:37:48,  1.71it/s]
Train steps ... :  65%|██████▌   | 65297/100000 [19:52:35<5:37:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65298/100000 [19:52:36<5:37:49,  1.71it/s]
Train steps ... :  65%|██████▌   | 65299/100000 [19:52:36<5:38:00,  1.71it/s]
Train steps ... :  65%|██████▌   | 65300/100000 [19:52:37<5:37:48,  1.71it/s]Step... (65300 / 100000 | Loss: 0.692715585231781, Learning Rate: 3.487437185929649e-05)
+
                                                                             
Step... (65300 / 100000 | Loss: 0.8084791898727417, Learning Rate: 3.487437185929649e-05)
+
Train steps ... :  65%|██████▌   | 65300/100000 [19:52:37<5:37:48,  1.71it/s]
Train steps ... :  65%|██████▌   | 65301/100000 [19:52:38<5:38:46,  1.71it/s]
Train steps ... :  65%|██████▌   | 65302/100000 [19:52:38<5:38:30,  1.71it/s]
Train steps ... :  65%|██████▌   | 65303/100000 [19:52:39<5:38:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65304/100000 [19:52:39<5:38:40,  1.71it/s]
Train steps ... :  65%|██████▌   | 65305/100000 [19:52:40<5:38:08,  1.71it/s]
Train steps ... :  65%|██████▌   | 65306/100000 [19:52:40<5:38:18,  1.71it/s]
Train steps ... :  65%|██████▌   | 65307/100000 [19:52:41<5:38:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65308/100000 [19:52:42<5:38:15,  1.71it/s]
Train steps ... :  65%|██████▌   | 65309/100000 [19:52:42<5:38:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65310/100000 [19:52:43<5:38:24,  1.71it/s]
Train steps ... :  65%|██████▌   | 65311/100000 [19:52:43<5:37:51,  1.71it/s]
Train steps ... :  65%|██████▌   | 65312/100000 [19:52:44<5:37:43,  1.71it/s]
Train steps ... :  65%|██████▌   | 65313/100000 [19:52:45<5:37:49,  1.71it/s]
Train steps ... :  65%|██████▌   | 65314/100000 [19:52:45<5:37:36,  1.71it/s]
Train steps ... :  65%|██████▌   | 65315/100000 [19:52:46<5:37:58,  1.71it/s]
Train steps ... :  65%|██████▌   | 65316/100000 [19:52:46<5:38:05,  1.71it/s]
Train steps ... :  65%|██████▌   | 65317/100000 [19:52:47<5:37:49,  1.71it/s]
Train steps ... :  65%|██████▌   | 65318/100000 [19:52:47<5:37:49,  1.71it/s]
Train steps ... :  65%|██████▌   | 65319/100000 [19:52:48<5:37:36,  1.71it/s]
Train steps ... :  65%|██████▌   | 65320/100000 [19:52:49<5:37:48,  1.71it/s]
Train steps ... :  65%|██████▌   | 65321/100000 [19:52:49<5:38:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65322/100000 [19:52:50<5:38:40,  1.71it/s]
Train steps ... :  65%|██████▌   | 65323/100000 [19:52:50<5:38:50,  1.71it/s]
Train steps ... :  65%|██████▌   | 65324/100000 [19:52:51<5:38:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65325/100000 [19:52:52<5:38:19,  1.71it/s]Step... (65325 / 100000 | Loss: 0.7556063532829285, Learning Rate: 3.484924623115578e-05)
+
                                                                             
Step... (65325 / 100000 | Loss: 0.7081802487373352, Learning Rate: 3.484924623115578e-05)
+
Train steps ... :  65%|██████▌   | 65325/100000 [19:52:52<5:38:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65326/100000 [19:52:52<5:38:10,  1.71it/s]
Train steps ... :  65%|██████▌   | 65327/100000 [19:52:53<5:38:38,  1.71it/s]
Train steps ... :  65%|██████▌   | 65328/100000 [19:52:53<5:38:28,  1.71it/s]
Train steps ... :  65%|██████▌   | 65329/100000 [19:52:54<5:38:31,  1.71it/s]
Train steps ... :  65%|██████▌   | 65330/100000 [19:52:55<5:38:02,  1.71it/s]
Train steps ... :  65%|██████▌   | 65331/100000 [19:52:55<5:38:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65332/100000 [19:52:56<5:38:23,  1.71it/s]
Train steps ... :  65%|██████▌   | 65333/100000 [19:52:56<5:38:14,  1.71it/s]
Train steps ... :  65%|██████▌   | 65334/100000 [19:52:57<5:38:01,  1.71it/s]
Train steps ... :  65%|██████▌   | 65335/100000 [19:52:57<5:37:40,  1.71it/s]
Train steps ... :  65%|██████▌   | 65336/100000 [19:52:58<5:37:41,  1.71it/s]
Train steps ... :  65%|██████▌   | 65337/100000 [19:52:59<5:37:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65338/100000 [19:52:59<5:37:40,  1.71it/s]
Train steps ... :  65%|██████▌   | 65339/100000 [19:53:00<5:37:38,  1.71it/s]
Train steps ... :  65%|██████▌   | 65340/100000 [19:53:00<5:37:31,  1.71it/s]
Train steps ... :  65%|██████▌   | 65341/100000 [19:53:01<5:37:37,  1.71it/s]
Train steps ... :  65%|██████▌   | 65342/100000 [19:53:02<5:37:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65343/100000 [19:53:02<5:37:36,  1.71it/s]
Train steps ... :  65%|██████▌   | 65344/100000 [19:53:03<5:37:30,  1.71it/s]
Train steps ... :  65%|██████▌   | 65345/100000 [19:53:03<5:37:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65346/100000 [19:53:04<5:37:12,  1.71it/s]
Train steps ... :  65%|██████▌   | 65347/100000 [19:53:04<5:37:05,  1.71it/s]
Train steps ... :  65%|██████▌   | 65348/100000 [19:53:05<5:37:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65349/100000 [19:53:06<5:37:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65350/100000 [19:53:06<5:37:44,  1.71it/s]Step... (65350 / 100000 | Loss: 0.6114481091499329, Learning Rate: 3.482412060301507e-05)
+
                                                                             
Step... (65350 / 100000 | Loss: 0.8272048234939575, Learning Rate: 3.482412060301507e-05)
+
Train steps ... :  65%|██████▌   | 65350/100000 [19:53:07<5:37:44,  1.71it/s]
Train steps ... :  65%|██████▌   | 65351/100000 [19:53:07<5:37:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65352/100000 [19:53:07<5:37:27,  1.71it/s]
Train steps ... :  65%|██████▌   | 65353/100000 [19:53:08<5:37:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65354/100000 [19:53:09<5:37:23,  1.71it/s]
Train steps ... :  65%|██████▌   | 65355/100000 [19:53:09<5:37:21,  1.71it/s]
Train steps ... :  65%|██████▌   | 65356/100000 [19:53:10<5:38:07,  1.71it/s]
Train steps ... :  65%|██████▌   | 65357/100000 [19:53:10<5:37:32,  1.71it/s]
Train steps ... :  65%|██████▌   | 65358/100000 [19:53:11<5:37:20,  1.71it/s]
Train steps ... :  65%|██████▌   | 65359/100000 [19:53:11<5:37:23,  1.71it/s]
Train steps ... :  65%|██████▌   | 65360/100000 [19:53:12<5:37:30,  1.71it/s]
Train steps ... :  65%|██████▌   | 65361/100000 [19:53:13<5:37:41,  1.71it/s]
Train steps ... :  65%|██████▌   | 65362/100000 [19:53:13<5:37:32,  1.71it/s]
Train steps ... :  65%|██████▌   | 65363/100000 [19:53:14<5:37:58,  1.71it/s]
Train steps ... :  65%|██████▌   | 65364/100000 [19:53:14<5:37:44,  1.71it/s]
Train steps ... :  65%|██████▌   | 65365/100000 [19:53:15<5:37:26,  1.71it/s]
Train steps ... :  65%|██████▌   | 65366/100000 [19:53:16<5:37:26,  1.71it/s]
Train steps ... :  65%|██████▌   | 65367/100000 [19:53:16<5:37:44,  1.71it/s]
Train steps ... :  65%|██████▌   | 65368/100000 [19:53:17<5:37:26,  1.71it/s]
Train steps ... :  65%|██████▌   | 65369/100000 [19:53:17<5:37:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65370/100000 [19:53:18<5:37:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65371/100000 [19:53:18<5:37:23,  1.71it/s]
Train steps ... :  65%|██████▌   | 65372/100000 [19:53:19<5:36:58,  1.71it/s]
Train steps ... :  65%|██████▌   | 65373/100000 [19:53:20<5:36:54,  1.71it/s]
Train steps ... :  65%|██████▌   | 65374/100000 [19:53:20<5:36:52,  1.71it/s]
Train steps ... :  65%|██████▌   | 65375/100000 [19:53:21<5:37:17,  1.71it/s]Step... (65375 / 100000 | Loss: 0.7975024580955505, Learning Rate: 3.479899497487437e-05)
+
                                                                             
Step... (65375 / 100000 | Loss: 0.5327474474906921, Learning Rate: 3.479899497487437e-05)
+
Train steps ... :  65%|██████▌   | 65375/100000 [19:53:21<5:37:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65376/100000 [19:53:21<5:37:10,  1.71it/s]
Train steps ... :  65%|██████▌   | 65377/100000 [19:53:22<5:37:04,  1.71it/s]
Train steps ... :  65%|██████▌   | 65378/100000 [19:53:23<5:37:02,  1.71it/s]
Train steps ... :  65%|██████▌   | 65379/100000 [19:53:23<5:36:54,  1.71it/s]
Train steps ... :  65%|██████▌   | 65380/100000 [19:53:24<5:37:04,  1.71it/s]
Train steps ... :  65%|██████▌   | 65381/100000 [19:53:24<5:36:55,  1.71it/s]
Train steps ... :  65%|██████▌   | 65382/100000 [19:53:25<5:37:13,  1.71it/s]
Train steps ... :  65%|██████▌   | 65383/100000 [19:53:25<5:37:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65384/100000 [19:53:26<5:37:00,  1.71it/s]
Train steps ... :  65%|██████▌   | 65385/100000 [19:53:27<5:36:44,  1.71it/s]
Train steps ... :  65%|██████▌   | 65386/100000 [19:53:27<5:36:52,  1.71it/s]
Train steps ... :  65%|██████▌   | 65387/100000 [19:53:28<5:37:02,  1.71it/s]
Train steps ... :  65%|██████▌   | 65388/100000 [19:53:28<5:37:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65389/100000 [19:53:29<5:37:13,  1.71it/s]
Train steps ... :  65%|██████▌   | 65390/100000 [19:53:30<5:37:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65391/100000 [19:53:30<5:37:10,  1.71it/s]
Train steps ... :  65%|██████▌   | 65392/100000 [19:53:31<5:37:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65393/100000 [19:53:31<5:36:53,  1.71it/s]
Train steps ... :  65%|██████▌   | 65394/100000 [19:53:32<5:37:15,  1.71it/s]
Train steps ... :  65%|██████▌   | 65395/100000 [19:53:32<5:37:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65396/100000 [19:53:33<5:37:12,  1.71it/s]
Train steps ... :  65%|██████▌   | 65397/100000 [19:53:34<5:37:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65398/100000 [19:53:34<5:37:18,  1.71it/s]
Train steps ... :  65%|██████▌   | 65399/100000 [19:53:35<5:36:57,  1.71it/s]
Train steps ... :  65%|██████▌   | 65400/100000 [19:53:35<5:36:51,  1.71it/s]Step... (65400 / 100000 | Loss: 0.5960800051689148, Learning Rate: 3.4773869346733667e-05)
+
                                                                             
Step... (65400 / 100000 | Loss: 0.8393404483795166, Learning Rate: 3.4773869346733667e-05)
+
Train steps ... :  65%|██████▌   | 65400/100000 [19:53:36<5:36:51,  1.71it/s]
Train steps ... :  65%|██████▌   | 65401/100000 [19:53:36<5:36:43,  1.71it/s]
Train steps ... :  65%|██████▌   | 65402/100000 [19:53:37<5:36:55,  1.71it/s]
Train steps ... :  65%|██████▌   | 65403/100000 [19:53:37<5:36:39,  1.71it/s]
Train steps ... :  65%|██████▌   | 65404/100000 [19:53:38<5:36:39,  1.71it/s]
Train steps ... :  65%|██████▌   | 65405/100000 [19:53:38<5:36:37,  1.71it/s]
Train steps ... :  65%|██████▌   | 65406/100000 [19:53:39<5:36:53,  1.71it/s]
Train steps ... :  65%|██████▌   | 65407/100000 [19:53:40<5:36:25,  1.71it/s]
Train steps ... :  65%|██████▌   | 65408/100000 [19:53:40<5:36:26,  1.71it/s]
Train steps ... :  65%|██████▌   | 65409/100000 [19:53:41<5:36:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65410/100000 [19:53:41<5:36:46,  1.71it/s]
Train steps ... :  65%|██████▌   | 65411/100000 [19:53:42<5:36:26,  1.71it/s]
Train steps ... :  65%|██████▌   | 65412/100000 [19:53:42<5:36:27,  1.71it/s]
Train steps ... :  65%|██████▌   | 65413/100000 [19:53:43<5:36:45,  1.71it/s]
Train steps ... :  65%|██████▌   | 65414/100000 [19:53:44<5:36:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65415/100000 [19:53:44<5:36:43,  1.71it/s]
Train steps ... :  65%|██████▌   | 65416/100000 [19:53:45<5:36:39,  1.71it/s]
Train steps ... :  65%|██████▌   | 65417/100000 [19:53:45<5:36:54,  1.71it/s]
Train steps ... :  65%|██████▌   | 65418/100000 [19:53:46<5:36:47,  1.71it/s]
Train steps ... :  65%|██████▌   | 65419/100000 [19:53:47<5:37:21,  1.71it/s]
Train steps ... :  65%|██████▌   | 65420/100000 [19:53:47<5:36:58,  1.71it/s]
Train steps ... :  65%|██████▌   | 65421/100000 [19:53:48<5:36:39,  1.71it/s]
Train steps ... :  65%|██████▌   | 65422/100000 [19:53:48<5:36:23,  1.71it/s]
Train steps ... :  65%|██████▌   | 65423/100000 [19:53:49<5:36:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65424/100000 [19:53:49<5:36:15,  1.71it/s]
Train steps ... :  65%|██████▌   | 65425/100000 [19:53:50<5:36:22,  1.71it/s]Step... (65425 / 100000 | Loss: 0.7093163728713989, Learning Rate: 3.474874371859297e-05)
+
                                                                             
Step... (65425 / 100000 | Loss: 0.6388202905654907, Learning Rate: 3.474874371859297e-05)
+
Train steps ... :  65%|██████▌   | 65425/100000 [19:53:50<5:36:22,  1.71it/s]
Train steps ... :  65%|██████▌   | 65426/100000 [19:53:51<5:36:55,  1.71it/s]
Train steps ... :  65%|██████▌   | 65427/100000 [19:53:51<5:36:36,  1.71it/s]
Train steps ... :  65%|██████▌   | 65428/100000 [19:53:52<5:36:39,  1.71it/s]
Train steps ... :  65%|██████▌   | 65429/100000 [19:53:52<5:36:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65430/100000 [19:53:53<5:36:25,  1.71it/s]
Train steps ... :  65%|██████▌   | 65431/100000 [19:53:54<5:36:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65432/100000 [19:53:54<5:36:18,  1.71it/s]
Train steps ... :  65%|██████▌   | 65433/100000 [19:53:55<5:36:35,  1.71it/s]
Train steps ... :  65%|██████▌   | 65434/100000 [19:53:55<5:36:19,  1.71it/s]
Train steps ... :  65%|██████▌   | 65435/100000 [19:53:56<5:36:13,  1.71it/s]
Train steps ... :  65%|██████▌   | 65436/100000 [19:53:56<5:36:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65437/100000 [19:53:57<5:36:00,  1.71it/s]
Train steps ... :  65%|██████▌   | 65438/100000 [19:53:58<5:36:13,  1.71it/s]
Train steps ... :  65%|██████▌   | 65439/100000 [19:53:58<5:35:49,  1.72it/s]
Train steps ... :  65%|██████▌   | 65440/100000 [19:53:59<5:35:59,  1.71it/s]
Train steps ... :  65%|██████▌   | 65441/100000 [19:53:59<5:36:08,  1.71it/s]
Train steps ... :  65%|██████▌   | 65442/100000 [19:54:00<5:36:34,  1.71it/s]
Train steps ... :  65%|██████▌   | 65443/100000 [19:54:01<5:36:23,  1.71it/s]
Train steps ... :  65%|██████▌   | 65444/100000 [19:54:01<5:36:07,  1.71it/s]
Train steps ... :  65%|██████▌   | 65445/100000 [19:54:02<5:36:25,  1.71it/s]
Train steps ... :  65%|██████▌   | 65446/100000 [19:54:02<5:36:21,  1.71it/s]
Train steps ... :  65%|██████▌   | 65447/100000 [19:54:03<5:36:15,  1.71it/s]
Train steps ... :  65%|██████▌   | 65448/100000 [19:54:03<5:36:34,  1.71it/s]
Train steps ... :  65%|██████▌   | 65449/100000 [19:54:04<5:36:15,  1.71it/s]
Train steps ... :  65%|██████▌   | 65450/100000 [19:54:05<5:36:05,  1.71it/s]Step... (65450 / 100000 | Loss: 0.7602908611297607, Learning Rate: 3.4723618090452267e-05)
+
                                                                             
Step... (65450 / 100000 | Loss: 0.7152340412139893, Learning Rate: 3.4723618090452267e-05)
+
Train steps ... :  65%|██████▌   | 65450/100000 [19:54:05<5:36:05,  1.71it/s]
Train steps ... :  65%|██████▌   | 65451/100000 [19:54:05<5:36:41,  1.71it/s]
Train steps ... :  65%|██████▌   | 65452/100000 [19:54:06<5:36:46,  1.71it/s]
Train steps ... :  65%|██████▌   | 65453/100000 [19:54:06<5:36:37,  1.71it/s]
Train steps ... :  65%|██████▌   | 65454/100000 [19:54:07<5:36:50,  1.71it/s]
Train steps ... :  65%|██████▌   | 65455/100000 [19:54:08<5:36:28,  1.71it/s]
Train steps ... :  65%|██████▌   | 65456/100000 [19:54:08<5:36:14,  1.71it/s]
Train steps ... :  65%|██████▌   | 65457/100000 [19:54:09<5:36:28,  1.71it/s]
Train steps ... :  65%|██████▌   | 65458/100000 [19:54:09<5:36:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65459/100000 [19:54:10<5:35:53,  1.71it/s]
Train steps ... :  65%|██████▌   | 65460/100000 [19:54:10<5:35:56,  1.71it/s]
Train steps ... :  65%|██████▌   | 65461/100000 [19:54:11<5:36:25,  1.71it/s]
Train steps ... :  65%|██████▌   | 65462/100000 [19:54:12<5:36:12,  1.71it/s]
Train steps ... :  65%|██████▌   | 65463/100000 [19:54:12<5:36:30,  1.71it/s]
Train steps ... :  65%|██████▌   | 65464/100000 [19:54:13<5:36:06,  1.71it/s]
Train steps ... :  65%|██████▌   | 65465/100000 [19:54:13<5:36:34,  1.71it/s]
Train steps ... :  65%|██████▌   | 65466/100000 [19:54:14<5:36:50,  1.71it/s]
Train steps ... :  65%|██████▌   | 65467/100000 [19:54:15<5:36:21,  1.71it/s]
Train steps ... :  65%|██████▌   | 65468/100000 [19:54:15<5:36:04,  1.71it/s]
Train steps ... :  65%|██████▌   | 65469/100000 [19:54:16<5:35:42,  1.71it/s]
Train steps ... :  65%|██████▌   | 65470/100000 [19:54:16<5:36:00,  1.71it/s]
Train steps ... :  65%|██████▌   | 65471/100000 [19:54:17<5:35:54,  1.71it/s]
Train steps ... :  65%|██████▌   | 65472/100000 [19:54:17<5:36:04,  1.71it/s]
Train steps ... :  65%|██████▌   | 65473/100000 [19:54:18<5:35:51,  1.71it/s]
Train steps ... :  65%|██████▌   | 65474/100000 [19:54:19<5:35:53,  1.71it/s]
Train steps ... :  65%|██████▌   | 65475/100000 [19:54:19<5:35:51,  1.71it/s]Step... (65475 / 100000 | Loss: 1.010035514831543, Learning Rate: 3.469849246231156e-05)
+
                                                                             
Step... (65475 / 100000 | Loss: 0.6515015959739685, Learning Rate: 3.469849246231156e-05)
+
Train steps ... :  65%|██████▌   | 65475/100000 [19:54:20<5:35:51,  1.71it/s]
Train steps ... :  65%|██████▌   | 65476/100000 [19:54:20<5:36:17,  1.71it/s]
Train steps ... :  65%|██████▌   | 65477/100000 [19:54:20<5:36:24,  1.71it/s]
Train steps ... :  65%|██████▌   | 65478/100000 [19:54:21<5:36:39,  1.71it/s]
Train steps ... :  65%|██████▌   | 65479/100000 [19:54:22<5:36:32,  1.71it/s]
Train steps ... :  65%|██████▌   | 65480/100000 [19:54:22<5:36:12,  1.71it/s]
Train steps ... :  65%|██████▌   | 65481/100000 [19:54:23<5:36:12,  1.71it/s]
Train steps ... :  65%|██████▌   | 65482/100000 [19:54:23<5:36:21,  1.71it/s]
Train steps ... :  65%|██████▌   | 65483/100000 [19:54:24<5:36:15,  1.71it/s]
Train steps ... :  65%|██████▌   | 65484/100000 [19:54:24<5:36:31,  1.71it/s]
Train steps ... :  65%|██████▌   | 65485/100000 [19:54:25<5:36:55,  1.71it/s]
Train steps ... :  65%|██████▌   | 65486/100000 [19:54:26<5:36:57,  1.71it/s]
Train steps ... :  65%|██████▌   | 65487/100000 [19:54:26<5:36:38,  1.71it/s]
Train steps ... :  65%|██████▌   | 65488/100000 [19:54:27<5:36:29,  1.71it/s]
Train steps ... :  65%|██████▌   | 65489/100000 [19:54:27<5:36:05,  1.71it/s]
Train steps ... :  65%|██████▌   | 65490/100000 [19:54:28<5:36:09,  1.71it/s]
Train steps ... :  65%|██████▌   | 65491/100000 [19:54:29<5:36:11,  1.71it/s]
Train steps ... :  65%|██████▌   | 65492/100000 [19:54:29<5:36:07,  1.71it/s]
Train steps ... :  65%|██████▌   | 65493/100000 [19:54:30<5:35:58,  1.71it/s]
Train steps ... :  65%|██████▌   | 65494/100000 [19:54:30<5:36:03,  1.71it/s]
Train steps ... :  65%|██████▌   | 65495/100000 [19:54:31<5:36:33,  1.71it/s]
Train steps ... :  65%|██████▌   | 65496/100000 [19:54:32<5:36:03,  1.71it/s]
Train steps ... :  65%|██████▌   | 65497/100000 [19:54:32<5:36:18,  1.71it/s]
Train steps ... :  65%|██████▌   | 65498/100000 [19:54:33<5:35:52,  1.71it/s]
Train steps ... :  65%|██████▌   | 65499/100000 [19:54:33<5:36:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 65500/100000 [19:54:34<5:36:13,  1.71it/s]Step... (65500 / 100000 | Loss: 0.5514936447143555, Learning Rate: 3.467336683417085e-05)
+
                                                                             
Step... (65500 / 100000 | Loss: 1.036102294921875, Learning Rate: 3.467336683417085e-05)
+
Train steps ... :  66%|██████▌   | 65500/100000 [19:54:34<5:36:13,  1.71it/s]
Train steps ... :  66%|██████▌   | 65501/100000 [19:54:34<5:36:22,  1.71it/s]
Train steps ... :  66%|██████▌   | 65502/100000 [19:54:35<5:36:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 65503/100000 [19:54:36<5:36:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 65504/100000 [19:54:36<5:36:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 65505/100000 [19:54:37<5:36:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65506/100000 [19:54:37<5:36:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 65507/100000 [19:54:38<5:35:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 65508/100000 [19:54:39<5:36:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 65509/100000 [19:54:39<5:35:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 65510/100000 [19:54:40<5:35:36,  1.71it/s]
Train steps ... :  66%|██████▌   | 65511/100000 [19:54:40<5:35:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65512/100000 [19:54:41<5:35:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 65513/100000 [19:54:41<5:36:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65514/100000 [19:54:42<5:35:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 65515/100000 [19:54:43<5:35:41,  1.71it/s]
Train steps ... :  66%|██████▌   | 65516/100000 [19:54:43<5:35:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65517/100000 [19:54:44<5:35:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 65518/100000 [19:54:44<5:35:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 65519/100000 [19:54:45<5:35:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 65520/100000 [19:54:46<5:35:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 65521/100000 [19:54:46<5:35:36,  1.71it/s]
Train steps ... :  66%|██████▌   | 65522/100000 [19:54:47<5:36:05,  1.71it/s]
Train steps ... :  66%|██████▌   | 65523/100000 [19:54:47<5:35:57,  1.71it/s]
Train steps ... :  66%|██████▌   | 65524/100000 [19:54:48<5:35:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 65525/100000 [19:54:48<5:35:59,  1.71it/s]Step... (65525 / 100000 | Loss: 0.6379454135894775, Learning Rate: 3.464824120603015e-05)
+
                                                                             
Step... (65525 / 100000 | Loss: 0.6626641750335693, Learning Rate: 3.464824120603015e-05)
+
Train steps ... :  66%|██████▌   | 65525/100000 [19:54:49<5:35:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 65526/100000 [19:54:49<5:36:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 65527/100000 [19:54:50<5:35:41,  1.71it/s]
Train steps ... :  66%|██████▌   | 65528/100000 [19:54:50<5:35:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65529/100000 [19:54:51<5:35:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 65530/100000 [19:54:51<5:35:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 65531/100000 [19:54:52<5:35:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 65532/100000 [19:54:53<5:35:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65533/100000 [19:54:53<5:35:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65534/100000 [19:54:54<5:36:02,  1.71it/s]
Train steps ... :  66%|██████▌   | 65535/100000 [19:54:54<5:35:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 65536/100000 [19:54:55<5:35:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65537/100000 [19:54:55<5:35:13,  1.71it/s]
Train steps ... :  66%|██████▌   | 65538/100000 [19:54:56<5:35:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 65539/100000 [19:54:57<5:35:21,  1.71it/s]
Train steps ... :  66%|██████▌   | 65540/100000 [19:54:57<5:35:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65541/100000 [19:54:58<5:35:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 65542/100000 [19:54:58<5:35:36,  1.71it/s]
Train steps ... :  66%|██████▌   | 65543/100000 [19:54:59<5:35:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 65544/100000 [19:55:00<5:36:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65545/100000 [19:55:00<5:35:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65546/100000 [19:55:01<5:35:57,  1.71it/s]
Train steps ... :  66%|██████▌   | 65547/100000 [19:55:01<5:35:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 65548/100000 [19:55:02<5:35:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 65549/100000 [19:55:02<5:35:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 65550/100000 [19:55:03<5:35:23,  1.71it/s]Step... (65550 / 100000 | Loss: 0.7868848443031311, Learning Rate: 3.4623115577889446e-05)
+
                                                                             
Step... (65550 / 100000 | Loss: 0.6310339570045471, Learning Rate: 3.4623115577889446e-05)
+
Train steps ... :  66%|██████▌   | 65550/100000 [19:55:03<5:35:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 65551/100000 [19:55:04<5:35:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65552/100000 [19:55:04<5:35:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 65553/100000 [19:55:05<5:35:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 65554/100000 [19:55:05<5:35:41,  1.71it/s]
Train steps ... :  66%|██████▌   | 65555/100000 [19:55:06<5:35:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 65556/100000 [19:55:07<5:35:36,  1.71it/s]
Train steps ... :  66%|██████▌   | 65557/100000 [19:55:07<5:36:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 65558/100000 [19:55:08<5:35:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 65559/100000 [19:55:08<5:35:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 65560/100000 [19:55:09<5:35:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 65561/100000 [19:55:09<5:35:16,  1.71it/s]
Train steps ... :  66%|██████▌   | 65562/100000 [19:55:10<5:35:03,  1.71it/s]
Train steps ... :  66%|██████▌   | 65563/100000 [19:55:11<5:35:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 65564/100000 [19:55:11<5:35:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 65565/100000 [19:55:12<5:37:49,  1.70it/s]
Train steps ... :  66%|██████▌   | 65566/100000 [19:55:12<5:36:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 65567/100000 [19:55:13<5:36:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 65568/100000 [19:55:14<5:36:42,  1.70it/s]
Train steps ... :  66%|██████▌   | 65569/100000 [19:55:14<5:36:43,  1.70it/s]
Train steps ... :  66%|██████▌   | 65570/100000 [19:55:15<5:35:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65571/100000 [19:55:15<5:36:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 65572/100000 [19:55:16<5:35:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 65573/100000 [19:55:17<5:35:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 65574/100000 [19:55:17<5:36:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 65575/100000 [19:55:18<5:36:10,  1.71it/s]Step... (65575 / 100000 | Loss: 0.9079318046569824, Learning Rate: 3.459798994974874e-05)
+
                                                                             
Step... (65575 / 100000 | Loss: 0.581760823726654, Learning Rate: 3.459798994974874e-05)
+
Train steps ... :  66%|██████▌   | 65575/100000 [19:55:18<5:36:10,  1.71it/s]
Train steps ... :  66%|██████▌   | 65576/100000 [19:55:18<5:46:26,  1.66it/s]
Train steps ... :  66%|██████▌   | 65577/100000 [19:55:19<5:44:09,  1.67it/s]
Train steps ... :  66%|██████▌   | 65578/100000 [19:55:20<5:41:10,  1.68it/s]
Train steps ... :  66%|██████▌   | 65579/100000 [19:55:20<5:39:16,  1.69it/s]
Train steps ... :  66%|██████▌   | 65580/100000 [19:55:21<5:38:07,  1.70it/s]
Train steps ... :  66%|██████▌   | 65581/100000 [19:55:21<5:37:24,  1.70it/s]
Train steps ... :  66%|██████▌   | 65582/100000 [19:55:22<5:36:42,  1.70it/s]
Train steps ... :  66%|██████▌   | 65583/100000 [19:55:22<5:37:01,  1.70it/s]
Train steps ... :  66%|██████▌   | 65584/100000 [19:55:23<5:36:51,  1.70it/s]
Train steps ... :  66%|██████▌   | 65585/100000 [19:55:24<5:36:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 65586/100000 [19:55:24<5:35:54,  1.71it/s]
Train steps ... :  66%|██████▌   | 65587/100000 [19:55:25<5:36:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 65588/100000 [19:55:25<5:35:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65589/100000 [19:55:26<5:36:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 65590/100000 [19:55:27<5:35:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65591/100000 [19:55:27<5:36:23,  1.70it/s]
Train steps ... :  66%|██████▌   | 65592/100000 [19:55:28<5:35:45,  1.71it/s]
Train steps ... :  66%|██████▌   | 65593/100000 [19:55:28<5:36:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 65594/100000 [19:55:29<5:35:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 65595/100000 [19:55:29<5:36:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 65596/100000 [19:55:30<5:36:59,  1.70it/s]
Train steps ... :  66%|██████▌   | 65597/100000 [19:55:31<5:36:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 65598/100000 [19:55:31<5:35:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 65599/100000 [19:55:32<5:36:23,  1.70it/s]
Train steps ... :  66%|██████▌   | 65600/100000 [19:55:32<5:36:36,  1.70it/s]Step... (65600 / 100000 | Loss: 0.9394524693489075, Learning Rate: 3.457286432160804e-05)
+
                                                                             
Step... (65600 / 100000 | Loss: 0.6238315105438232, Learning Rate: 3.457286432160804e-05)
+
Train steps ... :  66%|██████▌   | 65600/100000 [19:55:33<5:36:36,  1.70it/s]
Train steps ... :  66%|██████▌   | 65601/100000 [19:55:33<5:36:16,  1.70it/s]
Train steps ... :  66%|██████▌   | 65602/100000 [19:55:34<5:35:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 65603/100000 [19:55:34<5:36:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 65604/100000 [19:55:35<5:35:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 65605/100000 [19:55:35<5:35:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 65606/100000 [19:55:36<5:35:14,  1.71it/s]
Train steps ... :  66%|██████▌   | 65607/100000 [19:55:36<5:34:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 65608/100000 [19:55:37<5:35:05,  1.71it/s]
Train steps ... :  66%|██████▌   | 65609/100000 [19:55:38<5:35:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 65610/100000 [19:55:38<5:35:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 65611/100000 [19:55:39<5:35:03,  1.71it/s]
Train steps ... :  66%|██████▌   | 65612/100000 [19:55:39<5:34:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65613/100000 [19:55:40<5:35:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 65614/100000 [19:55:41<5:35:10,  1.71it/s]
Train steps ... :  66%|██████▌   | 65615/100000 [19:55:41<5:35:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 65616/100000 [19:55:42<5:35:02,  1.71it/s]
Train steps ... :  66%|██████▌   | 65617/100000 [19:55:42<5:35:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65618/100000 [19:55:43<5:34:58,  1.71it/s]
Train steps ... :  66%|██████▌   | 65619/100000 [19:55:44<5:35:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 65620/100000 [19:55:44<5:35:00,  1.71it/s]
Train steps ... :  66%|██████▌   | 65621/100000 [19:55:45<5:34:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 65622/100000 [19:55:45<5:36:06,  1.70it/s]
Train steps ... :  66%|██████▌   | 65623/100000 [19:55:46<5:34:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 65624/100000 [19:55:46<5:34:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65625/100000 [19:55:47<5:35:02,  1.71it/s]Step... (65625 / 100000 | Loss: 0.6215381622314453, Learning Rate: 3.454773869346734e-05)
+
                                                                             
Step... (65625 / 100000 | Loss: 0.7801110744476318, Learning Rate: 3.454773869346734e-05)
+
Train steps ... :  66%|██████▌   | 65625/100000 [19:55:47<5:35:02,  1.71it/s]
Train steps ... :  66%|██████▌   | 65626/100000 [19:55:48<5:34:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 65627/100000 [19:55:48<5:34:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 65628/100000 [19:55:49<5:34:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65629/100000 [19:55:49<5:35:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 65630/100000 [19:55:50<5:34:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65631/100000 [19:55:51<5:35:28,  1.71it/s]
Train steps ... :  66%|██████▌   | 65632/100000 [19:55:51<5:34:13,  1.71it/s]
Train steps ... :  66%|██████▌   | 65633/100000 [19:55:52<5:34:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 65634/100000 [19:55:52<5:35:02,  1.71it/s]
Train steps ... :  66%|██████▌   | 65635/100000 [19:55:53<5:34:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65636/100000 [19:55:53<5:34:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 65637/100000 [19:55:54<5:34:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 65638/100000 [19:55:55<5:34:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 65639/100000 [19:55:55<5:34:58,  1.71it/s]
Train steps ... :  66%|██████▌   | 65640/100000 [19:55:56<5:35:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 65641/100000 [19:55:56<5:35:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 65642/100000 [19:55:57<5:35:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 65643/100000 [19:55:58<5:35:52,  1.70it/s]
Train steps ... :  66%|██████▌   | 65644/100000 [19:55:58<5:35:55,  1.70it/s]
Train steps ... :  66%|██████▌   | 65645/100000 [19:55:59<5:36:11,  1.70it/s]
Train steps ... :  66%|██████▌   | 65646/100000 [19:55:59<5:34:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 65647/100000 [19:56:00<5:34:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 65648/100000 [19:56:00<5:35:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65649/100000 [19:56:01<5:34:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 65650/100000 [19:56:02<5:34:29,  1.71it/s]Step... (65650 / 100000 | Loss: 0.8378809690475464, Learning Rate: 3.452261306532664e-05)
+
                                                                             
Step... (65650 / 100000 | Loss: 0.8574655055999756, Learning Rate: 3.452261306532664e-05)
+
Train steps ... :  66%|██████▌   | 65650/100000 [19:56:02<5:34:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 65651/100000 [19:56:02<5:34:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 65652/100000 [19:56:03<5:34:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 65653/100000 [19:56:03<5:35:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 65654/100000 [19:56:04<5:35:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 65655/100000 [19:56:05<5:34:58,  1.71it/s]
Train steps ... :  66%|██████▌   | 65656/100000 [19:56:05<5:35:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 65657/100000 [19:56:06<5:34:58,  1.71it/s]
Train steps ... :  66%|██████▌   | 65658/100000 [19:56:06<5:35:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 65659/100000 [19:56:07<5:34:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 65660/100000 [19:56:08<5:34:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65661/100000 [19:56:08<5:34:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 65662/100000 [19:56:09<5:34:10,  1.71it/s]
Train steps ... :  66%|██████▌   | 65663/100000 [19:56:09<5:34:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 65664/100000 [19:56:10<5:34:03,  1.71it/s]
Train steps ... :  66%|██████▌   | 65665/100000 [19:56:10<5:34:00,  1.71it/s]
Train steps ... :  66%|██████▌   | 65666/100000 [19:56:11<5:34:16,  1.71it/s]
Train steps ... :  66%|██████▌   | 65667/100000 [19:56:12<5:34:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65668/100000 [19:56:12<5:34:16,  1.71it/s]
Train steps ... :  66%|██████▌   | 65669/100000 [19:56:13<5:34:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 65670/100000 [19:56:13<5:34:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 65671/100000 [19:56:14<5:34:00,  1.71it/s]
Train steps ... :  66%|██████▌   | 65672/100000 [19:56:15<5:34:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 65673/100000 [19:56:15<5:34:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 65674/100000 [19:56:16<5:34:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 65675/100000 [19:56:16<5:34:22,  1.71it/s]Step... (65675 / 100000 | Loss: 0.6286885142326355, Learning Rate: 3.449748743718593e-05)
+
                                                                             
Step... (65675 / 100000 | Loss: 0.8036097288131714, Learning Rate: 3.449748743718593e-05)
+
Train steps ... :  66%|██████▌   | 65675/100000 [19:56:17<5:34:22,  1.71it/s]
Train steps ... :  66%|██████▌   | 65676/100000 [19:56:17<5:34:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 65677/100000 [19:56:17<5:34:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 65678/100000 [19:56:18<5:34:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 65679/100000 [19:56:19<5:34:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 65680/100000 [19:56:19<5:34:31,  1.71it/s]
Train steps ... :  66%|██████▌   | 65681/100000 [19:56:20<5:34:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 65682/100000 [19:56:20<5:34:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 65683/100000 [19:56:21<5:34:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 65684/100000 [19:56:22<5:34:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65685/100000 [19:56:22<5:34:21,  1.71it/s]
Train steps ... :  66%|██████▌   | 65686/100000 [19:56:23<5:34:38,  1.71it/s]
Train steps ... :  66%|██████▌   | 65687/100000 [19:56:23<5:34:38,  1.71it/s]
Train steps ... :  66%|██████▌   | 65688/100000 [19:56:24<5:35:14,  1.71it/s]
Train steps ... :  66%|██████▌   | 65689/100000 [19:56:24<5:34:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 65690/100000 [19:56:25<5:34:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 65691/100000 [19:56:26<5:34:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 65692/100000 [19:56:26<5:34:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 65693/100000 [19:56:27<5:34:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 65694/100000 [19:56:27<5:34:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 65695/100000 [19:56:28<5:34:26,  1.71it/s]
Train steps ... :  66%|██████▌   | 65696/100000 [19:56:29<5:34:10,  1.71it/s]
Train steps ... :  66%|██████▌   | 65697/100000 [19:56:29<5:34:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65698/100000 [19:56:30<5:34:36,  1.71it/s]
Train steps ... :  66%|██████▌   | 65699/100000 [19:56:30<5:34:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 65700/100000 [19:56:31<5:35:12,  1.71it/s]Step... (65700 / 100000 | Loss: 0.6318176984786987, Learning Rate: 3.4472361809045226e-05)
+
                                                                             
Step... (65700 / 100000 | Loss: 0.5450440645217896, Learning Rate: 3.4472361809045226e-05)
+
Train steps ... :  66%|██████▌   | 65700/100000 [19:56:31<5:35:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 65701/100000 [19:56:31<5:34:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 65702/100000 [19:56:32<5:34:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65703/100000 [19:56:33<5:34:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 65704/100000 [19:56:33<5:34:36,  1.71it/s]
Train steps ... :  66%|██████▌   | 65705/100000 [19:56:34<5:34:03,  1.71it/s]
Train steps ... :  66%|██████▌   | 65706/100000 [19:56:34<5:33:57,  1.71it/s]
Train steps ... :  66%|██████▌   | 65707/100000 [19:56:35<5:33:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 65708/100000 [19:56:36<5:34:03,  1.71it/s]
Train steps ... :  66%|██████▌   | 65709/100000 [19:56:36<5:33:48,  1.71it/s]
Train steps ... :  66%|██████▌   | 65710/100000 [19:56:37<5:33:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65711/100000 [19:56:37<5:33:28,  1.71it/s]
Train steps ... :  66%|██████▌   | 65712/100000 [19:56:38<5:33:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 65713/100000 [19:56:38<5:33:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 65714/100000 [19:56:39<5:33:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 65715/100000 [19:56:40<5:33:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 65716/100000 [19:56:40<5:33:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 65717/100000 [19:56:41<5:33:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 65718/100000 [19:56:41<5:33:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65719/100000 [19:56:42<5:34:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 65720/100000 [19:56:43<5:33:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65721/100000 [19:56:43<5:33:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65722/100000 [19:56:44<5:33:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 65723/100000 [19:56:44<5:33:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 65724/100000 [19:56:45<5:33:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 65725/100000 [19:56:46<5:34:00,  1.71it/s]Step... (65725 / 100000 | Loss: 0.7904769778251648, Learning Rate: 3.444723618090452e-05)
+
                                                                             
Step... (65725 / 100000 | Loss: 1.0027838945388794, Learning Rate: 3.444723618090452e-05)
+
Train steps ... :  66%|██████▌   | 65725/100000 [19:56:46<5:34:00,  1.71it/s]
Train steps ... :  66%|██████▌   | 65726/100000 [19:56:46<5:34:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 65727/100000 [19:56:47<5:33:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 65728/100000 [19:56:47<5:34:22,  1.71it/s]
Train steps ... :  66%|██████▌   | 65729/100000 [19:56:48<5:34:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 65730/100000 [19:56:48<5:34:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 65731/100000 [19:56:49<5:34:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 65732/100000 [19:56:50<5:33:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 65733/100000 [19:56:50<5:33:31,  1.71it/s]
Train steps ... :  66%|██████▌   | 65734/100000 [19:56:51<5:33:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 65735/100000 [19:56:51<5:33:41,  1.71it/s]
Train steps ... :  66%|██████▌   | 65736/100000 [19:56:52<5:33:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65737/100000 [19:56:53<5:33:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 65738/100000 [19:56:53<5:33:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 65739/100000 [19:56:54<5:33:26,  1.71it/s]
Train steps ... :  66%|██████▌   | 65740/100000 [19:56:54<5:33:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 65741/100000 [19:56:55<5:33:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 65742/100000 [19:56:55<5:33:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 65743/100000 [19:56:56<5:33:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 65744/100000 [19:56:57<5:33:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 65745/100000 [19:56:57<5:33:41,  1.71it/s]
Train steps ... :  66%|██████▌   | 65746/100000 [19:56:58<5:33:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 65747/100000 [19:56:58<5:33:31,  1.71it/s]
Train steps ... :  66%|██████▌   | 65748/100000 [19:56:59<5:33:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 65749/100000 [19:57:00<5:33:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 65750/100000 [19:57:00<5:33:21,  1.71it/s]Step... (65750 / 100000 | Loss: 0.6252118349075317, Learning Rate: 3.442211055276382e-05)
+
                                                                             
Step... (65750 / 100000 | Loss: 0.9196447730064392, Learning Rate: 3.442211055276382e-05)
+
Train steps ... :  66%|██████▌   | 65750/100000 [19:57:00<5:33:21,  1.71it/s]
Train steps ... :  66%|██████▌   | 65751/100000 [19:57:01<5:33:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 65752/100000 [19:57:01<5:33:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65753/100000 [19:57:02<5:34:05,  1.71it/s]
Train steps ... :  66%|██████▌   | 65754/100000 [19:57:02<5:34:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 65755/100000 [19:57:03<5:33:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65756/100000 [19:57:04<5:33:20,  1.71it/s]
Train steps ... :  66%|██████▌   | 65757/100000 [19:57:04<5:34:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65758/100000 [19:57:05<5:34:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 65759/100000 [19:57:05<5:33:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 65760/100000 [19:57:06<5:33:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 65761/100000 [19:57:07<5:33:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 65762/100000 [19:57:07<5:33:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 65763/100000 [19:57:08<5:34:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 65764/100000 [19:57:08<5:34:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 65765/100000 [19:57:09<5:33:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 65766/100000 [19:57:09<5:33:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65767/100000 [19:57:10<5:34:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 65768/100000 [19:57:11<5:34:00,  1.71it/s]
Train steps ... :  66%|██████▌   | 65769/100000 [19:57:11<5:33:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65770/100000 [19:57:12<5:33:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 65771/100000 [19:57:12<5:33:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 65772/100000 [19:57:13<5:33:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 65773/100000 [19:57:14<5:33:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65774/100000 [19:57:14<5:33:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 65775/100000 [19:57:15<5:32:47,  1.71it/s]Step... (65775 / 100000 | Loss: 0.6461005806922913, Learning Rate: 3.4396984924623116e-05)
+
                                                                             
Step... (65775 / 100000 | Loss: 0.8441115617752075, Learning Rate: 3.4396984924623116e-05)
+
Train steps ... :  66%|██████▌   | 65775/100000 [19:57:15<5:32:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 65776/100000 [19:57:15<5:33:05,  1.71it/s]
Train steps ... :  66%|██████▌   | 65777/100000 [19:57:16<5:33:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65778/100000 [19:57:16<5:33:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65779/100000 [19:57:17<5:34:37,  1.70it/s]
Train steps ... :  66%|██████▌   | 65780/100000 [19:57:18<5:33:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65781/100000 [19:57:18<5:33:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 65782/100000 [19:57:19<5:34:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 65783/100000 [19:57:19<5:34:26,  1.71it/s]
Train steps ... :  66%|██████▌   | 65784/100000 [19:57:20<5:33:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65785/100000 [19:57:21<5:33:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 65786/100000 [19:57:21<5:34:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 65787/100000 [19:57:22<5:34:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 65788/100000 [19:57:22<5:34:32,  1.70it/s]
Train steps ... :  66%|██████▌   | 65789/100000 [19:57:23<5:33:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 65790/100000 [19:57:24<5:33:45,  1.71it/s]
Train steps ... :  66%|██████▌   | 65791/100000 [19:57:24<5:33:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 65792/100000 [19:57:25<5:33:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65793/100000 [19:57:25<5:33:03,  1.71it/s]
Train steps ... :  66%|██████▌   | 65794/100000 [19:57:26<5:33:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 65795/100000 [19:57:26<5:33:22,  1.71it/s]
Train steps ... :  66%|██████▌   | 65796/100000 [19:57:27<5:33:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 65797/100000 [19:57:28<5:32:54,  1.71it/s]
Train steps ... :  66%|██████▌   | 65798/100000 [19:57:28<5:33:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 65799/100000 [19:57:29<5:33:20,  1.71it/s]
Train steps ... :  66%|██████▌   | 65800/100000 [19:57:29<5:33:46,  1.71it/s]Step... (65800 / 100000 | Loss: 0.693308413028717, Learning Rate: 3.437185929648241e-05)
+
                                                                             
Step... (65800 / 100000 | Loss: 0.9352884888648987, Learning Rate: 3.437185929648241e-05)
+
Train steps ... :  66%|██████▌   | 65800/100000 [19:57:30<5:33:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 65801/100000 [19:57:30<5:33:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 65802/100000 [19:57:31<5:33:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 65803/100000 [19:57:31<5:32:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65804/100000 [19:57:32<5:32:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 65805/100000 [19:57:32<5:33:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 65806/100000 [19:57:33<5:33:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 65807/100000 [19:57:33<5:33:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 65808/100000 [19:57:34<5:33:28,  1.71it/s]
Train steps ... :  66%|██████▌   | 65809/100000 [19:57:35<5:33:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 65810/100000 [19:57:35<5:33:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 65811/100000 [19:57:36<5:34:20,  1.70it/s]
Train steps ... :  66%|██████▌   | 65812/100000 [19:57:36<5:33:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 65813/100000 [19:57:37<5:33:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 65814/100000 [19:57:38<5:33:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 65815/100000 [19:57:38<5:33:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 65816/100000 [19:57:39<5:33:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 65817/100000 [19:57:39<5:32:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 65818/100000 [19:57:40<5:33:41,  1.71it/s]
Train steps ... :  66%|██████▌   | 65819/100000 [19:57:40<5:32:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 65820/100000 [19:57:41<5:33:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 65821/100000 [19:57:42<5:33:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 65822/100000 [19:57:42<5:33:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65823/100000 [19:57:43<5:33:14,  1.71it/s]
Train steps ... :  66%|██████▌   | 65824/100000 [19:57:43<5:33:20,  1.71it/s]
Train steps ... :  66%|██████▌   | 65825/100000 [19:57:44<5:33:44,  1.71it/s]Step... (65825 / 100000 | Loss: 0.6986256837844849, Learning Rate: 3.4346733668341716e-05)
+
                                                                             
Step... (65825 / 100000 | Loss: 0.7606909871101379, Learning Rate: 3.4346733668341716e-05)
+
Train steps ... :  66%|██████▌   | 65825/100000 [19:57:44<5:33:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 65826/100000 [19:57:45<5:33:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65827/100000 [19:57:45<5:33:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 65828/100000 [19:57:46<5:33:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 65829/100000 [19:57:46<5:34:05,  1.70it/s]
Train steps ... :  66%|██████▌   | 65830/100000 [19:57:47<5:34:17,  1.70it/s]
Train steps ... :  66%|██████▌   | 65831/100000 [19:57:48<5:34:36,  1.70it/s]
Train steps ... :  66%|██████▌   | 65832/100000 [19:57:48<5:32:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65833/100000 [19:57:49<5:33:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 65834/100000 [19:57:49<5:33:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65835/100000 [19:57:50<5:34:15,  1.70it/s]
Train steps ... :  66%|██████▌   | 65836/100000 [19:57:50<5:33:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 65837/100000 [19:57:51<5:34:10,  1.70it/s]
Train steps ... :  66%|██████▌   | 65838/100000 [19:57:52<5:33:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 65839/100000 [19:57:52<5:33:48,  1.71it/s]
Train steps ... :  66%|██████▌   | 65840/100000 [19:57:53<5:33:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 65841/100000 [19:57:53<5:33:38,  1.71it/s]
Train steps ... :  66%|██████▌   | 65842/100000 [19:57:54<5:33:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 65843/100000 [19:57:55<5:33:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 65844/100000 [19:57:55<5:33:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 65845/100000 [19:57:56<5:33:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 65846/100000 [19:57:56<5:33:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 65847/100000 [19:57:57<5:32:38,  1.71it/s]
Train steps ... :  66%|██████▌   | 65848/100000 [19:57:57<5:32:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65849/100000 [19:57:58<5:32:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 65850/100000 [19:57:59<5:32:47,  1.71it/s]Step... (65850 / 100000 | Loss: 0.9382357597351074, Learning Rate: 3.4321608040201006e-05)
+
                                                                             
