The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 18149 examples [00:00, 177054.42 examples/s]
Generating train split: 54384 examples [00:00, 173143.42 examples/s]
Generating train split: 90647 examples [00:00, 170911.90 examples/s]
Generating train split: 115136 examples [00:00, 172763.06 examples/s]
Generating train split: 115136 examples [00:00, 172590.96 examples/s]

Generating validation split: 0 examples [00:00, ? examples/s]
Generating validation split: 128 examples [00:00, 24879.32 examples/s]

Filter:   0%|          | 0/115136 [00:00<?, ? examples/s]
Filter:   5%|▌         | 6000/115136 [00:00<00:01, 56662.56 examples/s]
Filter:  10%|█         | 12000/115136 [00:00<00:01, 57675.70 examples/s]
Filter:  16%|█▌        | 18000/115136 [00:00<00:01, 57864.71 examples/s]
Filter:  21%|██        | 24000/115136 [00:00<00:01, 58004.92 examples/s]
Filter:  26%|██▌       | 30000/115136 [00:00<00:01, 58150.58 examples/s]
Filter:  31%|███▏      | 36000/115136 [00:00<00:01, 58275.52 examples/s]
Filter:  36%|███▋      | 42000/115136 [00:00<00:01, 58357.88 examples/s]
Filter:  42%|████▏     | 48000/115136 [00:00<00:01, 58360.88 examples/s]
Filter:  47%|████▋     | 54000/115136 [00:00<00:01, 58214.37 examples/s]
Filter:  52%|█████▏    | 60000/115136 [00:01<00:00, 58005.25 examples/s]
Filter:  57%|█████▋    | 66000/115136 [00:01<00:00, 57931.13 examples/s]
Filter:  63%|██████▎   | 72000/115136 [00:01<00:00, 58061.21 examples/s]
Filter:  68%|██████▊   | 78000/115136 [00:01<00:00, 58023.50 examples/s]
Filter:  73%|███████▎  | 84000/115136 [00:01<00:00, 57419.44 examples/s]
Filter:  78%|███████▊  | 90000/115136 [00:01<00:00, 57681.80 examples/s]
Filter:  83%|████████▎ | 96000/115136 [00:01<00:00, 57870.37 examples/s]
Filter:  89%|████████▊ | 102000/115136 [00:01<00:00, 57565.44 examples/s]
Filter:  94%|█████████▍| 108000/115136 [00:01<00:00, 57290.62 examples/s]
Filter:  99%|█████████▉| 114000/115136 [00:01<00:00, 57257.42 examples/s]
Filter: 100%|██████████| 115136/115136 [00:01<00:00, 57721.47 examples/s]

Filter:   0%|          | 0/128 [00:00<?, ? examples/s]
Filter: 100%|██████████| 128/128 [00:00<00:00, 24405.44 examples/s]

Tokenizing:   0%|          | 0/115136 [00:00<?, ? examples/s]
Tokenizing:   2%|▏         | 2000/115136 [00:00<00:06, 17585.48 examples/s]
Tokenizing:   3%|▎         | 4000/115136 [00:00<00:12, 8575.37 examples/s] 
Tokenizing:   5%|▌         | 6000/115136 [00:00<00:09, 11353.02 examples/s]
Tokenizing:   7%|▋         | 8000/115136 [00:00<00:07, 13403.83 examples/s]
Tokenizing:   9%|▊         | 10000/115136 [00:00<00:07, 14224.94 examples/s]
Tokenizing:  10%|█         | 12000/115136 [00:00<00:06, 15206.32 examples/s]
Tokenizing:  12%|█▏        | 14000/115136 [00:00<00:06, 15977.01 examples/s]
Tokenizing:  14%|█▍        | 16000/115136 [00:01<00:05, 16890.10 examples/s]
Tokenizing:  16%|█▌        | 18000/115136 [00:01<00:08, 11411.57 examples/s]
Tokenizing:  17%|█▋        | 20000/115136 [00:01<00:07, 12873.45 examples/s]
Tokenizing:  19%|█▉        | 22000/115136 [00:01<00:06, 14238.86 examples/s]
Tokenizing:  21%|██        | 24000/115136 [00:01<00:05, 15388.46 examples/s]
Tokenizing:  23%|██▎       | 26000/115136 [00:01<00:05, 16336.68 examples/s]
Tokenizing:  24%|██▍       | 28000/115136 [00:01<00:05, 17177.19 examples/s]
Tokenizing:  26%|██▌       | 30000/115136 [00:02<00:06, 12875.29 examples/s]
Tokenizing:  28%|██▊       | 32000/115136 [00:02<00:05, 14255.29 examples/s]
Tokenizing:  30%|██▉       | 34000/115136 [00:02<00:05, 15377.67 examples/s]
Tokenizing:  31%|███▏      | 36000/115136 [00:02<00:04, 16276.58 examples/s]
Tokenizing:  33%|███▎      | 38000/115136 [00:02<00:04, 16934.71 examples/s]
Tokenizing:  35%|███▍      | 40000/115136 [00:02<00:04, 17522.14 examples/s]
Tokenizing:  36%|███▋      | 42000/115136 [00:02<00:04, 17867.88 examples/s]
Tokenizing:  38%|███▊      | 44000/115136 [00:03<00:05, 13686.94 examples/s]
Tokenizing:  40%|███▉      | 46000/115136 [00:03<00:04, 14673.99 examples/s]
Tokenizing:  42%|████▏     | 48000/115136 [00:03<00:04, 15693.18 examples/s]
Tokenizing:  43%|████▎     | 50000/115136 [00:03<00:03, 16372.31 examples/s]
Tokenizing:  45%|████▌     | 52000/115136 [00:03<00:03, 16928.00 examples/s]
Tokenizing:  47%|████▋     | 54000/115136 [00:03<00:03, 17432.21 examples/s]
Tokenizing:  49%|████▊     | 56000/115136 [00:03<00:03, 17828.35 examples/s]
Tokenizing:  50%|█████     | 58000/115136 [00:03<00:04, 12487.07 examples/s]
Tokenizing:  52%|█████▏    | 60000/115136 [00:04<00:04, 13201.04 examples/s]
Tokenizing:  54%|█████▍    | 62000/115136 [00:04<00:03, 13982.51 examples/s]
Tokenizing:  56%|█████▌    | 64000/115136 [00:04<00:03, 15100.48 examples/s]
Tokenizing:  57%|█████▋    | 66000/115136 [00:04<00:03, 16097.11 examples/s]
Tokenizing:  59%|█████▉    | 68000/115136 [00:04<00:02, 16869.73 examples/s]
Tokenizing:  61%|██████    | 70000/115136 [00:04<00:02, 17431.16 examples/s]
Tokenizing:  63%|██████▎   | 72000/115136 [00:04<00:03, 13787.78 examples/s]
Tokenizing:  65%|██████▌   | 75000/115136 [00:05<00:02, 15326.54 examples/s]
Tokenizing:  67%|██████▋   | 77000/115136 [00:05<00:02, 16109.26 examples/s]
Tokenizing:  69%|██████▊   | 79000/115136 [00:05<00:02, 16845.97 examples/s]
Tokenizing:  70%|███████   | 81000/115136 [00:05<00:01, 17328.24 examples/s]
Tokenizing:  72%|███████▏  | 83000/115136 [00:05<00:01, 17739.74 examples/s]
Tokenizing:  74%|███████▍  | 85000/115136 [00:05<00:01, 18103.19 examples/s]
Tokenizing:  76%|███████▌  | 87000/115136 [00:05<00:02, 13982.52 examples/s]
Tokenizing:  77%|███████▋  | 89000/115136 [00:05<00:01, 14922.50 examples/s]
Tokenizing:  79%|███████▉  | 91000/115136 [00:05<00:01, 15850.53 examples/s]
Tokenizing:  81%|████████  | 93000/115136 [00:06<00:01, 16706.53 examples/s]
Tokenizing:  83%|████████▎ | 95000/115136 [00:06<00:01, 17221.62 examples/s]
Tokenizing:  84%|████████▍ | 97000/115136 [00:06<00:01, 17683.85 examples/s]
Tokenizing:  86%|████████▌ | 99000/115136 [00:06<00:00, 18236.63 examples/s]
Tokenizing:  88%|████████▊ | 101000/115136 [00:06<00:01, 14109.21 examples/s]
Tokenizing:  89%|████████▉ | 103000/115136 [00:06<00:00, 15119.14 examples/s]
Tokenizing:  91%|█████████ | 105000/115136 [00:06<00:00, 16276.07 examples/s]
Tokenizing:  93%|█████████▎| 107000/115136 [00:06<00:00, 16942.05 examples/s]
Tokenizing:  95%|█████████▍| 109000/115136 [00:07<00:00, 17152.94 examples/s]
Tokenizing:  96%|█████████▋| 111000/115136 [00:07<00:00, 17811.55 examples/s]
Tokenizing:  98%|█████████▊| 113000/115136 [00:07<00:00, 18173.39 examples/s]
Tokenizing: 100%|█████████▉| 115000/115136 [00:07<00:00, 18345.60 examples/s]
Tokenizing: 100%|██████████| 115136/115136 [00:07<00:00, 15581.83 examples/s]

Tokenizing:   0%|          | 0/128 [00:00<?, ? examples/s]
Tokenizing: 100%|██████████| 128/128 [00:00<00:00, 9110.01 examples/s]
/opt/mobtranslate-v24-venv/lib/python3.11/site-packages/peft/tuners/tuners_utils.py:1332: UserWarning: You have requested `ensure_weight_tying`, but no tied modules are added in either `modules_to_save` or `target_modules`
  warnings.warn(
/workspace/v24.3-joint-lexeme-dose29-rerun1/scripts/train_nllb_lora.py:505: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `ExposureAccountingTrainer.__init__`. Use `processing_class` instead.
  super().__init__(*args, **kwargs)
trainable params: 47,186,944 || all params: 1,417,825,280 || trainable%: 3.3281

  0%|          | 0/3598 [00:00<?, ?it/s]
  0%|          | 1/3598 [00:01<1:29:24,  1.49s/it]
  0%|          | 2/3598 [00:02<1:07:51,  1.13s/it]
  0%|          | 3/3598 [00:03<1:13:43,  1.23s/it]
  0%|          | 4/3598 [00:04<1:05:23,  1.09s/it]
  0%|          | 5/3598 [00:05<59:22,  1.01it/s]  
  0%|          | 6/3598 [00:06<1:04:05,  1.07s/it]
  0%|          | 7/3598 [00:07<1:00:29,  1.01s/it]
  0%|          | 8/3598 [00:08<1:05:17,  1.09s/it]
  0%|          | 9/3598 [00:10<1:08:16,  1.14s/it]
  0%|          | 10/3598 [00:11<1:07:26,  1.13s/it]
                                                   

  0%|          | 10/3598 [00:11<1:07:26,  1.13s/it]
  0%|          | 11/3598 [00:12<1:02:59,  1.05s/it]
  0%|          | 12/3598 [00:12<1:01:05,  1.02s/it]
  0%|          | 13/3598 [00:14<1:03:46,  1.07s/it]
  0%|          | 14/3598 [00:15<1:07:45,  1.13s/it]
  0%|          | 15/3598 [00:16<1:08:59,  1.16s/it]
  0%|          | 16/3598 [00:17<1:04:22,  1.08s/it]
  0%|          | 17/3598 [00:18<1:01:17,  1.03s/it]
  1%|          | 18/3598 [00:19<1:07:26,  1.13s/it]
  1%|          | 19/3598 [00:20<1:03:30,  1.06s/it]
  1%|          | 20/3598 [00:21<1:00:26,  1.01s/it]
                                                   

  1%|          | 20/3598 [00:21<1:00:26,  1.01s/it]
  1%|          | 21/3598 [00:22<1:05:44,  1.10s/it]
  1%|          | 22/3598 [00:23<1:02:18,  1.05s/it]
  1%|          | 23/3598 [00:24<1:01:23,  1.03s/it]
  1%|          | 24/3598 [00:26<1:04:57,  1.09s/it]
  1%|          | 25/3598 [00:26<1:01:46,  1.04s/it]
  1%|          | 26/3598 [00:27<58:24,  1.02it/s]  
  1%|          | 27/3598 [00:28<56:51,  1.05it/s]
  1%|          | 28/3598 [00:29<55:12,  1.08it/s]
  1%|          | 29/3598 [00:30<52:50,  1.13it/s]
  1%|          | 30/3598 [00:31<54:34,  1.09it/s]
                                                 

  1%|          | 30/3598 [00:31<54:34,  1.09it/s]
  1%|          | 31/3598 [00:32<55:57,  1.06it/s]
  1%|          | 32/3598 [00:33<1:02:18,  1.05s/it]
  1%|          | 33/3598 [00:35<1:08:05,  1.15s/it]
  1%|          | 34/3598 [00:36<1:08:53,  1.16s/it]
  1%|          | 35/3598 [00:37<1:05:39,  1.11s/it]
  1%|          | 36/3598 [00:38<1:03:03,  1.06s/it]
  1%|          | 37/3598 [00:39<1:08:48,  1.16s/it]
  1%|          | 38/3598 [00:40<1:11:30,  1.21s/it]
  1%|          | 39/3598 [00:41<1:07:02,  1.13s/it]
  1%|          | 40/3598 [00:42<1:04:22,  1.09s/it]
                                                   

  1%|          | 40/3598 [00:42<1:04:22,  1.09s/it]
  1%|          | 41/3598 [00:44<1:09:39,  1.18s/it]
  1%|          | 42/3598 [00:45<1:04:50,  1.09s/it]
  1%|          | 43/3598 [00:46<1:01:39,  1.04s/it]
  1%|          | 44/3598 [00:46<58:56,  1.00it/s]  
  1%|▏         | 45/3598 [00:47<58:18,  1.02it/s]
  1%|▏         | 46/3598 [00:48<56:57,  1.04it/s]
  1%|▏         | 47/3598 [00:49<55:40,  1.06it/s]
  1%|▏         | 48/3598 [00:50<56:18,  1.05it/s]
  1%|▏         | 49/3598 [00:51<55:40,  1.06it/s]
  1%|▏         | 50/3598 [00:52<56:13,  1.05it/s]
                                                 

  1%|▏         | 50/3598 [00:52<56:13,  1.05it/s]
  1%|▏         | 51/3598 [00:53<55:54,  1.06it/s]
  1%|▏         | 52/3598 [00:54<53:06,  1.11it/s]
  1%|▏         | 53/3598 [00:55<54:05,  1.09it/s]
  2%|▏         | 54/3598 [00:56<1:01:47,  1.05s/it]
  2%|▏         | 55/3598 [00:57<1:00:42,  1.03s/it]
  2%|▏         | 56/3598 [00:58<57:41,  1.02it/s]  
  2%|▏         | 57/3598 [00:59<1:05:29,  1.11s/it]
  2%|▏         | 58/3598 [01:01<1:09:26,  1.18s/it]
  2%|▏         | 59/3598 [01:02<1:07:24,  1.14s/it]
  2%|▏         | 60/3598 [01:03<1:03:49,  1.08s/it]
                                                   

  2%|▏         | 60/3598 [01:03<1:03:49,  1.08s/it]
  2%|▏         | 61/3598 [01:04<1:02:15,  1.06s/it]
  2%|▏         | 62/3598 [01:05<1:07:59,  1.15s/it]
  2%|▏         | 63/3598 [01:06<1:04:13,  1.09s/it]
  2%|▏         | 64/3598 [01:07<1:06:58,  1.14s/it]
  2%|▏         | 65/3598 [01:08<1:04:06,  1.09s/it]
  2%|▏         | 66/3598 [01:09<1:00:30,  1.03s/it]
  2%|▏         | 67/3598 [01:10<1:06:46,  1.13s/it]
  2%|▏         | 68/3598 [01:11<1:02:36,  1.06s/it]
  2%|▏         | 69/3598 [01:13<1:05:49,  1.12s/it]
  2%|▏         | 70/3598 [01:14<1:03:30,  1.08s/it]
                                                   

  2%|▏         | 70/3598 [01:14<1:03:30,  1.08s/it]
  2%|▏         | 71/3598 [01:15<1:00:39,  1.03s/it]
  2%|▏         | 72/3598 [01:16<1:03:10,  1.07s/it]
  2%|▏         | 73/3598 [01:17<1:08:24,  1.16s/it]
  2%|▏         | 74/3598 [01:18<1:10:50,  1.21s/it]
  2%|▏         | 75/3598 [01:19<1:04:53,  1.11s/it]
  2%|▏         | 76/3598 [01:20<1:02:47,  1.07s/it]
  2%|▏         | 77/3598 [01:21<1:01:00,  1.04s/it]
  2%|▏         | 78/3598 [01:22<57:59,  1.01it/s]  
  2%|▏         | 79/3598 [01:23<57:33,  1.02it/s]
  2%|▏         | 80/3598 [01:24<56:44,  1.03it/s]
                                                 

  2%|▏         | 80/3598 [01:24<56:44,  1.03it/s]
  2%|▏         | 81/3598 [01:25<53:53,  1.09it/s]
  2%|▏         | 82/3598 [01:26<58:22,  1.00it/s]
  2%|▏         | 83/3598 [01:27<1:03:48,  1.09s/it]
  2%|▏         | 84/3598 [01:29<1:07:19,  1.15s/it]
  2%|▏         | 85/3598 [01:30<1:06:09,  1.13s/it]
  2%|▏         | 86/3598 [01:30<1:01:17,  1.05s/it]
  2%|▏         | 87/3598 [01:31<59:06,  1.01s/it]  
  2%|▏         | 88/3598 [01:33<1:01:47,  1.06s/it]
  2%|▏         | 89/3598 [01:34<1:04:09,  1.10s/it]
  3%|▎         | 90/3598 [01:35<59:47,  1.02s/it]  
                                                 

  3%|▎         | 90/3598 [01:35<59:47,  1.02s/it]
  3%|▎         | 91/3598 [01:36<1:00:36,  1.04s/it]
  3%|▎         | 92/3598 [01:37<58:46,  1.01s/it]  
  3%|▎         | 93/3598 [01:37<56:08,  1.04it/s]
  3%|▎         | 94/3598 [01:38<56:05,  1.04it/s]
  3%|▎         | 95/3598 [01:39<54:56,  1.06it/s]
  3%|▎         | 96/3598 [01:40<53:45,  1.09it/s]
  3%|▎         | 97/3598 [01:42<1:01:52,  1.06s/it]
  3%|▎         | 98/3598 [01:43<1:02:26,  1.07s/it]
  3%|▎         | 99/3598 [01:44<1:01:53,  1.06s/it]
  3%|▎         | 100/3598 [01:45<1:06:00,  1.13s/it]
                                                    

  3%|▎         | 100/3598 [01:45<1:06:00,  1.13s/it]
  3%|▎         | 101/3598 [01:46<1:01:31,  1.06s/it]
  3%|▎         | 102/3598 [01:47<1:00:23,  1.04s/it]
  3%|▎         | 103/3598 [01:48<1:04:46,  1.11s/it]
  3%|▎         | 104/3598 [01:50<1:09:18,  1.19s/it]
  3%|▎         | 105/3598 [01:51<1:08:13,  1.17s/it]
  3%|▎         | 106/3598 [01:52<1:04:00,  1.10s/it]
  3%|▎         | 107/3598 [01:53<1:05:14,  1.12s/it]
  3%|▎         | 108/3598 [01:54<1:00:41,  1.04s/it]
  3%|▎         | 109/3598 [01:55<57:59,  1.00it/s]  
  3%|▎         | 110/3598 [01:55<54:21,  1.07it/s]
                                                  

  3%|▎         | 110/3598 [01:55<54:21,  1.07it/s]
  3%|▎         | 111/3598 [01:56<57:06,  1.02it/s]
  3%|▎         | 112/3598 [01:57<56:01,  1.04it/s]
  3%|▎         | 113/3598 [01:58<55:50,  1.04it/s]
  3%|▎         | 114/3598 [01:59<58:00,  1.00it/s]
  3%|▎         | 115/3598 [02:01<1:02:03,  1.07s/it]
  3%|▎         | 116/3598 [02:02<1:01:16,  1.06s/it]
  3%|▎         | 117/3598 [02:03<1:05:00,  1.12s/it]
  3%|▎         | 118/3598 [02:04<1:01:08,  1.05s/it]
  3%|▎         | 119/3598 [02:05<57:39,  1.01it/s]  
  3%|▎         | 120/3598 [02:06<57:48,  1.00it/s]
                                                  

  3%|▎         | 120/3598 [02:06<57:48,  1.00it/s]
  3%|▎         | 121/3598 [02:07<59:59,  1.04s/it]
  3%|▎         | 122/3598 [02:08<57:43,  1.00it/s]
  3%|▎         | 123/3598 [02:09<55:40,  1.04it/s]
  3%|▎         | 124/3598 [02:10<1:01:09,  1.06s/it]
  3%|▎         | 125/3598 [02:11<1:00:36,  1.05s/it]
  4%|▎         | 126/3598 [02:12<1:00:48,  1.05s/it]
  4%|▎         | 127/3598 [02:13<57:36,  1.00it/s]  
  4%|▎         | 128/3598 [02:14<54:28,  1.06it/s]
  4%|▎         | 129/3598 [02:15<53:57,  1.07it/s]
  4%|▎         | 130/3598 [02:15<54:08,  1.07it/s]
                                                  

  4%|▎         | 130/3598 [02:15<54:08,  1.07it/s]
  4%|▎         | 131/3598 [02:16<52:36,  1.10it/s]
  4%|▎         | 132/3598 [02:17<50:50,  1.14it/s]
  4%|▎         | 133/3598 [02:18<57:30,  1.00it/s]
  4%|▎         | 134/3598 [02:19<57:27,  1.00it/s]
  4%|▍         | 135/3598 [02:20<57:33,  1.00it/s]
  4%|▍         | 136/3598 [02:21<55:47,  1.03it/s]
  4%|▍         | 137/3598 [02:22<53:21,  1.08it/s]
  4%|▍         | 138/3598 [02:23<51:50,  1.11it/s]
  4%|▍         | 139/3598 [02:24<51:21,  1.12it/s]
  4%|▍         | 140/3598 [02:25<57:47,  1.00s/it]
                                                  

  4%|▍         | 140/3598 [02:25<57:47,  1.00s/it]
  4%|▍         | 141/3598 [02:26<57:26,  1.00it/s]
  4%|▍         | 142/3598 [02:27<56:30,  1.02it/s]
  4%|▍         | 143/3598 [02:28<54:35,  1.05it/s]
  4%|▍         | 144/3598 [02:29<53:08,  1.08it/s]
  4%|▍         | 145/3598 [02:30<1:01:27,  1.07s/it]
  4%|▍         | 146/3598 [02:31<1:04:12,  1.12s/it]
  4%|▍         | 147/3598 [02:32<1:01:28,  1.07s/it]
  4%|▍         | 148/3598 [02:33<59:17,  1.03s/it]  
  4%|▍         | 149/3598 [02:34<58:27,  1.02s/it]
  4%|▍         | 150/3598 [02:35<55:27,  1.04it/s]
                                                  

  4%|▍         | 150/3598 [02:35<55:27,  1.04it/s]
  4%|▍         | 151/3598 [02:36<58:56,  1.03s/it]
  4%|▍         | 152/3598 [02:37<56:03,  1.02it/s]
  4%|▍         | 153/3598 [02:38<54:29,  1.05it/s]
  4%|▍         | 154/3598 [02:39<58:25,  1.02s/it]
  4%|▍         | 155/3598 [02:40<1:02:35,  1.09s/it]
  4%|▍         | 156/3598 [02:41<58:55,  1.03s/it]  
  4%|▍         | 157/3598 [02:43<1:03:49,  1.11s/it]
  4%|▍         | 158/3598 [02:44<1:01:28,  1.07s/it]
  4%|▍         | 159/3598 [02:45<59:10,  1.03s/it]  
  4%|▍         | 160/3598 [02:46<1:01:10,  1.07s/it]
                                                    

  4%|▍         | 160/3598 [02:46<1:01:10,  1.07s/it]
  4%|▍         | 161/3598 [02:47<57:52,  1.01s/it]  
  5%|▍         | 162/3598 [02:48<55:49,  1.03it/s]
  5%|▍         | 163/3598 [02:49<1:00:24,  1.06s/it]
  5%|▍         | 164/3598 [02:50<57:09,  1.00it/s]  
  5%|▍         | 165/3598 [02:51<1:01:11,  1.07s/it]
  5%|▍         | 166/3598 [02:52<58:37,  1.02s/it]  
  5%|▍         | 167/3598 [02:53<1:02:57,  1.10s/it]
  5%|▍         | 168/3598 [02:54<58:01,  1.02s/it]  
  5%|▍         | 169/3598 [02:55<56:26,  1.01it/s]
  5%|▍         | 170/3598 [02:56<56:36,  1.01it/s]
                                                  

  5%|▍         | 170/3598 [02:56<56:36,  1.01it/s]
  5%|▍         | 171/3598 [02:57<56:19,  1.01it/s]
  5%|▍         | 172/3598 [02:58<53:20,  1.07it/s]
  5%|▍         | 173/3598 [02:59<56:15,  1.01it/s]
  5%|▍         | 174/3598 [03:00<54:03,  1.06it/s]
  5%|▍         | 175/3598 [03:01<54:21,  1.05it/s]
  5%|▍         | 176/3598 [03:01<54:43,  1.04it/s]
  5%|▍         | 177/3598 [03:02<54:42,  1.04it/s]
  5%|▍         | 178/3598 [03:03<53:46,  1.06it/s]
  5%|▍         | 179/3598 [03:04<53:20,  1.07it/s]
  5%|▌         | 180/3598 [03:05<57:47,  1.01s/it]
                                                  

  5%|▌         | 180/3598 [03:05<57:47,  1.01s/it]
  5%|▌         | 181/3598 [03:06<54:17,  1.05it/s]
  5%|▌         | 182/3598 [03:07<53:30,  1.06it/s]
  5%|▌         | 183/3598 [03:08<55:26,  1.03it/s]
  5%|▌         | 184/3598 [03:10<1:01:33,  1.08s/it]
  5%|▌         | 185/3598 [03:10<58:25,  1.03s/it]  
  5%|▌         | 186/3598 [03:12<1:02:46,  1.10s/it]
  5%|▌         | 187/3598 [03:13<59:04,  1.04s/it]  
  5%|▌         | 188/3598 [03:14<56:20,  1.01it/s]
  5%|▌         | 189/3598 [03:14<55:06,  1.03it/s]
  5%|▌         | 190/3598 [03:15<53:40,  1.06it/s]
                                                  

  5%|▌         | 190/3598 [03:15<53:40,  1.06it/s]
  5%|▌         | 191/3598 [03:16<51:47,  1.10it/s]
  5%|▌         | 192/3598 [03:17<52:29,  1.08it/s]
  5%|▌         | 193/3598 [03:18<50:35,  1.12it/s]
  5%|▌         | 194/3598 [03:19<50:48,  1.12it/s]
  5%|▌         | 195/3598 [03:20<52:14,  1.09it/s]
  5%|▌         | 196/3598 [03:21<56:19,  1.01it/s]
  5%|▌         | 197/3598 [03:22<59:34,  1.05s/it]
  6%|▌         | 198/3598 [03:24<1:05:34,  1.16s/it]
  6%|▌         | 199/3598 [03:25<1:03:00,  1.11s/it]
  6%|▌         | 200/3598 [03:26<1:08:02,  1.20s/it]
                                                    

  6%|▌         | 200/3598 [03:26<1:08:02,  1.20s/it]
  6%|▌         | 201/3598 [03:27<1:01:59,  1.09s/it]
  6%|▌         | 202/3598 [03:28<59:08,  1.04s/it]  
  6%|▌         | 203/3598 [03:29<58:05,  1.03s/it]
  6%|▌         | 204/3598 [03:30<1:04:53,  1.15s/it]
  6%|▌         | 205/3598 [03:31<1:01:35,  1.09s/it]
  6%|▌         | 206/3598 [03:33<1:07:02,  1.19s/it]
  6%|▌         | 207/3598 [03:33<1:01:32,  1.09s/it]
  6%|▌         | 208/3598 [03:35<1:02:11,  1.10s/it]
  6%|▌         | 209/3598 [03:35<58:10,  1.03s/it]  
  6%|▌         | 210/3598 [03:36<55:31,  1.02it/s]
                                                  

  6%|▌         | 210/3598 [03:36<55:31,  1.02it/s]
  6%|▌         | 211/3598 [03:37<54:27,  1.04it/s]
  6%|▌         | 212/3598 [03:38<54:02,  1.04it/s]
  6%|▌         | 213/3598 [03:39<52:40,  1.07it/s]
  6%|▌         | 214/3598 [03:40<1:00:36,  1.07s/it]
  6%|▌         | 215/3598 [03:42<1:06:14,  1.17s/it]
  6%|▌         | 216/3598 [03:43<1:01:19,  1.09s/it]
  6%|▌         | 217/3598 [03:44<58:53,  1.05s/it]  
  6%|▌         | 218/3598 [03:45<56:11,  1.00it/s]
  6%|▌         | 219/3598 [03:46<55:54,  1.01it/s]
  6%|▌         | 220/3598 [03:46<54:24,  1.03it/s]
                                                  

  6%|▌         | 220/3598 [03:46<54:24,  1.03it/s]
  6%|▌         | 221/3598 [03:48<58:35,  1.04s/it]
  6%|▌         | 222/3598 [03:49<57:53,  1.03s/it]
  6%|▌         | 223/3598 [03:50<57:46,  1.03s/it]
  6%|▌         | 224/3598 [03:51<55:55,  1.01it/s]
  6%|▋         | 225/3598 [03:52<1:00:52,  1.08s/it]
  6%|▋         | 226/3598 [03:53<59:31,  1.06s/it]  
  6%|▋         | 227/3598 [03:54<1:05:33,  1.17s/it]
  6%|▋         | 228/3598 [03:56<1:09:13,  1.23s/it]
  6%|▋         | 229/3598 [03:57<1:04:49,  1.15s/it]
  6%|▋         | 230/3598 [03:58<1:06:17,  1.18s/it]
                                                    

  6%|▋         | 230/3598 [03:58<1:06:17,  1.18s/it]
  6%|▋         | 231/3598 [03:59<1:01:12,  1.09s/it]
  6%|▋         | 232/3598 [04:00<1:03:59,  1.14s/it]
  6%|▋         | 233/3598 [04:01<1:01:31,  1.10s/it]
  7%|▋         | 234/3598 [04:02<58:12,  1.04s/it]  
  7%|▋         | 235/3598 [04:03<57:27,  1.03s/it]
  7%|▋         | 236/3598 [04:04<54:51,  1.02it/s]
  7%|▋         | 237/3598 [04:05<53:22,  1.05it/s]
  7%|▋         | 238/3598 [04:06<52:17,  1.07it/s]
  7%|▋         | 239/3598 [04:06<51:53,  1.08it/s]
  7%|▋         | 240/3598 [04:07<51:00,  1.10it/s]
                                                  

  7%|▋         | 240/3598 [04:07<51:00,  1.10it/s]
  7%|▋         | 241/3598 [04:08<50:24,  1.11it/s]
  7%|▋         | 242/3598 [04:09<49:08,  1.14it/s]
  7%|▋         | 243/3598 [04:10<51:24,  1.09it/s]
  7%|▋         | 244/3598 [04:11<51:22,  1.09it/s]
  7%|▋         | 245/3598 [04:12<50:42,  1.10it/s]
  7%|▋         | 246/3598 [04:13<49:26,  1.13it/s]
  7%|▋         | 247/3598 [04:14<51:49,  1.08it/s]
  7%|▋         | 248/3598 [04:15<52:14,  1.07it/s]
  7%|▋         | 249/3598 [04:16<59:47,  1.07s/it]
  7%|▋         | 250/3598 [04:17<56:03,  1.00s/it]
                                                  

  7%|▋         | 250/3598 [04:17<56:03,  1.00s/it]
  7%|▋         | 251/3598 [04:18<58:04,  1.04s/it]
  7%|▋         | 252/3598 [04:19<56:49,  1.02s/it]
  7%|▋         | 253/3598 [04:20<54:30,  1.02it/s]
  7%|▋         | 254/3598 [04:21<56:36,  1.02s/it]
  7%|▋         | 255/3598 [04:22<55:26,  1.00it/s]
  7%|▋         | 256/3598 [04:23<52:50,  1.05it/s]
  7%|▋         | 257/3598 [04:24<55:35,  1.00it/s]
  7%|▋         | 258/3598 [04:25<55:23,  1.01it/s]
  7%|▋         | 259/3598 [04:26<53:37,  1.04it/s]
  7%|▋         | 260/3598 [04:27<50:55,  1.09it/s]
                                                  

  7%|▋         | 260/3598 [04:27<50:55,  1.09it/s]
  7%|▋         | 261/3598 [04:28<51:56,  1.07it/s]
  7%|▋         | 262/3598 [04:29<55:51,  1.00s/it]
  7%|▋         | 263/3598 [04:30<59:50,  1.08s/it]
  7%|▋         | 264/3598 [04:31<58:16,  1.05s/it]
  7%|▋         | 265/3598 [04:32<56:51,  1.02s/it]
  7%|▋         | 266/3598 [04:33<54:43,  1.01it/s]
  7%|▋         | 267/3598 [04:34<1:01:32,  1.11s/it]
  7%|▋         | 268/3598 [04:35<58:32,  1.05s/it]  
  7%|▋         | 269/3598 [04:36<1:03:13,  1.14s/it]
  8%|▊         | 270/3598 [04:37<59:09,  1.07s/it]  
                                                  

  8%|▊         | 270/3598 [04:37<59:09,  1.07s/it]
  8%|▊         | 271/3598 [04:38<56:04,  1.01s/it]
  8%|▊         | 272/3598 [04:39<53:27,  1.04it/s]
  8%|▊         | 273/3598 [04:41<1:00:50,  1.10s/it]
  8%|▊         | 274/3598 [04:42<1:00:23,  1.09s/it]
  8%|▊         | 275/3598 [04:43<1:00:26,  1.09s/it]
  8%|▊         | 276/3598 [04:44<1:06:10,  1.20s/it]
  8%|▊         | 277/3598 [04:45<1:01:27,  1.11s/it]
  8%|▊         | 278/3598 [04:46<56:16,  1.02s/it]  
  8%|▊         | 279/3598 [04:47<1:02:08,  1.12s/it]
  8%|▊         | 280/3598 [04:48<1:00:20,  1.09s/it]
                                                    

  8%|▊         | 280/3598 [04:48<1:00:20,  1.09s/it]
  8%|▊         | 281/3598 [04:50<1:04:44,  1.17s/it]
  8%|▊         | 282/3598 [04:50<59:31,  1.08s/it]  
  8%|▊         | 283/3598 [04:51<56:02,  1.01s/it]
  8%|▊         | 284/3598 [04:52<54:12,  1.02it/s]
  8%|▊         | 285/3598 [04:53<52:48,  1.05it/s]
  8%|▊         | 286/3598 [04:54<51:09,  1.08it/s]
  8%|▊         | 287/3598 [04:55<51:52,  1.06it/s]
  8%|▊         | 288/3598 [04:56<55:34,  1.01s/it]
  8%|▊         | 289/3598 [04:57<53:27,  1.03it/s]
  8%|▊         | 290/3598 [04:58<1:00:24,  1.10s/it]
                                                    

  8%|▊         | 290/3598 [04:58<1:00:24,  1.10s/it]
  8%|▊         | 291/3598 [04:59<59:25,  1.08s/it]  
  8%|▊         | 292/3598 [05:00<58:03,  1.05s/it]
  8%|▊         | 293/3598 [05:01<57:31,  1.04s/it]
  8%|▊         | 294/3598 [05:02<57:37,  1.05s/it]
  8%|▊         | 295/3598 [05:04<1:03:27,  1.15s/it]
  8%|▊         | 296/3598 [05:05<1:00:50,  1.11s/it]
  8%|▊         | 297/3598 [05:06<1:03:40,  1.16s/it]
  8%|▊         | 298/3598 [05:07<1:00:00,  1.09s/it]
  8%|▊         | 299/3598 [05:08<56:11,  1.02s/it]  
  8%|▊         | 300/3598 [05:09<54:57,  1.00it/s]
                                                  

  8%|▊         | 300/3598 [05:09<54:57,  1.00it/s]
  8%|▊         | 301/3598 [05:10<53:59,  1.02it/s]
  8%|▊         | 302/3598 [05:11<53:41,  1.02it/s]
  8%|▊         | 303/3598 [05:12<54:24,  1.01it/s]
  8%|▊         | 304/3598 [05:13<56:31,  1.03s/it]
  8%|▊         | 305/3598 [05:14<55:57,  1.02s/it]
  9%|▊         | 306/3598 [05:15<59:27,  1.08s/it]
  9%|▊         | 307/3598 [05:16<56:17,  1.03s/it]
  9%|▊         | 308/3598 [05:17<53:48,  1.02it/s]
  9%|▊         | 309/3598 [05:18<52:43,  1.04it/s]
  9%|▊         | 310/3598 [05:19<51:30,  1.06it/s]
                                                  