Step... (65850 / 100000 | Loss: 0.7187755107879639, Learning Rate: 3.4321608040201006e-05)
+
Train steps ... :  66%|██████▌   | 65850/100000 [19:57:59<5:32:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 65851/100000 [19:57:59<5:32:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 65852/100000 [19:58:00<5:32:57,  1.71it/s]
Train steps ... :  66%|██████▌   | 65853/100000 [19:58:00<5:32:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 65854/100000 [19:58:01<5:32:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 65855/100000 [19:58:02<5:32:57,  1.71it/s]
Train steps ... :  66%|██████▌   | 65856/100000 [19:58:02<5:33:26,  1.71it/s]
Train steps ... :  66%|██████▌   | 65857/100000 [19:58:03<5:32:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 65858/100000 [19:58:03<5:32:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 65859/100000 [19:58:04<5:34:08,  1.70it/s]
Train steps ... :  66%|██████▌   | 65860/100000 [19:58:04<5:33:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 65861/100000 [19:58:05<5:34:34,  1.70it/s]
Train steps ... :  66%|██████▌   | 65862/100000 [19:58:06<5:34:08,  1.70it/s]
Train steps ... :  66%|██████▌   | 65863/100000 [19:58:06<5:34:06,  1.70it/s]
Train steps ... :  66%|██████▌   | 65864/100000 [19:58:07<5:33:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 65865/100000 [19:58:07<5:33:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 65866/100000 [19:58:08<5:33:40,  1.70it/s]
Train steps ... :  66%|██████▌   | 65867/100000 [19:58:09<5:34:14,  1.70it/s]
Train steps ... :  66%|██████▌   | 65868/100000 [19:58:09<5:33:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 65869/100000 [19:58:10<5:33:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 65870/100000 [19:58:10<5:33:26,  1.71it/s]
Train steps ... :  66%|██████▌   | 65871/100000 [19:58:11<5:33:55,  1.70it/s]
Train steps ... :  66%|██████▌   | 65872/100000 [19:58:12<5:33:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65873/100000 [19:58:12<5:33:05,  1.71it/s]
Train steps ... :  66%|██████▌   | 65874/100000 [19:58:13<5:32:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 65875/100000 [19:58:13<5:32:42,  1.71it/s]Step... (65875 / 100000 | Loss: 0.9748977422714233, Learning Rate: 3.42964824120603e-05)
+
                                                                             
Step... (65875 / 100000 | Loss: 0.7136690616607666, Learning Rate: 3.42964824120603e-05)
+
Train steps ... :  66%|██████▌   | 65875/100000 [19:58:14<5:32:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 65876/100000 [19:58:14<5:33:40,  1.70it/s]
Train steps ... :  66%|██████▌   | 65877/100000 [19:58:14<5:34:08,  1.70it/s]
Train steps ... :  66%|██████▌   | 65878/100000 [19:58:15<5:33:02,  1.71it/s]
Train steps ... :  66%|██████▌   | 65879/100000 [19:58:16<5:32:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 65880/100000 [19:58:16<5:33:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 65881/100000 [19:58:17<5:33:20,  1.71it/s]
Train steps ... :  66%|██████▌   | 65882/100000 [19:58:17<5:33:28,  1.71it/s]
Train steps ... :  66%|██████▌   | 65883/100000 [19:58:18<5:33:26,  1.71it/s]
Train steps ... :  66%|██████▌   | 65884/100000 [19:58:19<5:34:15,  1.70it/s]
Train steps ... :  66%|██████▌   | 65885/100000 [19:58:19<5:34:16,  1.70it/s]
Train steps ... :  66%|██████▌   | 65886/100000 [19:58:20<5:34:14,  1.70it/s]
Train steps ... :  66%|██████▌   | 65887/100000 [19:58:20<5:33:39,  1.70it/s]
Train steps ... :  66%|██████▌   | 65888/100000 [19:58:21<5:33:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 65889/100000 [19:58:22<5:32:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65890/100000 [19:58:22<5:32:20,  1.71it/s]
Train steps ... :  66%|██████▌   | 65891/100000 [19:58:23<5:32:26,  1.71it/s]
Train steps ... :  66%|██████▌   | 65892/100000 [19:58:23<5:32:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 65893/100000 [19:58:24<5:32:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 65894/100000 [19:58:24<5:32:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 65895/100000 [19:58:25<5:32:13,  1.71it/s]
Train steps ... :  66%|██████▌   | 65896/100000 [19:58:26<5:32:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 65897/100000 [19:58:26<5:32:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65898/100000 [19:58:27<5:32:41,  1.71it/s]
Train steps ... :  66%|██████▌   | 65899/100000 [19:58:27<5:32:21,  1.71it/s]
Train steps ... :  66%|██████▌   | 65900/100000 [19:58:28<5:32:24,  1.71it/s]Step... (65900 / 100000 | Loss: 0.6927374005317688, Learning Rate: 3.42713567839196e-05)
+
                                                                             
Step... (65900 / 100000 | Loss: 0.8380199670791626, Learning Rate: 3.42713567839196e-05)
+
Train steps ... :  66%|██████▌   | 65900/100000 [19:58:28<5:32:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 65901/100000 [19:58:29<5:32:28,  1.71it/s]
Train steps ... :  66%|██████▌   | 65902/100000 [19:58:29<5:32:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 65903/100000 [19:58:30<5:32:31,  1.71it/s]
Train steps ... :  66%|██████▌   | 65904/100000 [19:58:30<5:33:03,  1.71it/s]
Train steps ... :  66%|██████▌   | 65905/100000 [19:58:31<5:32:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 65906/100000 [19:58:31<5:33:24,  1.70it/s]
Train steps ... :  66%|██████▌   | 65907/100000 [19:58:32<5:33:00,  1.71it/s]
Train steps ... :  66%|██████▌   | 65908/100000 [19:58:33<5:33:15,  1.70it/s]
Train steps ... :  66%|██████▌   | 65909/100000 [19:58:33<5:32:38,  1.71it/s]
Train steps ... :  66%|██████▌   | 65910/100000 [19:58:34<5:32:14,  1.71it/s]
Train steps ... :  66%|██████▌   | 65911/100000 [19:58:34<5:32:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65912/100000 [19:58:35<5:32:03,  1.71it/s]
Train steps ... :  66%|██████▌   | 65913/100000 [19:58:36<5:32:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 65914/100000 [19:58:36<5:33:31,  1.70it/s]
Train steps ... :  66%|██████▌   | 65915/100000 [19:58:37<5:33:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 65916/100000 [19:58:37<5:33:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 65917/100000 [19:58:38<5:32:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 65918/100000 [19:58:38<5:32:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 65919/100000 [19:58:39<5:32:45,  1.71it/s]
Train steps ... :  66%|██████▌   | 65920/100000 [19:58:40<5:32:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 65921/100000 [19:58:40<5:32:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 65922/100000 [19:58:41<5:33:32,  1.70it/s]
Train steps ... :  66%|██████▌   | 65923/100000 [19:58:41<5:32:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 65924/100000 [19:58:42<5:32:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 65925/100000 [19:58:43<5:32:16,  1.71it/s]Step... (65925 / 100000 | Loss: 0.7813829779624939, Learning Rate: 3.4246231155778896e-05)
+
                                                                             
Step... (65925 / 100000 | Loss: 0.6576632261276245, Learning Rate: 3.4246231155778896e-05)
+
Train steps ... :  66%|██████▌   | 65925/100000 [19:58:43<5:32:16,  1.71it/s]
Train steps ... :  66%|██████▌   | 65926/100000 [19:58:43<5:32:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65927/100000 [19:58:44<5:32:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 65928/100000 [19:58:44<5:31:58,  1.71it/s]
Train steps ... :  66%|██████▌   | 65929/100000 [19:58:45<5:33:05,  1.70it/s]
Train steps ... :  66%|██████▌   | 65930/100000 [19:58:46<5:34:27,  1.70it/s]
Train steps ... :  66%|██████▌   | 65931/100000 [19:58:46<5:33:54,  1.70it/s]
Train steps ... :  66%|██████▌   | 65932/100000 [19:58:47<5:33:04,  1.70it/s]
Train steps ... :  66%|██████▌   | 65933/100000 [19:58:47<5:32:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 65934/100000 [19:58:48<5:32:02,  1.71it/s]
Train steps ... :  66%|██████▌   | 65935/100000 [19:58:48<5:33:14,  1.70it/s]
Train steps ... :  66%|██████▌   | 65936/100000 [19:58:49<5:32:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65937/100000 [19:58:50<5:33:02,  1.70it/s]
Train steps ... :  66%|██████▌   | 65938/100000 [19:58:50<5:32:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 65939/100000 [19:58:51<5:31:57,  1.71it/s]
Train steps ... :  66%|██████▌   | 65940/100000 [19:58:51<5:32:58,  1.70it/s]
Train steps ... :  66%|██████▌   | 65941/100000 [19:58:52<5:32:20,  1.71it/s]
Train steps ... :  66%|██████▌   | 65942/100000 [19:58:53<5:31:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65943/100000 [19:58:53<5:31:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 65944/100000 [19:58:54<5:31:58,  1.71it/s]
Train steps ... :  66%|██████▌   | 65945/100000 [19:58:54<5:32:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 65946/100000 [19:58:55<5:32:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65947/100000 [19:58:55<5:31:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65948/100000 [19:58:56<5:31:59,  1.71it/s]
Train steps ... :  66%|█████��▌   | 65949/100000 [19:58:57<5:31:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65950/100000 [19:58:57<5:32:01,  1.71it/s]Step... (65950 / 100000 | Loss: 0.8585212826728821, Learning Rate: 3.422110552763819e-05)
+
                                                                             
Step... (65950 / 100000 | Loss: 0.6972024440765381, Learning Rate: 3.422110552763819e-05)
+
Train steps ... :  66%|██████▌   | 65950/100000 [19:58:58<5:32:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 65951/100000 [19:58:58<5:32:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 65952/100000 [19:58:58<5:33:06,  1.70it/s]
Train steps ... :  66%|██████▌   | 65953/100000 [19:58:59<5:32:00,  1.71it/s]
Train steps ... :  66%|██████▌   | 65954/100000 [19:59:00<5:31:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 65955/100000 [19:59:00<5:32:16,  1.71it/s]
Train steps ... :  66%|██████▌   | 65956/100000 [19:59:01<5:32:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 65957/100000 [19:59:01<5:32:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 65958/100000 [19:59:02<5:32:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 65959/100000 [19:59:02<5:31:58,  1.71it/s]
Train steps ... :  66%|██████▌   | 65960/100000 [19:59:03<5:33:03,  1.70it/s]
Train steps ... :  66%|██████▌   | 65961/100000 [19:59:04<5:32:20,  1.71it/s]
Train steps ... :  66%|██████▌   | 65962/100000 [19:59:04<5:31:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 65963/100000 [19:59:05<5:31:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 65964/100000 [19:59:05<5:31:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 65965/100000 [19:59:06<5:32:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 65966/100000 [19:59:07<5:32:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 65967/100000 [19:59:07<5:31:54,  1.71it/s]
Train steps ... :  66%|██████▌   | 65968/100000 [19:59:08<5:32:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 65969/100000 [19:59:08<5:33:05,  1.70it/s]
Train steps ... :  66%|██████▌   | 65970/100000 [19:59:09<5:32:56,  1.70it/s]
Train steps ... :  66%|██████▌   | 65971/100000 [19:59:10<5:32:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 65972/100000 [19:59:10<5:33:02,  1.70it/s]
Train steps ... :  66%|██████▌   | 65973/100000 [19:59:11<5:33:11,  1.70it/s]
Train steps ... :  66%|██████▌   | 65974/100000 [19:59:11<5:32:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 65975/100000 [19:59:12<5:32:04,  1.71it/s]Step... (65975 / 100000 | Loss: 0.7797088027000427, Learning Rate: 3.419597989949749e-05)
+
                                                                             
Step... (65975 / 100000 | Loss: 0.8333905935287476, Learning Rate: 3.419597989949749e-05)
+
Train steps ... :  66%|██████▌   | 65975/100000 [19:59:12<5:32:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 65976/100000 [19:59:12<5:31:58,  1.71it/s]
Train steps ... :  66%|██████▌   | 65977/100000 [19:59:13<5:31:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65978/100000 [19:59:14<5:31:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 65979/100000 [19:59:14<5:32:20,  1.71it/s]
Train steps ... :  66%|██████▌   | 65980/100000 [19:59:15<5:31:36,  1.71it/s]
Train steps ... :  66%|██████▌   | 65981/100000 [19:59:15<5:31:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 65982/100000 [19:59:16<5:31:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65983/100000 [19:59:17<5:31:13,  1.71it/s]
Train steps ... :  66%|██████▌   | 65984/100000 [19:59:17<5:31:14,  1.71it/s]
Train steps ... :  66%|██████▌   | 65985/100000 [19:59:18<5:31:26,  1.71it/s]
Train steps ... :  66%|██████▌   | 65986/100000 [19:59:18<5:32:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 65987/100000 [19:59:19<5:30:57,  1.71it/s]
Train steps ... :  66%|██████▌   | 65988/100000 [19:59:19<5:30:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 65989/100000 [19:59:20<5:31:10,  1.71it/s]
Train steps ... :  66%|██████▌   | 65990/100000 [19:59:21<5:31:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65991/100000 [19:59:21<5:31:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 65992/100000 [19:59:22<5:32:30,  1.70it/s]
Train steps ... :  66%|██████▌   | 65993/100000 [19:59:22<5:32:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 65994/100000 [19:59:23<5:32:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 65995/100000 [19:59:24<5:31:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 65996/100000 [19:59:24<5:31:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 65997/100000 [19:59:25<5:31:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 65998/100000 [19:59:25<5:31:41,  1.71it/s]
Train steps ... :  66%|██████▌   | 65999/100000 [19:59:26<5:32:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 66000/100000 [19:59:27<5:31:59,  1.71it/s]Step... (66000 / 100000 | Loss: 0.6865489482879639, Learning Rate: 3.4170854271356785e-05)
+
                                                                             
Step... (66000 / 100000 | Loss: 0.7686137557029724, Learning Rate: 3.4170854271356785e-05)
+
Train steps ... :  66%|██████▌   | 66000/100000 [19:59:27<5:31:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 66001/100000 [19:59:27<5:32:10,  1.71it/s]
Train steps ... :  66%|██████▌   | 66002/100000 [19:59:28<5:31:54,  1.71it/s]
Train steps ... :  66%|██████▌   | 66003/100000 [19:59:28<5:32:39,  1.70it/s]
Train steps ... :  66%|██████▌   | 66004/100000 [19:59:29<5:31:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 66005/100000 [19:59:29<5:31:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 66006/100000 [19:59:30<5:31:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 66007/100000 [19:59:31<5:31:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 66008/100000 [19:59:31<5:30:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 66009/100000 [19:59:32<5:31:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 66010/100000 [19:59:32<5:30:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 66011/100000 [19:59:33<5:31:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 66012/100000 [19:59:34<5:31:22,  1.71it/s]
Train steps ... :  66%|██████▌   | 66013/100000 [19:59:34<5:31:22,  1.71it/s]
Train steps ... :  66%|██████▌   | 66014/100000 [19:59:35<5:32:21,  1.70it/s]
Train steps ... :  66%|██████▌   | 66015/100000 [19:59:35<5:31:36,  1.71it/s]
Train steps ... :  66%|██████▌   | 66016/100000 [19:59:36<5:31:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 66017/100000 [19:59:36<5:31:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 66018/100000 [19:59:37<5:31:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 66019/100000 [19:59:38<5:31:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 66020/100000 [19:59:38<5:31:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 66021/100000 [19:59:39<5:32:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 66022/100000 [19:59:39<5:31:38,  1.71it/s]
Train steps ... :  66%|██████▌   | 66023/100000 [19:59:40<5:31:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 66024/100000 [19:59:41<5:31:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 66025/100000 [19:59:41<5:31:39,  1.71it/s]Step... (66025 / 100000 | Loss: 0.8409782648086548, Learning Rate: 3.414572864321608e-05)
+
                                                                             
Step... (66025 / 100000 | Loss: 0.7124358415603638, Learning Rate: 3.414572864321608e-05)
+
Train steps ... :  66%|██████▌   | 66025/100000 [19:59:41<5:31:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 66026/100000 [19:59:42<5:32:11,  1.70it/s]
Train steps ... :  66%|██████▌   | 66027/100000 [19:59:42<5:31:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 66028/100000 [19:59:43<5:32:50,  1.70it/s]
Train steps ... :  66%|██████▌   | 66029/100000 [19:59:43<5:31:54,  1.71it/s]
Train steps ... :  66%|██████▌   | 66030/100000 [19:59:44<5:32:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 66031/100000 [19:59:45<5:32:06,  1.70it/s]
Train steps ... :  66%|██████▌   | 66032/100000 [19:59:45<5:31:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 66033/100000 [19:59:46<5:31:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 66034/100000 [19:59:46<5:31:02,  1.71it/s]
Train steps ... :  66%|██████▌   | 66035/100000 [19:59:47<5:31:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 66036/100000 [19:59:48<5:31:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 66037/100000 [19:59:48<5:31:28,  1.71it/s]
Train steps ... :  66%|██████▌   | 66038/100000 [19:59:49<5:31:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 66039/100000 [19:59:49<5:31:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 66040/100000 [19:59:50<5:30:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 66041/100000 [19:59:51<5:30:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 66042/100000 [19:59:51<5:30:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 66043/100000 [19:59:52<5:30:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 66044/100000 [19:59:52<5:30:13,  1.71it/s]
Train steps ... :  66%|███��██▌   | 66045/100000 [19:59:53<5:30:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 66046/100000 [19:59:53<5:30:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 66047/100000 [19:59:54<5:30:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 66048/100000 [19:59:55<5:30:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 66049/100000 [19:59:55<5:30:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 66050/100000 [19:59:56<5:31:51,  1.71it/s]Step... (66050 / 100000 | Loss: 0.7507107853889465, Learning Rate: 3.412060301507538e-05)
+
                                                                             
Step... (66050 / 100000 | Loss: 0.9254546165466309, Learning Rate: 3.412060301507538e-05)
+
Train steps ... :  66%|██████▌   | 66050/100000 [19:59:56<5:31:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 66051/100000 [19:59:56<5:31:10,  1.71it/s]
Train steps ... :  66%|██████▌   | 66052/100000 [19:59:57<5:30:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 66053/100000 [19:59:58<5:31:02,  1.71it/s]
Train steps ... :  66%|██████▌   | 66054/100000 [19:59:58<5:31:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 66055/100000 [19:59:59<5:31:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 66056/100000 [19:59:59<5:31:52,  1.70it/s]
Train steps ... :  66%|██████▌   | 66057/100000 [20:00:00<5:30:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 66058/100000 [20:00:00<5:30:05,  1.71it/s]
Train steps ... :  66%|██████▌   | 66059/100000 [20:00:01<5:30:13,  1.71it/s]
Train steps ... :  66%|██████▌   | 66060/100000 [20:00:02<5:30:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 66061/100000 [20:00:02<5:30:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 66062/100000 [20:00:03<5:31:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 66063/100000 [20:00:03<5:31:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 66064/100000 [20:00:04<5:31:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 66065/100000 [20:00:05<5:31:21,  1.71it/s]
Train steps ... :  66%|██████▌   | 66066/100000 [20:00:05<5:30:28,  1.71it/s]
Train steps ... :  66%|██████▌   | 66067/100000 [20:00:06<5:31:16,  1.71it/s]
Train steps ... :  66%|██████▌   | 66068/100000 [20:00:06<5:31:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 66069/100000 [20:00:07<5:31:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 66070/100000 [20:00:07<5:31:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 66071/100000 [20:00:08<5:31:11,  1.71it/s]
Train steps ... :  66%|██████▌   | 66072/100000 [20:00:09<5:31:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 66073/100000 [20:00:09<5:31:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 66074/100000 [20:00:10<5:31:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 66075/100000 [20:00:10<5:31:08,  1.71it/s]Step... (66075 / 100000 | Loss: 0.5407565236091614, Learning Rate: 3.4095477386934675e-05)
+
                                                                             
Step... (66075 / 100000 | Loss: 0.8906368017196655, Learning Rate: 3.4095477386934675e-05)
+
Train steps ... :  66%|██████▌   | 66075/100000 [20:00:11<5:31:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 66076/100000 [20:00:11<5:31:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 66077/100000 [20:00:12<5:31:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 66078/100000 [20:00:12<5:31:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 66079/100000 [20:00:13<5:30:47,  1.71it/s]
Train steps ... :  66%|██████▌   | 66080/100000 [20:00:13<5:30:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 66081/100000 [20:00:14<5:30:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 66082/100000 [20:00:14<5:30:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 66083/100000 [20:00:15<5:30:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 66084/100000 [20:00:16<5:31:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 66085/100000 [20:00:16<5:30:59,  1.71it/s]
Train steps ... :  66%|██████▌   | 66086/100000 [20:00:17<5:30:38,  1.71it/s]
Train steps ... :  66%|██████▌   | 66087/100000 [20:00:17<5:30:54,  1.71it/s]
Train steps ... :  66%|██████▌   | 66088/100000 [20:00:18<5:30:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 66089/100000 [20:00:19<5:30:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 66090/100000 [20:00:19<5:31:21,  1.71it/s]
Train steps ... :  66%|██████▌   | 66091/100000 [20:00:20<5:30:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 66092/100000 [20:00:20<5:31:06,  1.71it/s]
Train steps ... :  66%|██���███▌   | 66093/100000 [20:00:21<5:30:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 66094/100000 [20:00:22<5:30:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 66095/100000 [20:00:22<5:30:16,  1.71it/s]
Train steps ... :  66%|██████▌   | 66096/100000 [20:00:23<5:30:22,  1.71it/s]
Train steps ... :  66%|██████▌   | 66097/100000 [20:00:23<5:30:40,  1.71it/s]
Train steps ... :  66%|██████▌   | 66098/100000 [20:00:24<5:30:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 66099/100000 [20:00:24<5:30:12,  1.71it/s]
Train steps ... :  66%|██████▌   | 66100/100000 [20:00:25<5:30:19,  1.71it/s]Step... (66100 / 100000 | Loss: 0.7675541639328003, Learning Rate: 3.407035175879397e-05)
+
                                                                             
Step... (66100 / 100000 | Loss: 0.8645707368850708, Learning Rate: 3.407035175879397e-05)
+
Train steps ... :  66%|██████▌   | 66100/100000 [20:00:25<5:30:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 66101/100000 [20:00:26<5:30:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 66102/100000 [20:00:26<5:30:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 66103/100000 [20:00:27<5:30:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 66104/100000 [20:00:27<5:30:02,  1.71it/s]
Train steps ... :  66%|██████▌   | 66105/100000 [20:00:28<5:29:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 66106/100000 [20:00:29<5:30:10,  1.71it/s]
Train steps ... :  66%|██████▌   | 66107/100000 [20:00:29<5:30:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 66108/100000 [20:00:30<5:31:50,  1.70it/s]
Train steps ... :  66%|██████▌   | 66109/100000 [20:00:30<5:31:31,  1.70it/s]
Train steps ... :  66%|██████▌   | 66110/100000 [20:00:31<5:30:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 66111/100000 [20:00:31<5:30:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 66112/100000 [20:00:32<5:30:22,  1.71it/s]
Train steps ... :  66%|██████▌   | 66113/100000 [20:00:33<5:30:14,  1.71it/s]
Train steps ... :  66%|██████▌   | 66114/100000 [20:00:33<5:30:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 66115/100000 [20:00:34<5:30:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 66116/100000 [20:00:34<5:30:05,  1.71it/s]
Train steps ... :  66%|██████▌   | 66117/100000 [20:00:35<5:29:57,  1.71it/s]
Train steps ... :  66%|██████▌   | 66118/100000 [20:00:36<5:30:05,  1.71it/s]
Train steps ... :  66%|██████▌   | 66119/100000 [20:00:36<5:30:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 66120/100000 [20:00:37<5:30:29,  1.71it/s]
Train steps ... :  66%|██████▌   | 66121/100000 [20:00:37<5:30:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 66122/100000 [20:00:38<5:30:36,  1.71it/s]
Train steps ... :  66%|██████▌   | 66123/100000 [20:00:38<5:31:54,  1.70it/s]
Train steps ... :  66%|██████▌   | 66124/100000 [20:00:39<5:31:47,  1.70it/s]
Train steps ... :  66%|██████▌   | 66125/100000 [20:00:40<5:30:37,  1.71it/s]Step... (66125 / 100000 | Loss: 0.6636754274368286, Learning Rate: 3.404522613065327e-05)
+
                                                                             
Step... (66125 / 100000 | Loss: 0.7911748290061951, Learning Rate: 3.404522613065327e-05)
+
Train steps ... :  66%|██████▌   | 66125/100000 [20:00:40<5:30:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 66126/100000 [20:00:40<5:31:04,  1.71it/s]
Train steps ... :  66%|██████▌   | 66127/100000 [20:00:41<5:30:38,  1.71it/s]
Train steps ... :  66%|██████▌   | 66128/100000 [20:00:41<5:30:26,  1.71it/s]
Train steps ... :  66%|██████▌   | 66129/100000 [20:00:42<5:30:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 66130/100000 [20:00:43<5:30:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 66131/100000 [20:00:43<5:30:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 66132/100000 [20:00:44<5:30:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 66133/100000 [20:00:44<5:30:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 66134/100000 [20:00:45<5:30:27,  1.71it/s]
Train steps ... :  66%|██████▌   | 66135/100000 [20:00:46<5:30:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 66136/100000 [20:00:46<5:31:20,  1.70it/s]
Train steps ... :  66%|██████▌   | 66137/100000 [20:00:47<5:31:24,  1.70it/s]
Train steps ... :  66%|██████▌   | 66138/100000 [20:00:47<5:31:06,  1.70it/s]
Train steps ... :  66%|██████▌   | 66139/100000 [20:00:48<5:30:58,  1.71it/s]
Train steps ... :  66%|██████▌   | 66140/100000 [20:00:48<5:31:06,  1.70it/s]
Train steps ... :  66%|█��████▌   | 66141/100000 [20:00:49<5:30:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 66142/100000 [20:00:50<5:32:19,  1.70it/s]
Train steps ... :  66%|██████▌   | 66143/100000 [20:00:50<5:31:01,  1.70it/s]
Train steps ... :  66%|██████▌   | 66144/100000 [20:00:51<5:30:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 66145/100000 [20:00:51<5:30:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 66146/100000 [20:00:52<5:30:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 66147/100000 [20:00:53<5:29:45,  1.71it/s]
Train steps ... :  66%|██████▌   | 66148/100000 [20:00:53<5:30:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 66149/100000 [20:00:54<5:30:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 66150/100000 [20:00:54<5:29:52,  1.71it/s]Step... (66150 / 100000 | Loss: 0.7352701425552368, Learning Rate: 3.4020100502512565e-05)
+
                                                                             
Step... (66150 / 100000 | Loss: 0.569988489151001, Learning Rate: 3.4020100502512565e-05)
+
Train steps ... :  66%|██████▌   | 66150/100000 [20:00:55<5:29:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 66151/100000 [20:00:55<5:29:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 66152/100000 [20:00:55<5:29:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 66153/100000 [20:00:56<5:29:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 66154/100000 [20:00:57<5:30:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 66155/100000 [20:00:57<5:29:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 66156/100000 [20:00:58<5:29:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 66157/100000 [20:00:58<5:29:34,  1.71it/s]
Train steps ... :  66%|██████▌   | 66158/100000 [20:00:59<5:29:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 66159/100000 [20:01:00<5:29:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 66160/100000 [20:01:00<5:29:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 66161/100000 [20:01:01<5:29:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 66162/100000 [20:01:01<5:29:08,  1.71it/s]
Train steps ... :  66%|██████▌   | 66163/100000 [20:01:02<5:29:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 66164/100000 [20:01:02<5:29:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 66165/100000 [20:01:03<5:29:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 66166/100000 [20:01:04<5:29:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 66167/100000 [20:01:04<5:29:21,  1.71it/s]
Train steps ... :  66%|██████▌   | 66168/100000 [20:01:05<5:29:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 66169/100000 [20:01:05<5:29:15,  1.71it/s]
Train steps ... :  66%|██████▌   | 66170/100000 [20:01:06<5:29:31,  1.71it/s]
Train steps ... :  66%|██████▌   | 66171/100000 [20:01:07<5:29:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 66172/100000 [20:01:07<5:29:38,  1.71it/s]
Train steps ... :  66%|██████▌   | 66173/100000 [20:01:08<5:29:22,  1.71it/s]
Train steps ... :  66%|██████▌   | 66174/100000 [20:01:08<5:29:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 66175/100000 [20:01:09<5:29:37,  1.71it/s]Step... (66175 / 100000 | Loss: 0.6254799962043762, Learning Rate: 3.399497487437186e-05)
+
                                                                             
Step... (66175 / 100000 | Loss: 0.6874284744262695, Learning Rate: 3.399497487437186e-05)
+
Train steps ... :  66%|██████▌   | 66175/100000 [20:01:09<5:29:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 66176/100000 [20:01:10<5:30:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 66177/100000 [20:01:10<5:29:50,  1.71it/s]
Train steps ... :  66%|██████▌   | 66178/100000 [20:01:11<5:29:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 66179/100000 [20:01:11<5:29:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 66180/100000 [20:01:12<5:29:20,  1.71it/s]
Train steps ... :  66%|██████▌   | 66181/100000 [20:01:12<5:29:14,  1.71it/s]
Train steps ... :  66%|██████▌   | 66182/100000 [20:01:13<5:29:42,  1.71it/s]
Train steps ... :  66%|██████▌   | 66183/100000 [20:01:14<5:29:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 66184/100000 [20:01:14<5:29:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 66185/100000 [20:01:15<5:29:25,  1.71it/s]
Train steps ... :  66%|██████▌   | 66186/100000 [20:01:15<5:29:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 66187/100000 [20:01:16<5:29:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 66188/100000 [20:01:17<5:29:26,  1.71it/s]
Train steps ... :  66%|��█████▌   | 66189/100000 [20:01:17<5:29:10,  1.71it/s]
Train steps ... :  66%|██████▌   | 66190/100000 [20:01:18<5:29:00,  1.71it/s]
Train steps ... :  66%|██████▌   | 66191/100000 [20:01:18<5:29:02,  1.71it/s]
Train steps ... :  66%|██████▌   | 66192/100000 [20:01:19<5:28:54,  1.71it/s]
Train steps ... :  66%|██████▌   | 66193/100000 [20:01:19<5:28:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 66194/100000 [20:01:20<5:29:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 66195/100000 [20:01:21<5:29:06,  1.71it/s]
Train steps ... :  66%|██████▌   | 66196/100000 [20:01:21<5:29:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 66197/100000 [20:01:22<5:29:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 66198/100000 [20:01:22<5:29:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 66199/100000 [20:01:23<5:30:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 66200/100000 [20:01:24<5:29:44,  1.71it/s]Step... (66200 / 100000 | Loss: 0.6504596471786499, Learning Rate: 3.396984924623116e-05)
+
                                                                             
Step... (66200 / 100000 | Loss: 0.5936849117279053, Learning Rate: 3.396984924623116e-05)
+
Train steps ... :  66%|██████▌   | 66200/100000 [20:01:24<5:29:44,  1.71it/s]
Train steps ... :  66%|██████▌   | 66201/100000 [20:01:24<5:30:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 66202/100000 [20:01:25<5:30:09,  1.71it/s]
Train steps ... :  66%|██████▌   | 66203/100000 [20:01:25<5:29:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 66204/100000 [20:01:26<5:29:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 66205/100000 [20:01:26<5:29:24,  1.71it/s]
Train steps ... :  66%|██████▌   | 66206/100000 [20:01:27<5:29:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 66207/100000 [20:01:28<5:29:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 66208/100000 [20:01:28<5:28:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 66209/100000 [20:01:29<5:29:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 66210/100000 [20:01:29<5:28:51,  1.71it/s]
Train steps ... :  66%|██████▌   | 66211/100000 [20:01:30<5:29:07,  1.71it/s]
Train steps ... :  66%|██████▌   | 66212/100000 [20:01:31<5:28:48,  1.71it/s]
Train steps ... :  66%|██████▌   | 66213/100000 [20:01:31<5:29:01,  1.71it/s]
Train steps ... :  66%|██████▌   | 66214/100000 [20:01:32<5:28:56,  1.71it/s]
Train steps ... :  66%|██████▌   | 66215/100000 [20:01:32<5:29:13,  1.71it/s]
Train steps ... :  66%|██████▌   | 66216/100000 [20:01:33<5:28:57,  1.71it/s]
Train steps ... :  66%|██████▌   | 66217/100000 [20:01:33<5:29:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 66218/100000 [20:01:34<5:29:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 66219/100000 [20:01:35<5:29:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 66220/100000 [20:01:35<5:29:35,  1.71it/s]
Train steps ... :  66%|██████▌   | 66221/100000 [20:01:36<5:29:30,  1.71it/s]
Train steps ... :  66%|██████▌   | 66222/100000 [20:01:36<5:29:18,  1.71it/s]
Train steps ... :  66%|██████▌   | 66223/100000 [20:01:37<5:29:32,  1.71it/s]
Train steps ... :  66%|██████▌   | 66224/100000 [20:01:38<5:29:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 66225/100000 [20:01:38<5:29:00,  1.71it/s]Step... (66225 / 100000 | Loss: 0.9335628747940063, Learning Rate: 3.394472361809045e-05)
+
                                                                             
Step... (66225 / 100000 | Loss: 0.9088959693908691, Learning Rate: 3.394472361809045e-05)
+
Train steps ... :  66%|██████▌   | 66225/100000 [20:01:38<5:29:00,  1.71it/s]
Train steps ... :  66%|██████▌   | 66226/100000 [20:01:39<5:29:54,  1.71it/s]
Train steps ... :  66%|██████▌   | 66227/100000 [20:01:39<5:29:20,  1.71it/s]
Train steps ... :  66%|██████▌   | 66228/100000 [20:01:40<5:29:28,  1.71it/s]
Train steps ... :  66%|██████▌   | 66229/100000 [20:01:41<5:29:14,  1.71it/s]
Train steps ... :  66%|██████▌   | 66230/100000 [20:01:41<5:29:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 66231/100000 [20:01:42<5:28:54,  1.71it/s]
Train steps ... :  66%|██████▌   | 66232/100000 [20:01:42<5:29:17,  1.71it/s]
Train steps ... :  66%|██████▌   | 66233/100000 [20:01:43<5:28:49,  1.71it/s]
Train steps ... :  66%|██████▌   | 66234/100000 [20:01:43<5:29:03,  1.71it/s]
Train steps ... :  66%|██████▌   | 66235/100000 [20:01:44<5:28:52,  1.71it/s]
Train steps ... :  66%|██████▌   | 66236/100000 [20:01:45<5:28:48,  1.71it/s]
Train steps ... :  66%|██████▌   | 66237/100000 [20:01:45<5:28:58,  1.71it/s]
Train steps ... :  66%|██████▌   | 66238/100000 [20:01:46<5:28:39,  1.71it/s]
Train steps ... :  66%|██████▌   | 66239/100000 [20:01:46<5:28:43,  1.71it/s]
Train steps ... :  66%|██████▌   | 66240/100000 [20:01:47<5:28:53,  1.71it/s]
Train steps ... :  66%|██████▌   | 66241/100000 [20:01:48<5:28:19,  1.71it/s]
Train steps ... :  66%|██████▌   | 66242/100000 [20:01:48<5:28:28,  1.71it/s]
Train steps ... :  66%|██████▌   | 66243/100000 [20:01:49<5:28:46,  1.71it/s]
Train steps ... :  66%|██████▌   | 66244/100000 [20:01:49<5:28:23,  1.71it/s]
Train steps ... :  66%|██████▌   | 66245/100000 [20:01:50<5:28:36,  1.71it/s]
Train steps ... :  66%|██████▌   | 66246/100000 [20:01:50<5:28:37,  1.71it/s]
Train steps ... :  66%|██████▌   | 66247/100000 [20:01:51<5:28:33,  1.71it/s]
Train steps ... :  66%|██████▌   | 66248/100000 [20:01:52<5:28:55,  1.71it/s]
Train steps ... :  66%|██████▌   | 66249/100000 [20:01:52<5:29:03,  1.71it/s]
Train steps ... :  66%|██████▋   | 66250/100000 [20:01:53<5:29:14,  1.71it/s]Step... (66250 / 100000 | Loss: 0.7524508237838745, Learning Rate: 3.391959798994975e-05)
+
                                                                             
Step... (66250 / 100000 | Loss: 0.704186201095581, Learning Rate: 3.391959798994975e-05)
+
Train steps ... :  66%|██████▋   | 66250/100000 [20:01:53<5:29:14,  1.71it/s]
Train steps ... :  66%|██████▋   | 66251/100000 [20:01:53<5:29:34,  1.71it/s]
Train steps ... :  66%|██████▋   | 66252/100000 [20:01:54<5:29:37,  1.71it/s]
Train steps ... :  66%|██████▋   | 66253/100000 [20:01:55<5:29:20,  1.71it/s]
Train steps ... :  66%|██████▋   | 66254/100000 [20:01:55<5:29:11,  1.71it/s]
Train steps ... :  66%|██████▋   | 66255/100000 [20:01:56<5:29:21,  1.71it/s]
Train steps ... :  66%|██████▋   | 66256/100000 [20:01:56<5:29:25,  1.71it/s]
Train steps ... :  66%|██████▋   | 66257/100000 [20:01:57<5:29:26,  1.71it/s]
Train steps ... :  66%|██████▋   | 66258/100000 [20:01:57<5:29:24,  1.71it/s]
Train steps ... :  66%|██████▋   | 66259/100000 [20:01:58<5:28:57,  1.71it/s]
Train steps ... :  66%|██████▋   | 66260/100000 [20:01:59<5:29:05,  1.71it/s]
Train steps ... :  66%|██████▋   | 66261/100000 [20:01:59<5:28:54,  1.71it/s]
Train steps ... :  66%|██████▋   | 66262/100000 [20:02:00<5:28:49,  1.71it/s]
Train steps ... :  66%|██████▋   | 66263/100000 [20:02:00<5:29:10,  1.71it/s]
Train steps ... :  66%|██████▋   | 66264/100000 [20:02:01<5:28:47,  1.71it/s]
Train steps ... :  66%|██████▋   | 66265/100000 [20:02:02<5:28:40,  1.71it/s]
Train steps ... :  66%|██████▋   | 66266/100000 [20:02:02<5:28:42,  1.71it/s]
Train steps ... :  66%|██████▋   | 66267/100000 [20:02:03<5:28:33,  1.71it/s]
Train steps ... :  66%|██████▋   | 66268/100000 [20:02:03<5:28:21,  1.71it/s]
Train steps ... :  66%|██████▋   | 66269/100000 [20:02:04<5:28:27,  1.71it/s]
Train steps ... :  66%|██████▋   | 66270/100000 [20:02:04<5:28:10,  1.71it/s]
Train steps ... :  66%|██████▋   | 66271/100000 [20:02:05<5:28:18,  1.71it/s]
Train steps ... :  66%|██████▋   | 66272/100000 [20:02:06<5:28:17,  1.71it/s]
Train steps ... :  66%|██████▋   | 66273/100000 [20:02:06<5:28:43,  1.71it/s]
Train steps ... :  66%|██████▋   | 66274/100000 [20:02:07<5:28:24,  1.71it/s]
Train steps ... :  66%|██████▋   | 66275/100000 [20:02:07<5:28:29,  1.71it/s]Step... (66275 / 100000 | Loss: 0.643632709980011, Learning Rate: 3.389447236180905e-05)
+
                                                                             
Step... (66275 / 100000 | Loss: 0.749467134475708, Learning Rate: 3.389447236180905e-05)
+
Train steps ... :  66%|██████▋   | 66275/100000 [20:02:08<5:28:29,  1.71it/s]
Train steps ... :  66%|██████▋   | 66276/100000 [20:02:08<5:28:57,  1.71it/s]
Train steps ... :  66%|██████▋   | 66277/100000 [20:02:09<5:29:18,  1.71it/s]
Train steps ... :  66%|██████▋   | 66278/100000 [20:02:09<5:29:03,  1.71it/s]
Train steps ... :  66%|██████▋   | 66279/100000 [20:02:10<5:28:58,  1.71it/s]
Train steps ... :  66%|██████▋   | 66280/100000 [20:02:10<5:28:29,  1.71it/s]
Train steps ... :  66%|██████▋   | 66281/100000 [20:02:11<5:28:19,  1.71it/s]
Train steps ... :  66%|██████▋   | 66282/100000 [20:02:11<5:28:56,  1.71it/s]
Train steps ... :  66%|██████▋   | 66283/100000 [20:02:12<5:28:08,  1.71it/s]
Train steps ... :  66%|██████▋   | 66284/100000 [20:02:13<5:28:45,  1.71it/s]
Train steps ... :  66%|���█████▋   | 66285/100000 [20:02:13<5:28:17,  1.71it/s]
Train steps ... :  66%|██████▋   | 66286/100000 [20:02:14<5:28:20,  1.71it/s]
Train steps ... :  66%|██████▋   | 66287/100000 [20:02:14<5:28:40,  1.71it/s]
Train steps ... :  66%|██████▋   | 66288/100000 [20:02:15<5:28:23,  1.71it/s]
Train steps ... :  66%|██████▋   | 66289/100000 [20:02:16<5:28:16,  1.71it/s]
Train steps ... :  66%|██████▋   | 66290/100000 [20:02:16<5:28:12,  1.71it/s]
Train steps ... :  66%|██████▋   | 66291/100000 [20:02:17<5:27:56,  1.71it/s]
Train steps ... :  66%|██████▋   | 66292/100000 [20:02:17<5:28:46,  1.71it/s]
Train steps ... :  66%|██████▋   | 66293/100000 [20:02:18<5:28:26,  1.71it/s]
Train steps ... :  66%|██████▋   | 66294/100000 [20:02:19<5:27:58,  1.71it/s]
Train steps ... :  66%|██████▋   | 66295/100000 [20:02:19<5:27:56,  1.71it/s]
Train steps ... :  66%|██████▋   | 66296/100000 [20:02:20<5:28:24,  1.71it/s]
Train steps ... :  66%|██████▋   | 66297/100000 [20:02:20<5:28:38,  1.71it/s]
Train steps ... :  66%|██████▋   | 66298/100000 [20:02:21<5:28:22,  1.71it/s]
Train steps ... :  66%|██████▋   | 66299/100000 [20:02:21<5:28:13,  1.71it/s]
Train steps ... :  66%|██████▋   | 66300/100000 [20:02:22<5:28:39,  1.71it/s]Step... (66300 / 100000 | Loss: 0.7668250203132629, Learning Rate: 3.3869346733668345e-05)
+
                                                                             
Step... (66300 / 100000 | Loss: 0.7548999786376953, Learning Rate: 3.3869346733668345e-05)
+
Train steps ... :  66%|██████▋   | 66300/100000 [20:02:22<5:28:39,  1.71it/s]
Train steps ... :  66%|██████▋   | 66301/100000 [20:02:23<5:28:30,  1.71it/s]
Train steps ... :  66%|██████▋   | 66302/100000 [20:02:23<5:28:38,  1.71it/s]
Train steps ... :  66%|██████▋   | 66303/100000 [20:02:24<5:28:20,  1.71it/s]
Train steps ... :  66%|██████▋   | 66304/100000 [20:02:24<5:28:00,  1.71it/s]
Train steps ... :  66%|██████▋   | 66305/100000 [20:02:25<5:28:00,  1.71it/s]
Train steps ... :  66%|██████▋   | 66306/100000 [20:02:26<5:27:59,  1.71it/s]
Train steps ... :  66%|██████▋   | 66307/100000 [20:02:26<5:28:29,  1.71it/s]
Train steps ... :  66%|██████▋   | 66308/100000 [20:02:27<5:28:23,  1.71it/s]
Train steps ... :  66%|██████▋   | 66309/100000 [20:02:27<5:28:17,  1.71it/s]
Train steps ... :  66%|██████▋   | 66310/100000 [20:02:28<5:28:08,  1.71it/s]
Train steps ... :  66%|██████▋   | 66311/100000 [20:02:28<5:28:31,  1.71it/s]
Train steps ... :  66%|██████▋   | 66312/100000 [20:02:29<5:28:32,  1.71it/s]
Train steps ... :  66%|██████▋   | 66313/100000 [20:02:30<5:28:23,  1.71it/s]
Train steps ... :  66%|██████▋   | 66314/100000 [20:02:30<5:28:28,  1.71it/s]
Train steps ... :  66%|██████▋   | 66315/100000 [20:02:31<5:28:27,  1.71it/s]
Train steps ... :  66%|██████▋   | 66316/100000 [20:02:31<5:28:30,  1.71it/s]
Train steps ... :  66%|██████▋   | 66317/100000 [20:02:32<5:28:15,  1.71it/s]
Train steps ... :  66%|██████▋   | 66318/100000 [20:02:33<5:28:03,  1.71it/s]
Train steps ... :  66%|██████▋   | 66319/100000 [20:02:33<5:27:55,  1.71it/s]
Train steps ... :  66%|██████▋   | 66320/100000 [20:02:34<5:27:39,  1.71it/s]
Train steps ... :  66%|██████▋   | 66321/100000 [20:02:34<5:27:57,  1.71it/s]
Train steps ... :  66%|██████▋   | 66322/100000 [20:02:35<5:28:07,  1.71it/s]
Train steps ... :  66%|██████▋   | 66323/100000 [20:02:35<5:28:03,  1.71it/s]
Train steps ... :  66%|██████▋   | 66324/100000 [20:02:36<5:28:08,  1.71it/s]
Train steps ... :  66%|██████▋   | 66325/100000 [20:02:37<5:28:16,  1.71it/s]Step... (66325 / 100000 | Loss: 0.9997270107269287, Learning Rate: 3.384422110552764e-05)
+
                                                                             
Step... (66325 / 100000 | Loss: 0.6518117189407349, Learning Rate: 3.384422110552764e-05)
+
Train steps ... :  66%|██████▋   | 66325/100000 [20:02:37<5:28:16,  1.71it/s]
Train steps ... :  66%|██████▋   | 66326/100000 [20:02:37<5:28:28,  1.71it/s]
Train steps ... :  66%|██████▋   | 66327/100000 [20:02:38<5:28:05,  1.71it/s]
Train steps ... :  66%|██████▋   | 66328/100000 [20:02:38<5:28:37,  1.71it/s]
Train steps ... :  66%|██████▋   | 66329/100000 [20:02:39<5:28:42,  1.71it/s]
Train steps ... :  66%|██████▋   | 66330/100000 [20:02:40<5:28:39,  1.71it/s]
Train steps ... :  66%|██████▋   | 66331/100000 [20:02:40<5:28:08,  1.71it/s]
Train steps ... :  66%|██████▋   | 66332/100000 [20:02:41<5:28:07,  1.71it/s]
Train steps ... :  66%|██████▋   | 66333/100000 [20:02:41<5:28:12,  1.71it/s]
Train steps ... :  66%|██████▋   | 66334/100000 [20:02:42<5:28:25,  1.71it/s]
Train steps ... :  66%|██████▋   | 66335/100000 [20:02:42<5:27:54,  1.71it/s]
Train steps ... :  66%|██████▋   | 66336/100000 [20:02:43<5:27:53,  1.71it/s]
Train steps ... :  66%|██████▋   | 66337/100000 [20:02:44<5:28:05,  1.71it/s]
Train steps ... :  66%|██████▋   | 66338/100000 [20:02:44<5:28:04,  1.71it/s]
Train steps ... :  66%|██████▋   | 66339/100000 [20:02:45<5:27:59,  1.71it/s]
Train steps ... :  66%|██████▋   | 66340/100000 [20:02:45<5:28:12,  1.71it/s]
Train steps ... :  66%|██████▋   | 66341/100000 [20:02:46<5:28:24,  1.71it/s]
Train steps ... :  66%|██████▋   | 66342/100000 [20:02:47<5:28:14,  1.71it/s]
Train steps ... :  66%|██████▋   | 66343/100000 [20:02:47<5:27:59,  1.71it/s]
Train steps ... :  66%|██████▋   | 66344/100000 [20:02:48<5:28:32,  1.71it/s]
Train steps ... :  66%|██████▋   | 66345/100000 [20:02:48<5:29:06,  1.70it/s]
Train steps ... :  66%|██████▋   | 66346/100000 [20:02:49<5:28:30,  1.71it/s]
Train steps ... :  66%|██████▋   | 66347/100000 [20:02:50<5:28:03,  1.71it/s]
Train steps ... :  66%|██████▋   | 66348/100000 [20:02:50<5:27:54,  1.71it/s]
Train steps ... :  66%|██████▋   | 66349/100000 [20:02:51<5:27:51,  1.71it/s]
Train steps ... :  66%|██████▋   | 66350/100000 [20:02:51<5:28:00,  1.71it/s]Step... (66350 / 100000 | Loss: 0.7542133331298828, Learning Rate: 3.381909547738694e-05)
+
                                                                             
Step... (66350 / 100000 | Loss: 0.6925934553146362, Learning Rate: 3.381909547738694e-05)
+
Train steps ... :  66%|██████▋   | 66350/100000 [20:02:52<5:28:00,  1.71it/s]
Train steps ... :  66%|██████▋   | 66351/100000 [20:02:52<5:27:53,  1.71it/s]
Train steps ... :  66%|██████▋   | 66352/100000 [20:02:52<5:27:33,  1.71it/s]
Train steps ... :  66%|██████▋   | 66353/100000 [20:02:53<5:27:30,  1.71it/s]
Train steps ... :  66%|██████▋   | 66354/100000 [20:02:54<5:28:04,  1.71it/s]
Train steps ... :  66%|██████▋   | 66355/100000 [20:02:54<5:27:25,  1.71it/s]
Train steps ... :  66%|██████▋   | 66356/100000 [20:02:55<5:27:21,  1.71it/s]
Train steps ... :  66%|██████▋   | 66357/100000 [20:02:55<5:27:45,  1.71it/s]
Train steps ... :  66%|██████▋   | 66358/100000 [20:02:56<5:27:58,  1.71it/s]
Train steps ... :  66%|██████▋   | 66359/100000 [20:02:57<5:28:05,  1.71it/s]
Train steps ... :  66%|██████▋   | 66360/100000 [20:02:57<5:27:50,  1.71it/s]
Train steps ... :  66%|██████▋   | 66361/100000 [20:02:58<5:28:06,  1.71it/s]
Train steps ... :  66%|██████▋   | 66362/100000 [20:02:58<5:28:01,  1.71it/s]
Train steps ... :  66%|██████▋   | 66363/100000 [20:02:59<5:28:12,  1.71it/s]
Train steps ... :  66%|██████▋   | 66364/100000 [20:02:59<5:28:03,  1.71it/s]
Train steps ... :  66%|██████▋   | 66365/100000 [20:03:00<5:27:40,  1.71it/s]
Train steps ... :  66%|██████▋   | 66366/100000 [20:03:01<5:27:55,  1.71it/s]
Train steps ... :  66%|██████▋   | 66367/100000 [20:03:01<5:27:47,  1.71it/s]
Train steps ... :  66%|██████▋   | 66368/100000 [20:03:02<5:27:59,  1.71it/s]
Train steps ... :  66%|██████▋   | 66369/100000 [20:03:02<5:27:44,  1.71it/s]
Train steps ... :  66%|██████▋   | 66370/100000 [20:03:03<5:27:52,  1.71it/s]
Train steps ... :  66%|██████▋   | 66371/100000 [20:03:04<5:27:39,  1.71it/s]
Train steps ... :  66%|██████▋   | 66372/100000 [20:03:04<5:28:15,  1.71it/s]
Train steps ... :  66%|██████▋   | 66373/100000 [20:03:05<5:27:54,  1.71it/s]
Train steps ... :  66%|██████▋   | 66374/100000 [20:03:05<5:27:57,  1.71it/s]
Train steps ... :  66%|██████▋   | 66375/100000 [20:03:06<5:27:52,  1.71it/s]Step... (66375 / 100000 | Loss: 0.7011245489120483, Learning Rate: 3.3793969849246235e-05)
+
                                                                             
Step... (66375 / 100000 | Loss: 0.763519287109375, Learning Rate: 3.3793969849246235e-05)
+
Train steps ... :  66%|██████▋   | 66375/100000 [20:03:06<5:27:52,  1.71it/s]
Train steps ... :  66%|██████▋   | 66376/100000 [20:03:06<5:27:43,  1.71it/s]
Train steps ... :  66%|██████▋   | 66377/100000 [20:03:07<5:28:11,  1.71it/s]
Train steps ... :  66%|██████▋   | 66378/100000 [20:03:08<5:27:44,  1.71it/s]
Train steps ... :  66%|██████▋   | 66379/100000 [20:03:08<5:27:43,  1.71it/s]
Train steps ... :  66%|██████▋   | 66380/100000 [20:03:09<5:27:30,  1.71it/s]
Train steps ... :  66%|██████▋   | 66381/100000 [20:03:09<5:27:29,  1.71it/s]
Train steps ... :  66%|██████▋   | 66382/100000 [20:03:10<5:27:59,  1.71it/s]
Train steps ... :  66%|██████▋   | 66383/100000 [20:03:11<5:27:34,  1.71it/s]
Train steps ... :  66%|██████▋   | 66384/100000 [20:03:11<5:27:32,  1.71it/s]
Train steps ... :  66%|██████▋   | 66385/100000 [20:03:12<5:27:51,  1.71it/s]
Train steps ... :  66%|██████▋   | 66386/100000 [20:03:12<5:27:54,  1.71it/s]
Train steps ... :  66%|██████▋   | 66387/100000 [20:03:13<5:27:23,  1.71it/s]
Train steps ... :  66%|██████▋   | 66388/100000 [20:03:13<5:27:24,  1.71it/s]
Train steps ... :  66%|██████▋   | 66389/100000 [20:03:14<5:27:24,  1.71it/s]
Train steps ... :  66%|██████▋   | 66390/100000 [20:03:15<5:27:14,  1.71it/s]
Train steps ... :  66%|██████▋   | 66391/100000 [20:03:15<5:27:12,  1.71it/s]
Train steps ... :  66%|██████▋   | 66392/100000 [20:03:16<5:27:00,  1.71it/s]
Train steps ... :  66%|██████▋   | 66393/100000 [20:03:16<5:26:56,  1.71it/s]
Train steps ... :  66%|██████▋   | 66394/100000 [20:03:17<5:27:16,  1.71it/s]
Train steps ... :  66%|██████▋   | 66395/100000 [20:03:18<5:27:32,  1.71it/s]
Train steps ... :  66%|██████▋   | 66396/100000 [20:03:18<5:27:25,  1.71it/s]
Train steps ... :  66%|██████▋   | 66397/100000 [20:03:19<5:27:14,  1.71it/s]
Train steps ... :  66%|██████▋   | 66398/100000 [20:03:19<5:27:17,  1.71it/s]
Train steps ... :  66%|██████▋   | 66399/100000 [20:03:20<5:27:48,  1.71it/s]
Train steps ... :  66%|██████▋   | 66400/100000 [20:03:20<5:27:46,  1.71it/s]Step... (66400 / 100000 | Loss: 0.792429506778717, Learning Rate: 3.3768844221105525e-05)
+
                                                                             
Step... (66400 / 100000 | Loss: 0.8425886631011963, Learning Rate: 3.3768844221105525e-05)
+
Train steps ... :  66%|██████▋   | 66400/100000 [20:03:21<5:27:46,  1.71it/s]
Train steps ... :  66%|██████▋   | 66401/100000 [20:03:21<5:28:13,  1.71it/s]
Train steps ... :  66%|██████▋   | 66402/100000 [20:03:22<5:28:00,  1.71it/s]
Train steps ... :  66%|██████▋   | 66403/100000 [20:03:22<5:28:02,  1.71it/s]
Train steps ... :  66%|██████▋   | 66404/100000 [20:03:23<5:27:43,  1.71it/s]
Train steps ... :  66%|██████▋   | 66405/100000 [20:03:23<5:27:24,  1.71it/s]
Train steps ... :  66%|██████▋   | 66406/100000 [20:03:24<5:27:14,  1.71it/s]
Train steps ... :  66%|██████▋   | 66407/100000 [20:03:25<5:27:31,  1.71it/s]
Train steps ... :  66%|██████▋   | 66408/100000 [20:03:25<5:27:30,  1.71it/s]
Train steps ... :  66%|██████▋   | 66409/100000 [20:03:26<5:27:07,  1.71it/s]
Train steps ... :  66%|██████▋   | 66410/100000 [20:03:26<5:27:40,  1.71it/s]
Train steps ... :  66%|██████▋   | 66411/100000 [20:03:27<5:27:12,  1.71it/s]
Train steps ... :  66%|██████▋   | 66412/100000 [20:03:28<5:27:25,  1.71it/s]
Train steps ... :  66%|██████▋   | 66413/100000 [20:03:28<5:27:55,  1.71it/s]
Train steps ... :  66%|██████▋   | 66414/100000 [20:03:29<5:27:49,  1.71it/s]
Train steps ... :  66%|██████▋   | 66415/100000 [20:03:29<5:28:17,  1.71it/s]
Train steps ... :  66%|██████▋   | 66416/100000 [20:03:30<5:27:27,  1.71it/s]
Train steps ... :  66%|██████▋   | 66417/100000 [20:03:30<5:27:32,  1.71it/s]
Train steps ... :  66%|██████▋   | 66418/100000 [20:03:31<5:27:36,  1.71it/s]
Train steps ... :  66%|██████▋   | 66419/100000 [20:03:32<5:27:15,  1.71it/s]
Train steps ... :  66%|██████▋   | 66420/100000 [20:03:32<5:27:08,  1.71it/s]
Train steps ... :  66%|██████▋   | 66421/100000 [20:03:33<5:27:43,  1.71it/s]
Train steps ... :  66%|██████▋   | 66422/100000 [20:03:33<5:27:31,  1.71it/s]
Train steps ... :  66%|██████▋   | 66423/100000 [20:03:34<5:27:28,  1.71it/s]
Train steps ... :  66%|██████▋   | 66424/100000 [20:03:35<5:27:20,  1.71it/s]
Train steps ... :  66%|██████▋   | 66425/100000 [20:03:35<5:27:31,  1.71it/s]Step... (66425 / 100000 | Loss: 0.6497294902801514, Learning Rate: 3.374371859296482e-05)
+
                                                                             
Step... (66425 / 100000 | Loss: 0.7872121930122375, Learning Rate: 3.374371859296482e-05)
+
Train steps ... :  66%|██████▋   | 66425/100000 [20:03:35<5:27:31,  1.71it/s]
Train steps ... :  66%|██████▋   | 66426/100000 [20:03:36<5:27:42,  1.71it/s]
Train steps ... :  66%|██████▋   | 66427/100000 [20:03:36<5:27:17,  1.71it/s]
Train steps ... :  66%|██████▋   | 66428/100000 [20:03:37<5:27:41,  1.71it/s]
Train steps ... :  66%|██████▋   | 66429/100000 [20:03:37<5:27:35,  1.71it/s]
Train steps ... :  66%|██████▋   | 66430/100000 [20:03:38<5:27:59,  1.71it/s]
Train steps ... :  66%|██████▋   | 66431/100000 [20:03:39<5:27:22,  1.71it/s]
Train steps ... :  66%|██████▋   | 66432/100000 [20:03:39<5:27:00,  1.71it/s]
Train steps ... :  66%|██████▋   | 66433/100000 [20:03:40<5:27:02,  1.71it/s]
Train steps ... :  66%|██████▋   | 66434/100000 [20:03:40<5:26:41,  1.71it/s]
Train steps ... :  66%|██████▋   | 66435/100000 [20:03:41<5:26:56,  1.71it/s]
Train steps ... :  66%|██████▋   | 66436/100000 [20:03:42<5:27:01,  1.71it/s]
Train steps ... :  66%|██████▋   | 66437/100000 [20:03:42<5:26:50,  1.71it/s]
Train steps ... :  66%|██████▋   | 66438/100000 [20:03:43<5:26:45,  1.71it/s]
Train steps ... :  66%|██████▋   | 66439/100000 [20:03:43<5:26:42,  1.71it/s]
Train steps ... :  66%|██████▋   | 66440/100000 [20:03:44<5:27:08,  1.71it/s]
Train steps ... :  66%|██████▋   | 66441/100000 [20:03:44<5:26:43,  1.71it/s]
Train steps ... :  66%|██████▋   | 66442/100000 [20:03:45<5:26:39,  1.71it/s]
Train steps ... :  66%|██████▋   | 66443/100000 [20:03:46<5:26:41,  1.71it/s]
Train steps ... :  66%|██████▋   | 66444/100000 [20:03:46<5:26:59,  1.71it/s]
Train steps ... :  66%|██████▋   | 66445/100000 [20:03:47<5:27:03,  1.71it/s]
Train steps ... :  66%|██████▋   | 66446/100000 [20:03:47<5:26:53,  1.71it/s]
Train steps ... :  66%|██████▋   | 66447/100000 [20:03:48<5:26:45,  1.71it/s]
Train steps ... :  66%|██████▋   | 66448/100000 [20:03:49<5:27:00,  1.71it/s]
Train steps ... :  66%|██████▋   | 66449/100000 [20:03:49<5:27:00,  1.71it/s]
Train steps ... :  66%|██████▋   | 66450/100000 [20:03:50<5:27:57,  1.70it/s]Step... (66450 / 100000 | Loss: 0.7809014320373535, Learning Rate: 3.371859296482412e-05)
+
                                                                             
Step... (66450 / 100000 | Loss: 0.671959400177002, Learning Rate: 3.371859296482412e-05)
+
Train steps ... :  66%|██████▋   | 66450/100000 [20:03:50<5:27:57,  1.70it/s]
Train steps ... :  66%|██████▋   | 66451/100000 [20:03:50<5:27:39,  1.71it/s]
Train steps ... :  66%|██████▋   | 66452/100000 [20:03:51<5:27:37,  1.71it/s]
Train steps ... :  66%|██████▋   | 66453/100000 [20:03:52<5:27:15,  1.71it/s]
Train steps ... :  66%|██████▋   | 66454/100000 [20:03:52<5:27:00,  1.71it/s]
Train steps ... :  66%|██████▋   | 66455/100000 [20:03:53<5:26:58,  1.71it/s]
Train steps ... :  66%|██████▋   | 66456/100000 [20:03:53<5:27:25,  1.71it/s]
Train steps ... :  66%|██████▋   | 66457/100000 [20:03:54<5:27:18,  1.71it/s]
Train steps ... :  66%|██████▋   | 66458/100000 [20:03:54<5:27:18,  1.71it/s]
Train steps ... :  66%|██████▋   | 66459/100000 [20:03:55<5:27:15,  1.71it/s]
Train steps ... :  66%|██████▋   | 66460/100000 [20:03:56<5:26:56,  1.71it/s]
Train steps ... :  66%|██████▋   | 66461/100000 [20:03:56<5:26:45,  1.71it/s]
Train steps ... :  66%|██████▋   | 66462/100000 [20:03:57<5:26:33,  1.71it/s]
Train steps ... :  66%|██████▋   | 66463/100000 [20:03:57<5:26:44,  1.71it/s]
Train steps ... :  66%|██████▋   | 66464/100000 [20:03:58<5:26:40,  1.71it/s]
Train steps ... :  66%|██████▋   | 66465/100000 [20:03:59<5:26:39,  1.71it/s]
Train steps ... :  66%|██████▋   | 66466/100000 [20:03:59<5:26:23,  1.71it/s]
Train steps ... :  66%|██████▋   | 66467/100000 [20:04:00<5:27:01,  1.71it/s]
Train steps ... :  66%|██████▋   | 66468/100000 [20:04:00<5:26:54,  1.71it/s]
Train steps ... :  66%|██████▋   | 66469/100000 [20:04:01<5:27:08,  1.71it/s]
Train steps ... :  66%|██████▋   | 66470/100000 [20:04:01<5:26:41,  1.71it/s]
Train steps ... :  66%|██████▋   | 66471/100000 [20:04:02<5:27:06,  1.71it/s]
Train steps ... :  66%|██████▋   | 66472/100000 [20:04:03<5:26:46,  1.71it/s]
Train steps ... :  66%|██████▋   | 66473/100000 [20:04:03<5:26:40,  1.71it/s]
Train steps ... :  66%|██████▋   | 66474/100000 [20:04:04<5:26:32,  1.71it/s]
Train steps ... :  66%|██████▋   | 66475/100000 [20:04:04<5:26:53,  1.71it/s]Step... (66475 / 100000 | Loss: 0.6457372903823853, Learning Rate: 3.369346733668342e-05)
+
                                                                             
Step... (66475 / 100000 | Loss: 0.7488201260566711, Learning Rate: 3.369346733668342e-05)
+
Train steps ... :  66%|██████▋   | 66475/100000 [20:04:05<5:26:53,  1.71it/s]
Train steps ... :  66%|██████▋   | 66476/100000 [20:04:05<5:26:30,  1.71it/s]
Train steps ... :  66%|██████▋   | 66477/100000 [20:04:06<5:26:41,  1.71it/s]
Train steps ... :  66%|██████▋   | 66478/100000 [20:04:06<5:26:30,  1.71it/s]
Train steps ... :  66%|██████▋   | 66479/100000 [20:04:07<5:27:33,  1.71it/s]
Train steps ... :  66%|██████▋   | 66480/100000 [20:04:07<5:27:26,  1.71it/s]
Train steps ... :  66%|██████▋   | 66481/100000 [20:04:08<5:27:00,  1.71it/s]
Train steps ... :  66%|██████▋   | 66482/100000 [20:04:08<5:26:42,  1.71it/s]
Train steps ... :  66%|██████▋   | 66483/100000 [20:04:09<5:26:36,  1.71it/s]
Train steps ... :  66%|██████▋   | 66484/100000 [20:04:10<5:26:26,  1.71it/s]
Train steps ... :  66%|██████▋   | 66485/100000 [20:04:10<5:26:23,  1.71it/s]
Train steps ... :  66%|██████▋   | 66486/100000 [20:04:11<5:26:19,  1.71it/s]
Train steps ... :  66%|██████▋   | 66487/100000 [20:04:11<5:26:41,  1.71it/s]
Train steps ... :  66%|██████▋   | 66488/100000 [20:04:12<5:26:21,  1.71it/s]
Train steps ... :  66%|██████▋   | 66489/100000 [20:04:13<5:26:25,  1.71it/s]
Train steps ... :  66%|██████▋   | 66490/100000 [20:04:13<5:26:42,  1.71it/s]
Train steps ... :  66%|██████▋   | 66491/100000 [20:04:14<5:26:52,  1.71it/s]
Train steps ... :  66%|██████▋   | 66492/100000 [20:04:14<5:26:39,  1.71it/s]
Train steps ... :  66%|██████▋   | 66493/100000 [20:04:15<5:26:21,  1.71it/s]
Train steps ... :  66%|██████▋   | 66494/100000 [20:04:15<5:26:27,  1.71it/s]
Train steps ... :  66%|██████▋   | 66495/100000 [20:04:16<5:26:21,  1.71it/s]
Train steps ... :  66%|██████▋   | 66496/100000 [20:04:17<5:26:26,  1.71it/s]
Train steps ... :  66%|██████▋   | 66497/100000 [20:04:17<5:26:40,  1.71it/s]
Train steps ... :  66%|██████▋   | 66498/100000 [20:04:18<5:26:38,  1.71it/s]
Train steps ... :  66%|██████▋   | 66499/100000 [20:04:18<5:26:24,  1.71it/s]
Train steps ... :  66%|██████▋   | 66500/100000 [20:04:19<5:26:26,  1.71it/s]Step... (66500 / 100000 | Loss: 0.5983182787895203, Learning Rate: 3.366834170854272e-05)
+
                                                                             
Step... (66500 / 100000 | Loss: 0.7729024887084961, Learning Rate: 3.366834170854272e-05)
+
Train steps ... :  66%|██████▋   | 66500/100000 [20:04:19<5:26:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66501/100000 [20:04:20<5:26:39,  1.71it/s]
Train steps ... :  67%|██████▋   | 66502/100000 [20:04:20<5:26:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66503/100000 [20:04:21<5:26:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 66504/100000 [20:04:21<5:26:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66505/100000 [20:04:22<5:27:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 66506/100000 [20:04:23<5:27:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 66507/100000 [20:04:23<5:26:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66508/100000 [20:04:24<5:26:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 66509/100000 [20:04:24<5:26:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 66510/100000 [20:04:25<5:26:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 66511/100000 [20:04:25<5:26:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 66512/100000 [20:04:26<5:26:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 66513/100000 [20:04:27<5:26:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 66514/100000 [20:04:27<5:26:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 66515/100000 [20:04:28<5:26:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 66516/100000 [20:04:28<5:26:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66517/100000 [20:04:29<5:26:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 66518/100000 [20:04:30<5:26:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 66519/100000 [20:04:30<5:26:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 66520/100000 [20:04:31<5:26:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 66521/100000 [20:04:31<5:25:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 66522/100000 [20:04:32<5:25:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66523/100000 [20:04:32<5:26:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 66524/100000 [20:04:33<5:26:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 66525/100000 [20:04:34<5:26:01,  1.71it/s]Step... (66525 / 100000 | Loss: 0.9635471105575562, Learning Rate: 3.3643216080402014e-05)
+
                                                                             
Step... (66525 / 100000 | Loss: 0.6535355448722839, Learning Rate: 3.3643216080402014e-05)
+
Train steps ... :  67%|██████▋   | 66525/100000 [20:04:34<5:26:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 66526/100000 [20:04:34<5:26:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66527/100000 [20:04:35<5:26:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 66528/100000 [20:04:35<5:25:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66529/100000 [20:04:36<5:26:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 66530/100000 [20:04:37<5:26:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 66531/100000 [20:04:37<5:26:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66532/100000 [20:04:38<5:26:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 66533/100000 [20:04:38<5:26:11,  1.71it/s]
Train steps ... :  67%|██████▋   | 66534/100000 [20:04:39<5:26:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 66535/100000 [20:04:39<5:26:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66536/100000 [20:04:40<5:26:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66537/100000 [20:04:41<5:26:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66538/100000 [20:04:41<5:26:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66539/100000 [20:04:42<5:26:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 66540/100000 [20:04:42<5:26:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 66541/100000 [20:04:43<5:26:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 66542/100000 [20:04:44<5:25:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 66543/100000 [20:04:44<5:26:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 66544/100000 [20:04:45<5:26:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66545/100000 [20:04:45<5:26:11,  1.71it/s]
Train steps ... :  67%|██████▋   | 66546/100000 [20:04:46<5:26:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66547/100000 [20:04:46<5:26:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66548/100000 [20:04:47<5:25:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66549/100000 [20:04:48<5:25:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 66550/100000 [20:04:48<5:25:50,  1.71it/s]Step... (66550 / 100000 | Loss: 0.8503491878509521, Learning Rate: 3.361809045226131e-05)
+
                                                                             
Step... (66550 / 100000 | Loss: 0.710567831993103, Learning Rate: 3.361809045226131e-05)
+
Train steps ... :  67%|██████▋   | 66550/100000 [20:04:49<5:25:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 66551/100000 [20:04:49<5:25:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66552/100000 [20:04:49<5:26:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 66553/100000 [20:04:50<5:26:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 66554/100000 [20:04:51<5:25:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66555/100000 [20:04:51<5:25:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66556/100000 [20:04:52<5:26:18,  1.71it/s]
Train steps ... :  67%|██████▋   | 66557/100000 [20:04:52<5:26:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66558/100000 [20:04:53<5:26:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66559/100000 [20:04:54<5:26:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 66560/100000 [20:04:54<5:26:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66561/100000 [20:04:55<5:26:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66562/100000 [20:04:55<5:26:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 66563/100000 [20:04:56<5:25:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 66564/100000 [20:04:56<5:26:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66565/100000 [20:04:57<5:26:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 66566/100000 [20:04:58<5:26:18,  1.71it/s]
Train steps ... :  67%|██████▋   | 66567/100000 [20:04:58<5:26:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66568/100000 [20:04:59<5:26:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 66569/100000 [20:04:59<5:26:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66570/100000 [20:05:00<5:26:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 66571/100000 [20:05:01<5:26:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66572/100000 [20:05:01<5:25:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66573/100000 [20:05:02<5:25:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66574/100000 [20:05:02<5:25:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66575/100000 [20:05:03<5:25:33,  1.71it/s]Step... (66575 / 100000 | Loss: 0.732083261013031, Learning Rate: 3.35929648241206e-05)
+
                                                                             
Step... (66575 / 100000 | Loss: 0.5884971618652344, Learning Rate: 3.35929648241206e-05)
+
Train steps ... :  67%|██████▋   | 66575/100000 [20:05:03<5:25:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 66576/100000 [20:05:03<5:25:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 66577/100000 [20:05:04<5:25:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66578/100000 [20:05:05<5:25:39,  1.71it/s]
Train steps ... :  67%|██████▋   | 66579/100000 [20:05:05<5:26:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66580/100000 [20:05:06<5:26:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 66581/100000 [20:05:06<5:25:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 66582/100000 [20:05:07<5:25:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 66583/100000 [20:05:08<5:25:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 66584/100000 [20:05:08<5:25:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 66585/100000 [20:05:09<5:26:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66586/100000 [20:05:09<5:25:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 66587/100000 [20:05:10<5:26:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66588/100000 [20:05:10<5:25:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66589/100000 [20:05:11<5:25:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66590/100000 [20:05:12<5:26:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66591/100000 [20:05:12<5:26:18,  1.71it/s]
Train steps ... :  67%|██████▋   | 66592/100000 [20:05:13<5:25:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66593/100000 [20:05:13<5:26:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 66594/100000 [20:05:14<5:25:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 66595/100000 [20:05:15<5:25:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66596/100000 [20:05:15<5:25:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 66597/100000 [20:05:16<5:25:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 66598/100000 [20:05:16<5:26:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 66599/100000 [20:05:17<5:26:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 66600/100000 [20:05:18<5:26:52,  1.70it/s]Step... (66600 / 100000 | Loss: 1.0451769828796387, Learning Rate: 3.35678391959799e-05)
+
                                                                             
Step... (66600 / 100000 | Loss: 0.6562105417251587, Learning Rate: 3.35678391959799e-05)
+
Train steps ... :  67%|██████▋   | 66600/100000 [20:05:18<5:26:52,  1.70it/s]
Train steps ... :  67%|██████▋   | 66601/100000 [20:05:18<5:26:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66602/100000 [20:05:19<5:25:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 66603/100000 [20:05:19<5:25:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66604/100000 [20:05:20<5:25:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 66605/100000 [20:05:20<5:25:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66606/100000 [20:05:21<5:25:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66607/100000 [20:05:22<5:25:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66608/100000 [20:05:22<5:25:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 66609/100000 [20:05:23<5:25:11,  1.71it/s]
Train steps ... :  67%|██████▋   | 66610/100000 [20:05:23<5:25:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66611/100000 [20:05:24<5:24:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 66612/100000 [20:05:25<5:25:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66613/100000 [20:05:25<5:25:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 66614/100000 [20:05:26<5:24:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 66615/100000 [20:05:26<5:24:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66616/100000 [20:05:27<5:25:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 66617/100000 [20:05:27<5:24:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 66618/100000 [20:05:28<5:25:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 66619/100000 [20:05:29<5:25:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 66620/100000 [20:05:29<5:25:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66621/100000 [20:05:30<5:25:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 66622/100000 [20:05:30<5:25:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66623/100000 [20:05:31<5:25:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66624/100000 [20:05:32<5:25:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 66625/100000 [20:05:32<5:24:58,  1.71it/s]Step... (66625 / 100000 | Loss: 0.5524997115135193, Learning Rate: 3.3542713567839194e-05)
+
                                                                             
Step... (66625 / 100000 | Loss: 0.7828487157821655, Learning Rate: 3.3542713567839194e-05)
+
Train steps ... :  67%|██████▋   | 66625/100000 [20:05:32<5:24:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 66626/100000 [20:05:33<5:25:11,  1.71it/s]
Train steps ... :  67%|██████▋   | 66627/100000 [20:05:33<5:25:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66628/100000 [20:05:34<5:25:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 66629/100000 [20:05:34<5:24:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 66630/100000 [20:05:35<5:24:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 66631/100000 [20:05:36<5:24:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66632/100000 [20:05:36<5:24:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66633/100000 [20:05:37<5:24:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66634/100000 [20:05:37<5:24:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 66635/100000 [20:05:38<5:24:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 66636/100000 [20:05:39<5:24:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66637/100000 [20:05:39<5:24:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 66638/100000 [20:05:40<5:24:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 66639/100000 [20:05:40<5:24:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 66640/100000 [20:05:41<5:24:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66641/100000 [20:05:41<5:24:08,  1.72it/s]
Train steps ... :  67%|██████▋   | 66642/100000 [20:05:42<5:24:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66643/100000 [20:05:43<5:24:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66644/100000 [20:05:43<5:24:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 66645/100000 [20:05:44<5:24:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66646/100000 [20:05:44<5:24:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 66647/100000 [20:05:45<5:24:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 66648/100000 [20:05:46<5:24:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 66649/100000 [20:05:46<5:24:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 66650/100000 [20:05:47<5:24:12,  1.71it/s]Step... (66650 / 100000 | Loss: 0.5622382164001465, Learning Rate: 3.351758793969849e-05)
+
                                                                             
Step... (66650 / 100000 | Loss: 1.0745296478271484, Learning Rate: 3.351758793969849e-05)
+
Train steps ... :  67%|██████▋   | 66650/100000 [20:05:47<5:24:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66651/100000 [20:05:47<5:24:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 66652/100000 [20:05:48<5:24:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 66653/100000 [20:05:48<5:24:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 66654/100000 [20:05:49<5:24:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 66655/100000 [20:05:50<5:24:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 66656/100000 [20:05:50<5:24:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66657/100000 [20:05:51<5:24:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 66658/100000 [20:05:51<5:24:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 66659/100000 [20:05:52<5:24:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 66660/100000 [20:05:53<5:24:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66661/100000 [20:05:53<5:24:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 66662/100000 [20:05:54<5:24:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 66663/100000 [20:05:54<5:25:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66664/100000 [20:05:55<5:24:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 66665/100000 [20:05:55<5:25:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 66666/100000 [20:05:56<5:24:34,  1.71it/s]
Train steps ... :  67%|██████▋   | 66667/100000 [20:05:57<5:24:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 66668/100000 [20:05:57<5:24:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 66669/100000 [20:05:58<5:25:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 66670/100000 [20:05:58<5:24:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 66671/100000 [20:05:59<5:24:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66672/100000 [20:06:00<5:24:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 66673/100000 [20:06:00<5:24:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 66674/100000 [20:06:01<5:24:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 66675/100000 [20:06:01<5:24:23,  1.71it/s]Step... (66675 / 100000 | Loss: 0.6480693817138672, Learning Rate: 3.3492462311557794e-05)
+
                                                                             
Step... (66675 / 100000 | Loss: 0.9333912134170532, Learning Rate: 3.3492462311557794e-05)
+
Train steps ... :  67%|██████▋   | 66675/100000 [20:06:02<5:24:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 66676/100000 [20:06:02<5:24:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66677/100000 [20:06:02<5:24:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66678/100000 [20:06:03<5:24:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 66679/100000 [20:06:04<5:24:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66680/100000 [20:06:04<5:24:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 66681/100000 [20:06:05<5:24:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 66682/100000 [20:06:05<5:24:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66683/100000 [20:06:06<5:24:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 66684/100000 [20:06:07<5:24:18,  1.71it/s]
Train steps ... :  67%|██████▋   | 66685/100000 [20:06:07<5:24:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 66686/100000 [20:06:08<5:24:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66687/100000 [20:06:08<5:24:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 66688/100000 [20:06:09<5:24:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 66689/100000 [20:06:09<5:23:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66690/100000 [20:06:10<5:24:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66691/100000 [20:06:11<5:24:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66692/100000 [20:06:11<5:24:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66693/100000 [20:06:12<5:24:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 66694/100000 [20:06:12<5:24:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 66695/100000 [20:06:13<5:24:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 66696/100000 [20:06:14<5:23:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66697/100000 [20:06:14<5:24:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66698/100000 [20:06:15<5:24:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66699/100000 [20:06:15<5:24:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66700/100000 [20:06:16<5:23:58,  1.71it/s]Step... (66700 / 100000 | Loss: 0.7149558067321777, Learning Rate: 3.346733668341709e-05)
+
                                                                             
Step... (66700 / 100000 | Loss: 0.7242344617843628, Learning Rate: 3.346733668341709e-05)
+
Train steps ... :  67%|██████▋   | 66700/100000 [20:06:16<5:23:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 66701/100000 [20:06:17<5:24:18,  1.71it/s]
Train steps ... :  67%|██████▋   | 66702/100000 [20:06:17<5:24:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 66703/100000 [20:06:18<5:25:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 66704/100000 [20:06:18<5:24:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66705/100000 [20:06:19<5:24:27,  1.71it/s]
Train steps ... :  67%|██████▋   | 66706/100000 [20:06:19<5:24:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 66707/100000 [20:06:20<5:24:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 66708/100000 [20:06:21<5:24:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 66709/100000 [20:06:21<5:24:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66710/100000 [20:06:22<5:24:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 66711/100000 [20:06:22<5:23:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 66712/100000 [20:06:23<5:24:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 66713/100000 [20:06:24<5:24:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66714/100000 [20:06:24<5:24:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66715/100000 [20:06:25<5:24:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66716/100000 [20:06:25<5:24:27,  1.71it/s]
Train steps ... :  67%|██████▋   | 66717/100000 [20:06:26<5:24:27,  1.71it/s]
Train steps ... :  67%|██████▋   | 66718/100000 [20:06:26<5:24:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 66719/100000 [20:06:27<5:24:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66720/100000 [20:06:28<5:24:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 66721/100000 [20:06:28<5:23:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 66722/100000 [20:06:29<5:24:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 66723/100000 [20:06:29<5:24:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 66724/100000 [20:06:30<5:24:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 66725/100000 [20:06:31<5:24:15,  1.71it/s]Step... (66725 / 100000 | Loss: 1.0801236629486084, Learning Rate: 3.344221105527639e-05)
+
                                                                             
Step... (66725 / 100000 | Loss: 0.6236201524734497, Learning Rate: 3.344221105527639e-05)
+
Train steps ... :  67%|██████▋   | 66725/100000 [20:06:31<5:24:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66726/100000 [20:06:31<5:24:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66727/100000 [20:06:32<5:24:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66728/100000 [20:06:32<5:24:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66729/100000 [20:06:33<5:24:34,  1.71it/s]
Train steps ... :  67%|██████▋   | 66730/100000 [20:06:33<5:24:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 66731/100000 [20:06:34<5:24:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 66732/100000 [20:06:35<5:23:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66733/100000 [20:06:35<5:23:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 66734/100000 [20:06:36<5:23:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66735/100000 [20:06:36<5:23:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 66736/100000 [20:06:37<5:24:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 66737/100000 [20:06:38<5:23:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 66738/100000 [20:06:38<5:23:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 66739/100000 [20:06:39<5:23:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 66740/100000 [20:06:39<5:24:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 66741/100000 [20:06:40<5:23:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 66742/100000 [20:06:40<5:23:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 66743/100000 [20:06:41<5:23:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 66744/100000 [20:06:42<5:23:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66745/100000 [20:06:42<5:23:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66746/100000 [20:06:43<5:23:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 66747/100000 [20:06:43<5:23:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 66748/100000 [20:06:44<5:23:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66749/100000 [20:06:45<5:23:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66750/100000 [20:06:45<5:24:21,  1.71it/s]Step... (66750 / 100000 | Loss: 0.7914523482322693, Learning Rate: 3.341708542713568e-05)
+
                                                                             
Step... (66750 / 100000 | Loss: 0.570097804069519, Learning Rate: 3.341708542713568e-05)
+
Train steps ... :  67%|██████▋   | 66750/100000 [20:06:45<5:24:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 66751/100000 [20:06:46<5:24:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 66752/100000 [20:06:46<5:23:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 66753/100000 [20:06:47<5:23:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 66754/100000 [20:06:47<5:23:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 66755/100000 [20:06:48<5:24:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 66756/100000 [20:06:49<5:24:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66757/100000 [20:06:49<5:24:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66758/100000 [20:06:50<5:23:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 66759/100000 [20:06:50<5:23:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 66760/100000 [20:06:51<5:24:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66761/100000 [20:06:52<5:24:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 66762/100000 [20:06:52<5:24:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66763/100000 [20:06:53<5:23:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 66764/100000 [20:06:53<5:24:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 66765/100000 [20:06:54<5:23:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66766/100000 [20:06:55<5:23:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 66767/100000 [20:06:55<5:23:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 66768/100000 [20:06:56<5:23:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66769/100000 [20:06:56<5:23:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66770/100000 [20:06:57<5:23:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66771/100000 [20:06:57<5:23:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 66772/100000 [20:06:58<5:23:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66773/100000 [20:06:59<5:24:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 66774/100000 [20:06:59<5:23:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 66775/100000 [20:07:00<5:24:20,  1.71it/s]Step... (66775 / 100000 | Loss: 0.8670480251312256, Learning Rate: 3.3391959798994974e-05)
+
                                                                             
Step... (66775 / 100000 | Loss: 0.8323206305503845, Learning Rate: 3.3391959798994974e-05)
+
Train steps ... :  67%|██████▋   | 66775/100000 [20:07:00<5:24:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 66776/100000 [20:07:00<5:23:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66777/100000 [20:07:01<5:23:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 66778/100000 [20:07:02<5:23:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 66779/100000 [20:07:02<5:23:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66780/100000 [20:07:03<5:23:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 66781/100000 [20:07:03<5:23:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66782/100000 [20:07:04<5:23:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66783/100000 [20:07:04<5:23:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 66784/100000 [20:07:05<5:23:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66785/100000 [20:07:06<5:23:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66786/100000 [20:07:06<5:23:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 66787/100000 [20:07:07<5:23:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 66788/100000 [20:07:07<5:23:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 66789/100000 [20:07:08<5:23:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 66790/100000 [20:07:09<5:23:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 66791/100000 [20:07:09<5:23:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66792/100000 [20:07:10<5:23:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 66793/100000 [20:07:10<5:23:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 66794/100000 [20:07:11<5:23:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66795/100000 [20:07:11<5:23:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 66796/100000 [20:07:12<5:23:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 66797/100000 [20:07:13<5:23:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 66798/100000 [20:07:13<5:23:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 66799/100000 [20:07:14<5:23:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 66800/100000 [20:07:14<5:23:24,  1.71it/s]Step... (66800 / 100000 | Loss: 0.7910858988761902, Learning Rate: 3.336683417085427e-05)
+
                                                                             
Step... (66800 / 100000 | Loss: 0.6470892429351807, Learning Rate: 3.336683417085427e-05)
+
Train steps ... :  67%|██████▋   | 66800/100000 [20:07:15<5:23:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 66801/100000 [20:07:15<5:23:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 66802/100000 [20:07:16<5:23:39,  1.71it/s]
Train steps ... :  67%|██████▋   | 66803/100000 [20:07:16<5:23:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66804/100000 [20:07:17<5:23:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66805/100000 [20:07:17<5:23:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 66806/100000 [20:07:18<5:23:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 66807/100000 [20:07:18<5:23:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66808/100000 [20:07:19<5:22:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 66809/100000 [20:07:20<5:22:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 66810/100000 [20:07:20<5:23:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 66811/100000 [20:07:21<5:23:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 66812/100000 [20:07:21<5:23:39,  1.71it/s]
Train steps ... :  67%|██████▋   | 66813/100000 [20:07:22<5:23:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 66814/100000 [20:07:23<5:23:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66815/100000 [20:07:23<5:23:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66816/100000 [20:07:24<5:23:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66817/100000 [20:07:24<5:23:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 66818/100000 [20:07:25<5:23:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 66819/100000 [20:07:25<5:23:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66820/100000 [20:07:26<5:23:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66821/100000 [20:07:27<5:23:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 66822/100000 [20:07:27<5:23:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66823/100000 [20:07:28<5:23:27,  1.71it/s]
Train steps ... :  67%|██████▋   | 66824/100000 [20:07:28<5:24:23,  1.70it/s]
Train steps ... :  67%|██████▋   | 66825/100000 [20:07:29<5:24:01,  1.71it/s]Step... (66825 / 100000 | Loss: 0.7272304892539978, Learning Rate: 3.334170854271357e-05)
+
                                                                             
Step... (66825 / 100000 | Loss: 0.5895788073539734, Learning Rate: 3.334170854271357e-05)
+
Train steps ... :  67%|██████▋   | 66825/100000 [20:07:29<5:24:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 66826/100000 [20:07:30<5:25:29,  1.70it/s]
Train steps ... :  67%|██████▋   | 66827/100000 [20:07:30<5:24:35,  1.70it/s]
Train steps ... :  67%|██████▋   | 66828/100000 [20:07:31<5:23:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 66829/100000 [20:07:31<5:23:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 66830/100000 [20:07:32<5:23:18,  1.71it/s]
Train steps ... :  67%|██████▋   | 66831/100000 [20:07:33<5:23:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66832/100000 [20:07:33<5:23:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 66833/100000 [20:07:34<5:22:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66834/100000 [20:07:34<5:23:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 66835/100000 [20:07:35<5:23:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 66836/100000 [20:07:35<5:22:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 66837/100000 [20:07:36<5:22:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66838/100000 [20:07:37<5:22:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 66839/100000 [20:07:37<5:22:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66840/100000 [20:07:38<5:22:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 66841/100000 [20:07:38<5:22:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66842/100000 [20:07:39<5:22:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 66843/100000 [20:07:40<5:23:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 66844/100000 [20:07:40<5:23:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 66845/100000 [20:07:41<5:23:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66846/100000 [20:07:41<5:23:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66847/100000 [20:07:42<5:23:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 66848/100000 [20:07:42<5:22:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 66849/100000 [20:07:43<5:23:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 66850/100000 [20:07:44<5:22:53,  1.71it/s]Step... (66850 / 100000 | Loss: 0.8489910364151001, Learning Rate: 3.3316582914572864e-05)
+
                                                                             
Step... (66850 / 100000 | Loss: 0.75213623046875, Learning Rate: 3.3316582914572864e-05)
+
Train steps ... :  67%|██████▋   | 66850/100000 [20:07:44<5:22:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66851/100000 [20:07:44<5:22:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66852/100000 [20:07:45<5:23:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66853/100000 [20:07:45<5:22:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66854/100000 [20:07:46<5:23:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 66855/100000 [20:07:47<5:23:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 66856/100000 [20:07:47<5:23:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 66857/100000 [20:07:48<5:23:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 66858/100000 [20:07:48<5:23:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 66859/100000 [20:07:49<5:23:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66860/100000 [20:07:49<5:23:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66861/100000 [20:07:50<5:23:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66862/100000 [20:07:51<5:23:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 66863/100000 [20:07:51<5:22:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66864/100000 [20:07:52<5:22:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66865/100000 [20:07:52<5:22:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66866/100000 [20:07:53<5:22:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 66867/100000 [20:07:54<5:23:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 66868/100000 [20:07:54<5:22:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 66869/100000 [20:07:55<5:22:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 66870/100000 [20:07:55<5:22:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66871/100000 [20:07:56<5:22:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 66872/100000 [20:07:56<5:23:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 66873/100000 [20:07:57<5:23:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 66874/100000 [20:07:58<5:22:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66875/100000 [20:07:58<5:23:02,  1.71it/s]Step... (66875 / 100000 | Loss: 0.6011658310890198, Learning Rate: 3.329145728643217e-05)
+
                                                                             
Step... (66875 / 100000 | Loss: 0.9594690799713135, Learning Rate: 3.329145728643217e-05)
+
Train steps ... :  67%|██████▋   | 66875/100000 [20:07:59<5:23:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 66876/100000 [20:07:59<5:23:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 66877/100000 [20:07:59<5:23:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 66878/100000 [20:08:00<5:23:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 66879/100000 [20:08:01<5:23:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66880/100000 [20:08:01<5:23:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 66881/100000 [20:08:02<5:22:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 66882/100000 [20:08:02<5:22:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66883/100000 [20:08:03<5:22:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66884/100000 [20:08:04<5:22:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 66885/100000 [20:08:04<5:22:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 66886/100000 [20:08:05<5:22:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66887/100000 [20:08:05<5:22:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 66888/100000 [20:08:06<5:22:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66889/100000 [20:08:06<5:22:34,  1.71it/s]
Train steps ... :  67%|██████▋   | 66890/100000 [20:08:07<5:22:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66891/100000 [20:08:08<5:22:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66892/100000 [20:08:08<5:23:49,  1.70it/s]
Train steps ... :  67%|██████▋   | 66893/100000 [20:08:09<5:23:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66894/100000 [20:08:09<5:22:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66895/100000 [20:08:10<5:22:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 66896/100000 [20:08:11<5:23:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66897/100000 [20:08:11<5:22:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66898/100000 [20:08:12<5:22:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66899/100000 [20:08:12<5:22:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66900/100000 [20:08:13<5:22:37,  1.71it/s]Step... (66900 / 100000 | Loss: 0.8395307064056396, Learning Rate: 3.3266331658291464e-05)
+
                                                                             
Step... (66900 / 100000 | Loss: 0.9712268710136414, Learning Rate: 3.3266331658291464e-05)
+
Train steps ... :  67%|██████▋   | 66900/100000 [20:08:13<5:22:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 66901/100000 [20:08:13<5:22:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66902/100000 [20:08:14<5:22:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66903/100000 [20:08:15<5:22:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 66904/100000 [20:08:15<5:22:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 66905/100000 [20:08:16<5:22:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 66906/100000 [20:08:16<5:22:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66907/100000 [20:08:17<5:22:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 66908/100000 [20:08:18<5:22:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 66909/100000 [20:08:18<5:22:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 66910/100000 [20:08:19<5:22:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 66911/100000 [20:08:19<5:23:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66912/100000 [20:08:20<5:22:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66913/100000 [20:08:20<5:22:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 66914/100000 [20:08:21<5:22:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66915/100000 [20:08:22<5:22:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 66916/100000 [20:08:22<5:22:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 66917/100000 [20:08:23<5:22:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 66918/100000 [20:08:23<5:22:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 66919/100000 [20:08:24<5:22:11,  1.71it/s]
Train steps ... :  67%|██████▋   | 66920/100000 [20:08:25<5:22:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 66921/100000 [20:08:25<5:22:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 66922/100000 [20:08:26<5:22:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 66923/100000 [20:08:26<5:22:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 66924/100000 [20:08:27<5:22:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66925/100000 [20:08:27<5:22:17,  1.71it/s]Step... (66925 / 100000 | Loss: 0.6104128360748291, Learning Rate: 3.3241206030150754e-05)
+
                                                                             
Step... (66925 / 100000 | Loss: 0.7392337322235107, Learning Rate: 3.3241206030150754e-05)
+
Train steps ... :  67%|██████▋   | 66925/100000 [20:08:28<5:22:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 66926/100000 [20:08:28<5:22:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 66927/100000 [20:08:29<5:22:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 66928/100000 [20:08:29<5:22:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 66929/100000 [20:08:30<5:22:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66930/100000 [20:08:30<5:22:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 66931/100000 [20:08:31<5:22:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66932/100000 [20:08:32<5:22:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66933/100000 [20:08:32<5:22:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 66934/100000 [20:08:33<5:21:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 66935/100000 [20:08:33<5:21:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 66936/100000 [20:08:34<5:21:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66937/100000 [20:08:35<5:21:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 66938/100000 [20:08:35<5:21:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 66939/100000 [20:08:36<5:21:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66940/100000 [20:08:36<5:21:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 66941/100000 [20:08:37<5:21:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 66942/100000 [20:08:37<5:21:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 66943/100000 [20:08:38<5:21:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66944/100000 [20:08:39<5:21:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 66945/100000 [20:08:39<5:21:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 66946/100000 [20:08:40<5:21:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 66947/100000 [20:08:40<5:22:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 66948/100000 [20:08:41<5:21:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66949/100000 [20:08:42<5:22:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66950/100000 [20:08:42<5:22:45,  1.71it/s]Step... (66950 / 100000 | Loss: 0.5999391078948975, Learning Rate: 3.321608040201005e-05)
+
                                                                             
Step... (66950 / 100000 | Loss: 0.618962824344635, Learning Rate: 3.321608040201005e-05)
+
Train steps ... :  67%|██████▋   | 66950/100000 [20:08:42<5:22:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 66951/100000 [20:08:43<5:22:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 66952/100000 [20:08:43<5:22:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 66953/100000 [20:08:44<5:22:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 66954/100000 [20:08:44<5:21:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 66955/100000 [20:08:45<5:22:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 66956/100000 [20:08:46<5:22:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 66957/100000 [20:08:46<5:22:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 66958/100000 [20:08:47<5:22:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 66959/100000 [20:08:47<5:22:34,  1.71it/s]
Train steps ... :  67%|██████▋   | 66960/100000 [20:08:48<5:22:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 66961/100000 [20:08:49<5:22:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 66962/100000 [20:08:49<5:22:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 66963/100000 [20:08:50<5:22:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 66964/100000 [20:08:50<5:21:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 66965/100000 [20:08:51<5:21:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 66966/100000 [20:08:51<5:22:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 66967/100000 [20:08:52<5:21:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 66968/100000 [20:08:53<5:21:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 66969/100000 [20:08:53<5:21:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 66970/100000 [20:08:54<5:21:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 66971/100000 [20:08:54<5:21:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 66972/100000 [20:08:55<5:21:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 66973/100000 [20:08:56<5:21:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 66974/100000 [20:08:56<5:21:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 66975/100000 [20:08:57<5:21:42,  1.71it/s]Step... (66975 / 100000 | Loss: 0.6123877167701721, Learning Rate: 3.319095477386935e-05)
+
                                                                             
Step... (66975 / 100000 | Loss: 0.6835448741912842, Learning Rate: 3.319095477386935e-05)
+
Train steps ... :  67%|██████▋   | 66975/100000 [20:08:57<5:21:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 66976/100000 [20:08:57<5:21:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 66977/100000 [20:08:58<5:21:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 66978/100000 [20:08:58<5:21:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 66979/100000 [20:08:59<5:21:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 66980/100000 [20:09:00<5:21:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 66981/100000 [20:09:00<5:21:39,  1.71it/s]
Train steps ... :  67%|██████▋   | 66982/100000 [20:09:01<5:21:27,  1.71it/s]
Train steps ... :  67%|██████▋   | 66983/100000 [20:09:01<5:21:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 66984/100000 [20:09:02<5:21:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 66985/100000 [20:09:03<5:21:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 66986/100000 [20:09:03<5:21:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 66987/100000 [20:09:04<5:21:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 66988/100000 [20:09:04<5:21:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 66989/100000 [20:09:05<5:21:39,  1.71it/s]
Train steps ... :  67%|██████▋   | 66990/100000 [20:09:05<5:21:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66991/100000 [20:09:06<5:21:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66992/100000 [20:09:07<5:21:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 66993/100000 [20:09:07<5:21:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 66994/100000 [20:09:08<5:21:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 66995/100000 [20:09:08<5:21:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 66996/100000 [20:09:09<5:21:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 66997/100000 [20:09:10<5:21:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 66998/100000 [20:09:10<5:22:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 66999/100000 [20:09:11<5:21:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 67000/100000 [20:09:11<5:21:45,  1.71it/s]Step... (67000 / 100000 | Loss: 0.688575267791748, Learning Rate: 3.3165829145728643e-05)
+
                                                                             
Step... (67000 / 100000 | Loss: 0.8053511381149292, Learning Rate: 3.3165829145728643e-05)
+
Train steps ... :  67%|██████▋   | 67000/100000 [20:09:12<5:21:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 67001/100000 [20:09:12<5:21:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 67002/100000 [20:09:13<5:21:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 67003/100000 [20:09:13<5:21:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 67004/100000 [20:09:14<5:22:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 67005/100000 [20:09:14<5:21:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 67006/100000 [20:09:15<5:21:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 67007/100000 [20:09:15<5:21:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 67008/100000 [20:09:16<5:22:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 67009/100000 [20:09:17<5:22:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 67010/100000 [20:09:17<5:22:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67011/100000 [20:09:18<5:22:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67012/100000 [20:09:18<5:22:40,  1.70it/s]
Train steps ... :  67%|██████▋   | 67013/100000 [20:09:19<5:22:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67014/100000 [20:09:20<5:21:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 67015/100000 [20:09:20<5:21:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67016/100000 [20:09:21<5:21:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 67017/100000 [20:09:21<5:21:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 67018/100000 [20:09:22<5:21:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 67019/100000 [20:09:22<5:22:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 67020/100000 [20:09:23<5:21:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 67021/100000 [20:09:24<5:21:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 67022/100000 [20:09:24<5:21:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 67023/100000 [20:09:25<5:21:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 67024/100000 [20:09:25<5:21:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 67025/100000 [20:09:26<5:21:17,  1.71it/s]Step... (67025 / 100000 | Loss: 0.7519909143447876, Learning Rate: 3.314070351758794e-05)
+
                                                                             