  9%|▊         | 310/3598 [05:19<51:30,  1.06it/s]
  9%|▊         | 311/3598 [05:20<52:03,  1.05it/s]
  9%|▊         | 312/3598 [05:21<50:42,  1.08it/s]
  9%|▊         | 313/3598 [05:22<51:20,  1.07it/s]
  9%|▊         | 314/3598 [05:22<49:53,  1.10it/s]
  9%|▉         | 315/3598 [05:24<54:10,  1.01it/s]
  9%|▉         | 316/3598 [05:24<51:49,  1.06it/s]
  9%|▉         | 317/3598 [05:26<55:37,  1.02s/it]
  9%|▉         | 318/3598 [05:27<53:30,  1.02it/s]
  9%|▉         | 319/3598 [05:27<51:30,  1.06it/s]
  9%|▉         | 320/3598 [05:28<54:23,  1.00it/s]
                                                  

  9%|▉         | 320/3598 [05:28<54:23,  1.00it/s]
  9%|▉         | 321/3598 [05:30<58:13,  1.07s/it]
  9%|▉         | 322/3598 [05:31<54:19,  1.01it/s]
  9%|▉         | 323/3598 [05:32<55:23,  1.01s/it]
  9%|▉         | 324/3598 [05:33<58:09,  1.07s/it]
  9%|▉         | 325/3598 [05:34<56:17,  1.03s/it]
  9%|▉         | 326/3598 [05:35<55:12,  1.01s/it]
  9%|▉         | 327/3598 [05:36<54:46,  1.00s/it]
  9%|▉         | 328/3598 [05:37<53:16,  1.02it/s]
  9%|▉         | 329/3598 [05:38<53:18,  1.02it/s]
  9%|▉         | 330/3598 [05:39<53:03,  1.03it/s]
                                                  

  9%|▉         | 330/3598 [05:39<53:03,  1.03it/s]
  9%|▉         | 331/3598 [05:39<51:33,  1.06it/s]
  9%|▉         | 332/3598 [05:41<57:05,  1.05s/it]
  9%|▉         | 333/3598 [05:42<1:02:40,  1.15s/it]
  9%|▉         | 334/3598 [05:43<57:49,  1.06s/it]  
  9%|▉         | 335/3598 [05:44<56:47,  1.04s/it]
  9%|▉         | 336/3598 [05:45<54:28,  1.00s/it]
  9%|▉         | 337/3598 [05:46<51:06,  1.06it/s]
  9%|▉         | 338/3598 [05:47<51:25,  1.06it/s]
  9%|▉         | 339/3598 [05:48<55:01,  1.01s/it]
  9%|▉         | 340/3598 [05:49<1:00:38,  1.12s/it]
                                                    

  9%|▉         | 340/3598 [05:49<1:00:38,  1.12s/it]
  9%|▉         | 341/3598 [05:50<1:00:38,  1.12s/it]
 10%|▉         | 342/3598 [05:51<58:14,  1.07s/it]  
 10%|▉         | 343/3598 [05:53<1:01:14,  1.13s/it]
 10%|▉         | 344/3598 [05:54<1:04:49,  1.20s/it]
 10%|▉         | 345/3598 [05:55<59:35,  1.10s/it]  
 10%|▉         | 346/3598 [05:56<57:39,  1.06s/it]
 10%|▉         | 347/3598 [05:57<1:00:31,  1.12s/it]
 10%|▉         | 348/3598 [05:58<56:54,  1.05s/it]  
 10%|▉         | 349/3598 [05:59<58:47,  1.09s/it]
 10%|▉         | 350/3598 [06:00<54:30,  1.01s/it]
                                                  

 10%|▉         | 350/3598 [06:00<54:30,  1.01s/it]
 10%|▉         | 351/3598 [06:01<52:11,  1.04it/s]
 10%|▉         | 352/3598 [06:02<50:37,  1.07it/s]
 10%|▉         | 353/3598 [06:03<54:15,  1.00s/it]
 10%|▉         | 354/3598 [06:04<52:23,  1.03it/s]
 10%|▉         | 355/3598 [06:05<52:00,  1.04it/s]
 10%|▉         | 356/3598 [06:05<50:35,  1.07it/s]
 10%|▉         | 357/3598 [06:06<50:10,  1.08it/s]
 10%|▉         | 358/3598 [06:07<49:53,  1.08it/s]
 10%|▉         | 359/3598 [06:08<49:16,  1.10it/s]
 10%|█         | 360/3598 [06:09<48:36,  1.11it/s]
                                                  

 10%|█         | 360/3598 [06:09<48:36,  1.11it/s]
 10%|█         | 361/3598 [06:10<51:53,  1.04it/s]
 10%|█         | 362/3598 [06:11<51:03,  1.06it/s]
 10%|█         | 363/3598 [06:12<50:05,  1.08it/s]
 10%|█         | 364/3598 [06:13<50:43,  1.06it/s]
 10%|█         | 365/3598 [06:14<50:47,  1.06it/s]
 10%|█         | 366/3598 [06:15<57:42,  1.07s/it]
 10%|█         | 367/3598 [06:16<55:57,  1.04s/it]
 10%|█         | 368/3598 [06:18<1:01:44,  1.15s/it]
 10%|█         | 369/3598 [06:18<57:31,  1.07s/it]  
 10%|█         | 370/3598 [06:19<56:26,  1.05s/it]
                                                  

 10%|█         | 370/3598 [06:19<56:26,  1.05s/it]
 10%|█         | 371/3598 [06:20<54:15,  1.01s/it]
 10%|█         | 372/3598 [06:21<54:05,  1.01s/it]
 10%|█         | 373/3598 [06:22<51:32,  1.04it/s]
 10%|█         | 374/3598 [06:23<51:23,  1.05it/s]
 10%|█         | 375/3598 [06:25<57:15,  1.07s/it]
 10%|█         | 376/3598 [06:25<54:31,  1.02s/it]
 10%|█         | 377/3598 [06:26<52:30,  1.02it/s]
 11%|█         | 378/3598 [06:28<58:45,  1.09s/it]
 11%|█         | 379/3598 [06:29<1:03:24,  1.18s/it]
 11%|█         | 380/3598 [06:30<1:01:45,  1.15s/it]
                                                    

 11%|█         | 380/3598 [06:30<1:01:45,  1.15s/it]
 11%|█         | 381/3598 [06:31<58:18,  1.09s/it]  
 11%|█         | 382/3598 [06:32<53:25,  1.00it/s]
 11%|█         | 383/3598 [06:33<58:58,  1.10s/it]
 11%|█         | 384/3598 [06:34<53:48,  1.00s/it]
 11%|█         | 385/3598 [06:35<51:39,  1.04it/s]
 11%|█         | 386/3598 [06:36<58:39,  1.10s/it]
 11%|█         | 387/3598 [06:37<54:33,  1.02s/it]
 11%|█         | 388/3598 [06:38<52:10,  1.03it/s]
 11%|█         | 389/3598 [06:39<53:21,  1.00it/s]
 11%|█         | 390/3598 [06:40<52:43,  1.01it/s]
                                                  

 11%|█         | 390/3598 [06:40<52:43,  1.01it/s]
 11%|█         | 391/3598 [06:41<53:41,  1.00s/it]
 11%|█         | 392/3598 [06:42<56:50,  1.06s/it]
 11%|█         | 393/3598 [06:43<59:08,  1.11s/it]
 11%|█         | 394/3598 [06:44<57:52,  1.08s/it]
 11%|█         | 395/3598 [06:46<1:00:52,  1.14s/it]
 11%|█         | 396/3598 [06:47<58:31,  1.10s/it]  
 11%|█         | 397/3598 [06:48<1:00:08,  1.13s/it]
 11%|█         | 398/3598 [06:49<56:30,  1.06s/it]  
 11%|█         | 399/3598 [06:50<54:14,  1.02s/it]
 11%|█         | 400/3598 [06:51<1:00:14,  1.13s/it]
                                                    

 11%|█         | 400/3598 [06:51<1:00:14,  1.13s/it]
 11%|█         | 401/3598 [06:52<57:48,  1.08s/it]  
 11%|█         | 402/3598 [06:53<57:57,  1.09s/it]
 11%|█         | 403/3598 [06:54<55:23,  1.04s/it]
 11%|█         | 404/3598 [06:55<52:49,  1.01it/s]
 11%|█▏        | 405/3598 [06:56<53:02,  1.00it/s]
 11%|█▏        | 406/3598 [06:57<49:35,  1.07it/s]
 11%|█▏        | 407/3598 [06:58<48:11,  1.10it/s]
 11%|█▏        | 408/3598 [06:59<50:06,  1.06it/s]
 11%|█▏        | 409/3598 [07:00<56:03,  1.05s/it]
 11%|█▏        | 410/3598 [07:01<51:38,  1.03it/s]
                                                  

 11%|█▏        | 410/3598 [07:01<51:38,  1.03it/s]
 11%|█▏        | 411/3598 [07:02<50:42,  1.05it/s]
 11%|█▏        | 412/3598 [07:03<55:45,  1.05s/it]
 11%|█▏        | 413/3598 [07:04<59:16,  1.12s/it]
 12%|█▏        | 414/3598 [07:06<1:02:25,  1.18s/it]
 12%|█▏        | 415/3598 [07:07<1:02:24,  1.18s/it]
 12%|█▏        | 416/3598 [07:08<59:14,  1.12s/it]  
 12%|█▏        | 417/3598 [07:09<59:58,  1.13s/it]
 12%|█▏        | 418/3598 [07:10<1:03:36,  1.20s/it]
 12%|█▏        | 419/3598 [07:12<1:05:51,  1.24s/it]
 12%|█▏        | 420/3598 [07:13<1:05:58,  1.25s/it]
                                                    

 12%|█▏        | 420/3598 [07:13<1:05:58,  1.25s/it]
 12%|█▏        | 421/3598 [07:14<59:46,  1.13s/it]  
 12%|█▏        | 422/3598 [07:15<57:18,  1.08s/it]
 12%|█▏        | 423/3598 [07:16<58:37,  1.11s/it]
 12%|█▏        | 424/3598 [07:17<54:13,  1.03s/it]
 12%|█▏        | 425/3598 [07:18<53:03,  1.00s/it]
 12%|█▏        | 426/3598 [07:18<49:58,  1.06it/s]
 12%|█▏        | 427/3598 [07:20<55:08,  1.04s/it]
 12%|█▏        | 428/3598 [07:21<1:00:33,  1.15s/it]
 12%|█▏        | 429/3598 [07:22<59:44,  1.13s/it]  
 12%|█▏        | 430/3598 [07:23<56:36,  1.07s/it]
                                                  

 12%|█▏        | 430/3598 [07:23<56:36,  1.07s/it]
 12%|█▏        | 431/3598 [07:24<1:01:04,  1.16s/it]
 12%|█▏        | 432/3598 [07:26<1:01:11,  1.16s/it]
 12%|█▏        | 433/3598 [07:27<56:49,  1.08s/it]  
 12%|█▏        | 434/3598 [07:28<1:01:33,  1.17s/it]
 12%|█▏        | 435/3598 [07:29<1:04:55,  1.23s/it]
 12%|█▏        | 436/3598 [07:31<1:07:10,  1.27s/it]
 12%|█▏        | 437/3598 [07:32<1:00:29,  1.15s/it]
 12%|█▏        | 438/3598 [07:33<58:51,  1.12s/it]  
 12%|█▏        | 439/3598 [07:34<1:00:39,  1.15s/it]
 12%|█▏        | 440/3598 [07:35<58:42,  1.12s/it]  
                                                  

 12%|█▏        | 440/3598 [07:35<58:42,  1.12s/it]
 12%|█▏        | 441/3598 [07:36<1:02:38,  1.19s/it]
 12%|█▏        | 442/3598 [07:37<58:47,  1.12s/it]  
 12%|█▏        | 443/3598 [07:38<57:17,  1.09s/it]
 12%|█▏        | 444/3598 [07:39<54:03,  1.03s/it]
 12%|█▏        | 445/3598 [07:40<52:43,  1.00s/it]
 12%|█▏        | 446/3598 [07:41<55:56,  1.06s/it]
 12%|█▏        | 447/3598 [07:42<59:34,  1.13s/it]
 12%|█▏        | 448/3598 [07:43<57:22,  1.09s/it]
 12%|█▏        | 449/3598 [07:44<55:55,  1.07s/it]
 13%|█▎        | 450/3598 [07:45<52:25,  1.00it/s]
                                                  

 13%|█▎        | 450/3598 [07:45<52:25,  1.00it/s]
 13%|█▎        | 451/3598 [07:46<50:35,  1.04it/s]
 13%|█▎        | 452/3598 [07:48<56:30,  1.08s/it]
 13%|█▎        | 453/3598 [07:49<54:43,  1.04s/it]
 13%|█▎        | 454/3598 [07:50<55:54,  1.07s/it]
 13%|█▎        | 455/3598 [07:51<53:40,  1.02s/it]
 13%|█▎        | 456/3598 [07:51<51:56,  1.01it/s]
 13%|█▎        | 457/3598 [07:52<51:02,  1.03it/s]
 13%|█▎        | 458/3598 [07:53<49:32,  1.06it/s]
 13%|█▎        | 459/3598 [07:54<51:15,  1.02it/s]
 13%|█▎        | 460/3598 [07:55<51:32,  1.01it/s]
                                                  

 13%|█▎        | 460/3598 [07:55<51:32,  1.01it/s]
 13%|█▎        | 461/3598 [07:57<56:36,  1.08s/it]
 13%|█▎        | 462/3598 [07:58<54:30,  1.04s/it]
 13%|█▎        | 463/3598 [07:59<57:11,  1.09s/it]
 13%|█▎        | 464/3598 [08:00<53:27,  1.02s/it]
 13%|█▎        | 465/3598 [08:01<52:18,  1.00s/it]
 13%|█▎        | 466/3598 [08:02<52:11,  1.00it/s]
 13%|█▎        | 467/3598 [08:03<51:47,  1.01it/s]
 13%|█▎        | 468/3598 [08:04<58:00,  1.11s/it]
 13%|█▎        | 469/3598 [08:05<1:01:18,  1.18s/it]
 13%|█▎        | 470/3598 [08:06<57:39,  1.11s/it]  
                                                  

 13%|█▎        | 470/3598 [08:06<57:39,  1.11s/it]
 13%|█▎        | 471/3598 [08:07<54:50,  1.05s/it]
 13%|█▎        | 472/3598 [08:08<52:31,  1.01s/it]
 13%|█▎        | 473/3598 [08:09<51:58,  1.00it/s]
 13%|█▎        | 474/3598 [08:10<51:25,  1.01it/s]
 13%|█▎        | 475/3598 [08:11<51:00,  1.02it/s]
 13%|█▎        | 476/3598 [08:12<50:17,  1.03it/s]
 13%|█▎        | 477/3598 [08:13<50:51,  1.02it/s]
 13%|█▎        | 478/3598 [08:14<51:38,  1.01it/s]
 13%|█▎        | 479/3598 [08:15<53:21,  1.03s/it]
 13%|█▎        | 480/3598 [08:16<52:57,  1.02s/it]
                                                  

 13%|█▎        | 480/3598 [08:16<52:57,  1.02s/it]
 13%|█▎        | 481/3598 [08:17<57:02,  1.10s/it]
 13%|█▎        | 482/3598 [08:18<56:25,  1.09s/it]
 13%|█▎        | 483/3598 [08:19<54:43,  1.05s/it]
 13%|█▎        | 484/3598 [08:20<52:06,  1.00s/it]
 13%|█▎        | 485/3598 [08:21<50:47,  1.02it/s]
 14%|█▎        | 486/3598 [08:22<49:08,  1.06it/s]
 14%|█▎        | 487/3598 [08:23<48:48,  1.06it/s]
 14%|█▎        | 488/3598 [08:24<47:29,  1.09it/s]
 14%|█▎        | 489/3598 [08:25<48:31,  1.07it/s]
 14%|█▎        | 490/3598 [08:26<51:10,  1.01it/s]
                                                  

 14%|█▎        | 490/3598 [08:26<51:10,  1.01it/s]
 14%|█▎        | 491/3598 [08:27<54:44,  1.06s/it]
 14%|█▎        | 492/3598 [08:29<59:54,  1.16s/it]
 14%|█▎        | 493/3598 [08:30<59:08,  1.14s/it]
 14%|█▎        | 494/3598 [08:31<1:02:00,  1.20s/it]
 14%|█▍        | 495/3598 [08:32<1:02:10,  1.20s/it]
 14%|█▍        | 496/3598 [08:33<1:03:14,  1.22s/it]
 14%|█▍        | 497/3598 [08:34<57:28,  1.11s/it]  
 14%|█▍        | 498/3598 [08:35<53:37,  1.04s/it]
 14%|█▍        | 499/3598 [08:36<49:58,  1.03it/s]
 14%|█▍        | 500/3598 [08:37<50:02,  1.03it/s]
                                                  

 14%|█▍        | 500/3598 [08:37<50:02,  1.03it/s]
 14%|█▍        | 501/3598 [08:38<51:28,  1.00it/s]
 14%|█▍        | 502/3598 [08:39<49:57,  1.03it/s]
 14%|█▍        | 503/3598 [08:40<48:53,  1.05it/s]
 14%|█▍        | 504/3598 [08:41<47:29,  1.09it/s]
 14%|█▍        | 505/3598 [08:42<47:02,  1.10it/s]
 14%|█▍        | 506/3598 [08:43<52:54,  1.03s/it]
 14%|█▍        | 507/3598 [08:44<51:27,  1.00it/s]
 14%|█▍        | 508/3598 [08:45<51:02,  1.01it/s]
 14%|█▍        | 509/3598 [08:46<53:09,  1.03s/it]
 14%|█▍        | 510/3598 [08:47<57:26,  1.12s/it]
                                                  

 14%|█▍        | 510/3598 [08:47<57:26,  1.12s/it]
 14%|█▍        | 511/3598 [08:48<55:09,  1.07s/it]
 14%|█▍        | 512/3598 [08:50<59:45,  1.16s/it]
 14%|█▍        | 513/3598 [08:50<55:36,  1.08s/it]
 14%|█▍        | 514/3598 [08:51<52:26,  1.02s/it]
 14%|█▍        | 515/3598 [08:52<53:12,  1.04s/it]
 14%|█▍        | 516/3598 [08:53<51:16,  1.00it/s]
 14%|█▍        | 517/3598 [08:54<49:32,  1.04it/s]
 14%|█▍        | 518/3598 [08:56<55:14,  1.08s/it]
 14%|█▍        | 519/3598 [08:57<53:40,  1.05s/it]
 14%|█▍        | 520/3598 [08:57<51:16,  1.00it/s]
                                                  

 14%|█▍        | 520/3598 [08:57<51:16,  1.00it/s]
 14%|█▍        | 521/3598 [08:58<49:00,  1.05it/s]
 15%|█▍        | 522/3598 [08:59<47:55,  1.07it/s]
 15%|█▍        | 523/3598 [09:00<48:06,  1.07it/s]
 15%|█▍        | 524/3598 [09:01<50:49,  1.01it/s]
 15%|█▍        | 525/3598 [09:02<48:45,  1.05it/s]
 15%|█▍        | 526/3598 [09:03<47:59,  1.07it/s]
 15%|█▍        | 527/3598 [09:04<47:39,  1.07it/s]
 15%|█▍        | 528/3598 [09:05<47:40,  1.07it/s]
 15%|█▍        | 529/3598 [09:06<52:08,  1.02s/it]
 15%|█▍        | 530/3598 [09:07<49:51,  1.03it/s]
                                                  

 15%|█▍        | 530/3598 [09:07<49:51,  1.03it/s]
 15%|█▍        | 531/3598 [09:08<51:05,  1.00it/s]
 15%|█▍        | 532/3598 [09:09<49:25,  1.03it/s]
 15%|█▍        | 533/3598 [09:10<47:29,  1.08it/s]
 15%|█▍        | 534/3598 [09:11<47:15,  1.08it/s]
 15%|█▍        | 535/3598 [09:12<52:54,  1.04s/it]
 15%|█▍        | 536/3598 [09:13<54:09,  1.06s/it]
 15%|█▍        | 537/3598 [09:14<52:13,  1.02s/it]
 15%|█▍        | 538/3598 [09:15<50:59,  1.00it/s]
 15%|█▍        | 539/3598 [09:16<51:50,  1.02s/it]
 15%|█▌        | 540/3598 [09:17<50:30,  1.01it/s]
                                                  

 15%|█▌        | 540/3598 [09:17<50:30,  1.01it/s]
 15%|█▌        | 541/3598 [09:18<49:38,  1.03it/s]
 15%|█▌        | 542/3598 [09:19<48:06,  1.06it/s]
 15%|█▌        | 543/3598 [09:20<48:52,  1.04it/s]
 15%|█▌        | 544/3598 [09:21<54:27,  1.07s/it]
 15%|█▌        | 545/3598 [09:22<53:03,  1.04s/it]
 15%|█▌        | 546/3598 [09:23<50:58,  1.00s/it]
 15%|█▌        | 547/3598 [09:24<57:26,  1.13s/it]
 15%|█▌        | 548/3598 [09:25<54:56,  1.08s/it]
 15%|█▌        | 549/3598 [09:26<52:02,  1.02s/it]
 15%|█▌        | 550/3598 [09:27<53:13,  1.05s/it]
                                                  

 15%|█▌        | 550/3598 [09:27<53:13,  1.05s/it]
 15%|█▌        | 551/3598 [09:28<52:16,  1.03s/it]
 15%|█▌        | 552/3598 [09:30<57:49,  1.14s/it]
 15%|█▌        | 553/3598 [09:31<54:49,  1.08s/it]
 15%|█▌        | 554/3598 [09:32<52:08,  1.03s/it]
 15%|█▌        | 555/3598 [09:33<52:30,  1.04s/it]
 15%|█▌        | 556/3598 [09:33<50:00,  1.01it/s]
 15%|█▌        | 557/3598 [09:34<49:30,  1.02it/s]
 16%|█▌        | 558/3598 [09:35<47:50,  1.06it/s]
 16%|█▌        | 559/3598 [09:36<48:19,  1.05it/s]
 16%|█▌        | 560/3598 [09:37<47:59,  1.06it/s]
                                                  

 16%|█▌        | 560/3598 [09:37<47:59,  1.06it/s]
 16%|█▌        | 561/3598 [09:38<47:19,  1.07it/s]
 16%|█▌        | 562/3598 [09:39<46:58,  1.08it/s]
 16%|█▌        | 563/3598 [09:40<47:01,  1.08it/s]
 16%|█▌        | 564/3598 [09:41<46:10,  1.10it/s]
 16%|█▌        | 565/3598 [09:42<48:44,  1.04it/s]
 16%|█▌        | 566/3598 [09:43<55:13,  1.09s/it]
 16%|█▌        | 567/3598 [09:44<51:43,  1.02s/it]
 16%|█▌        | 568/3598 [09:45<51:38,  1.02s/it]
 16%|█▌        | 569/3598 [09:46<53:21,  1.06s/it]
 16%|█▌        | 570/3598 [09:47<52:17,  1.04s/it]
                                                  

 16%|█▌        | 570/3598 [09:47<52:17,  1.04s/it]
 16%|█▌        | 571/3598 [09:48<53:46,  1.07s/it]
 16%|█▌        | 572/3598 [09:50<58:39,  1.16s/it]
 16%|█▌        | 573/3598 [09:51<54:27,  1.08s/it]
 16%|█▌        | 574/3598 [09:52<58:53,  1.17s/it]
 16%|█▌        | 575/3598 [09:53<59:15,  1.18s/it]
 16%|█▌        | 576/3598 [09:54<54:46,  1.09s/it]
 16%|█▌        | 577/3598 [09:56<58:49,  1.17s/it]
 16%|█▌        | 578/3598 [09:56<54:16,  1.08s/it]
 16%|█▌        | 579/3598 [09:57<51:50,  1.03s/it]
 16%|█▌        | 580/3598 [09:59<57:09,  1.14s/it]
                                                  

 16%|█▌        | 580/3598 [09:59<57:09,  1.14s/it]
 16%|█▌        | 581/3598 [10:00<54:01,  1.07s/it]
 16%|█▌        | 582/3598 [10:01<51:02,  1.02s/it]
 16%|█▌        | 583/3598 [10:01<48:39,  1.03it/s]
 16%|█▌        | 584/3598 [10:02<47:26,  1.06it/s]
 16%|█▋        | 585/3598 [10:03<49:18,  1.02it/s]
 16%|█▋        | 586/3598 [10:04<47:53,  1.05it/s]
 16%|█▋        | 587/3598 [10:05<47:11,  1.06it/s]
 16%|█▋        | 588/3598 [10:06<46:29,  1.08it/s]
 16%|█▋        | 589/3598 [10:07<47:08,  1.06it/s]
 16%|█▋        | 590/3598 [10:08<48:03,  1.04it/s]
                                                  

 16%|█▋        | 590/3598 [10:08<48:03,  1.04it/s]
 16%|█▋        | 591/3598 [10:09<48:28,  1.03it/s]
 16%|█▋        | 592/3598 [10:10<54:05,  1.08s/it]
 16%|█▋        | 593/3598 [10:11<53:37,  1.07s/it]
 17%|█▋        | 594/3598 [10:12<49:54,  1.00it/s]
 17%|█▋        | 595/3598 [10:13<48:49,  1.03it/s]
 17%|█▋        | 596/3598 [10:14<45:55,  1.09it/s]
 17%|█▋        | 597/3598 [10:15<45:31,  1.10it/s]
 17%|█▋        | 598/3598 [10:16<45:38,  1.10it/s]
 17%|█▋        | 599/3598 [10:17<50:55,  1.02s/it]
 17%|█▋        | 600/3598 [10:18<49:17,  1.01it/s]
                                                  

 17%|█▋        | 600/3598 [10:18<49:17,  1.01it/s]
 17%|█▋        | 601/3598 [10:19<47:38,  1.05it/s]
 17%|█▋        | 602/3598 [10:20<46:01,  1.08it/s]
 17%|█▋        | 603/3598 [10:21<52:25,  1.05s/it]
 17%|█▋        | 604/3598 [10:22<57:37,  1.15s/it]
 17%|█▋        | 605/3598 [10:23<53:48,  1.08s/it]
 17%|█▋        | 606/3598 [10:25<57:25,  1.15s/it]
 17%|█▋        | 607/3598 [10:26<59:39,  1.20s/it]
 17%|█▋        | 608/3598 [10:27<54:46,  1.10s/it]
 17%|█▋        | 609/3598 [10:28<52:30,  1.05s/it]
 17%|█▋        | 610/3598 [10:29<50:35,  1.02s/it]
                                                  

 17%|█▋        | 610/3598 [10:29<50:35,  1.02s/it]
 17%|█▋        | 611/3598 [10:30<49:37,  1.00it/s]
 17%|█▋        | 612/3598 [10:31<48:16,  1.03it/s]
 17%|█▋        | 613/3598 [10:31<48:06,  1.03it/s]
 17%|█▋        | 614/3598 [10:32<48:28,  1.03it/s]
 17%|█▋        | 615/3598 [10:34<54:21,  1.09s/it]
 17%|█▋        | 616/3598 [10:35<58:01,  1.17s/it]
 17%|█▋        | 617/3598 [10:36<53:56,  1.09s/it]
 17%|█▋        | 618/3598 [10:37<53:21,  1.07s/it]
 17%|█▋        | 619/3598 [10:38<50:36,  1.02s/it]
 17%|█▋        | 620/3598 [10:39<50:39,  1.02s/it]
                                                  

 17%|█▋        | 620/3598 [10:39<50:39,  1.02s/it]
 17%|█▋        | 621/3598 [10:40<48:45,  1.02it/s]
 17%|█▋        | 622/3598 [10:41<47:12,  1.05it/s]
 17%|█▋        | 623/3598 [10:42<47:52,  1.04it/s]
 17%|█▋        | 624/3598 [10:43<52:51,  1.07s/it]
 17%|█▋        | 625/3598 [10:44<49:53,  1.01s/it]
 17%|█▋        | 626/3598 [10:45<49:06,  1.01it/s]
 17%|█▋        | 627/3598 [10:46<53:20,  1.08s/it]
 17%|█▋        | 628/3598 [10:47<49:54,  1.01s/it]
 17%|█▋        | 629/3598 [10:48<49:10,  1.01it/s]
 18%|█▊        | 630/3598 [10:49<52:19,  1.06s/it]
                                                  

 18%|█▊        | 630/3598 [10:49<52:19,  1.06s/it]
 18%|█▊        | 631/3598 [10:50<55:14,  1.12s/it]
 18%|█▊        | 632/3598 [10:52<57:11,  1.16s/it]
 18%|█▊        | 633/3598 [10:53<54:23,  1.10s/it]
 18%|█▊        | 634/3598 [10:54<51:10,  1.04s/it]
 18%|█▊        | 635/3598 [10:55<50:30,  1.02s/it]
 18%|█▊        | 636/3598 [10:55<47:56,  1.03it/s]
 18%|█▊        | 637/3598 [10:56<47:25,  1.04it/s]
 18%|█▊        | 638/3598 [10:57<46:46,  1.05it/s]
 18%|█▊        | 639/3598 [10:58<47:09,  1.05it/s]
 18%|█▊        | 640/3598 [10:59<45:53,  1.07it/s]
                                                  

 18%|█▊        | 640/3598 [10:59<45:53,  1.07it/s]
 18%|█▊        | 641/3598 [11:00<48:20,  1.02it/s]
 18%|█▊        | 642/3598 [11:01<47:22,  1.04it/s]
 18%|█▊        | 643/3598 [11:02<47:49,  1.03it/s]
 18%|█▊        | 644/3598 [11:03<47:55,  1.03it/s]
 18%|█▊        | 645/3598 [11:04<48:48,  1.01it/s]
 18%|█▊        | 646/3598 [11:05<48:10,  1.02it/s]
 18%|█▊        | 647/3598 [11:06<47:49,  1.03it/s]
 18%|█▊        | 648/3598 [11:07<47:29,  1.04it/s]
 18%|█▊        | 649/3598 [11:08<53:43,  1.09s/it]
 18%|█▊        | 650/3598 [11:09<51:35,  1.05s/it]
                                                  

 18%|█▊        | 650/3598 [11:09<51:35,  1.05s/it]
 18%|█▊        | 651/3598 [11:10<49:21,  1.00s/it]
 18%|█▊        | 652/3598 [11:11<47:48,  1.03it/s]
 18%|█▊        | 653/3598 [11:12<47:40,  1.03it/s]
 18%|█▊        | 654/3598 [11:13<45:58,  1.07it/s]
 18%|█▊        | 655/3598 [11:14<44:54,  1.09it/s]
 18%|█▊        | 656/3598 [11:15<44:48,  1.09it/s]
 18%|█▊        | 657/3598 [11:16<44:20,  1.11it/s]
 18%|█▊        | 658/3598 [11:17<45:12,  1.08it/s]
 18%|█▊        | 659/3598 [11:18<46:00,  1.06it/s]
 18%|█▊        | 660/3598 [11:19<46:21,  1.06it/s]
                                                  

 18%|█▊        | 660/3598 [11:19<46:21,  1.06it/s]
 18%|█▊        | 661/3598 [11:19<45:27,  1.08it/s]
 18%|█▊        | 662/3598 [11:20<46:59,  1.04it/s]
 18%|█▊        | 663/3598 [11:22<50:52,  1.04s/it]
 18%|█▊        | 664/3598 [11:23<48:40,  1.00it/s]
 18%|█▊        | 665/3598 [11:24<47:47,  1.02it/s]
 19%|█▊        | 666/3598 [11:25<48:19,  1.01it/s]
 19%|█▊        | 667/3598 [11:26<49:25,  1.01s/it]
 19%|█▊        | 668/3598 [11:26<47:56,  1.02it/s]
 19%|█▊        | 669/3598 [11:27<47:05,  1.04it/s]
 19%|█▊        | 670/3598 [11:28<47:30,  1.03it/s]
                                                  

 19%|█▊        | 670/3598 [11:28<47:30,  1.03it/s]
 19%|█▊        | 671/3598 [11:30<49:50,  1.02s/it]
 19%|█▊        | 672/3598 [11:31<49:48,  1.02s/it]
 19%|█▊        | 673/3598 [11:31<48:24,  1.01it/s]
 19%|█▊        | 674/3598 [11:32<46:49,  1.04it/s]
 19%|█▉        | 675/3598 [11:33<45:10,  1.08it/s]
 19%|█▉        | 676/3598 [11:34<48:08,  1.01it/s]
 19%|█▉        | 677/3598 [11:35<47:40,  1.02it/s]
 19%|█▉        | 678/3598 [11:36<46:02,  1.06it/s]
 19%|█▉        | 679/3598 [11:37<44:32,  1.09it/s]
 19%|█▉        | 680/3598 [11:38<45:54,  1.06it/s]
                                                  

 19%|█▉        | 680/3598 [11:38<45:54,  1.06it/s]
 19%|█▉        | 681/3598 [11:39<44:19,  1.10it/s]
 19%|█▉        | 682/3598 [11:40<44:06,  1.10it/s]
 19%|█▉        | 683/3598 [11:41<43:10,  1.13it/s]
 19%|█▉        | 684/3598 [11:42<43:12,  1.12it/s]
 19%|█▉        | 685/3598 [11:43<49:16,  1.01s/it]
 19%|█▉        | 686/3598 [11:44<50:12,  1.03s/it]
 19%|█▉        | 687/3598 [11:45<48:34,  1.00s/it]
 19%|█▉        | 688/3598 [11:46<47:15,  1.03it/s]
 19%|█▉        | 689/3598 [11:47<47:52,  1.01it/s]
 19%|█▉        | 690/3598 [11:48<48:28,  1.00s/it]
                                                  

 19%|█▉        | 690/3598 [11:48<48:28,  1.00s/it]
 19%|█▉        | 691/3598 [11:49<48:35,  1.00s/it]
 19%|█▉        | 692/3598 [11:50<50:28,  1.04s/it]
 19%|█▉        | 693/3598 [11:51<47:48,  1.01it/s]
 19%|█▉        | 694/3598 [11:52<48:19,  1.00it/s]
 19%|█▉        | 695/3598 [11:53<46:51,  1.03it/s]
 19%|█▉        | 696/3598 [11:54<52:36,  1.09s/it]
 19%|█▉        | 697/3598 [11:55<49:48,  1.03s/it]
 19%|█▉        | 698/3598 [11:56<53:46,  1.11s/it]
 19%|█▉        | 699/3598 [11:57<51:59,  1.08s/it]
 19%|█▉        | 700/3598 [11:58<49:42,  1.03s/it]
                                                  

 19%|█▉        | 700/3598 [11:58<49:42,  1.03s/it]
 19%|█▉        | 701/3598 [11:59<48:53,  1.01s/it]
 20%|█▉        | 702/3598 [12:00<47:24,  1.02it/s]
 20%|█▉        | 703/3598 [12:01<47:22,  1.02it/s]
 20%|█▉        | 704/3598 [12:02<47:04,  1.02it/s]
 20%|█▉        | 705/3598 [12:03<44:25,  1.09it/s]
 20%|█▉        | 706/3598 [12:04<44:05,  1.09it/s]
 20%|█▉        | 707/3598 [12:05<44:15,  1.09it/s]
 20%|█▉        | 708/3598 [12:06<45:30,  1.06it/s]
 20%|█▉        | 709/3598 [12:07<47:25,  1.02it/s]
 20%|█▉        | 710/3598 [12:08<53:03,  1.10s/it]
                                                  

 20%|█▉        | 710/3598 [12:08<53:03,  1.10s/it]
 20%|█▉        | 711/3598 [12:09<52:21,  1.09s/it]
 20%|█▉        | 712/3598 [12:10<49:32,  1.03s/it]
 20%|█▉        | 713/3598 [12:11<48:14,  1.00s/it]
 20%|█▉        | 714/3598 [12:12<47:18,  1.02it/s]
 20%|█▉        | 715/3598 [12:13<48:11,  1.00s/it]
 20%|█▉        | 716/3598 [12:14<45:53,  1.05it/s]
 20%|█▉        | 717/3598 [12:15<45:39,  1.05it/s]
 20%|█▉        | 718/3598 [12:16<44:57,  1.07it/s]
 20%|█▉        | 719/3598 [12:17<49:58,  1.04s/it]
 20%|██        | 720/3598 [12:18<48:42,  1.02s/it]
                                                  