Step... (67025 / 100000 | Loss: 0.9459851980209351, Learning Rate: 3.314070351758794e-05)
+
Train steps ... :  67%|██████▋   | 67025/100000 [20:09:26<5:21:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 67026/100000 [20:09:27<5:21:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67027/100000 [20:09:27<5:21:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 67028/100000 [20:09:28<5:21:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 67029/100000 [20:09:28<5:21:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67030/100000 [20:09:29<5:21:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67031/100000 [20:09:29<5:21:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67032/100000 [20:09:30<5:21:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67033/100000 [20:09:31<5:21:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 67034/100000 [20:09:31<5:20:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 67035/100000 [20:09:32<5:22:18,  1.70it/s]
Train steps ... :  67%|██████▋   | 67036/100000 [20:09:32<5:21:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 67037/100000 [20:09:33<5:21:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 67038/100000 [20:09:34<5:21:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 67039/100000 [20:09:34<5:21:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67040/100000 [20:09:35<5:21:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 67041/100000 [20:09:35<5:21:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 67042/100000 [20:09:36<5:21:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67043/100000 [20:09:37<5:20:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67044/100000 [20:09:37<5:21:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67045/100000 [20:09:38<5:21:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 67046/100000 [20:09:38<5:21:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 67047/100000 [20:09:39<5:21:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 67048/100000 [20:09:39<5:21:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 67049/100000 [20:09:40<5:21:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67050/100000 [20:09:41<5:21:31,  1.71it/s]Step... (67050 / 100000 | Loss: 0.7790859341621399, Learning Rate: 3.311557788944724e-05)
+
                                                                             
Step... (67050 / 100000 | Loss: 0.9097057580947876, Learning Rate: 3.311557788944724e-05)
+
Train steps ... :  67%|██████▋   | 67050/100000 [20:09:41<5:21:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 67051/100000 [20:09:41<5:21:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 67052/100000 [20:09:42<5:21:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 67053/100000 [20:09:42<5:21:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 67054/100000 [20:09:43<5:20:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 67055/100000 [20:09:44<5:20:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 67056/100000 [20:09:44<5:21:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 67057/100000 [20:09:45<5:21:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 67058/100000 [20:09:45<5:20:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 67059/100000 [20:09:46<5:20:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 67060/100000 [20:09:46<5:21:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67061/100000 [20:09:47<5:20:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67062/100000 [20:09:48<5:20:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 67063/100000 [20:09:48<5:21:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67064/100000 [20:09:49<5:21:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 67065/100000 [20:09:49<5:21:18,  1.71it/s]
Train steps ... :  67%|██████▋   | 67066/100000 [20:09:50<5:21:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 67067/100000 [20:09:51<5:21:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 67068/100000 [20:09:51<5:21:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 67069/100000 [20:09:52<5:21:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67070/100000 [20:09:52<5:20:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 67071/100000 [20:09:53<5:20:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67072/100000 [20:09:53<5:21:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 67073/100000 [20:09:54<5:20:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67074/100000 [20:09:55<5:21:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 67075/100000 [20:09:55<5:21:17,  1.71it/s]Step... (67075 / 100000 | Loss: 0.7496916055679321, Learning Rate: 3.309045226130653e-05)
+
                                                                             
Step... (67075 / 100000 | Loss: 0.9149087071418762, Learning Rate: 3.309045226130653e-05)
+
Train steps ... :  67%|██████▋   | 67075/100000 [20:09:56<5:21:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 67076/100000 [20:09:56<5:21:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 67077/100000 [20:09:56<5:20:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 67078/100000 [20:09:57<5:21:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 67079/100000 [20:09:58<5:20:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 67080/100000 [20:09:58<5:21:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 67081/100000 [20:09:59<5:21:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67082/100000 [20:09:59<5:20:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 67083/100000 [20:10:00<5:21:11,  1.71it/s]
Train steps ... :  67%|██████▋   | 67084/100000 [20:10:00<5:21:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 67085/100000 [20:10:01<5:21:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67086/100000 [20:10:02<5:21:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 67087/100000 [20:10:02<5:20:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67088/100000 [20:10:03<5:20:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67089/100000 [20:10:03<5:21:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 67090/100000 [20:10:04<5:21:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 67091/100000 [20:10:05<5:20:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 67092/100000 [20:10:05<5:20:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 67093/100000 [20:10:06<5:20:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 67094/100000 [20:10:06<5:20:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 67095/100000 [20:10:07<5:21:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67096/100000 [20:10:08<5:20:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67097/100000 [20:10:08<5:20:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 67098/100000 [20:10:09<5:20:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 67099/100000 [20:10:09<5:20:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 67100/100000 [20:10:10<5:20:42,  1.71it/s]Step... (67100 / 100000 | Loss: 0.6823482513427734, Learning Rate: 3.306532663316583e-05)
+
                                                                             
Step... (67100 / 100000 | Loss: 0.865602433681488, Learning Rate: 3.306532663316583e-05)
+
Train steps ... :  67%|██████▋   | 67100/100000 [20:10:10<5:20:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 67101/100000 [20:10:10<5:20:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 67102/100000 [20:10:11<5:20:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 67103/100000 [20:10:12<5:20:34,  1.71it/s]
Train steps ... :  67%|██████▋   | 67104/100000 [20:10:12<5:20:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 67105/100000 [20:10:13<5:20:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 67106/100000 [20:10:13<5:20:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 67107/100000 [20:10:14<5:20:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 67108/100000 [20:10:15<5:21:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 67109/100000 [20:10:15<5:21:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67110/100000 [20:10:16<5:21:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67111/100000 [20:10:16<5:21:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 67112/100000 [20:10:17<5:21:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67113/100000 [20:10:17<5:21:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67114/100000 [20:10:18<5:20:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 67115/100000 [20:10:19<5:20:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 67116/100000 [20:10:19<5:20:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 67117/100000 [20:10:20<5:20:34,  1.71it/s]
Train steps ... :  67%|██████▋   | 67118/100000 [20:10:20<5:20:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67119/100000 [20:10:21<5:20:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 67120/100000 [20:10:22<5:20:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 67121/100000 [20:10:22<5:20:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 67122/100000 [20:10:23<5:20:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 67123/100000 [20:10:23<5:20:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67124/100000 [20:10:24<5:20:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67125/100000 [20:10:24<5:20:07,  1.71it/s]Step... (67125 / 100000 | Loss: 1.041558861732483, Learning Rate: 3.3040201005025127e-05)
+
                                                                             
Step... (67125 / 100000 | Loss: 0.896651029586792, Learning Rate: 3.3040201005025127e-05)
+
Train steps ... :  67%|██████▋   | 67125/100000 [20:10:25<5:20:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 67126/100000 [20:10:25<5:20:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67127/100000 [20:10:26<5:20:27,  1.71it/s]
Train steps ... :  67%|██████▋   | 67128/100000 [20:10:26<5:20:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 67129/100000 [20:10:27<5:20:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 67130/100000 [20:10:27<5:20:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67131/100000 [20:10:28<5:20:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67132/100000 [20:10:29<5:20:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 67133/100000 [20:10:29<5:20:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 67134/100000 [20:10:30<5:20:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67135/100000 [20:10:30<5:20:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 67136/100000 [20:10:31<5:20:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 67137/100000 [20:10:31<5:20:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67138/100000 [20:10:32<5:20:27,  1.71it/s]
Train steps ... :  67%|██████▋   | 67139/100000 [20:10:33<5:20:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67140/100000 [20:10:33<5:20:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 67141/100000 [20:10:34<5:20:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 67142/100000 [20:10:34<5:20:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 67143/100000 [20:10:35<5:20:11,  1.71it/s]
Train steps ... :  67%|██████▋   | 67144/100000 [20:10:36<5:20:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 67145/100000 [20:10:36<5:19:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 67146/100000 [20:10:37<5:20:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 67147/100000 [20:10:37<5:20:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 67148/100000 [20:10:38<5:20:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 67149/100000 [20:10:39<5:20:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 67150/100000 [20:10:39<5:20:45,  1.71it/s]Step... (67150 / 100000 | Loss: 0.6767077445983887, Learning Rate: 3.301507537688442e-05)
+
                                                                             
Step... (67150 / 100000 | Loss: 0.6506029367446899, Learning Rate: 3.301507537688442e-05)
+
Train steps ... :  67%|██████▋   | 67150/100000 [20:10:39<5:20:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 67151/100000 [20:10:40<5:21:26,  1.70it/s]
Train steps ... :  67%|██████▋   | 67152/100000 [20:10:40<5:20:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67153/100000 [20:10:41<5:20:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 67154/100000 [20:10:41<5:20:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 67155/100000 [20:10:42<5:20:18,  1.71it/s]
Train steps ... :  67%|██████▋   | 67156/100000 [20:10:43<5:20:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67157/100000 [20:10:43<5:19:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 67158/100000 [20:10:44<5:19:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 67159/100000 [20:10:44<5:20:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 67160/100000 [20:10:45<5:20:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 67161/100000 [20:10:46<5:20:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 67162/100000 [20:10:46<5:20:27,  1.71it/s]
Train steps ... :  67%|██████▋   | 67163/100000 [20:10:47<5:20:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 67164/100000 [20:10:47<5:20:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67165/100000 [20:10:48<5:20:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 67166/100000 [20:10:48<5:20:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 67167/100000 [20:10:49<5:20:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 67168/100000 [20:10:50<5:19:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67169/100000 [20:10:50<5:19:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 67170/100000 [20:10:51<5:20:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 67171/100000 [20:10:51<5:20:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 67172/100000 [20:10:52<5:20:39,  1.71it/s]
Train steps ... :  67%|██████▋   | 67173/100000 [20:10:53<5:20:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 67174/100000 [20:10:53<5:20:58,  1.70it/s]
Train steps ... :  67%|██████▋   | 67175/100000 [20:10:54<5:20:48,  1.71it/s]Step... (67175 / 100000 | Loss: 0.785285472869873, Learning Rate: 3.298994974874372e-05)
+
                                                                             
Step... (67175 / 100000 | Loss: 1.0148744583129883, Learning Rate: 3.298994974874372e-05)
+
Train steps ... :  67%|██████▋   | 67175/100000 [20:10:54<5:20:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 67176/100000 [20:10:54<5:20:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 67177/100000 [20:10:55<5:20:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 67178/100000 [20:10:55<5:19:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 67179/100000 [20:10:56<5:19:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 67180/100000 [20:10:57<5:19:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 67181/100000 [20:10:57<5:19:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 67182/100000 [20:10:58<5:20:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 67183/100000 [20:10:58<5:20:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 67184/100000 [20:10:59<5:20:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67185/100000 [20:11:00<5:20:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 67186/100000 [20:11:00<5:19:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 67187/100000 [20:11:01<5:19:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 67188/100000 [20:11:01<5:19:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 67189/100000 [20:11:02<5:19:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 67190/100000 [20:11:03<5:19:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 67191/100000 [20:11:03<5:20:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 67192/100000 [20:11:04<5:19:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 67193/100000 [20:11:04<5:19:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 67194/100000 [20:11:05<5:19:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 67195/100000 [20:11:05<5:19:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67196/100000 [20:11:06<5:19:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 67197/100000 [20:11:07<5:19:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 67198/100000 [20:11:07<5:19:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 67199/100000 [20:11:08<5:19:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 67200/100000 [20:11:08<5:20:00,  1.71it/s]Step... (67200 / 100000 | Loss: 0.9009613394737244, Learning Rate: 3.2964824120603016e-05)
+
                                                                             
Step... (67200 / 100000 | Loss: 0.6770062446594238, Learning Rate: 3.2964824120603016e-05)
+
Train steps ... :  67%|██████▋   | 67200/100000 [20:11:09<5:20:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 67201/100000 [20:11:09<5:19:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67202/100000 [20:11:10<5:19:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67203/100000 [20:11:10<5:19:34,  1.71it/s]
Train steps ... :  67%|██████▋   | 67204/100000 [20:11:11<5:19:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 67205/100000 [20:11:11<5:19:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 67206/100000 [20:11:12<5:19:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 67207/100000 [20:11:12<5:19:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 67208/100000 [20:11:13<5:19:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67209/100000 [20:11:14<5:19:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67210/100000 [20:11:14<5:20:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 67211/100000 [20:11:15<5:19:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67212/100000 [20:11:15<5:20:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 67213/100000 [20:11:16<5:20:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 67214/100000 [20:11:17<5:20:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 67215/100000 [20:11:17<5:20:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67216/100000 [20:11:18<5:19:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67217/100000 [20:11:18<5:20:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 67218/100000 [20:11:19<5:20:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 67219/100000 [20:11:19<5:19:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67220/100000 [20:11:20<5:19:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67221/100000 [20:11:21<5:19:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 67222/100000 [20:11:21<5:19:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 67223/100000 [20:11:22<5:19:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67224/100000 [20:11:22<5:19:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67225/100000 [20:11:23<5:19:01,  1.71it/s]Step... (67225 / 100000 | Loss: 0.5802546143531799, Learning Rate: 3.293969849246231e-05)
+
                                                                             
Step... (67225 / 100000 | Loss: 0.597789466381073, Learning Rate: 3.293969849246231e-05)
+
Train steps ... :  67%|██████▋   | 67225/100000 [20:11:23<5:19:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 67226/100000 [20:11:24<5:19:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 67227/100000 [20:11:24<5:19:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 67228/100000 [20:11:25<5:19:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 67229/100000 [20:11:25<5:19:34,  1.71it/s]
Train steps ... :  67%|██████▋   | 67230/100000 [20:11:26<5:19:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 67231/100000 [20:11:26<5:19:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 67232/100000 [20:11:27<5:19:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67233/100000 [20:11:28<5:19:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 67234/100000 [20:11:28<5:19:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 67235/100000 [20:11:29<5:19:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67236/100000 [20:11:29<5:19:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 67237/100000 [20:11:30<5:19:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 67238/100000 [20:11:31<5:19:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67239/100000 [20:11:31<5:19:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 67240/100000 [20:11:32<5:19:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 67241/100000 [20:11:32<5:19:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 67242/100000 [20:11:33<5:19:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67243/100000 [20:11:34<5:18:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 67244/100000 [20:11:34<5:18:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 67245/100000 [20:11:35<5:19:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67246/100000 [20:11:35<5:18:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67247/100000 [20:11:36<5:18:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67248/100000 [20:11:36<5:19:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 67249/100000 [20:11:37<5:19:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 67250/100000 [20:11:38<5:18:50,  1.71it/s]Step... (67250 / 100000 | Loss: 0.8833395838737488, Learning Rate: 3.291457286432161e-05)
+
                                                                             
Step... (67250 / 100000 | Loss: 0.6422550082206726, Learning Rate: 3.291457286432161e-05)
+
Train steps ... :  67%|██████▋   | 67250/100000 [20:11:38<5:18:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 67251/100000 [20:11:38<5:19:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67252/100000 [20:11:39<5:19:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 67253/100000 [20:11:39<5:19:11,  1.71it/s]
Train steps ... :  67%|██████▋   | 67254/100000 [20:11:40<5:19:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67255/100000 [20:11:41<5:19:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67256/100000 [20:11:41<5:19:17,  1.71it/s]
Train steps ... :  67%|██████▋   | 67257/100000 [20:11:42<5:19:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67258/100000 [20:11:42<5:19:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67259/100000 [20:11:43<5:19:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 67260/100000 [20:11:43<5:18:50,  1.71it/s]
Train steps ... :  67%|██████▋   | 67261/100000 [20:11:44<5:19:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 67262/100000 [20:11:45<5:19:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67263/100000 [20:11:45<5:18:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 67264/100000 [20:11:46<5:18:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 67265/100000 [20:11:46<5:18:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 67266/100000 [20:11:47<5:18:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 67267/100000 [20:11:48<5:18:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 67268/100000 [20:11:48<5:18:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67269/100000 [20:11:49<5:19:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67270/100000 [20:11:49<5:19:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 67271/100000 [20:11:50<5:19:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 67272/100000 [20:11:50<5:19:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67273/100000 [20:11:51<5:19:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 67274/100000 [20:11:52<5:18:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 67275/100000 [20:11:52<5:19:04,  1.71it/s]Step... (67275 / 100000 | Loss: 0.8222547769546509, Learning Rate: 3.2889447236180906e-05)
+
                                                                             
Step... (67275 / 100000 | Loss: 0.8643219470977783, Learning Rate: 3.2889447236180906e-05)
+
Train steps ... :  67%|██████▋   | 67275/100000 [20:11:53<5:19:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 67276/100000 [20:11:53<5:18:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 67277/100000 [20:11:53<5:18:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 67278/100000 [20:11:54<5:18:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 67279/100000 [20:11:55<5:18:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 67280/100000 [20:11:55<5:18:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 67281/100000 [20:11:56<5:18:27,  1.71it/s]
Train steps ... :  67%|██████▋   | 67282/100000 [20:11:56<5:18:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67283/100000 [20:11:57<5:18:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 67284/100000 [20:11:57<5:18:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 67285/100000 [20:11:58<5:18:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 67286/100000 [20:11:59<5:19:33,  1.71it/s]
Train steps ... :  67%|██████▋   | 67287/100000 [20:11:59<5:19:11,  1.71it/s]
Train steps ... :  67%|██████▋   | 67288/100000 [20:12:00<5:18:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 67289/100000 [20:12:00<5:18:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 67290/100000 [20:12:01<5:18:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67291/100000 [20:12:02<5:18:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67292/100000 [20:12:02<5:18:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 67293/100000 [20:12:03<5:18:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67294/100000 [20:12:03<5:18:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 67295/100000 [20:12:04<5:18:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67296/100000 [20:12:05<5:18:34,  1.71it/s]
Train steps ... :  67%|██████▋   | 67297/100000 [20:12:05<5:18:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 67298/100000 [20:12:06<5:18:21,  1.71it/s]
Train steps ... :  67%|██████▋   | 67299/100000 [20:12:06<5:18:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67300/100000 [20:12:07<5:18:22,  1.71it/s]Step... (67300 / 100000 | Loss: 0.8980579376220703, Learning Rate: 3.28643216080402e-05)
+
                                                                             
Step... (67300 / 100000 | Loss: 0.6549067497253418, Learning Rate: 3.28643216080402e-05)
+
Train steps ... :  67%|██████▋   | 67300/100000 [20:12:07<5:18:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 67301/100000 [20:12:07<5:18:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 67302/100000 [20:12:08<5:18:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 67303/100000 [20:12:09<5:18:34,  1.71it/s]
Train steps ... :  67%|██████▋   | 67304/100000 [20:12:09<5:18:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 67305/100000 [20:12:10<5:18:40,  1.71it/s]
Train steps ... :  67%|██████▋   | 67306/100000 [20:12:10<5:18:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67307/100000 [20:12:11<5:18:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67308/100000 [20:12:12<5:18:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 67309/100000 [20:12:12<5:18:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 67310/100000 [20:12:13<5:18:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67311/100000 [20:12:13<5:18:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 67312/100000 [20:12:14<5:18:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 67313/100000 [20:12:14<5:18:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 67314/100000 [20:12:15<5:18:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67315/100000 [20:12:16<5:18:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67316/100000 [20:12:16<5:19:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67317/100000 [20:12:17<5:18:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 67318/100000 [20:12:17<5:18:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 67319/100000 [20:12:18<5:18:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 67320/100000 [20:12:19<5:18:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 67321/100000 [20:12:19<5:18:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 67322/100000 [20:12:20<5:18:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67323/100000 [20:12:20<5:19:55,  1.70it/s]
Train steps ... :  67%|██████▋   | 67324/100000 [20:12:21<5:19:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67325/100000 [20:12:21<5:18:56,  1.71it/s]Step... (67325 / 100000 | Loss: 0.8870956897735596, Learning Rate: 3.28391959798995e-05)
+
                                                                             
Step... (67325 / 100000 | Loss: 0.7477682828903198, Learning Rate: 3.28391959798995e-05)
+
Train steps ... :  67%|██████▋   | 67325/100000 [20:12:22<5:18:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 67326/100000 [20:12:22<5:18:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67327/100000 [20:12:23<5:18:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 67328/100000 [20:12:23<5:18:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67329/100000 [20:12:24<5:18:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67330/100000 [20:12:24<5:18:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 67331/100000 [20:12:25<5:18:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 67332/100000 [20:12:26<5:18:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 67333/100000 [20:12:26<5:18:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 67334/100000 [20:12:27<5:18:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 67335/100000 [20:12:27<5:18:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67336/100000 [20:12:28<5:18:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 67337/100000 [20:12:28<5:18:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 67338/100000 [20:12:29<5:18:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 67339/100000 [20:12:30<5:18:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 67340/100000 [20:12:30<5:18:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 67341/100000 [20:12:31<5:18:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 67342/100000 [20:12:31<5:18:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67343/100000 [20:12:32<5:18:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67344/100000 [20:12:33<5:18:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67345/100000 [20:12:33<5:18:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 67346/100000 [20:12:34<5:18:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67347/100000 [20:12:34<5:18:11,  1.71it/s]
Train steps ... :  67%|████��█▋   | 67348/100000 [20:12:35<5:18:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67349/100000 [20:12:36<5:18:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 67350/100000 [20:12:36<5:18:09,  1.71it/s]Step... (67350 / 100000 | Loss: 0.8576513528823853, Learning Rate: 3.2814070351758796e-05)
+
                                                                             
Step... (67350 / 100000 | Loss: 0.7323729991912842, Learning Rate: 3.2814070351758796e-05)
+
Train steps ... :  67%|██████▋   | 67350/100000 [20:12:36<5:18:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67351/100000 [20:12:37<5:18:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67352/100000 [20:12:37<5:18:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 67353/100000 [20:12:38<5:19:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 67354/100000 [20:12:38<5:19:08,  1.70it/s]
Train steps ... :  67%|██████▋   | 67355/100000 [20:12:39<5:18:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 67356/100000 [20:12:40<5:18:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67357/100000 [20:12:40<5:18:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67358/100000 [20:12:41<5:17:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 67359/100000 [20:12:41<5:18:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67360/100000 [20:12:42<5:17:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 67361/100000 [20:12:43<5:17:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 67362/100000 [20:12:43<5:17:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 67363/100000 [20:12:44<5:17:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 67364/100000 [20:12:44<5:18:00,  1.71it/s]
Train steps ... :  67%|██████▋   | 67365/100000 [20:12:45<5:17:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 67366/100000 [20:12:45<5:17:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67367/100000 [20:12:46<5:17:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 67368/100000 [20:12:47<5:17:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 67369/100000 [20:12:47<5:17:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 67370/100000 [20:12:48<5:18:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 67371/100000 [20:12:48<5:18:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67372/100000 [20:12:49<5:17:53,  1.71it/s]
Train steps ... :  67%|██████▋   | 67373/100000 [20:12:50<5:17:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 67374/100000 [20:12:50<5:17:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 67375/100000 [20:12:51<5:17:44,  1.71it/s]Step... (67375 / 100000 | Loss: 0.8232921361923218, Learning Rate: 3.278894472361809e-05)
+
                                                                             
Step... (67375 / 100000 | Loss: 0.6984715461730957, Learning Rate: 3.278894472361809e-05)
+
Train steps ... :  67%|██████▋   | 67375/100000 [20:12:51<5:17:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67376/100000 [20:12:51<5:18:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67377/100000 [20:12:52<5:18:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 67378/100000 [20:12:52<5:17:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 67379/100000 [20:12:53<5:17:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 67380/100000 [20:12:54<5:17:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 67381/100000 [20:12:54<5:18:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67382/100000 [20:12:55<5:17:42,  1.71it/s]
Train steps ... :  67%|██████▋   | 67383/100000 [20:12:55<5:17:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67384/100000 [20:12:56<5:17:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67385/100000 [20:12:57<5:17:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67386/100000 [20:12:57<5:18:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67387/100000 [20:12:58<5:18:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 67388/100000 [20:12:58<5:18:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67389/100000 [20:12:59<5:17:58,  1.71it/s]
Train steps ... :  67%|██████▋   | 67390/100000 [20:12:59<5:18:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 67391/100000 [20:13:00<5:18:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 67392/100000 [20:13:01<5:18:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 67393/100000 [20:13:01<5:18:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67394/100000 [20:13:02<5:18:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67395/100000 [20:13:02<5:17:59,  1.71it/s]
Train steps ... :  67%|███���██▋   | 67396/100000 [20:13:03<5:18:06,  1.71it/s]
Train steps ... :  67%|██████▋   | 67397/100000 [20:13:04<5:18:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 67398/100000 [20:13:04<5:18:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 67399/100000 [20:13:05<5:17:52,  1.71it/s]
Train steps ... :  67%|██████▋   | 67400/100000 [20:13:05<5:17:38,  1.71it/s]Step... (67400 / 100000 | Loss: 0.6246874928474426, Learning Rate: 3.276381909547739e-05)
+
                                                                             
Step... (67400 / 100000 | Loss: 0.6616385579109192, Learning Rate: 3.276381909547739e-05)
+
Train steps ... :  67%|██████▋   | 67400/100000 [20:13:06<5:17:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 67401/100000 [20:13:06<5:17:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 67402/100000 [20:13:07<5:18:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 67403/100000 [20:13:07<5:18:01,  1.71it/s]
Train steps ... :  67%|██████▋   | 67404/100000 [20:13:08<5:17:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 67405/100000 [20:13:08<5:17:39,  1.71it/s]
Train steps ... :  67%|██████▋   | 67406/100000 [20:13:09<5:17:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 67407/100000 [20:13:09<5:17:24,  1.71it/s]
Train steps ... :  67%|██████▋   | 67408/100000 [20:13:10<5:17:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 67409/100000 [20:13:11<5:17:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 67410/100000 [20:13:11<5:17:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 67411/100000 [20:13:12<5:17:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 67412/100000 [20:13:12<5:17:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 67413/100000 [20:13:13<5:17:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67414/100000 [20:13:14<5:17:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 67415/100000 [20:13:14<5:17:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 67416/100000 [20:13:15<5:18:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 67417/100000 [20:13:15<5:17:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 67418/100000 [20:13:16<5:17:39,  1.71it/s]
Train steps ... :  67%|██████▋   | 67419/100000 [20:13:16<5:18:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67420/100000 [20:13:17<5:17:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 67421/100000 [20:13:18<5:17:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67422/100000 [20:13:18<5:17:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 67423/100000 [20:13:19<5:17:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 67424/100000 [20:13:19<5:17:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 67425/100000 [20:13:20<5:17:46,  1.71it/s]Step... (67425 / 100000 | Loss: 0.7633365392684937, Learning Rate: 3.2738693467336686e-05)
+
                                                                             
Step... (67425 / 100000 | Loss: 0.6774142980575562, Learning Rate: 3.2738693467336686e-05)
+
Train steps ... :  67%|██████▋   | 67425/100000 [20:13:20<5:17:46,  1.71it/s]
Train steps ... :  67%|██████▋   | 67426/100000 [20:13:21<5:17:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 67427/100000 [20:13:21<5:17:43,  1.71it/s]
Train steps ... :  67%|██████▋   | 67428/100000 [20:13:22<5:17:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67429/100000 [20:13:22<5:17:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 67430/100000 [20:13:23<5:17:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67431/100000 [20:13:23<5:17:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 67432/100000 [20:13:24<5:17:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67433/100000 [20:13:25<5:17:38,  1.71it/s]
Train steps ... :  67%|██████▋   | 67434/100000 [20:13:25<5:17:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 67435/100000 [20:13:26<5:17:39,  1.71it/s]
Train steps ... :  67%|██████▋   | 67436/100000 [20:13:26<5:17:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67437/100000 [20:13:27<5:17:26,  1.71it/s]
Train steps ... :  67%|██████▋   | 67438/100000 [20:13:28<5:17:29,  1.71it/s]
Train steps ... :  67%|██████▋   | 67439/100000 [20:13:28<5:17:30,  1.71it/s]
Train steps ... :  67%|██████▋   | 67440/100000 [20:13:29<5:17:45,  1.71it/s]
Train steps ... :  67%|██████▋   | 67441/100000 [20:13:29<5:17:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 67442/100000 [20:13:30<5:17:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 67443/100000 [20:13:30<5:17:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67444/100000 [20:13:31<5:17:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67445/100000 [20:13:32<5:17:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 67446/100000 [20:13:32<5:16:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 67447/100000 [20:13:33<5:17:04,  1.71it/s]
Train steps ... :  67%|██████▋   | 67448/100000 [20:13:33<5:17:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 67449/100000 [20:13:34<5:17:15,  1.71it/s]
Train steps ... :  67%|██████▋   | 67450/100000 [20:13:35<5:17:13,  1.71it/s]Step... (67450 / 100000 | Loss: 0.7032414674758911, Learning Rate: 3.271356783919598e-05)
+
                                                                             
Step... (67450 / 100000 | Loss: 0.6295979022979736, Learning Rate: 3.271356783919598e-05)
+
Train steps ... :  67%|██████▋   | 67450/100000 [20:13:35<5:17:13,  1.71it/s]
Train steps ... :  67%|██████▋   | 67451/100000 [20:13:35<5:17:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 67452/100000 [20:13:36<5:16:55,  1.71it/s]
Train steps ... :  67%|██████▋   | 67453/100000 [20:13:36<5:16:49,  1.71it/s]
Train steps ... :  67%|██████▋   | 67454/100000 [20:13:37<5:17:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 67455/100000 [20:13:38<5:16:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 67456/100000 [20:13:38<5:17:19,  1.71it/s]
Train steps ... :  67%|██████▋   | 67457/100000 [20:13:39<5:16:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 67458/100000 [20:13:39<5:16:51,  1.71it/s]
Train steps ... :  67%|██████▋   | 67459/100000 [20:13:40<5:16:54,  1.71it/s]
Train steps ... :  67%|██████▋   | 67460/100000 [20:13:40<5:16:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 67461/100000 [20:13:41<5:17:10,  1.71it/s]
Train steps ... :  67%|██████▋   | 67462/100000 [20:13:42<5:17:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 67463/100000 [20:13:42<5:16:56,  1.71it/s]
Train steps ... :  67%|██████▋   | 67464/100000 [20:13:43<5:17:16,  1.71it/s]
Train steps ... :  67%|██████▋   | 67465/100000 [20:13:43<5:17:08,  1.71it/s]
Train steps ... :  67%|██████▋   | 67466/100000 [20:13:44<5:17:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 67467/100000 [20:13:45<5:17:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 67468/100000 [20:13:45<5:17:37,  1.71it/s]
Train steps ... :  67%|██████▋   | 67469/100000 [20:13:46<5:18:00,  1.70it/s]
Train steps ... :  67%|██████▋   | 67470/100000 [20:13:46<5:17:32,  1.71it/s]
Train steps ... :  67%|██████▋   | 67471/100000 [20:13:47<5:17:28,  1.71it/s]
Train steps ... :  67%|██████▋   | 67472/100000 [20:13:47<5:17:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 67473/100000 [20:13:48<5:17:48,  1.71it/s]
Train steps ... :  67%|██████▋   | 67474/100000 [20:13:49<5:17:31,  1.71it/s]
Train steps ... :  67%|██████▋   | 67475/100000 [20:13:49<5:17:12,  1.71it/s]Step... (67475 / 100000 | Loss: 0.629335880279541, Learning Rate: 3.268844221105527e-05)
+
                                                                             
Step... (67475 / 100000 | Loss: 0.6167799830436707, Learning Rate: 3.268844221105527e-05)
+
Train steps ... :  67%|██████▋   | 67475/100000 [20:13:50<5:17:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 67476/100000 [20:13:50<5:17:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67477/100000 [20:13:50<5:17:09,  1.71it/s]
Train steps ... :  67%|██████▋   | 67478/100000 [20:13:51<5:17:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 67479/100000 [20:13:52<5:17:14,  1.71it/s]
Train steps ... :  67%|██████▋   | 67480/100000 [20:13:52<5:17:03,  1.71it/s]
Train steps ... :  67%|██████▋   | 67481/100000 [20:13:53<5:16:57,  1.71it/s]
Train steps ... :  67%|██████▋   | 67482/100000 [20:13:53<5:17:12,  1.71it/s]
Train steps ... :  67%|██████▋   | 67483/100000 [20:13:54<5:16:59,  1.71it/s]
Train steps ... :  67%|██████▋   | 67484/100000 [20:13:54<5:17:25,  1.71it/s]
Train steps ... :  67%|██████▋   | 67485/100000 [20:13:55<5:17:53,  1.70it/s]
Train steps ... :  67%|██████▋   | 67486/100000 [20:13:56<5:17:41,  1.71it/s]
Train steps ... :  67%|██████▋   | 67487/100000 [20:13:56<5:17:22,  1.71it/s]
Train steps ... :  67%|██████▋   | 67488/100000 [20:13:57<5:17:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 67489/100000 [20:13:57<5:17:20,  1.71it/s]
Train steps ... :  67%|██████▋   | 67490/100000 [20:13:58<5:17:36,  1.71it/s]
Train steps ... :  67%|██████▋   | 67491/100000 [20:13:59<5:17:16,  1.71it/s]
Train steps ... :  67%|█��████▋   | 67492/100000 [20:13:59<5:17:35,  1.71it/s]
Train steps ... :  67%|██████▋   | 67493/100000 [20:14:00<5:17:23,  1.71it/s]
Train steps ... :  67%|██████▋   | 67494/100000 [20:14:00<5:17:02,  1.71it/s]
Train steps ... :  67%|██████▋   | 67495/100000 [20:14:01<5:17:05,  1.71it/s]
Train steps ... :  67%|██████▋   | 67496/100000 [20:14:02<5:17:07,  1.71it/s]
Train steps ... :  67%|██████▋   | 67497/100000 [20:14:02<5:16:44,  1.71it/s]
Train steps ... :  67%|██████▋   | 67498/100000 [20:14:03<5:16:47,  1.71it/s]
Train steps ... :  67%|██████▋   | 67499/100000 [20:14:03<5:16:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 67500/100000 [20:14:04<5:16:43,  1.71it/s]Step... (67500 / 100000 | Loss: 0.6188970804214478, Learning Rate: 3.2663316582914576e-05)
+
                                                                             
Step... (67500 / 100000 | Loss: 0.8444899320602417, Learning Rate: 3.2663316582914576e-05)
+
Train steps ... :  68%|██████▊   | 67500/100000 [20:14:04<5:16:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 67501/100000 [20:14:04<5:17:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67502/100000 [20:14:05<5:16:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67503/100000 [20:14:06<5:16:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 67504/100000 [20:14:06<5:17:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 67505/100000 [20:14:07<5:16:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 67506/100000 [20:14:07<5:17:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 67507/100000 [20:14:08<5:16:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 67508/100000 [20:14:09<5:16:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67509/100000 [20:14:09<5:16:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 67510/100000 [20:14:10<5:16:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67511/100000 [20:14:10<5:16:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 67512/100000 [20:14:11<5:16:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 67513/100000 [20:14:11<5:16:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 67514/100000 [20:14:12<5:16:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 67515/100000 [20:14:13<5:16:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 67516/100000 [20:14:13<5:16:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 67517/100000 [20:14:14<5:16:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 67518/100000 [20:14:14<5:16:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 67519/100000 [20:14:15<5:16:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67520/100000 [20:14:16<5:16:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67521/100000 [20:14:16<5:16:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67522/100000 [20:14:17<5:17:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 67523/100000 [20:14:17<5:16:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67524/100000 [20:14:18<5:16:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67525/100000 [20:14:18<5:16:29,  1.71it/s]Step... (67525 / 100000 | Loss: 0.6264918446540833, Learning Rate: 3.263819095477387e-05)
+
                                                                             
Step... (67525 / 100000 | Loss: 0.7101939916610718, Learning Rate: 3.263819095477387e-05)
+
Train steps ... :  68%|██████▊   | 67525/100000 [20:14:19<5:16:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 67526/100000 [20:14:19<5:16:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 67527/100000 [20:14:20<5:17:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 67528/100000 [20:14:20<5:16:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 67529/100000 [20:14:21<5:16:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67530/100000 [20:14:21<5:16:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 67531/100000 [20:14:22<5:16:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 67532/100000 [20:14:23<5:16:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67533/100000 [20:14:23<5:16:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67534/100000 [20:14:24<5:16:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 67535/100000 [20:14:24<5:16:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 67536/100000 [20:14:25<5:17:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 67537/100000 [20:14:26<5:17:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67538/100000 [20:14:26<5:16:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 67539/100000 [20:14:27<5:16:58,  1.71it/s]
Train steps ... :  68%|���█████▊   | 67540/100000 [20:14:27<5:16:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 67541/100000 [20:14:28<5:16:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 67542/100000 [20:14:28<5:16:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 67543/100000 [20:14:29<5:16:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 67544/100000 [20:14:30<5:16:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 67545/100000 [20:14:30<5:16:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 67546/100000 [20:14:31<5:16:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67547/100000 [20:14:31<5:16:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 67548/100000 [20:14:32<5:15:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 67549/100000 [20:14:33<5:16:06,  1.71it/s]
Train steps ... :  68%|██████▊   | 67550/100000 [20:14:33<5:16:20,  1.71it/s]Step... (67550 / 100000 | Loss: 1.0744521617889404, Learning Rate: 3.261306532663317e-05)
+
                                                                             
Step... (67550 / 100000 | Loss: 0.658703088760376, Learning Rate: 3.261306532663317e-05)
+
Train steps ... :  68%|██████▊   | 67550/100000 [20:14:33<5:16:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67551/100000 [20:14:34<5:16:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 67552/100000 [20:14:34<5:16:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 67553/100000 [20:14:35<5:16:06,  1.71it/s]
Train steps ... :  68%|██████▊   | 67554/100000 [20:14:35<5:15:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 67555/100000 [20:14:36<5:16:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 67556/100000 [20:14:37<5:16:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 67557/100000 [20:14:37<5:16:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 67558/100000 [20:14:38<5:16:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 67559/100000 [20:14:38<5:16:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 67560/100000 [20:14:39<5:16:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67561/100000 [20:14:40<5:16:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 67562/100000 [20:14:40<5:16:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67563/100000 [20:14:41<5:16:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67564/100000 [20:14:41<5:15:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 67565/100000 [20:14:42<5:16:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67566/100000 [20:14:42<5:16:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67567/100000 [20:14:43<5:16:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67568/100000 [20:14:44<5:16:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 67569/100000 [20:14:44<5:16:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67570/100000 [20:14:45<5:16:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 67571/100000 [20:14:45<5:16:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 67572/100000 [20:14:46<5:15:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 67573/100000 [20:14:47<5:15:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 67574/100000 [20:14:47<5:15:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 67575/100000 [20:14:48<5:15:44,  1.71it/s]Step... (67575 / 100000 | Loss: 0.823255181312561, Learning Rate: 3.2587939698492466e-05)
+
                                                                             
Step... (67575 / 100000 | Loss: 0.5096997022628784, Learning Rate: 3.2587939698492466e-05)
+
Train steps ... :  68%|██████▊   | 67575/100000 [20:14:48<5:15:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67576/100000 [20:14:48<5:15:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 67577/100000 [20:14:49<5:17:00,  1.70it/s]
Train steps ... :  68%|██████▊   | 67578/100000 [20:14:49<5:16:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 67579/100000 [20:14:50<5:16:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 67580/100000 [20:14:51<5:16:26,  1.71it/s]
Train steps ... :  68%|██████▊   | 67581/100000 [20:14:51<5:16:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 67582/100000 [20:14:52<5:16:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67583/100000 [20:14:52<5:16:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 67584/100000 [20:14:53<5:15:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 67585/100000 [20:14:54<5:16:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67586/100000 [20:14:54<5:16:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 67587/100000 [20:14:55<5:16:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 67588/100000 [20:14:55<5:16:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67589/100000 [20:14:56<5:15:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 67590/100000 [20:14:57<5:16:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 67591/100000 [20:14:57<5:16:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67592/100000 [20:14:58<5:15:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 67593/100000 [20:14:58<5:15:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67594/100000 [20:14:59<5:16:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 67595/100000 [20:14:59<5:15:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 67596/100000 [20:15:00<5:16:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 67597/100000 [20:15:01<5:15:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 67598/100000 [20:15:01<5:15:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 67599/100000 [20:15:02<5:15:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 67600/100000 [20:15:02<5:15:54,  1.71it/s]Step... (67600 / 100000 | Loss: 0.6035763025283813, Learning Rate: 3.256281407035176e-05)
+
                                                                             
Step... (67600 / 100000 | Loss: 0.7054469585418701, Learning Rate: 3.256281407035176e-05)
+
Train steps ... :  68%|██████▊   | 67600/100000 [20:15:03<5:15:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 67601/100000 [20:15:03<5:16:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 67602/100000 [20:15:04<5:15:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 67603/100000 [20:15:04<5:15:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 67604/100000 [20:15:05<5:15:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 67605/100000 [20:15:05<5:15:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67606/100000 [20:15:06<5:15:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 67607/100000 [20:15:06<5:15:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 67608/100000 [20:15:07<5:15:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 67609/100000 [20:15:08<5:15:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 67610/100000 [20:15:08<5:16:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 67611/100000 [20:15:09<5:15:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 67612/100000 [20:15:09<5:16:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 67613/100000 [20:15:10<5:15:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 67614/100000 [20:15:11<5:15:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 67615/100000 [20:15:11<5:15:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 67616/100000 [20:15:12<5:15:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67617/100000 [20:15:12<5:15:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67618/100000 [20:15:13<5:15:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 67619/100000 [20:15:13<5:15:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 67620/100000 [20:15:14<5:15:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 67621/100000 [20:15:15<5:15:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 67622/100000 [20:15:15<5:15:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 67623/100000 [20:15:16<5:15:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 67624/100000 [20:15:16<5:15:26,  1.71it/s]
Train steps ... :  68%|██████▊   | 67625/100000 [20:15:17<5:15:34,  1.71it/s]Step... (67625 / 100000 | Loss: 0.8694992065429688, Learning Rate: 3.253768844221106e-05)
+
                                                                             
Step... (67625 / 100000 | Loss: 0.5506278872489929, Learning Rate: 3.253768844221106e-05)
+
Train steps ... :  68%|██████▊   | 67625/100000 [20:15:17<5:15:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 67626/100000 [20:15:18<5:15:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67627/100000 [20:15:18<5:15:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67628/100000 [20:15:19<5:16:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 67629/100000 [20:15:19<5:16:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 67630/100000 [20:15:20<5:15:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 67631/100000 [20:15:20<5:16:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 67632/100000 [20:15:21<5:15:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 67633/100000 [20:15:22<5:15:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67634/100000 [20:15:22<5:15:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 67635/100000 [20:15:23<5:15:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67636/100000 [20:15:23<5:15:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67637/100000 [20:15:24<5:15:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 67638/100000 [20:15:25<5:15:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67639/100000 [20:15:25<5:15:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 67640/100000 [20:15:26<5:15:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 67641/100000 [20:15:26<5:16:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 67642/100000 [20:15:27<5:15:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 67643/100000 [20:15:28<5:15:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 67644/100000 [20:15:28<5:15:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67645/100000 [20:15:29<5:15:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67646/100000 [20:15:29<5:15:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 67647/100000 [20:15:30<5:15:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 67648/100000 [20:15:30<5:15:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 67649/100000 [20:15:31<5:15:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67650/100000 [20:15:32<5:15:25,  1.71it/s]Step... (67650 / 100000 | Loss: 0.6822899580001831, Learning Rate: 3.251256281407035e-05)
+
                                                                             
Step... (67650 / 100000 | Loss: 0.5741181373596191, Learning Rate: 3.251256281407035e-05)
+
Train steps ... :  68%|██████▊   | 67650/100000 [20:15:32<5:15:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67651/100000 [20:15:32<5:15:26,  1.71it/s]
Train steps ... :  68%|██████▊   | 67652/100000 [20:15:33<5:15:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 67653/100000 [20:15:33<5:15:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67654/100000 [20:15:34<5:15:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 67655/100000 [20:15:35<5:15:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67656/100000 [20:15:35<5:15:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67657/100000 [20:15:36<5:15:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67658/100000 [20:15:36<5:15:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67659/100000 [20:15:37<5:15:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67660/100000 [20:15:37<5:15:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 67661/100000 [20:15:38<5:15:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 67662/100000 [20:15:39<5:15:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 67663/100000 [20:15:39<5:15:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 67664/100000 [20:15:40<5:15:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 67665/100000 [20:15:40<5:15:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67666/100000 [20:15:41<5:15:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 67667/100000 [20:15:42<5:15:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67668/100000 [20:15:42<5:15:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 67669/100000 [20:15:43<5:15:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67670/100000 [20:15:43<5:15:21,  1.71it/s]
Train steps ... :  68%|██████▊   | 67671/100000 [20:15:44<5:15:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67672/100000 [20:15:44<5:15:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67673/100000 [20:15:45<5:15:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67674/100000 [20:15:46<5:15:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67675/100000 [20:15:46<5:15:08,  1.71it/s]Step... (67675 / 100000 | Loss: 0.5528346300125122, Learning Rate: 3.2487437185929645e-05)
+
                                                                             
Step... (67675 / 100000 | Loss: 0.6126164197921753, Learning Rate: 3.2487437185929645e-05)
+
Train steps ... :  68%|██████▊   | 67675/100000 [20:15:47<5:15:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 67676/100000 [20:15:47<5:15:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 67677/100000 [20:15:47<5:15:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 67678/100000 [20:15:48<5:15:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 67679/100000 [20:15:49<5:16:29,  1.70it/s]
Train steps ... :  68%|██████▊   | 67680/100000 [20:15:49<5:16:05,  1.70it/s]
Train steps ... :  68%|██████▊   | 67681/100000 [20:15:50<5:15:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67682/100000 [20:15:50<5:15:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 67683/100000 [20:15:51<5:15:26,  1.71it/s]
Train steps ... :  68%|██████▊   | 67684/100000 [20:15:52<5:15:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67685/100000 [20:15:52<5:15:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 67686/100000 [20:15:53<5:15:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67687/100000 [20:15:53<5:15:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67688/100000 [20:15:54<5:15:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 67689/100000 [20:15:54<5:15:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 67690/100000 [20:15:55<5:15:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 67691/100000 [20:15:56<5:15:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 67692/100000 [20:15:56<5:14:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 67693/100000 [20:15:57<5:14:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67694/100000 [20:15:57<5:15:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 67695/100000 [20:15:58<5:16:05,  1.70it/s]
Train steps ... :  68%|██████▊   | 67696/100000 [20:15:59<5:16:01,  1.70it/s]
Train steps ... :  68%|██████▊   | 67697/100000 [20:15:59<5:15:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 67698/100000 [20:16:00<5:15:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 67699/100000 [20:16:00<5:15:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 67700/100000 [20:16:01<5:14:53,  1.71it/s]Step... (67700 / 100000 | Loss: 0.7565504312515259, Learning Rate: 3.246231155778894e-05)
+
                                                                             
Step... (67700 / 100000 | Loss: 0.9109723567962646, Learning Rate: 3.246231155778894e-05)
+
Train steps ... :  68%|██████▊   | 67700/100000 [20:16:01<5:14:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67701/100000 [20:16:01<5:15:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 67702/100000 [20:16:02<5:15:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 67703/100000 [20:16:03<5:15:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 67704/100000 [20:16:03<5:15:02,  1.71it/s]
Train steps ... :  68%|██████▊   | 67705/100000 [20:16:04<5:14:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 67706/100000 [20:16:04<5:15:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 67707/100000 [20:16:05<5:15:26,  1.71it/s]
Train steps ... :  68%|██████▊   | 67708/100000 [20:16:06<5:15:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 67709/100000 [20:16:06<5:14:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 67710/100000 [20:16:07<5:14:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 67711/100000 [20:16:07<5:14:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67712/100000 [20:16:08<5:14:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 67713/100000 [20:16:09<5:14:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 67714/100000 [20:16:09<5:14:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 67715/100000 [20:16:10<5:14:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67716/100000 [20:16:10<5:14:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 67717/100000 [20:16:11<5:15:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 67718/100000 [20:16:11<5:15:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 67719/100000 [20:16:12<5:15:42,  1.70it/s]
Train steps ... :  68%|██████▊   | 67720/100000 [20:16:13<5:14:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 67721/100000 [20:16:13<5:15:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 67722/100000 [20:16:14<5:15:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67723/100000 [20:16:14<5:15:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 67724/100000 [20:16:15<5:14:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 67725/100000 [20:16:16<5:15:04,  1.71it/s]Step... (67725 / 100000 | Loss: 0.9465368390083313, Learning Rate: 3.2437185929648245e-05)
+
                                                                             
Step... (67725 / 100000 | Loss: 0.6724145412445068, Learning Rate: 3.2437185929648245e-05)
+
Train steps ... :  68%|██████▊   | 67725/100000 [20:16:16<5:15:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 67726/100000 [20:16:16<5:15:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67727/100000 [20:16:17<5:15:36,  1.70it/s]
Train steps ... :  68%|██████▊   | 67728/100000 [20:16:17<5:15:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67729/100000 [20:16:18<5:14:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67730/100000 [20:16:18<5:16:02,  1.70it/s]
Train steps ... :  68%|██████▊   | 67731/100000 [20:16:19<5:15:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 67732/100000 [20:16:20<5:15:36,  1.70it/s]
Train steps ... :  68%|██████▊   | 67733/100000 [20:16:20<5:14:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 67734/100000 [20:16:21<5:14:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 67735/100000 [20:16:21<5:14:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 67736/100000 [20:16:22<5:14:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 67737/100000 [20:16:23<5:14:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67738/100000 [20:16:23<5:14:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67739/100000 [20:16:24<5:14:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67740/100000 [20:16:24<5:14:21,  1.71it/s]
Train steps ... :  68%|██████▊   | 67741/100000 [20:16:25<5:14:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 67742/100000 [20:16:25<5:14:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 67743/100000 [20:16:26<5:14:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 67744/100000 [20:16:27<5:14:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 67745/100000 [20:16:27<5:14:07,  1.71it/s]
Train steps ... :  68%|██████▊   | 67746/100000 [20:16:28<5:14:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 67747/100000 [20:16:28<5:14:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67748/100000 [20:16:29<5:14:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67749/100000 [20:16:30<5:14:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 67750/100000 [20:16:30<5:14:24,  1.71it/s]Step... (67750 / 100000 | Loss: 0.7543907165527344, Learning Rate: 3.241206030150754e-05)
+
                                                                             
Step... (67750 / 100000 | Loss: 0.6887023448944092, Learning Rate: 3.241206030150754e-05)
+
Train steps ... :  68%|██████▊   | 67750/100000 [20:16:31<5:14:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 67751/100000 [20:16:31<5:14:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 67752/100000 [20:16:31<5:14:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67753/100000 [20:16:32<5:14:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 67754/100000 [20:16:33<5:14:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 67755/100000 [20:16:33<5:14:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 67756/100000 [20:16:34<5:14:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67757/100000 [20:16:34<5:14:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 67758/100000 [20:16:35<5:14:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 67759/100000 [20:16:35<5:14:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 67760/100000 [20:16:36<5:14:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 67761/100000 [20:16:37<5:15:15,  1.70it/s]
Train steps ... :  68%|██████▊   | 67762/100000 [20:16:37<5:15:36,  1.70it/s]
Train steps ... :  68%|██████▊   | 67763/100000 [20:16:38<5:15:58,  1.70it/s]
Train steps ... :  68%|██████▊   | 67764/100000 [20:16:38<5:14:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 67765/100000 [20:16:39<5:14:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 67766/100000 [20:16:40<5:14:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 67767/100000 [20:16:40<5:14:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 67768/100000 [20:16:41<5:14:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 67769/100000 [20:16:41<5:15:04,  1.70it/s]
Train steps ... :  68%|██████▊   | 67770/100000 [20:16:42<5:14:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 67771/100000 [20:16:42<5:14:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67772/100000 [20:16:43<5:14:21,  1.71it/s]
Train steps ... :  68%|██████▊   | 67773/100000 [20:16:44<5:14:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 67774/100000 [20:16:44<5:13:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 67775/100000 [20:16:45<5:14:19,  1.71it/s]Step... (67775 / 100000 | Loss: 0.7391414046287537, Learning Rate: 3.238693467336684e-05)
+
                                                                             
Step... (67775 / 100000 | Loss: 0.8185708522796631, Learning Rate: 3.238693467336684e-05)
+
Train steps ... :  68%|██████▊   | 67775/100000 [20:16:45<5:14:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 67776/100000 [20:16:45<5:14:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67777/100000 [20:16:46<5:14:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 67778/100000 [20:16:47<5:14:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67779/100000 [20:16:47<5:14:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67780/100000 [20:16:48<5:14:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67781/100000 [20:16:48<5:14:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 67782/100000 [20:16:49<5:14:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 67783/100000 [20:16:49<5:14:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 67784/100000 [20:16:50<5:14:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 67785/100000 [20:16:51<5:14:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 67786/100000 [20:16:51<5:14:07,  1.71it/s]
Train steps ... :  68%|██████▊   | 67787/100000 [20:16:52<5:14:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67788/100000 [20:16:52<5:14:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 67789/100000 [20:16:53<5:14:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 67790/100000 [20:16:54<5:14:06,  1.71it/s]
Train steps ... :  68%|██████▊   | 67791/100000 [20:16:54<5:14:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67792/100000 [20:16:55<5:13:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 67793/100000 [20:16:55<5:13:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67794/100000 [20:16:56<5:14:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 67795/100000 [20:16:57<5:14:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 67796/100000 [20:16:57<5:14:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 67797/100000 [20:16:58<5:14:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 67798/100000 [20:16:58<5:14:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 67799/100000 [20:16:59<5:14:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 67800/100000 [20:16:59<5:14:04,  1.71it/s]Step... (67800 / 100000 | Loss: 0.8376418948173523, Learning Rate: 3.2361809045226135e-05)
+
                                                                             
Step... (67800 / 100000 | Loss: 0.554984986782074, Learning Rate: 3.2361809045226135e-05)
+
Train steps ... :  68%|██████▊   | 67800/100000 [20:17:00<5:14:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 67801/100000 [20:17:00<5:14:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67802/100000 [20:17:01<5:13:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 67803/100000 [20:17:01<5:14:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 67804/100000 [20:17:02<5:13:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 67805/100000 [20:17:02<5:13:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 67806/100000 [20:17:03<5:13:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 67807/100000 [20:17:04<5:13:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67808/100000 [20:17:04<5:13:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 67809/100000 [20:17:05<5:13:26,  1.71it/s]
Train steps ... :  68%|██████▊   | 67810/100000 [20:17:05<5:13:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 67811/100000 [20:17:06<5:14:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 67812/100000 [20:17:06<5:13:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67813/100000 [20:17:07<5:13:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 67814/100000 [20:17:08<5:13:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67815/100000 [20:17:08<5:13:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 67816/100000 [20:17:09<5:14:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 67817/100000 [20:17:09<5:14:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67818/100000 [20:17:10<5:14:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67819/100000 [20:17:11<5:14:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 67820/100000 [20:17:11<5:14:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 67821/100000 [20:17:12<5:14:07,  1.71it/s]
Train steps ... :  68%|██████▊   | 67822/100000 [20:17:12<5:13:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67823/100000 [20:17:13<5:13:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67824/100000 [20:17:13<5:13:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 67825/100000 [20:17:14<5:13:49,  1.71it/s]Step... (67825 / 100000 | Loss: 0.7055023908615112, Learning Rate: 3.2336683417085425e-05)
+
                                                                             
Step... (67825 / 100000 | Loss: 0.7760103344917297, Learning Rate: 3.2336683417085425e-05)
+
Train steps ... :  68%|██████▊   | 67825/100000 [20:17:14<5:13:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 67826/100000 [20:17:15<5:14:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 67827/100000 [20:17:15<5:13:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67828/100000 [20:17:16<5:13:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 67829/100000 [20:17:16<5:13:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 67830/100000 [20:17:17<5:13:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67831/100000 [20:17:18<5:13:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 67832/100000 [20:17:18<5:13:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 67833/100000 [20:17:19<5:13:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 67834/100000 [20:17:19<5:13:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 67835/100000 [20:17:20<5:13:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67836/100000 [20:17:21<5:13:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 67837/100000 [20:17:21<5:13:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67838/100000 [20:17:22<5:13:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67839/100000 [20:17:22<5:13:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 67840/100000 [20:17:23<5:13:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 67841/100000 [20:17:23<5:13:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 67842/100000 [20:17:24<5:13:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 67843/100000 [20:17:25<5:12:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 67844/100000 [20:17:25<5:13:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 67845/100000 [20:17:26<5:13:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67846/100000 [20:17:26<5:13:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67847/100000 [20:17:27<5:13:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 67848/100000 [20:17:28<5:13:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 67849/100000 [20:17:28<5:13:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67850/100000 [20:17:29<5:12:46,  1.71it/s]Step... (67850 / 100000 | Loss: 0.8447110056877136, Learning Rate: 3.231155778894472e-05)
+
                                                                             
Step... (67850 / 100000 | Loss: 0.8636996746063232, Learning Rate: 3.231155778894472e-05)
+
Train steps ... :  68%|██████▊   | 67850/100000 [20:17:29<5:12:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 67851/100000 [20:17:29<5:13:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 67852/100000 [20:17:30<5:13:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 67853/100000 [20:17:30<5:13:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 67854/100000 [20:17:31<5:13:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67855/100000 [20:17:32<5:13:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67856/100000 [20:17:32<5:13:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 67857/100000 [20:17:33<5:12:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 67858/100000 [20:17:33<5:12:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 67859/100000 [20:17:34<5:12:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 67860/100000 [20:17:35<5:12:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67861/100000 [20:17:35<5:12:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67862/100000 [20:17:36<5:13:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 67863/100000 [20:17:36<5:13:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 67864/100000 [20:17:37<5:13:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67865/100000 [20:17:37<5:13:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67866/100000 [20:17:38<5:13:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 67867/100000 [20:17:39<5:14:31,  1.70it/s]
Train steps ... :  68%|██████▊   | 67868/100000 [20:17:39<5:13:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 67869/100000 [20:17:40<5:13:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 67870/100000 [20:17:40<5:13:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67871/100000 [20:17:41<5:13:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 67872/100000 [20:17:42<5:13:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 67873/100000 [20:17:42<5:13:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67874/100000 [20:17:43<5:12:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 67875/100000 [20:17:43<5:13:04,  1.71it/s]Step... (67875 / 100000 | Loss: 0.7549425363540649, Learning Rate: 3.228643216080402e-05)
+
                                                                             
Step... (67875 / 100000 | Loss: 0.6455733776092529, Learning Rate: 3.228643216080402e-05)
+
Train steps ... :  68%|██████▊   | 67875/100000 [20:17:44<5:13:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 67876/100000 [20:17:44<5:13:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 67877/100000 [20:17:44<5:13:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67878/100000 [20:17:45<5:13:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 67879/100000 [20:17:46<5:13:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 67880/100000 [20:17:46<5:13:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 67881/100000 [20:17:47<5:13:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 67882/100000 [20:17:47<5:13:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 67883/100000 [20:17:48<5:13:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67884/100000 [20:17:49<5:13:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 67885/100000 [20:17:49<5:14:27,  1.70it/s]
Train steps ... :  68%|██████▊   | 67886/100000 [20:17:50<5:13:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 67887/100000 [20:17:50<5:12:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 67888/100000 [20:17:51<5:12:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 67889/100000 [20:17:52<5:12:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 67890/100000 [20:17:52<5:13:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67891/100000 [20:17:53<5:12:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67892/100000 [20:17:53<5:12:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 67893/100000 [20:17:54<5:12:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 67894/100000 [20:17:54<5:12:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 67895/100000 [20:17:55<5:12:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67896/100000 [20:17:56<5:12:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 67897/100000 [20:17:56<5:12:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 67898/100000 [20:17:57<5:12:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 67899/100000 [20:17:57<5:12:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67900/100000 [20:17:58<5:12:23,  1.71it/s]Step... (67900 / 100000 | Loss: 0.6877211928367615, Learning Rate: 3.2261306532663315e-05)
+
                                                                             
Step... (67900 / 100000 | Loss: 0.6983323097229004, Learning Rate: 3.2261306532663315e-05)
+
Train steps ... :  68%|██████▊   | 67900/100000 [20:17:58<5:12:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 67901/100000 [20:17:59<5:12:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 67902/100000 [20:17:59<5:13:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 67903/100000 [20:18:00<5:12:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 67904/100000 [20:18:00<5:13:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 67905/100000 [20:18:01<5:12:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 67906/100000 [20:18:01<5:12:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 67907/100000 [20:18:02<5:12:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67908/100000 [20:18:03<5:12:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67909/100000 [20:18:03<5:12:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 67910/100000 [20:18:04<5:12:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 67911/100000 [20:18:04<5:12:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67912/100000 [20:18:05<5:12:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 67913/100000 [20:18:06<5:12:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 67914/100000 [20:18:06<5:12:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 67915/100000 [20:18:07<5:12:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 67916/100000 [20:18:07<5:12:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 67917/100000 [20:18:08<5:12:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 67918/100000 [20:18:08<5:12:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 67919/100000 [20:18:09<5:12:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 67920/100000 [20:18:10<5:12:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 67921/100000 [20:18:10<5:12:26,  1.71it/s]
Train steps ... :  68%|██████▊   | 67922/100000 [20:18:11<5:12:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 67923/100000 [20:18:11<5:12:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 67924/100000 [20:18:12<5:12:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67925/100000 [20:18:13<5:13:03,  1.71it/s]Step... (67925 / 100000 | Loss: 0.8516141176223755, Learning Rate: 3.223618090452262e-05)
+
                                                                             
Step... (67925 / 100000 | Loss: 0.8062955141067505, Learning Rate: 3.223618090452262e-05)
+
Train steps ... :  68%|██████▊   | 67925/100000 [20:18:13<5:13:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 67926/100000 [20:18:13<5:13:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 67927/100000 [20:18:14<5:12:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 67928/100000 [20:18:14<5:12:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67929/100000 [20:18:15<5:12:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 67930/100000 [20:18:15<5:12:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67931/100000 [20:18:16<5:12:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 67932/100000 [20:18:17<5:12:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67933/100000 [20:18:17<5:13:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67934/100000 [20:18:18<5:13:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 67935/100000 [20:18:18<5:13:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 67936/100000 [20:18:19<5:13:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 67937/100000 [20:18:20<5:13:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67938/100000 [20:18:20<5:12:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 67939/100000 [20:18:21<5:12:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 67940/100000 [20:18:21<5:12:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 67941/100000 [20:18:22<5:12:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 67942/100000 [20:18:23<5:12:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 67943/100000 [20:18:23<5:12:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67944/100000 [20:18:24<5:12:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 67945/100000 [20:18:24<5:12:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 67946/100000 [20:18:25<5:12:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 67947/100000 [20:18:25<5:12:21,  1.71it/s]
Train steps ... :  68%|██████▊   | 67948/100000 [20:18:26<5:12:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67949/100000 [20:18:27<5:12:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 67950/100000 [20:18:27<5:12:31,  1.71it/s]Step... (67950 / 100000 | Loss: 0.6542137265205383, Learning Rate: 3.2211055276381915e-05)
+
                                                                             
Step... (67950 / 100000 | Loss: 0.8228844404220581, Learning Rate: 3.2211055276381915e-05)
+
Train steps ... :  68%|██████▊   | 67950/100000 [20:18:28<5:12:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67951/100000 [20:18:28<5:12:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 67952/100000 [20:18:28<5:12:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67953/100000 [20:18:29<5:12:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 67954/100000 [20:18:30<5:12:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 67955/100000 [20:18:30<5:12:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67956/100000 [20:18:31<5:12:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 67957/100000 [20:18:31<5:12:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 67958/100000 [20:18:32<5:12:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 67959/100000 [20:18:32<5:12:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 67960/100000 [20:18:33<5:12:06,  1.71it/s]
Train steps ... :  68%|██████▊   | 67961/100000 [20:18:34<5:12:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 67962/100000 [20:18:34<5:13:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 67963/100000 [20:18:35<5:12:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 67964/100000 [20:18:35<5:12:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 67965/100000 [20:18:36<5:12:07,  1.71it/s]
Train steps ... :  68%|██████▊   | 67966/100000 [20:18:37<5:12:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67967/100000 [20:18:37<5:12:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 67968/100000 [20:18:38<5:12:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 67969/100000 [20:18:38<5:12:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 67970/100000 [20:18:39<5:12:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 67971/100000 [20:18:39<5:11:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 67972/100000 [20:18:40<5:12:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67973/100000 [20:18:41<5:12:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 67974/100000 [20:18:41<5:12:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67975/100000 [20:18:42<5:12:48,  1.71it/s]Step... (67975 / 100000 | Loss: 0.8738080263137817, Learning Rate: 3.218592964824121e-05)
+
                                                                             
Step... (67975 / 100000 | Loss: 0.8517788648605347, Learning Rate: 3.218592964824121e-05)
+
Train steps ... :  68%|██████▊   | 67975/100000 [20:18:42<5:12:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67976/100000 [20:18:42<5:12:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 67977/100000 [20:18:43<5:12:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 67978/100000 [20:18:44<5:12:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67979/100000 [20:18:44<5:12:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 67980/100000 [20:18:45<5:12:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 67981/100000 [20:18:45<5:12:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 67982/100000 [20:18:46<5:12:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 67983/100000 [20:18:46<5:12:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 67984/100000 [20:18:47<5:12:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 67985/100000 [20:18:48<5:12:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 67986/100000 [20:18:48<5:11:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 67987/100000 [20:18:49<5:12:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 67988/100000 [20:18:49<5:11:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 67989/100000 [20:18:50<5:11:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 67990/100000 [20:18:51<5:12:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 67991/100000 [20:18:51<5:12:02,  1.71it/s]
Train steps ... :  68%|██████▊   | 67992/100000 [20:18:52<5:11:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 67993/100000 [20:18:52<5:11:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 67994/100000 [20:18:53<5:11:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 67995/100000 [20:18:54<5:11:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 67996/100000 [20:18:54<5:11:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 67997/100000 [20:18:55<5:11:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 67998/100000 [20:18:55<5:11:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 67999/100000 [20:18:56<5:11:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68000/100000 [20:18:56<5:11:57,  1.71it/s]Step... (68000 / 100000 | Loss: 0.5971240997314453, Learning Rate: 3.21608040201005e-05)
+
                                                                             
Step... (68000 / 100000 | Loss: 0.5510776042938232, Learning Rate: 3.21608040201005e-05)
+
Train steps ... :  68%|██████▊   | 68000/100000 [20:18:57<5:11:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 68001/100000 [20:18:57<5:12:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 68002/100000 [20:18:58<5:12:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68003/100000 [20:18:58<5:12:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 68004/100000 [20:18:59<5:11:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 68005/100000 [20:18:59<5:11:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 68006/100000 [20:19:00<5:12:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 68007/100000 [20:19:01<5:12:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 68008/100000 [20:19:01<5:11:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68009/100000 [20:19:02<5:11:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68010/100000 [20:19:02<5:11:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68011/100000 [20:19:03<5:11:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68012/100000 [20:19:03<5:11:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 68013/100000 [20:19:04<5:12:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 68014/100000 [20:19:05<5:11:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 68015/100000 [20:19:05<5:11:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68016/100000 [20:19:06<5:11:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 68017/100000 [20:19:06<5:11:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 68018/100000 [20:19:07<5:11:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 68019/100000 [20:19:08<5:11:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 68020/100000 [20:19:08<5:11:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68021/100000 [20:19:09<5:11:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 68022/100000 [20:19:09<5:12:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 68023/100000 [20:19:10<5:11:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 68024/100000 [20:19:10<5:11:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68025/100000 [20:19:11<5:11:44,  1.71it/s]Step... (68025 / 100000 | Loss: 0.6273306012153625, Learning Rate: 3.21356783919598e-05)
+
                                                                             
Step... (68025 / 100000 | Loss: 0.6665366291999817, Learning Rate: 3.21356783919598e-05)
+
Train steps ... :  68%|██████▊   | 68025/100000 [20:19:11<5:11:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 68026/100000 [20:19:12<5:11:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68027/100000 [20:19:12<5:11:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 68028/100000 [20:19:13<5:11:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 68029/100000 [20:19:13<5:11:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 68030/100000 [20:19:14<5:11:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 68031/100000 [20:19:15<5:11:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68032/100000 [20:19:15<5:11:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 68033/100000 [20:19:16<5:11:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 68034/100000 [20:19:16<5:11:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 68035/100000 [20:19:17<5:11:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68036/100000 [20:19:17<5:11:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68037/100000 [20:19:18<5:12:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 68038/100000 [20:19:19<5:12:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 68039/100000 [20:19:19<5:11:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68040/100000 [20:19:20<5:11:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 68041/100000 [20:19:20<5:11:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 68042/100000 [20:19:21<5:12:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68043/100000 [20:19:22<5:12:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 68044/100000 [20:19:22<5:11:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 68045/100000 [20:19:23<5:11:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 68046/100000 [20:19:23<5:11:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 68047/100000 [20:19:24<5:11:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 68048/100000 [20:19:25<5:11:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 68049/100000 [20:19:25<5:11:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 68050/100000 [20:19:26<5:11:18,  1.71it/s]Step... (68050 / 100000 | Loss: 0.6862537860870361, Learning Rate: 3.2110552763819095e-05)
+
                                                                             
Step... (68050 / 100000 | Loss: 0.7955242395401001, Learning Rate: 3.2110552763819095e-05)
+
Train steps ... :  68%|██████▊   | 68050/100000 [20:19:26<5:11:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 68051/100000 [20:19:26<5:11:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 68052/100000 [20:19:27<5:11:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68053/100000 [20:19:27<5:11:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 68054/100000 [20:19:28<5:11:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 68055/100000 [20:19:29<5:11:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 68056/100000 [20:19:29<5:11:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 68057/100000 [20:19:30<5:11:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68058/100000 [20:19:30<5:11:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 68059/100000 [20:19:31<5:11:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68060/100000 [20:19:32<5:11:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 68061/100000 [20:19:32<5:11:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 68062/100000 [20:19:33<5:11:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 68063/100000 [20:19:33<5:12:02,  1.71it/s]
Train steps ... :  68%|██████▊   | 68064/100000 [20:19:34<5:12:06,  1.71it/s]
Train steps ... :  68%|██████▊   | 68065/100000 [20:19:34<5:11:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 68066/100000 [20:19:35<5:11:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 68067/100000 [20:19:36<5:11:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 68068/100000 [20:19:36<5:11:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 68069/100000 [20:19:37<5:11:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 68070/100000 [20:19:37<5:11:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68071/100000 [20:19:38<5:11:02,  1.71it/s]
Train steps ... :  68%|██████▊   | 68072/100000 [20:19:39<5:11:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 68073/100000 [20:19:39<5:11:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68074/100000 [20:19:40<5:12:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 68075/100000 [20:19:40<5:12:14,  1.70it/s]Step... (68075 / 100000 | Loss: 0.6148264408111572, Learning Rate: 3.208542713567839e-05)
+
                                                                             
Step... (68075 / 100000 | Loss: 0.6805998682975769, Learning Rate: 3.208542713567839e-05)
+
Train steps ... :  68%|██████▊   | 68075/100000 [20:19:41<5:12:14,  1.70it/s]
Train steps ... :  68%|██████▊   | 68076/100000 [20:19:41<5:12:05,  1.70it/s]
Train steps ... :  68%|██████▊   | 68077/100000 [20:19:41<5:11:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 68078/100000 [20:19:42<5:11:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 68079/100000 [20:19:43<5:11:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 68080/100000 [20:19:43<5:10:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 68081/100000 [20:19:44<5:10:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68082/100000 [20:19:44<5:10:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 68083/100000 [20:19:45<5:10:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68084/100000 [20:19:46<5:10:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68085/100000 [20:19:46<5:10:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 68086/100000 [20:19:47<5:10:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68087/100000 [20:19:47<5:11:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 68088/100000 [20:19:48<5:11:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68089/100000 [20:19:49<5:11:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 68090/100000 [20:19:49<5:11:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68091/100000 [20:19:50<5:11:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68092/100000 [20:19:50<5:11:55,  1.70it/s]
Train steps ... :  68%|██████▊   | 68093/100000 [20:19:51<5:11:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68094/100000 [20:19:51<5:11:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68095/100000 [20:19:52<5:10:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 68096/100000 [20:19:53<5:11:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68097/100000 [20:19:53<5:11:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 68098/100000 [20:19:54<5:10:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 68099/100000 [20:19:54<5:11:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 68100/100000 [20:19:55<5:11:07,  1.71it/s]Step... (68100 / 100000 | Loss: 1.1110734939575195, Learning Rate: 3.206030150753769e-05)
+
                                                                             
Step... (68100 / 100000 | Loss: 0.6842250823974609, Learning Rate: 3.206030150753769e-05)
+
Train steps ... :  68%|██████▊   | 68100/100000 [20:19:55<5:11:07,  1.71it/s]
Train steps ... :  68%|██████▊   | 68101/100000 [20:19:56<5:11:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 68102/100000 [20:19:56<5:10:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 68103/100000 [20:19:57<5:10:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 68104/100000 [20:19:57<5:10:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68105/100000 [20:19:58<5:10:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68106/100000 [20:19:58<5:10:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 68107/100000 [20:19:59<5:10:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 68108/100000 [20:20:00<5:10:26,  1.71it/s]
Train steps ... :  68%|██████▊   | 68109/100000 [20:20:00<5:10:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 68110/100000 [20:20:01<5:10:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 68111/100000 [20:20:01<5:10:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 68112/100000 [20:20:02<5:10:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68113/100000 [20:20:03<5:10:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68114/100000 [20:20:03<5:10:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 68115/100000 [20:20:04<5:10:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 68116/100000 [20:20:04<5:10:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68117/100000 [20:20:05<5:10:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68118/100000 [20:20:05<5:10:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 68119/100000 [20:20:06<5:10:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 68120/100000 [20:20:07<5:11:02,  1.71it/s]
Train steps ... :  68%|██████▊   | 68121/100000 [20:20:07<5:11:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 68122/100000 [20:20:08<5:10:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68123/100000 [20:20:08<5:10:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 68124/100000 [20:20:09<5:11:06,  1.71it/s]
Train steps ... :  68%|██████▊   | 68125/100000 [20:20:10<5:11:05,  1.71it/s]Step... (68125 / 100000 | Loss: 0.5508645176887512, Learning Rate: 3.203517587939699e-05)
+
                                                                             
Step... (68125 / 100000 | Loss: 1.1313889026641846, Learning Rate: 3.203517587939699e-05)
+
Train steps ... :  68%|██████▊   | 68125/100000 [20:20:10<5:11:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68126/100000 [20:20:10<5:11:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68127/100000 [20:20:11<5:11:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 68128/100000 [20:20:11<5:10:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 68129/100000 [20:20:12<5:10:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 68130/100000 [20:20:12<5:10:21,  1.71it/s]
Train steps ... :  68%|██████▊   | 68131/100000 [20:20:13<5:10:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 68132/100000 [20:20:14<5:10:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 68133/100000 [20:20:14<5:10:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 68134/100000 [20:20:15<5:10:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 68135/100000 [20:20:15<5:10:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 68136/100000 [20:20:16<5:10:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 68137/100000 [20:20:17<5:10:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 68138/100000 [20:20:17<5:10:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 68139/100000 [20:20:18<5:10:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 68140/100000 [20:20:18<5:11:06,  1.71it/s]
Train steps ... :  68%|██████▊   | 68141/100000 [20:20:19<5:11:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68142/100000 [20:20:20<5:10:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68143/100000 [20:20:20<5:10:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 68144/100000 [20:20:21<5:10:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68145/100000 [20:20:21<5:10:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 68146/100000 [20:20:22<5:10:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 68147/100000 [20:20:22<5:10:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 68148/100000 [20:20:23<5:10:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 68149/100000 [20:20:24<5:10:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68150/100000 [20:20:24<5:10:46,  1.71it/s]Step... (68150 / 100000 | Loss: 0.7484922409057617, Learning Rate: 3.201005025125629e-05)
+
                                                                             
Step... (68150 / 100000 | Loss: 0.6970832347869873, Learning Rate: 3.201005025125629e-05)
+
Train steps ... :  68%|██████▊   | 68150/100000 [20:20:25<5:10:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68151/100000 [20:20:25<5:10:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 68152/100000 [20:20:25<5:10:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 68153/100000 [20:20:26<5:10:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 68154/100000 [20:20:27<5:10:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 68155/100000 [20:20:27<5:10:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68156/100000 [20:20:28<5:10:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 68157/100000 [20:20:28<5:10:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 68158/100000 [20:20:29<5:10:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 68159/100000 [20:20:29<5:10:21,  1.71it/s]
Train steps ... :  68%|██████▊   | 68160/100000 [20:20:30<5:10:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 68161/100000 [20:20:31<5:10:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 68162/100000 [20:20:31<5:10:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 68163/100000 [20:20:32<5:10:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 68164/100000 [20:20:32<5:10:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68165/100000 [20:20:33<5:10:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 68166/100000 [20:20:34<5:10:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 68167/100000 [20:20:34<5:10:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 68168/100000 [20:20:35<5:10:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 68169/100000 [20:20:35<5:10:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68170/100000 [20:20:36<5:11:16,  1.70it/s]
Train steps ... :  68%|██████▊   | 68171/100000 [20:20:36<5:10:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 68172/100000 [20:20:37<5:10:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68173/100000 [20:20:38<5:10:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 68174/100000 [20:20:38<5:10:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 68175/100000 [20:20:39<5:11:39,  1.70it/s]Step... (68175 / 100000 | Loss: 0.747868001461029, Learning Rate: 3.198492462311558e-05)
+
                                                                             
Step... (68175 / 100000 | Loss: 1.0578491687774658, Learning Rate: 3.198492462311558e-05)
+
Train steps ... :  68%|██████▊   | 68175/100000 [20:20:39<5:11:39,  1.70it/s]
Train steps ... :  68%|██████▊   | 68176/100000 [20:20:39<5:10:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 68177/100000 [20:20:40<5:10:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 68178/100000 [20:20:41<5:11:41,  1.70it/s]
Train steps ... :  68%|██████▊   | 68179/100000 [20:20:41<5:10:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 68180/100000 [20:20:42<5:10:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 68181/100000 [20:20:42<5:10:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 68182/100000 [20:20:43<5:10:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68183/100000 [20:20:44<5:10:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 68184/100000 [20:20:44<5:10:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 68185/100000 [20:20:45<5:10:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 68186/100000 [20:20:45<5:10:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 68187/100000 [20:20:46<5:10:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 68188/100000 [20:20:46<5:10:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 68189/100000 [20:20:47<5:10:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 68190/100000 [20:20:48<5:10:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68191/100000 [20:20:48<5:10:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68192/100000 [20:20:49<5:10:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 68193/100000 [20:20:49<5:10:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 68194/100000 [20:20:50<5:10:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 68195/100000 [20:20:51<5:10:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68196/100000 [20:20:51<5:10:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 68197/100000 [20:20:52<5:10:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 68198/100000 [20:20:52<5:10:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68199/100000 [20:20:53<5:10:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 68200/100000 [20:20:53<5:10:14,  1.71it/s]Step... (68200 / 100000 | Loss: 0.8096099495887756, Learning Rate: 3.1959798994974875e-05)
+
                                                                             
Step... (68200 / 100000 | Loss: 0.6709873676300049, Learning Rate: 3.1959798994974875e-05)
+
Train steps ... :  68%|██████▊   | 68200/100000 [20:20:54<5:10:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 68201/100000 [20:20:54<5:09:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 68202/100000 [20:20:55<5:10:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 68203/100000 [20:20:55<5:10:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68204/100000 [20:20:56<5:10:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 68205/100000 [20:20:56<5:10:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 68206/100000 [20:20:57<5:10:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 68207/100000 [20:20:58<5:10:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 68208/100000 [20:20:58<5:10:46,  1.70it/s]
Train steps ... :  68%|██████▊   | 68209/100000 [20:20:59<5:09:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68210/100000 [20:20:59<5:10:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 68211/100000 [20:21:00<5:10:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68212/100000 [20:21:00<5:10:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68213/100000 [20:21:01<5:10:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68214/100000 [20:21:02<5:10:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 68215/100000 [20:21:02<5:10:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 68216/100000 [20:21:03<5:10:21,  1.71it/s]
Train steps ... :  68%|██████▊   | 68217/100000 [20:21:03<5:10:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 68218/100000 [20:21:04<5:10:07,  1.71it/s]
Train steps ... :  68%|██████▊   | 68219/100000 [20:21:05<5:09:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 68220/100000 [20:21:05<5:09:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 68221/100000 [20:21:06<5:10:02,  1.71it/s]
Train steps ... :  68%|██████▊   | 68222/100000 [20:21:06<5:09:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 68223/100000 [20:21:07<5:10:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 68224/100000 [20:21:08<5:10:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 68225/100000 [20:21:08<5:10:14,  1.71it/s]Step... (68225 / 100000 | Loss: 0.6230907440185547, Learning Rate: 3.193467336683417e-05)
+
                                                                             
Step... (68225 / 100000 | Loss: 0.6040763854980469, Learning Rate: 3.193467336683417e-05)
+
Train steps ... :  68%|██████▊   | 68225/100000 [20:21:08<5:10:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 68226/100000 [20:21:09<5:10:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 68227/100000 [20:21:09<5:09:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 68228/100000 [20:21:10<5:10:06,  1.71it/s]
Train steps ... :  68%|██████▊   | 68229/100000 [20:21:10<5:10:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 68230/100000 [20:21:11<5:10:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 68231/100000 [20:21:12<5:10:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 68232/100000 [20:21:12<5:09:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68233/100000 [20:21:13<5:09:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 68234/100000 [20:21:13<5:09:43,  1.71it/s]
Train steps ... :  68%|██████▊   | 68235/100000 [20:21:14<5:09:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 68236/100000 [20:21:15<5:10:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 68237/100000 [20:21:15<5:10:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68238/100000 [20:21:16<5:09:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 68239/100000 [20:21:16<5:09:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68240/100000 [20:21:17<5:09:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 68241/100000 [20:21:17<5:09:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 68242/100000 [20:21:18<5:09:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 68243/100000 [20:21:19<5:10:35,  1.70it/s]
Train steps ... :  68%|██████▊   | 68244/100000 [20:21:19<5:09:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 68245/100000 [20:21:20<5:09:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 68246/100000 [20:21:20<5:09:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 68247/100000 [20:21:21<5:09:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 68248/100000 [20:21:22<5:09:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 68249/100000 [20:21:22<5:09:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 68250/100000 [20:21:23<5:09:28,  1.71it/s]Step... (68250 / 100000 | Loss: 0.901275634765625, Learning Rate: 3.190954773869347e-05)
+
                                                                             
Step... (68250 / 100000 | Loss: 0.7939145565032959, Learning Rate: 3.190954773869347e-05)
+
Train steps ... :  68%|██████▊   | 68250/100000 [20:21:23<5:09:28,  1.71it/s]
Train steps ... :  68%|██████▊   | 68251/100000 [20:21:23<5:09:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68252/100000 [20:21:24<5:09:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 68253/100000 [20:21:24<5:09:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68254/100000 [20:21:25<5:09:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 68255/100000 [20:21:26<5:09:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68256/100000 [20:21:26<5:09:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 68257/100000 [20:21:27<5:09:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 68258/100000 [20:21:27<5:09:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68259/100000 [20:21:28<5:09:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 68260/100000 [20:21:29<5:09:06,  1.71it/s]
Train steps ... :  68%|██████▊   | 68261/100000 [20:21:29<5:09:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 68262/100000 [20:21:30<5:09:06,  1.71it/s]
Train steps ... :  68%|██████▊   | 68263/100000 [20:21:30<5:09:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 68264/100000 [20:21:31<5:09:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 68265/100000 [20:21:32<5:09:22,  1.71it/s]
Train steps ... :  68%|██████▊   | 68266/100000 [20:21:32<5:09:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 68267/100000 [20:21:33<5:09:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 68268/100000 [20:21:33<5:09:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 68269/100000 [20:21:34<5:09:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68270/100000 [20:21:34<5:09:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68271/100000 [20:21:35<5:09:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 68272/100000 [20:21:36<5:09:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 68273/100000 [20:21:36<5:09:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68274/100000 [20:21:37<5:09:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68275/100000 [20:21:37<5:09:45,  1.71it/s]Step... (68275 / 100000 | Loss: 0.7129955291748047, Learning Rate: 3.1884422110552764e-05)
+
                                                                             
Step... (68275 / 100000 | Loss: 0.8298418521881104, Learning Rate: 3.1884422110552764e-05)
+
Train steps ... :  68%|██████▊   | 68275/100000 [20:21:38<5:09:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68276/100000 [20:21:38<5:09:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 68277/100000 [20:21:39<5:09:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68278/100000 [20:21:39<5:09:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68279/100000 [20:21:40<5:09:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 68280/100000 [20:21:40<5:09:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 68281/100000 [20:21:41<5:09:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68282/100000 [20:21:41<5:09:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68283/100000 [20:21:42<5:09:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68284/100000 [20:21:43<5:09:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 68285/100000 [20:21:43<5:09:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68286/100000 [20:21:44<5:09:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 68287/100000 [20:21:44<5:09:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 68288/100000 [20:21:45<5:09:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68289/100000 [20:21:46<5:09:07,  1.71it/s]
Train steps ... :  68%|██████▊   | 68290/100000 [20:21:46<5:09:16,  1.71it/s]
Train steps ... :  68%|██████▊   | 68291/100000 [20:21:47<5:09:26,  1.71it/s]
Train steps ... :  68%|██████▊   | 68292/100000 [20:21:47<5:09:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 68293/100000 [20:21:48<5:09:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68294/100000 [20:21:48<5:09:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 68295/100000 [20:21:49<5:09:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 68296/100000 [20:21:50<5:09:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68297/100000 [20:21:50<5:09:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 68298/100000 [20:21:51<5:09:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 68299/100000 [20:21:51<5:09:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68300/100000 [20:21:52<5:10:06,  1.70it/s]Step... (68300 / 100000 | Loss: 0.9383276104927063, Learning Rate: 3.185929648241206e-05)
+
                                                                             
Step... (68300 / 100000 | Loss: 0.6268797516822815, Learning Rate: 3.185929648241206e-05)
+
Train steps ... :  68%|██████▊   | 68300/100000 [20:21:52<5:10:06,  1.70it/s]
Train steps ... :  68%|██████▊   | 68301/100000 [20:21:53<5:09:57,  1.70it/s]
Train steps ... :  68%|██████▊   | 68302/100000 [20:21:53<5:09:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68303/100000 [20:21:54<5:09:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68304/100000 [20:21:54<5:09:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 68305/100000 [20:21:55<5:09:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 68306/100000 [20:21:56<5:09:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68307/100000 [20:21:56<5:09:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68308/100000 [20:21:57<5:09:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68309/100000 [20:21:57<5:09:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68310/100000 [20:21:58<5:09:07,  1.71it/s]
Train steps ... :  68%|██████▊   | 68311/100000 [20:21:58<5:09:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68312/100000 [20:21:59<5:09:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 68313/100000 [20:22:00<5:09:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 68314/100000 [20:22:00<5:09:35,  1.71it/s]
Train steps ... :  68%|██████▊   | 68315/100000 [20:22:01<5:09:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 68316/100000 [20:22:01<5:09:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 68317/100000 [20:22:02<5:09:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 68318/100000 [20:22:03<5:08:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68319/100000 [20:22:03<5:08:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 68320/100000 [20:22:04<5:08:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68321/100000 [20:22:04<5:08:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 68322/100000 [20:22:05<5:08:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 68323/100000 [20:22:05<5:08:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 68324/100000 [20:22:06<5:08:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68325/100000 [20:22:07<5:08:45,  1.71it/s]Step... (68325 / 100000 | Loss: 0.6997581720352173, Learning Rate: 3.183417085427136e-05)
+
                                                                             
Step... (68325 / 100000 | Loss: 0.7199810743331909, Learning Rate: 3.183417085427136e-05)
+
Train steps ... :  68%|██████▊   | 68325/100000 [20:22:07<5:08:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68326/100000 [20:22:07<5:08:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 68327/100000 [20:22:08<5:08:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68328/100000 [20:22:08<5:08:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 68329/100000 [20:22:09<5:08:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 68330/100000 [20:22:10<5:09:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 68331/100000 [20:22:10<5:08:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 68332/100000 [20:22:11<5:09:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68333/100000 [20:22:11<5:08:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 68334/100000 [20:22:12<5:08:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 68335/100000 [20:22:12<5:08:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 68336/100000 [20:22:13<5:08:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68337/100000 [20:22:14<5:08:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 68338/100000 [20:22:14<5:09:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 68339/100000 [20:22:15<5:08:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 68340/100000 [20:22:15<5:08:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 68341/100000 [20:22:16<5:08:19,  1.71it/s]
Train steps ... :  68%|██████▊   | 68342/100000 [20:22:17<5:08:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 68343/100000 [20:22:17<5:07:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 68344/100000 [20:22:18<5:07:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 68345/100000 [20:22:18<5:07:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 68346/100000 [20:22:19<5:08:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 68347/100000 [20:22:20<5:08:21,  1.71it/s]
Train steps ... :  68%|██████▊   | 68348/100000 [20:22:20<5:07:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 68349/100000 [20:22:21<5:08:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 68350/100000 [20:22:21<5:08:01,  1.71it/s]Step... (68350 / 100000 | Loss: 0.8789114952087402, Learning Rate: 3.1809045226130654e-05)
+
                                                                             
Step... (68350 / 100000 | Loss: 0.9250196218490601, Learning Rate: 3.1809045226130654e-05)
+
Train steps ... :  68%|██████▊   | 68350/100000 [20:22:22<5:08:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 68351/100000 [20:22:22<5:07:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68352/100000 [20:22:22<5:07:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 68353/100000 [20:22:23<5:08:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68354/100000 [20:22:24<5:08:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 68355/100000 [20:22:24<5:08:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 68356/100000 [20:22:25<5:08:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 68357/100000 [20:22:25<5:07:52,  1.71it/s]
Train steps ... :  68%|██████▊   | 68358/100000 [20:22:26<5:07:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68359/100000 [20:22:27<5:07:29,  1.72it/s]
Train steps ... :  68%|██████▊   | 68360/100000 [20:22:28<6:28:40,  1.36it/s]
Train steps ... :  68%|██████▊   | 68361/100000 [20:22:31<14:36:49,  1.66s/it]
Train steps ... :  68%|██████▊   | 68362/100000 [20:22:32<11:46:02,  1.34s/it]
Train steps ... :  68%|██████▊   | 68363/100000 [20:22:33<9:46:44,  1.11s/it] 
Train steps ... :  68%|██████▊   | 68364/100000 [20:22:33<8:23:45,  1.05it/s]
Train steps ... :  68%|██████▊   | 68365/100000 [20:22:34<7:24:56,  1.18it/s]
Train steps ... :  68%|██████▊   | 68366/100000 [20:22:34<6:44:11,  1.30it/s]
Train steps ... :  68%|██████▊   | 68367/100000 [20:22:35<6:15:34,  1.40it/s]
Train steps ... :  68%|██████▊   | 68368/100000 [20:22:36<5:55:17,  1.48it/s]
Train steps ... :  68%|██████▊   | 68369/100000 [20:22:36<5:41:03,  1.55it/s]
Train steps ... :  68%|██████▊   | 68370/100000 [20:22:37<5:31:47,  1.59it/s]
Train steps ... :  68%|██████▊   | 68371/100000 [20:22:37<5:24:41,  1.62it/s]
Train steps ... :  68%|██████▊   | 68372/100000 [20:22:38<5:19:32,  1.65it/s]
Train steps ... :  68%|██████▊   | 68373/100000 [20:22:38<5:15:55,  1.67it/s]
Train steps ... :  68%|██████▊   | 68374/100000 [20:22:39<5:13:23,  1.68it/s]
Train steps ... :  68%|██████▊   | 68375/100000 [20:22:40<5:11:51,  1.69it/s]Step... (68375 / 100000 | Loss: 0.6540886163711548, Learning Rate: 3.178391959798995e-05)
+
                                                                             
Step... (68375 / 100000 | Loss: 0.7219393253326416, Learning Rate: 3.178391959798995e-05)
+
Train steps ... :  68%|██████▊   | 68375/100000 [20:22:40<5:11:51,  1.69it/s]
Train steps ... :  68%|██████▊   | 68376/100000 [20:22:40<5:10:52,  1.70it/s]
Train steps ... :  68%|██████▊   | 68377/100000 [20:22:41<5:10:05,  1.70it/s]
Train steps ... :  68%|██████▊   | 68378/100000 [20:22:41<5:09:34,  1.70it/s]
Train steps ... :  68%|██████▊   | 68379/100000 [20:22:42<5:09:23,  1.70it/s]
Train steps ... :  68%|██████▊   | 68380/100000 [20:22:43<5:08:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 68381/100000 [20:22:43<5:08:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68382/100000 [20:22:44<5:08:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 68383/100000 [20:22:44<5:07:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 68384/100000 [20:22:45<5:07:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68385/100000 [20:22:45<5:07:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 68386/100000 [20:22:46<5:07:55,  1.71it/s]
Train steps ... :  68%|██████▊   | 68387/100000 [20:22:47<5:07:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 68388/100000 [20:22:47<5:08:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 68389/100000 [20:22:48<5:08:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 68390/100000 [20:22:48<5:08:15,  1.71it/s]
Train steps ... :  68%|██████▊   | 68391/100000 [20:22:49<5:08:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 68392/100000 [20:22:50<5:07:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 68393/100000 [20:22:50<5:08:02,  1.71it/s]
Train steps ... :  68%|██████▊   | 68394/100000 [20:22:51<5:08:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68395/100000 [20:22:51<5:07:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 68396/100000 [20:22:52<5:08:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 68397/100000 [20:22:52<5:07:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 68398/100000 [20:22:53<5:07:40,  1.71it/s]
Train steps ... :  68%|██████▊   | 68399/100000 [20:22:54<5:08:01,  1.71it/s]
Train steps ... :  68%|██████▊   | 68400/100000 [20:22:54<5:08:38,  1.71it/s]Step... (68400 / 100000 | Loss: 0.6248102784156799, Learning Rate: 3.175879396984925e-05)
+
                                                                             
Step... (68400 / 100000 | Loss: 0.6073129177093506, Learning Rate: 3.175879396984925e-05)
+
Train steps ... :  68%|██████▊   | 68400/100000 [20:22:55<5:08:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 68401/100000 [20:22:55<5:08:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 68402/100000 [20:22:55<5:08:09,  1.71it/s]
Train steps ... :  68%|██████▊   | 68403/100000 [20:22:56<5:07:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68404/100000 [20:22:57<5:08:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 68405/100000 [20:22:57<5:08:21,  1.71it/s]
Train steps ... :  68%|██████▊   | 68406/100000 [20:22:58<5:08:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 68407/100000 [20:22:58<5:08:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 68408/100000 [20:22:59<5:08:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68409/100000 [20:23:00<5:08:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 68410/100000 [20:23:00<5:07:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 68411/100000 [20:23:01<5:08:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 68412/100000 [20:23:01<5:08:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 68413/100000 [20:23:02<5:08:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 68414/100000 [20:23:02<5:07:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 68415/100000 [20:23:03<5:07:41,  1.71it/s]
Train steps ... :  68%|██████▊   | 68416/100000 [20:23:04<5:07:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 68417/100000 [20:23:04<5:07:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 68418/100000 [20:23:05<5:07:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68419/100000 [20:23:05<5:07:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68420/100000 [20:23:06<5:08:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 68421/100000 [20:23:07<5:08:14,  1.71it/s]
Train steps ... :  68%|██████▊   | 68422/100000 [20:23:07<5:08:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 68423/100000 [20:23:08<5:08:13,  1.71it/s]
Train steps ... :  68%|██████▊   | 68424/100000 [20:23:08<5:08:00,  1.71it/s]
Train steps ... :  68%|██████▊   | 68425/100000 [20:23:09<5:07:50,  1.71it/s]Step... (68425 / 100000 | Loss: 0.6303880214691162, Learning Rate: 3.1733668341708544e-05)
+
                                                                             
Step... (68425 / 100000 | Loss: 0.6211684346199036, Learning Rate: 3.1733668341708544e-05)
+
Train steps ... :  68%|██████▊   | 68425/100000 [20:23:09<5:07:50,  1.71it/s]
Train steps ... :  68%|██████▊   | 68426/100000 [20:23:09<5:07:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 68427/100000 [20:23:10<5:07:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 68428/100000 [20:23:11<5:07:51,  1.71it/s]
Train steps ... :  68%|██████▊   | 68429/100000 [20:23:11<5:07:54,  1.71it/s]
Train steps ... :  68%|██████▊   | 68430/100000 [20:23:12<5:07:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 68431/100000 [20:23:12<5:07:39,  1.71it/s]
Train steps ... :  68%|██████▊   | 68432/100000 [20:23:13<5:07:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 68433/100000 [20:23:14<5:07:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68434/100000 [20:23:14<5:07:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 68435/100000 [20:23:15<5:07:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 68436/100000 [20:23:15<5:07:33,  1.71it/s]
Train steps ... :  68%|██████▊   | 68437/100000 [20:23:16<5:07:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 68438/100000 [20:23:16<5:07:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 68439/100000 [20:23:17<5:07:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 68440/100000 [20:23:18<5:07:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68441/100000 [20:23:18<5:07:30,  1.71it/s]
Train steps ... :  68%|██████▊   | 68442/100000 [20:23:19<5:07:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 68443/100000 [20:23:19<5:07:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68444/100000 [20:23:20<5:07:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68445/100000 [20:23:21<5:07:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 68446/100000 [20:23:21<5:07:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 68447/100000 [20:23:22<5:07:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 68448/100000 [20:23:22<5:07:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 68449/100000 [20:23:23<5:07:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 68450/100000 [20:23:23<5:07:18,  1.71it/s]Step... (68450 / 100000 | Loss: 0.7146351337432861, Learning Rate: 3.170854271356784e-05)
+
                                                                             
Step... (68450 / 100000 | Loss: 0.5391359329223633, Learning Rate: 3.170854271356784e-05)
+
Train steps ... :  68%|██████▊   | 68450/100000 [20:23:24<5:07:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 68451/100000 [20:23:24<5:07:12,  1.71it/s]
Train steps ... :  68%|██████▊   | 68452/100000 [20:23:25<5:07:27,  1.71it/s]
Train steps ... :  68%|██████▊   | 68453/100000 [20:23:25<5:07:11,  1.71it/s]
Train steps ... :  68%|██████▊   | 68454/100000 [20:23:26<5:07:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 68455/100000 [20:23:26<5:07:24,  1.71it/s]
Train steps ... :  68%|██████▊   | 68456/100000 [20:23:27<5:07:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 68457/100000 [20:23:28<5:07:34,  1.71it/s]
Train steps ... :  68%|██████▊   | 68458/100000 [20:23:28<5:07:37,  1.71it/s]
Train steps ... :  68%|██████▊   | 68459/100000 [20:23:29<5:07:44,  1.71it/s]
Train steps ... :  68%|██████▊   | 68460/100000 [20:23:29<5:07:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 68461/100000 [20:23:30<5:07:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 68462/100000 [20:23:31<5:07:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 68463/100000 [20:23:31<5:07:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68464/100000 [20:23:32<5:07:03,  1.71it/s]
Train steps ... :  68%|██████▊   | 68465/100000 [20:23:32<5:07:02,  1.71it/s]
Train steps ... :  68%|██████▊   | 68466/100000 [20:23:33<5:06:56,  1.71it/s]
Train steps ... :  68%|██████▊   | 68467/100000 [20:23:33<5:07:38,  1.71it/s]
Train steps ... :  68%|██████▊   | 68468/100000 [20:23:34<5:07:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 68469/100000 [20:23:35<5:07:18,  1.71it/s]
Train steps ... :  68%|██████▊   | 68470/100000 [20:23:35<5:07:17,  1.71it/s]
Train steps ... :  68%|██████▊   | 68471/100000 [20:23:36<5:06:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 68472/100000 [20:23:36<5:07:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 68473/100000 [20:23:37<5:07:23,  1.71it/s]
Train steps ... :  68%|██████▊   | 68474/100000 [20:23:38<5:07:32,  1.71it/s]
Train steps ... :  68%|██████▊   | 68475/100000 [20:23:38<5:07:48,  1.71it/s]Step... (68475 / 100000 | Loss: 0.7101173400878906, Learning Rate: 3.168341708542714e-05)
+
                                                                             