 20%|██        | 720/3598 [12:18<48:42,  1.02s/it]
 20%|██        | 721/3598 [12:19<46:45,  1.03it/s]
 20%|██        | 722/3598 [12:20<48:10,  1.01s/it]
 20%|██        | 723/3598 [12:21<45:39,  1.05it/s]
 20%|██        | 724/3598 [12:21<43:08,  1.11it/s]
 20%|██        | 725/3598 [12:23<44:59,  1.06it/s]
 20%|██        | 726/3598 [12:23<44:46,  1.07it/s]
 20%|██        | 727/3598 [12:24<43:52,  1.09it/s]
 20%|██        | 728/3598 [12:26<49:40,  1.04s/it]
 20%|██        | 729/3598 [12:27<53:23,  1.12s/it]
 20%|██        | 730/3598 [12:28<49:15,  1.03s/it]
                                                  

 20%|██        | 730/3598 [12:28<49:15,  1.03s/it]
 20%|██        | 731/3598 [12:29<54:04,  1.13s/it]
 20%|██        | 732/3598 [12:30<51:50,  1.09s/it]
 20%|██        | 733/3598 [12:31<55:04,  1.15s/it]
 20%|██        | 734/3598 [12:32<50:56,  1.07s/it]
 20%|██        | 735/3598 [12:33<47:54,  1.00s/it]
 20%|██        | 736/3598 [12:34<45:48,  1.04it/s]
 20%|██        | 737/3598 [12:35<45:50,  1.04it/s]
 21%|██        | 738/3598 [12:36<44:55,  1.06it/s]
 21%|██        | 739/3598 [12:37<51:06,  1.07s/it]
 21%|██        | 740/3598 [12:38<47:59,  1.01s/it]
                                                  

 21%|██        | 740/3598 [12:38<47:59,  1.01s/it]
 21%|██        | 741/3598 [12:39<45:40,  1.04it/s]
 21%|██        | 742/3598 [12:40<46:34,  1.02it/s]
 21%|██        | 743/3598 [12:41<44:36,  1.07it/s]
 21%|██        | 744/3598 [12:42<43:16,  1.10it/s]
 21%|██        | 745/3598 [12:43<42:46,  1.11it/s]
 21%|██        | 746/3598 [12:43<42:59,  1.11it/s]
 21%|██        | 747/3598 [12:45<50:40,  1.07s/it]
 21%|██        | 748/3598 [12:46<54:32,  1.15s/it]
 21%|██        | 749/3598 [12:47<50:22,  1.06s/it]
 21%|██        | 750/3598 [12:48<53:36,  1.13s/it]
                                                  

 21%|██        | 750/3598 [12:48<53:36,  1.13s/it]
 21%|██        | 751/3598 [12:50<55:20,  1.17s/it]
 21%|██        | 752/3598 [12:51<51:54,  1.09s/it]
 21%|██        | 753/3598 [12:52<53:06,  1.12s/it]
 21%|██        | 754/3598 [12:53<49:27,  1.04s/it]
 21%|██        | 755/3598 [12:54<51:41,  1.09s/it]
 21%|██        | 756/3598 [12:55<52:03,  1.10s/it]
 21%|██        | 757/3598 [12:56<49:00,  1.04s/it]
 21%|██        | 758/3598 [12:57<48:24,  1.02s/it]
 21%|██        | 759/3598 [12:58<47:57,  1.01s/it]
 21%|██        | 760/3598 [12:59<49:06,  1.04s/it]
                                                  

 21%|██        | 760/3598 [12:59<49:06,  1.04s/it]
 21%|██        | 761/3598 [13:00<47:39,  1.01s/it]
 21%|██        | 762/3598 [13:01<48:43,  1.03s/it]
 21%|██        | 763/3598 [13:02<47:44,  1.01s/it]
 21%|██        | 764/3598 [13:03<47:19,  1.00s/it]
 21%|██▏       | 765/3598 [13:04<50:11,  1.06s/it]
 21%|██▏       | 766/3598 [13:05<49:02,  1.04s/it]
 21%|██▏       | 767/3598 [13:06<50:44,  1.08s/it]
 21%|██▏       | 768/3598 [13:07<48:01,  1.02s/it]
 21%|██▏       | 769/3598 [13:08<45:37,  1.03it/s]
 21%|██▏       | 770/3598 [13:09<45:28,  1.04it/s]
                                                  

 21%|██▏       | 770/3598 [13:09<45:28,  1.04it/s]
 21%|██▏       | 771/3598 [13:10<49:58,  1.06s/it]
 21%|██▏       | 772/3598 [13:11<46:02,  1.02it/s]
 21%|██▏       | 773/3598 [13:12<52:08,  1.11s/it]
 22%|██▏       | 774/3598 [13:14<54:06,  1.15s/it]
 22%|██▏       | 775/3598 [13:15<55:56,  1.19s/it]
 22%|██▏       | 776/3598 [13:16<50:28,  1.07s/it]
 22%|██▏       | 777/3598 [13:17<49:13,  1.05s/it]
 22%|██▏       | 778/3598 [13:18<48:10,  1.02s/it]
 22%|██▏       | 779/3598 [13:19<49:30,  1.05s/it]
 22%|██▏       | 780/3598 [13:20<52:37,  1.12s/it]
                                                  

 22%|██▏       | 780/3598 [13:20<52:37,  1.12s/it]
 22%|██▏       | 781/3598 [13:21<52:23,  1.12s/it]
 22%|██▏       | 782/3598 [13:22<48:42,  1.04s/it]
 22%|██▏       | 783/3598 [13:23<53:30,  1.14s/it]
 22%|██▏       | 784/3598 [13:24<51:31,  1.10s/it]
 22%|██▏       | 785/3598 [13:25<47:17,  1.01s/it]
 22%|██▏       | 786/3598 [13:26<45:33,  1.03it/s]
 22%|██▏       | 787/3598 [13:27<50:10,  1.07s/it]
 22%|██▏       | 788/3598 [13:28<47:59,  1.02s/it]
 22%|██▏       | 789/3598 [13:29<45:58,  1.02it/s]
 22%|██▏       | 790/3598 [13:30<46:29,  1.01it/s]
                                                  
{'loss': 2.1046, 'grad_norm': 0.4140295088291168, 'learning_rate': 1.1111111111111112e-05, 'epoch': 0.0}
{'loss': 1.8483, 'grad_norm': 0.46193182468414307, 'learning_rate': 2.2222222222222223e-05, 'epoch': 0.01}
{'loss': 1.9831, 'grad_norm': 0.30134496092796326, 'learning_rate': 3.3333333333333335e-05, 'epoch': 0.01}
{'loss': 1.9877, 'grad_norm': 0.28117668628692627, 'learning_rate': 4.4444444444444447e-05, 'epoch': 0.01}
{'loss': 1.9154, 'grad_norm': 0.31306493282318115, 'learning_rate': 5.555555555555556e-05, 'epoch': 0.01}
{'loss': 1.9655, 'grad_norm': 0.370194673538208, 'learning_rate': 6.666666666666667e-05, 'epoch': 0.02}
{'loss': 1.9722, 'grad_norm': 0.45251625776290894, 'learning_rate': 7.777777777777778e-05, 'epoch': 0.02}
{'loss': 1.7918, 'grad_norm': 0.4766435921192169, 'learning_rate': 8.888888888888889e-05, 'epoch': 0.02}
{'loss': 1.881, 'grad_norm': 0.5220038294792175, 'learning_rate': 0.0001, 'epoch': 0.03}
{'loss': 1.8093, 'grad_norm': 0.37182119488716125, 'learning_rate': 0.00011111111111111112, 'epoch': 0.03}
{'loss': 1.8168, 'grad_norm': 0.528815507888794, 'learning_rate': 0.00012222222222222224, 'epoch': 0.03}
{'loss': 1.7512, 'grad_norm': 0.5603467226028442, 'learning_rate': 0.00013333333333333334, 'epoch': 0.03}
{'loss': 1.8719, 'grad_norm': 0.41087475419044495, 'learning_rate': 0.00014444444444444444, 'epoch': 0.04}
{'loss': 1.8271, 'grad_norm': 0.5450639128684998, 'learning_rate': 0.00015555555555555556, 'epoch': 0.04}
{'loss': 1.9108, 'grad_norm': 0.7078911066055298, 'learning_rate': 0.0001666666666666667, 'epoch': 0.04}
{'loss': 1.7895, 'grad_norm': 0.5440416932106018, 'learning_rate': 0.00017777777777777779, 'epoch': 0.04}
{'loss': 1.8499, 'grad_norm': 0.6741238236427307, 'learning_rate': 0.00018888888888888888, 'epoch': 0.05}
{'loss': 1.745, 'grad_norm': 0.6223885416984558, 'learning_rate': 0.0002, 'epoch': 0.05}
{'loss': 1.637, 'grad_norm': 0.654057502746582, 'learning_rate': 0.0001994148624926858, 'epoch': 0.05}
{'loss': 1.802, 'grad_norm': 0.47887322306632996, 'learning_rate': 0.00019882972498537157, 'epoch': 0.06}
{'loss': 1.8009, 'grad_norm': 0.783930778503418, 'learning_rate': 0.00019824458747805734, 'epoch': 0.06}
{'loss': 1.847, 'grad_norm': 0.9810641407966614, 'learning_rate': 0.00019765944997074313, 'epoch': 0.06}
{'loss': 1.7683, 'grad_norm': 0.6390312910079956, 'learning_rate': 0.0001970743124634289, 'epoch': 0.06}
{'loss': 1.5858, 'grad_norm': 0.7976217865943909, 'learning_rate': 0.0001964891749561147, 'epoch': 0.07}
{'loss': 1.6725, 'grad_norm': 0.9233970046043396, 'learning_rate': 0.0001959040374488005, 'epoch': 0.07}
{'loss': 1.5629, 'grad_norm': 0.9889336228370667, 'learning_rate': 0.00019531889994148626, 'epoch': 0.07}
{'loss': 1.6842, 'grad_norm': 0.8263123035430908, 'learning_rate': 0.00019473376243417202, 'epoch': 0.08}
{'loss': 1.6994, 'grad_norm': 0.7401031851768494, 'learning_rate': 0.00019414862492685782, 'epoch': 0.08}
{'loss': 1.6662, 'grad_norm': 0.6099547147750854, 'learning_rate': 0.00019356348741954359, 'epoch': 0.08}
{'loss': 1.7344, 'grad_norm': 0.9664725065231323, 'learning_rate': 0.00019297834991222938, 'epoch': 0.08}
{'loss': 1.5765, 'grad_norm': 1.102137565612793, 'learning_rate': 0.00019239321240491518, 'epoch': 0.09}
{'loss': 1.6127, 'grad_norm': 0.8319466710090637, 'learning_rate': 0.00019180807489760094, 'epoch': 0.09}
{'loss': 1.6298, 'grad_norm': 0.8705776333808899, 'learning_rate': 0.0001912229373902867, 'epoch': 0.09}
{'loss': 1.625, 'grad_norm': 0.6215114593505859, 'learning_rate': 0.0001906377998829725, 'epoch': 0.09}
{'loss': 1.6475, 'grad_norm': 0.9244978427886963, 'learning_rate': 0.0001900526623756583, 'epoch': 0.1}
{'loss': 1.6164, 'grad_norm': 1.0081429481506348, 'learning_rate': 0.00018946752486834407, 'epoch': 0.1}
{'loss': 1.5784, 'grad_norm': 0.9833176732063293, 'learning_rate': 0.00018888238736102986, 'epoch': 0.1}
{'loss': 1.4971, 'grad_norm': 1.0448380708694458, 'learning_rate': 0.00018829724985371563, 'epoch': 0.11}
{'loss': 1.5317, 'grad_norm': 0.963756799697876, 'learning_rate': 0.0001877121123464014, 'epoch': 0.11}
{'loss': 1.6251, 'grad_norm': 0.7907305955886841, 'learning_rate': 0.0001871269748390872, 'epoch': 0.11}
{'loss': 1.4419, 'grad_norm': 1.3546243906021118, 'learning_rate': 0.00018654183733177298, 'epoch': 0.11}
{'loss': 1.5571, 'grad_norm': 0.9288954138755798, 'learning_rate': 0.00018595669982445875, 'epoch': 0.12}
{'loss': 1.5006, 'grad_norm': 1.1262363195419312, 'learning_rate': 0.00018537156231714455, 'epoch': 0.12}
{'loss': 1.5663, 'grad_norm': 0.9970844984054565, 'learning_rate': 0.00018478642480983034, 'epoch': 0.12}
{'loss': 1.458, 'grad_norm': 1.299085259437561, 'learning_rate': 0.00018420128730251608, 'epoch': 0.13}
{'loss': 1.5316, 'grad_norm': 0.9666916131973267, 'learning_rate': 0.00018361614979520188, 'epoch': 0.13}
{'loss': 1.4571, 'grad_norm': 0.9775465726852417, 'learning_rate': 0.00018303101228788767, 'epoch': 0.13}
{'loss': 1.6143, 'grad_norm': 1.0702718496322632, 'learning_rate': 0.00018244587478057344, 'epoch': 0.13}
{'loss': 1.4133, 'grad_norm': 1.0198723077774048, 'learning_rate': 0.00018186073727325923, 'epoch': 0.14}
{'loss': 1.4449, 'grad_norm': 1.1751333475112915, 'learning_rate': 0.00018127559976594503, 'epoch': 0.14}
{'loss': 1.58, 'grad_norm': 1.124013900756836, 'learning_rate': 0.00018069046225863077, 'epoch': 0.14}
{'loss': 1.4243, 'grad_norm': 1.1146219968795776, 'learning_rate': 0.00018010532475131656, 'epoch': 0.14}
{'loss': 1.3418, 'grad_norm': 0.9221692085266113, 'learning_rate': 0.00017952018724400236, 'epoch': 0.15}
{'loss': 1.3914, 'grad_norm': 1.2927697896957397, 'learning_rate': 0.00017893504973668812, 'epoch': 0.15}
{'loss': 1.4291, 'grad_norm': 1.2189618349075317, 'learning_rate': 0.00017834991222937392, 'epoch': 0.15}
{'loss': 1.3442, 'grad_norm': 1.2801870107650757, 'learning_rate': 0.0001777647747220597, 'epoch': 0.16}
{'loss': 1.313, 'grad_norm': 1.3508485555648804, 'learning_rate': 0.00017717963721474545, 'epoch': 0.16}
{'loss': 1.4554, 'grad_norm': 0.9896947145462036, 'learning_rate': 0.00017659449970743125, 'epoch': 0.16}
{'loss': 1.3431, 'grad_norm': 0.8964052796363831, 'learning_rate': 0.00017600936220011704, 'epoch': 0.16}
{'loss': 1.4533, 'grad_norm': 1.3584518432617188, 'learning_rate': 0.0001754242246928028, 'epoch': 0.17}
{'loss': 1.3523, 'grad_norm': 1.092515468597412, 'learning_rate': 0.0001748390871854886, 'epoch': 0.17}
{'loss': 1.3369, 'grad_norm': 1.2471967935562134, 'learning_rate': 0.0001742539496781744, 'epoch': 0.17}
{'loss': 1.3657, 'grad_norm': 1.297553539276123, 'learning_rate': 0.00017366881217086014, 'epoch': 0.18}
{'loss': 1.2446, 'grad_norm': 1.4945882558822632, 'learning_rate': 0.00017308367466354593, 'epoch': 0.18}
{'loss': 1.3642, 'grad_norm': 1.7191970348358154, 'learning_rate': 0.00017249853715623173, 'epoch': 0.18}
{'loss': 1.2716, 'grad_norm': 1.278106451034546, 'learning_rate': 0.0001719133996489175, 'epoch': 0.18}
{'loss': 1.2181, 'grad_norm': 1.4567068815231323, 'learning_rate': 0.0001713282621416033, 'epoch': 0.19}
{'loss': 1.1919, 'grad_norm': 1.1871955394744873, 'learning_rate': 0.00017074312463428908, 'epoch': 0.19}
{'loss': 1.3186, 'grad_norm': 1.064318060874939, 'learning_rate': 0.00017015798712697485, 'epoch': 0.19}
{'loss': 1.2643, 'grad_norm': 1.5443544387817383, 'learning_rate': 0.00016957284961966062, 'epoch': 0.19}
{'loss': 1.2199, 'grad_norm': 1.0379834175109863, 'learning_rate': 0.0001689877121123464, 'epoch': 0.2}
{'loss': 1.2775, 'grad_norm': 1.4339805841445923, 'learning_rate': 0.00016840257460503218, 'epoch': 0.2}
{'loss': 1.2689, 'grad_norm': 1.7690389156341553, 'learning_rate': 0.00016781743709771797, 'epoch': 0.2}
{'loss': 1.1829, 'grad_norm': 1.3799852132797241, 'learning_rate': 0.00016723229959040377, 'epoch': 0.21}
{'loss': 1.2952, 'grad_norm': 1.0880959033966064, 'learning_rate': 0.00016664716208308954, 'epoch': 0.21}
{'loss': 1.1756, 'grad_norm': 0.9457182884216309, 'learning_rate': 0.0001660620245757753, 'epoch': 0.21}
{'loss': 1.2704, 'grad_norm': 1.383113145828247, 'learning_rate': 0.0001654768870684611, 'epoch': 0.21}
{'loss': 1.294, 'grad_norm': 1.0459240674972534, 'learning_rate': 0.0001648917495611469, 'epoch': 0.22}
{'loss': 1.2052, 'grad_norm': 1.2870111465454102, 'learning_rate': 0.00016430661205383266, 'epoch': 0.22}
 22%|██▏       | 790/3598 [13:30<46:29,  1.01it/s]
 22%|██▏       | 791/3598 [13:31<46:17,  1.01it/s]
 22%|██▏       | 792/3598 [13:32<50:17,  1.08s/it]
 22%|██▏       | 793/3598 [13:34<53:46,  1.15s/it]
 22%|██▏       | 794/3598 [13:35<51:14,  1.10s/it]
 22%|██▏       | 795/3598 [13:36<51:04,  1.09s/it]
 22%|██▏       | 796/3598 [13:37<50:18,  1.08s/it]
 22%|██▏       | 797/3598 [13:38<49:15,  1.06s/it]
 22%|██▏       | 798/3598 [13:39<47:47,  1.02s/it]
 22%|██▏       | 799/3598 [13:40<45:48,  1.02it/s]
 22%|██▏       | 800/3598 [13:41<44:33,  1.05it/s]
                                                  

 22%|██▏       | 800/3598 [13:41<44:33,  1.05it/s]
 22%|██▏       | 801/3598 [13:42<45:29,  1.02it/s]
 22%|██▏       | 802/3598 [13:43<44:47,  1.04it/s]
 22%|██▏       | 803/3598 [13:44<48:09,  1.03s/it]
 22%|██▏       | 804/3598 [13:45<48:41,  1.05s/it]
 22%|██▏       | 805/3598 [13:46<50:26,  1.08s/it]
 22%|██▏       | 806/3598 [13:47<47:53,  1.03s/it]
 22%|██▏       | 807/3598 [13:48<48:45,  1.05s/it]
 22%|██▏       | 808/3598 [13:49<46:11,  1.01it/s]
 22%|██▏       | 809/3598 [13:50<44:48,  1.04it/s]
 23%|██▎       | 810/3598 [13:51<43:40,  1.06it/s]
                                                  

 23%|██▎       | 810/3598 [13:51<43:40,  1.06it/s]
 23%|██▎       | 811/3598 [13:52<42:59,  1.08it/s]
 23%|██▎       | 812/3598 [13:52<41:56,  1.11it/s]
 23%|██▎       | 813/3598 [13:53<42:33,  1.09it/s]
 23%|██▎       | 814/3598 [13:55<48:41,  1.05s/it]
 23%|██▎       | 815/3598 [13:56<46:43,  1.01s/it]
 23%|██▎       | 816/3598 [13:56<44:40,  1.04it/s]
 23%|██▎       | 817/3598 [13:57<44:34,  1.04it/s]
 23%|██▎       | 818/3598 [13:59<49:07,  1.06s/it]
 23%|██▎       | 819/3598 [14:00<48:53,  1.06s/it]
 23%|██▎       | 820/3598 [14:01<46:03,  1.01it/s]
                                                  

 23%|██▎       | 820/3598 [14:01<46:03,  1.01it/s]
 23%|██▎       | 821/3598 [14:02<45:41,  1.01it/s]
 23%|██▎       | 822/3598 [14:03<48:33,  1.05s/it]
 23%|██▎       | 823/3598 [14:04<47:25,  1.03s/it]
 23%|██▎       | 824/3598 [14:05<52:29,  1.14s/it]
 23%|██▎       | 825/3598 [14:06<48:59,  1.06s/it]
 23%|██▎       | 826/3598 [14:07<47:35,  1.03s/it]
 23%|██▎       | 827/3598 [14:08<45:48,  1.01it/s]
 23%|██▎       | 828/3598 [14:09<45:11,  1.02it/s]
 23%|██▎       | 829/3598 [14:10<43:21,  1.06it/s]
 23%|██▎       | 830/3598 [14:11<44:41,  1.03it/s]
                                                  

 23%|██▎       | 830/3598 [14:11<44:41,  1.03it/s]
 23%|██▎       | 831/3598 [14:12<42:46,  1.08it/s]
 23%|██▎       | 832/3598 [14:12<42:00,  1.10it/s]
 23%|██▎       | 833/3598 [14:13<41:27,  1.11it/s]
 23%|██▎       | 834/3598 [14:14<42:38,  1.08it/s]
 23%|██▎       | 835/3598 [14:16<49:14,  1.07s/it]
 23%|██▎       | 836/3598 [14:17<48:19,  1.05s/it]
 23%|██▎       | 837/3598 [14:18<45:21,  1.01it/s]
 23%|██▎       | 838/3598 [14:18<44:08,  1.04it/s]
 23%|██▎       | 839/3598 [14:20<49:16,  1.07s/it]
 23%|██▎       | 840/3598 [14:21<47:33,  1.03s/it]
                                                  

 23%|██▎       | 840/3598 [14:21<47:33,  1.03s/it]
 23%|██▎       | 841/3598 [14:22<47:16,  1.03s/it]
 23%|██▎       | 842/3598 [14:23<48:14,  1.05s/it]
 23%|██▎       | 843/3598 [14:24<46:43,  1.02s/it]
 23%|██▎       | 844/3598 [14:25<51:57,  1.13s/it]
 23%|██▎       | 845/3598 [14:26<47:08,  1.03s/it]
 24%|██▎       | 846/3598 [14:27<51:01,  1.11s/it]
 24%|██▎       | 847/3598 [14:28<47:10,  1.03s/it]
 24%|██▎       | 848/3598 [14:29<52:11,  1.14s/it]
 24%|██▎       | 849/3598 [14:30<48:30,  1.06s/it]
 24%|██▎       | 850/3598 [14:31<46:14,  1.01s/it]
                                                  

 24%|██▎       | 850/3598 [14:31<46:14,  1.01s/it]
 24%|██▎       | 851/3598 [14:33<51:25,  1.12s/it]
 24%|██▎       | 852/3598 [14:33<47:36,  1.04s/it]
 24%|██▎       | 853/3598 [14:34<45:39,  1.00it/s]
 24%|██▎       | 854/3598 [14:35<46:09,  1.01s/it]
 24%|██▍       | 855/3598 [14:36<45:29,  1.00it/s]
 24%|██▍       | 856/3598 [14:37<43:26,  1.05it/s]
 24%|██▍       | 857/3598 [14:38<42:38,  1.07it/s]
 24%|██▍       | 858/3598 [14:39<43:00,  1.06it/s]
 24%|██▍       | 859/3598 [14:40<41:06,  1.11it/s]
 24%|██▍       | 860/3598 [14:41<41:21,  1.10it/s]
                                                  

 24%|██▍       | 860/3598 [14:41<41:21,  1.10it/s]
 24%|██▍       | 861/3598 [14:42<40:51,  1.12it/s]
 24%|██▍       | 862/3598 [14:43<44:52,  1.02it/s]
 24%|██▍       | 863/3598 [14:44<43:59,  1.04it/s]
 24%|██▍       | 864/3598 [14:45<43:29,  1.05it/s]
 24%|██▍       | 865/3598 [14:46<46:48,  1.03s/it]
 24%|██▍       | 866/3598 [14:47<45:03,  1.01it/s]
 24%|██▍       | 867/3598 [14:48<45:28,  1.00it/s]
 24%|██▍       | 868/3598 [14:49<44:33,  1.02it/s]
 24%|██▍       | 869/3598 [14:50<43:21,  1.05it/s]
 24%|██▍       | 870/3598 [14:51<44:12,  1.03it/s]
                                                  

 24%|██▍       | 870/3598 [14:51<44:12,  1.03it/s]
 24%|██▍       | 871/3598 [14:52<42:58,  1.06it/s]
 24%|██▍       | 872/3598 [14:52<41:02,  1.11it/s]
 24%|██▍       | 873/3598 [14:53<40:59,  1.11it/s]
 24%|██▍       | 874/3598 [14:54<39:52,  1.14it/s]
 24%|██▍       | 875/3598 [14:55<40:47,  1.11it/s]
 24%|██▍       | 876/3598 [14:56<40:31,  1.12it/s]
 24%|██▍       | 877/3598 [14:57<39:43,  1.14it/s]
 24%|██▍       | 878/3598 [14:58<40:30,  1.12it/s]
 24%|██▍       | 879/3598 [14:59<41:06,  1.10it/s]
 24%|██▍       | 880/3598 [15:00<47:58,  1.06s/it]
                                                  

 24%|██▍       | 880/3598 [15:00<47:58,  1.06s/it]
 24%|██▍       | 881/3598 [15:01<46:50,  1.03s/it]
 25%|██▍       | 882/3598 [15:02<44:43,  1.01it/s]
 25%|██▍       | 883/3598 [15:03<44:38,  1.01it/s]
 25%|██▍       | 884/3598 [15:04<50:11,  1.11s/it]
 25%|██▍       | 885/3598 [15:05<45:48,  1.01s/it]
 25%|██▍       | 886/3598 [15:06<43:24,  1.04it/s]
 25%|██▍       | 887/3598 [15:07<41:03,  1.10it/s]
 25%|██▍       | 888/3598 [15:07<39:26,  1.15it/s]
 25%|██▍       | 889/3598 [15:08<38:36,  1.17it/s]
 25%|██▍       | 890/3598 [15:10<43:54,  1.03it/s]
                                                  

 25%|██▍       | 890/3598 [15:10<43:54,  1.03it/s]
 25%|██▍       | 891/3598 [15:10<41:08,  1.10it/s]
 25%|██▍       | 892/3598 [15:11<39:19,  1.15it/s]
 25%|██▍       | 893/3598 [15:12<46:13,  1.03s/it]
 25%|██▍       | 894/3598 [15:13<42:56,  1.05it/s]
 25%|██▍       | 895/3598 [15:14<45:24,  1.01s/it]
 25%|██▍       | 896/3598 [15:15<43:36,  1.03it/s]
 25%|██▍       | 897/3598 [15:16<43:44,  1.03it/s]
 25%|██▍       | 898/3598 [15:18<47:33,  1.06s/it]
 25%|██▍       | 899/3598 [15:19<50:58,  1.13s/it]
 25%|██▌       | 900/3598 [15:20<47:50,  1.06s/it]
                                                  

 25%|██▌       | 900/3598 [15:20<47:50,  1.06s/it]
{'loss': 1.2649, 'grad_norm': 1.4526729583740234, 'learning_rate': 0.00016372147454651845, 'epoch': 0.22}
{'loss': 1.0921, 'grad_norm': 1.846928358078003, 'learning_rate': 0.00016313633703920422, 'epoch': 0.23}
{'loss': 1.2423, 'grad_norm': 1.5239036083221436, 'learning_rate': 0.00016255119953189, 'epoch': 0.23}
{'loss': 1.1756, 'grad_norm': 1.3172131776809692, 'learning_rate': 0.00016196606202457578, 'epoch': 0.23}
{'loss': 1.1734, 'grad_norm': 1.5167595148086548, 'learning_rate': 0.00016138092451726158, 'epoch': 0.23}
{'loss': 1.2039, 'grad_norm': 1.349012851715088, 'learning_rate': 0.00016079578700994735, 'epoch': 0.24}
{'loss': 1.1005, 'grad_norm': 1.1730643510818481, 'learning_rate': 0.00016021064950263314, 'epoch': 0.24}
{'loss': 1.1946, 'grad_norm': 1.320278286933899, 'learning_rate': 0.0001596255119953189, 'epoch': 0.24}
{'loss': 1.09, 'grad_norm': 0.9002246260643005, 'learning_rate': 0.00015904037448800467, 'epoch': 0.24}
{'loss': 1.0499, 'grad_norm': 1.1015177965164185, 'learning_rate': 0.00015845523698069047, 'epoch': 0.25}
{'loss': 1.1817, 'grad_norm': 1.7522237300872803, 'learning_rate': 0.00015787009947337626, 'epoch': 0.25}


  0%|          | 0/4 [00:00<?, ?it/s]

 50%|█████     | 2/4 [00:13<00:13,  6.67s/it]

 75%|███████▌  | 3/4 [00:28<00:10, 10.23s/it]

100%|██████████| 4/4 [00:33<00:00,  8.35s/it]
                                                  

                                             

 25%|██▌       | 900/3598 [16:02<47:50,  1.06s/it]

100%|██████████| 4/4 [00:33<00:00,  8.35s/it]

                                             /opt/mobtranslate-v24-venv/lib/python3.11/site-packages/peft/utils/save_and_load.py:386: UserWarning: Setting `save_embedding_layers` to `True` as the embedding layer has been resized during finetuning.
  warnings.warn(

 25%|██▌       | 901/3598 [16:07<11:05:06, 14.80s/it]
 25%|██▌       | 902/3598 [16:08<8:04:03, 10.77s/it] 
 25%|██▌       | 903/3598 [16:09<5:54:11,  7.89s/it]
 25%|██▌       | 904/3598 [16:10<4:21:11,  5.82s/it]
 25%|██▌       | 905/3598 [16:11<3:21:13,  4.48s/it]
 25%|██▌       | 906/3598 [16:12<2:32:43,  3.40s/it]
 25%|██▌       | 907/3598 [16:13<1:58:52,  2.65s/it]
 25%|██▌       | 908/3598 [16:14<1:35:51,  2.14s/it]
 25%|██▌       | 909/3598 [16:15<1:20:24,  1.79s/it]
 25%|██▌       | 910/3598 [16:16<1:08:48,  1.54s/it]
                                                    

 25%|██▌       | 910/3598 [16:16<1:08:48,  1.54s/it]
 25%|██▌       | 911/3598 [16:17<1:00:03,  1.34s/it]
 25%|██▌       | 912/3598 [16:18<1:00:08,  1.34s/it]
 25%|██▌       | 913/3598 [16:19<53:54,  1.20s/it]  
 25%|██▌       | 914/3598 [16:20<51:34,  1.15s/it]
 25%|██▌       | 915/3598 [16:21<50:20,  1.13s/it]
 25%|██▌       | 916/3598 [16:22<46:06,  1.03s/it]
 25%|██▌       | 917/3598 [16:23<43:35,  1.03it/s]
 26%|██▌       | 918/3598 [16:24<48:02,  1.08s/it]
 26%|██▌       | 919/3598 [16:25<45:32,  1.02s/it]
 26%|██▌       | 920/3598 [16:26<45:54,  1.03s/it]
                                                  

 26%|██▌       | 920/3598 [16:26<45:54,  1.03s/it]
 26%|██▌       | 921/3598 [16:28<50:43,  1.14s/it]
 26%|██▌       | 922/3598 [16:29<52:08,  1.17s/it]
 26%|██▌       | 923/3598 [16:30<48:27,  1.09s/it]
 26%|██▌       | 924/3598 [16:31<45:14,  1.02s/it]
 26%|██▌       | 925/3598 [16:32<49:24,  1.11s/it]
 26%|██▌       | 926/3598 [16:33<46:04,  1.03s/it]
 26%|██▌       | 927/3598 [16:34<44:23,  1.00it/s]
 26%|██▌       | 928/3598 [16:35<49:29,  1.11s/it]
 26%|██▌       | 929/3598 [16:36<47:14,  1.06s/it]
 26%|██▌       | 930/3598 [16:37<51:11,  1.15s/it]
                                                  

 26%|██▌       | 930/3598 [16:37<51:11,  1.15s/it]
 26%|██▌       | 931/3598 [16:39<52:04,  1.17s/it]
 26%|██▌       | 932/3598 [16:39<47:36,  1.07s/it]
 26%|██▌       | 933/3598 [16:41<48:06,  1.08s/it]
 26%|██▌       | 934/3598 [16:41<45:52,  1.03s/it]
 26%|██▌       | 935/3598 [16:43<46:13,  1.04s/it]
 26%|██▌       | 936/3598 [16:43<45:04,  1.02s/it]
 26%|██▌       | 937/3598 [16:44<44:48,  1.01s/it]
 26%|██▌       | 938/3598 [16:45<44:43,  1.01s/it]
 26%|██▌       | 939/3598 [16:46<43:50,  1.01it/s]
 26%|██▌       | 940/3598 [16:47<41:59,  1.06it/s]
                                                  

 26%|██▌       | 940/3598 [16:47<41:59,  1.06it/s]
 26%|██▌       | 941/3598 [16:48<44:38,  1.01s/it]
 26%|██▌       | 942/3598 [16:50<48:32,  1.10s/it]
 26%|██▌       | 943/3598 [16:51<49:56,  1.13s/it]
 26%|██▌       | 944/3598 [16:52<47:55,  1.08s/it]
 26%|██▋       | 945/3598 [16:53<46:56,  1.06s/it]
 26%|██▋       | 946/3598 [16:54<48:51,  1.11s/it]
 26%|██▋       | 947/3598 [16:55<52:21,  1.18s/it]
 26%|██▋       | 948/3598 [16:56<48:32,  1.10s/it]
 26%|██▋       | 949/3598 [16:57<47:29,  1.08s/it]
 26%|██▋       | 950/3598 [16:59<51:53,  1.18s/it]
                                                  

 26%|██▋       | 950/3598 [16:59<51:53,  1.18s/it]
 26%|██▋       | 951/3598 [17:00<49:31,  1.12s/it]
 26%|██▋       | 952/3598 [17:01<47:40,  1.08s/it]
 26%|██▋       | 953/3598 [17:02<51:33,  1.17s/it]
 27%|██▋       | 954/3598 [17:03<47:57,  1.09s/it]
 27%|██▋       | 955/3598 [17:04<44:27,  1.01s/it]
 27%|██▋       | 956/3598 [17:05<42:43,  1.03it/s]
 27%|██▋       | 957/3598 [17:06<43:19,  1.02it/s]
 27%|██▋       | 958/3598 [17:07<42:11,  1.04it/s]
 27%|██▋       | 959/3598 [17:08<46:04,  1.05s/it]
 27%|██▋       | 960/3598 [17:09<43:18,  1.02it/s]
                                                  

 27%|██▋       | 960/3598 [17:09<43:18,  1.02it/s]
 27%|██▋       | 961/3598 [17:10<44:41,  1.02s/it]
 27%|██▋       | 962/3598 [17:11<43:04,  1.02it/s]
 27%|██▋       | 963/3598 [17:12<47:28,  1.08s/it]
 27%|██▋       | 964/3598 [17:13<50:39,  1.15s/it]
 27%|██▋       | 965/3598 [17:15<50:58,  1.16s/it]
 27%|██▋       | 966/3598 [17:16<53:07,  1.21s/it]
 27%|██▋       | 967/3598 [17:17<47:28,  1.08s/it]
 27%|██▋       | 968/3598 [17:18<45:43,  1.04s/it]
 27%|██▋       | 969/3598 [17:19<44:14,  1.01s/it]
 27%|██▋       | 970/3598 [17:20<46:47,  1.07s/it]
                                                  

 27%|██▋       | 970/3598 [17:20<46:47,  1.07s/it]
 27%|██▋       | 971/3598 [17:21<44:26,  1.01s/it]
 27%|██▋       | 972/3598 [17:22<48:38,  1.11s/it]
 27%|██▋       | 973/3598 [17:23<51:15,  1.17s/it]
 27%|██▋       | 974/3598 [17:25<51:41,  1.18s/it]
 27%|██▋       | 975/3598 [17:26<53:40,  1.23s/it]
 27%|██▋       | 976/3598 [17:27<49:20,  1.13s/it]
 27%|██▋       | 977/3598 [17:28<47:27,  1.09s/it]
 27%|██▋       | 978/3598 [17:29<44:57,  1.03s/it]
 27%|██▋       | 979/3598 [17:30<46:32,  1.07s/it]
 27%|██▋       | 980/3598 [17:31<43:58,  1.01s/it]
                                                  