Step... (68475 / 100000 | Loss: 0.5617103576660156, Learning Rate: 3.168341708542714e-05)
+
Train steps ... :  68%|██████▊   | 68475/100000 [20:23:38<5:07:48,  1.71it/s]
Train steps ... :  68%|██████▊   | 68476/100000 [20:23:39<5:08:07,  1.71it/s]
Train steps ... :  68%|██████▊   | 68477/100000 [20:23:39<5:07:58,  1.71it/s]
Train steps ... :  68%|██████▊   | 68478/100000 [20:23:40<5:07:36,  1.71it/s]
Train steps ... :  68%|██████▊   | 68479/100000 [20:23:40<5:07:45,  1.71it/s]
Train steps ... :  68%|██████▊   | 68480/100000 [20:23:41<5:08:02,  1.71it/s]
Train steps ... :  68%|██████▊   | 68481/100000 [20:23:42<5:07:53,  1.71it/s]
Train steps ... :  68%|██████▊   | 68482/100000 [20:23:42<5:07:25,  1.71it/s]
Train steps ... :  68%|██████▊   | 68483/100000 [20:23:43<5:07:08,  1.71it/s]
Train steps ... :  68%|██████▊   | 68484/100000 [20:23:43<5:07:05,  1.71it/s]
Train steps ... :  68%|██████▊   | 68485/100000 [20:23:44<5:06:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 68486/100000 [20:23:45<5:06:49,  1.71it/s]
Train steps ... :  68%|██████▊   | 68487/100000 [20:23:45<5:07:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 68488/100000 [20:23:46<5:07:29,  1.71it/s]
Train steps ... :  68%|██████▊   | 68489/100000 [20:23:46<5:07:20,  1.71it/s]
Train steps ... :  68%|██████▊   | 68490/100000 [20:23:47<5:07:02,  1.71it/s]
Train steps ... :  68%|██████▊   | 68491/100000 [20:23:47<5:07:04,  1.71it/s]
Train steps ... :  68%|██████▊   | 68492/100000 [20:23:48<5:06:46,  1.71it/s]
Train steps ... :  68%|██████▊   | 68493/100000 [20:23:49<5:06:47,  1.71it/s]
Train steps ... :  68%|██████▊   | 68494/100000 [20:23:49<5:06:31,  1.71it/s]
Train steps ... :  68%|██████▊   | 68495/100000 [20:23:50<5:06:57,  1.71it/s]
Train steps ... :  68%|██████▊   | 68496/100000 [20:23:50<5:06:42,  1.71it/s]
Train steps ... :  68%|██████▊   | 68497/100000 [20:23:51<5:06:59,  1.71it/s]
Train steps ... :  68%|██████▊   | 68498/100000 [20:23:52<5:07:10,  1.71it/s]
Train steps ... :  68%|██████▊   | 68499/100000 [20:23:52<5:07:21,  1.71it/s]
Train steps ... :  68%|██████▊   | 68500/100000 [20:23:53<5:07:00,  1.71it/s]Step... (68500 / 100000 | Loss: 1.119281530380249, Learning Rate: 3.1658291457286434e-05)
+
                                                                             
Step... (68500 / 100000 | Loss: 0.7820653915405273, Learning Rate: 3.1658291457286434e-05)
+
Train steps ... :  68%|██████▊   | 68500/100000 [20:23:53<5:07:00,  1.71it/s]
Train steps ... :  69%|██████▊   | 68501/100000 [20:23:53<5:07:05,  1.71it/s]
Train steps ... :  69%|██████▊   | 68502/100000 [20:23:54<5:06:51,  1.71it/s]
Train steps ... :  69%|██████���   | 68503/100000 [20:23:54<5:06:30,  1.71it/s]
Train steps ... :  69%|██████▊   | 68504/100000 [20:23:55<5:06:46,  1.71it/s]
Train steps ... :  69%|██████▊   | 68505/100000 [20:23:56<5:06:54,  1.71it/s]
Train steps ... :  69%|██████▊   | 68506/100000 [20:23:56<5:06:57,  1.71it/s]
Train steps ... :  69%|██████▊   | 68507/100000 [20:23:57<5:07:20,  1.71it/s]
Train steps ... :  69%|██████▊   | 68508/100000 [20:23:57<5:06:57,  1.71it/s]
Train steps ... :  69%|██████▊   | 68509/100000 [20:23:58<5:07:14,  1.71it/s]
Train steps ... :  69%|██████▊   | 68510/100000 [20:23:59<5:07:12,  1.71it/s]
Train steps ... :  69%|██████▊   | 68511/100000 [20:23:59<5:06:52,  1.71it/s]
Train steps ... :  69%|██████▊   | 68512/100000 [20:24:00<5:07:01,  1.71it/s]
Train steps ... :  69%|██████▊   | 68513/100000 [20:24:00<5:06:47,  1.71it/s]
Train steps ... :  69%|██████▊   | 68514/100000 [20:24:01<5:06:55,  1.71it/s]
Train steps ... :  69%|██████▊   | 68515/100000 [20:24:02<5:06:56,  1.71it/s]
Train steps ... :  69%|██████▊   | 68516/100000 [20:24:02<5:06:35,  1.71it/s]
Train steps ... :  69%|██████▊   | 68517/100000 [20:24:03<5:07:16,  1.71it/s]
Train steps ... :  69%|██████▊   | 68518/100000 [20:24:03<5:07:19,  1.71it/s]
Train steps ... :  69%|██████▊   | 68519/100000 [20:24:04<5:07:47,  1.70it/s]
Train steps ... :  69%|██████▊   | 68520/100000 [20:24:04<5:07:12,  1.71it/s]
Train steps ... :  69%|██████▊   | 68521/100000 [20:24:05<5:06:50,  1.71it/s]
Train steps ... :  69%|██████▊   | 68522/100000 [20:24:06<5:07:03,  1.71it/s]
Train steps ... :  69%|██████▊   | 68523/100000 [20:24:06<5:06:53,  1.71it/s]
Train steps ... :  69%|██████▊   | 68524/100000 [20:24:07<5:06:53,  1.71it/s]
Train steps ... :  69%|██████▊   | 68525/100000 [20:24:07<5:06:34,  1.71it/s]Step... (68525 / 100000 | Loss: 0.6003131866455078, Learning Rate: 3.163316582914573e-05)
+
                                                                             
Step... (68525 / 100000 | Loss: 0.7475889921188354, Learning Rate: 3.163316582914573e-05)
+
Train steps ... :  69%|██████▊   | 68525/100000 [20:24:08<5:06:34,  1.71it/s]
Train steps ... :  69%|██████▊   | 68526/100000 [20:24:08<5:06:38,  1.71it/s]
Train steps ... :  69%|██████▊   | 68527/100000 [20:24:09<5:06:38,  1.71it/s]
Train steps ... :  69%|██████▊   | 68528/100000 [20:24:09<5:06:58,  1.71it/s]
Train steps ... :  69%|██████▊   | 68529/100000 [20:24:10<5:06:38,  1.71it/s]
Train steps ... :  69%|██████▊   | 68530/100000 [20:24:10<5:07:04,  1.71it/s]
Train steps ... :  69%|██████▊   | 68531/100000 [20:24:11<5:07:04,  1.71it/s]
Train steps ... :  69%|██████▊   | 68532/100000 [20:24:11<5:06:36,  1.71it/s]
Train steps ... :  69%|██████▊   | 68533/100000 [20:24:12<5:06:26,  1.71it/s]
Train steps ... :  69%|██████▊   | 68534/100000 [20:24:13<5:06:33,  1.71it/s]
Train steps ... :  69%|██████▊   | 68535/100000 [20:24:13<5:06:52,  1.71it/s]
Train steps ... :  69%|██████▊   | 68536/100000 [20:24:14<5:06:43,  1.71it/s]
Train steps ... :  69%|██████▊   | 68537/100000 [20:24:14<5:08:13,  1.70it/s]
Train steps ... :  69%|██████▊   | 68538/100000 [20:24:15<5:07:11,  1.71it/s]
Train steps ... :  69%|██████▊   | 68539/100000 [20:24:16<5:06:42,  1.71it/s]
Train steps ... :  69%|██████▊   | 68540/100000 [20:24:16<5:06:35,  1.71it/s]
Train steps ... :  69%|██████▊   | 68541/100000 [20:24:17<5:06:33,  1.71it/s]
Train steps ... :  69%|██████▊   | 68542/100000 [20:24:17<5:06:42,  1.71it/s]
Train steps ... :  69%|██████▊   | 68543/100000 [20:24:18<5:06:46,  1.71it/s]
Train steps ... :  69%|██████▊   | 68544/100000 [20:24:18<5:06:53,  1.71it/s]
Train steps ... :  69%|██████▊   | 68545/100000 [20:24:19<5:06:57,  1.71it/s]
Train steps ... :  69%|██████▊   | 68546/100000 [20:24:20<5:06:58,  1.71it/s]
Train steps ... :  69%|██████▊   | 68547/100000 [20:24:20<5:06:50,  1.71it/s]
Train steps ... :  69%|██████▊   | 68548/100000 [20:24:21<5:06:26,  1.71it/s]
Train steps ... :  69%|██████▊   | 68549/100000 [20:24:21<5:06:33,  1.71it/s]
Train steps ... :  69%|██████▊   | 68550/100000 [20:24:22<5:06:12,  1.71it/s]Step... (68550 / 100000 | Loss: 0.7059227228164673, Learning Rate: 3.160804020100503e-05)
+
                                                                             
Step... (68550 / 100000 | Loss: 0.580918550491333, Learning Rate: 3.160804020100503e-05)
+
Train steps ... :  69%|██████▊   | 68550/100000 [20:24:22<5:06:12,  1.71it/s]
Train steps ... :  69%|██████▊   | 68551/100000 [20:24:23<5:06:35,  1.71it/s]
Train steps ... :  69%|██████▊   | 68552/100000 [20:24:23<5:06:20,  1.71it/s]
Train steps ... :  69%|██████▊   | 68553/100000 [20:24:24<5:06:12,  1.71it/s]
Train steps ... :  69%|██████▊   | 68554/100000 [20:24:24<5:06:07,  1.71it/s]
Train steps ... :  69%|██████▊   | 68555/100000 [20:24:25<5:06:14,  1.71it/s]
Train steps ... :  69%|██████▊   | 68556/100000 [20:24:25<5:06:31,  1.71it/s]
Train steps ... :  69%|██████▊   | 68557/100000 [20:24:26<5:06:13,  1.71it/s]
Train steps ... :  69%|██████▊   | 68558/100000 [20:24:27<5:06:03,  1.71it/s]
Train steps ... :  69%|██████▊   | 68559/100000 [20:24:27<5:06:27,  1.71it/s]
Train steps ... :  69%|██████▊   | 68560/100000 [20:24:28<5:06:12,  1.71it/s]
Train steps ... :  69%|██████▊   | 68561/100000 [20:24:28<5:06:02,  1.71it/s]
Train steps ... :  69%|██████▊   | 68562/100000 [20:24:29<5:06:27,  1.71it/s]
Train steps ... :  69%|██████▊   | 68563/100000 [20:24:30<5:06:06,  1.71it/s]
Train steps ... :  69%|██████▊   | 68564/100000 [20:24:30<5:06:07,  1.71it/s]
Train steps ... :  69%|██████▊   | 68565/100000 [20:24:31<5:05:55,  1.71it/s]
Train steps ... :  69%|██████▊   | 68566/100000 [20:24:31<5:06:01,  1.71it/s]
Train steps ... :  69%|██████▊   | 68567/100000 [20:24:32<5:05:58,  1.71it/s]
Train steps ... :  69%|██████▊   | 68568/100000 [20:24:32<5:06:04,  1.71it/s]
Train steps ... :  69%|██████▊   | 68569/100000 [20:24:33<5:06:01,  1.71it/s]
Train steps ... :  69%|██████▊   | 68570/100000 [20:24:34<5:06:50,  1.71it/s]
Train steps ... :  69%|██████▊   | 68571/100000 [20:24:34<5:06:21,  1.71it/s]
Train steps ... :  69%|██████▊   | 68572/100000 [20:24:35<5:06:15,  1.71it/s]
Train steps ... :  69%|██████▊   | 68573/100000 [20:24:35<5:06:19,  1.71it/s]
Train steps ... :  69%|██████▊   | 68574/100000 [20:24:36<5:06:14,  1.71it/s]
Train steps ... :  69%|██████▊   | 68575/100000 [20:24:37<5:06:15,  1.71it/s]Step... (68575 / 100000 | Loss: 0.6233311295509338, Learning Rate: 3.1582914572864324e-05)
+
                                                                             
Step... (68575 / 100000 | Loss: 0.6502712965011597, Learning Rate: 3.1582914572864324e-05)
+
Train steps ... :  69%|██████▊   | 68575/100000 [20:24:37<5:06:15,  1.71it/s]
Train steps ... :  69%|██████▊   | 68576/100000 [20:24:37<5:06:10,  1.71it/s]
Train steps ... :  69%|██████▊   | 68577/100000 [20:24:38<5:06:05,  1.71it/s]
Train steps ... :  69%|██████▊   | 68578/100000 [20:24:38<5:06:02,  1.71it/s]
Train steps ... :  69%|██████▊   | 68579/100000 [20:24:39<5:06:07,  1.71it/s]
Train steps ... :  69%|██████▊   | 68580/100000 [20:24:40<5:05:53,  1.71it/s]
Train steps ... :  69%|██████▊   | 68581/100000 [20:24:40<5:06:02,  1.71it/s]
Train steps ... :  69%|██████▊   | 68582/100000 [20:24:41<5:06:04,  1.71it/s]
Train steps ... :  69%|██████▊   | 68583/100000 [20:24:41<5:06:01,  1.71it/s]
Train steps ... :  69%|██████▊   | 68584/100000 [20:24:42<5:06:00,  1.71it/s]
Train steps ... :  69%|██████▊   | 68585/100000 [20:24:42<5:06:21,  1.71it/s]
Train steps ... :  69%|██████▊   | 68586/100000 [20:24:43<5:06:14,  1.71it/s]
Train steps ... :  69%|██████▊   | 68587/100000 [20:24:44<5:06:10,  1.71it/s]
Train steps ... :  69%|██████▊   | 68588/100000 [20:24:44<5:06:05,  1.71it/s]
Train steps ... :  69%|██████▊   | 68589/100000 [20:24:45<5:06:30,  1.71it/s]
Train steps ... :  69%|██████▊   | 68590/100000 [20:24:45<5:06:35,  1.71it/s]
Train steps ... :  69%|██████▊   | 68591/100000 [20:24:46<5:07:00,  1.71it/s]
Train steps ... :  69%|██████▊   | 68592/100000 [20:24:47<5:07:00,  1.71it/s]
Train steps ... :  69%|██████▊   | 68593/100000 [20:24:47<5:06:50,  1.71it/s]
Train steps ... :  69%|██████▊   | 68594/100000 [20:24:48<5:06:27,  1.71it/s]
Train steps ... :  69%|██████▊   | 68595/100000 [20:24:48<5:06:28,  1.71it/s]
Train steps ... :  69%|██████▊   | 68596/100000 [20:24:49<5:06:33,  1.71it/s]
Train steps ... :  69%|██████▊   | 68597/100000 [20:24:49<5:06:10,  1.71it/s]
Train steps ... :  69%|██████▊   | 68598/100000 [20:24:50<5:06:06,  1.71it/s]
Train steps ... :  69%|██████▊   | 68599/100000 [20:24:51<5:06:12,  1.71it/s]
Train steps ... :  69%|██████▊   | 68600/100000 [20:24:51<5:06:08,  1.71it/s]Step... (68600 / 100000 | Loss: 0.6190400123596191, Learning Rate: 3.155778894472362e-05)
+
                                                                             
Step... (68600 / 100000 | Loss: 0.7069989442825317, Learning Rate: 3.155778894472362e-05)
+
Train steps ... :  69%|██████▊   | 68600/100000 [20:24:52<5:06:08,  1.71it/s]
Train steps ... :  69%|██████▊   | 68601/100000 [20:24:52<5:06:02,  1.71it/s]
Train steps ... :  69%|██████▊   | 68602/100000 [20:24:52<5:06:03,  1.71it/s]
Train steps ... :  69%|██████▊   | 68603/100000 [20:24:53<5:05:54,  1.71it/s]
Train steps ... :  69%|██████▊   | 68604/100000 [20:24:54<5:06:01,  1.71it/s]
Train steps ... :  69%|██████▊   | 68605/100000 [20:24:54<5:06:12,  1.71it/s]
Train steps ... :  69%|██████▊   | 68606/100000 [20:24:55<5:06:01,  1.71it/s]
Train steps ... :  69%|██████▊   | 68607/100000 [20:24:55<5:05:45,  1.71it/s]
Train steps ... :  69%|██████▊   | 68608/100000 [20:24:56<5:05:55,  1.71it/s]
Train steps ... :  69%|██████▊   | 68609/100000 [20:24:56<5:05:56,  1.71it/s]
Train steps ... :  69%|██████▊   | 68610/100000 [20:24:57<5:05:54,  1.71it/s]
Train steps ... :  69%|██████▊   | 68611/100000 [20:24:58<5:05:35,  1.71it/s]
Train steps ... :  69%|██████▊   | 68612/100000 [20:24:58<5:05:32,  1.71it/s]
Train steps ... :  69%|██████▊   | 68613/100000 [20:24:59<5:05:37,  1.71it/s]
Train steps ... :  69%|██████▊   | 68614/100000 [20:24:59<5:05:29,  1.71it/s]
Train steps ... :  69%|██████▊   | 68615/100000 [20:25:00<5:05:26,  1.71it/s]
Train steps ... :  69%|██████▊   | 68616/100000 [20:25:01<5:05:27,  1.71it/s]
Train steps ... :  69%|██████▊   | 68617/100000 [20:25:01<5:05:22,  1.71it/s]
Train steps ... :  69%|██████▊   | 68618/100000 [20:25:02<5:05:25,  1.71it/s]
Train steps ... :  69%|██████▊   | 68619/100000 [20:25:02<5:05:37,  1.71it/s]
Train steps ... :  69%|██████▊   | 68620/100000 [20:25:03<5:05:32,  1.71it/s]
Train steps ... :  69%|██████▊   | 68621/100000 [20:25:03<5:05:29,  1.71it/s]
Train steps ... :  69%|██████▊   | 68622/100000 [20:25:04<5:05:20,  1.71it/s]
Train steps ... :  69%|██████▊   | 68623/100000 [20:25:05<5:05:28,  1.71it/s]
Train steps ... :  69%|██████▊   | 68624/100000 [20:25:05<5:05:24,  1.71it/s]
Train steps ... :  69%|██████▊   | 68625/100000 [20:25:06<5:05:28,  1.71it/s]Step... (68625 / 100000 | Loss: 0.5911284685134888, Learning Rate: 3.153266331658292e-05)
+
                                                                             
Step... (68625 / 100000 | Loss: 0.5119138956069946, Learning Rate: 3.153266331658292e-05)
+
Train steps ... :  69%|██████▊   | 68625/100000 [20:25:06<5:05:28,  1.71it/s]
Train steps ... :  69%|██████▊   | 68626/100000 [20:25:06<5:05:31,  1.71it/s]
Train steps ... :  69%|██████▊   | 68627/100000 [20:25:07<5:05:31,  1.71it/s]
Train steps ... :  69%|██████▊   | 68628/100000 [20:25:08<5:05:24,  1.71it/s]
Train steps ... :  69%|██████▊   | 68629/100000 [20:25:08<5:05:34,  1.71it/s]
Train steps ... :  69%|██████▊   | 68630/100000 [20:25:09<5:05:48,  1.71it/s]
Train steps ... :  69%|██████▊   | 68631/100000 [20:25:09<5:05:46,  1.71it/s]
Train steps ... :  69%|██████▊   | 68632/100000 [20:25:10<5:05:43,  1.71it/s]
Train steps ... :  69%|██████▊   | 68633/100000 [20:25:11<5:05:56,  1.71it/s]
Train steps ... :  69%|██████▊   | 68634/100000 [20:25:11<5:06:05,  1.71it/s]
Train steps ... :  69%|██████▊   | 68635/100000 [20:25:12<5:05:56,  1.71it/s]
Train steps ... :  69%|██████▊   | 68636/100000 [20:25:12<5:05:43,  1.71it/s]
Train steps ... :  69%|██████▊   | 68637/100000 [20:25:13<5:05:31,  1.71it/s]
Train steps ... :  69%|██████▊   | 68638/100000 [20:25:13<5:05:47,  1.71it/s]
Train steps ... :  69%|██████▊   | 68639/100000 [20:25:14<5:06:03,  1.71it/s]
Train steps ... :  69%|██████▊   | 68640/100000 [20:25:15<5:06:05,  1.71it/s]
Train steps ... :  69%|██████▊   | 68641/100000 [20:25:15<5:05:32,  1.71it/s]
Train steps ... :  69%|██████▊   | 68642/100000 [20:25:16<5:05:43,  1.71it/s]
Train steps ... :  69%|██████▊   | 68643/100000 [20:25:16<5:05:38,  1.71it/s]
Train steps ... :  69%|██████▊   | 68644/100000 [20:25:17<5:05:20,  1.71it/s]
Train steps ... :  69%|██████▊   | 68645/100000 [20:25:18<5:05:07,  1.71it/s]
Train steps ... :  69%|██████▊   | 68646/100000 [20:25:18<5:05:27,  1.71it/s]
Train steps ... :  69%|██████▊   | 68647/100000 [20:25:19<5:05:41,  1.71it/s]
Train steps ... :  69%|██████▊   | 68648/100000 [20:25:19<5:05:55,  1.71it/s]
Train steps ... :  69%|██████▊   | 68649/100000 [20:25:20<5:05:51,  1.71it/s]
Train steps ... :  69%|██████▊   | 68650/100000 [20:25:20<5:06:10,  1.71it/s]Step... (68650 / 100000 | Loss: 0.6326274275779724, Learning Rate: 3.1507537688442214e-05)
+
                                                                             
Step... (68650 / 100000 | Loss: 0.7100217938423157, Learning Rate: 3.1507537688442214e-05)
+
Train steps ... :  69%|██████▊   | 68650/100000 [20:25:21<5:06:10,  1.71it/s]
Train steps ... :  69%|██████▊   | 68651/100000 [20:25:21<5:06:20,  1.71it/s]
Train steps ... :  69%|██████▊   | 68652/100000 [20:25:22<5:05:58,  1.71it/s]
Train steps ... :  69%|██████▊   | 68653/100000 [20:25:22<5:05:56,  1.71it/s]
Train steps ... :  69%|██████▊   | 68654/100000 [20:25:23<5:05:42,  1.71it/s]
Train steps ... :  69%|██████▊   | 68655/100000 [20:25:23<5:05:20,  1.71it/s]
Train steps ... :  69%|██████▊   | 68656/100000 [20:25:24<5:05:09,  1.71it/s]
Train steps ... :  69%|██████▊   | 68657/100000 [20:25:25<5:05:05,  1.71it/s]
Train steps ... :  69%|██████▊   | 68658/100000 [20:25:25<5:04:56,  1.71it/s]
Train steps ... :  69%|██████▊   | 68659/100000 [20:25:26<5:04:59,  1.71it/s]
Train steps ... :  69%|██████▊   | 68660/100000 [20:25:26<5:05:17,  1.71it/s]
Train steps ... :  69%|██████▊   | 68661/100000 [20:25:27<5:05:11,  1.71it/s]
Train steps ... :  69%|██████▊   | 68662/100000 [20:25:27<5:05:12,  1.71it/s]
Train steps ... :  69%|██████▊   | 68663/100000 [20:25:28<5:05:43,  1.71it/s]
Train steps ... :  69%|██████▊   | 68664/100000 [20:25:29<5:05:38,  1.71it/s]
Train steps ... :  69%|██████▊   | 68665/100000 [20:25:29<5:05:26,  1.71it/s]
Train steps ... :  69%|██████▊   | 68666/100000 [20:25:30<5:05:33,  1.71it/s]
Train steps ... :  69%|██████▊   | 68667/100000 [20:25:30<5:05:34,  1.71it/s]
Train steps ... :  69%|██████▊   | 68668/100000 [20:25:31<5:05:43,  1.71it/s]
Train steps ... :  69%|██████▊   | 68669/100000 [20:25:32<5:05:26,  1.71it/s]
Train steps ... :  69%|██████▊   | 68670/100000 [20:25:32<5:05:27,  1.71it/s]
Train steps ... :  69%|██████▊   | 68671/100000 [20:25:33<5:05:24,  1.71it/s]
Train steps ... :  69%|██████▊   | 68672/100000 [20:25:33<5:05:13,  1.71it/s]
Train steps ... :  69%|██████▊   | 68673/100000 [20:25:34<5:05:04,  1.71it/s]
Train steps ... :  69%|██████▊   | 68674/100000 [20:25:34<5:05:07,  1.71it/s]
Train steps ... :  69%|██████▊   | 68675/100000 [20:25:35<5:05:20,  1.71it/s]Step... (68675 / 100000 | Loss: 0.5203256607055664, Learning Rate: 3.148241206030151e-05)
+
                                                                             
Step... (68675 / 100000 | Loss: 0.8607335090637207, Learning Rate: 3.148241206030151e-05)
+
Train steps ... :  69%|██████▊   | 68675/100000 [20:25:35<5:05:20,  1.71it/s]
Train steps ... :  69%|██████▊   | 68676/100000 [20:25:36<5:05:46,  1.71it/s]
Train steps ... :  69%|██████▊   | 68677/100000 [20:25:36<5:06:01,  1.71it/s]
Train steps ... :  69%|██████▊   | 68678/100000 [20:25:37<5:05:50,  1.71it/s]
Train steps ... :  69%|██████▊   | 68679/100000 [20:25:37<5:05:45,  1.71it/s]
Train steps ... :  69%|██████▊   | 68680/100000 [20:25:38<5:05:52,  1.71it/s]
Train steps ... :  69%|██████▊   | 68681/100000 [20:25:39<5:05:19,  1.71it/s]
Train steps ... :  69%|██████▊   | 68682/100000 [20:25:39<5:05:32,  1.71it/s]
Train steps ... :  69%|██████▊   | 68683/100000 [20:25:40<5:05:15,  1.71it/s]
Train steps ... :  69%|██████▊   | 68684/100000 [20:25:40<5:05:34,  1.71it/s]
Train steps ... :  69%|██████▊   | 68685/100000 [20:25:41<5:05:18,  1.71it/s]
Train steps ... :  69%|██████▊   | 68686/100000 [20:25:42<5:05:26,  1.71it/s]
Train steps ... :  69%|██████▊   | 68687/100000 [20:25:42<5:05:19,  1.71it/s]
Train steps ... :  69%|██████▊   | 68688/100000 [20:25:43<5:05:17,  1.71it/s]
Train steps ... :  69%|██████▊   | 68689/100000 [20:25:43<5:05:35,  1.71it/s]
Train steps ... :  69%|██████▊   | 68690/100000 [20:25:44<5:05:55,  1.71it/s]
Train steps ... :  69%|██████▊   | 68691/100000 [20:25:44<5:05:52,  1.71it/s]
Train steps ... :  69%|██████▊   | 68692/100000 [20:25:45<5:05:49,  1.71it/s]
Train steps ... :  69%|██████▊   | 68693/100000 [20:25:46<5:06:02,  1.70it/s]
Train steps ... :  69%|██████▊   | 68694/100000 [20:25:46<5:05:30,  1.71it/s]
Train steps ... :  69%|██████▊   | 68695/100000 [20:25:47<5:05:59,  1.71it/s]
Train steps ... :  69%|██████▊   | 68696/100000 [20:25:47<5:05:38,  1.71it/s]
Train steps ... :  69%|██████▊   | 68697/100000 [20:25:48<5:05:16,  1.71it/s]
Train steps ... :  69%|██████▊   | 68698/100000 [20:25:49<5:05:26,  1.71it/s]
Train steps ... :  69%|██████▊   | 68699/100000 [20:25:49<5:05:26,  1.71it/s]
Train steps ... :  69%|██████▊   | 68700/100000 [20:25:50<5:05:06,  1.71it/s]Step... (68700 / 100000 | Loss: 0.6942511796951294, Learning Rate: 3.145728643216081e-05)
+
                                                                             
Step... (68700 / 100000 | Loss: 0.7851428985595703, Learning Rate: 3.145728643216081e-05)
+
Train steps ... :  69%|██████▊   | 68700/100000 [20:25:50<5:05:06,  1.71it/s]
Train steps ... :  69%|██████▊   | 68701/100000 [20:25:50<5:05:48,  1.71it/s]
Train steps ... :  69%|██████▊   | 68702/100000 [20:25:51<5:05:44,  1.71it/s]
Train steps ... :  69%|██████▊   | 68703/100000 [20:25:51<5:05:27,  1.71it/s]
Train steps ... :  69%|██████▊   | 68704/100000 [20:25:52<5:05:32,  1.71it/s]
Train steps ... :  69%|██████▊   | 68705/100000 [20:25:53<5:05:29,  1.71it/s]
Train steps ... :  69%|██████▊   | 68706/100000 [20:25:53<5:05:27,  1.71it/s]
Train steps ... :  69%|██████▊   | 68707/100000 [20:25:54<5:05:31,  1.71it/s]
Train steps ... :  69%|██████▊   | 68708/100000 [20:25:54<5:05:40,  1.71it/s]
Train steps ... :  69%|██████▊   | 68709/100000 [20:25:55<5:05:48,  1.71it/s]
Train steps ... :  69%|██████▊   | 68710/100000 [20:25:56<5:05:38,  1.71it/s]
Train steps ... :  69%|██████▊   | 68711/100000 [20:25:56<5:05:21,  1.71it/s]
Train steps ... :  69%|██████▊   | 68712/100000 [20:25:57<5:05:11,  1.71it/s]
Train steps ... :  69%|██████▊   | 68713/100000 [20:25:57<5:04:54,  1.71it/s]
Train steps ... :  69%|██████▊   | 68714/100000 [20:25:58<5:04:40,  1.71it/s]
Train steps ... :  69%|██████▊   | 68715/100000 [20:25:58<5:04:45,  1.71it/s]
Train steps ... :  69%|██████▊   | 68716/100000 [20:25:59<5:05:09,  1.71it/s]
Train steps ... :  69%|██████▊   | 68717/100000 [20:26:00<5:05:11,  1.71it/s]
Train steps ... :  69%|██████▊   | 68718/100000 [20:26:00<5:04:58,  1.71it/s]
Train steps ... :  69%|██████▊   | 68719/100000 [20:26:01<5:04:55,  1.71it/s]
Train steps ... :  69%|██████▊   | 68720/100000 [20:26:01<5:04:53,  1.71it/s]
Train steps ... :  69%|██████▊   | 68721/100000 [20:26:02<5:05:00,  1.71it/s]
Train steps ... :  69%|██████▊   | 68722/100000 [20:26:03<5:04:49,  1.71it/s]
Train steps ... :  69%|██████▊   | 68723/100000 [20:26:03<5:04:30,  1.71it/s]
Train steps ... :  69%|██████▊   | 68724/100000 [20:26:04<5:05:33,  1.71it/s]
Train steps ... :  69%|██████▊   | 68725/100000 [20:26:04<5:05:40,  1.71it/s]Step... (68725 / 100000 | Loss: 0.6264101266860962, Learning Rate: 3.14321608040201e-05)
+
                                                                             
Step... (68725 / 100000 | Loss: 0.5968213081359863, Learning Rate: 3.14321608040201e-05)
+
Train steps ... :  69%|██████▊   | 68725/100000 [20:26:05<5:05:40,  1.71it/s]
Train steps ... :  69%|██████▊   | 68726/100000 [20:26:05<5:05:10,  1.71it/s]
Train steps ... :  69%|██████▊   | 68727/100000 [20:26:06<5:04:50,  1.71it/s]
Train steps ... :  69%|██████▊   | 68728/100000 [20:26:06<5:04:54,  1.71it/s]
Train steps ... :  69%|██████▊   | 68729/100000 [20:26:07<5:04:39,  1.71it/s]
Train steps ... :  69%|██████▊   | 68730/100000 [20:26:07<5:04:41,  1.71it/s]
Train steps ... :  69%|██████▊   | 68731/100000 [20:26:08<5:04:34,  1.71it/s]
Train steps ... :  69%|██████▊   | 68732/100000 [20:26:08<5:04:29,  1.71it/s]
Train steps ... :  69%|██████▊   | 68733/100000 [20:26:09<5:04:37,  1.71it/s]
Train steps ... :  69%|██████▊   | 68734/100000 [20:26:10<5:04:43,  1.71it/s]
Train steps ... :  69%|██████▊   | 68735/100000 [20:26:10<5:04:49,  1.71it/s]
Train steps ... :  69%|██████▊   | 68736/100000 [20:26:11<5:04:51,  1.71it/s]
Train steps ... :  69%|██████▊   | 68737/100000 [20:26:11<5:04:48,  1.71it/s]
Train steps ... :  69%|██████▊   | 68738/100000 [20:26:12<5:04:59,  1.71it/s]
Train steps ... :  69%|██████▊   | 68739/100000 [20:26:13<5:04:32,  1.71it/s]
Train steps ... :  69%|██████▊   | 68740/100000 [20:26:13<5:04:32,  1.71it/s]
Train steps ... :  69%|██████▊   | 68741/100000 [20:26:14<5:04:44,  1.71it/s]
Train steps ... :  69%|██████▊   | 68742/100000 [20:26:14<5:05:21,  1.71it/s]
Train steps ... :  69%|██████▊   | 68743/100000 [20:26:15<5:05:23,  1.71it/s]
Train steps ... :  69%|██████▊   | 68744/100000 [20:26:15<5:05:15,  1.71it/s]
Train steps ... :  69%|██████▊   | 68745/100000 [20:26:16<5:04:56,  1.71it/s]
Train steps ... :  69%|██████▊   | 68746/100000 [20:26:17<5:04:39,  1.71it/s]
Train steps ... :  69%|██████▊   | 68747/100000 [20:26:17<5:05:08,  1.71it/s]
Train steps ... :  69%|██████▊   | 68748/100000 [20:26:18<5:04:55,  1.71it/s]
Train steps ... :  69%|██████▊   | 68749/100000 [20:26:18<5:05:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 68750/100000 [20:26:19<5:04:45,  1.71it/s]Step... (68750 / 100000 | Loss: 0.6851046681404114, Learning Rate: 3.14070351758794e-05)
+
                                                                             
Step... (68750 / 100000 | Loss: 0.6505287885665894, Learning Rate: 3.14070351758794e-05)
+
Train steps ... :  69%|██████▉   | 68750/100000 [20:26:19<5:04:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 68751/100000 [20:26:20<5:05:35,  1.70it/s]
Train steps ... :  69%|██████▉   | 68752/100000 [20:26:20<5:04:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68753/100000 [20:26:21<5:04:24,  1.71it/s]
Train steps ... :  69%|██████▉   | 68754/100000 [20:26:21<5:04:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 68755/100000 [20:26:22<5:04:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 68756/100000 [20:26:22<5:04:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 68757/100000 [20:26:23<5:04:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 68758/100000 [20:26:24<5:04:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 68759/100000 [20:26:24<5:04:31,  1.71it/s]
Train steps ... :  69%|██████▉   | 68760/100000 [20:26:25<5:04:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 68761/100000 [20:26:25<5:05:36,  1.70it/s]
Train steps ... :  69%|██████▉   | 68762/100000 [20:26:26<5:04:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 68763/100000 [20:26:27<5:04:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 68764/100000 [20:26:27<5:04:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 68765/100000 [20:26:28<5:04:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 68766/100000 [20:26:28<5:04:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 68767/100000 [20:26:29<5:04:20,  1.71it/s]
Train steps ... :  69%|██████▉   | 68768/100000 [20:26:30<5:04:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68769/100000 [20:26:30<5:04:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 68770/100000 [20:26:31<5:04:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 68771/100000 [20:26:31<5:04:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 68772/100000 [20:26:32<5:04:43,  1.71it/s]
Train steps ... :  69%|██████▉   | 68773/100000 [20:26:32<5:04:56,  1.71it/s]
Train steps ... :  69%|██████▉   | 68774/100000 [20:26:33<5:04:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 68775/100000 [20:26:34<5:04:25,  1.71it/s]Step... (68775 / 100000 | Loss: 0.707633376121521, Learning Rate: 3.13819095477387e-05)
+
                                                                             
Step... (68775 / 100000 | Loss: 0.5635955333709717, Learning Rate: 3.13819095477387e-05)
+
Train steps ... :  69%|██████▉   | 68775/100000 [20:26:34<5:04:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 68776/100000 [20:26:34<5:04:43,  1.71it/s]
Train steps ... :  69%|██████▉   | 68777/100000 [20:26:35<5:04:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 68778/100000 [20:26:35<5:05:28,  1.70it/s]
Train steps ... :  69%|██████▉   | 68779/100000 [20:26:36<5:05:26,  1.70it/s]
Train steps ... :  69%|██████▉   | 68780/100000 [20:26:37<5:04:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 68781/100000 [20:26:37<5:04:31,  1.71it/s]
Train steps ... :  69%|██████▉   | 68782/100000 [20:26:38<5:05:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 68783/100000 [20:26:38<5:04:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 68784/100000 [20:26:39<5:04:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 68785/100000 [20:26:39<5:04:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 68786/100000 [20:26:40<5:04:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 68787/100000 [20:26:41<5:04:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 68788/100000 [20:26:41<5:04:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 68789/100000 [20:26:42<5:04:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 68790/100000 [20:26:42<5:05:15,  1.70it/s]
Train steps ... :  69%|██████▉   | 68791/100000 [20:26:43<5:04:20,  1.71it/s]
Train steps ... :  69%|██████▉   | 68792/100000 [20:26:44<5:04:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 68793/100000 [20:26:44<5:05:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 68794/100000 [20:26:45<5:04:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 68795/100000 [20:26:45<5:04:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 68796/100000 [20:26:46<5:04:50,  1.71it/s]
Train steps ... :  69%|██████▉   | 68797/100000 [20:26:46<5:04:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 68798/100000 [20:26:47<5:04:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 68799/100000 [20:26:48<5:04:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 68800/100000 [20:26:48<5:03:46,  1.71it/s]Step... (68800 / 100000 | Loss: 1.1515052318572998, Learning Rate: 3.1356783919597993e-05)
+
                                                                             
Step... (68800 / 100000 | Loss: 0.6717760562896729, Learning Rate: 3.1356783919597993e-05)
+
Train steps ... :  69%|██████▉   | 68800/100000 [20:26:49<5:03:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 68801/100000 [20:26:49<5:03:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 68802/100000 [20:26:49<5:03:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 68803/100000 [20:26:50<5:04:04,  1.71it/s]
Train steps ... :  69%|██████▉   | 68804/100000 [20:26:51<5:03:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 68805/100000 [20:26:51<5:03:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 68806/100000 [20:26:52<5:03:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 68807/100000 [20:26:52<5:04:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 68808/100000 [20:26:53<5:04:16,  1.71it/s]
Train steps ... :  69%|██████▉   | 68809/100000 [20:26:54<5:04:05,  1.71it/s]
Train steps ... :  69%|██████▉   | 68810/100000 [20:26:54<5:04:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 68811/100000 [20:26:55<5:03:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 68812/100000 [20:26:55<5:03:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 68813/100000 [20:26:56<5:04:13,  1.71it/s]
Train steps ... :  69%|██████▉   | 68814/100000 [20:26:56<5:04:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 68815/100000 [20:26:57<5:03:44,  1.71it/s]
Train steps ... :  69%|██████▉   | 68816/100000 [20:26:58<5:03:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 68817/100000 [20:26:58<5:03:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 68818/100000 [20:26:59<5:03:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 68819/100000 [20:26:59<5:03:33,  1.71it/s]
Train steps ... :  69%|██████▉   | 68820/100000 [20:27:00<5:03:31,  1.71it/s]
Train steps ... :  69%|██████▉   | 68821/100000 [20:27:01<5:04:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 68822/100000 [20:27:01<5:04:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 68823/100000 [20:27:02<5:04:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 68824/100000 [20:27:02<5:04:05,  1.71it/s]
Train steps ... :  69%|██████▉   | 68825/100000 [20:27:03<5:04:18,  1.71it/s]Step... (68825 / 100000 | Loss: 0.6519793272018433, Learning Rate: 3.133165829145729e-05)
+
                                                                             
Step... (68825 / 100000 | Loss: 0.5802293419837952, Learning Rate: 3.133165829145729e-05)
+
Train steps ... :  69%|██████▉   | 68825/100000 [20:27:03<5:04:18,  1.71it/s]
Train steps ... :  69%|██████▉   | 68826/100000 [20:27:03<5:04:19,  1.71it/s]
Train steps ... :  69%|██████▉   | 68827/100000 [20:27:04<5:04:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 68828/100000 [20:27:05<5:03:33,  1.71it/s]
Train steps ... :  69%|██████▉   | 68829/100000 [20:27:05<5:03:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 68830/100000 [20:27:06<5:05:05,  1.70it/s]
Train steps ... :  69%|██████▉   | 68831/100000 [20:27:06<5:03:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 68832/100000 [20:27:07<5:03:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 68833/100000 [20:27:08<5:03:57,  1.71it/s]
Train steps ... :  69%|██████▉   | 68834/100000 [20:27:08<5:03:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 68835/100000 [20:27:09<5:03:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 68836/100000 [20:27:09<5:03:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 68837/100000 [20:27:10<5:03:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 68838/100000 [20:27:10<5:03:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 68839/100000 [20:27:11<5:03:24,  1.71it/s]
Train steps ... :  69%|██████▉   | 68840/100000 [20:27:12<5:03:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68841/100000 [20:27:12<5:03:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68842/100000 [20:27:13<5:03:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68843/100000 [20:27:13<5:03:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 68844/100000 [20:27:14<5:03:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 68845/100000 [20:27:15<5:03:42,  1.71it/s]
Train steps ... :  69%|██████▉   | 68846/100000 [20:27:15<5:03:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 68847/100000 [20:27:16<5:03:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 68848/100000 [20:27:16<5:03:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 68849/100000 [20:27:17<5:03:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 68850/100000 [20:27:17<5:03:23,  1.71it/s]Step... (68850 / 100000 | Loss: 0.6338211894035339, Learning Rate: 3.130653266331659e-05)
+
                                                                             
Step... (68850 / 100000 | Loss: 0.5942019820213318, Learning Rate: 3.130653266331659e-05)
+
Train steps ... :  69%|██████▉   | 68850/100000 [20:27:18<5:03:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 68851/100000 [20:27:18<5:04:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 68852/100000 [20:27:19<5:04:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 68853/100000 [20:27:19<5:03:31,  1.71it/s]
Train steps ... :  69%|██████▉   | 68854/100000 [20:27:20<5:03:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 68855/100000 [20:27:20<5:04:57,  1.70it/s]
Train steps ... :  69%|██████▉   | 68856/100000 [20:27:21<5:03:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 68857/100000 [20:27:22<5:03:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 68858/100000 [20:27:22<5:03:24,  1.71it/s]
Train steps ... :  69%|██████▉   | 68859/100000 [20:27:23<5:03:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 68860/100000 [20:27:23<5:03:04,  1.71it/s]
Train steps ... :  69%|██████▉   | 68861/100000 [20:27:24<5:03:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 68862/100000 [20:27:25<5:03:42,  1.71it/s]
Train steps ... :  69%|██████▉   | 68863/100000 [20:27:25<5:03:24,  1.71it/s]
Train steps ... :  69%|██████▉   | 68864/100000 [20:27:26<5:03:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 68865/100000 [20:27:26<5:03:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 68866/100000 [20:27:27<5:03:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 68867/100000 [20:27:27<5:03:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 68868/100000 [20:27:28<5:03:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 68869/100000 [20:27:29<5:03:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 68870/100000 [20:27:29<5:03:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68871/100000 [20:27:30<5:03:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 68872/100000 [20:27:30<5:03:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 68873/100000 [20:27:31<5:03:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 68874/100000 [20:27:32<5:03:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68875/100000 [20:27:32<5:04:09,  1.71it/s]Step... (68875 / 100000 | Loss: 0.6326768398284912, Learning Rate: 3.128140703517588e-05)
+
                                                                             
Step... (68875 / 100000 | Loss: 0.5242868661880493, Learning Rate: 3.128140703517588e-05)
+
Train steps ... :  69%|██████▉   | 68875/100000 [20:27:32<5:04:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 68876/100000 [20:27:33<5:04:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 68877/100000 [20:27:33<5:03:43,  1.71it/s]
Train steps ... :  69%|██████▉   | 68878/100000 [20:27:34<5:03:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 68879/100000 [20:27:34<5:03:20,  1.71it/s]
Train steps ... :  69%|██████▉   | 68880/100000 [20:27:35<5:03:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 68881/100000 [20:27:36<5:03:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 68882/100000 [20:27:36<5:03:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 68883/100000 [20:27:37<5:04:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 68884/100000 [20:27:37<5:03:50,  1.71it/s]
Train steps ... :  69%|██████▉   | 68885/100000 [20:27:38<5:03:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 68886/100000 [20:27:39<5:03:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 68887/100000 [20:27:39<5:03:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 68888/100000 [20:27:40<5:03:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 68889/100000 [20:27:40<5:03:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 68890/100000 [20:27:41<5:04:28,  1.70it/s]
Train steps ... :  69%|██████▉   | 68891/100000 [20:27:41<5:03:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 68892/100000 [20:27:42<5:03:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 68893/100000 [20:27:43<5:03:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 68894/100000 [20:27:43<5:03:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 68895/100000 [20:27:44<5:03:07,  1.71it/s]
Train steps ... :  69%|██████▉   | 68896/100000 [20:27:44<5:02:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 68897/100000 [20:27:45<5:03:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 68898/100000 [20:27:46<5:02:56,  1.71it/s]
Train steps ... :  69%|██████▉   | 68899/100000 [20:27:46<5:02:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 68900/100000 [20:27:47<5:02:52,  1.71it/s]Step... (68900 / 100000 | Loss: 0.5501977205276489, Learning Rate: 3.125628140703517e-05)
+
                                                                             
Step... (68900 / 100000 | Loss: 0.6644574999809265, Learning Rate: 3.125628140703517e-05)
+
Train steps ... :  69%|██████▉   | 68900/100000 [20:27:47<5:02:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 68901/100000 [20:27:47<5:02:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 68902/100000 [20:27:48<5:02:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68903/100000 [20:27:49<5:02:43,  1.71it/s]
Train steps ... :  69%|██████▉   | 68904/100000 [20:27:49<5:02:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 68905/100000 [20:27:50<5:02:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 68906/100000 [20:27:50<5:02:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 68907/100000 [20:27:51<5:03:12,  1.71it/s]
Train steps ... :  69%|██████▉   | 68908/100000 [20:27:51<5:03:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 68909/100000 [20:27:52<5:02:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 68910/100000 [20:27:53<5:02:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 68911/100000 [20:27:53<5:02:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 68912/100000 [20:27:54<5:02:56,  1.71it/s]
Train steps ... :  69%|██████▉   | 68913/100000 [20:27:54<5:02:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68914/100000 [20:27:55<5:02:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 68915/100000 [20:27:56<5:02:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 68916/100000 [20:27:56<5:03:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 68917/100000 [20:27:57<5:02:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 68918/100000 [20:27:57<5:02:44,  1.71it/s]
Train steps ... :  69%|██████▉   | 68919/100000 [20:27:58<5:02:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 68920/100000 [20:27:58<5:03:13,  1.71it/s]
Train steps ... :  69%|██████▉   | 68921/100000 [20:27:59<5:02:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 68922/100000 [20:28:00<5:02:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 68923/100000 [20:28:00<5:02:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 68924/100000 [20:28:01<5:02:42,  1.71it/s]
Train steps ... :  69%|██████▉   | 68925/100000 [20:28:01<5:02:37,  1.71it/s]Step... (68925 / 100000 | Loss: 0.6923036575317383, Learning Rate: 3.123115577889447e-05)
+
                                                                             
Step... (68925 / 100000 | Loss: 0.6564702987670898, Learning Rate: 3.123115577889447e-05)
+
Train steps ... :  69%|██████▉   | 68925/100000 [20:28:02<5:02:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 68926/100000 [20:28:02<5:02:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 68927/100000 [20:28:03<5:02:57,  1.71it/s]
Train steps ... :  69%|██████▉   | 68928/100000 [20:28:03<5:02:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 68929/100000 [20:28:04<5:02:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 68930/100000 [20:28:04<5:02:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 68931/100000 [20:28:05<5:03:21,  1.71it/s]
Train steps ... :  69%|██████▉   | 68932/100000 [20:28:05<5:03:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 68933/100000 [20:28:06<5:02:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 68934/100000 [20:28:07<5:03:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 68935/100000 [20:28:07<5:03:16,  1.71it/s]
Train steps ... :  69%|██████▉   | 68936/100000 [20:28:08<5:02:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 68937/100000 [20:28:08<5:03:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 68938/100000 [20:28:09<5:02:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 68939/100000 [20:28:10<5:02:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68940/100000 [20:28:10<5:02:57,  1.71it/s]
Train steps ... :  69%|██████▉   | 68941/100000 [20:28:11<5:03:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 68942/100000 [20:28:11<5:03:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 68943/100000 [20:28:12<5:02:44,  1.71it/s]
Train steps ... :  69%|██████▉   | 68944/100000 [20:28:12<5:02:33,  1.71it/s]
Train steps ... :  69%|██████▉   | 68945/100000 [20:28:13<5:02:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 68946/100000 [20:28:14<5:02:56,  1.71it/s]
Train steps ... :  69%|██████▉   | 68947/100000 [20:28:14<5:02:31,  1.71it/s]
Train steps ... :  69%|██████▉   | 68948/100000 [20:28:15<5:02:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 68949/100000 [20:28:15<5:02:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 68950/100000 [20:28:16<5:02:25,  1.71it/s]Step... (68950 / 100000 | Loss: 0.6537180542945862, Learning Rate: 3.1206030150753766e-05)
+
                                                                             
Step... (68950 / 100000 | Loss: 0.7106592655181885, Learning Rate: 3.1206030150753766e-05)
+
Train steps ... :  69%|██████▉   | 68950/100000 [20:28:16<5:02:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 68951/100000 [20:28:17<5:02:19,  1.71it/s]
Train steps ... :  69%|██████▉   | 68952/100000 [20:28:17<5:02:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 68953/100000 [20:28:18<5:02:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 68954/100000 [20:28:18<5:02:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 68955/100000 [20:28:19<5:02:56,  1.71it/s]
Train steps ... :  69%|██████▉   | 68956/100000 [20:28:20<5:02:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 68957/100000 [20:28:20<5:02:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 68958/100000 [20:28:21<5:02:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 68959/100000 [20:28:21<5:03:20,  1.71it/s]
Train steps ... :  69%|██████▉   | 68960/100000 [20:28:22<5:02:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 68961/100000 [20:28:22<5:02:43,  1.71it/s]
Train steps ... :  69%|██████▉   | 68962/100000 [20:28:23<5:02:16,  1.71it/s]
Train steps ... :  69%|██████▉   | 68963/100000 [20:28:24<5:02:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68964/100000 [20:28:24<5:02:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 68965/100000 [20:28:25<5:02:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 68966/100000 [20:28:25<5:02:13,  1.71it/s]
Train steps ... :  69%|██████▉   | 68967/100000 [20:28:26<5:02:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 68968/100000 [20:28:27<5:02:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 68969/100000 [20:28:27<5:02:31,  1.71it/s]
Train steps ... :  69%|██████▉   | 68970/100000 [20:28:28<5:02:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 68971/100000 [20:28:28<5:02:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 68972/100000 [20:28:29<5:02:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 68973/100000 [20:28:29<5:02:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 68974/100000 [20:28:30<5:02:21,  1.71it/s]
Train steps ... :  69%|██████▉   | 68975/100000 [20:28:31<5:02:33,  1.71it/s]Step... (68975 / 100000 | Loss: 0.7798730134963989, Learning Rate: 3.118090452261307e-05)
+
                                                                             