 27%|██▋       | 980/3598 [17:31<43:58,  1.01s/it]
 27%|██▋       | 981/3598 [17:32<43:43,  1.00s/it]
 27%|██▋       | 982/3598 [17:33<41:56,  1.04it/s]
 27%|██▋       | 983/3598 [17:33<40:19,  1.08it/s]
 27%|██▋       | 984/3598 [17:34<40:36,  1.07it/s]
 27%|██▋       | 985/3598 [17:35<41:52,  1.04it/s]
 27%|██▋       | 986/3598 [17:37<47:09,  1.08s/it]
 27%|██▋       | 987/3598 [17:38<51:05,  1.17s/it]
 27%|██▋       | 988/3598 [17:39<51:48,  1.19s/it]
 27%|██▋       | 989/3598 [17:40<47:04,  1.08s/it]
 28%|██▊       | 990/3598 [17:41<44:28,  1.02s/it]
                                                  

 28%|██▊       | 990/3598 [17:41<44:28,  1.02s/it]
 28%|██▊       | 991/3598 [17:42<47:08,  1.09s/it]
 28%|██▊       | 992/3598 [17:43<45:55,  1.06s/it]
 28%|██▊       | 993/3598 [17:44<43:21,  1.00it/s]
 28%|██▊       | 994/3598 [17:45<43:00,  1.01it/s]
 28%|██▊       | 995/3598 [17:46<42:43,  1.02it/s]
 28%|██▊       | 996/3598 [17:47<42:20,  1.02it/s]
 28%|██▊       | 997/3598 [17:48<41:49,  1.04it/s]
 28%|██▊       | 998/3598 [17:49<43:02,  1.01it/s]
 28%|██▊       | 999/3598 [17:50<41:41,  1.04it/s]
 28%|██▊       | 1000/3598 [17:51<41:44,  1.04it/s]
                                                   

 28%|██▊       | 1000/3598 [17:51<41:44,  1.04it/s]
 28%|██▊       | 1001/3598 [17:52<47:07,  1.09s/it]
 28%|██▊       | 1002/3598 [17:53<47:00,  1.09s/it]
 28%|██▊       | 1003/3598 [17:54<45:55,  1.06s/it]
 28%|██▊       | 1004/3598 [17:55<42:17,  1.02it/s]
 28%|██▊       | 1005/3598 [17:56<45:49,  1.06s/it]
 28%|██▊       | 1006/3598 [17:57<43:14,  1.00s/it]
 28%|██▊       | 1007/3598 [17:58<41:23,  1.04it/s]
 28%|██▊       | 1008/3598 [17:59<41:36,  1.04it/s]
 28%|██▊       | 1009/3598 [18:00<40:29,  1.07it/s]
 28%|██▊       | 1010/3598 [18:01<42:51,  1.01it/s]
                                                   

 28%|██▊       | 1010/3598 [18:01<42:51,  1.01it/s]
 28%|██▊       | 1011/3598 [18:02<41:04,  1.05it/s]
 28%|██▊       | 1012/3598 [18:03<45:45,  1.06s/it]
 28%|██▊       | 1013/3598 [18:04<44:33,  1.03s/it]
 28%|██▊       | 1014/3598 [18:05<42:05,  1.02it/s]
 28%|██▊       | 1015/3598 [18:06<42:24,  1.01it/s]
 28%|██▊       | 1016/3598 [18:07<42:32,  1.01it/s]
 28%|██▊       | 1017/3598 [18:08<39:47,  1.08it/s]
 28%|██▊       | 1018/3598 [18:09<40:01,  1.07it/s]
 28%|██▊       | 1019/3598 [18:10<38:23,  1.12it/s]
 28%|██▊       | 1020/3598 [18:10<37:42,  1.14it/s]
                                                   

 28%|██▊       | 1020/3598 [18:10<37:42,  1.14it/s]
 28%|██▊       | 1021/3598 [18:11<39:49,  1.08it/s]
 28%|██▊       | 1022/3598 [18:13<43:28,  1.01s/it]
 28%|██▊       | 1023/3598 [18:14<44:38,  1.04s/it]
 28%|██▊       | 1024/3598 [18:15<46:28,  1.08s/it]
 28%|██▊       | 1025/3598 [18:16<45:53,  1.07s/it]
 29%|██▊       | 1026/3598 [18:17<45:38,  1.06s/it]
 29%|██▊       | 1027/3598 [18:18<42:45,  1.00it/s]
 29%|██▊       | 1028/3598 [18:19<40:56,  1.05it/s]
 29%|██▊       | 1029/3598 [18:20<40:02,  1.07it/s]
 29%|██▊       | 1030/3598 [18:21<39:25,  1.09it/s]
                                                   

 29%|██▊       | 1030/3598 [18:21<39:25,  1.09it/s]
 29%|██▊       | 1031/3598 [18:22<39:56,  1.07it/s]
 29%|██▊       | 1032/3598 [18:23<43:16,  1.01s/it]
 29%|██▊       | 1033/3598 [18:24<42:59,  1.01s/it]
 29%|██▊       | 1034/3598 [18:25<44:06,  1.03s/it]
 29%|██▉       | 1035/3598 [18:26<43:03,  1.01s/it]
 29%|██▉       | 1036/3598 [18:27<43:10,  1.01s/it]
 29%|██▉       | 1037/3598 [18:28<42:10,  1.01it/s]
 29%|██▉       | 1038/3598 [18:29<42:13,  1.01it/s]
 29%|██▉       | 1039/3598 [18:30<40:56,  1.04it/s]
 29%|██▉       | 1040/3598 [18:31<46:31,  1.09s/it]
                                                   

 29%|██▉       | 1040/3598 [18:31<46:31,  1.09s/it]
 29%|██▉       | 1041/3598 [18:32<44:29,  1.04s/it]
 29%|██▉       | 1042/3598 [18:33<42:09,  1.01it/s]
 29%|██▉       | 1043/3598 [18:34<40:20,  1.06it/s]
 29%|██▉       | 1044/3598 [18:35<43:06,  1.01s/it]
 29%|██▉       | 1045/3598 [18:36<43:53,  1.03s/it]
 29%|██▉       | 1046/3598 [18:37<43:01,  1.01s/it]
 29%|██▉       | 1047/3598 [18:38<41:23,  1.03it/s]
 29%|██▉       | 1048/3598 [18:39<40:18,  1.05it/s]
 29%|██▉       | 1049/3598 [18:40<39:35,  1.07it/s]
 29%|██▉       | 1050/3598 [18:40<38:54,  1.09it/s]
                                                   

 29%|██▉       | 1050/3598 [18:40<38:54,  1.09it/s]
 29%|██▉       | 1051/3598 [18:41<40:42,  1.04it/s]
 29%|██▉       | 1052/3598 [18:42<41:27,  1.02it/s]
 29%|██▉       | 1053/3598 [18:43<39:48,  1.07it/s]
 29%|██▉       | 1054/3598 [18:44<39:38,  1.07it/s]
 29%|██▉       | 1055/3598 [18:45<38:36,  1.10it/s]
 29%|██▉       | 1056/3598 [18:46<38:12,  1.11it/s]
 29%|██▉       | 1057/3598 [18:47<43:45,  1.03s/it]
 29%|██▉       | 1058/3598 [18:48<42:21,  1.00s/it]
 29%|██▉       | 1059/3598 [18:49<40:21,  1.05it/s]
 29%|██▉       | 1060/3598 [18:50<39:05,  1.08it/s]
                                                   

 29%|██▉       | 1060/3598 [18:50<39:05,  1.08it/s]
 29%|██▉       | 1061/3598 [18:51<39:54,  1.06it/s]
 30%|██▉       | 1062/3598 [18:52<39:06,  1.08it/s]
 30%|██▉       | 1063/3598 [18:53<38:50,  1.09it/s]
 30%|██▉       | 1064/3598 [18:54<38:03,  1.11it/s]
 30%|██▉       | 1065/3598 [18:55<38:57,  1.08it/s]
 30%|██▉       | 1066/3598 [18:56<43:37,  1.03s/it]
 30%|██▉       | 1067/3598 [18:57<47:44,  1.13s/it]
 30%|██▉       | 1068/3598 [18:58<45:07,  1.07s/it]
 30%|██▉       | 1069/3598 [18:59<43:32,  1.03s/it]
 30%|██▉       | 1070/3598 [19:00<43:24,  1.03s/it]
                                                   

 30%|██▉       | 1070/3598 [19:00<43:24,  1.03s/it]
 30%|██▉       | 1071/3598 [19:01<42:37,  1.01s/it]
 30%|██▉       | 1072/3598 [19:02<42:12,  1.00s/it]
 30%|██▉       | 1073/3598 [19:03<40:13,  1.05it/s]
 30%|██▉       | 1074/3598 [19:04<38:52,  1.08it/s]
 30%|██▉       | 1075/3598 [19:05<38:14,  1.10it/s]
 30%|██▉       | 1076/3598 [19:06<38:28,  1.09it/s]
 30%|██▉       | 1077/3598 [19:06<37:53,  1.11it/s]
 30%|██▉       | 1078/3598 [19:08<43:59,  1.05s/it]
 30%|██▉       | 1079/3598 [19:09<41:35,  1.01it/s]
 30%|███       | 1080/3598 [19:10<45:02,  1.07s/it]
                                                   

 30%|███       | 1080/3598 [19:10<45:02,  1.07s/it]
 30%|███       | 1081/3598 [19:11<43:02,  1.03s/it]
 30%|███       | 1082/3598 [19:12<41:12,  1.02it/s]
 30%|███       | 1083/3598 [19:13<40:27,  1.04it/s]
 30%|███       | 1084/3598 [19:14<38:59,  1.07it/s]
 30%|███       | 1085/3598 [19:14<38:41,  1.08it/s]
 30%|███       | 1086/3598 [19:15<36:52,  1.14it/s]
 30%|███       | 1087/3598 [19:17<42:57,  1.03s/it]
 30%|███       | 1088/3598 [19:17<41:05,  1.02it/s]
 30%|███       | 1089/3598 [19:18<39:24,  1.06it/s]
 30%|███       | 1090/3598 [19:19<39:37,  1.05it/s]
                                                   

 30%|███       | 1090/3598 [19:19<39:37,  1.05it/s]
 30%|███       | 1091/3598 [19:21<45:01,  1.08s/it]
 30%|███       | 1092/3598 [19:22<42:33,  1.02s/it]
 30%|███       | 1093/3598 [19:22<39:58,  1.04it/s]
 30%|███       | 1094/3598 [19:23<39:32,  1.06it/s]
 30%|███       | 1095/3598 [19:25<44:41,  1.07s/it]
 30%|███       | 1096/3598 [19:26<43:27,  1.04s/it]
 30%|███       | 1097/3598 [19:27<43:22,  1.04s/it]
 31%|███       | 1098/3598 [19:27<40:54,  1.02it/s]
 31%|███       | 1099/3598 [19:29<45:43,  1.10s/it]
 31%|███       | 1100/3598 [19:30<46:40,  1.12s/it]
                                                   

 31%|███       | 1100/3598 [19:30<46:40,  1.12s/it]
 31%|███       | 1101/3598 [19:31<43:52,  1.05s/it]
 31%|███       | 1102/3598 [19:32<43:24,  1.04s/it]
 31%|███       | 1103/3598 [19:33<43:55,  1.06s/it]
 31%|███       | 1104/3598 [19:34<43:00,  1.03s/it]
 31%|███       | 1105/3598 [19:35<39:55,  1.04it/s]
 31%|███       | 1106/3598 [19:36<41:31,  1.00it/s]
 31%|███       | 1107/3598 [19:37<40:12,  1.03it/s]
 31%|███       | 1108/3598 [19:38<39:37,  1.05it/s]
 31%|███       | 1109/3598 [19:39<38:09,  1.09it/s]
 31%|███       | 1110/3598 [19:39<37:28,  1.11it/s]
                                                   

 31%|███       | 1110/3598 [19:39<37:28,  1.11it/s]
 31%|███       | 1111/3598 [19:40<37:56,  1.09it/s]
 31%|███       | 1112/3598 [19:41<38:28,  1.08it/s]
 31%|███       | 1113/3598 [19:42<39:27,  1.05it/s]
 31%|███       | 1114/3598 [19:44<45:35,  1.10s/it]
 31%|███       | 1115/3598 [19:45<47:00,  1.14s/it]
 31%|███       | 1116/3598 [19:46<43:11,  1.04s/it]
 31%|███       | 1117/3598 [19:47<47:47,  1.16s/it]
 31%|███       | 1118/3598 [19:48<44:35,  1.08s/it]
 31%|███       | 1119/3598 [19:49<42:33,  1.03s/it]
 31%|███       | 1120/3598 [19:50<41:55,  1.01s/it]
                                                   

 31%|███       | 1120/3598 [19:50<41:55,  1.01s/it]
 31%|███       | 1121/3598 [19:51<40:11,  1.03it/s]
 31%|███       | 1122/3598 [19:52<42:00,  1.02s/it]
 31%|███       | 1123/3598 [19:53<44:16,  1.07s/it]
 31%|███       | 1124/3598 [19:54<43:03,  1.04s/it]
 31%|███▏      | 1125/3598 [19:55<41:07,  1.00it/s]
 31%|███▏      | 1126/3598 [19:56<40:17,  1.02it/s]
 31%|███▏      | 1127/3598 [19:57<41:15,  1.00s/it]
 31%|███▏      | 1128/3598 [19:58<43:36,  1.06s/it]
 31%|███▏      | 1129/3598 [20:00<47:34,  1.16s/it]
 31%|███▏      | 1130/3598 [20:01<44:01,  1.07s/it]
                                                   

 31%|███▏      | 1130/3598 [20:01<44:01,  1.07s/it]
 31%|███▏      | 1131/3598 [20:01<42:37,  1.04s/it]
 31%|███▏      | 1132/3598 [20:03<43:45,  1.06s/it]
 31%|███▏      | 1133/3598 [20:04<46:04,  1.12s/it]
 32%|███▏      | 1134/3598 [20:05<48:04,  1.17s/it]
 32%|███▏      | 1135/3598 [20:06<45:35,  1.11s/it]
 32%|███▏      | 1136/3598 [20:07<42:41,  1.04s/it]
 32%|███▏      | 1137/3598 [20:08<44:41,  1.09s/it]
 32%|███▏      | 1138/3598 [20:09<43:11,  1.05s/it]
 32%|███▏      | 1139/3598 [20:10<41:20,  1.01s/it]
 32%|███▏      | 1140/3598 [20:11<40:40,  1.01it/s]
                                                   

 32%|███▏      | 1140/3598 [20:11<40:40,  1.01it/s]
 32%|███▏      | 1141/3598 [20:12<39:54,  1.03it/s]
 32%|███▏      | 1142/3598 [20:13<40:35,  1.01it/s]
 32%|███▏      | 1143/3598 [20:14<42:47,  1.05s/it]
 32%|███▏      | 1144/3598 [20:15<41:52,  1.02s/it]
 32%|███▏      | 1145/3598 [20:17<46:07,  1.13s/it]
 32%|███▏      | 1146/3598 [20:17<43:53,  1.07s/it]
 32%|███▏      | 1147/3598 [20:18<42:36,  1.04s/it]
 32%|███▏      | 1148/3598 [20:19<41:08,  1.01s/it]
 32%|███▏      | 1149/3598 [20:21<43:26,  1.06s/it]
 32%|███▏      | 1150/3598 [20:22<42:40,  1.05s/it]
                                                   

 32%|███▏      | 1150/3598 [20:22<42:40,  1.05s/it]
 32%|███▏      | 1151/3598 [20:22<40:22,  1.01it/s]
 32%|███▏      | 1152/3598 [20:24<45:21,  1.11s/it]
 32%|███▏      | 1153/3598 [20:25<41:18,  1.01s/it]
 32%|███▏      | 1154/3598 [20:25<39:20,  1.04it/s]
 32%|███▏      | 1155/3598 [20:26<38:53,  1.05it/s]
 32%|███▏      | 1156/3598 [20:27<39:47,  1.02it/s]
 32%|███▏      | 1157/3598 [20:28<37:56,  1.07it/s]
 32%|███▏      | 1158/3598 [20:29<36:09,  1.12it/s]
 32%|███▏      | 1159/3598 [20:30<36:03,  1.13it/s]
 32%|███▏      | 1160/3598 [20:31<36:31,  1.11it/s]
                                                   

 32%|███▏      | 1160/3598 [20:31<36:31,  1.11it/s]
 32%|███▏      | 1161/3598 [20:32<36:45,  1.10it/s]
 32%|███▏      | 1162/3598 [20:33<42:45,  1.05s/it]
 32%|███▏      | 1163/3598 [20:34<40:31,  1.00it/s]
 32%|███▏      | 1164/3598 [20:35<39:50,  1.02it/s]
 32%|███▏      | 1165/3598 [20:36<44:48,  1.10s/it]
 32%|███▏      | 1166/3598 [20:38<46:38,  1.15s/it]
 32%|███▏      | 1167/3598 [20:38<43:16,  1.07s/it]
 32%|███▏      | 1168/3598 [20:40<42:39,  1.05s/it]
 32%|███▏      | 1169/3598 [20:41<42:14,  1.04s/it]
 33%|███▎      | 1170/3598 [20:42<45:05,  1.11s/it]
                                                   

 33%|███▎      | 1170/3598 [20:42<45:05,  1.11s/it]
 33%|███▎      | 1171/3598 [20:43<46:13,  1.14s/it]
 33%|███▎      | 1172/3598 [20:44<48:04,  1.19s/it]
 33%|███▎      | 1173/3598 [20:46<50:04,  1.24s/it]
 33%|███▎      | 1174/3598 [20:47<51:22,  1.27s/it]
 33%|███▎      | 1175/3598 [20:48<45:39,  1.13s/it]
 33%|███▎      | 1176/3598 [20:49<42:49,  1.06s/it]
 33%|███▎      | 1177/3598 [20:50<39:51,  1.01it/s]
 33%|███▎      | 1178/3598 [20:50<38:23,  1.05it/s]
 33%|███▎      | 1179/3598 [20:52<40:15,  1.00it/s]
 33%|███▎      | 1180/3598 [20:53<40:12,  1.00it/s]
                                                   

 33%|███▎      | 1180/3598 [20:53<40:12,  1.00it/s]
 33%|███▎      | 1181/3598 [20:53<40:01,  1.01it/s]
 33%|███▎      | 1182/3598 [20:54<39:33,  1.02it/s]
 33%|███▎      | 1183/3598 [20:55<37:53,  1.06it/s]
 33%|███▎      | 1184/3598 [20:56<37:44,  1.07it/s]
 33%|███▎      | 1185/3598 [20:57<38:13,  1.05it/s]
 33%|███▎      | 1186/3598 [20:58<38:25,  1.05it/s]
 33%|███▎      | 1187/3598 [20:59<40:20,  1.00s/it]
 33%|███▎      | 1188/3598 [21:00<41:58,  1.04s/it]
 33%|███▎      | 1189/3598 [21:01<40:20,  1.00s/it]
 33%|███▎      | 1190/3598 [21:03<43:20,  1.08s/it]
                                                   

 33%|███▎      | 1190/3598 [21:03<43:20,  1.08s/it]
 33%|███▎      | 1191/3598 [21:04<45:47,  1.14s/it]
 33%|███▎      | 1192/3598 [21:05<43:07,  1.08s/it]
 33%|███▎      | 1193/3598 [21:06<42:02,  1.05s/it]
 33%|███▎      | 1194/3598 [21:07<40:20,  1.01s/it]
 33%|███▎      | 1195/3598 [21:08<40:54,  1.02s/it]
 33%|███▎      | 1196/3598 [21:09<41:27,  1.04s/it]
 33%|███▎      | 1197/3598 [21:10<39:23,  1.02it/s]
 33%|███▎      | 1198/3598 [21:11<38:55,  1.03it/s]
 33%|███▎      | 1199/3598 [21:12<43:44,  1.09s/it]
 33%|███▎      | 1200/3598 [21:13<43:00,  1.08s/it]
                                                   

 33%|███▎      | 1200/3598 [21:13<43:00,  1.08s/it]
 33%|███▎      | 1201/3598 [21:14<42:40,  1.07s/it]
 33%|███▎      | 1202/3598 [21:15<42:29,  1.06s/it]
 33%|███▎      | 1203/3598 [21:16<45:28,  1.14s/it]
 33%|███▎      | 1204/3598 [21:18<47:11,  1.18s/it]
 33%|███▎      | 1205/3598 [21:19<43:39,  1.09s/it]
 34%|███▎      | 1206/3598 [21:20<44:04,  1.11s/it]
 34%|███▎      | 1207/3598 [21:21<42:23,  1.06s/it]
 34%|███▎      | 1208/3598 [21:22<40:17,  1.01s/it]
 34%|███▎      | 1209/3598 [21:23<39:43,  1.00it/s]
 34%|███▎      | 1210/3598 [21:24<40:28,  1.02s/it]
                                                   

 34%|███▎      | 1210/3598 [21:24<40:28,  1.02s/it]
 34%|███▎      | 1211/3598 [21:25<43:43,  1.10s/it]
 34%|███▎      | 1212/3598 [21:26<41:32,  1.04s/it]
 34%|███▎      | 1213/3598 [21:27<40:26,  1.02s/it]
 34%|███▎      | 1214/3598 [21:28<39:59,  1.01s/it]
 34%|███▍      | 1215/3598 [21:29<37:27,  1.06it/s]
 34%|███▍      | 1216/3598 [21:30<39:07,  1.01it/s]
 34%|███▍      | 1217/3598 [21:30<36:51,  1.08it/s]
 34%|███▍      | 1218/3598 [21:32<39:22,  1.01it/s]
 34%|███▍      | 1219/3598 [21:33<39:40,  1.00s/it]
 34%|███▍      | 1220/3598 [21:33<38:02,  1.04it/s]
                                                   

 34%|███▍      | 1220/3598 [21:33<38:02,  1.04it/s]
 34%|███▍      | 1221/3598 [21:34<37:22,  1.06it/s]
 34%|███▍      | 1222/3598 [21:36<42:59,  1.09s/it]
 34%|███▍      | 1223/3598 [21:37<40:30,  1.02s/it]
 34%|███▍      | 1224/3598 [21:38<39:53,  1.01s/it]
 34%|███▍      | 1225/3598 [21:39<42:24,  1.07s/it]
 34%|███▍      | 1226/3598 [21:40<46:28,  1.18s/it]
 34%|███▍      | 1227/3598 [21:41<42:27,  1.07s/it]
 34%|███▍      | 1228/3598 [21:42<41:08,  1.04s/it]
 34%|███▍      | 1229/3598 [21:43<39:47,  1.01s/it]
 34%|███▍      | 1230/3598 [21:44<38:15,  1.03it/s]
                                                   

 34%|███▍      | 1230/3598 [21:44<38:15,  1.03it/s]
 34%|███▍      | 1231/3598 [21:45<41:38,  1.06s/it]
 34%|███▍      | 1232/3598 [21:46<40:40,  1.03s/it]
 34%|███▍      | 1233/3598 [21:47<40:04,  1.02s/it]
 34%|███▍      | 1234/3598 [21:48<40:52,  1.04s/it]
 34%|███▍      | 1235/3598 [21:50<43:48,  1.11s/it]
 34%|███▍      | 1236/3598 [21:50<40:28,  1.03s/it]
 34%|███▍      | 1237/3598 [21:51<40:17,  1.02s/it]
 34%|███▍      | 1238/3598 [21:52<40:41,  1.03s/it]
 34%|███▍      | 1239/3598 [21:54<41:47,  1.06s/it]
 34%|███▍      | 1240/3598 [21:55<40:59,  1.04s/it]
                                                   

 34%|███▍      | 1240/3598 [21:55<40:59,  1.04s/it]
 34%|███▍      | 1241/3598 [21:55<39:39,  1.01s/it]
 35%|███▍      | 1242/3598 [21:57<43:16,  1.10s/it]
 35%|███▍      | 1243/3598 [21:58<41:41,  1.06s/it]
 35%|███▍      | 1244/3598 [21:59<40:05,  1.02s/it]
 35%|███▍      | 1245/3598 [21:59<37:28,  1.05it/s]
 35%|███▍      | 1246/3598 [22:01<40:49,  1.04s/it]
 35%|███▍      | 1247/3598 [22:02<40:56,  1.05s/it]
 35%|███▍      | 1248/3598 [22:03<40:07,  1.02s/it]
 35%|███▍      | 1249/3598 [22:04<42:21,  1.08s/it]
 35%|███▍      | 1250/3598 [22:05<40:44,  1.04s/it]
                                                   

 35%|███▍      | 1250/3598 [22:05<40:44,  1.04s/it]
 35%|███▍      | 1251/3598 [22:06<43:14,  1.11s/it]
 35%|███▍      | 1252/3598 [22:08<46:30,  1.19s/it]
 35%|███▍      | 1253/3598 [22:09<46:24,  1.19s/it]
 35%|███▍      | 1254/3598 [22:10<42:21,  1.08s/it]
 35%|███▍      | 1255/3598 [22:11<40:36,  1.04s/it]
 35%|███▍      | 1256/3598 [22:12<40:02,  1.03s/it]
 35%|███▍      | 1257/3598 [22:13<42:09,  1.08s/it]
 35%|███▍      | 1258/3598 [22:14<44:51,  1.15s/it]
 35%|███▍      | 1259/3598 [22:15<43:12,  1.11s/it]
 35%|███▌      | 1260/3598 [22:16<41:16,  1.06s/it]
                                                   

 35%|███▌      | 1260/3598 [22:16<41:16,  1.06s/it]
 35%|███▌      | 1261/3598 [22:17<40:11,  1.03s/it]
 35%|███▌      | 1262/3598 [22:18<39:43,  1.02s/it]
 35%|███▌      | 1263/3598 [22:19<38:35,  1.01it/s]
 35%|███▌      | 1264/3598 [22:20<40:42,  1.05s/it]
 35%|███▌      | 1265/3598 [22:21<38:20,  1.01it/s]
 35%|███▌      | 1266/3598 [22:22<39:26,  1.01s/it]
 35%|███▌      | 1267/3598 [22:23<38:26,  1.01it/s]
 35%|███▌      | 1268/3598 [22:24<43:04,  1.11s/it]
 35%|███▌      | 1269/3598 [22:25<40:41,  1.05s/it]
 35%|███▌      | 1270/3598 [22:26<38:59,  1.01s/it]
                                                   

 35%|███▌      | 1270/3598 [22:26<38:59,  1.01s/it]
 35%|███▌      | 1271/3598 [22:27<39:22,  1.02s/it]
 35%|███▌      | 1272/3598 [22:28<38:16,  1.01it/s]
 35%|███▌      | 1273/3598 [22:29<36:31,  1.06it/s]
 35%|███▌      | 1274/3598 [22:30<36:54,  1.05it/s]
 35%|███▌      | 1275/3598 [22:31<36:54,  1.05it/s]
 35%|███▌      | 1276/3598 [22:32<36:58,  1.05it/s]
 35%|███▌      | 1277/3598 [22:33<36:43,  1.05it/s]
 36%|███▌      | 1278/3598 [22:34<37:12,  1.04it/s]
 36%|███▌      | 1279/3598 [22:35<37:13,  1.04it/s]
 36%|███▌      | 1280/3598 [22:36<39:31,  1.02s/it]
                                                   

 36%|███▌      | 1280/3598 [22:36<39:31,  1.02s/it]
 36%|███▌      | 1281/3598 [22:37<38:51,  1.01s/it]
 36%|███▌      | 1282/3598 [22:38<42:28,  1.10s/it]
 36%|███▌      | 1283/3598 [22:39<39:45,  1.03s/it]
 36%|███▌      | 1284/3598 [22:40<39:04,  1.01s/it]
 36%|███▌      | 1285/3598 [22:41<37:17,  1.03it/s]
 36%|███▌      | 1286/3598 [22:42<35:59,  1.07it/s]
 36%|███▌      | 1287/3598 [22:43<38:07,  1.01it/s]
 36%|███▌      | 1288/3598 [22:44<38:36,  1.00s/it]
 36%|███▌      | 1289/3598 [22:45<41:56,  1.09s/it]
 36%|███▌      | 1290/3598 [22:46<44:15,  1.15s/it]
                                                   

 36%|███▌      | 1290/3598 [22:46<44:15,  1.15s/it]
 36%|███▌      | 1291/3598 [22:47<41:47,  1.09s/it]
 36%|███▌      | 1292/3598 [22:48<40:09,  1.05s/it]
 36%|███▌      | 1293/3598 [22:50<43:42,  1.14s/it]
 36%|███▌      | 1294/3598 [22:51<43:28,  1.13s/it]
 36%|███▌      | 1295/3598 [22:52<43:37,  1.14s/it]
 36%|███▌      | 1296/3598 [22:53<46:08,  1.20s/it]
 36%|███▌      | 1297/3598 [22:54<43:13,  1.13s/it]
 36%|███▌      | 1298/3598 [22:55<40:38,  1.06s/it]
 36%|███▌      | 1299/3598 [22:57<44:03,  1.15s/it]
 36%|███▌      | 1300/3598 [22:57<40:09,  1.05s/it]
                                                   

 36%|███▌      | 1300/3598 [22:57<40:09,  1.05s/it]
 36%|███▌      | 1301/3598 [22:58<39:08,  1.02s/it]
 36%|███▌      | 1302/3598 [22:59<37:01,  1.03it/s]
 36%|███▌      | 1303/3598 [23:00<41:24,  1.08s/it]
 36%|███▌      | 1304/3598 [23:01<39:19,  1.03s/it]
 36%|███▋      | 1305/3598 [23:02<38:45,  1.01s/it]
 36%|███▋      | 1306/3598 [23:03<37:52,  1.01it/s]
 36%|███▋      | 1307/3598 [23:04<37:29,  1.02it/s]
 36%|███▋      | 1308/3598 [23:05<36:47,  1.04it/s]
 36%|███▋      | 1309/3598 [23:06<35:45,  1.07it/s]
 36%|███▋      | 1310/3598 [23:07<41:23,  1.09s/it]
                                                   

 36%|███▋      | 1310/3598 [23:07<41:23,  1.09s/it]
 36%|███▋      | 1311/3598 [23:08<39:03,  1.02s/it]
 36%|███▋      | 1312/3598 [23:10<43:25,  1.14s/it]
 36%|███▋      | 1313/3598 [23:11<42:00,  1.10s/it]
 37%|███▋      | 1314/3598 [23:12<39:56,  1.05s/it]
 37%|███▋      | 1315/3598 [23:13<43:57,  1.16s/it]
 37%|███▋      | 1316/3598 [23:15<46:39,  1.23s/it]
 37%|███▋      | 1317/3598 [23:16<45:01,  1.18s/it]
 37%|███▋      | 1318/3598 [23:17<44:29,  1.17s/it]
 37%|███▋      | 1319/3598 [23:18<47:30,  1.25s/it]
 37%|███▋      | 1320/3598 [23:19<44:12,  1.16s/it]
                                                   

 37%|███▋      | 1320/3598 [23:19<44:12,  1.16s/it]
 37%|███▋      | 1321/3598 [23:20<41:05,  1.08s/it]
 37%|███▋      | 1322/3598 [23:21<39:07,  1.03s/it]
 37%|███▋      | 1323/3598 [23:22<37:48,  1.00it/s]
 37%|███▋      | 1324/3598 [23:23<37:36,  1.01it/s]
 37%|███▋      | 1325/3598 [23:24<37:02,  1.02it/s]
 37%|███▋      | 1326/3598 [23:25<39:05,  1.03s/it]
 37%|███▋      | 1327/3598 [23:26<37:46,  1.00it/s]
 37%|███▋      | 1328/3598 [23:27<39:58,  1.06s/it]
 37%|███▋      | 1329/3598 [23:28<39:16,  1.04s/it]
 37%|███▋      | 1330/3598 [23:29<37:38,  1.00it/s]
                                                   

 37%|███▋      | 1330/3598 [23:29<37:38,  1.00it/s]
 37%|███▋      | 1331/3598 [23:30<36:49,  1.03it/s]
 37%|███▋      | 1332/3598 [23:31<36:35,  1.03it/s]
 37%|███▋      | 1333/3598 [23:32<37:08,  1.02it/s]
 37%|███▋      | 1334/3598 [23:33<37:11,  1.01it/s]
 37%|███▋      | 1335/3598 [23:34<36:36,  1.03it/s]
 37%|███▋      | 1336/3598 [23:35<35:58,  1.05it/s]
 37%|███▋      | 1337/3598 [23:36<39:54,  1.06s/it]
 37%|███▋      | 1338/3598 [23:37<43:58,  1.17s/it]
 37%|███▋      | 1339/3598 [23:39<44:34,  1.18s/it]
 37%|███▋      | 1340/3598 [23:40<46:53,  1.25s/it]
                                                   

 37%|███▋      | 1340/3598 [23:40<46:53,  1.25s/it]
 37%|███▋      | 1341/3598 [23:41<44:01,  1.17s/it]
 37%|███▋      | 1342/3598 [23:42<41:04,  1.09s/it]
 37%|███▋      | 1343/3598 [23:43<43:42,  1.16s/it]
 37%|███▋      | 1344/3598 [23:44<40:18,  1.07s/it]
 37%|███▋      | 1345/3598 [23:45<38:33,  1.03s/it]
 37%|███▋      | 1346/3598 [23:46<36:29,  1.03it/s]
 37%|███▋      | 1347/3598 [23:47<36:25,  1.03it/s]
 37%|███▋      | 1348/3598 [23:48<39:15,  1.05s/it]
 37%|███▋      | 1349/3598 [23:49<42:51,  1.14s/it]
 38%|███▊      | 1350/3598 [23:50<39:54,  1.07s/it]
                                                   

 38%|███▊      | 1350/3598 [23:50<39:54,  1.07s/it]
 38%|███▊      | 1351/3598 [23:52<45:28,  1.21s/it]
 38%|███▊      | 1352/3598 [23:53<41:40,  1.11s/it]
 38%|███▊      | 1353/3598 [23:54<39:05,  1.04s/it]
 38%|███▊      | 1354/3598 [23:55<37:47,  1.01s/it]
 38%|███▊      | 1355/3598 [23:55<36:08,  1.03it/s]
 38%|███▊      | 1356/3598 [23:56<35:00,  1.07it/s]
 38%|███▊      | 1357/3598 [23:57<34:27,  1.08it/s]
 38%|███▊      | 1358/3598 [23:58<35:12,  1.06it/s]
 38%|███▊      | 1359/3598 [23:59<36:47,  1.01it/s]
 38%|███▊      | 1360/3598 [24:00<36:37,  1.02it/s]
                                                   

 38%|███▊      | 1360/3598 [24:00<36:37,  1.02it/s]
 38%|███▊      | 1361/3598 [24:01<35:24,  1.05it/s]
 38%|███▊      | 1362/3598 [24:02<36:10,  1.03it/s]
 38%|███▊      | 1363/3598 [24:03<39:01,  1.05s/it]
 38%|███▊      | 1364/3598 [24:04<37:39,  1.01s/it]
 38%|███▊      | 1365/3598 [24:05<37:34,  1.01s/it]
 38%|███▊      | 1366/3598 [24:06<36:29,  1.02it/s]
 38%|███▊      | 1367/3598 [24:07<37:30,  1.01s/it]
 38%|███▊      | 1368/3598 [24:09<41:35,  1.12s/it]
 38%|███▊      | 1369/3598 [24:10<39:34,  1.07s/it]
 38%|███▊      | 1370/3598 [24:11<40:12,  1.08s/it]
                                                   

 38%|███▊      | 1370/3598 [24:11<40:12,  1.08s/it]
 38%|███▊      | 1371/3598 [24:12<38:19,  1.03s/it]
 38%|███▊      | 1372/3598 [24:12<36:14,  1.02it/s]
 38%|███▊      | 1373/3598 [24:14<38:07,  1.03s/it]
 38%|███▊      | 1374/3598 [24:15<38:14,  1.03s/it]
 38%|███▊      | 1375/3598 [24:16<36:32,  1.01it/s]
 38%|███▊      | 1376/3598 [24:17<36:45,  1.01it/s]
 38%|███▊      | 1377/3598 [24:18<41:02,  1.11s/it]
 38%|███▊      | 1378/3598 [24:19<37:46,  1.02s/it]
 38%|███▊      | 1379/3598 [24:20<39:20,  1.06s/it]
 38%|███▊      | 1380/3598 [24:21<37:36,  1.02s/it]
                                                   

 38%|███▊      | 1380/3598 [24:21<37:36,  1.02s/it]
 38%|███▊      | 1381/3598 [24:22<42:11,  1.14s/it]
 38%|███▊      | 1382/3598 [24:23<39:38,  1.07s/it]
 38%|███▊      | 1383/3598 [24:25<42:34,  1.15s/it]
 38%|███▊      | 1384/3598 [24:25<39:32,  1.07s/it]
 38%|███▊      | 1385/3598 [24:27<40:40,  1.10s/it]
 39%|███▊      | 1386/3598 [24:28<39:22,  1.07s/it]
 39%|███▊      | 1387/3598 [24:29<40:12,  1.09s/it]
 39%|███▊      | 1388/3598 [24:30<37:58,  1.03s/it]
 39%|███▊      | 1389/3598 [24:31<41:55,  1.14s/it]
 39%|███▊      | 1390/3598 [24:32<40:02,  1.09s/it]
                                                   

 39%|███▊      | 1390/3598 [24:32<40:02,  1.09s/it]
 39%|███▊      | 1391/3598 [24:33<37:56,  1.03s/it]
 39%|███▊      | 1392/3598 [24:34<37:49,  1.03s/it]
 39%|███▊      | 1393/3598 [24:35<39:53,  1.09s/it]
 39%|███▊      | 1394/3598 [24:36<38:54,  1.06s/it]
 39%|███▉      | 1395/3598 [24:37<37:32,  1.02s/it]
 39%|███▉      | 1396/3598 [24:38<35:15,  1.04it/s]
 39%|███▉      | 1397/3598 [24:39<39:15,  1.07s/it]
 39%|███▉      | 1398/3598 [24:40<37:30,  1.02s/it]
 39%|███▉      | 1399/3598 [24:41<38:01,  1.04s/it]
 39%|███▉      | 1400/3598 [24:42<36:54,  1.01s/it]
                                                   

 39%|███▉      | 1400/3598 [24:42<36:54,  1.01s/it]
 39%|███▉      | 1401/3598 [24:43<35:03,  1.04it/s]
 39%|███▉      | 1402/3598 [24:44<35:21,  1.03it/s]
 39%|███▉      | 1403/3598 [24:45<34:22,  1.06it/s]
 39%|███▉      | 1404/3598 [24:46<35:08,  1.04it/s]
 39%|███▉      | 1405/3598 [24:47<36:37,  1.00s/it]
 39%|███▉      | 1406/3598 [24:48<35:43,  1.02it/s]
 39%|███▉      | 1407/3598 [24:49<35:35,  1.03it/s]
 39%|███▉      | 1408/3598 [24:50<34:52,  1.05it/s]
 39%|███▉      | 1409/3598 [24:51<35:15,  1.03it/s]
 39%|███▉      | 1410/3598 [24:52<35:32,  1.03it/s]
                                                   

 39%|███▉      | 1410/3598 [24:52<35:32,  1.03it/s]
 39%|███▉      | 1411/3598 [24:53<34:47,  1.05it/s]
 39%|███▉      | 1412/3598 [24:54<37:41,  1.03s/it]
 39%|███▉      | 1413/3598 [24:55<36:35,  1.00s/it]
 39%|███▉      | 1414/3598 [24:56<40:11,  1.10s/it]
 39%|███▉      | 1415/3598 [24:57<38:15,  1.05s/it]
 39%|███▉      | 1416/3598 [24:58<36:34,  1.01s/it]
 39%|███▉      | 1417/3598 [24:59<35:43,  1.02it/s]
 39%|███▉      | 1418/3598 [25:00<34:24,  1.06it/s]
 39%|███▉      | 1419/3598 [25:01<33:02,  1.10it/s]
 39%|███▉      | 1420/3598 [25:02<33:29,  1.08it/s]
                                                   

 39%|███▉      | 1420/3598 [25:02<33:29,  1.08it/s]
 39%|███▉      | 1421/3598 [25:03<37:54,  1.04s/it]
 40%|███▉      | 1422/3598 [25:04<40:03,  1.10s/it]
 40%|███▉      | 1423/3598 [25:05<41:28,  1.14s/it]
 40%|███▉      | 1424/3598 [25:07<43:00,  1.19s/it]
 40%|███▉      | 1425/3598 [25:08<40:44,  1.12s/it]
 40%|███▉      | 1426/3598 [25:09<43:16,  1.20s/it]
 40%|███▉      | 1427/3598 [25:10<41:33,  1.15s/it]
 40%|███▉      | 1428/3598 [25:11<40:15,  1.11s/it]
 40%|███▉      | 1429/3598 [25:12<39:38,  1.10s/it]
 40%|███▉      | 1430/3598 [25:13<40:50,  1.13s/it]
                                                   

 40%|███▉      | 1430/3598 [25:13<40:50,  1.13s/it]
 40%|███▉      | 1431/3598 [25:14<38:43,  1.07s/it]
 40%|███▉      | 1432/3598 [25:15<39:01,  1.08s/it]
 40%|███▉      | 1433/3598 [25:16<38:22,  1.06s/it]
 40%|███▉      | 1434/3598 [25:17<37:33,  1.04s/it]
 40%|███▉      | 1435/3598 [25:18<36:22,  1.01s/it]
 40%|███▉      | 1436/3598 [25:19<36:31,  1.01s/it]
 40%|███▉      | 1437/3598 [25:20<36:08,  1.00s/it]
 40%|███▉      | 1438/3598 [25:21<36:27,  1.01s/it]
 40%|███▉      | 1439/3598 [25:22<35:49,  1.00it/s]
 40%|████      | 1440/3598 [25:23<35:34,  1.01it/s]
                                                   

 40%|████      | 1440/3598 [25:23<35:34,  1.01it/s]
 40%|████      | 1441/3598 [25:24<34:43,  1.04it/s]
 40%|████      | 1442/3598 [25:25<35:51,  1.00it/s]
 40%|████      | 1443/3598 [25:26<37:30,  1.04s/it]
 40%|████      | 1444/3598 [25:27<36:21,  1.01s/it]
 40%|████      | 1445/3598 [25:28<37:28,  1.04s/it]
 40%|████      | 1446/3598 [25:29<36:09,  1.01s/it]
 40%|████      | 1447/3598 [25:30<34:50,  1.03it/s]
 40%|████      | 1448/3598 [25:31<33:54,  1.06it/s]
 40%|████      | 1449/3598 [25:32<33:59,  1.05it/s]
 40%|████      | 1450/3598 [25:33<33:10,  1.08it/s]
                                                   

 40%|████      | 1450/3598 [25:33<33:10,  1.08it/s]
 40%|████      | 1451/3598 [25:34<37:48,  1.06s/it]
 40%|████      | 1452/3598 [25:35<36:30,  1.02s/it]
 40%|████      | 1453/3598 [25:36<34:01,  1.05it/s]
 40%|████      | 1454/3598 [25:37<34:40,  1.03it/s]
 40%|████      | 1455/3598 [25:38<35:20,  1.01it/s]
 40%|████      | 1456/3598 [25:39<34:54,  1.02it/s]
 40%|████      | 1457/3598 [25:40<33:58,  1.05it/s]
 41%|████      | 1458/3598 [25:41<37:27,  1.05s/it]
 41%|████      | 1459/3598 [25:42<35:29,  1.00it/s]
 41%|████      | 1460/3598 [25:43<38:42,  1.09s/it]
                                                   

 41%|████      | 1460/3598 [25:43<38:42,  1.09s/it]
 41%|████      | 1461/3598 [25:44<38:38,  1.08s/it]
 41%|████      | 1462/3598 [25:45<37:45,  1.06s/it]
 41%|████      | 1463/3598 [25:47<41:05,  1.16s/it]
 41%|████      | 1464/3598 [25:48<42:54,  1.21s/it]
 41%|████      | 1465/3598 [25:50<45:00,  1.27s/it]
 41%|████      | 1466/3598 [25:50<41:16,  1.16s/it]
 41%|████      | 1467/3598 [25:51<38:09,  1.07s/it]
 41%|████      | 1468/3598 [25:52<37:04,  1.04s/it]
 41%|████      | 1469/3598 [25:54<40:09,  1.13s/it]
 41%|████      | 1470/3598 [25:55<37:43,  1.06s/it]
                                                   

 41%|████      | 1470/3598 [25:55<37:43,  1.06s/it]
 41%|████      | 1471/3598 [25:55<36:08,  1.02s/it]
 41%|████      | 1472/3598 [25:56<34:32,  1.03it/s]
 41%|████      | 1473/3598 [25:57<34:32,  1.03it/s]
 41%|████      | 1474/3598 [25:59<37:18,  1.05s/it]
 41%|████      | 1475/3598 [26:00<36:12,  1.02s/it]
 41%|████      | 1476/3598 [26:01<38:36,  1.09s/it]
 41%|████      | 1477/3598 [26:02<40:55,  1.16s/it]
 41%|████      | 1478/3598 [26:03<37:00,  1.05s/it]
 41%|████      | 1479/3598 [26:04<35:50,  1.01s/it]
 41%|████      | 1480/3598 [26:05<34:25,  1.03it/s]
                                                   

 41%|████      | 1480/3598 [26:05<34:25,  1.03it/s]
 41%|████      | 1481/3598 [26:06<37:13,  1.06s/it]
 41%|████      | 1482/3598 [26:07<35:21,  1.00s/it]
 41%|████      | 1483/3598 [26:08<33:59,  1.04it/s]
 41%|████      | 1484/3598 [26:09<38:11,  1.08s/it]
 41%|████▏     | 1485/3598 [26:10<41:16,  1.17s/it]
 41%|████▏     | 1486/3598 [26:11<37:54,  1.08s/it]
 41%|████▏     | 1487/3598 [26:12<36:03,  1.02s/it]
 41%|████▏     | 1488/3598 [26:13<35:16,  1.00s/it]
 41%|████▏     | 1489/3598 [26:14<36:07,  1.03s/it]
 41%|████▏     | 1490/3598 [26:15<33:56,  1.04it/s]
                                                   

 41%|████▏     | 1490/3598 [26:15<33:56,  1.04it/s]
 41%|████▏     | 1491/3598 [26:16<36:41,  1.04s/it]
 41%|████▏     | 1492/3598 [26:17<34:27,  1.02it/s]
 41%|████▏     | 1493/3598 [26:18<34:32,  1.02it/s]
 42%|████▏     | 1494/3598 [26:19<37:12,  1.06s/it]
 42%|████▏     | 1495/3598 [26:20<36:52,  1.05s/it]
 42%|████▏     | 1496/3598 [26:21<33:56,  1.03it/s]
 42%|████▏     | 1497/3598 [26:22<33:58,  1.03it/s]
 42%|████▏     | 1498/3598 [26:23<32:37,  1.07it/s]
 42%|████▏     | 1499/3598 [26:24<33:17,  1.05it/s]
 42%|████▏     | 1500/3598 [26:25<33:26,  1.05it/s]
                                                   

 42%|████▏     | 1500/3598 [26:25<33:26,  1.05it/s]
 42%|████▏     | 1501/3598 [26:26<34:26,  1.01it/s]
 42%|████▏     | 1502/3598 [26:27<35:48,  1.03s/it]
 42%|████▏     | 1503/3598 [26:28<34:29,  1.01it/s]
 42%|████▏     | 1504/3598 [26:29<33:48,  1.03it/s]
 42%|████▏     | 1505/3598 [26:30<37:46,  1.08s/it]
 42%|████▏     | 1506/3598 [26:31<35:35,  1.02s/it]
 42%|████▏     | 1507/3598 [26:32<34:38,  1.01it/s]
 42%|████▏     | 1508/3598 [26:33<37:11,  1.07s/it]
 42%|████▏     | 1509/3598 [26:35<40:29,  1.16s/it]
 42%|████▏     | 1510/3598 [26:36<38:51,  1.12s/it]
                                                   

 42%|████▏     | 1510/3598 [26:36<38:51,  1.12s/it]
 42%|████▏     | 1511/3598 [26:37<40:11,  1.16s/it]
 42%|████▏     | 1512/3598 [26:38<40:17,  1.16s/it]
 42%|████▏     | 1513/3598 [26:39<37:59,  1.09s/it]
 42%|████▏     | 1514/3598 [26:40<39:01,  1.12s/it]
 42%|████▏     | 1515/3598 [26:42<40:58,  1.18s/it]
 42%|████▏     | 1516/3598 [26:42<38:02,  1.10s/it]
 42%|████▏     | 1517/3598 [26:44<40:04,  1.16s/it]
 42%|████▏     | 1518/3598 [26:45<40:22,  1.16s/it]
 42%|████▏     | 1519/3598 [26:46<37:41,  1.09s/it]
 42%|████▏     | 1520/3598 [26:47<37:25,  1.08s/it]
                                                   

 42%|████▏     | 1520/3598 [26:47<37:25,  1.08s/it]
 42%|████▏     | 1521/3598 [26:48<34:59,  1.01s/it]
 42%|████▏     | 1522/3598 [26:49<36:35,  1.06s/it]
 42%|████▏     | 1523/3598 [26:50<38:36,  1.12s/it]
 42%|████▏     | 1524/3598 [26:51<35:36,  1.03s/it]
 42%|████▏     | 1525/3598 [26:52<38:26,  1.11s/it]
 42%|████▏     | 1526/3598 [26:53<35:29,  1.03s/it]
 42%|████▏     | 1527/3598 [26:54<33:59,  1.02it/s]
 42%|████▏     | 1528/3598 [26:55<32:33,  1.06it/s]
 42%|████▏     | 1529/3598 [26:56<33:29,  1.03it/s]
 43%|████▎     | 1530/3598 [26:57<34:35,  1.00s/it]
                                                   

 43%|████▎     | 1530/3598 [26:57<34:35,  1.00s/it]
 43%|████▎     | 1531/3598 [26:58<37:49,  1.10s/it]
 43%|████▎     | 1532/3598 [26:59<35:56,  1.04s/it]
 43%|████▎     | 1533/3598 [27:01<38:46,  1.13s/it]
 43%|████▎     | 1534/3598 [27:02<37:27,  1.09s/it]
 43%|████▎     | 1535/3598 [27:03<39:25,  1.15s/it]
 43%|████▎     | 1536/3598 [27:04<37:19,  1.09s/it]
 43%|████▎     | 1537/3598 [27:05<38:11,  1.11s/it]
 43%|████▎     | 1538/3598 [27:06<35:44,  1.04s/it]
 43%|████▎     | 1539/3598 [27:07<33:35,  1.02it/s]
 43%|████▎     | 1540/3598 [27:08<32:58,  1.04it/s]
                                                   

 43%|████▎     | 1540/3598 [27:08<32:58,  1.04it/s]
 43%|████▎     | 1541/3598 [27:08<32:15,  1.06it/s]
 43%|████▎     | 1542/3598 [27:09<32:11,  1.06it/s]
 43%|████▎     | 1543/3598 [27:11<35:06,  1.03s/it]
 43%|████▎     | 1544/3598 [27:12<36:55,  1.08s/it]
 43%|████▎     | 1545/3598 [27:13<36:01,  1.05s/it]
 43%|████▎     | 1546/3598 [27:14<39:24,  1.15s/it]
 43%|████▎     | 1547/3598 [27:15<38:01,  1.11s/it]
 43%|████▎     | 1548/3598 [27:16<36:06,  1.06s/it]
 43%|████▎     | 1549/3598 [27:17<35:44,  1.05s/it]
 43%|████▎     | 1550/3598 [27:18<33:52,  1.01it/s]
                                                   

 43%|████▎     | 1550/3598 [27:18<33:52,  1.01it/s]
 43%|████▎     | 1551/3598 [27:19<33:21,  1.02it/s]
 43%|████▎     | 1552/3598 [27:20<34:03,  1.00it/s]
 43%|████▎     | 1553/3598 [27:21<37:52,  1.11s/it]
 43%|████▎     | 1554/3598 [27:22<35:20,  1.04s/it]
 43%|████▎     | 1555/3598 [27:23<34:38,  1.02s/it]
 43%|████▎     | 1556/3598 [27:24<32:29,  1.05it/s]
 43%|████▎     | 1557/3598 [27:25<36:50,  1.08s/it]
 43%|████▎     | 1558/3598 [27:26<34:35,  1.02s/it]
 43%|████▎     | 1559/3598 [27:27<33:47,  1.01it/s]
 43%|████▎     | 1560/3598 [27:28<32:32,  1.04it/s]
                                                   

 43%|████▎     | 1560/3598 [27:28<32:32,  1.04it/s]
 43%|████▎     | 1561/3598 [27:29<35:52,  1.06s/it]
 43%|████▎     | 1562/3598 [27:31<39:15,  1.16s/it]
 43%|████▎     | 1563/3598 [27:32<41:30,  1.22s/it]
 43%|████▎     | 1564/3598 [27:33<38:01,  1.12s/it]
 43%|████▎     | 1565/3598 [27:34<36:32,  1.08s/it]
 44%|████▎     | 1566/3598 [27:35<35:16,  1.04s/it]
 44%|████▎     | 1567/3598 [27:36<33:03,  1.02it/s]
 44%|████▎     | 1568/3598 [27:37<36:22,  1.07s/it]
 44%|████▎     | 1569/3598 [27:38<37:28,  1.11s/it]
 44%|████▎     | 1570/3598 [27:39<35:46,  1.06s/it]
                                                   

 44%|████▎     | 1570/3598 [27:39<35:46,  1.06s/it]
 44%|████▎     | 1571/3598 [27:41<38:28,  1.14s/it]
 44%|████▎     | 1572/3598 [27:42<39:22,  1.17s/it]
 44%|████▎     | 1573/3598 [27:43<37:15,  1.10s/it]
 44%|████▎     | 1574/3598 [27:44<35:56,  1.07s/it]
 44%|████▍     | 1575/3598 [27:45<38:33,  1.14s/it]
 44%|████▍     | 1576/3598 [27:46<36:02,  1.07s/it]
 44%|████▍     | 1577/3598 [27:47<37:03,  1.10s/it]
 44%|████▍     | 1578/3598 [27:48<34:53,  1.04s/it]
 44%|████▍     | 1579/3598 [27:49<34:52,  1.04s/it]
 44%|████▍     | 1580/3598 [27:50<33:51,  1.01s/it]
                                                   

 44%|████▍     | 1580/3598 [27:50<33:51,  1.01s/it]
 44%|████▍     | 1581/3598 [27:51<33:24,  1.01it/s]
 44%|████▍     | 1582/3598 [27:52<31:43,  1.06it/s]
 44%|████▍     | 1583/3598 [27:53<30:50,  1.09it/s]
 44%|████▍     | 1584/3598 [27:54<32:20,  1.04it/s]
 44%|████▍     | 1585/3598 [27:55<33:09,  1.01it/s]
 44%|████▍     | 1586/3598 [27:56<32:20,  1.04it/s]
 44%|████▍     | 1587/3598 [27:57<32:11,  1.04it/s]
 44%|████▍     | 1588/3598 [27:58<33:01,  1.01it/s]
 44%|████▍     | 1589/3598 [27:59<32:40,  1.02it/s]
 44%|████▍     | 1590/3598 [28:00<33:47,  1.01s/it]
                                                   

 44%|████▍     | 1590/3598 [28:00<33:47,  1.01s/it]
 44%|████▍     | 1591/3598 [28:01<33:37,  1.01s/it]
 44%|████▍     | 1592/3598 [28:02<32:31,  1.03it/s]
 44%|████▍     | 1593/3598 [28:03<35:25,  1.06s/it]
 44%|████▍     | 1594/3598 [28:04<37:19,  1.12s/it]
 44%|████▍     | 1595/3598 [28:05<34:51,  1.04s/it]
 44%|████▍     | 1596/3598 [28:06<33:39,  1.01s/it]
 44%|████▍     | 1597/3598 [28:07<34:26,  1.03s/it]
 44%|████▍     | 1598/3598 [28:08<35:47,  1.07s/it]
 44%|████▍     | 1599/3598 [28:09<33:32,  1.01s/it]
 44%|████▍     | 1600/3598 [28:10<35:50,  1.08s/it]
                                                   

 44%|████▍     | 1600/3598 [28:10<35:50,  1.08s/it]
 44%|████▍     | 1601/3598 [28:11<34:52,  1.05s/it]
 45%|████▍     | 1602/3598 [28:13<38:16,  1.15s/it]
 45%|████▍     | 1603/3598 [28:14<40:14,  1.21s/it]
 45%|████▍     | 1604/3598 [28:15<36:25,  1.10s/it]
 45%|████▍     | 1605/3598 [28:16<34:08,  1.03s/it]
 45%|████▍     | 1606/3598 [28:17<32:57,  1.01it/s]
 45%|████▍     | 1607/3598 [28:18<32:54,  1.01it/s]
 45%|████▍     | 1608/3598 [28:19<34:06,  1.03s/it]
 45%|████▍     | 1609/3598 [28:20<33:23,  1.01s/it]
 45%|████▍     | 1610/3598 [28:20<31:30,  1.05it/s]
                                                   

 45%|████▍     | 1610/3598 [28:20<31:30,  1.05it/s]
 45%|████▍     | 1611/3598 [28:21<32:08,  1.03it/s]
 45%|████▍     | 1612/3598 [28:23<34:43,  1.05s/it]
 45%|████▍     | 1613/3598 [28:24<36:16,  1.10s/it]
 45%|████▍     | 1614/3598 [28:25<35:55,  1.09s/it]
 45%|████▍     | 1615/3598 [28:26<34:12,  1.04s/it]
 45%|████▍     | 1616/3598 [28:27<33:09,  1.00s/it]
 45%|████▍     | 1617/3598 [28:28<35:43,  1.08s/it]
 45%|████▍     | 1618/3598 [28:29<34:03,  1.03s/it]
 45%|████▍     | 1619/3598 [28:30<34:49,  1.06s/it]
 45%|████▌     | 1620/3598 [28:31<33:23,  1.01s/it]
                                                   

 45%|████▌     | 1620/3598 [28:31<33:23,  1.01s/it]
 45%|████▌     | 1621/3598 [28:32<32:00,  1.03it/s]
 45%|████▌     | 1622/3598 [28:33<32:02,  1.03it/s]
 45%|████▌     | 1623/3598 [28:34<34:26,  1.05s/it]
 45%|████▌     | 1624/3598 [28:35<37:19,  1.13s/it]
 45%|████▌     | 1625/3598 [28:37<38:30,  1.17s/it]
 45%|████▌     | 1626/3598 [28:38<36:28,  1.11s/it]
 45%|████▌     | 1627/3598 [28:39<36:20,  1.11s/it]
 45%|████▌     | 1628/3598 [28:40<36:01,  1.10s/it]
 45%|████▌     | 1629/3598 [28:41<34:36,  1.05s/it]
 45%|████▌     | 1630/3598 [28:42<33:52,  1.03s/it]
                                                   

 45%|████▌     | 1630/3598 [28:42<33:52,  1.03s/it]
 45%|████▌     | 1631/3598 [28:43<32:31,  1.01it/s]
 45%|████▌     | 1632/3598 [28:44<35:01,  1.07s/it]
 45%|████▌     | 1633/3598 [28:45<37:24,  1.14s/it]
 45%|████▌     | 1634/3598 [28:46<35:33,  1.09s/it]
 45%|████▌     | 1635/3598 [28:47<33:02,  1.01s/it]
 45%|████▌     | 1636/3598 [28:48<33:39,  1.03s/it]
 45%|████▌     | 1637/3598 [28:49<31:52,  1.03it/s]
 46%|████▌     | 1638/3598 [28:50<35:09,  1.08s/it]
 46%|████▌     | 1639/3598 [28:51<36:27,  1.12s/it]
 46%|████▌     | 1640/3598 [28:52<34:06,  1.05s/it]
                                                   

 46%|████▌     | 1640/3598 [28:52<34:06,  1.05s/it]
 46%|████▌     | 1641/3598 [28:53<33:46,  1.04s/it]
 46%|████▌     | 1642/3598 [28:54<33:12,  1.02s/it]
 46%|████▌     | 1643/3598 [28:55<31:57,  1.02it/s]
 46%|████▌     | 1644/3598 [28:56<30:59,  1.05it/s]
 46%|████▌     | 1645/3598 [28:57<31:27,  1.03it/s]
 46%|████▌     | 1646/3598 [28:58<31:24,  1.04it/s]
 46%|████▌     | 1647/3598 [28:59<31:19,  1.04it/s]
 46%|████▌     | 1648/3598 [29:00<30:26,  1.07it/s]
 46%|████▌     | 1649/3598 [29:01<32:42,  1.01s/it]
 46%|████▌     | 1650/3598 [29:02<36:19,  1.12s/it]
                                                   

 46%|████▌     | 1650/3598 [29:02<36:19,  1.12s/it]
 46%|████▌     | 1651/3598 [29:03<33:41,  1.04s/it]
 46%|████▌     | 1652/3598 [29:04<32:18,  1.00it/s]
 46%|████▌     | 1653/3598 [29:05<30:54,  1.05it/s]
 46%|████▌     | 1654/3598 [29:06<30:38,  1.06it/s]
 46%|████▌     | 1655/3598 [29:07<30:16,  1.07it/s]
 46%|████▌     | 1656/3598 [29:08<35:01,  1.08s/it]
 46%|████▌     | 1657/3598 [29:09<33:35,  1.04s/it]
 46%|████▌     | 1658/3598 [29:10<31:47,  1.02it/s]
 46%|████▌     | 1659/3598 [29:11<31:22,  1.03it/s]
 46%|████▌     | 1660/3598 [29:12<34:58,  1.08s/it]
                                                   
{'eval_loss': 1.0395417213439941, 'eval_bleu': 31.364990029729668, 'eval_chrf': 58.3898577852921, 'eval_runtime': 42.676, 'eval_samples_per_second': 2.999, 'eval_steps_per_second': 0.094, 'epoch': 0.25}
{'loss': 1.1484, 'grad_norm': 1.428255558013916, 'learning_rate': 0.00015728496196606203, 'epoch': 0.25}
{'loss': 1.0764, 'grad_norm': 1.135252594947815, 'learning_rate': 0.00015669982445874783, 'epoch': 0.26}
{'loss': 1.2365, 'grad_norm': 1.3112901449203491, 'learning_rate': 0.0001561146869514336, 'epoch': 0.26}
{'loss': 1.1562, 'grad_norm': 1.7242013216018677, 'learning_rate': 0.00015552954944411936, 'epoch': 0.26}
{'loss': 1.1331, 'grad_norm': 1.1144850254058838, 'learning_rate': 0.00015494441193680515, 'epoch': 0.26}
{'loss': 1.1032, 'grad_norm': 1.4144283533096313, 'learning_rate': 0.00015435927442949095, 'epoch': 0.27}
{'loss': 1.1417, 'grad_norm': 1.3410099744796753, 'learning_rate': 0.00015377413692217672, 'epoch': 0.27}
{'loss': 1.1226, 'grad_norm': 1.7101255655288696, 'learning_rate': 0.0001531889994148625, 'epoch': 0.27}
{'loss': 1.0927, 'grad_norm': 1.9083212614059448, 'learning_rate': 0.00015260386190754828, 'epoch': 0.28}
{'loss': 1.1131, 'grad_norm': 1.3412920236587524, 'learning_rate': 0.00015201872440023405, 'epoch': 0.28}
{'loss': 1.0512, 'grad_norm': 1.5229618549346924, 'learning_rate': 0.00015143358689291984, 'epoch': 0.28}
{'loss': 0.9792, 'grad_norm': 1.5586941242218018, 'learning_rate': 0.00015084844938560564, 'epoch': 0.28}
{'loss': 1.0279, 'grad_norm': 1.6615018844604492, 'learning_rate': 0.0001502633118782914, 'epoch': 0.29}
{'loss': 1.0815, 'grad_norm': 1.12063729763031, 'learning_rate': 0.0001496781743709772, 'epoch': 0.29}
{'loss': 1.0282, 'grad_norm': 1.9666633605957031, 'learning_rate': 0.00014909303686366296, 'epoch': 0.29}
{'loss': 0.9798, 'grad_norm': 1.6202434301376343, 'learning_rate': 0.00014850789935634876, 'epoch': 0.29}
{'loss': 1.0827, 'grad_norm': 1.3234361410140991, 'learning_rate': 0.00014792276184903453, 'epoch': 0.3}
{'loss': 0.957, 'grad_norm': 1.2288326025009155, 'learning_rate': 0.00014733762434172032, 'epoch': 0.3}
{'loss': 0.8825, 'grad_norm': 1.2778434753417969, 'learning_rate': 0.0001467524868344061, 'epoch': 0.3}
{'loss': 1.1411, 'grad_norm': 1.1895047426223755, 'learning_rate': 0.00014616734932709186, 'epoch': 0.31}
{'loss': 1.0162, 'grad_norm': 1.9118584394454956, 'learning_rate': 0.00014558221181977765, 'epoch': 0.31}
{'loss': 1.0447, 'grad_norm': 1.5872502326965332, 'learning_rate': 0.00014499707431246344, 'epoch': 0.31}
{'loss': 1.0535, 'grad_norm': 1.7727245092391968, 'learning_rate': 0.0001444119368051492, 'epoch': 0.31}
{'loss': 1.0742, 'grad_norm': 1.2673349380493164, 'learning_rate': 0.000143826799297835, 'epoch': 0.32}
{'loss': 1.0535, 'grad_norm': 1.6242469549179077, 'learning_rate': 0.00014324166179052077, 'epoch': 0.32}
{'loss': 0.8432, 'grad_norm': 1.7397310733795166, 'learning_rate': 0.00014265652428320654, 'epoch': 0.32}
{'loss': 1.0957, 'grad_norm': 1.0805168151855469, 'learning_rate': 0.00014207138677589234, 'epoch': 0.33}
{'loss': 1.0128, 'grad_norm': 1.5562666654586792, 'learning_rate': 0.00014148624926857813, 'epoch': 0.33}
{'loss': 0.9449, 'grad_norm': 1.4101382493972778, 'learning_rate': 0.0001409011117612639, 'epoch': 0.33}
{'loss': 0.9858, 'grad_norm': 1.4961520433425903, 'learning_rate': 0.0001403159742539497, 'epoch': 0.33}
{'loss': 1.0111, 'grad_norm': 1.5171849727630615, 'learning_rate': 0.00013973083674663549, 'epoch': 0.34}
{'loss': 0.9343, 'grad_norm': 1.8383678197860718, 'learning_rate': 0.00013914569923932123, 'epoch': 0.34}
{'loss': 1.0233, 'grad_norm': 1.9662550687789917, 'learning_rate': 0.00013856056173200702, 'epoch': 0.34}
{'loss': 1.0285, 'grad_norm': 1.3497370481491089, 'learning_rate': 0.00013797542422469282, 'epoch': 0.34}
{'loss': 1.0515, 'grad_norm': 1.725982904434204, 'learning_rate': 0.00013739028671737858, 'epoch': 0.35}
{'loss': 1.0562, 'grad_norm': 1.6530572175979614, 'learning_rate': 0.00013680514921006438, 'epoch': 0.35}
{'loss': 0.9152, 'grad_norm': 1.6330093145370483, 'learning_rate': 0.00013622001170275017, 'epoch': 0.35}
{'loss': 0.9699, 'grad_norm': 1.0460683107376099, 'learning_rate': 0.0001356348741954359, 'epoch': 0.36}
{'loss': 0.9806, 'grad_norm': 1.5580418109893799, 'learning_rate': 0.0001350497366881217, 'epoch': 0.36}
{'loss': 1.007, 'grad_norm': 2.0592973232269287, 'learning_rate': 0.0001344645991808075, 'epoch': 0.36}
{'loss': 0.9665, 'grad_norm': 1.3635998964309692, 'learning_rate': 0.00013387946167349327, 'epoch': 0.36}
{'loss': 1.1398, 'grad_norm': 1.568021297454834, 'learning_rate': 0.00013329432416617906, 'epoch': 0.37}
{'loss': 0.9148, 'grad_norm': 2.066228151321411, 'learning_rate': 0.00013270918665886486, 'epoch': 0.37}
{'loss': 0.9977, 'grad_norm': 1.1922526359558105, 'learning_rate': 0.0001321240491515506, 'epoch': 0.37}
{'loss': 0.8754, 'grad_norm': 2.051551103591919, 'learning_rate': 0.0001315389116442364, 'epoch': 0.38}
{'loss': 0.9025, 'grad_norm': 1.1191948652267456, 'learning_rate': 0.0001309537741369222, 'epoch': 0.38}
{'loss': 0.9634, 'grad_norm': 1.243485927581787, 'learning_rate': 0.00013036863662960795, 'epoch': 0.38}
{'loss': 0.8412, 'grad_norm': 1.4225202798843384, 'learning_rate': 0.00012978349912229375, 'epoch': 0.38}
{'loss': 1.0081, 'grad_norm': 1.2499719858169556, 'learning_rate': 0.00012919836161497954, 'epoch': 0.39}
{'loss': 0.9025, 'grad_norm': 1.6100412607192993, 'learning_rate': 0.0001286132241076653, 'epoch': 0.39}
{'loss': 0.8203, 'grad_norm': 1.9911744594573975, 'learning_rate': 0.00012802808660035108, 'epoch': 0.39}
{'loss': 0.8276, 'grad_norm': 1.4758795499801636, 'learning_rate': 0.00012744294909303687, 'epoch': 0.39}
{'loss': 1.0634, 'grad_norm': 1.4166537523269653, 'learning_rate': 0.00012685781158572264, 'epoch': 0.4}
{'loss': 0.866, 'grad_norm': 1.478798508644104, 'learning_rate': 0.00012627267407840843, 'epoch': 0.4}
{'loss': 0.8046, 'grad_norm': 1.518876552581787, 'learning_rate': 0.00012568753657109423, 'epoch': 0.4}
{'loss': 0.9057, 'grad_norm': 1.5666396617889404, 'learning_rate': 0.00012510239906378, 'epoch': 0.41}
{'loss': 0.9224, 'grad_norm': 1.593050241470337, 'learning_rate': 0.00012451726155646576, 'epoch': 0.41}
{'loss': 0.8986, 'grad_norm': 2.082044839859009, 'learning_rate': 0.00012393212404915156, 'epoch': 0.41}
{'loss': 0.888, 'grad_norm': 2.0891640186309814, 'learning_rate': 0.00012334698654183735, 'epoch': 0.41}
{'loss': 0.8905, 'grad_norm': 1.358191967010498, 'learning_rate': 0.00012276184903452312, 'epoch': 0.42}
{'loss': 0.8238, 'grad_norm': 1.4863574504852295, 'learning_rate': 0.00012217671152720891, 'epoch': 0.42}
{'loss': 0.9423, 'grad_norm': 1.2066727876663208, 'learning_rate': 0.00012159157401989467, 'epoch': 0.42}
{'loss': 0.7907, 'grad_norm': 1.4324455261230469, 'learning_rate': 0.00012100643651258046, 'epoch': 0.43}
{'loss': 0.9682, 'grad_norm': 1.3111741542816162, 'learning_rate': 0.00012042129900526624, 'epoch': 0.43}
{'loss': 0.875, 'grad_norm': 2.182124376296997, 'learning_rate': 0.00011983616149795202, 'epoch': 0.43}
{'loss': 0.8221, 'grad_norm': 1.8315985202789307, 'learning_rate': 0.0001192510239906378, 'epoch': 0.43}
{'loss': 0.9896, 'grad_norm': 1.3867039680480957, 'learning_rate': 0.0001186658864833236, 'epoch': 0.44}
{'loss': 0.9384, 'grad_norm': 1.614179253578186, 'learning_rate': 0.00011808074897600935, 'epoch': 0.44}
{'loss': 0.7823, 'grad_norm': 1.388555884361267, 'learning_rate': 0.00011749561146869515, 'epoch': 0.44}
{'loss': 0.7731, 'grad_norm': 1.1316096782684326, 'learning_rate': 0.00011691047396138093, 'epoch': 0.44}
{'loss': 0.7917, 'grad_norm': 1.9281110763549805, 'learning_rate': 0.00011632533645406671, 'epoch': 0.45}
{'loss': 0.935, 'grad_norm': 1.7171776294708252, 'learning_rate': 0.0001157401989467525, 'epoch': 0.45}
{'loss': 0.9694, 'grad_norm': 1.5820637941360474, 'learning_rate': 0.00011515506143943829, 'epoch': 0.45}
{'loss': 0.8795, 'grad_norm': 1.323703646659851, 'learning_rate': 0.00011456992393212404, 'epoch': 0.46}
{'loss': 0.7887, 'grad_norm': 1.4957565069198608, 'learning_rate': 0.00011398478642480983, 'epoch': 0.46}
{'loss': 0.8062, 'grad_norm': 1.8945534229278564, 'learning_rate': 0.00011339964891749561, 'epoch': 0.46}
 46%|████▌     | 1660/3598 [29:12<34:58,  1.08s/it]
 46%|████▌     | 1661/3598 [29:13<34:15,  1.06s/it]
 46%|████▌     | 1662/3598 [29:14<32:48,  1.02s/it]
 46%|████▌     | 1663/3598 [29:15<31:00,  1.04it/s]
 46%|████▌     | 1664/3598 [29:16<30:34,  1.05it/s]
 46%|████▋     | 1665/3598 [29:17<29:27,  1.09it/s]
 46%|████▋     | 1666/3598 [29:18<28:41,  1.12it/s]
 46%|████▋     | 1667/3598 [29:19<32:00,  1.01it/s]
 46%|████▋     | 1668/3598 [29:20<31:35,  1.02it/s]
 46%|████▋     | 1669/3598 [29:21<30:37,  1.05it/s]
 46%|████▋     | 1670/3598 [29:22<33:18,  1.04s/it]
                                                   