Step... (68975 / 100000 | Loss: 0.8017895221710205, Learning Rate: 3.118090452261307e-05)
+
Train steps ... :  69%|██████▉   | 68975/100000 [20:28:31<5:02:33,  1.71it/s]
Train steps ... :  69%|██████▉   | 68976/100000 [20:28:31<5:02:42,  1.71it/s]
Train steps ... :  69%|██████▉   | 68977/100000 [20:28:32<5:02:20,  1.71it/s]
Train steps ... :  69%|██████▉   | 68978/100000 [20:28:32<5:02:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 68979/100000 [20:28:33<5:02:20,  1.71it/s]
Train steps ... :  69%|██████▉   | 68980/100000 [20:28:34<5:02:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 68981/100000 [20:28:34<5:02:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 68982/100000 [20:28:35<5:02:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 68983/100000 [20:28:35<5:02:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 68984/100000 [20:28:36<5:02:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 68985/100000 [20:28:36<5:02:16,  1.71it/s]
Train steps ... :  69%|██████▉   | 68986/100000 [20:28:37<5:02:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 68987/100000 [20:28:38<5:02:21,  1.71it/s]
Train steps ... :  69%|██████▉   | 68988/100000 [20:28:38<5:02:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 68989/100000 [20:28:39<5:02:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 68990/100000 [20:28:39<5:02:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 68991/100000 [20:28:40<5:02:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 68992/100000 [20:28:41<5:02:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 68993/100000 [20:28:41<5:02:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 68994/100000 [20:28:42<5:02:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 68995/100000 [20:28:42<5:02:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 68996/100000 [20:28:43<5:02:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 68997/100000 [20:28:43<5:01:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 68998/100000 [20:28:44<5:01:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 68999/100000 [20:28:45<5:02:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 69000/100000 [20:28:45<5:02:11,  1.71it/s]Step... (69000 / 100000 | Loss: 0.731881320476532, Learning Rate: 3.1155778894472366e-05)
+
                                                                             
Step... (69000 / 100000 | Loss: 0.6007862091064453, Learning Rate: 3.1155778894472366e-05)
+
Train steps ... :  69%|██████▉   | 69000/100000 [20:28:46<5:02:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69001/100000 [20:28:46<5:02:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 69002/100000 [20:28:46<5:01:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 69003/100000 [20:28:47<5:01:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69004/100000 [20:28:48<5:01:43,  1.71it/s]
Train steps ... :  69%|██████▉   | 69005/100000 [20:28:48<5:01:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69006/100000 [20:28:49<5:01:44,  1.71it/s]
Train steps ... :  69%|██████▉   | 69007/100000 [20:28:49<5:01:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 69008/100000 [20:28:50<5:01:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69009/100000 [20:28:50<5:02:00,  1.71it/s]
Train steps ... :  69%|██████▉   | 69010/100000 [20:28:51<5:01:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 69011/100000 [20:28:52<5:01:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 69012/100000 [20:28:52<5:02:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69013/100000 [20:28:53<5:01:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 69014/100000 [20:28:53<5:01:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69015/100000 [20:28:54<5:02:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 69016/100000 [20:28:55<5:01:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 69017/100000 [20:28:55<5:01:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 69018/100000 [20:28:56<5:01:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69019/100000 [20:28:56<5:01:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69020/100000 [20:28:57<5:01:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 69021/100000 [20:28:58<5:01:56,  1.71it/s]
Train steps ... :  69%|██████▉   | 69022/100000 [20:28:58<5:01:57,  1.71it/s]
Train steps ... :  69%|██████▉   | 69023/100000 [20:28:59<5:02:07,  1.71it/s]
Train steps ... :  69%|██████▉   | 69024/100000 [20:28:59<5:02:12,  1.71it/s]
Train steps ... :  69%|██████▉   | 69025/100000 [20:29:00<5:02:03,  1.71it/s]Step... (69025 / 100000 | Loss: 0.6758431792259216, Learning Rate: 3.113065326633166e-05)
+
                                                                             
Step... (69025 / 100000 | Loss: 0.5662142038345337, Learning Rate: 3.113065326633166e-05)
+
Train steps ... :  69%|██████▉   | 69025/100000 [20:29:00<5:02:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69026/100000 [20:29:00<5:02:12,  1.71it/s]
Train steps ... :  69%|██████▉   | 69027/100000 [20:29:01<5:02:07,  1.71it/s]
Train steps ... :  69%|██████▉   | 69028/100000 [20:29:02<5:02:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 69029/100000 [20:29:02<5:02:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 69030/100000 [20:29:03<5:02:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 69031/100000 [20:29:03<5:01:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 69032/100000 [20:29:04<5:01:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 69033/100000 [20:29:05<5:01:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 69034/100000 [20:29:05<5:01:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69035/100000 [20:29:06<5:01:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69036/100000 [20:29:06<5:01:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69037/100000 [20:29:07<5:01:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69038/100000 [20:29:07<5:01:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 69039/100000 [20:29:08<5:01:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 69040/100000 [20:29:09<5:01:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69041/100000 [20:29:09<5:01:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 69042/100000 [20:29:10<5:01:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 69043/100000 [20:29:10<5:02:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 69044/100000 [20:29:11<5:01:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 69045/100000 [20:29:12<5:01:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 69046/100000 [20:29:12<5:01:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 69047/100000 [20:29:13<5:01:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69048/100000 [20:29:13<5:01:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 69049/100000 [20:29:14<5:01:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 69050/100000 [20:29:14<5:02:12,  1.71it/s]Step... (69050 / 100000 | Loss: 0.7843517661094666, Learning Rate: 3.110552763819096e-05)
+
                                                                             
Step... (69050 / 100000 | Loss: 0.6102793216705322, Learning Rate: 3.110552763819096e-05)
+
Train steps ... :  69%|██████▉   | 69050/100000 [20:29:15<5:02:12,  1.71it/s]
Train steps ... :  69%|██████▉   | 69051/100000 [20:29:15<5:02:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69052/100000 [20:29:16<5:02:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69053/100000 [20:29:16<5:01:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 69054/100000 [20:29:17<5:01:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 69055/100000 [20:29:17<5:01:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69056/100000 [20:29:18<5:01:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 69057/100000 [20:29:19<5:01:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 69058/100000 [20:29:19<5:01:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69059/100000 [20:29:20<5:01:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69060/100000 [20:29:20<5:01:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 69061/100000 [20:29:21<5:01:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69062/100000 [20:29:22<5:01:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 69063/100000 [20:29:22<5:01:12,  1.71it/s]
Train steps ... :  69%|██████▉   | 69064/100000 [20:29:23<5:01:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69065/100000 [20:29:23<5:01:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69066/100000 [20:29:24<5:01:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69067/100000 [20:29:24<5:01:31,  1.71it/s]
Train steps ... :  69%|██████▉   | 69068/100000 [20:29:25<5:01:42,  1.71it/s]
Train steps ... :  69%|██████▉   | 69069/100000 [20:29:26<5:01:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 69070/100000 [20:29:26<5:01:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69071/100000 [20:29:27<5:01:24,  1.71it/s]
Train steps ... :  69%|██████▉   | 69072/100000 [20:29:27<5:01:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 69073/100000 [20:29:28<5:01:12,  1.71it/s]
Train steps ... :  69%|██████▉   | 69074/100000 [20:29:29<5:01:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 69075/100000 [20:29:29<5:01:09,  1.71it/s]Step... (69075 / 100000 | Loss: 0.8907006978988647, Learning Rate: 3.108040201005025e-05)
+
                                                                             
Step... (69075 / 100000 | Loss: 0.6658567786216736, Learning Rate: 3.108040201005025e-05)
+
Train steps ... :  69%|██████▉   | 69075/100000 [20:29:29<5:01:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 69076/100000 [20:29:30<5:02:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 69077/100000 [20:29:30<5:01:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 69078/100000 [20:29:31<5:01:21,  1.71it/s]
Train steps ... :  69%|██████▉   | 69079/100000 [20:29:31<5:01:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69080/100000 [20:29:32<5:01:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69081/100000 [20:29:33<5:02:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69082/100000 [20:29:33<5:01:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 69083/100000 [20:29:34<5:01:31,  1.71it/s]
Train steps ... :  69%|██████▉   | 69084/100000 [20:29:34<5:01:16,  1.71it/s]
Train steps ... :  69%|██████▉   | 69085/100000 [20:29:35<5:01:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69086/100000 [20:29:36<5:01:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 69087/100000 [20:29:36<5:01:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69088/100000 [20:29:37<5:01:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 69089/100000 [20:29:37<5:01:19,  1.71it/s]
Train steps ... :  69%|██████▉   | 69090/100000 [20:29:38<5:01:43,  1.71it/s]
Train steps ... :  69%|██████▉   | 69091/100000 [20:29:38<5:01:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 69092/100000 [20:29:39<5:01:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69093/100000 [20:29:40<5:01:10,  1.71it/s]
Train steps ... :  69%|██████▉   | 69094/100000 [20:29:40<5:01:16,  1.71it/s]
Train steps ... :  69%|██████▉   | 69095/100000 [20:29:41<5:00:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 69096/100000 [20:29:41<5:00:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 69097/100000 [20:29:42<5:00:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 69098/100000 [20:29:43<5:00:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 69099/100000 [20:29:43<5:00:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 69100/100000 [20:29:44<5:00:54,  1.71it/s]Step... (69100 / 100000 | Loss: 0.6435376405715942, Learning Rate: 3.1055276381909546e-05)
+
                                                                             
Step... (69100 / 100000 | Loss: 0.7350528240203857, Learning Rate: 3.1055276381909546e-05)
+
Train steps ... :  69%|██████▉   | 69100/100000 [20:29:44<5:00:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 69101/100000 [20:29:44<5:01:07,  1.71it/s]
Train steps ... :  69%|██████▉   | 69102/100000 [20:29:45<5:01:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 69103/100000 [20:29:45<5:01:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 69104/100000 [20:29:46<5:01:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 69105/100000 [20:29:47<5:00:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 69106/100000 [20:29:47<5:01:12,  1.71it/s]
Train steps ... :  69%|██████▉   | 69107/100000 [20:29:48<5:01:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69108/100000 [20:29:48<5:01:18,  1.71it/s]
Train steps ... :  69%|██████▉   | 69109/100000 [20:29:49<5:01:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 69110/100000 [20:29:50<5:01:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 69111/100000 [20:29:50<5:00:56,  1.71it/s]
Train steps ... :  69%|██████▉   | 69112/100000 [20:29:51<5:01:07,  1.71it/s]
Train steps ... :  69%|██████▉   | 69113/100000 [20:29:51<5:01:05,  1.71it/s]
Train steps ... :  69%|██████▉   | 69114/100000 [20:29:52<5:01:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69115/100000 [20:29:52<5:01:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 69116/100000 [20:29:53<5:01:18,  1.71it/s]
Train steps ... :  69%|██████▉   | 69117/100000 [20:29:54<5:00:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 69118/100000 [20:29:54<5:01:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 69119/100000 [20:29:55<5:01:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69120/100000 [20:29:55<5:01:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69121/100000 [20:29:56<5:01:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 69122/100000 [20:29:57<5:01:13,  1.71it/s]
Train steps ... :  69%|██████▉   | 69123/100000 [20:29:57<5:00:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 69124/100000 [20:29:58<5:00:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69125/100000 [20:29:58<5:00:37,  1.71it/s]Step... (69125 / 100000 | Loss: 0.8431616425514221, Learning Rate: 3.103015075376884e-05)
+
                                                                             
Step... (69125 / 100000 | Loss: 0.557612955570221, Learning Rate: 3.103015075376884e-05)
+
Train steps ... :  69%|██████▉   | 69125/100000 [20:29:59<5:00:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69126/100000 [20:29:59<5:00:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 69127/100000 [20:30:00<5:00:50,  1.71it/s]
Train steps ... :  69%|██████▉   | 69128/100000 [20:30:00<5:01:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69129/100000 [20:30:01<5:01:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 69130/100000 [20:30:01<5:00:56,  1.71it/s]
Train steps ... :  69%|██████▉   | 69131/100000 [20:30:02<5:00:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 69132/100000 [20:30:02<5:00:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69133/100000 [20:30:03<5:00:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69134/100000 [20:30:04<5:00:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69135/100000 [20:30:04<5:00:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 69136/100000 [20:30:05<5:00:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69137/100000 [20:30:05<5:00:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 69138/100000 [20:30:06<5:00:42,  1.71it/s]
Train steps ... :  69%|██████▉   | 69139/100000 [20:30:07<5:00:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69140/100000 [20:30:07<5:00:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 69141/100000 [20:30:08<5:01:10,  1.71it/s]
Train steps ... :  69%|██████▉   | 69142/100000 [20:30:08<5:01:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69143/100000 [20:30:09<5:01:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 69144/100000 [20:30:09<5:02:03,  1.70it/s]
Train steps ... :  69%|██████▉   | 69145/100000 [20:30:10<5:01:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 69146/100000 [20:30:11<5:01:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 69147/100000 [20:30:11<5:00:50,  1.71it/s]
Train steps ... :  69%|██████▉   | 69148/100000 [20:30:12<5:00:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 69149/100000 [20:30:12<5:00:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 69150/100000 [20:30:13<5:01:28,  1.71it/s]Step... (69150 / 100000 | Loss: 0.6106332540512085, Learning Rate: 3.100502512562814e-05)
+
                                                                             
Step... (69150 / 100000 | Loss: 0.8793241381645203, Learning Rate: 3.100502512562814e-05)
+
Train steps ... :  69%|██████▉   | 69150/100000 [20:30:13<5:01:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 69151/100000 [20:30:14<5:01:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 69152/100000 [20:30:14<5:01:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 69153/100000 [20:30:15<5:01:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 69154/100000 [20:30:15<5:01:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 69155/100000 [20:30:16<5:00:57,  1.71it/s]
Train steps ... :  69%|██████▉   | 69156/100000 [20:30:16<5:00:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69157/100000 [20:30:17<5:00:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 69158/100000 [20:30:18<5:01:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69159/100000 [20:30:18<5:01:58,  1.70it/s]
Train steps ... :  69%|██████▉   | 69160/100000 [20:30:19<5:01:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69161/100000 [20:30:19<5:01:00,  1.71it/s]
Train steps ... :  69%|██████▉   | 69162/100000 [20:30:20<5:00:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 69163/100000 [20:30:21<5:00:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 69164/100000 [20:30:21<5:00:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69165/100000 [20:30:22<5:00:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 69166/100000 [20:30:22<5:00:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69167/100000 [20:30:23<5:00:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 69168/100000 [20:30:24<5:00:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 69169/100000 [20:30:24<5:00:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 69170/100000 [20:30:25<5:00:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69171/100000 [20:30:25<5:00:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 69172/100000 [20:30:26<5:00:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69173/100000 [20:30:26<5:00:42,  1.71it/s]
Train steps ... :  69%|██████▉   | 69174/100000 [20:30:27<5:00:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69175/100000 [20:30:28<5:00:48,  1.71it/s]Step... (69175 / 100000 | Loss: 0.8402488827705383, Learning Rate: 3.097989949748744e-05)
+
                                                                             
Step... (69175 / 100000 | Loss: 0.5618478059768677, Learning Rate: 3.097989949748744e-05)
+
Train steps ... :  69%|██████▉   | 69175/100000 [20:30:28<5:00:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 69176/100000 [20:30:28<5:01:00,  1.71it/s]
Train steps ... :  69%|██████▉   | 69177/100000 [20:30:29<5:01:31,  1.70it/s]
Train steps ... :  69%|██████▉   | 69178/100000 [20:30:29<5:01:42,  1.70it/s]
Train steps ... :  69%|██████▉   | 69179/100000 [20:30:30<5:01:35,  1.70it/s]
Train steps ... :  69%|██████▉   | 69180/100000 [20:30:31<5:01:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 69181/100000 [20:30:31<5:00:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 69182/100000 [20:30:32<5:01:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 69183/100000 [20:30:32<5:00:31,  1.71it/s]
Train steps ... :  69%|██████▉   | 69184/100000 [20:30:33<5:00:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 69185/100000 [20:30:33<5:01:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69186/100000 [20:30:34<5:00:44,  1.71it/s]
Train steps ... :  69%|██████▉   | 69187/100000 [20:30:35<5:00:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69188/100000 [20:30:35<5:00:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 69189/100000 [20:30:36<5:00:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 69190/100000 [20:30:36<5:00:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69191/100000 [20:30:37<5:00:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69192/100000 [20:30:38<5:00:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 69193/100000 [20:30:38<5:00:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69194/100000 [20:30:39<5:00:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 69195/100000 [20:30:39<5:00:50,  1.71it/s]
Train steps ... :  69%|██████▉   | 69196/100000 [20:30:40<5:00:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 69197/100000 [20:30:41<5:00:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 69198/100000 [20:30:41<5:00:05,  1.71it/s]
Train steps ... :  69%|██████▉   | 69199/100000 [20:30:42<5:00:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 69200/100000 [20:30:42<5:00:20,  1.71it/s]Step... (69200 / 100000 | Loss: 0.4961020350456238, Learning Rate: 3.095477386934674e-05)
+
                                                                             
Step... (69200 / 100000 | Loss: 0.6768416166305542, Learning Rate: 3.095477386934674e-05)
+
Train steps ... :  69%|██████▉   | 69200/100000 [20:30:43<5:00:20,  1.71it/s]
Train steps ... :  69%|██████▉   | 69201/100000 [20:30:43<5:00:33,  1.71it/s]
Train steps ... :  69%|██████▉   | 69202/100000 [20:30:43<5:00:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69203/100000 [20:30:44<5:00:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 69204/100000 [20:30:45<5:00:19,  1.71it/s]
Train steps ... :  69%|██████▉   | 69205/100000 [20:30:45<5:00:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69206/100000 [20:30:46<5:00:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69207/100000 [20:30:46<5:00:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 69208/100000 [20:30:47<5:00:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69209/100000 [20:30:48<5:00:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 69210/100000 [20:30:48<4:59:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69211/100000 [20:30:49<4:59:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69212/100000 [20:30:49<4:59:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69213/100000 [20:30:50<5:00:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 69214/100000 [20:30:50<5:00:16,  1.71it/s]
Train steps ... :  69%|██████▉   | 69215/100000 [20:30:51<5:00:05,  1.71it/s]
Train steps ... :  69%|██████▉   | 69216/100000 [20:30:52<5:00:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 69217/100000 [20:30:52<5:00:07,  1.71it/s]
Train steps ... :  69%|██████▉   | 69218/100000 [20:30:53<4:59:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69219/100000 [20:30:53<4:59:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 69220/100000 [20:30:54<5:00:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 69221/100000 [20:30:55<5:00:44,  1.71it/s]
Train steps ... :  69%|██████▉   | 69222/100000 [20:30:55<5:00:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69223/100000 [20:30:56<5:00:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69224/100000 [20:30:56<5:00:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 69225/100000 [20:30:57<5:00:55,  1.70it/s]Step... (69225 / 100000 | Loss: 0.662776529788971, Learning Rate: 3.0929648241206036e-05)
+
                                                                             
Step... (69225 / 100000 | Loss: 0.6508867144584656, Learning Rate: 3.0929648241206036e-05)
+
Train steps ... :  69%|██████▉   | 69225/100000 [20:30:57<5:00:55,  1.70it/s]
Train steps ... :  69%|██████▉   | 69226/100000 [20:30:57<5:00:49,  1.70it/s]
Train steps ... :  69%|██████▉   | 69227/100000 [20:30:58<5:01:23,  1.70it/s]
Train steps ... :  69%|██████▉   | 69228/100000 [20:30:59<5:00:33,  1.71it/s]
Train steps ... :  69%|██████▉   | 69229/100000 [20:30:59<5:00:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 69230/100000 [20:31:00<5:01:55,  1.70it/s]
Train steps ... :  69%|██████▉   | 69231/100000 [20:31:00<5:01:15,  1.70it/s]
Train steps ... :  69%|██████▉   | 69232/100000 [20:31:01<5:02:02,  1.70it/s]
Train steps ... :  69%|██████▉   | 69233/100000 [20:31:02<5:00:49,  1.70it/s]
Train steps ... :  69%|██████▉   | 69234/100000 [20:31:02<5:00:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69235/100000 [20:31:03<5:01:20,  1.70it/s]
Train steps ... :  69%|██████▉   | 69236/100000 [20:31:03<5:00:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69237/100000 [20:31:04<5:00:07,  1.71it/s]
Train steps ... :  69%|██████▉   | 69238/100000 [20:31:05<5:00:51,  1.70it/s]
Train steps ... :  69%|██████▉   | 69239/100000 [20:31:05<5:00:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69240/100000 [20:31:06<5:00:47,  1.70it/s]
Train steps ... :  69%|██████▉   | 69241/100000 [20:31:06<5:01:29,  1.70it/s]
Train steps ... :  69%|██████▉   | 69242/100000 [20:31:07<5:00:33,  1.71it/s]
Train steps ... :  69%|██████▉   | 69243/100000 [20:31:07<5:01:11,  1.70it/s]
Train steps ... :  69%|██████▉   | 69244/100000 [20:31:08<5:00:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 69245/100000 [20:31:09<5:00:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 69246/100000 [20:31:09<5:00:21,  1.71it/s]
Train steps ... :  69%|██████▉   | 69247/100000 [20:31:10<5:00:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 69248/100000 [20:31:10<5:00:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 69249/100000 [20:31:11<5:00:24,  1.71it/s]
Train steps ... :  69%|██████▉   | 69250/100000 [20:31:12<5:00:33,  1.71it/s]Step... (69250 / 100000 | Loss: 0.5116176605224609, Learning Rate: 3.0904522613065326e-05)
+
                                                                             
Step... (69250 / 100000 | Loss: 0.7663270235061646, Learning Rate: 3.0904522613065326e-05)
+
Train steps ... :  69%|██████▉   | 69250/100000 [20:31:12<5:00:33,  1.71it/s]
Train steps ... :  69%|██████▉   | 69251/100000 [20:31:12<5:00:40,  1.70it/s]
Train steps ... :  69%|██████▉   | 69252/100000 [20:31:13<5:00:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 69253/100000 [20:31:13<5:00:55,  1.70it/s]
Train steps ... :  69%|██████▉   | 69254/100000 [20:31:14<5:00:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 69255/100000 [20:31:14<5:01:29,  1.70it/s]
Train steps ... :  69%|██████▉   | 69256/100000 [20:31:15<5:01:01,  1.70it/s]
Train steps ... :  69%|██████▉   | 69257/100000 [20:31:16<5:00:37,  1.70it/s]
Train steps ... :  69%|██████▉   | 69258/100000 [20:31:16<5:00:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 69259/100000 [20:31:17<5:00:07,  1.71it/s]
Train steps ... :  69%|██████▉   | 69260/100000 [20:31:17<4:59:43,  1.71it/s]
Train steps ... :  69%|██████▉   | 69261/100000 [20:31:18<4:59:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69262/100000 [20:31:19<5:00:44,  1.70it/s]
Train steps ... :  69%|██████▉   | 69263/100000 [20:31:19<5:00:35,  1.70it/s]
Train steps ... :  69%|██████▉   | 69264/100000 [20:31:20<5:00:38,  1.70it/s]
Train steps ... :  69%|██████▉   | 69265/100000 [20:31:20<5:00:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69266/100000 [20:31:21<4:59:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 69267/100000 [20:31:22<4:59:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 69268/100000 [20:31:22<5:00:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 69269/100000 [20:31:23<5:00:24,  1.70it/s]
Train steps ... :  69%|██████▉   | 69270/100000 [20:31:23<4:59:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 69271/100000 [20:31:24<4:59:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 69272/100000 [20:31:24<5:00:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69273/100000 [20:31:25<4:59:42,  1.71it/s]
Train steps ... :  69%|██████▉   | 69274/100000 [20:31:26<5:00:04,  1.71it/s]
Train steps ... :  69%|██████▉   | 69275/100000 [20:31:26<5:00:17,  1.71it/s]Step... (69275 / 100000 | Loss: 0.7547838687896729, Learning Rate: 3.087939698492462e-05)
+
                                                                             
Step... (69275 / 100000 | Loss: 0.648597240447998, Learning Rate: 3.087939698492462e-05)
+
Train steps ... :  69%|██████▉   | 69275/100000 [20:31:27<5:00:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 69276/100000 [20:31:27<5:00:04,  1.71it/s]
Train steps ... :  69%|██████▉   | 69277/100000 [20:31:27<5:00:05,  1.71it/s]
Train steps ... :  69%|██████▉   | 69278/100000 [20:31:28<5:00:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69279/100000 [20:31:29<4:59:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 69280/100000 [20:31:29<4:59:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69281/100000 [20:31:30<5:00:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69282/100000 [20:31:30<4:59:50,  1.71it/s]
Train steps ... :  69%|██████▉   | 69283/100000 [20:31:31<4:59:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 69284/100000 [20:31:31<4:59:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69285/100000 [20:31:32<4:59:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69286/100000 [20:31:33<4:59:04,  1.71it/s]
Train steps ... :  69%|██████▉   | 69287/100000 [20:31:33<4:58:57,  1.71it/s]
Train steps ... :  69%|██████▉   | 69288/100000 [20:31:34<4:59:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69289/100000 [20:31:34<4:59:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69290/100000 [20:31:35<5:00:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 69291/100000 [20:31:36<4:59:44,  1.71it/s]
Train steps ... :  69%|██████▉   | 69292/100000 [20:31:36<4:59:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 69293/100000 [20:31:37<5:00:00,  1.71it/s]
Train steps ... :  69%|██████▉   | 69294/100000 [20:31:37<4:59:31,  1.71it/s]
Train steps ... :  69%|██████▉   | 69295/100000 [20:31:38<4:59:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69296/100000 [20:31:39<5:00:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 69297/100000 [20:31:39<4:59:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 69298/100000 [20:31:40<5:00:12,  1.70it/s]
Train steps ... :  69%|██████▉   | 69299/100000 [20:31:40<4:59:56,  1.71it/s]
Train steps ... :  69%|██████▉   | 69300/100000 [20:31:41<4:59:33,  1.71it/s]Step... (69300 / 100000 | Loss: 0.8443413972854614, Learning Rate: 3.085427135678392e-05)
+
                                                                             
Step... (69300 / 100000 | Loss: 0.648186445236206, Learning Rate: 3.085427135678392e-05)
+
Train steps ... :  69%|██████▉   | 69300/100000 [20:31:41<4:59:33,  1.71it/s]
Train steps ... :  69%|██████▉   | 69301/100000 [20:31:41<4:59:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 69302/100000 [20:31:42<5:00:20,  1.70it/s]
Train steps ... :  69%|██████▉   | 69303/100000 [20:31:43<4:59:18,  1.71it/s]
Train steps ... :  69%|██████▉   | 69304/100000 [20:31:43<4:59:21,  1.71it/s]
Train steps ... :  69%|██████▉   | 69305/100000 [20:31:44<4:59:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 69306/100000 [20:31:44<5:00:00,  1.71it/s]
Train steps ... :  69%|██████▉   | 69307/100000 [20:31:45<4:59:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 69308/100000 [20:31:46<4:59:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 69309/100000 [20:31:46<4:59:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69310/100000 [20:31:47<4:59:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 69311/100000 [20:31:47<4:59:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 69312/100000 [20:31:48<4:59:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 69313/100000 [20:31:48<4:59:57,  1.71it/s]
Train steps ... :  69%|██████▉   | 69314/100000 [20:31:49<5:00:01,  1.70it/s]
Train steps ... :  69%|██████▉   | 69315/100000 [20:31:50<4:59:58,  1.70it/s]
Train steps ... :  69%|██████▉   | 69316/100000 [20:31:50<5:00:08,  1.70it/s]
Train steps ... :  69%|██████▉   | 69317/100000 [20:31:51<4:59:59,  1.70it/s]
Train steps ... :  69%|██████▉   | 69318/100000 [20:31:51<4:59:48,  1.71it/s]
Train steps ... :  69%|██████▉   | 69319/100000 [20:31:52<4:59:43,  1.71it/s]
Train steps ... :  69%|██████▉   | 69320/100000 [20:31:53<4:59:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69321/100000 [20:31:53<4:59:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 69322/100000 [20:31:54<4:59:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69323/100000 [20:31:54<4:59:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 69324/100000 [20:31:55<4:59:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69325/100000 [20:31:55<4:58:58,  1.71it/s]Step... (69325 / 100000 | Loss: 0.559665858745575, Learning Rate: 3.0829145728643216e-05)
+
                                                                             
Step... (69325 / 100000 | Loss: 0.6808807849884033, Learning Rate: 3.0829145728643216e-05)
+
Train steps ... :  69%|██████▉   | 69325/100000 [20:31:56<4:58:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 69326/100000 [20:31:56<4:59:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 69327/100000 [20:31:57<4:59:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69328/100000 [20:31:57<4:58:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 69329/100000 [20:31:58<4:59:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 69330/100000 [20:31:58<4:59:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 69331/100000 [20:31:59<4:58:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 69332/100000 [20:32:00<4:58:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 69333/100000 [20:32:00<4:59:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69334/100000 [20:32:01<4:59:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69335/100000 [20:32:01<4:59:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 69336/100000 [20:32:02<4:58:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 69337/100000 [20:32:03<4:59:00,  1.71it/s]
Train steps ... :  69%|██████▉   | 69338/100000 [20:32:03<4:58:57,  1.71it/s]
Train steps ... :  69%|██████▉   | 69339/100000 [20:32:04<4:58:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69340/100000 [20:32:04<4:58:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 69341/100000 [20:32:05<4:59:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 69342/100000 [20:32:05<4:59:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 69343/100000 [20:32:06<4:58:44,  1.71it/s]
Train steps ... :  69%|██████▉   | 69344/100000 [20:32:07<4:59:19,  1.71it/s]
Train steps ... :  69%|██████▉   | 69345/100000 [20:32:07<4:59:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 69346/100000 [20:32:08<4:59:07,  1.71it/s]
Train steps ... :  69%|██████▉   | 69347/100000 [20:32:08<4:59:21,  1.71it/s]
Train steps ... :  69%|██████▉   | 69348/100000 [20:32:09<4:59:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 69349/100000 [20:32:10<4:59:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 69350/100000 [20:32:10<4:59:02,  1.71it/s]Step... (69350 / 100000 | Loss: 0.5815356969833374, Learning Rate: 3.080402010050251e-05)
+
                                                                             
Step... (69350 / 100000 | Loss: 0.8612112998962402, Learning Rate: 3.080402010050251e-05)
+
Train steps ... :  69%|██████▉   | 69350/100000 [20:32:10<4:59:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 69351/100000 [20:32:11<4:58:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 69352/100000 [20:32:11<4:58:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69353/100000 [20:32:12<4:58:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69354/100000 [20:32:12<4:58:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 69355/100000 [20:32:13<4:58:19,  1.71it/s]
Train steps ... :  69%|██████▉   | 69356/100000 [20:32:14<4:58:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 69357/100000 [20:32:14<4:58:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 69358/100000 [20:32:15<4:58:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 69359/100000 [20:32:15<4:58:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 69360/100000 [20:32:16<4:58:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 69361/100000 [20:32:17<4:58:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69362/100000 [20:32:17<4:58:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69363/100000 [20:32:18<4:58:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69364/100000 [20:32:18<4:59:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69365/100000 [20:32:19<4:58:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 69366/100000 [20:32:19<4:58:24,  1.71it/s]
Train steps ... :  69%|██████▉   | 69367/100000 [20:32:20<4:58:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69368/100000 [20:32:21<4:58:35,  1.71it/s]
Train steps ... :  69%|██████▉   | 69369/100000 [20:32:21<4:58:44,  1.71it/s]
Train steps ... :  69%|██████▉   | 69370/100000 [20:32:22<4:58:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 69371/100000 [20:32:22<4:58:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69372/100000 [20:32:23<4:58:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 69373/100000 [20:32:24<4:58:18,  1.71it/s]
Train steps ... :  69%|██████▉   | 69374/100000 [20:32:24<4:58:20,  1.71it/s]
Train steps ... :  69%|██████▉   | 69375/100000 [20:32:25<4:58:17,  1.71it/s]Step... (69375 / 100000 | Loss: 0.6226342916488647, Learning Rate: 3.077889447236181e-05)
+
                                                                             
Step... (69375 / 100000 | Loss: 0.8304033279418945, Learning Rate: 3.077889447236181e-05)
+
Train steps ... :  69%|██████▉   | 69375/100000 [20:32:25<4:58:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 69376/100000 [20:32:25<4:59:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69377/100000 [20:32:26<4:58:43,  1.71it/s]
Train steps ... :  69%|██████▉   | 69378/100000 [20:32:27<4:58:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 69379/100000 [20:32:27<4:59:12,  1.71it/s]
Train steps ... :  69%|██████▉   | 69380/100000 [20:32:28<4:58:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 69381/100000 [20:32:28<4:59:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69382/100000 [20:32:29<4:58:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 69383/100000 [20:32:29<4:58:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 69384/100000 [20:32:30<4:58:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69385/100000 [20:32:31<4:58:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 69386/100000 [20:32:31<4:58:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69387/100000 [20:32:32<4:58:21,  1.71it/s]
Train steps ... :  69%|██████▉   | 69388/100000 [20:32:32<4:58:13,  1.71it/s]
Train steps ... :  69%|██████▉   | 69389/100000 [20:32:33<4:58:18,  1.71it/s]
Train steps ... :  69%|██████▉   | 69390/100000 [20:32:34<4:58:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 69391/100000 [20:32:34<4:58:20,  1.71it/s]
Train steps ... :  69%|██████▉   | 69392/100000 [20:32:35<4:58:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 69393/100000 [20:32:35<4:58:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69394/100000 [20:32:36<4:57:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 69395/100000 [20:32:36<4:58:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 69396/100000 [20:32:37<4:57:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 69397/100000 [20:32:38<4:58:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69398/100000 [20:32:38<4:57:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 69399/100000 [20:32:39<4:58:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 69400/100000 [20:32:39<4:58:07,  1.71it/s]Step... (69400 / 100000 | Loss: 0.764857828617096, Learning Rate: 3.075376884422111e-05)
+
                                                                             
Step... (69400 / 100000 | Loss: 0.6208460330963135, Learning Rate: 3.075376884422111e-05)
+
Train steps ... :  69%|██████▉   | 69400/100000 [20:32:40<4:58:07,  1.71it/s]
Train steps ... :  69%|██████▉   | 69401/100000 [20:32:40<4:57:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 69402/100000 [20:32:41<4:57:41,  1.71it/s]
Train steps ... :  69%|██████▉   | 69403/100000 [20:32:41<4:57:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69404/100000 [20:32:42<4:57:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 69405/100000 [20:32:42<4:57:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69406/100000 [20:32:43<4:58:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69407/100000 [20:32:43<4:58:10,  1.71it/s]
Train steps ... :  69%|██████▉   | 69408/100000 [20:32:44<4:58:18,  1.71it/s]
Train steps ... :  69%|██████▉   | 69409/100000 [20:32:45<4:58:36,  1.71it/s]
Train steps ... :  69%|██████▉   | 69410/100000 [20:32:45<4:58:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 69411/100000 [20:32:46<4:58:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69412/100000 [20:32:46<4:57:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 69413/100000 [20:32:47<4:57:58,  1.71it/s]
Train steps ... :  69%|██████▉   | 69414/100000 [20:32:48<4:58:24,  1.71it/s]
Train steps ... :  69%|██████▉   | 69415/100000 [20:32:48<4:58:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69416/100000 [20:32:49<4:58:46,  1.71it/s]
Train steps ... :  69%|██████▉   | 69417/100000 [20:32:49<4:58:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 69418/100000 [20:32:50<4:58:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 69419/100000 [20:32:50<4:58:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69420/100000 [20:32:51<4:58:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69421/100000 [20:32:52<4:58:27,  1.71it/s]
Train steps ... :  69%|██████▉   | 69422/100000 [20:32:52<4:58:21,  1.71it/s]
Train steps ... :  69%|██████▉   | 69423/100000 [20:32:53<4:58:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 69424/100000 [20:32:53<4:58:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69425/100000 [20:32:54<4:58:19,  1.71it/s]Step... (69425 / 100000 | Loss: 0.5062066316604614, Learning Rate: 3.07286432160804e-05)
+
                                                                             
Step... (69425 / 100000 | Loss: 0.7766696810722351, Learning Rate: 3.07286432160804e-05)
+
Train steps ... :  69%|██████▉   | 69425/100000 [20:32:54<4:58:19,  1.71it/s]
Train steps ... :  69%|██████▉   | 69426/100000 [20:32:55<4:58:12,  1.71it/s]
Train steps ... :  69%|██████▉   | 69427/100000 [20:32:55<4:57:59,  1.71it/s]
Train steps ... :  69%|██████▉   | 69428/100000 [20:32:56<4:57:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69429/100000 [20:32:56<4:58:04,  1.71it/s]
Train steps ... :  69%|██████▉   | 69430/100000 [20:32:57<4:58:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 69431/100000 [20:32:58<4:58:13,  1.71it/s]
Train steps ... :  69%|██████▉   | 69432/100000 [20:32:58<4:58:29,  1.71it/s]
Train steps ... :  69%|██████▉   | 69433/100000 [20:32:59<4:58:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 69434/100000 [20:32:59<4:59:11,  1.70it/s]
Train steps ... :  69%|██████▉   | 69435/100000 [20:33:00<4:58:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 69436/100000 [20:33:00<4:58:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 69437/100000 [20:33:01<4:58:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69438/100000 [20:33:02<4:57:57,  1.71it/s]
Train steps ... :  69%|██████▉   | 69439/100000 [20:33:02<4:57:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 69440/100000 [20:33:03<4:57:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69441/100000 [20:33:03<4:58:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 69442/100000 [20:33:04<4:58:03,  1.71it/s]
Train steps ... :  69%|██████▉   | 69443/100000 [20:33:05<4:57:38,  1.71it/s]
Train steps ... :  69%|██████▉   | 69444/100000 [20:33:05<4:57:45,  1.71it/s]
Train steps ... :  69%|██████▉   | 69445/100000 [20:33:06<4:58:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 69446/100000 [20:33:06<4:57:51,  1.71it/s]
Train steps ... :  69%|██████▉   | 69447/100000 [20:33:07<4:57:55,  1.71it/s]
Train steps ... :  69%|██████▉   | 69448/100000 [20:33:07<4:58:05,  1.71it/s]
Train steps ... :  69%|██████▉   | 69449/100000 [20:33:08<4:58:18,  1.71it/s]
Train steps ... :  69%|██████▉   | 69450/100000 [20:33:09<4:58:13,  1.71it/s]Step... (69450 / 100000 | Loss: 0.5382773876190186, Learning Rate: 3.07035175879397e-05)
+
                                                                             
Step... (69450 / 100000 | Loss: 0.6847794055938721, Learning Rate: 3.07035175879397e-05)
+
Train steps ... :  69%|██████▉   | 69450/100000 [20:33:09<4:58:13,  1.71it/s]
Train steps ... :  69%|██████▉   | 69451/100000 [20:33:09<4:58:02,  1.71it/s]
Train steps ... :  69%|██████▉   | 69452/100000 [20:33:10<4:57:56,  1.71it/s]
Train steps ... :  69%|██████▉   | 69453/100000 [20:33:10<4:57:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 69454/100000 [20:33:11<4:57:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69455/100000 [20:33:12<4:57:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69456/100000 [20:33:12<4:57:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 69457/100000 [20:33:13<4:58:01,  1.71it/s]
Train steps ... :  69%|██████▉   | 69458/100000 [20:33:13<4:57:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69459/100000 [20:33:14<4:57:49,  1.71it/s]
Train steps ... :  69%|██████▉   | 69460/100000 [20:33:14<4:57:24,  1.71it/s]
Train steps ... :  69%|██████▉   | 69461/100000 [20:33:15<4:58:21,  1.71it/s]
Train steps ... :  69%|██████▉   | 69462/100000 [20:33:16<4:57:40,  1.71it/s]
Train steps ... :  69%|██████▉   | 69463/100000 [20:33:16<4:57:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 69464/100000 [20:33:17<4:57:15,  1.71it/s]
Train steps ... :  69%|██████▉   | 69465/100000 [20:33:17<4:57:16,  1.71it/s]
Train steps ... :  69%|██████▉   | 69466/100000 [20:33:18<4:57:04,  1.71it/s]
Train steps ... :  69%|██████▉   | 69467/100000 [20:33:19<4:57:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 69468/100000 [20:33:19<4:57:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69469/100000 [20:33:20<4:57:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 69470/100000 [20:33:20<4:57:53,  1.71it/s]
Train steps ... :  69%|██████▉   | 69471/100000 [20:33:21<4:58:06,  1.71it/s]
Train steps ... :  69%|██████▉   | 69472/100000 [20:33:21<4:57:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 69473/100000 [20:33:22<4:57:44,  1.71it/s]
Train steps ... :  69%|██████▉   | 69474/100000 [20:33:23<4:57:34,  1.71it/s]
Train steps ... :  69%|██████▉   | 69475/100000 [20:33:23<4:57:23,  1.71it/s]Step... (69475 / 100000 | Loss: 0.5696194171905518, Learning Rate: 3.0678391959798995e-05)
+
                                                                             
Step... (69475 / 100000 | Loss: 0.6062692403793335, Learning Rate: 3.0678391959798995e-05)
+
Train steps ... :  69%|██████▉   | 69475/100000 [20:33:24<4:57:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69476/100000 [20:33:24<4:57:32,  1.71it/s]
Train steps ... :  69%|██████▉   | 69477/100000 [20:33:24<4:58:00,  1.71it/s]
Train steps ... :  69%|██████▉   | 69478/100000 [20:33:25<4:57:52,  1.71it/s]
Train steps ... :  69%|██████▉   | 69479/100000 [20:33:26<4:58:11,  1.71it/s]
Train steps ... :  69%|██████▉   | 69480/100000 [20:33:26<4:57:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69481/100000 [20:33:27<4:57:42,  1.71it/s]
Train steps ... :  69%|██████▉   | 69482/100000 [20:33:27<4:57:39,  1.71it/s]
Train steps ... :  69%|██████▉   | 69483/100000 [20:33:28<4:57:47,  1.71it/s]
Train steps ... :  69%|██████▉   | 69484/100000 [20:33:29<4:57:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69485/100000 [20:33:29<4:57:37,  1.71it/s]
Train steps ... :  69%|██████▉   | 69486/100000 [20:33:30<4:57:25,  1.71it/s]
Train steps ... :  69%|██████▉   | 69487/100000 [20:33:30<4:57:23,  1.71it/s]
Train steps ... :  69%|██████▉   | 69488/100000 [20:33:31<4:57:17,  1.71it/s]
Train steps ... :  69%|██████▉   | 69489/100000 [20:33:31<4:57:09,  1.71it/s]
Train steps ... :  69%|██████▉   | 69490/100000 [20:33:32<4:57:26,  1.71it/s]
Train steps ... :  69%|██████▉   | 69491/100000 [20:33:33<4:57:08,  1.71it/s]
Train steps ... :  69%|██████▉   | 69492/100000 [20:33:33<4:57:22,  1.71it/s]
Train steps ... :  69%|██████▉   | 69493/100000 [20:33:34<4:57:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 69494/100000 [20:33:34<4:57:28,  1.71it/s]
Train steps ... :  69%|██████▉   | 69495/100000 [20:33:35<4:57:50,  1.71it/s]
Train steps ... :  69%|██████▉   | 69496/100000 [20:33:36<4:57:54,  1.71it/s]
Train steps ... :  69%|██████▉   | 69497/100000 [20:33:36<4:57:30,  1.71it/s]
Train steps ... :  69%|██████▉   | 69498/100000 [20:33:37<4:57:14,  1.71it/s]
Train steps ... :  69%|██████▉   | 69499/100000 [20:33:37<4:57:12,  1.71it/s]
Train steps ... :  70%|██████▉   | 69500/100000 [20:33:38<4:57:28,  1.71it/s]Step... (69500 / 100000 | Loss: 0.630357563495636, Learning Rate: 3.065326633165829e-05)
+
                                                                             
Step... (69500 / 100000 | Loss: 0.6779243350028992, Learning Rate: 3.065326633165829e-05)
+
Train steps ... :  70%|██████▉   | 69500/100000 [20:33:38<4:57:28,  1.71it/s]
Train steps ... :  70%|██████▉   | 69501/100000 [20:33:38<4:58:14,  1.70it/s]
Train steps ... :  70%|██████▉   | 69502/100000 [20:33:39<4:58:37,  1.70it/s]
Train steps ... :  70%|██████▉   | 69503/100000 [20:33:40<4:58:32,  1.70it/s]
Train steps ... :  70%|██████▉   | 69504/100000 [20:33:40<4:58:36,  1.70it/s]
Train steps ... :  70%|██████▉   | 69505/100000 [20:33:41<4:58:28,  1.70it/s]
Train steps ... :  70%|██████▉   | 69506/100000 [20:33:41<4:58:14,  1.70it/s]
Train steps ... :  70%|██████▉   | 69507/100000 [20:33:42<4:57:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69508/100000 [20:33:43<4:57:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69509/100000 [20:33:43<4:57:36,  1.71it/s]
Train steps ... :  70%|██████▉   | 69510/100000 [20:33:44<4:57:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69511/100000 [20:33:44<4:57:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69512/100000 [20:33:45<4:57:50,  1.71it/s]
Train steps ... :  70%|██████▉   | 69513/100000 [20:33:46<4:57:50,  1.71it/s]
Train steps ... :  70%|██████▉   | 69514/100000 [20:33:46<4:57:58,  1.71it/s]
Train steps ... :  70%|██████▉   | 69515/100000 [20:33:47<4:57:51,  1.71it/s]
Train steps ... :  70%|██████▉   | 69516/100000 [20:33:47<4:57:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69517/100000 [20:33:48<4:57:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69518/100000 [20:33:48<4:57:37,  1.71it/s]
Train steps ... :  70%|██████▉   | 69519/100000 [20:33:49<4:57:23,  1.71it/s]
Train steps ... :  70%|██████▉   | 69520/100000 [20:33:50<4:57:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69521/100000 [20:33:50<4:57:25,  1.71it/s]
Train steps ... :  70%|██████▉   | 69522/100000 [20:33:51<4:58:16,  1.70it/s]
Train steps ... :  70%|██████▉   | 69523/100000 [20:33:51<4:57:18,  1.71it/s]
Train steps ... :  70%|██████▉   | 69524/100000 [20:33:52<4:57:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69525/100000 [20:33:53<4:57:11,  1.71it/s]Step... (69525 / 100000 | Loss: 0.7076945304870605, Learning Rate: 3.062814070351759e-05)
+
                                                                             
Step... (69525 / 100000 | Loss: 0.6092783808708191, Learning Rate: 3.062814070351759e-05)
+
Train steps ... :  70%|██████▉   | 69525/100000 [20:33:53<4:57:11,  1.71it/s]
Train steps ... :  70%|██████▉   | 69526/100000 [20:33:53<4:57:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69527/100000 [20:33:54<4:57:11,  1.71it/s]
Train steps ... :  70%|██████▉   | 69528/100000 [20:33:54<4:57:01,  1.71it/s]
Train steps ... :  70%|██████▉   | 69529/100000 [20:33:55<4:57:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69530/100000 [20:33:55<4:57:23,  1.71it/s]
Train steps ... :  70%|██████▉   | 69531/100000 [20:33:56<4:57:18,  1.71it/s]
Train steps ... :  70%|██████▉   | 69532/100000 [20:33:57<4:57:09,  1.71it/s]
Train steps ... :  70%|██████▉   | 69533/100000 [20:33:57<4:57:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69534/100000 [20:33:58<4:57:20,  1.71it/s]
Train steps ... :  70%|██████▉   | 69535/100000 [20:33:58<4:57:23,  1.71it/s]
Train steps ... :  70%|██████▉   | 69536/100000 [20:33:59<4:57:07,  1.71it/s]
Train steps ... :  70%|██████▉   | 69537/100000 [20:34:00<4:57:06,  1.71it/s]
Train steps ... :  70%|██████▉   | 69538/100000 [20:34:00<4:57:08,  1.71it/s]
Train steps ... :  70%|██████▉   | 69539/100000 [20:34:01<4:56:49,  1.71it/s]
Train steps ... :  70%|██████▉   | 69540/100000 [20:34:01<4:56:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69541/100000 [20:34:02<4:56:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69542/100000 [20:34:02<4:57:13,  1.71it/s]
Train steps ... :  70%|██████▉   | 69543/100000 [20:34:03<4:56:58,  1.71it/s]
Train steps ... :  70%|██████▉   | 69544/100000 [20:34:04<4:56:45,  1.71it/s]
Train steps ... :  70%|██████▉   | 69545/100000 [20:34:04<4:56:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69546/100000 [20:34:05<4:56:51,  1.71it/s]
Train steps ... :  70%|██████▉   | 69547/100000 [20:34:05<4:56:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69548/100000 [20:34:06<4:57:03,  1.71it/s]
Train steps ... :  70%|██████▉   | 69549/100000 [20:34:07<4:57:13,  1.71it/s]
Train steps ... :  70%|██████▉   | 69550/100000 [20:34:07<4:57:09,  1.71it/s]Step... (69550 / 100000 | Loss: 0.729840874671936, Learning Rate: 3.0603015075376885e-05)
+
                                                                             
Step... (69550 / 100000 | Loss: 0.6812887191772461, Learning Rate: 3.0603015075376885e-05)
+
Train steps ... :  70%|██████▉   | 69550/100000 [20:34:08<4:57:09,  1.71it/s]
Train steps ... :  70%|██████▉   | 69551/100000 [20:34:08<4:57:15,  1.71it/s]
Train steps ... :  70%|██████▉   | 69552/100000 [20:34:08<4:57:02,  1.71it/s]
Train steps ... :  70%|██████▉   | 69553/100000 [20:34:09<4:57:07,  1.71it/s]
Train steps ... :  70%|██████▉   | 69554/100000 [20:34:10<4:56:53,  1.71it/s]
Train steps ... :  70%|██████▉   | 69555/100000 [20:34:10<4:56:48,  1.71it/s]
Train steps ... :  70%|██████▉   | 69556/100000 [20:34:11<4:57:06,  1.71it/s]
Train steps ... :  70%|██████▉   | 69557/100000 [20:34:11<4:56:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69558/100000 [20:34:12<4:56:43,  1.71it/s]
Train steps ... :  70%|██████▉   | 69559/100000 [20:34:12<4:57:15,  1.71it/s]
Train steps ... :  70%|██████▉   | 69560/100000 [20:34:13<4:56:51,  1.71it/s]
Train steps ... :  70%|██████▉   | 69561/100000 [20:34:14<4:57:42,  1.70it/s]
Train steps ... :  70%|██████▉   | 69562/100000 [20:34:14<4:57:20,  1.71it/s]
Train steps ... :  70%|██████▉   | 69563/100000 [20:34:15<4:57:15,  1.71it/s]
Train steps ... :  70%|██████▉   | 69564/100000 [20:34:15<4:57:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69565/100000 [20:34:16<4:56:51,  1.71it/s]
Train steps ... :  70%|██████▉   | 69566/100000 [20:34:17<4:57:03,  1.71it/s]
Train steps ... :  70%|██████▉   | 69567/100000 [20:34:17<4:57:01,  1.71it/s]
Train steps ... :  70%|██████▉   | 69568/100000 [20:34:18<4:57:09,  1.71it/s]
Train steps ... :  70%|██████▉   | 69569/100000 [20:34:18<4:57:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69570/100000 [20:34:19<4:57:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69571/100000 [20:34:19<4:57:04,  1.71it/s]
Train steps ... :  70%|██████▉   | 69572/100000 [20:34:20<4:57:53,  1.70it/s]
Train steps ... :  70%|██████▉   | 69573/100000 [20:34:21<4:57:22,  1.71it/s]
Train steps ... :  70%|██████▉   | 69574/100000 [20:34:21<4:56:52,  1.71it/s]
Train steps ... :  70%|██████▉   | 69575/100000 [20:34:22<4:56:35,  1.71it/s]Step... (69575 / 100000 | Loss: 0.6683590412139893, Learning Rate: 3.057788944723618e-05)
+
                                                                             