 46%|████▋     | 1670/3598 [29:22<33:18,  1.04s/it]
 46%|████▋     | 1671/3598 [29:23<32:53,  1.02s/it]
 46%|████▋     | 1672/3598 [29:24<32:27,  1.01s/it]
 46%|████▋     | 1673/3598 [29:25<31:10,  1.03it/s]
 47%|████▋     | 1674/3598 [29:26<30:09,  1.06it/s]
 47%|████▋     | 1675/3598 [29:27<31:04,  1.03it/s]
 47%|████▋     | 1676/3598 [29:28<33:57,  1.06s/it]
 47%|████▋     | 1677/3598 [29:29<32:34,  1.02s/it]
 47%|████▋     | 1678/3598 [29:30<34:38,  1.08s/it]
 47%|████▋     | 1679/3598 [29:31<33:02,  1.03s/it]
 47%|████▋     | 1680/3598 [29:32<34:48,  1.09s/it]
                                                   

 47%|████▋     | 1680/3598 [29:32<34:48,  1.09s/it]
 47%|████▋     | 1681/3598 [29:33<32:43,  1.02s/it]
 47%|████▋     | 1682/3598 [29:34<30:15,  1.06it/s]
 47%|████▋     | 1683/3598 [29:35<29:41,  1.08it/s]
 47%|████▋     | 1684/3598 [29:36<29:06,  1.10it/s]
 47%|████▋     | 1685/3598 [29:37<28:56,  1.10it/s]
 47%|████▋     | 1686/3598 [29:38<29:38,  1.08it/s]
 47%|████▋     | 1687/3598 [29:39<30:33,  1.04it/s]
 47%|████▋     | 1688/3598 [29:40<33:36,  1.06s/it]
 47%|████▋     | 1689/3598 [29:41<36:12,  1.14s/it]
 47%|████▋     | 1690/3598 [29:43<38:20,  1.21s/it]
                                                   

 47%|████▋     | 1690/3598 [29:43<38:20,  1.21s/it]
 47%|████▋     | 1691/3598 [29:44<35:15,  1.11s/it]
 47%|████▋     | 1692/3598 [29:45<33:41,  1.06s/it]
 47%|████▋     | 1693/3598 [29:45<32:09,  1.01s/it]
 47%|████▋     | 1694/3598 [29:46<31:38,  1.00it/s]
 47%|████▋     | 1695/3598 [29:48<34:58,  1.10s/it]
 47%|████▋     | 1696/3598 [29:49<32:38,  1.03s/it]
 47%|████▋     | 1697/3598 [29:50<35:38,  1.12s/it]
 47%|████▋     | 1698/3598 [29:51<33:25,  1.06s/it]
 47%|████▋     | 1699/3598 [29:52<36:41,  1.16s/it]
 47%|████▋     | 1700/3598 [29:53<34:41,  1.10s/it]
                                                   

 47%|████▋     | 1700/3598 [29:53<34:41,  1.10s/it]
 47%|████▋     | 1701/3598 [29:54<33:08,  1.05s/it]
 47%|████▋     | 1702/3598 [29:55<32:30,  1.03s/it]
 47%|████▋     | 1703/3598 [29:56<31:13,  1.01it/s]
 47%|████▋     | 1704/3598 [29:57<30:11,  1.05it/s]
 47%|████▋     | 1705/3598 [29:58<30:53,  1.02it/s]
 47%|████▋     | 1706/3598 [29:59<31:09,  1.01it/s]
 47%|████▋     | 1707/3598 [30:00<30:22,  1.04it/s]
 47%|████▋     | 1708/3598 [30:01<30:23,  1.04it/s]
 47%|████▋     | 1709/3598 [30:02<33:11,  1.05s/it]
 48%|████▊     | 1710/3598 [30:03<35:10,  1.12s/it]
                                                   

 48%|████▊     | 1710/3598 [30:03<35:10,  1.12s/it]
 48%|████▊     | 1711/3598 [30:04<32:48,  1.04s/it]
 48%|████▊     | 1712/3598 [30:05<32:20,  1.03s/it]
 48%|████▊     | 1713/3598 [30:06<31:13,  1.01it/s]
 48%|████▊     | 1714/3598 [30:07<29:49,  1.05it/s]
 48%|████▊     | 1715/3598 [30:08<29:27,  1.07it/s]
 48%|████▊     | 1716/3598 [30:09<29:52,  1.05it/s]
 48%|████▊     | 1717/3598 [30:10<30:00,  1.04it/s]
 48%|████▊     | 1718/3598 [30:11<30:34,  1.02it/s]
 48%|████▊     | 1719/3598 [30:12<29:46,  1.05it/s]
 48%|████▊     | 1720/3598 [30:13<29:24,  1.06it/s]
                                                   

 48%|████▊     | 1720/3598 [30:13<29:24,  1.06it/s]
 48%|████▊     | 1721/3598 [30:13<28:27,  1.10it/s]
 48%|████▊     | 1722/3598 [30:14<28:49,  1.08it/s]
 48%|████▊     | 1723/3598 [30:15<28:58,  1.08it/s]
 48%|████▊     | 1724/3598 [30:16<29:27,  1.06it/s]
 48%|████▊     | 1725/3598 [30:18<32:44,  1.05s/it]
 48%|████▊     | 1726/3598 [30:19<31:54,  1.02s/it]
 48%|████▊     | 1727/3598 [30:20<31:18,  1.00s/it]
 48%|████▊     | 1728/3598 [30:21<31:19,  1.00s/it]
 48%|████▊     | 1729/3598 [30:22<34:19,  1.10s/it]
 48%|████▊     | 1730/3598 [30:23<31:15,  1.00s/it]
                                                   

 48%|████▊     | 1730/3598 [30:23<31:15,  1.00s/it]
 48%|████▊     | 1731/3598 [30:24<30:58,  1.00it/s]
 48%|████▊     | 1732/3598 [30:25<29:58,  1.04it/s]
 48%|████▊     | 1733/3598 [30:26<30:25,  1.02it/s]
 48%|████▊     | 1734/3598 [30:27<34:12,  1.10s/it]
 48%|████▊     | 1735/3598 [30:28<32:51,  1.06s/it]
 48%|████▊     | 1736/3598 [30:29<30:58,  1.00it/s]
 48%|████▊     | 1737/3598 [30:30<30:15,  1.03it/s]
 48%|████▊     | 1738/3598 [30:31<29:10,  1.06it/s]
 48%|████▊     | 1739/3598 [30:32<33:29,  1.08s/it]
 48%|████▊     | 1740/3598 [30:33<32:04,  1.04s/it]
                                                   

 48%|████▊     | 1740/3598 [30:33<32:04,  1.04s/it]
 48%|████▊     | 1741/3598 [30:34<31:39,  1.02s/it]
 48%|████▊     | 1742/3598 [30:35<31:04,  1.00s/it]
 48%|████▊     | 1743/3598 [30:36<30:11,  1.02it/s]
 48%|████▊     | 1744/3598 [30:37<30:14,  1.02it/s]
 48%|████▊     | 1745/3598 [30:38<34:17,  1.11s/it]
 49%|████▊     | 1746/3598 [30:39<33:48,  1.10s/it]
 49%|████▊     | 1747/3598 [30:40<32:18,  1.05s/it]
 49%|████▊     | 1748/3598 [30:41<34:20,  1.11s/it]
 49%|████▊     | 1749/3598 [30:42<32:08,  1.04s/it]
 49%|████▊     | 1750/3598 [30:43<30:57,  1.01s/it]
                                                   

 49%|████▊     | 1750/3598 [30:43<30:57,  1.01s/it]
 49%|████▊     | 1751/3598 [30:44<30:05,  1.02it/s]
 49%|████▊     | 1752/3598 [30:46<33:56,  1.10s/it]
 49%|████▊     | 1753/3598 [30:46<31:47,  1.03s/it]
 49%|████▊     | 1754/3598 [30:47<30:43,  1.00it/s]
 49%|████▉     | 1755/3598 [30:48<29:34,  1.04it/s]
 49%|████▉     | 1756/3598 [30:50<33:12,  1.08s/it]
 49%|████▉     | 1757/3598 [30:50<31:48,  1.04s/it]
 49%|████▉     | 1758/3598 [30:51<30:23,  1.01it/s]
 49%|████▉     | 1759/3598 [30:52<29:54,  1.02it/s]
 49%|████▉     | 1760/3598 [30:53<29:52,  1.03it/s]
                                                   

 49%|████▉     | 1760/3598 [30:53<29:52,  1.03it/s]
 49%|████▉     | 1761/3598 [30:55<32:44,  1.07s/it]
 49%|████▉     | 1762/3598 [30:55<30:58,  1.01s/it]
 49%|████▉     | 1763/3598 [30:57<33:34,  1.10s/it]
 49%|████▉     | 1764/3598 [30:58<34:58,  1.14s/it]
 49%|████▉     | 1765/3598 [30:59<32:28,  1.06s/it]
 49%|████▉     | 1766/3598 [31:00<31:07,  1.02s/it]
 49%|████▉     | 1767/3598 [31:01<29:49,  1.02it/s]
 49%|████▉     | 1768/3598 [31:01<28:24,  1.07it/s]
 49%|████▉     | 1769/3598 [31:02<28:52,  1.06it/s]
 49%|████▉     | 1770/3598 [31:03<27:45,  1.10it/s]
                                                   

 49%|████▉     | 1770/3598 [31:03<27:45,  1.10it/s]
 49%|████▉     | 1771/3598 [31:05<31:21,  1.03s/it]
 49%|████▉     | 1772/3598 [31:06<34:38,  1.14s/it]
 49%|████▉     | 1773/3598 [31:07<32:34,  1.07s/it]
 49%|████▉     | 1774/3598 [31:08<30:23,  1.00it/s]
 49%|████▉     | 1775/3598 [31:09<30:07,  1.01it/s]
 49%|████▉     | 1776/3598 [31:10<28:56,  1.05it/s]
 49%|████▉     | 1777/3598 [31:10<27:59,  1.08it/s]
 49%|████▉     | 1778/3598 [31:11<28:13,  1.07it/s]
 49%|████▉     | 1779/3598 [31:12<28:09,  1.08it/s]
 49%|████▉     | 1780/3598 [31:13<29:11,  1.04it/s]
                                                   

 49%|████▉     | 1780/3598 [31:13<29:11,  1.04it/s]
 49%|████▉     | 1781/3598 [31:15<32:35,  1.08s/it]
 50%|████▉     | 1782/3598 [31:16<31:19,  1.03s/it]
 50%|████▉     | 1783/3598 [31:17<30:07,  1.00it/s]
 50%|████▉     | 1784/3598 [31:17<29:54,  1.01it/s]
 50%|████▉     | 1785/3598 [31:18<29:24,  1.03it/s]
 50%|████▉     | 1786/3598 [31:19<28:19,  1.07it/s]
 50%|████▉     | 1787/3598 [31:20<29:20,  1.03it/s]
 50%|████▉     | 1788/3598 [31:22<32:27,  1.08s/it]
 50%|████▉     | 1789/3598 [31:23<32:34,  1.08s/it]
 50%|████▉     | 1790/3598 [31:24<32:04,  1.06s/it]
                                                   

 50%|████▉     | 1790/3598 [31:24<32:04,  1.06s/it]
 50%|████▉     | 1791/3598 [31:25<30:29,  1.01s/it]
 50%|████▉     | 1792/3598 [31:26<29:10,  1.03it/s]
 50%|████▉     | 1793/3598 [31:27<29:15,  1.03it/s]
 50%|████▉     | 1794/3598 [31:27<28:28,  1.06it/s]
 50%|████▉     | 1795/3598 [31:28<27:29,  1.09it/s]
 50%|████▉     | 1796/3598 [31:30<31:10,  1.04s/it]
 50%|████▉     | 1797/3598 [31:31<33:42,  1.12s/it]
 50%|████▉     | 1798/3598 [31:32<31:21,  1.05s/it]
 50%|█████     | 1799/3598 [31:33<30:06,  1.00s/it]
 50%|█████     | 1800/3598 [31:34<28:58,  1.03it/s]
                                                   

 50%|█████     | 1800/3598 [31:34<28:58,  1.03it/s]
{'loss': 0.714, 'grad_norm': 1.5251452922821045, 'learning_rate': 0.0001128145114101814, 'epoch': 0.46}
{'loss': 0.8684, 'grad_norm': 1.431054711341858, 'learning_rate': 0.00011222937390286719, 'epoch': 0.47}
{'loss': 0.824, 'grad_norm': 1.121795654296875, 'learning_rate': 0.00011164423639555297, 'epoch': 0.47}
{'loss': 0.7963, 'grad_norm': 1.7896941900253296, 'learning_rate': 0.00011105909888823874, 'epoch': 0.47}
{'loss': 0.7842, 'grad_norm': 1.2749794721603394, 'learning_rate': 0.00011047396138092452, 'epoch': 0.48}
{'loss': 0.7423, 'grad_norm': 1.5560483932495117, 'learning_rate': 0.0001098888238736103, 'epoch': 0.48}
{'loss': 0.9013, 'grad_norm': 1.4849023818969727, 'learning_rate': 0.00010930368636629608, 'epoch': 0.48}
{'loss': 0.8111, 'grad_norm': 1.5528464317321777, 'learning_rate': 0.00010871854885898188, 'epoch': 0.48}
{'loss': 0.8145, 'grad_norm': 1.897931456565857, 'learning_rate': 0.00010813341135166766, 'epoch': 0.49}
{'loss': 0.7912, 'grad_norm': 1.4603521823883057, 'learning_rate': 0.00010754827384435342, 'epoch': 0.49}
{'loss': 0.7772, 'grad_norm': 1.7950726747512817, 'learning_rate': 0.0001069631363370392, 'epoch': 0.49}
{'loss': 0.6913, 'grad_norm': 1.4596202373504639, 'learning_rate': 0.00010637799882972499, 'epoch': 0.49}
{'loss': 0.801, 'grad_norm': 1.0710797309875488, 'learning_rate': 0.00010579286132241078, 'epoch': 0.5}
{'loss': 0.7098, 'grad_norm': 1.7335723638534546, 'learning_rate': 0.00010520772381509656, 'epoch': 0.5}


  0%|          | 0/4 [00:00<?, ?it/s]

 50%|█████     | 2/4 [00:12<00:12,  6.49s/it]

 75%|███████▌  | 3/4 [00:28<00:10, 10.38s/it]

100%|██████████| 4/4 [00:34<00:00,  8.72s/it]
                                                   

                                             

 50%|█████     | 1800/3598 [32:16<28:58,  1.03it/s]

100%|██████████| 4/4 [00:34<00:00,  8.72s/it]

                                             /opt/mobtranslate-v24-venv/lib/python3.11/site-packages/peft/utils/save_and_load.py:386: UserWarning: Setting `save_embedding_layers` to `True` as the embedding layer has been resized during finetuning.
  warnings.warn(

 50%|█████     | 1801/3598 [32:22<7:31:12, 15.07s/it]
 50%|█████     | 1802/3598 [32:23<5:24:52, 10.85s/it]
 50%|█████     | 1803/3598 [32:23<3:54:58,  7.85s/it]
 50%|█████     | 1804/3598 [32:25<2:56:38,  5.91s/it]
 50%|█████     | 1805/3598 [32:26<2:14:59,  4.52s/it]
 50%|█████     | 1806/3598 [32:27<1:42:26,  3.43s/it]
 50%|█████     | 1807/3598 [32:28<1:21:08,  2.72s/it]
 50%|█████     | 1808/3598 [32:29<1:05:58,  2.21s/it]
 50%|█████     | 1809/3598 [32:30<55:17,  1.85s/it]  
 50%|█████     | 1810/3598 [32:31<51:08,  1.72s/it]
                                                   

 50%|█████     | 1810/3598 [32:31<51:08,  1.72s/it]
 50%|█████     | 1811/3598 [32:33<48:34,  1.63s/it]
 50%|█████     | 1812/3598 [32:34<43:10,  1.45s/it]
 50%|█████     | 1813/3598 [32:35<41:04,  1.38s/it]
 50%|█████     | 1814/3598 [32:36<37:46,  1.27s/it]
 50%|█████     | 1815/3598 [32:38<39:04,  1.31s/it]
 50%|█████     | 1816/3598 [32:39<38:59,  1.31s/it]
 51%|█████     | 1817/3598 [32:40<34:57,  1.18s/it]
 51%|█████     | 1818/3598 [32:41<32:48,  1.11s/it]
 51%|█████     | 1819/3598 [32:42<31:05,  1.05s/it]
 51%|█████     | 1820/3598 [32:42<28:58,  1.02it/s]
                                                   

 51%|█████     | 1820/3598 [32:42<28:58,  1.02it/s]
 51%|█████     | 1821/3598 [32:43<29:01,  1.02it/s]
 51%|█████     | 1822/3598 [32:45<31:49,  1.08s/it]
 51%|█████     | 1823/3598 [32:46<31:31,  1.07s/it]
 51%|█████     | 1824/3598 [32:47<31:32,  1.07s/it]
 51%|█████     | 1825/3598 [32:48<31:04,  1.05s/it]
 51%|█████     | 1826/3598 [32:49<29:40,  1.00s/it]
 51%|█████     | 1827/3598 [32:50<29:37,  1.00s/it]
 51%|█████     | 1828/3598 [32:51<29:14,  1.01it/s]
 51%|█████     | 1829/3598 [32:52<32:05,  1.09s/it]
 51%|█████     | 1830/3598 [32:53<34:43,  1.18s/it]
                                                   

 51%|█████     | 1830/3598 [32:53<34:43,  1.18s/it]
 51%|█████     | 1831/3598 [32:54<33:05,  1.12s/it]
 51%|█████     | 1832/3598 [32:55<31:37,  1.07s/it]
 51%|█████     | 1833/3598 [32:56<30:03,  1.02s/it]
 51%|█████     | 1834/3598 [32:57<28:49,  1.02it/s]
 51%|█████     | 1835/3598 [32:58<27:31,  1.07it/s]
 51%|█████     | 1836/3598 [32:59<27:46,  1.06it/s]
 51%|█████     | 1837/3598 [33:00<27:41,  1.06it/s]
 51%|█████     | 1838/3598 [33:01<28:01,  1.05it/s]
 51%|█████     | 1839/3598 [33:02<30:19,  1.03s/it]
 51%|█████     | 1840/3598 [33:03<29:32,  1.01s/it]
                                                   

 51%|█████     | 1840/3598 [33:03<29:32,  1.01s/it]
 51%|█████     | 1841/3598 [33:04<28:24,  1.03it/s]
 51%|█████     | 1842/3598 [33:05<27:57,  1.05it/s]
 51%|█████     | 1843/3598 [33:06<27:41,  1.06it/s]
 51%|█████▏    | 1844/3598 [33:07<27:05,  1.08it/s]
 51%|█████▏    | 1845/3598 [33:07<26:48,  1.09it/s]
 51%|█████▏    | 1846/3598 [33:09<29:14,  1.00s/it]
 51%|█████▏    | 1847/3598 [33:10<32:42,  1.12s/it]
 51%|█████▏    | 1848/3598 [33:11<31:01,  1.06s/it]
 51%|█████▏    | 1849/3598 [33:12<31:19,  1.07s/it]
 51%|█████▏    | 1850/3598 [33:13<31:12,  1.07s/it]
                                                   

 51%|█████▏    | 1850/3598 [33:13<31:12,  1.07s/it]
 51%|█████▏    | 1851/3598 [33:14<31:10,  1.07s/it]
 51%|█████▏    | 1852/3598 [33:15<30:43,  1.06s/it]
 52%|█████▏    | 1853/3598 [33:17<32:36,  1.12s/it]
 52%|█████▏    | 1854/3598 [33:18<33:22,  1.15s/it]
 52%|█████▏    | 1855/3598 [33:19<31:49,  1.10s/it]
 52%|█████▏    | 1856/3598 [33:20<29:49,  1.03s/it]
 52%|█████▏    | 1857/3598 [33:21<29:24,  1.01s/it]
 52%|█████▏    | 1858/3598 [33:22<31:16,  1.08s/it]
 52%|█████▏    | 1859/3598 [33:23<33:37,  1.16s/it]
 52%|█████▏    | 1860/3598 [33:24<31:46,  1.10s/it]
                                                   

 52%|█████▏    | 1860/3598 [33:24<31:46,  1.10s/it]
 52%|█████▏    | 1861/3598 [33:25<32:41,  1.13s/it]
 52%|█████▏    | 1862/3598 [33:26<30:10,  1.04s/it]
 52%|█████▏    | 1863/3598 [33:27<29:01,  1.00s/it]
 52%|█████▏    | 1864/3598 [33:28<32:19,  1.12s/it]
 52%|█████▏    | 1865/3598 [33:29<30:01,  1.04s/it]
 52%|█████▏    | 1866/3598 [33:31<32:44,  1.13s/it]
 52%|█████▏    | 1867/3598 [33:32<34:18,  1.19s/it]
 52%|█████▏    | 1868/3598 [33:33<32:19,  1.12s/it]
 52%|█████▏    | 1869/3598 [33:34<32:13,  1.12s/it]
 52%|█████▏    | 1870/3598 [33:35<30:19,  1.05s/it]
                                                   

 52%|█████▏    | 1870/3598 [33:35<30:19,  1.05s/it]
 52%|█████▏    | 1871/3598 [33:36<29:34,  1.03s/it]
 52%|█████▏    | 1872/3598 [33:37<28:02,  1.03it/s]
 52%|█████▏    | 1873/3598 [33:38<30:32,  1.06s/it]
 52%|█████▏    | 1874/3598 [33:39<29:40,  1.03s/it]
 52%|█████▏    | 1875/3598 [33:40<32:01,  1.12s/it]
 52%|█████▏    | 1876/3598 [33:41<30:34,  1.07s/it]
 52%|█████▏    | 1877/3598 [33:42<29:31,  1.03s/it]
 52%|█████▏    | 1878/3598 [33:43<29:58,  1.05s/it]
 52%|█████▏    | 1879/3598 [33:44<29:05,  1.02s/it]
 52%|█████▏    | 1880/3598 [33:45<27:56,  1.02it/s]
                                                   

 52%|█████▏    | 1880/3598 [33:45<27:56,  1.02it/s]
 52%|█████▏    | 1881/3598 [33:46<27:42,  1.03it/s]
 52%|█████▏    | 1882/3598 [33:47<28:59,  1.01s/it]
 52%|█████▏    | 1883/3598 [33:48<29:47,  1.04s/it]
 52%|█████▏    | 1884/3598 [33:49<28:46,  1.01s/it]
 52%|█████▏    | 1885/3598 [33:50<27:19,  1.04it/s]
 52%|█████▏    | 1886/3598 [33:51<28:17,  1.01it/s]
 52%|█████▏    | 1887/3598 [33:52<29:11,  1.02s/it]
 52%|█████▏    | 1888/3598 [33:53<28:44,  1.01s/it]
 53%|█████▎    | 1889/3598 [33:54<27:12,  1.05it/s]
 53%|█████▎    | 1890/3598 [33:55<26:51,  1.06it/s]
                                                   

 53%|█████▎    | 1890/3598 [33:55<26:51,  1.06it/s]
 53%|█████▎    | 1891/3598 [33:56<27:05,  1.05it/s]
 53%|█████▎    | 1892/3598 [33:57<30:40,  1.08s/it]
 53%|█████▎    | 1893/3598 [33:59<32:29,  1.14s/it]
 53%|█████▎    | 1894/3598 [33:59<29:55,  1.05s/it]
 53%|█████▎    | 1895/3598 [34:00<29:29,  1.04s/it]
 53%|█████▎    | 1896/3598 [34:01<27:40,  1.03it/s]
 53%|█████▎    | 1897/3598 [34:03<31:08,  1.10s/it]
 53%|█████▎    | 1898/3598 [34:04<29:09,  1.03s/it]
 53%|█████▎    | 1899/3598 [34:04<27:33,  1.03it/s]
 53%|█████▎    | 1900/3598 [34:06<31:11,  1.10s/it]
                                                   

 53%|█████▎    | 1900/3598 [34:06<31:11,  1.10s/it]
 53%|█████▎    | 1901/3598 [34:07<29:56,  1.06s/it]
 53%|█████▎    | 1902/3598 [34:08<29:21,  1.04s/it]
 53%|█████▎    | 1903/3598 [34:09<28:48,  1.02s/it]
 53%|█████▎    | 1904/3598 [34:10<31:59,  1.13s/it]
 53%|█████▎    | 1905/3598 [34:11<30:25,  1.08s/it]
 53%|█████▎    | 1906/3598 [34:12<31:48,  1.13s/it]
 53%|█████▎    | 1907/3598 [34:14<33:12,  1.18s/it]
 53%|█████▎    | 1908/3598 [34:15<33:08,  1.18s/it]
 53%|█████▎    | 1909/3598 [34:16<29:47,  1.06s/it]
 53%|█████▎    | 1910/3598 [34:16<28:08,  1.00s/it]
                                                   

 53%|█████▎    | 1910/3598 [34:16<28:08,  1.00s/it]
 53%|█████▎    | 1911/3598 [34:17<27:53,  1.01it/s]
 53%|█████▎    | 1912/3598 [34:19<30:10,  1.07s/it]
 53%|█████▎    | 1913/3598 [34:19<28:17,  1.01s/it]
 53%|█████▎    | 1914/3598 [34:20<27:22,  1.03it/s]
 53%|█████▎    | 1915/3598 [34:21<27:45,  1.01it/s]
 53%|█████▎    | 1916/3598 [34:22<26:39,  1.05it/s]
 53%|█████▎    | 1917/3598 [34:23<27:05,  1.03it/s]
 53%|█████▎    | 1918/3598 [34:25<30:38,  1.09s/it]
 53%|█████▎    | 1919/3598 [34:26<32:22,  1.16s/it]
 53%|█████▎    | 1920/3598 [34:27<30:06,  1.08s/it]
                                                   

 53%|█████▎    | 1920/3598 [34:27<30:06,  1.08s/it]
 53%|█████▎    | 1921/3598 [34:28<29:53,  1.07s/it]
 53%|█████▎    | 1922/3598 [34:29<31:03,  1.11s/it]
 53%|█████▎    | 1923/3598 [34:30<31:44,  1.14s/it]
 53%|█████▎    | 1924/3598 [34:31<29:39,  1.06s/it]
 54%|█████▎    | 1925/3598 [34:32<29:40,  1.06s/it]
 54%|█████▎    | 1926/3598 [34:34<31:46,  1.14s/it]
 54%|█████▎    | 1927/3598 [34:35<33:09,  1.19s/it]
 54%|█████▎    | 1928/3598 [34:36<31:35,  1.14s/it]
 54%|█████▎    | 1929/3598 [34:37<33:09,  1.19s/it]
 54%|█████▎    | 1930/3598 [34:38<30:31,  1.10s/it]
                                                   

 54%|█████▎    | 1930/3598 [34:38<30:31,  1.10s/it]
 54%|█████▎    | 1931/3598 [34:39<30:37,  1.10s/it]
 54%|█████▎    | 1932/3598 [34:40<28:13,  1.02s/it]
 54%|█████▎    | 1933/3598 [34:41<27:57,  1.01s/it]
 54%|█████▍    | 1934/3598 [34:42<27:07,  1.02it/s]
 54%|█████▍    | 1935/3598 [34:43<27:12,  1.02it/s]
 54%|█████▍    | 1936/3598 [34:44<29:15,  1.06s/it]
 54%|█████▍    | 1937/3598 [34:45<28:54,  1.04s/it]
 54%|█████▍    | 1938/3598 [34:46<27:29,  1.01it/s]
 54%|█████▍    | 1939/3598 [34:47<27:49,  1.01s/it]
 54%|█████▍    | 1940/3598 [34:48<26:49,  1.03it/s]
                                                   

 54%|█████▍    | 1940/3598 [34:48<26:49,  1.03it/s]
 54%|█████▍    | 1941/3598 [34:49<25:23,  1.09it/s]
 54%|█████▍    | 1942/3598 [34:50<25:12,  1.09it/s]
 54%|█████▍    | 1943/3598 [34:51<25:04,  1.10it/s]
 54%|█████▍    | 1944/3598 [34:52<27:47,  1.01s/it]
 54%|█████▍    | 1945/3598 [34:53<29:15,  1.06s/it]
 54%|█████▍    | 1946/3598 [34:54<28:23,  1.03s/it]
 54%|█████▍    | 1947/3598 [34:55<27:33,  1.00s/it]
 54%|█████▍    | 1948/3598 [34:56<26:25,  1.04it/s]
 54%|█████▍    | 1949/3598 [34:57<25:44,  1.07it/s]
 54%|█████▍    | 1950/3598 [34:58<29:29,  1.07s/it]
                                                   

 54%|█████▍    | 1950/3598 [34:58<29:29,  1.07s/it]
 54%|█████▍    | 1951/3598 [34:59<29:42,  1.08s/it]
 54%|█████▍    | 1952/3598 [35:00<28:49,  1.05s/it]
 54%|█████▍    | 1953/3598 [35:01<31:42,  1.16s/it]
 54%|█████▍    | 1954/3598 [35:02<29:27,  1.08s/it]
 54%|█████▍    | 1955/3598 [35:04<31:17,  1.14s/it]
 54%|█████▍    | 1956/3598 [35:05<30:50,  1.13s/it]
 54%|█████▍    | 1957/3598 [35:06<32:50,  1.20s/it]
 54%|█████▍    | 1958/3598 [35:07<31:26,  1.15s/it]
 54%|█████▍    | 1959/3598 [35:09<33:24,  1.22s/it]
 54%|█████▍    | 1960/3598 [35:10<31:19,  1.15s/it]
                                                   

 54%|█████▍    | 1960/3598 [35:10<31:19,  1.15s/it]
 55%|█████▍    | 1961/3598 [35:11<31:56,  1.17s/it]
 55%|█████▍    | 1962/3598 [35:12<33:19,  1.22s/it]
 55%|█████▍    | 1963/3598 [35:13<31:20,  1.15s/it]
 55%|█████▍    | 1964/3598 [35:14<29:38,  1.09s/it]
 55%|█████▍    | 1965/3598 [35:15<31:29,  1.16s/it]
 55%|█████▍    | 1966/3598 [35:16<30:37,  1.13s/it]
 55%|█████▍    | 1967/3598 [35:17<28:19,  1.04s/it]
 55%|█████▍    | 1968/3598 [35:18<26:49,  1.01it/s]
 55%|█████▍    | 1969/3598 [35:19<27:13,  1.00s/it]
 55%|█████▍    | 1970/3598 [35:20<27:02,  1.00it/s]
                                                   

 55%|█████▍    | 1970/3598 [35:20<27:02,  1.00it/s]
 55%|█████▍    | 1971/3598 [35:21<29:44,  1.10s/it]
 55%|█████▍    | 1972/3598 [35:22<28:40,  1.06s/it]
 55%|█████▍    | 1973/3598 [35:24<31:10,  1.15s/it]
 55%|█████▍    | 1974/3598 [35:25<31:17,  1.16s/it]
 55%|█████▍    | 1975/3598 [35:26<32:13,  1.19s/it]
 55%|█████▍    | 1976/3598 [35:27<30:24,  1.12s/it]
 55%|█████▍    | 1977/3598 [35:28<28:15,  1.05s/it]
 55%|█████▍    | 1978/3598 [35:29<26:44,  1.01it/s]
 55%|█████▌    | 1979/3598 [35:30<29:20,  1.09s/it]
 55%|█████▌    | 1980/3598 [35:31<29:39,  1.10s/it]
                                                   

 55%|█████▌    | 1980/3598 [35:31<29:39,  1.10s/it]
 55%|█████▌    | 1981/3598 [35:32<27:52,  1.03s/it]
 55%|█████▌    | 1982/3598 [35:33<26:54,  1.00it/s]
 55%|█████▌    | 1983/3598 [35:35<29:32,  1.10s/it]
 55%|█████▌    | 1984/3598 [35:36<29:15,  1.09s/it]
 55%|█████▌    | 1985/3598 [35:37<28:23,  1.06s/it]
 55%|█████▌    | 1986/3598 [35:37<27:05,  1.01s/it]
 55%|█████▌    | 1987/3598 [35:38<27:11,  1.01s/it]
 55%|█████▌    | 1988/3598 [35:40<29:46,  1.11s/it]
 55%|█████▌    | 1989/3598 [35:41<31:53,  1.19s/it]
 55%|█████▌    | 1990/3598 [35:42<30:48,  1.15s/it]
                                                   

 55%|█████▌    | 1990/3598 [35:42<30:48,  1.15s/it]
 55%|█████▌    | 1991/3598 [35:43<29:24,  1.10s/it]
 55%|█████▌    | 1992/3598 [35:44<27:35,  1.03s/it]
 55%|█████▌    | 1993/3598 [35:45<26:41,  1.00it/s]
 55%|█████▌    | 1994/3598 [35:46<25:57,  1.03it/s]
 55%|█████▌    | 1995/3598 [35:47<27:35,  1.03s/it]
 55%|█████▌    | 1996/3598 [35:48<25:57,  1.03it/s]
 56%|█████▌    | 1997/3598 [35:49<25:02,  1.07it/s]
 56%|█████▌    | 1998/3598 [35:50<25:11,  1.06it/s]
 56%|█████▌    | 1999/3598 [35:51<25:44,  1.04it/s]
 56%|█████▌    | 2000/3598 [35:52<25:17,  1.05it/s]
                                                   

 56%|█████▌    | 2000/3598 [35:52<25:17,  1.05it/s]
 56%|█████▌    | 2001/3598 [35:53<24:50,  1.07it/s]
 56%|█████▌    | 2002/3598 [35:54<24:57,  1.07it/s]
 56%|█████▌    | 2003/3598 [35:54<24:14,  1.10it/s]
 56%|█████▌    | 2004/3598 [35:56<28:04,  1.06s/it]
 56%|█████▌    | 2005/3598 [35:57<26:59,  1.02s/it]
 56%|█████▌    | 2006/3598 [35:58<29:07,  1.10s/it]
 56%|█████▌    | 2007/3598 [35:59<26:43,  1.01s/it]
 56%|█████▌    | 2008/3598 [36:00<29:41,  1.12s/it]
 56%|█████▌    | 2009/3598 [36:01<27:53,  1.05s/it]
 56%|█████▌    | 2010/3598 [36:02<25:46,  1.03it/s]
                                                   

 56%|█████▌    | 2010/3598 [36:02<25:46,  1.03it/s]
 56%|█████▌    | 2011/3598 [36:03<26:03,  1.01it/s]
 56%|█████▌    | 2012/3598 [36:04<28:28,  1.08s/it]
 56%|█████▌    | 2013/3598 [36:05<27:36,  1.05s/it]
 56%|█████▌    | 2014/3598 [36:06<26:10,  1.01it/s]
 56%|█████▌    | 2015/3598 [36:07<25:09,  1.05it/s]
 56%|█████▌    | 2016/3598 [36:08<25:17,  1.04it/s]
 56%|█████▌    | 2017/3598 [36:09<24:59,  1.05it/s]
 56%|█████▌    | 2018/3598 [36:10<24:57,  1.06it/s]
 56%|█████▌    | 2019/3598 [36:11<24:31,  1.07it/s]
 56%|█████▌    | 2020/3598 [36:11<23:56,  1.10it/s]
                                                   

 56%|█████▌    | 2020/3598 [36:11<23:56,  1.10it/s]
 56%|█████▌    | 2021/3598 [36:12<24:41,  1.06it/s]
 56%|█████▌    | 2022/3598 [36:14<27:20,  1.04s/it]
 56%|█████▌    | 2023/3598 [36:15<27:10,  1.04s/it]
 56%|█████▋    | 2024/3598 [36:16<29:17,  1.12s/it]
 56%|█████▋    | 2025/3598 [36:17<28:36,  1.09s/it]
 56%|█████▋    | 2026/3598 [36:18<28:39,  1.09s/it]
 56%|█████▋    | 2027/3598 [36:19<28:14,  1.08s/it]
 56%|█████▋    | 2028/3598 [36:20<27:22,  1.05s/it]
 56%|█████▋    | 2029/3598 [36:21<26:13,  1.00s/it]
 56%|█████▋    | 2030/3598 [36:22<24:59,  1.05it/s]
                                                   

 56%|█████▋    | 2030/3598 [36:22<24:59,  1.05it/s]
 56%|█████▋    | 2031/3598 [36:23<25:05,  1.04it/s]
 56%|█████▋    | 2032/3598 [36:24<25:04,  1.04it/s]
 57%|█████▋    | 2033/3598 [36:25<25:47,  1.01it/s]
 57%|█████▋    | 2034/3598 [36:26<27:49,  1.07s/it]
 57%|█████▋    | 2035/3598 [36:27<29:13,  1.12s/it]
 57%|█████▋    | 2036/3598 [36:28<28:22,  1.09s/it]
 57%|█████▋    | 2037/3598 [36:30<30:58,  1.19s/it]
 57%|█████▋    | 2038/3598 [36:31<28:19,  1.09s/it]
 57%|█████▋    | 2039/3598 [36:32<27:26,  1.06s/it]
 57%|█████▋    | 2040/3598 [36:33<26:29,  1.02s/it]
                                                   

 57%|█████▋    | 2040/3598 [36:33<26:29,  1.02s/it]
 57%|█████▋    | 2041/3598 [36:34<25:25,  1.02it/s]
 57%|█████▋    | 2042/3598 [36:35<25:47,  1.01it/s]
 57%|█████▋    | 2043/3598 [36:35<25:19,  1.02it/s]
 57%|█████▋    | 2044/3598 [36:36<23:56,  1.08it/s]
 57%|█████▋    | 2045/3598 [36:37<24:24,  1.06it/s]
 57%|█████▋    | 2046/3598 [36:39<27:06,  1.05s/it]
 57%|█████▋    | 2047/3598 [36:39<26:00,  1.01s/it]
 57%|█████▋    | 2048/3598 [36:41<29:06,  1.13s/it]
 57%|█████▋    | 2049/3598 [36:42<26:58,  1.05s/it]
 57%|█████▋    | 2050/3598 [36:43<26:52,  1.04s/it]
                                                   

 57%|█████▋    | 2050/3598 [36:43<26:52,  1.04s/it]
 57%|█████▋    | 2051/3598 [36:44<27:42,  1.07s/it]
 57%|█████▋    | 2052/3598 [36:45<28:00,  1.09s/it]
 57%|█████▋    | 2053/3598 [36:46<30:37,  1.19s/it]
 57%|█████▋    | 2054/3598 [36:48<30:31,  1.19s/it]
 57%|█████▋    | 2055/3598 [36:49<28:07,  1.09s/it]
 57%|█████▋    | 2056/3598 [36:49<27:02,  1.05s/it]
 57%|█████▋    | 2057/3598 [36:50<25:54,  1.01s/it]
 57%|█████▋    | 2058/3598 [36:52<28:53,  1.13s/it]
 57%|█████▋    | 2059/3598 [36:53<26:58,  1.05s/it]
 57%|█████▋    | 2060/3598 [36:54<25:39,  1.00s/it]
                                                   

 57%|█████▋    | 2060/3598 [36:54<25:39,  1.00s/it]
 57%|█████▋    | 2061/3598 [36:54<24:52,  1.03it/s]
 57%|█████▋    | 2062/3598 [36:55<24:41,  1.04it/s]
 57%|█████▋    | 2063/3598 [36:56<24:46,  1.03it/s]
 57%|█████▋    | 2064/3598 [36:58<26:34,  1.04s/it]
 57%|█████▋    | 2065/3598 [36:58<25:04,  1.02it/s]
 57%|█████▋    | 2066/3598 [36:59<24:49,  1.03it/s]
 57%|█████▋    | 2067/3598 [37:00<24:31,  1.04it/s]
 57%|█████▋    | 2068/3598 [37:01<25:03,  1.02it/s]
 58%|█████▊    | 2069/3598 [37:02<24:51,  1.03it/s]
 58%|█████▊    | 2070/3598 [37:03<25:04,  1.02it/s]
                                                   

 58%|█████▊    | 2070/3598 [37:03<25:04,  1.02it/s]
 58%|█████▊    | 2071/3598 [37:04<24:26,  1.04it/s]
 58%|█████▊    | 2072/3598 [37:05<26:39,  1.05s/it]
 58%|█████▊    | 2073/3598 [37:07<26:42,  1.05s/it]
 58%|█████▊    | 2074/3598 [37:07<25:05,  1.01it/s]
 58%|█████▊    | 2075/3598 [37:08<25:15,  1.00it/s]
 58%|█████▊    | 2076/3598 [37:09<24:46,  1.02it/s]
 58%|█████▊    | 2077/3598 [37:10<25:00,  1.01it/s]
 58%|█████▊    | 2078/3598 [37:11<24:13,  1.05it/s]
 58%|█████▊    | 2079/3598 [37:12<23:35,  1.07it/s]
 58%|█████▊    | 2080/3598 [37:13<25:35,  1.01s/it]
                                                   

 58%|█████▊    | 2080/3598 [37:13<25:35,  1.01s/it]
 58%|█████▊    | 2081/3598 [37:15<28:37,  1.13s/it]
 58%|█████▊    | 2082/3598 [37:16<27:34,  1.09s/it]
 58%|█████▊    | 2083/3598 [37:17<26:13,  1.04s/it]
 58%|█████▊    | 2084/3598 [37:18<26:04,  1.03s/it]
 58%|█████▊    | 2085/3598 [37:19<27:31,  1.09s/it]
 58%|█████▊    | 2086/3598 [37:20<25:19,  1.00s/it]
 58%|█████▊    | 2087/3598 [37:21<24:36,  1.02it/s]
 58%|█████▊    | 2088/3598 [37:22<27:02,  1.07s/it]
 58%|█████▊    | 2089/3598 [37:23<25:40,  1.02s/it]
 58%|█████▊    | 2090/3598 [37:24<24:42,  1.02it/s]
                                                   

 58%|█████▊    | 2090/3598 [37:24<24:42,  1.02it/s]
 58%|█████▊    | 2091/3598 [37:25<23:53,  1.05it/s]
 58%|█████▊    | 2092/3598 [37:25<22:56,  1.09it/s]
 58%|█████▊    | 2093/3598 [37:27<24:59,  1.00it/s]
 58%|█████▊    | 2094/3598 [37:28<27:30,  1.10s/it]
 58%|█████▊    | 2095/3598 [37:29<29:11,  1.17s/it]
 58%|█████▊    | 2096/3598 [37:30<27:06,  1.08s/it]
 58%|█████▊    | 2097/3598 [37:31<29:15,  1.17s/it]
 58%|█████▊    | 2098/3598 [37:32<27:02,  1.08s/it]
 58%|█████▊    | 2099/3598 [37:34<29:23,  1.18s/it]
 58%|█████▊    | 2100/3598 [37:35<27:13,  1.09s/it]
                                                   

 58%|█████▊    | 2100/3598 [37:35<27:13,  1.09s/it]
 58%|█████▊    | 2101/3598 [37:36<29:32,  1.18s/it]
 58%|█████▊    | 2102/3598 [37:37<29:43,  1.19s/it]
 58%|█████▊    | 2103/3598 [37:38<28:24,  1.14s/it]
 58%|█████▊    | 2104/3598 [37:39<26:44,  1.07s/it]
 59%|█████▊    | 2105/3598 [37:41<29:09,  1.17s/it]
 59%|█████▊    | 2106/3598 [37:42<30:45,  1.24s/it]
 59%|█████▊    | 2107/3598 [37:43<28:46,  1.16s/it]
 59%|█████▊    | 2108/3598 [37:44<29:57,  1.21s/it]
 59%|█████▊    | 2109/3598 [37:45<27:32,  1.11s/it]
 59%|█████▊    | 2110/3598 [37:46<27:22,  1.10s/it]
                                                   

 59%|█████▊    | 2110/3598 [37:46<27:22,  1.10s/it]
 59%|█████▊    | 2111/3598 [37:47<26:08,  1.05s/it]
 59%|█████▊    | 2112/3598 [37:48<25:04,  1.01s/it]
 59%|█████▊    | 2113/3598 [37:49<23:55,  1.03it/s]
 59%|█████▉    | 2114/3598 [37:50<23:15,  1.06it/s]
 59%|█████▉    | 2115/3598 [37:51<22:48,  1.08it/s]
 59%|█████▉    | 2116/3598 [37:52<23:32,  1.05it/s]
 59%|█████▉    | 2117/3598 [37:53<23:05,  1.07it/s]
 59%|█████▉    | 2118/3598 [37:54<22:53,  1.08it/s]
 59%|█████▉    | 2119/3598 [37:54<22:52,  1.08it/s]
 59%|█████▉    | 2120/3598 [37:55<23:28,  1.05it/s]
                                                   

 59%|█████▉    | 2120/3598 [37:55<23:28,  1.05it/s]
 59%|█████▉    | 2121/3598 [37:57<26:49,  1.09s/it]
 59%|█████▉    | 2122/3598 [37:58<26:20,  1.07s/it]
 59%|█████▉    | 2123/3598 [37:59<26:57,  1.10s/it]
 59%|█████▉    | 2124/3598 [38:00<26:24,  1.08s/it]
 59%|█████▉    | 2125/3598 [38:01<24:47,  1.01s/it]
 59%|█████▉    | 2126/3598 [38:02<23:48,  1.03it/s]
 59%|█████▉    | 2127/3598 [38:03<25:39,  1.05s/it]
 59%|█████▉    | 2128/3598 [38:04<24:38,  1.01s/it]
 59%|█████▉    | 2129/3598 [38:05<24:07,  1.01it/s]
 59%|█████▉    | 2130/3598 [38:06<24:45,  1.01s/it]
                                                   

 59%|█████▉    | 2130/3598 [38:06<24:45,  1.01s/it]
 59%|█████▉    | 2131/3598 [38:07<23:59,  1.02it/s]
 59%|█████▉    | 2132/3598 [38:08<26:29,  1.08s/it]
 59%|█████▉    | 2133/3598 [38:09<25:11,  1.03s/it]
 59%|█████▉    | 2134/3598 [38:10<27:23,  1.12s/it]
 59%|█████▉    | 2135/3598 [38:11<26:08,  1.07s/it]
 59%|█████▉    | 2136/3598 [38:13<27:59,  1.15s/it]
 59%|█████▉    | 2137/3598 [38:14<29:58,  1.23s/it]
 59%|█████▉    | 2138/3598 [38:15<28:31,  1.17s/it]
 59%|█████▉    | 2139/3598 [38:16<26:05,  1.07s/it]
 59%|█████▉    | 2140/3598 [38:17<25:24,  1.05s/it]
                                                   

 59%|█████▉    | 2140/3598 [38:17<25:24,  1.05s/it]
 60%|█████▉    | 2141/3598 [38:18<26:53,  1.11s/it]
 60%|█████▉    | 2142/3598 [38:19<25:06,  1.03s/it]
 60%|█████▉    | 2143/3598 [38:20<26:34,  1.10s/it]
 60%|█████▉    | 2144/3598 [38:21<25:06,  1.04s/it]
 60%|█████▉    | 2145/3598 [38:22<24:27,  1.01s/it]
 60%|█████▉    | 2146/3598 [38:23<22:51,  1.06it/s]
 60%|█████▉    | 2147/3598 [38:24<23:16,  1.04it/s]
 60%|█████▉    | 2148/3598 [38:25<23:49,  1.01it/s]
 60%|█████▉    | 2149/3598 [38:26<23:03,  1.05it/s]
 60%|█████▉    | 2150/3598 [38:27<24:20,  1.01s/it]
                                                   

 60%|█████▉    | 2150/3598 [38:27<24:20,  1.01s/it]
 60%|█████▉    | 2151/3598 [38:28<26:41,  1.11s/it]
 60%|█████▉    | 2152/3598 [38:30<28:26,  1.18s/it]
 60%|█████▉    | 2153/3598 [38:31<26:55,  1.12s/it]
 60%|█████▉    | 2154/3598 [38:32<25:53,  1.08s/it]
 60%|█████▉    | 2155/3598 [38:33<24:18,  1.01s/it]
 60%|█████▉    | 2156/3598 [38:34<25:36,  1.07s/it]
 60%|█████▉    | 2157/3598 [38:35<24:09,  1.01s/it]
 60%|█████▉    | 2158/3598 [38:36<23:08,  1.04it/s]
 60%|██████    | 2159/3598 [38:36<22:28,  1.07it/s]
 60%|██████    | 2160/3598 [38:37<22:11,  1.08it/s]
                                                   

 60%|██████    | 2160/3598 [38:37<22:11,  1.08it/s]
 60%|██████    | 2161/3598 [38:38<22:20,  1.07it/s]
 60%|██████    | 2162/3598 [38:39<21:39,  1.10it/s]
 60%|██████    | 2163/3598 [38:40<21:03,  1.14it/s]
 60%|██████    | 2164/3598 [38:41<22:28,  1.06it/s]
 60%|██████    | 2165/3598 [38:42<21:51,  1.09it/s]
 60%|██████    | 2166/3598 [38:43<21:23,  1.12it/s]
 60%|██████    | 2167/3598 [38:44<25:05,  1.05s/it]
 60%|██████    | 2168/3598 [38:45<27:24,  1.15s/it]
 60%|██████    | 2169/3598 [38:46<25:08,  1.06s/it]
 60%|██████    | 2170/3598 [38:48<27:33,  1.16s/it]
                                                   

 60%|██████    | 2170/3598 [38:48<27:33,  1.16s/it]
 60%|██████    | 2171/3598 [38:49<27:15,  1.15s/it]
 60%|██████    | 2172/3598 [38:50<25:18,  1.07s/it]
 60%|██████    | 2173/3598 [38:51<24:00,  1.01s/it]
 60%|██████    | 2174/3598 [38:51<22:54,  1.04it/s]
 60%|██████    | 2175/3598 [38:53<24:51,  1.05s/it]
 60%|██████    | 2176/3598 [38:54<23:48,  1.00s/it]
 61%|██████    | 2177/3598 [38:54<22:51,  1.04it/s]
 61%|██████    | 2178/3598 [38:55<22:10,  1.07it/s]
 61%|██████    | 2179/3598 [38:57<23:47,  1.01s/it]
 61%|██████    | 2180/3598 [38:58<26:28,  1.12s/it]
                                                   

 61%|██████    | 2180/3598 [38:58<26:28,  1.12s/it]
 61%|██████    | 2181/3598 [38:59<27:33,  1.17s/it]
 61%|██████    | 2182/3598 [39:00<25:44,  1.09s/it]
 61%|██████    | 2183/3598 [39:01<24:07,  1.02s/it]
 61%|██████    | 2184/3598 [39:02<25:49,  1.10s/it]
 61%|██████    | 2185/3598 [39:03<24:56,  1.06s/it]
 61%|██████    | 2186/3598 [39:04<24:23,  1.04s/it]
 61%|██████    | 2187/3598 [39:05<23:44,  1.01s/it]
 61%|██████    | 2188/3598 [39:06<22:18,  1.05it/s]
 61%|██████    | 2189/3598 [39:07<23:40,  1.01s/it]
 61%|██████    | 2190/3598 [39:08<22:53,  1.03it/s]
                                                   

 61%|██████    | 2190/3598 [39:08<22:53,  1.03it/s]
 61%|██████    | 2191/3598 [39:09<22:06,  1.06it/s]
 61%|██████    | 2192/3598 [39:10<21:41,  1.08it/s]
 61%|██████    | 2193/3598 [39:11<22:15,  1.05it/s]
 61%|██████    | 2194/3598 [39:12<22:16,  1.05it/s]
 61%|██████    | 2195/3598 [39:13<24:17,  1.04s/it]
 61%|██████    | 2196/3598 [39:14<25:18,  1.08s/it]
 61%|██████    | 2197/3598 [39:15<23:29,  1.01s/it]
 61%|██████    | 2198/3598 [39:16<22:33,  1.03it/s]
 61%|██████    | 2199/3598 [39:17<22:18,  1.05it/s]
 61%|██████    | 2200/3598 [39:18<22:09,  1.05it/s]
                                                   

 61%|██████    | 2200/3598 [39:18<22:09,  1.05it/s]
 61%|██████    | 2201/3598 [39:19<21:34,  1.08it/s]
 61%|██████    | 2202/3598 [39:19<20:52,  1.11it/s]
 61%|██████    | 2203/3598 [39:20<20:24,  1.14it/s]
 61%|██████▏   | 2204/3598 [39:21<20:23,  1.14it/s]
 61%|██████▏   | 2205/3598 [39:22<20:54,  1.11it/s]
 61%|██████▏   | 2206/3598 [39:23<21:04,  1.10it/s]
 61%|██████▏   | 2207/3598 [39:24<20:56,  1.11it/s]
 61%|██████▏   | 2208/3598 [39:25<21:31,  1.08it/s]
 61%|██████▏   | 2209/3598 [39:26<22:26,  1.03it/s]
 61%|██████▏   | 2210/3598 [39:27<21:51,  1.06it/s]
                                                   

 61%|██████▏   | 2210/3598 [39:27<21:51,  1.06it/s]
 61%|██████▏   | 2211/3598 [39:28<22:11,  1.04it/s]
 61%|██████▏   | 2212/3598 [39:29<22:46,  1.01it/s]
 62%|██████▏   | 2213/3598 [39:30<25:31,  1.11s/it]
 62%|██████▏   | 2214/3598 [39:31<24:04,  1.04s/it]
 62%|██████▏   | 2215/3598 [39:32<23:37,  1.02s/it]
 62%|██████▏   | 2216/3598 [39:33<23:52,  1.04s/it]
 62%|██████▏   | 2217/3598 [39:34<22:46,  1.01it/s]
 62%|██████▏   | 2218/3598 [39:35<22:02,  1.04it/s]
 62%|██████▏   | 2219/3598 [39:36<21:47,  1.05it/s]
 62%|██████▏   | 2220/3598 [39:37<24:01,  1.05s/it]
                                                   

 62%|██████▏   | 2220/3598 [39:37<24:01,  1.05s/it]
 62%|██████▏   | 2221/3598 [39:38<23:06,  1.01s/it]
 62%|██████▏   | 2222/3598 [39:39<25:53,  1.13s/it]
 62%|██████▏   | 2223/3598 [39:40<24:32,  1.07s/it]
 62%|██████▏   | 2224/3598 [39:41<24:31,  1.07s/it]
 62%|██████▏   | 2225/3598 [39:43<24:30,  1.07s/it]
 62%|██████▏   | 2226/3598 [39:44<26:12,  1.15s/it]
 62%|██████▏   | 2227/3598 [39:45<25:46,  1.13s/it]
 62%|██████▏   | 2228/3598 [39:46<24:24,  1.07s/it]
 62%|██████▏   | 2229/3598 [39:47<25:57,  1.14s/it]
 62%|██████▏   | 2230/3598 [39:48<25:01,  1.10s/it]
                                                   

 62%|██████▏   | 2230/3598 [39:48<25:01,  1.10s/it]
 62%|██████▏   | 2231/3598 [39:49<26:23,  1.16s/it]
 62%|██████▏   | 2232/3598 [39:50<24:51,  1.09s/it]
 62%|██████▏   | 2233/3598 [39:51<22:57,  1.01s/it]
 62%|██████▏   | 2234/3598 [39:52<22:31,  1.01it/s]
 62%|██████▏   | 2235/3598 [39:53<22:28,  1.01it/s]
 62%|██████▏   | 2236/3598 [39:54<22:43,  1.00s/it]
 62%|██████▏   | 2237/3598 [39:55<22:48,  1.01s/it]
 62%|██████▏   | 2238/3598 [39:57<25:25,  1.12s/it]
 62%|██████▏   | 2239/3598 [39:57<23:41,  1.05s/it]
 62%|██████▏   | 2240/3598 [39:58<22:26,  1.01it/s]
                                                   

 62%|██████▏   | 2240/3598 [39:58<22:26,  1.01it/s]
 62%|██████▏   | 2241/3598 [39:59<22:09,  1.02it/s]
 62%|██████▏   | 2242/3598 [40:00<21:24,  1.06it/s]
 62%|██████▏   | 2243/3598 [40:01<22:08,  1.02it/s]
 62%|██████▏   | 2244/3598 [40:02<21:34,  1.05it/s]
 62%|██████▏   | 2245/3598 [40:03<21:10,  1.06it/s]
 62%|██████▏   | 2246/3598 [40:04<21:58,  1.03it/s]
 62%|██████▏   | 2247/3598 [40:05<21:17,  1.06it/s]
 62%|██████▏   | 2248/3598 [40:06<20:49,  1.08it/s]
 63%|██████▎   | 2249/3598 [40:07<21:56,  1.02it/s]
 63%|██████▎   | 2250/3598 [40:08<21:54,  1.03it/s]
                                                   

 63%|██████▎   | 2250/3598 [40:08<21:54,  1.03it/s]
 63%|██████▎   | 2251/3598 [40:09<24:32,  1.09s/it]
 63%|██████▎   | 2252/3598 [40:11<25:57,  1.16s/it]
 63%|██████▎   | 2253/3598 [40:12<26:34,  1.19s/it]
 63%|██████▎   | 2254/3598 [40:13<25:01,  1.12s/it]
 63%|██████▎   | 2255/3598 [40:14<24:06,  1.08s/it]
 63%|██████▎   | 2256/3598 [40:15<26:12,  1.17s/it]
 63%|██████▎   | 2257/3598 [40:16<23:53,  1.07s/it]
 63%|██████▎   | 2258/3598 [40:17<22:13,  1.00it/s]
 63%|██████▎   | 2259/3598 [40:18<22:19,  1.00s/it]
 63%|██████▎   | 2260/3598 [40:19<25:03,  1.12s/it]
                                                   

 63%|██████▎   | 2260/3598 [40:19<25:03,  1.12s/it]
 63%|██████▎   | 2261/3598 [40:20<23:27,  1.05s/it]
 63%|██████▎   | 2262/3598 [40:21<23:16,  1.05s/it]
 63%|██████▎   | 2263/3598 [40:22<23:08,  1.04s/it]
 63%|██████▎   | 2264/3598 [40:23<22:39,  1.02s/it]
 63%|██████▎   | 2265/3598 [40:24<21:43,  1.02it/s]
 63%|██████▎   | 2266/3598 [40:25<21:20,  1.04it/s]
 63%|██████▎   | 2267/3598 [40:26<23:08,  1.04s/it]
 63%|██████▎   | 2268/3598 [40:28<25:06,  1.13s/it]
 63%|██████▎   | 2269/3598 [40:29<25:56,  1.17s/it]
 63%|██████▎   | 2270/3598 [40:30<24:14,  1.10s/it]
                                                   

 63%|██████▎   | 2270/3598 [40:30<24:14,  1.10s/it]
 63%|██████▎   | 2271/3598 [40:31<24:48,  1.12s/it]
 63%|██████▎   | 2272/3598 [40:32<25:31,  1.16s/it]
 63%|██████▎   | 2273/3598 [40:34<27:03,  1.22s/it]
 63%|██████▎   | 2274/3598 [40:35<27:05,  1.23s/it]
 63%|██████▎   | 2275/3598 [40:36<26:00,  1.18s/it]
 63%|██████▎   | 2276/3598 [40:37<25:02,  1.14s/it]
 63%|██████▎   | 2277/3598 [40:38<23:21,  1.06s/it]
 63%|██████▎   | 2278/3598 [40:39<22:53,  1.04s/it]
 63%|██████▎   | 2279/3598 [40:40<22:59,  1.05s/it]
 63%|██████▎   | 2280/3598 [40:41<22:57,  1.04s/it]
                                                   

 63%|██████▎   | 2280/3598 [40:41<22:57,  1.04s/it]
 63%|██████▎   | 2281/3598 [40:42<24:55,  1.14s/it]
 63%|██████▎   | 2282/3598 [40:43<23:32,  1.07s/it]
 63%|██████▎   | 2283/3598 [40:44<24:53,  1.14s/it]
 63%|██████▎   | 2284/3598 [40:46<26:15,  1.20s/it]
 64%|██████▎   | 2285/3598 [40:47<27:52,  1.27s/it]
 64%|██████▎   | 2286/3598 [40:48<25:16,  1.16s/it]
 64%|██████▎   | 2287/3598 [40:49<26:04,  1.19s/it]
 64%|██████▎   | 2288/3598 [40:51<27:18,  1.25s/it]
 64%|██████▎   | 2289/3598 [40:52<24:44,  1.13s/it]
 64%|██████▎   | 2290/3598 [40:53<25:24,  1.17s/it]
                                                   

 64%|██████▎   | 2290/3598 [40:53<25:24,  1.17s/it]
 64%|██████▎   | 2291/3598 [40:54<25:13,  1.16s/it]
 64%|██████▎   | 2292/3598 [40:55<23:35,  1.08s/it]
 64%|██████▎   | 2293/3598 [40:56<22:10,  1.02s/it]
 64%|██████▍   | 2294/3598 [40:57<22:15,  1.02s/it]
 64%|██████▍   | 2295/3598 [40:58<24:38,  1.13s/it]
 64%|██████▍   | 2296/3598 [40:59<23:04,  1.06s/it]
 64%|██████▍   | 2297/3598 [41:00<25:16,  1.17s/it]
 64%|██████▍   | 2298/3598 [41:02<26:33,  1.23s/it]
 64%|██████▍   | 2299/3598 [41:03<27:32,  1.27s/it]
 64%|██████▍   | 2300/3598 [41:04<25:00,  1.16s/it]
                                                   

 64%|██████▍   | 2300/3598 [41:04<25:00,  1.16s/it]
 64%|██████▍   | 2301/3598 [41:05<25:33,  1.18s/it]
 64%|██████▍   | 2302/3598 [41:06<23:43,  1.10s/it]
 64%|██████▍   | 2303/3598 [41:07<22:17,  1.03s/it]
 64%|██████▍   | 2304/3598 [41:08<21:46,  1.01s/it]
 64%|██████▍   | 2305/3598 [41:09<23:13,  1.08s/it]
 64%|██████▍   | 2306/3598 [41:10<22:53,  1.06s/it]
 64%|██████▍   | 2307/3598 [41:11<21:51,  1.02s/it]
 64%|██████▍   | 2308/3598 [41:12<21:19,  1.01it/s]
 64%|██████▍   | 2309/3598 [41:13<22:40,  1.06s/it]
 64%|██████▍   | 2310/3598 [41:14<22:15,  1.04s/it]
                                                   

 64%|██████▍   | 2310/3598 [41:14<22:15,  1.04s/it]
 64%|██████▍   | 2311/3598 [41:15<21:38,  1.01s/it]
 64%|██████▍   | 2312/3598 [41:17<23:14,  1.08s/it]
 64%|██████▍   | 2313/3598 [41:18<24:24,  1.14s/it]
 64%|██████▍   | 2314/3598 [41:19<23:48,  1.11s/it]
 64%|██████▍   | 2315/3598 [41:20<22:07,  1.03s/it]
 64%|██████▍   | 2316/3598 [41:21<21:07,  1.01it/s]
 64%|██████▍   | 2317/3598 [41:22<20:43,  1.03it/s]
 64%|██████▍   | 2318/3598 [41:23<20:47,  1.03it/s]
 64%|██████▍   | 2319/3598 [41:24<21:04,  1.01it/s]
 64%|██████▍   | 2320/3598 [41:25<22:39,  1.06s/it]
                                                   

 64%|██████▍   | 2320/3598 [41:25<22:39,  1.06s/it]
 65%|██████▍   | 2321/3598 [41:26<21:48,  1.02s/it]
 65%|██████▍   | 2322/3598 [41:27<21:11,  1.00it/s]
 65%|██████▍   | 2323/3598 [41:28<20:27,  1.04it/s]
 65%|██████▍   | 2324/3598 [41:28<19:57,  1.06it/s]
 65%|██████▍   | 2325/3598 [41:30<21:22,  1.01s/it]
 65%|██████▍   | 2326/3598 [41:31<21:36,  1.02s/it]
 65%|██████▍   | 2327/3598 [41:32<21:34,  1.02s/it]
 65%|██████▍   | 2328/3598 [41:33<20:30,  1.03it/s]
 65%|██████▍   | 2329/3598 [41:33<20:12,  1.05it/s]
 65%|██████▍   | 2330/3598 [41:34<20:24,  1.04it/s]
                                                   

 65%|██████▍   | 2330/3598 [41:34<20:24,  1.04it/s]
 65%|██████▍   | 2331/3598 [41:35<19:55,  1.06it/s]
 65%|██████▍   | 2332/3598 [41:36<19:40,  1.07it/s]
 65%|██████▍   | 2333/3598 [41:37<20:02,  1.05it/s]
 65%|██████▍   | 2334/3598 [41:38<20:47,  1.01it/s]
 65%|██████▍   | 2335/3598 [41:40<23:12,  1.10s/it]
 65%|██████▍   | 2336/3598 [41:41<24:33,  1.17s/it]
 65%|██████▍   | 2337/3598 [41:42<23:20,  1.11s/it]
 65%|██████▍   | 2338/3598 [41:43<22:08,  1.05s/it]
 65%|██████▌   | 2339/3598 [41:44<21:14,  1.01s/it]
 65%|██████▌   | 2340/3598 [41:45<21:03,  1.00s/it]
                                                   

 65%|██████▌   | 2340/3598 [41:45<21:03,  1.00s/it]
 65%|██████▌   | 2341/3598 [41:46<20:36,  1.02it/s]
 65%|██████▌   | 2342/3598 [41:47<22:51,  1.09s/it]
 65%|██████▌   | 2343/3598 [41:48<22:14,  1.06s/it]
 65%|██████▌   | 2344/3598 [41:49<21:39,  1.04s/it]
 65%|██████▌   | 2345/3598 [41:50<22:53,  1.10s/it]
 65%|██████▌   | 2346/3598 [41:51<23:18,  1.12s/it]
 65%|██████▌   | 2347/3598 [41:53<22:45,  1.09s/it]
 65%|██████▌   | 2348/3598 [41:53<22:06,  1.06s/it]
 65%|██████▌   | 2349/3598 [41:54<20:53,  1.00s/it]
 65%|██████▌   | 2350/3598 [41:56<22:59,  1.11s/it]
                                                   

 65%|██████▌   | 2350/3598 [41:56<22:59,  1.11s/it]
 65%|██████▌   | 2351/3598 [41:57<22:29,  1.08s/it]
 65%|██████▌   | 2352/3598 [41:58<21:40,  1.04s/it]
 65%|██████▌   | 2353/3598 [41:59<21:50,  1.05s/it]
 65%|██████▌   | 2354/3598 [42:00<23:49,  1.15s/it]
 65%|██████▌   | 2355/3598 [42:01<22:35,  1.09s/it]
 65%|██████▌   | 2356/3598 [42:02<21:13,  1.03s/it]
 66%|██████▌   | 2357/3598 [42:03<21:08,  1.02s/it]
 66%|██████▌   | 2358/3598 [42:04<20:41,  1.00s/it]
 66%|██████▌   | 2359/3598 [42:05<21:02,  1.02s/it]
 66%|██████▌   | 2360/3598 [42:06<22:44,  1.10s/it]
                                                   

 66%|██████▌   | 2360/3598 [42:06<22:44,  1.10s/it]
 66%|██████▌   | 2361/3598 [42:07<23:19,  1.13s/it]
 66%|██████▌   | 2362/3598 [42:09<24:06,  1.17s/it]
 66%|██████▌   | 2363/3598 [42:10<22:47,  1.11s/it]
 66%|██████▌   | 2364/3598 [42:11<23:34,  1.15s/it]
 66%|██████▌   | 2365/3598 [42:12<24:40,  1.20s/it]
 66%|██████▌   | 2366/3598 [42:13<24:38,  1.20s/it]
 66%|██████▌   | 2367/3598 [42:14<22:46,  1.11s/it]
 66%|██████▌   | 2368/3598 [42:16<23:43,  1.16s/it]
 66%|██████▌   | 2369/3598 [42:17<23:59,  1.17s/it]
 66%|██████▌   | 2370/3598 [42:18<22:46,  1.11s/it]
                                                   

 66%|██████▌   | 2370/3598 [42:18<22:46,  1.11s/it]
 66%|██████▌   | 2371/3598 [42:19<22:04,  1.08s/it]
 66%|██████▌   | 2372/3598 [42:20<20:46,  1.02s/it]
 66%|██████▌   | 2373/3598 [42:21<20:01,  1.02it/s]
 66%|██████▌   | 2374/3598 [42:22<21:41,  1.06s/it]
 66%|██████▌   | 2375/3598 [42:23<20:40,  1.01s/it]
 66%|██████▌   | 2376/3598 [42:24<22:11,  1.09s/it]
 66%|██████▌   | 2377/3598 [42:25<21:27,  1.05s/it]
 66%|██████▌   | 2378/3598 [42:26<23:01,  1.13s/it]
 66%|██████▌   | 2379/3598 [42:28<24:08,  1.19s/it]
 66%|██████▌   | 2380/3598 [42:29<23:34,  1.16s/it]
                                                   

 66%|██████▌   | 2380/3598 [42:29<23:34,  1.16s/it]
 66%|██████▌   | 2381/3598 [42:30<21:45,  1.07s/it]
 66%|██████▌   | 2382/3598 [42:31<23:20,  1.15s/it]
 66%|██████▌   | 2383/3598 [42:32<21:49,  1.08s/it]
 66%|██████▋   | 2384/3598 [42:33<20:41,  1.02s/it]
 66%|██████▋   | 2385/3598 [42:34<21:42,  1.07s/it]
 66%|██████▋   | 2386/3598 [42:35<20:31,  1.02s/it]
 66%|██████▋   | 2387/3598 [42:36<19:39,  1.03it/s]
 66%|██████▋   | 2388/3598 [42:37<19:40,  1.02it/s]
 66%|██████▋   | 2389/3598 [42:37<18:52,  1.07it/s]
 66%|██████▋   | 2390/3598 [42:38<18:55,  1.06it/s]
                                                   

 66%|██████▋   | 2390/3598 [42:38<18:55,  1.06it/s]
 66%|██████▋   | 2391/3598 [42:40<21:39,  1.08s/it]
 66%|██████▋   | 2392/3598 [42:41<21:04,  1.05s/it]
 67%|██████▋   | 2393/3598 [42:42<21:59,  1.09s/it]
 67%|██████▋   | 2394/3598 [42:43<20:43,  1.03s/it]
 67%|██████▋   | 2395/3598 [42:44<19:49,  1.01it/s]
 67%|██████▋   | 2396/3598 [42:45<19:12,  1.04it/s]
 67%|██████▋   | 2397/3598 [42:46<18:46,  1.07it/s]
 67%|██████▋   | 2398/3598 [42:47<19:04,  1.05it/s]
 67%|██████▋   | 2399/3598 [42:48<19:13,  1.04it/s]
 67%|██████▋   | 2400/3598 [42:49<20:36,  1.03s/it]
                                                   

 67%|██████▋   | 2400/3598 [42:49<20:36,  1.03s/it]
 67%|██████▋   | 2401/3598 [42:50<20:15,  1.02s/it]
 67%|██████▋   | 2402/3598 [42:51<19:38,  1.01it/s]
 67%|██████▋   | 2403/3598 [42:52<20:06,  1.01s/it]
 67%|██████▋   | 2404/3598 [42:53<20:17,  1.02s/it]
 67%|██████▋   | 2405/3598 [42:54<21:40,  1.09s/it]
 67%|██████▋   | 2406/3598 [42:55<22:33,  1.14s/it]
 67%|██████▋   | 2407/3598 [42:56<23:11,  1.17s/it]
 67%|██████▋   | 2408/3598 [42:57<22:02,  1.11s/it]
 67%|██████▋   | 2409/3598 [42:58<21:29,  1.08s/it]
 67%|██████▋   | 2410/3598 [43:00<23:26,  1.18s/it]
                                                   

 67%|██████▋   | 2410/3598 [43:00<23:26,  1.18s/it]
 67%|██████▋   | 2411/3598 [43:01<24:07,  1.22s/it]
 67%|██████▋   | 2412/3598 [43:02<22:17,  1.13s/it]
 67%|██████▋   | 2413/3598 [43:04<23:54,  1.21s/it]
 67%|██████▋   | 2414/3598 [43:04<21:49,  1.11s/it]
 67%|██████▋   | 2415/3598 [43:05<20:32,  1.04s/it]
 67%|██████▋   | 2416/3598 [43:06<19:18,  1.02it/s]
 67%|██████▋   | 2417/3598 [43:07<20:09,  1.02s/it]
 67%|██████▋   | 2418/3598 [43:09<21:33,  1.10s/it]
 67%|██████▋   | 2419/3598 [43:09<20:55,  1.06s/it]
 67%|██████▋   | 2420/3598 [43:11<22:05,  1.13s/it]
                                                   

 67%|██████▋   | 2420/3598 [43:11<22:05,  1.13s/it]
 67%|██████▋   | 2421/3598 [43:12<21:02,  1.07s/it]
 67%|██████▋   | 2422/3598 [43:13<19:54,  1.02s/it]
 67%|██████▋   | 2423/3598 [43:14<21:55,  1.12s/it]
 67%|██████▋   | 2424/3598 [43:15<22:12,  1.13s/it]
 67%|██████▋   | 2425/3598 [43:16<20:42,  1.06s/it]
 67%|██████▋   | 2426/3598 [43:17<20:09,  1.03s/it]
 67%|██████▋   | 2427/3598 [43:18<19:34,  1.00s/it]
 67%|██████▋   | 2428/3598 [43:19<21:24,  1.10s/it]
 68%|██████▊   | 2429/3598 [43:20<22:04,  1.13s/it]
 68%|██████▊   | 2430/3598 [43:21<20:49,  1.07s/it]
                                                   