Step... (69575 / 100000 | Loss: 0.8396299481391907, Learning Rate: 3.057788944723618e-05)
+
Train steps ... :  70%|██████▉   | 69575/100000 [20:34:22<4:56:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69576/100000 [20:34:22<4:56:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69577/100000 [20:34:23<4:56:24,  1.71it/s]
Train steps ... :  70%|██████▉   | 69578/100000 [20:34:24<4:56:41,  1.71it/s]
Train steps ... :  70%|██████▉   | 69579/100000 [20:34:24<4:56:56,  1.71it/s]
Train steps ... :  70%|██████▉   | 69580/100000 [20:34:25<4:56:31,  1.71it/s]
Train steps ... :  70%|██████▉   | 69581/100000 [20:34:25<4:56:48,  1.71it/s]
Train steps ... :  70%|██████▉   | 69582/100000 [20:34:26<4:57:14,  1.71it/s]
Train steps ... :  70%|██████▉   | 69583/100000 [20:34:26<4:56:51,  1.71it/s]
Train steps ... :  70%|██████▉   | 69584/100000 [20:34:27<4:56:49,  1.71it/s]
Train steps ... :  70%|██████▉   | 69585/100000 [20:34:28<4:56:29,  1.71it/s]
Train steps ... :  70%|██████▉   | 69586/100000 [20:34:28<4:56:27,  1.71it/s]
Train steps ... :  70%|██████▉   | 69587/100000 [20:34:29<4:56:34,  1.71it/s]
Train steps ... :  70%|██████▉   | 69588/100000 [20:34:29<4:56:39,  1.71it/s]
Train steps ... :  70%|██████▉   | 69589/100000 [20:34:30<4:56:34,  1.71it/s]
Train steps ... :  70%|██████▉   | 69590/100000 [20:34:31<4:56:31,  1.71it/s]
Train steps ... :  70%|██████▉   | 69591/100000 [20:34:31<4:56:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69592/100000 [20:34:32<4:56:22,  1.71it/s]
Train steps ... :  70%|██████▉   | 69593/100000 [20:34:32<4:56:25,  1.71it/s]
Train steps ... :  70%|██████▉   | 69594/100000 [20:34:33<4:56:14,  1.71it/s]
Train steps ... :  70%|██████▉   | 69595/100000 [20:34:34<4:56:25,  1.71it/s]
Train steps ... :  70%|██████▉   | 69596/100000 [20:34:34<4:56:31,  1.71it/s]
Train steps ... :  70%|██████▉   | 69597/100000 [20:34:35<4:56:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69598/100000 [20:34:35<4:56:29,  1.71it/s]
Train steps ... :  70%|██████▉   | 69599/100000 [20:34:36<4:56:25,  1.71it/s]
Train steps ... :  70%|██████▉   | 69600/100000 [20:34:36<4:56:38,  1.71it/s]Step... (69600 / 100000 | Loss: 0.8477768898010254, Learning Rate: 3.055276381909548e-05)
+
                                                                             
Step... (69600 / 100000 | Loss: 0.6219356060028076, Learning Rate: 3.055276381909548e-05)
+
Train steps ... :  70%|██████▉   | 69600/100000 [20:34:37<4:56:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69601/100000 [20:34:37<4:56:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69602/100000 [20:34:38<4:56:36,  1.71it/s]
Train steps ... :  70%|██████▉   | 69603/100000 [20:34:38<4:56:29,  1.71it/s]
Train steps ... :  70%|██████▉   | 69604/100000 [20:34:39<4:56:33,  1.71it/s]
Train steps ... :  70%|██████▉   | 69605/100000 [20:34:39<4:56:11,  1.71it/s]
Train steps ... :  70%|██████▉   | 69606/100000 [20:34:40<4:56:45,  1.71it/s]
Train steps ... :  70%|██████▉   | 69607/100000 [20:34:41<4:57:24,  1.70it/s]
Train steps ... :  70%|██████▉   | 69608/100000 [20:34:41<4:57:04,  1.71it/s]
Train steps ... :  70%|██████▉   | 69609/100000 [20:34:42<4:56:33,  1.71it/s]
Train steps ... :  70%|██████▉   | 69610/100000 [20:34:42<4:56:50,  1.71it/s]
Train steps ... :  70%|██████▉   | 69611/100000 [20:34:43<4:56:27,  1.71it/s]
Train steps ... :  70%|██████▉   | 69612/100000 [20:34:43<4:56:05,  1.71it/s]
Train steps ... :  70%|██████▉   | 69613/100000 [20:34:44<4:55:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69614/100000 [20:34:45<4:55:50,  1.71it/s]
Train steps ... :  70%|██████▉   | 69615/100000 [20:34:45<4:56:17,  1.71it/s]
Train steps ... :  70%|██████▉   | 69616/100000 [20:34:46<4:56:05,  1.71it/s]
Train steps ... :  70%|██████▉   | 69617/100000 [20:34:46<4:56:20,  1.71it/s]
Train steps ... :  70%|██████▉   | 69618/100000 [20:34:47<4:56:17,  1.71it/s]
Train steps ... :  70%|██████▉   | 69619/100000 [20:34:48<4:56:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69620/100000 [20:34:48<4:56:25,  1.71it/s]
Train steps ... :  70%|██████▉   | 69621/100000 [20:34:49<4:56:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69622/100000 [20:34:49<4:56:04,  1.71it/s]
Train steps ... :  70%|██████▉   | 69623/100000 [20:34:50<4:56:24,  1.71it/s]
Train steps ... :  70%|██████▉   | 69624/100000 [20:34:50<4:56:03,  1.71it/s]
Train steps ... :  70%|██████▉   | 69625/100000 [20:34:51<4:56:12,  1.71it/s]Step... (69625 / 100000 | Loss: 0.5808023810386658, Learning Rate: 3.0527638190954775e-05)
+
                                                                             
Step... (69625 / 100000 | Loss: 0.666900634765625, Learning Rate: 3.0527638190954775e-05)
+
Train steps ... :  70%|██████▉   | 69625/100000 [20:34:51<4:56:12,  1.71it/s]
Train steps ... :  70%|██████▉   | 69626/100000 [20:34:52<4:56:15,  1.71it/s]
Train steps ... :  70%|██████▉   | 69627/100000 [20:34:52<4:56:07,  1.71it/s]
Train steps ... :  70%|██████▉   | 69628/100000 [20:34:53<4:55:56,  1.71it/s]
Train steps ... :  70%|██████▉   | 69629/100000 [20:34:53<4:56:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69630/100000 [20:34:54<4:56:23,  1.71it/s]
Train steps ... :  70%|██████▉   | 69631/100000 [20:34:55<4:56:06,  1.71it/s]
Train steps ... :  70%|██████▉   | 69632/100000 [20:34:55<4:56:04,  1.71it/s]
Train steps ... :  70%|██████▉   | 69633/100000 [20:34:56<4:55:54,  1.71it/s]
Train steps ... :  70%|██████▉   | 69634/100000 [20:34:56<4:55:48,  1.71it/s]
Train steps ... :  70%|██████▉   | 69635/100000 [20:34:57<4:55:59,  1.71it/s]
Train steps ... :  70%|██████▉   | 69636/100000 [20:34:58<4:55:59,  1.71it/s]
Train steps ... :  70%|██████▉   | 69637/100000 [20:34:58<4:56:17,  1.71it/s]
Train steps ... :  70%|██████▉   | 69638/100000 [20:34:59<4:56:00,  1.71it/s]
Train steps ... :  70%|██████▉   | 69639/100000 [20:34:59<4:56:17,  1.71it/s]
Train steps ... :  70%|██████▉   | 69640/100000 [20:35:00<4:56:09,  1.71it/s]
Train steps ... :  70%|██████▉   | 69641/100000 [20:35:00<4:55:58,  1.71it/s]
Train steps ... :  70%|██████▉   | 69642/100000 [20:35:01<4:55:54,  1.71it/s]
Train steps ... :  70%|██████▉   | 69643/100000 [20:35:02<4:55:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69644/100000 [20:35:02<4:55:54,  1.71it/s]
Train steps ... :  70%|██████▉   | 69645/100000 [20:35:03<4:56:01,  1.71it/s]
Train steps ... :  70%|██████▉   | 69646/100000 [20:35:03<4:56:08,  1.71it/s]
Train steps ... :  70%|██████▉   | 69647/100000 [20:35:04<4:56:13,  1.71it/s]
Train steps ... :  70%|██████▉   | 69648/100000 [20:35:05<4:56:20,  1.71it/s]
Train steps ... :  70%|██████▉   | 69649/100000 [20:35:05<4:56:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69650/100000 [20:35:06<4:56:20,  1.71it/s]Step... (69650 / 100000 | Loss: 0.8172025084495544, Learning Rate: 3.0502512562814072e-05)
+
                                                                             
Step... (69650 / 100000 | Loss: 0.7135053873062134, Learning Rate: 3.0502512562814072e-05)
+
Train steps ... :  70%|██████▉   | 69650/100000 [20:35:06<4:56:20,  1.71it/s]
Train steps ... :  70%|██████▉   | 69651/100000 [20:35:06<4:56:01,  1.71it/s]
Train steps ... :  70%|██████▉   | 69652/100000 [20:35:07<4:55:53,  1.71it/s]
Train steps ... :  70%|██████▉   | 69653/100000 [20:35:07<4:56:06,  1.71it/s]
Train steps ... :  70%|██████▉   | 69654/100000 [20:35:08<4:55:57,  1.71it/s]
Train steps ... :  70%|██████▉   | 69655/100000 [20:35:09<4:55:57,  1.71it/s]
Train steps ... :  70%|██████▉   | 69656/100000 [20:35:09<4:55:51,  1.71it/s]
Train steps ... :  70%|██████▉   | 69657/100000 [20:35:10<4:56:17,  1.71it/s]
Train steps ... :  70%|██████▉   | 69658/100000 [20:35:10<4:55:57,  1.71it/s]
Train steps ... :  70%|██████▉   | 69659/100000 [20:35:11<4:55:41,  1.71it/s]
Train steps ... :  70%|██████▉   | 69660/100000 [20:35:12<4:55:29,  1.71it/s]
Train steps ... :  70%|██████▉   | 69661/100000 [20:35:12<4:56:09,  1.71it/s]
Train steps ... :  70%|██████▉   | 69662/100000 [20:35:13<4:56:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69663/100000 [20:35:13<4:56:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69664/100000 [20:35:14<4:55:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69665/100000 [20:35:14<4:55:48,  1.71it/s]
Train steps ... :  70%|██████▉   | 69666/100000 [20:35:15<4:56:00,  1.71it/s]
Train steps ... :  70%|██████▉   | 69667/100000 [20:35:16<4:55:52,  1.71it/s]
Train steps ... :  70%|██████▉   | 69668/100000 [20:35:16<4:55:37,  1.71it/s]
Train steps ... :  70%|██████▉   | 69669/100000 [20:35:17<4:55:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69670/100000 [20:35:17<4:55:18,  1.71it/s]
Train steps ... :  70%|██████▉   | 69671/100000 [20:35:18<4:55:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69672/100000 [20:35:19<4:55:24,  1.71it/s]
Train steps ... :  70%|██████▉   | 69673/100000 [20:35:19<4:55:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69674/100000 [20:35:20<4:55:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69675/100000 [20:35:20<4:55:38,  1.71it/s]Step... (69675 / 100000 | Loss: 0.5482136607170105, Learning Rate: 3.047738693467337e-05)
+
                                                                             
Step... (69675 / 100000 | Loss: 0.7296887636184692, Learning Rate: 3.047738693467337e-05)
+
Train steps ... :  70%|██████▉   | 69675/100000 [20:35:21<4:55:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69676/100000 [20:35:21<4:55:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69677/100000 [20:35:21<4:55:51,  1.71it/s]
Train steps ... :  70%|██████▉   | 69678/100000 [20:35:22<4:55:37,  1.71it/s]
Train steps ... :  70%|██████▉   | 69679/100000 [20:35:23<4:55:30,  1.71it/s]
Train steps ... :  70%|██████▉   | 69680/100000 [20:35:23<4:55:42,  1.71it/s]
Train steps ... :  70%|██████▉   | 69681/100000 [20:35:24<4:55:53,  1.71it/s]
Train steps ... :  70%|██████▉   | 69682/100000 [20:35:24<4:55:29,  1.71it/s]
Train steps ... :  70%|██████▉   | 69683/100000 [20:35:25<4:55:30,  1.71it/s]
Train steps ... :  70%|██████▉   | 69684/100000 [20:35:26<4:55:37,  1.71it/s]
Train steps ... :  70%|██████▉   | 69685/100000 [20:35:26<4:55:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69686/100000 [20:35:27<4:55:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69687/100000 [20:35:27<4:55:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69688/100000 [20:35:28<4:55:09,  1.71it/s]
Train steps ... :  70%|██████▉   | 69689/100000 [20:35:29<4:55:27,  1.71it/s]
Train steps ... :  70%|██████▉   | 69690/100000 [20:35:29<4:55:37,  1.71it/s]
Train steps ... :  70%|██████▉   | 69691/100000 [20:35:30<4:55:52,  1.71it/s]
Train steps ... :  70%|██████▉   | 69692/100000 [20:35:30<4:56:51,  1.70it/s]
Train steps ... :  70%|██████▉   | 69693/100000 [20:35:31<4:55:36,  1.71it/s]
Train steps ... :  70%|██████▉   | 69694/100000 [20:35:31<4:55:17,  1.71it/s]
Train steps ... :  70%|██████▉   | 69695/100000 [20:35:32<4:55:08,  1.71it/s]
Train steps ... :  70%|██████▉   | 69696/100000 [20:35:33<4:55:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69697/100000 [20:35:33<4:55:08,  1.71it/s]
Train steps ... :  70%|██████▉   | 69698/100000 [20:35:34<4:55:12,  1.71it/s]
Train steps ... :  70%|██████▉   | 69699/100000 [20:35:34<4:55:08,  1.71it/s]
Train steps ... :  70%|██████▉   | 69700/100000 [20:35:35<4:55:54,  1.71it/s]Step... (69700 / 100000 | Loss: 0.6544147729873657, Learning Rate: 3.0452261306532665e-05)
+
                                                                             
Step... (69700 / 100000 | Loss: 0.5301288962364197, Learning Rate: 3.0452261306532665e-05)
+
Train steps ... :  70%|██████▉   | 69700/100000 [20:35:35<4:55:54,  1.71it/s]
Train steps ... :  70%|██████▉   | 69701/100000 [20:35:36<4:55:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69702/100000 [20:35:36<4:55:59,  1.71it/s]
Train steps ... :  70%|██████▉   | 69703/100000 [20:35:37<4:55:59,  1.71it/s]
Train steps ... :  70%|██████▉   | 69704/100000 [20:35:37<4:55:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69705/100000 [20:35:38<4:55:27,  1.71it/s]
Train steps ... :  70%|██████▉   | 69706/100000 [20:35:38<4:55:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69707/100000 [20:35:39<4:56:04,  1.71it/s]
Train steps ... :  70%|██████▉   | 69708/100000 [20:35:40<4:55:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69709/100000 [20:35:40<4:55:24,  1.71it/s]
Train steps ... :  70%|██████▉   | 69710/100000 [20:35:41<4:55:29,  1.71it/s]
Train steps ... :  70%|██████▉   | 69711/100000 [20:35:41<4:56:49,  1.70it/s]
Train steps ... :  70%|██████▉   | 69712/100000 [20:35:42<4:55:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69713/100000 [20:35:43<4:56:07,  1.70it/s]
Train steps ... :  70%|██████▉   | 69714/100000 [20:35:43<4:55:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69715/100000 [20:35:44<4:55:49,  1.71it/s]
Train steps ... :  70%|██████▉   | 69716/100000 [20:35:44<4:55:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69717/100000 [20:35:45<4:55:57,  1.71it/s]
Train steps ... :  70%|██████▉   | 69718/100000 [20:35:46<4:55:49,  1.71it/s]
Train steps ... :  70%|██████▉   | 69719/100000 [20:35:46<4:55:59,  1.71it/s]
Train steps ... :  70%|██████▉   | 69720/100000 [20:35:47<4:56:24,  1.70it/s]
Train steps ... :  70%|██████▉   | 69721/100000 [20:35:47<4:55:57,  1.71it/s]
Train steps ... :  70%|██████▉   | 69722/100000 [20:35:48<4:55:31,  1.71it/s]
Train steps ... :  70%|██████▉   | 69723/100000 [20:35:48<4:55:54,  1.71it/s]
Train steps ... :  70%|██████▉   | 69724/100000 [20:35:49<4:55:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69725/100000 [20:35:50<4:55:40,  1.71it/s]Step... (69725 / 100000 | Loss: 0.7205889225006104, Learning Rate: 3.042713567839196e-05)
+
                                                                             
Step... (69725 / 100000 | Loss: 0.61260586977005, Learning Rate: 3.042713567839196e-05)
+
Train steps ... :  70%|██████▉   | 69725/100000 [20:35:50<4:55:40,  1.71it/s]
Train steps ... :  70%|██████▉   | 69726/100000 [20:35:50<4:56:06,  1.70it/s]
Train steps ... :  70%|██████▉   | 69727/100000 [20:35:51<4:56:10,  1.70it/s]
Train steps ... :  70%|██████▉   | 69728/100000 [20:35:51<4:55:55,  1.70it/s]
Train steps ... :  70%|██████▉   | 69729/100000 [20:35:52<4:57:35,  1.70it/s]
Train steps ... :  70%|██████▉   | 69730/100000 [20:35:53<4:55:58,  1.70it/s]
Train steps ... :  70%|██████▉   | 69731/100000 [20:35:53<4:55:57,  1.70it/s]
Train steps ... :  70%|██████▉   | 69732/100000 [20:35:54<4:56:03,  1.70it/s]
Train steps ... :  70%|██████▉   | 69733/100000 [20:35:54<4:55:33,  1.71it/s]
Train steps ... :  70%|██████▉   | 69734/100000 [20:35:55<4:55:33,  1.71it/s]
Train steps ... :  70%|██████▉   | 69735/100000 [20:35:55<4:55:39,  1.71it/s]
Train steps ... :  70%|██████▉   | 69736/100000 [20:35:56<4:56:12,  1.70it/s]
Train steps ... :  70%|██████▉   | 69737/100000 [20:35:57<4:55:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69738/100000 [20:35:57<4:56:15,  1.70it/s]
Train steps ... :  70%|██████▉   | 69739/100000 [20:35:58<4:55:48,  1.70it/s]
Train steps ... :  70%|██████▉   | 69740/100000 [20:35:58<4:55:48,  1.70it/s]
Train steps ... :  70%|██████▉   | 69741/100000 [20:35:59<4:55:51,  1.70it/s]
Train steps ... :  70%|██████▉   | 69742/100000 [20:36:00<4:55:53,  1.70it/s]
Train steps ... :  70%|██████▉   | 69743/100000 [20:36:00<4:55:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69744/100000 [20:36:01<4:55:33,  1.71it/s]
Train steps ... :  70%|██████▉   | 69745/100000 [20:36:01<4:55:02,  1.71it/s]
Train steps ... :  70%|██████▉   | 69746/100000 [20:36:02<4:54:43,  1.71it/s]
Train steps ... :  70%|██████▉   | 69747/100000 [20:36:03<4:56:01,  1.70it/s]
Train steps ... :  70%|██████▉   | 69748/100000 [20:36:03<4:55:46,  1.70it/s]
Train steps ... :  70%|██████▉   | 69749/100000 [20:36:04<4:55:33,  1.71it/s]
Train steps ... :  70%|██████▉   | 69750/100000 [20:36:04<4:55:03,  1.71it/s]Step... (69750 / 100000 | Loss: 0.8738936185836792, Learning Rate: 3.0402010050251255e-05)
+
                                                                             
Step... (69750 / 100000 | Loss: 0.6132329106330872, Learning Rate: 3.0402010050251255e-05)
+
Train steps ... :  70%|██████▉   | 69750/100000 [20:36:05<4:55:03,  1.71it/s]
Train steps ... :  70%|██████▉   | 69751/100000 [20:36:05<4:55:32,  1.71it/s]
Train steps ... :  70%|██████▉   | 69752/100000 [20:36:05<4:55:02,  1.71it/s]
Train steps ... :  70%|██████▉   | 69753/100000 [20:36:06<4:55:12,  1.71it/s]
Train steps ... :  70%|██████▉   | 69754/100000 [20:36:07<4:54:32,  1.71it/s]
Train steps ... :  70%|██████▉   | 69755/100000 [20:36:07<4:54:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69756/100000 [20:36:08<4:54:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69757/100000 [20:36:08<4:54:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69758/100000 [20:36:09<4:55:03,  1.71it/s]
Train steps ... :  70%|██████▉   | 69759/100000 [20:36:10<4:55:09,  1.71it/s]
Train steps ... :  70%|██████▉   | 69760/100000 [20:36:10<4:54:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69761/100000 [20:36:11<4:54:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69762/100000 [20:36:11<4:55:13,  1.71it/s]
Train steps ... :  70%|██████▉   | 69763/100000 [20:36:12<4:54:58,  1.71it/s]
Train steps ... :  70%|██████▉   | 69764/100000 [20:36:12<4:55:05,  1.71it/s]
Train steps ... :  70%|██████▉   | 69765/100000 [20:36:13<4:55:00,  1.71it/s]
Train steps ... :  70%|██████▉   | 69766/100000 [20:36:14<4:55:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69767/100000 [20:36:14<4:55:01,  1.71it/s]
Train steps ... :  70%|██████▉   | 69768/100000 [20:36:15<4:54:40,  1.71it/s]
Train steps ... :  70%|██████▉   | 69769/100000 [20:36:15<4:54:39,  1.71it/s]
Train steps ... :  70%|██████▉   | 69770/100000 [20:36:16<4:54:42,  1.71it/s]
Train steps ... :  70%|██████▉   | 69771/100000 [20:36:17<4:54:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69772/100000 [20:36:17<4:54:23,  1.71it/s]
Train steps ... :  70%|██████▉   | 69773/100000 [20:36:18<4:54:43,  1.71it/s]
Train steps ... :  70%|██████▉   | 69774/100000 [20:36:18<4:54:26,  1.71it/s]
Train steps ... :  70%|██████▉   | 69775/100000 [20:36:19<4:54:20,  1.71it/s]Step... (69775 / 100000 | Loss: 0.8492693901062012, Learning Rate: 3.037688442211055e-05)
+
                                                                             
Step... (69775 / 100000 | Loss: 0.7085883617401123, Learning Rate: 3.037688442211055e-05)
+
Train steps ... :  70%|██████▉   | 69775/100000 [20:36:19<4:54:20,  1.71it/s]
Train steps ... :  70%|██████▉   | 69776/100000 [20:36:19<4:54:49,  1.71it/s]
Train steps ... :  70%|██████▉   | 69777/100000 [20:36:20<4:54:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69778/100000 [20:36:21<4:55:07,  1.71it/s]
Train steps ... :  70%|██████▉   | 69779/100000 [20:36:21<4:55:08,  1.71it/s]
Train steps ... :  70%|██████▉   | 69780/100000 [20:36:22<4:54:32,  1.71it/s]
Train steps ... :  70%|██████▉   | 69781/100000 [20:36:22<4:54:39,  1.71it/s]
Train steps ... :  70%|██████▉   | 69782/100000 [20:36:23<4:54:24,  1.71it/s]
Train steps ... :  70%|██████▉   | 69783/100000 [20:36:24<4:54:28,  1.71it/s]
Train steps ... :  70%|██████▉   | 69784/100000 [20:36:24<4:54:27,  1.71it/s]
Train steps ... :  70%|██████▉   | 69785/100000 [20:36:25<4:54:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69786/100000 [20:36:25<4:54:28,  1.71it/s]
Train steps ... :  70%|██████▉   | 69787/100000 [20:36:26<4:54:25,  1.71it/s]
Train steps ... :  70%|██████▉   | 69788/100000 [20:36:26<4:54:12,  1.71it/s]
Train steps ... :  70%|██████▉   | 69789/100000 [20:36:27<4:54:09,  1.71it/s]
Train steps ... :  70%|██████▉   | 69790/100000 [20:36:28<4:54:28,  1.71it/s]
Train steps ... :  70%|██████▉   | 69791/100000 [20:36:28<4:54:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69792/100000 [20:36:29<4:54:26,  1.71it/s]
Train steps ... :  70%|██████▉   | 69793/100000 [20:36:29<4:54:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69794/100000 [20:36:30<4:54:28,  1.71it/s]
Train steps ... :  70%|██████▉   | 69795/100000 [20:36:31<4:54:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69796/100000 [20:36:31<4:54:30,  1.71it/s]
Train steps ... :  70%|██████▉   | 69797/100000 [20:36:32<4:54:17,  1.71it/s]
Train steps ... :  70%|██████▉   | 69798/100000 [20:36:32<4:54:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69799/100000 [20:36:33<4:54:36,  1.71it/s]
Train steps ... :  70%|██████▉   | 69800/100000 [20:36:34<4:54:55,  1.71it/s]Step... (69800 / 100000 | Loss: 0.799733579158783, Learning Rate: 3.0351758793969855e-05)
+
                                                                             
Step... (69800 / 100000 | Loss: 0.7837345600128174, Learning Rate: 3.0351758793969855e-05)
+
Train steps ... :  70%|██████▉   | 69800/100000 [20:36:34<4:54:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69801/100000 [20:36:34<4:54:56,  1.71it/s]
Train steps ... :  70%|██████▉   | 69802/100000 [20:36:35<4:54:39,  1.71it/s]
Train steps ... :  70%|██████▉   | 69803/100000 [20:36:35<4:54:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69804/100000 [20:36:36<4:54:27,  1.71it/s]
Train steps ... :  70%|██████▉   | 69805/100000 [20:36:36<4:54:25,  1.71it/s]
Train steps ... :  70%|██████��   | 69806/100000 [20:36:37<4:54:53,  1.71it/s]
Train steps ... :  70%|██████▉   | 69807/100000 [20:36:38<4:54:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69808/100000 [20:36:38<4:54:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69809/100000 [20:36:39<4:54:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69810/100000 [20:36:39<4:54:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69811/100000 [20:36:40<4:54:51,  1.71it/s]
Train steps ... :  70%|██████▉   | 69812/100000 [20:36:41<4:54:48,  1.71it/s]
Train steps ... :  70%|██████▉   | 69813/100000 [20:36:41<4:54:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69814/100000 [20:36:42<4:54:18,  1.71it/s]
Train steps ... :  70%|██████▉   | 69815/100000 [20:36:42<4:54:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69816/100000 [20:36:43<4:54:56,  1.71it/s]
Train steps ... :  70%|██████▉   | 69817/100000 [20:36:43<4:54:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69818/100000 [20:36:44<4:54:58,  1.71it/s]
Train steps ... :  70%|██████▉   | 69819/100000 [20:36:45<4:54:50,  1.71it/s]
Train steps ... :  70%|██████▉   | 69820/100000 [20:36:45<4:55:03,  1.70it/s]
Train steps ... :  70%|██████▉   | 69821/100000 [20:36:46<4:54:41,  1.71it/s]
Train steps ... :  70%|██████▉   | 69822/100000 [20:36:46<4:54:41,  1.71it/s]
Train steps ... :  70%|██████▉   | 69823/100000 [20:36:47<4:54:18,  1.71it/s]
Train steps ... :  70%|██████▉   | 69824/100000 [20:36:48<4:54:06,  1.71it/s]
Train steps ... :  70%|██████▉   | 69825/100000 [20:36:48<4:54:00,  1.71it/s]Step... (69825 / 100000 | Loss: 0.544940173625946, Learning Rate: 3.0326633165829148e-05)
+
                                                                             
Step... (69825 / 100000 | Loss: 0.6394115686416626, Learning Rate: 3.0326633165829148e-05)
+
Train steps ... :  70%|██████▉   | 69825/100000 [20:36:48<4:54:00,  1.71it/s]
Train steps ... :  70%|██████▉   | 69826/100000 [20:36:49<4:54:25,  1.71it/s]
Train steps ... :  70%|██████▉   | 69827/100000 [20:36:49<4:54:06,  1.71it/s]
Train steps ... :  70%|██████▉   | 69828/100000 [20:36:50<4:53:52,  1.71it/s]
Train steps ... :  70%|██████▉   | 69829/100000 [20:36:50<4:54:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69830/100000 [20:36:51<4:54:23,  1.71it/s]
Train steps ... :  70%|██████▉   | 69831/100000 [20:36:52<4:54:09,  1.71it/s]
Train steps ... :  70%|██████▉   | 69832/100000 [20:36:52<4:53:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69833/100000 [20:36:53<4:53:58,  1.71it/s]
Train steps ... :  70%|██████▉   | 69834/100000 [20:36:53<4:53:39,  1.71it/s]
Train steps ... :  70%|██████▉   | 69835/100000 [20:36:54<4:54:11,  1.71it/s]
Train steps ... :  70%|██████▉   | 69836/100000 [20:36:55<4:53:37,  1.71it/s]
Train steps ... :  70%|██████▉   | 69837/100000 [20:36:55<4:53:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69838/100000 [20:36:56<4:53:36,  1.71it/s]
Train steps ... :  70%|██████▉   | 69839/100000 [20:36:56<4:53:48,  1.71it/s]
Train steps ... :  70%|██████▉   | 69840/100000 [20:36:57<4:53:48,  1.71it/s]
Train steps ... :  70%|██████▉   | 69841/100000 [20:36:58<4:53:56,  1.71it/s]
Train steps ... :  70%|██████▉   | 69842/100000 [20:36:58<4:53:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69843/100000 [20:36:59<4:54:03,  1.71it/s]
Train steps ... :  70%|██████▉   | 69844/100000 [20:36:59<4:54:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69845/100000 [20:37:00<4:54:01,  1.71it/s]
Train steps ... :  70%|██████▉   | 69846/100000 [20:37:00<4:53:45,  1.71it/s]
Train steps ... :  70%|██████▉   | 69847/100000 [20:37:01<4:53:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69848/100000 [20:37:02<4:53:43,  1.71it/s]
Train steps ... :  70%|██████▉   | 69849/100000 [20:37:02<4:53:25,  1.71it/s]
Train steps ... :  70%|██████▉   | 69850/100000 [20:37:03<4:53:33,  1.71it/s]Step... (69850 / 100000 | Loss: 0.7281632423400879, Learning Rate: 3.0301507537688445e-05)
+
                                                                             
Step... (69850 / 100000 | Loss: 0.6356839537620544, Learning Rate: 3.0301507537688445e-05)
+
Train steps ... :  70%|██████▉   | 69850/100000 [20:37:03<4:53:33,  1.71it/s]
Train steps ... :  70%|██████▉   | 69851/100000 [20:37:03<4:53:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69852/100000 [20:37:04<4:53:31,  1.71it/s]
Train steps ... :  70%|██████▉   | 69853/100000 [20:37:05<4:53:58,  1.71it/s]
Train steps ... :  70%|██████▉   | 69854/100000 [20:37:05<4:53:49,  1.71it/s]
Train steps ... :  70%|██████▉   | 69855/100000 [20:37:06<4:53:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69856/100000 [20:37:06<4:53:59,  1.71it/s]
Train steps ... :  70%|██████▉   | 69857/100000 [20:37:07<4:53:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69858/100000 [20:37:07<4:53:41,  1.71it/s]
Train steps ... :  70%|██████▉   | 69859/100000 [20:37:08<4:53:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69860/100000 [20:37:09<4:53:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69861/100000 [20:37:09<4:54:27,  1.71it/s]
Train steps ... :  70%|██████▉   | 69862/100000 [20:37:10<4:54:02,  1.71it/s]
Train steps ... :  70%|██████▉   | 69863/100000 [20:37:10<4:53:48,  1.71it/s]
Train steps ... :  70%|██████▉   | 69864/100000 [20:37:11<4:53:37,  1.71it/s]
Train steps ... :  70%|██████▉   | 69865/100000 [20:37:12<4:53:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69866/100000 [20:37:12<4:54:01,  1.71it/s]
Train steps ... :  70%|██████▉   | 69867/100000 [20:37:13<4:54:00,  1.71it/s]
Train steps ... :  70%|██████▉   | 69868/100000 [20:37:13<4:53:34,  1.71it/s]
Train steps ... :  70%|██████▉   | 69869/100000 [20:37:14<4:53:36,  1.71it/s]
Train steps ... :  70%|██████▉   | 69870/100000 [20:37:14<4:53:50,  1.71it/s]
Train steps ... :  70%|██████▉   | 69871/100000 [20:37:15<4:53:42,  1.71it/s]
Train steps ... :  70%|██████▉   | 69872/100000 [20:37:16<4:53:58,  1.71it/s]
Train steps ... :  70%|██████▉   | 69873/100000 [20:37:16<4:53:39,  1.71it/s]
Train steps ... :  70%|██████▉   | 69874/100000 [20:37:17<4:53:31,  1.71it/s]
Train steps ... :  70%|██████▉   | 69875/100000 [20:37:17<4:53:30,  1.71it/s]Step... (69875 / 100000 | Loss: 0.5025167465209961, Learning Rate: 3.027638190954774e-05)
+
                                                                             
Step... (69875 / 100000 | Loss: 0.5190936326980591, Learning Rate: 3.027638190954774e-05)
+
Train steps ... :  70%|██████▉   | 69875/100000 [20:37:18<4:53:30,  1.71it/s]
Train steps ... :  70%|██████▉   | 69876/100000 [20:37:18<4:53:26,  1.71it/s]
Train steps ... :  70%|██████▉   | 69877/100000 [20:37:19<4:53:38,  1.71it/s]
Train steps ... :  70%|██████▉   | 69878/100000 [20:37:19<4:53:27,  1.71it/s]
Train steps ... :  70%|██████▉   | 69879/100000 [20:37:20<4:53:28,  1.71it/s]
Train steps ... :  70%|██████▉   | 69880/100000 [20:37:20<4:53:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69881/100000 [20:37:21<4:53:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69882/100000 [20:37:21<4:53:26,  1.71it/s]
Train steps ... :  70%|██████▉   | 69883/100000 [20:37:22<4:53:23,  1.71it/s]
Train steps ... :  70%|██████▉   | 69884/100000 [20:37:23<4:53:31,  1.71it/s]
Train steps ... :  70%|██████▉   | 69885/100000 [20:37:23<4:53:28,  1.71it/s]
Train steps ... :  70%|██████▉   | 69886/100000 [20:37:24<4:53:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69887/100000 [20:37:24<4:53:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69888/100000 [20:37:25<4:53:28,  1.71it/s]
Train steps ... :  70%|██████▉   | 69889/100000 [20:37:26<4:53:40,  1.71it/s]
Train steps ... :  70%|██████▉   | 69890/100000 [20:37:26<4:53:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69891/100000 [20:37:27<4:53:36,  1.71it/s]
Train steps ... :  70%|██████▉   | 69892/100000 [20:37:27<4:53:49,  1.71it/s]
Train steps ... :  70%|██████▉   | 69893/100000 [20:37:28<4:53:34,  1.71it/s]
Train steps ... :  70%|██████▉   | 69894/100000 [20:37:29<4:53:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69895/100000 [20:37:29<4:53:34,  1.71it/s]
Train steps ... :  70%|██████▉   | 69896/100000 [20:37:30<4:53:30,  1.71it/s]
Train steps ... :  70%|██████▉   | 69897/100000 [20:37:30<4:53:20,  1.71it/s]
Train steps ... :  70%|██████▉   | 69898/100000 [20:37:31<4:53:34,  1.71it/s]
Train steps ... :  70%|██████▉   | 69899/100000 [20:37:31<4:53:30,  1.71it/s]
Train steps ... :  70%|██████▉   | 69900/100000 [20:37:32<4:53:28,  1.71it/s]Step... (69900 / 100000 | Loss: 0.5722877979278564, Learning Rate: 3.0251256281407038e-05)
+
                                                                             
Step... (69900 / 100000 | Loss: 0.6895901560783386, Learning Rate: 3.0251256281407038e-05)
+
Train steps ... :  70%|██████▉   | 69900/100000 [20:37:32<4:53:28,  1.71it/s]
Train steps ... :  70%|██████▉   | 69901/100000 [20:37:33<4:53:25,  1.71it/s]
Train steps ... :  70%|███��██▉   | 69902/100000 [20:37:33<4:53:17,  1.71it/s]
Train steps ... :  70%|██████▉   | 69903/100000 [20:37:34<4:53:00,  1.71it/s]
Train steps ... :  70%|██████▉   | 69904/100000 [20:37:34<4:53:20,  1.71it/s]
Train steps ... :  70%|██████▉   | 69905/100000 [20:37:35<4:53:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69906/100000 [20:37:36<4:53:03,  1.71it/s]
Train steps ... :  70%|██████▉   | 69907/100000 [20:37:36<4:52:59,  1.71it/s]
Train steps ... :  70%|██████▉   | 69908/100000 [20:37:37<4:52:58,  1.71it/s]
Train steps ... :  70%|██████▉   | 69909/100000 [20:37:37<4:53:23,  1.71it/s]
Train steps ... :  70%|██████▉   | 69910/100000 [20:37:38<4:53:20,  1.71it/s]
Train steps ... :  70%|██████▉   | 69911/100000 [20:37:38<4:53:02,  1.71it/s]
Train steps ... :  70%|██████▉   | 69912/100000 [20:37:39<4:53:02,  1.71it/s]
Train steps ... :  70%|██████▉   | 69913/100000 [20:37:40<4:52:52,  1.71it/s]
Train steps ... :  70%|██████▉   | 69914/100000 [20:37:40<4:53:11,  1.71it/s]
Train steps ... :  70%|██████▉   | 69915/100000 [20:37:41<4:53:30,  1.71it/s]
Train steps ... :  70%|██████▉   | 69916/100000 [20:37:41<4:53:12,  1.71it/s]
Train steps ... :  70%|██████▉   | 69917/100000 [20:37:42<4:53:23,  1.71it/s]
Train steps ... :  70%|██████▉   | 69918/100000 [20:37:43<4:52:49,  1.71it/s]
Train steps ... :  70%|██████▉   | 69919/100000 [20:37:43<4:53:17,  1.71it/s]
Train steps ... :  70%|██████▉   | 69920/100000 [20:37:44<4:52:53,  1.71it/s]
Train steps ... :  70%|██████▉   | 69921/100000 [20:37:44<4:52:54,  1.71it/s]
Train steps ... :  70%|██████▉   | 69922/100000 [20:37:45<4:53:11,  1.71it/s]
Train steps ... :  70%|██████▉   | 69923/100000 [20:37:45<4:53:11,  1.71it/s]
Train steps ... :  70%|██████▉   | 69924/100000 [20:37:46<4:53:27,  1.71it/s]
Train steps ... :  70%|██████▉   | 69925/100000 [20:37:47<4:53:24,  1.71it/s]Step... (69925 / 100000 | Loss: 0.684380292892456, Learning Rate: 3.022613065326633e-05)
+
                                                                             
Step... (69925 / 100000 | Loss: 0.6568412780761719, Learning Rate: 3.022613065326633e-05)
+
Train steps ... :  70%|██████▉   | 69925/100000 [20:37:47<4:53:24,  1.71it/s]
Train steps ... :  70%|██████▉   | 69926/100000 [20:37:47<4:53:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69927/100000 [20:37:48<4:53:59,  1.70it/s]
Train steps ... :  70%|██████▉   | 69928/100000 [20:37:48<4:53:30,  1.71it/s]
Train steps ... :  70%|██████▉   | 69929/100000 [20:37:49<4:53:36,  1.71it/s]
Train steps ... :  70%|██████▉   | 69930/100000 [20:37:50<4:53:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69931/100000 [20:37:50<4:53:02,  1.71it/s]
Train steps ... :  70%|██████▉   | 69932/100000 [20:37:51<4:53:13,  1.71it/s]
Train steps ... :  70%|██████▉   | 69933/100000 [20:37:51<4:53:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69934/100000 [20:37:52<4:52:59,  1.71it/s]
Train steps ... :  70%|██████▉   | 69935/100000 [20:37:52<4:52:48,  1.71it/s]
Train steps ... :  70%|██████▉   | 69936/100000 [20:37:53<4:52:58,  1.71it/s]
Train steps ... :  70%|██████▉   | 69937/100000 [20:37:54<4:53:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69938/100000 [20:37:54<4:52:54,  1.71it/s]
Train steps ... :  70%|██████▉   | 69939/100000 [20:37:55<4:52:56,  1.71it/s]
Train steps ... :  70%|██████▉   | 69940/100000 [20:37:55<4:52:42,  1.71it/s]
Train steps ... :  70%|██████▉   | 69941/100000 [20:37:56<4:52:56,  1.71it/s]
Train steps ... :  70%|██████▉   | 69942/100000 [20:37:57<4:52:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69943/100000 [20:37:57<4:52:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69944/100000 [20:37:58<4:52:47,  1.71it/s]
Train steps ... :  70%|██████▉   | 69945/100000 [20:37:58<4:52:42,  1.71it/s]
Train steps ... :  70%|██████▉   | 69946/100000 [20:37:59<4:52:41,  1.71it/s]
Train steps ... :  70%|██████▉   | 69947/100000 [20:38:00<4:52:53,  1.71it/s]
Train steps ... :  70%|██████▉   | 69948/100000 [20:38:00<4:52:55,  1.71it/s]
Train steps ... :  70%|██████▉   | 69949/100000 [20:38:01<4:52:40,  1.71it/s]
Train steps ... :  70%|██████▉   | 69950/100000 [20:38:01<4:52:48,  1.71it/s]Step... (69950 / 100000 | Loss: 0.6818666458129883, Learning Rate: 3.0201005025125628e-05)
+
                                                                             
Step... (69950 / 100000 | Loss: 0.8953131437301636, Learning Rate: 3.0201005025125628e-05)
+
Train steps ... :  70%|██��███▉   | 69950/100000 [20:38:02<4:52:48,  1.71it/s]
Train steps ... :  70%|██████▉   | 69951/100000 [20:38:02<4:52:43,  1.71it/s]
Train steps ... :  70%|██████▉   | 69952/100000 [20:38:02<4:52:30,  1.71it/s]
Train steps ... :  70%|██████▉   | 69953/100000 [20:38:03<4:52:52,  1.71it/s]
Train steps ... :  70%|██████▉   | 69954/100000 [20:38:04<4:52:45,  1.71it/s]
Train steps ... :  70%|██████▉   | 69955/100000 [20:38:04<4:52:33,  1.71it/s]
Train steps ... :  70%|██████▉   | 69956/100000 [20:38:05<4:53:11,  1.71it/s]
Train steps ... :  70%|██████▉   | 69957/100000 [20:38:05<4:53:14,  1.71it/s]
Train steps ... :  70%|██████▉   | 69958/100000 [20:38:06<4:53:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69959/100000 [20:38:07<4:53:06,  1.71it/s]
Train steps ... :  70%|██████▉   | 69960/100000 [20:38:07<4:53:02,  1.71it/s]
Train steps ... :  70%|██████▉   | 69961/100000 [20:38:08<4:52:56,  1.71it/s]
Train steps ... :  70%|██████▉   | 69962/100000 [20:38:08<4:52:40,  1.71it/s]
Train steps ... :  70%|██████▉   | 69963/100000 [20:38:09<4:52:28,  1.71it/s]
Train steps ... :  70%|██████▉   | 69964/100000 [20:38:09<4:52:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69965/100000 [20:38:10<4:52:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69966/100000 [20:38:11<4:53:03,  1.71it/s]
Train steps ... :  70%|██████▉   | 69967/100000 [20:38:11<4:52:40,  1.71it/s]
Train steps ... :  70%|██████▉   | 69968/100000 [20:38:12<4:52:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69969/100000 [20:38:12<4:53:06,  1.71it/s]
Train steps ... :  70%|██████▉   | 69970/100000 [20:38:13<4:53:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69971/100000 [20:38:14<4:53:25,  1.71it/s]
Train steps ... :  70%|██████▉   | 69972/100000 [20:38:14<4:53:23,  1.71it/s]
Train steps ... :  70%|██████▉   | 69973/100000 [20:38:15<4:53:00,  1.71it/s]
Train steps ... :  70%|██████▉   | 69974/100000 [20:38:15<4:52:54,  1.71it/s]
Train steps ... :  70%|██████▉   | 69975/100000 [20:38:16<4:52:45,  1.71it/s]Step... (69975 / 100000 | Loss: 0.6717560291290283, Learning Rate: 3.0175879396984924e-05)
+
                                                                             
Step... (69975 / 100000 | Loss: 0.691656768321991, Learning Rate: 3.0175879396984924e-05)
+
Train steps ... :  70%|██████▉   | 69975/100000 [20:38:16<4:52:45,  1.71it/s]
Train steps ... :  70%|██████▉   | 69976/100000 [20:38:16<4:52:41,  1.71it/s]
Train steps ... :  70%|██████▉   | 69977/100000 [20:38:17<4:52:36,  1.71it/s]
Train steps ... :  70%|██████▉   | 69978/100000 [20:38:18<4:52:44,  1.71it/s]
Train steps ... :  70%|██████▉   | 69979/100000 [20:38:18<4:52:46,  1.71it/s]
Train steps ... :  70%|██████▉   | 69980/100000 [20:38:19<4:52:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69981/100000 [20:38:19<4:52:35,  1.71it/s]
Train steps ... :  70%|██████▉   | 69982/100000 [20:38:20<4:52:30,  1.71it/s]
Train steps ... :  70%|██████▉   | 69983/100000 [20:38:21<4:52:31,  1.71it/s]
Train steps ... :  70%|██████▉   | 69984/100000 [20:38:21<4:52:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69985/100000 [20:38:22<4:52:16,  1.71it/s]
Train steps ... :  70%|██████▉   | 69986/100000 [20:38:22<4:52:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69987/100000 [20:38:23<4:52:08,  1.71it/s]
Train steps ... :  70%|██████▉   | 69988/100000 [20:38:23<4:52:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69989/100000 [20:38:24<4:52:02,  1.71it/s]
Train steps ... :  70%|██████▉   | 69990/100000 [20:38:25<4:52:21,  1.71it/s]
Train steps ... :  70%|██████▉   | 69991/100000 [20:38:25<4:52:10,  1.71it/s]
Train steps ... :  70%|██████▉   | 69992/100000 [20:38:26<4:52:07,  1.71it/s]
Train steps ... :  70%|██████▉   | 69993/100000 [20:38:26<4:52:29,  1.71it/s]
Train steps ... :  70%|██████▉   | 69994/100000 [20:38:27<4:53:03,  1.71it/s]
Train steps ... :  70%|██████▉   | 69995/100000 [20:38:28<4:52:34,  1.71it/s]
Train steps ... :  70%|██████▉   | 69996/100000 [20:38:28<4:52:29,  1.71it/s]
Train steps ... :  70%|██████▉   | 69997/100000 [20:38:29<4:52:19,  1.71it/s]
Train steps ... :  70%|██████▉   | 69998/100000 [20:38:29<4:52:11,  1.71it/s]
Train steps ... :  70%|██████▉   | 69999/100000 [20:38:30<4:52:04,  1.71it/s]
Train steps ... :  70%|███████   | 70000/100000 [20:38:30<4:52:13,  1.71it/s]Step... (70000 / 100000 | Loss: 0.5002646446228027, Learning Rate: 3.015075376884422e-05)
+
                                                                             
Step... (70000 / 100000 | Loss: 0.8032557964324951, Learning Rate: 3.015075376884422e-05)
+
Train steps ... :  70%|███████   | 70000/100000 [20:38:31<4:52:13,  1.71it/s]06/18/2024 12:32:58 - INFO - accelerate.accelerator - Saving current state to ./checkpoint-70000-epoch-4
+06/18/2024 12:32:58 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/18/2024 12:33:00 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-70000-epoch-4/model.safetensors
+06/18/2024 12:33:00 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/18/2024 12:33:04 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-70000-epoch-4/model_1.safetensors
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Optimizer state saved in checkpoint-70000-epoch-4/optimizer.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Scheduler state saved in checkpoint-70000-epoch-4/scheduler.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in checkpoint-70000-epoch-4/sampler.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in checkpoint-70000-epoch-4/sampler_1.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 2 saved in checkpoint-70000-epoch-4/sampler_2.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 3 saved in checkpoint-70000-epoch-4/sampler_3.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 4 saved in checkpoint-70000-epoch-4/sampler_4.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 5 saved in checkpoint-70000-epoch-4/sampler_5.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 6 saved in checkpoint-70000-epoch-4/sampler_6.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 7 saved in checkpoint-70000-epoch-4/sampler_7.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 8 saved in checkpoint-70000-epoch-4/sampler_8.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 9 saved in checkpoint-70000-epoch-4/sampler_9.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 10 saved in checkpoint-70000-epoch-4/sampler_10.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 11 saved in checkpoint-70000-epoch-4/sampler_11.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 12 saved in checkpoint-70000-epoch-4/sampler_12.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 13 saved in checkpoint-70000-epoch-4/sampler_13.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 14 saved in checkpoint-70000-epoch-4/sampler_14.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 15 saved in checkpoint-70000-epoch-4/sampler_15.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 16 saved in checkpoint-70000-epoch-4/sampler_16.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Sampler state for dataloader 17 saved in checkpoint-70000-epoch-4/sampler_17.bin
+06/18/2024 12:33:05 - INFO - accelerate.checkpointing - Random states saved in checkpoint-70000-epoch-4/random_states_0.pkl
+06/18/2024 12:33:05 - INFO - __main__ - Deleting older checkpoint [checkpoint-45000-epoch-2] due to args.save_total_limit
+
+
  0%|          | 0/5 [00:00<?, ?it/s]
+
 20%|██        | 1/5 [01:45<07:00, 105.15s/it]
+
 40%|████      | 2/5 [02:19<03:09, 63.30s/it] 
+
 60%|██████    | 3/5 [02:19<01:09, 34.70s/it]
+
 80%|████████  | 4/5 [02:20<00:21, 21.31s/it]
+
100%|██████████| 5/5 [02:21<00:00, 13.81s/it]
100%|██████████| 5/5 [02:21<00:00, 28.23s/it]