 68%|██████▊   | 2430/3598 [43:21<20:49,  1.07s/it]
 68%|██████▊   | 2431/3598 [43:22<20:10,  1.04s/it]
 68%|██████▊   | 2432/3598 [43:23<19:18,  1.01it/s]
 68%|██████▊   | 2433/3598 [43:24<19:00,  1.02it/s]
 68%|██████▊   | 2434/3598 [43:25<18:26,  1.05it/s]
 68%|██████▊   | 2435/3598 [43:26<18:58,  1.02it/s]
 68%|██████▊   | 2436/3598 [43:27<21:21,  1.10s/it]
 68%|██████▊   | 2437/3598 [43:28<20:04,  1.04s/it]
 68%|██████▊   | 2438/3598 [43:29<18:51,  1.03it/s]
 68%|██████▊   | 2439/3598 [43:30<19:04,  1.01it/s]
 68%|██████▊   | 2440/3598 [43:31<18:40,  1.03it/s]
                                                   

 68%|██████▊   | 2440/3598 [43:31<18:40,  1.03it/s]
 68%|██████▊   | 2441/3598 [43:32<18:45,  1.03it/s]
 68%|██████▊   | 2442/3598 [43:33<18:50,  1.02it/s]
 68%|██████▊   | 2443/3598 [43:34<19:30,  1.01s/it]
 68%|██████▊   | 2444/3598 [43:35<18:57,  1.01it/s]
 68%|██████▊   | 2445/3598 [43:36<18:31,  1.04it/s]
 68%|██████▊   | 2446/3598 [43:37<20:12,  1.05s/it]
 68%|██████▊   | 2447/3598 [43:38<19:42,  1.03s/it]
 68%|██████▊   | 2448/3598 [43:39<18:51,  1.02it/s]
 68%|██████▊   | 2449/3598 [43:41<21:12,  1.11s/it]
 68%|██████▊   | 2450/3598 [43:41<20:05,  1.05s/it]
                                                   

 68%|██████▊   | 2450/3598 [43:41<20:05,  1.05s/it]
 68%|██████▊   | 2451/3598 [43:42<19:04,  1.00it/s]
 68%|██████▊   | 2452/3598 [43:43<18:57,  1.01it/s]
 68%|██████▊   | 2453/3598 [43:44<17:53,  1.07it/s]
 68%|██████▊   | 2454/3598 [43:45<18:12,  1.05it/s]
 68%|██████▊   | 2455/3598 [43:46<17:21,  1.10it/s]
 68%|██████▊   | 2456/3598 [43:47<17:20,  1.10it/s]
 68%|██████▊   | 2457/3598 [43:48<17:19,  1.10it/s]
 68%|██████▊   | 2458/3598 [43:49<18:42,  1.02it/s]
 68%|██████▊   | 2459/3598 [43:50<17:59,  1.06it/s]
 68%|██████▊   | 2460/3598 [43:51<17:43,  1.07it/s]
                                                   

 68%|██████▊   | 2460/3598 [43:51<17:43,  1.07it/s]
 68%|██████▊   | 2461/3598 [43:52<17:53,  1.06it/s]
 68%|██████▊   | 2462/3598 [43:53<20:24,  1.08s/it]
 68%|██████▊   | 2463/3598 [43:54<20:16,  1.07s/it]
 68%|██████▊   | 2464/3598 [43:55<19:12,  1.02s/it]
 69%|██████▊   | 2465/3598 [43:56<18:23,  1.03it/s]
 69%|██████▊   | 2466/3598 [43:57<17:41,  1.07it/s]
 69%|██████▊   | 2467/3598 [43:58<20:02,  1.06s/it]
 69%|██████▊   | 2468/3598 [43:59<20:03,  1.06s/it]
 69%|██████▊   | 2469/3598 [44:00<18:56,  1.01s/it]
 69%|██████▊   | 2470/3598 [44:01<18:42,  1.00it/s]
                                                   

 69%|██████▊   | 2470/3598 [44:01<18:42,  1.00it/s]
 69%|██████▊   | 2471/3598 [44:02<18:35,  1.01it/s]
 69%|██████▊   | 2472/3598 [44:03<18:32,  1.01it/s]
 69%|██████▊   | 2473/3598 [44:04<18:25,  1.02it/s]
 69%|██████▉   | 2474/3598 [44:05<19:29,  1.04s/it]
 69%|██████▉   | 2475/3598 [44:06<18:46,  1.00s/it]
 69%|██████▉   | 2476/3598 [44:07<17:40,  1.06it/s]
 69%|██████▉   | 2477/3598 [44:08<17:50,  1.05it/s]
 69%|██████▉   | 2478/3598 [44:09<17:45,  1.05it/s]
 69%|██████▉   | 2479/3598 [44:10<20:00,  1.07s/it]
 69%|██████▉   | 2480/3598 [44:11<19:12,  1.03s/it]
                                                   

 69%|██████▉   | 2480/3598 [44:11<19:12,  1.03s/it]
 69%|██████▉   | 2481/3598 [44:12<18:17,  1.02it/s]
 69%|██████▉   | 2482/3598 [44:13<19:10,  1.03s/it]
 69%|██████▉   | 2483/3598 [44:14<19:15,  1.04s/it]
 69%|██████▉   | 2484/3598 [44:15<19:16,  1.04s/it]
 69%|██████▉   | 2485/3598 [44:16<20:39,  1.11s/it]
 69%|██████▉   | 2486/3598 [44:17<19:37,  1.06s/it]
 69%|██████▉   | 2487/3598 [44:18<19:00,  1.03s/it]
 69%|██████▉   | 2488/3598 [44:19<18:52,  1.02s/it]
 69%|██████▉   | 2489/3598 [44:20<19:18,  1.04s/it]
 69%|██████▉   | 2490/3598 [44:22<20:37,  1.12s/it]
                                                   

 69%|██████▉   | 2490/3598 [44:22<20:37,  1.12s/it]
 69%|██████▉   | 2491/3598 [44:23<22:00,  1.19s/it]
 69%|██████▉   | 2492/3598 [44:24<23:13,  1.26s/it]
 69%|██████▉   | 2493/3598 [44:26<21:59,  1.19s/it]
 69%|██████▉   | 2494/3598 [44:27<22:35,  1.23s/it]
 69%|██████▉   | 2495/3598 [44:28<21:20,  1.16s/it]
 69%|██████▉   | 2496/3598 [44:29<20:20,  1.11s/it]
 69%|██████▉   | 2497/3598 [44:30<19:50,  1.08s/it]
 69%|██████▉   | 2498/3598 [44:31<18:19,  1.00it/s]
 69%|██████▉   | 2499/3598 [44:32<18:38,  1.02s/it]
 69%|██████▉   | 2500/3598 [44:33<20:51,  1.14s/it]
                                                   

 69%|██████▉   | 2500/3598 [44:33<20:51,  1.14s/it]
 70%|██████▉   | 2501/3598 [44:34<20:01,  1.09s/it]
 70%|██████▉   | 2502/3598 [44:35<19:09,  1.05s/it]
 70%|██████▉   | 2503/3598 [44:36<19:07,  1.05s/it]
 70%|██████▉   | 2504/3598 [44:37<18:54,  1.04s/it]
 70%|██████▉   | 2505/3598 [44:38<18:40,  1.02s/it]
 70%|██████▉   | 2506/3598 [44:39<19:35,  1.08s/it]
 70%|██████▉   | 2507/3598 [44:41<20:46,  1.14s/it]
 70%|██████▉   | 2508/3598 [44:42<20:59,  1.16s/it]
 70%|██████▉   | 2509/3598 [44:43<22:16,  1.23s/it]
 70%|██████▉   | 2510/3598 [44:44<20:50,  1.15s/it]
                                                   

 70%|██████▉   | 2510/3598 [44:44<20:50,  1.15s/it]
 70%|██████▉   | 2511/3598 [44:45<19:35,  1.08s/it]
 70%|██████▉   | 2512/3598 [44:46<18:52,  1.04s/it]
 70%|██████▉   | 2513/3598 [44:47<18:16,  1.01s/it]
 70%|██████▉   | 2514/3598 [44:48<17:14,  1.05it/s]
 70%|██████▉   | 2515/3598 [44:49<16:53,  1.07it/s]
 70%|██████▉   | 2516/3598 [44:50<16:24,  1.10it/s]
 70%|██████▉   | 2517/3598 [44:51<18:58,  1.05s/it]
 70%|██████▉   | 2518/3598 [44:52<18:33,  1.03s/it]
 70%|███████   | 2519/3598 [44:53<17:55,  1.00it/s]
 70%|███████   | 2520/3598 [44:54<19:41,  1.10s/it]
                                                   

 70%|███████   | 2520/3598 [44:54<19:41,  1.10s/it]
 70%|███████   | 2521/3598 [44:55<18:43,  1.04s/it]
 70%|███████   | 2522/3598 [44:56<20:37,  1.15s/it]
 70%|███████   | 2523/3598 [44:58<22:09,  1.24s/it]
 70%|███████   | 2524/3598 [44:59<20:52,  1.17s/it]
 70%|███████   | 2525/3598 [45:00<19:15,  1.08s/it]
 70%|███████   | 2526/3598 [45:01<18:51,  1.06s/it]
 70%|███████   | 2527/3598 [45:02<18:25,  1.03s/it]
 70%|███████   | 2528/3598 [45:03<18:01,  1.01s/it]
 70%|███████   | 2529/3598 [45:04<17:19,  1.03it/s]
 70%|███████   | 2530/3598 [45:05<17:20,  1.03it/s]
                                                   

 70%|███████   | 2530/3598 [45:05<17:20,  1.03it/s]
 70%|███████   | 2531/3598 [45:06<19:06,  1.07s/it]
 70%|███████   | 2532/3598 [45:07<19:08,  1.08s/it]
 70%|███████   | 2533/3598 [45:08<17:55,  1.01s/it]
 70%|███████   | 2534/3598 [45:09<16:44,  1.06it/s]
 70%|███████   | 2535/3598 [45:10<16:31,  1.07it/s]
 70%|███████   | 2536/3598 [45:11<18:36,  1.05s/it]
 71%|███████   | 2537/3598 [45:12<17:47,  1.01s/it]
 71%|███████   | 2538/3598 [45:13<19:42,  1.12s/it]
 71%|███████   | 2539/3598 [45:14<18:54,  1.07s/it]
 71%|███████   | 2540/3598 [45:15<18:24,  1.04s/it]
                                                   

 71%|███████   | 2540/3598 [45:15<18:24,  1.04s/it]
 71%|███████   | 2541/3598 [45:16<17:59,  1.02s/it]
 71%|███████   | 2542/3598 [45:17<17:35,  1.00it/s]
 71%|███████   | 2543/3598 [45:18<17:19,  1.01it/s]
 71%|███████   | 2544/3598 [45:19<17:29,  1.00it/s]
 71%|███████   | 2545/3598 [45:20<17:25,  1.01it/s]
 71%|███████   | 2546/3598 [45:21<16:37,  1.05it/s]
 71%|███████   | 2547/3598 [45:22<16:24,  1.07it/s]
 71%|███████   | 2548/3598 [45:23<16:18,  1.07it/s]
 71%|███████   | 2549/3598 [45:23<15:59,  1.09it/s]
 71%|███████   | 2550/3598 [45:24<15:57,  1.09it/s]
                                                   

 71%|███████   | 2550/3598 [45:24<15:57,  1.09it/s]
 71%|███████   | 2551/3598 [45:25<15:59,  1.09it/s]
 71%|███████   | 2552/3598 [45:26<15:46,  1.11it/s]
 71%|███████   | 2553/3598 [45:27<17:07,  1.02it/s]
 71%|███████   | 2554/3598 [45:28<16:43,  1.04it/s]
 71%|███████   | 2555/3598 [45:29<17:13,  1.01it/s]
 71%|███████   | 2556/3598 [45:31<19:09,  1.10s/it]
 71%|███████   | 2557/3598 [45:32<18:53,  1.09s/it]
 71%|███████   | 2558/3598 [45:33<18:10,  1.05s/it]
 71%|███████   | 2559/3598 [45:34<17:16,  1.00it/s]
 71%|███████   | 2560/3598 [45:34<16:35,  1.04it/s]
                                                   

 71%|███████   | 2560/3598 [45:34<16:35,  1.04it/s]
 71%|███████   | 2561/3598 [45:35<16:23,  1.05it/s]
 71%|███████   | 2562/3598 [45:36<16:19,  1.06it/s]
 71%|███████   | 2563/3598 [45:38<18:31,  1.07s/it]
 71%|███████▏  | 2564/3598 [45:39<17:23,  1.01s/it]
 71%|███████▏  | 2565/3598 [45:40<18:26,  1.07s/it]
 71%|███████▏  | 2566/3598 [45:41<17:09,  1.00it/s]
 71%|███████▏  | 2567/3598 [45:42<17:54,  1.04s/it]
 71%|███████▏  | 2568/3598 [45:43<17:17,  1.01s/it]
 71%|███████▏  | 2569/3598 [45:44<16:51,  1.02it/s]
 71%|███████▏  | 2570/3598 [45:45<18:57,  1.11s/it]
                                                   
{'eval_loss': 0.7931228876113892, 'eval_bleu': 34.04529754823484, 'eval_chrf': 64.48607517273312, 'eval_runtime': 42.7183, 'eval_samples_per_second': 2.996, 'eval_steps_per_second': 0.094, 'epoch': 0.5}
{'loss': 0.9306, 'grad_norm': 1.0163995027542114, 'learning_rate': 0.00010462258630778234, 'epoch': 0.5}
{'loss': 0.8217, 'grad_norm': 2.198115825653076, 'learning_rate': 0.00010403744880046811, 'epoch': 0.51}
{'loss': 0.8926, 'grad_norm': 1.5556522607803345, 'learning_rate': 0.00010345231129315389, 'epoch': 0.51}
{'loss': 0.8042, 'grad_norm': 1.499470591545105, 'learning_rate': 0.00010286717378583967, 'epoch': 0.51}
{'loss': 0.7806, 'grad_norm': 1.47234308719635, 'learning_rate': 0.00010228203627852547, 'epoch': 0.51}
{'loss': 0.914, 'grad_norm': 1.721991777420044, 'learning_rate': 0.00010169689877121125, 'epoch': 0.52}
{'loss': 0.8043, 'grad_norm': 1.593459963798523, 'learning_rate': 0.00010111176126389703, 'epoch': 0.52}
{'loss': 0.8101, 'grad_norm': 1.5574313402175903, 'learning_rate': 0.0001005266237565828, 'epoch': 0.52}
{'loss': 0.6948, 'grad_norm': 1.370987892150879, 'learning_rate': 9.994148624926858e-05, 'epoch': 0.53}
{'loss': 0.7938, 'grad_norm': 1.3755780458450317, 'learning_rate': 9.935634874195436e-05, 'epoch': 0.53}
{'loss': 0.7416, 'grad_norm': 1.7554758787155151, 'learning_rate': 9.877121123464015e-05, 'epoch': 0.53}
{'loss': 0.8454, 'grad_norm': 1.7844148874282837, 'learning_rate': 9.818607372732592e-05, 'epoch': 0.53}
{'loss': 0.8501, 'grad_norm': 1.3822129964828491, 'learning_rate': 9.760093622001171e-05, 'epoch': 0.54}
{'loss': 0.7248, 'grad_norm': 1.7859715223312378, 'learning_rate': 9.70157987126975e-05, 'epoch': 0.54}
{'loss': 0.7495, 'grad_norm': 1.0760029554367065, 'learning_rate': 9.643066120538326e-05, 'epoch': 0.54}
{'loss': 0.9286, 'grad_norm': 1.3241146802902222, 'learning_rate': 9.584552369806906e-05, 'epoch': 0.54}
{'loss': 0.8068, 'grad_norm': 1.3033974170684814, 'learning_rate': 9.526038619075484e-05, 'epoch': 0.55}
{'loss': 0.8309, 'grad_norm': 1.403512954711914, 'learning_rate': 9.46752486834406e-05, 'epoch': 0.55}
{'loss': 0.8311, 'grad_norm': 1.3144944906234741, 'learning_rate': 9.40901111761264e-05, 'epoch': 0.55}
{'loss': 0.6458, 'grad_norm': 1.645932674407959, 'learning_rate': 9.350497366881218e-05, 'epoch': 0.56}
{'loss': 0.6814, 'grad_norm': 2.137310028076172, 'learning_rate': 9.291983616149795e-05, 'epoch': 0.56}
{'loss': 0.6609, 'grad_norm': 1.8444314002990723, 'learning_rate': 9.233469865418374e-05, 'epoch': 0.56}
{'loss': 0.8411, 'grad_norm': 1.7156598567962646, 'learning_rate': 9.174956114686952e-05, 'epoch': 0.56}
{'loss': 0.7718, 'grad_norm': 2.0496068000793457, 'learning_rate': 9.116442363955529e-05, 'epoch': 0.57}
{'loss': 0.7309, 'grad_norm': 1.2874308824539185, 'learning_rate': 9.057928613224108e-05, 'epoch': 0.57}
{'loss': 0.755, 'grad_norm': 1.6933300495147705, 'learning_rate': 8.999414862492687e-05, 'epoch': 0.57}
{'loss': 0.6792, 'grad_norm': 1.5075557231903076, 'learning_rate': 8.940901111761265e-05, 'epoch': 0.58}
{'loss': 0.717, 'grad_norm': 1.6459001302719116, 'learning_rate': 8.882387361029843e-05, 'epoch': 0.58}
{'loss': 0.7334, 'grad_norm': 1.4591081142425537, 'learning_rate': 8.823873610298421e-05, 'epoch': 0.58}
{'loss': 0.82, 'grad_norm': 1.903427004814148, 'learning_rate': 8.765359859566999e-05, 'epoch': 0.58}
{'loss': 0.7907, 'grad_norm': 1.269168496131897, 'learning_rate': 8.706846108835577e-05, 'epoch': 0.59}
{'loss': 0.5817, 'grad_norm': 1.237375259399414, 'learning_rate': 8.648332358104155e-05, 'epoch': 0.59}
{'loss': 0.7943, 'grad_norm': 1.5938820838928223, 'learning_rate': 8.589818607372733e-05, 'epoch': 0.59}
{'loss': 0.7878, 'grad_norm': 1.3069621324539185, 'learning_rate': 8.531304856641311e-05, 'epoch': 0.59}
{'loss': 0.641, 'grad_norm': 1.2887060642242432, 'learning_rate': 8.47279110590989e-05, 'epoch': 0.6}
{'loss': 0.7156, 'grad_norm': 1.7033811807632446, 'learning_rate': 8.414277355178467e-05, 'epoch': 0.6}
{'loss': 0.6544, 'grad_norm': 1.3568116426467896, 'learning_rate': 8.355763604447046e-05, 'epoch': 0.6}
{'loss': 0.6654, 'grad_norm': 0.8526349663734436, 'learning_rate': 8.297249853715624e-05, 'epoch': 0.61}
{'loss': 0.7027, 'grad_norm': 2.007845878601074, 'learning_rate': 8.238736102984202e-05, 'epoch': 0.61}
{'loss': 0.6089, 'grad_norm': 1.4187250137329102, 'learning_rate': 8.18022235225278e-05, 'epoch': 0.61}
{'loss': 0.6562, 'grad_norm': 1.5305442810058594, 'learning_rate': 8.121708601521358e-05, 'epoch': 0.61}
{'loss': 0.6893, 'grad_norm': 1.2007344961166382, 'learning_rate': 8.063194850789936e-05, 'epoch': 0.62}
{'loss': 0.7424, 'grad_norm': 1.8552879095077515, 'learning_rate': 8.004681100058514e-05, 'epoch': 0.62}
{'loss': 0.6859, 'grad_norm': 1.5317975282669067, 'learning_rate': 7.946167349327092e-05, 'epoch': 0.62}
{'loss': 0.6576, 'grad_norm': 2.109940528869629, 'learning_rate': 7.88765359859567e-05, 'epoch': 0.63}
{'loss': 0.7508, 'grad_norm': 1.2298418283462524, 'learning_rate': 7.829139847864248e-05, 'epoch': 0.63}
{'loss': 0.6816, 'grad_norm': 1.3538986444473267, 'learning_rate': 7.770626097132827e-05, 'epoch': 0.63}
{'loss': 0.746, 'grad_norm': 1.1908177137374878, 'learning_rate': 7.712112346401405e-05, 'epoch': 0.63}
{'loss': 0.7993, 'grad_norm': 1.1318070888519287, 'learning_rate': 7.653598595669983e-05, 'epoch': 0.64}
{'loss': 0.8078, 'grad_norm': 1.5441361665725708, 'learning_rate': 7.595084844938561e-05, 'epoch': 0.64}
{'loss': 0.7411, 'grad_norm': 1.4957458972930908, 'learning_rate': 7.536571094207139e-05, 'epoch': 0.64}
{'loss': 0.6281, 'grad_norm': 1.059766411781311, 'learning_rate': 7.478057343475717e-05, 'epoch': 0.64}
{'loss': 0.5841, 'grad_norm': 1.3983445167541504, 'learning_rate': 7.419543592744296e-05, 'epoch': 0.65}
{'loss': 0.7042, 'grad_norm': 1.3938812017440796, 'learning_rate': 7.361029842012873e-05, 'epoch': 0.65}
{'loss': 0.8477, 'grad_norm': 1.8146742582321167, 'learning_rate': 7.302516091281451e-05, 'epoch': 0.65}
{'loss': 0.7584, 'grad_norm': 1.1325688362121582, 'learning_rate': 7.244002340550031e-05, 'epoch': 0.66}
{'loss': 0.8167, 'grad_norm': 1.1988415718078613, 'learning_rate': 7.185488589818607e-05, 'epoch': 0.66}
{'loss': 0.7592, 'grad_norm': 0.8537703156471252, 'learning_rate': 7.126974839087186e-05, 'epoch': 0.66}
{'loss': 0.6157, 'grad_norm': 1.336398959159851, 'learning_rate': 7.068461088355765e-05, 'epoch': 0.66}
{'loss': 0.6364, 'grad_norm': 1.6869962215423584, 'learning_rate': 7.009947337624342e-05, 'epoch': 0.67}
{'loss': 0.7279, 'grad_norm': 1.4955002069473267, 'learning_rate': 6.95143358689292e-05, 'epoch': 0.67}
{'loss': 0.7611, 'grad_norm': 0.9639846682548523, 'learning_rate': 6.892919836161499e-05, 'epoch': 0.67}
{'loss': 0.658, 'grad_norm': 1.3936442136764526, 'learning_rate': 6.834406085430076e-05, 'epoch': 0.68}
{'loss': 0.6369, 'grad_norm': 1.0887020826339722, 'learning_rate': 6.775892334698654e-05, 'epoch': 0.68}
{'loss': 0.6722, 'grad_norm': 1.2021764516830444, 'learning_rate': 6.717378583967232e-05, 'epoch': 0.68}
{'loss': 0.58, 'grad_norm': 1.4362479448318481, 'learning_rate': 6.65886483323581e-05, 'epoch': 0.68}
{'loss': 0.6546, 'grad_norm': 1.6736342906951904, 'learning_rate': 6.600351082504388e-05, 'epoch': 0.69}
{'loss': 0.6311, 'grad_norm': 1.3882834911346436, 'learning_rate': 6.541837331772966e-05, 'epoch': 0.69}
{'loss': 0.8076, 'grad_norm': 1.1238460540771484, 'learning_rate': 6.483323581041545e-05, 'epoch': 0.69}
{'loss': 0.725, 'grad_norm': 1.5184351205825806, 'learning_rate': 6.424809830310124e-05, 'epoch': 0.69}
{'loss': 0.6874, 'grad_norm': 1.5520931482315063, 'learning_rate': 6.366296079578701e-05, 'epoch': 0.7}
{'loss': 0.6594, 'grad_norm': 1.1347784996032715, 'learning_rate': 6.307782328847279e-05, 'epoch': 0.7}
{'loss': 0.5981, 'grad_norm': 1.0782485008239746, 'learning_rate': 6.249268578115858e-05, 'epoch': 0.7}
{'loss': 0.7258, 'grad_norm': 1.3466250896453857, 'learning_rate': 6.190754827384435e-05, 'epoch': 0.71}
{'loss': 0.5458, 'grad_norm': 1.4698735475540161, 'learning_rate': 6.132241076653013e-05, 'epoch': 0.71}
{'loss': 0.6835, 'grad_norm': 1.6065407991409302, 'learning_rate': 6.073727325921592e-05, 'epoch': 0.71}
{'loss': 0.7253, 'grad_norm': 0.9917827248573303, 'learning_rate': 6.015213575190169e-05, 'epoch': 0.71}
 71%|███████▏  | 2570/3598 [45:45<18:57,  1.11s/it]
 71%|███████▏  | 2571/3598 [45:46<17:43,  1.04s/it]
 71%|███████▏  | 2572/3598 [45:47<17:44,  1.04s/it]
 72%|███████▏  | 2573/3598 [45:48<19:36,  1.15s/it]
 72%|███████▏  | 2574/3598 [45:50<20:50,  1.22s/it]
 72%|███████▏  | 2575/3598 [45:51<20:43,  1.22s/it]
 72%|███████▏  | 2576/3598 [45:52<19:03,  1.12s/it]
 72%|███████▏  | 2577/3598 [45:53<20:20,  1.20s/it]
 72%|███████▏  | 2578/3598 [45:54<20:25,  1.20s/it]
 72%|███████▏  | 2579/3598 [45:55<18:48,  1.11s/it]
 72%|███████▏  | 2580/3598 [45:56<17:37,  1.04s/it]
                                                   

 72%|███████▏  | 2580/3598 [45:56<17:37,  1.04s/it]
 72%|███████▏  | 2581/3598 [45:57<17:25,  1.03s/it]
 72%|███████▏  | 2582/3598 [45:58<17:01,  1.01s/it]
 72%|███████▏  | 2583/3598 [45:59<16:53,  1.00it/s]
 72%|███████▏  | 2584/3598 [46:00<16:33,  1.02it/s]
 72%|███████▏  | 2585/3598 [46:01<16:25,  1.03it/s]
 72%|███████▏  | 2586/3598 [46:02<15:39,  1.08it/s]
 72%|███████▏  | 2587/3598 [46:03<16:40,  1.01it/s]
 72%|███████▏  | 2588/3598 [46:04<16:16,  1.03it/s]
 72%|███████▏  | 2589/3598 [46:05<16:34,  1.01it/s]
 72%|███████▏  | 2590/3598 [46:06<16:33,  1.02it/s]
                                                   

 72%|███████▏  | 2590/3598 [46:06<16:33,  1.02it/s]
 72%|███████▏  | 2591/3598 [46:07<18:21,  1.09s/it]
 72%|███████▏  | 2592/3598 [46:08<18:54,  1.13s/it]
 72%|███████▏  | 2593/3598 [46:10<19:19,  1.15s/it]
 72%|███████▏  | 2594/3598 [46:11<19:01,  1.14s/it]
 72%|███████▏  | 2595/3598 [46:12<18:02,  1.08s/it]
 72%|███████▏  | 2596/3598 [46:13<19:07,  1.15s/it]
 72%|███████▏  | 2597/3598 [46:14<19:00,  1.14s/it]
 72%|███████▏  | 2598/3598 [46:15<17:14,  1.03s/it]
 72%|███████▏  | 2599/3598 [46:16<16:52,  1.01s/it]
 72%|███████▏  | 2600/3598 [46:17<15:54,  1.05it/s]
                                                   

 72%|███████▏  | 2600/3598 [46:17<15:54,  1.05it/s]
 72%|███████▏  | 2601/3598 [46:18<17:59,  1.08s/it]
 72%|███████▏  | 2602/3598 [46:19<19:33,  1.18s/it]
 72%|███████▏  | 2603/3598 [46:20<18:28,  1.11s/it]
 72%|███████▏  | 2604/3598 [46:21<18:16,  1.10s/it]
 72%|███████▏  | 2605/3598 [46:23<19:14,  1.16s/it]
 72%|███████▏  | 2606/3598 [46:24<18:56,  1.15s/it]
 72%|███████▏  | 2607/3598 [46:25<17:45,  1.08s/it]
 72%|███████▏  | 2608/3598 [46:26<16:40,  1.01s/it]
 73%|███████▎  | 2609/3598 [46:26<15:31,  1.06it/s]
 73%|███████▎  | 2610/3598 [46:28<16:34,  1.01s/it]
                                                   

 73%|███████▎  | 2610/3598 [46:28<16:34,  1.01s/it]
 73%|███████▎  | 2611/3598 [46:29<16:27,  1.00s/it]
 73%|███████▎  | 2612/3598 [46:30<16:20,  1.01it/s]
 73%|███████▎  | 2613/3598 [46:31<18:19,  1.12s/it]
 73%|███████▎  | 2614/3598 [46:32<17:48,  1.09s/it]
 73%|███████▎  | 2615/3598 [46:33<16:54,  1.03s/it]
 73%|███████▎  | 2616/3598 [46:34<15:42,  1.04it/s]
 73%|███████▎  | 2617/3598 [46:35<16:52,  1.03s/it]
 73%|███████▎  | 2618/3598 [46:36<16:00,  1.02it/s]
 73%|███████▎  | 2619/3598 [46:37<17:45,  1.09s/it]
 73%|███████▎  | 2620/3598 [46:38<18:08,  1.11s/it]
                                                   

 73%|███████▎  | 2620/3598 [46:38<18:08,  1.11s/it]
 73%|███████▎  | 2621/3598 [46:39<17:09,  1.05s/it]
 73%|███████▎  | 2622/3598 [46:41<18:49,  1.16s/it]
 73%|███████▎  | 2623/3598 [46:42<17:51,  1.10s/it]
 73%|███████▎  | 2624/3598 [46:43<18:56,  1.17s/it]
 73%|███████▎  | 2625/3598 [46:44<17:44,  1.09s/it]
 73%|███████▎  | 2626/3598 [46:45<16:33,  1.02s/it]
 73%|███████▎  | 2627/3598 [46:46<16:02,  1.01it/s]
 73%|███████▎  | 2628/3598 [46:46<15:11,  1.06it/s]
 73%|███████▎  | 2629/3598 [46:47<14:42,  1.10it/s]
 73%|███████▎  | 2630/3598 [46:48<14:32,  1.11it/s]
                                                   

 73%|███████▎  | 2630/3598 [46:48<14:32,  1.11it/s]
 73%|███████▎  | 2631/3598 [46:49<15:15,  1.06it/s]
 73%|███████▎  | 2632/3598 [46:50<14:46,  1.09it/s]
 73%|███████▎  | 2633/3598 [46:51<14:35,  1.10it/s]
 73%|███████▎  | 2634/3598 [46:52<14:47,  1.09it/s]
 73%|███████▎  | 2635/3598 [46:53<15:37,  1.03it/s]
 73%|███████▎  | 2636/3598 [46:54<15:43,  1.02it/s]
 73%|███████▎  | 2637/3598 [46:55<17:49,  1.11s/it]
 73%|███████▎  | 2638/3598 [46:56<16:32,  1.03s/it]
 73%|███████▎  | 2639/3598 [46:57<17:19,  1.08s/it]
 73%|███████▎  | 2640/3598 [46:58<16:25,  1.03s/it]
                                                   

 73%|███████▎  | 2640/3598 [46:58<16:25,  1.03s/it]
 73%|███████▎  | 2641/3598 [46:59<16:13,  1.02s/it]
 73%|███████▎  | 2642/3598 [47:00<16:54,  1.06s/it]
 73%|███████▎  | 2643/3598 [47:01<16:02,  1.01s/it]
 73%|███████▎  | 2644/3598 [47:03<17:51,  1.12s/it]
 74%|███████▎  | 2645/3598 [47:04<17:02,  1.07s/it]
 74%|███████▎  | 2646/3598 [47:05<18:31,  1.17s/it]
 74%|███████▎  | 2647/3598 [47:06<17:19,  1.09s/it]
 74%|███████▎  | 2648/3598 [47:07<16:55,  1.07s/it]
 74%|███████▎  | 2649/3598 [47:08<17:09,  1.09s/it]
 74%|███████▎  | 2650/3598 [47:09<17:52,  1.13s/it]
                                                   

 74%|███████▎  | 2650/3598 [47:09<17:52,  1.13s/it]
 74%|███████▎  | 2651/3598 [47:11<18:43,  1.19s/it]
 74%|███████▎  | 2652/3598 [47:12<17:17,  1.10s/it]
 74%|███████▎  | 2653/3598 [47:12<15:50,  1.01s/it]
 74%|███████▍  | 2654/3598 [47:13<15:11,  1.04it/s]
 74%|███████▍  | 2655/3598 [47:14<15:42,  1.00it/s]
 74%|███████▍  | 2656/3598 [47:15<16:04,  1.02s/it]
 74%|███████▍  | 2657/3598 [47:16<16:08,  1.03s/it]
 74%|███████▍  | 2658/3598 [47:17<15:28,  1.01it/s]
 74%|███████▍  | 2659/3598 [47:18<15:24,  1.02it/s]
 74%|███████▍  | 2660/3598 [47:20<16:34,  1.06s/it]
                                                   

 74%|███████▍  | 2660/3598 [47:20<16:34,  1.06s/it]
 74%|███████▍  | 2661/3598 [47:20<15:34,  1.00it/s]
 74%|███████▍  | 2662/3598 [47:21<15:01,  1.04it/s]
 74%|███████▍  | 2663/3598 [47:22<14:39,  1.06it/s]
 74%|███████▍  | 2664/3598 [47:24<16:39,  1.07s/it]
 74%|███████▍  | 2665/3598 [47:25<18:21,  1.18s/it]
 74%|███████▍  | 2666/3598 [47:26<17:02,  1.10s/it]
 74%|███████▍  | 2667/3598 [47:27<18:25,  1.19s/it]
 74%|███████▍  | 2668/3598 [47:28<16:53,  1.09s/it]
 74%|███████▍  | 2669/3598 [47:29<17:35,  1.14s/it]
 74%|███████▍  | 2670/3598 [47:31<18:15,  1.18s/it]
                                                   

 74%|███████▍  | 2670/3598 [47:31<18:15,  1.18s/it]
 74%|███████▍  | 2671/3598 [47:32<16:56,  1.10s/it]
 74%|███████▍  | 2672/3598 [47:33<18:05,  1.17s/it]
 74%|███████▍  | 2673/3598 [47:34<17:15,  1.12s/it]
 74%|███████▍  | 2674/3598 [47:35<15:43,  1.02s/it]
 74%|███████▍  | 2675/3598 [47:36<15:27,  1.01s/it]
 74%|███████▍  | 2676/3598 [47:37<14:48,  1.04it/s]
 74%|███████▍  | 2677/3598 [47:38<16:26,  1.07s/it]
 74%|███████▍  | 2678/3598 [47:39<15:29,  1.01s/it]
 74%|███████▍  | 2679/3598 [47:40<15:04,  1.02it/s]
 74%|███████▍  | 2680/3598 [47:41<14:30,  1.05it/s]
                                                   

 74%|███████▍  | 2680/3598 [47:41<14:30,  1.05it/s]
 75%|███████▍  | 2681/3598 [47:42<16:02,  1.05s/it]
 75%|███████▍  | 2682/3598 [47:43<17:04,  1.12s/it]
 75%|███████▍  | 2683/3598 [47:44<16:33,  1.09s/it]
 75%|███████▍  | 2684/3598 [47:45<15:32,  1.02s/it]
 75%|███████▍  | 2685/3598 [47:46<16:03,  1.05s/it]
 75%|███████▍  | 2686/3598 [47:47<15:22,  1.01s/it]
 75%|███████▍  | 2687/3598 [47:48<16:49,  1.11s/it]
 75%|███████▍  | 2688/3598 [47:49<16:29,  1.09s/it]
 75%|███████▍  | 2689/3598 [47:50<15:48,  1.04s/it]
 75%|███████▍  | 2690/3598 [47:52<16:47,  1.11s/it]
                                                   

 75%|███████▍  | 2690/3598 [47:52<16:47,  1.11s/it]
 75%|███████▍  | 2691/3598 [47:52<15:48,  1.05s/it]
 75%|███████▍  | 2692/3598 [47:53<15:24,  1.02s/it]
 75%|███████▍  | 2693/3598 [47:54<14:44,  1.02it/s]
 75%|███████▍  | 2694/3598 [47:56<16:25,  1.09s/it]
 75%|███████▍  | 2695/3598 [47:57<15:51,  1.05s/it]
 75%|███████▍  | 2696/3598 [47:58<14:57,  1.01it/s]
 75%|███████▍  | 2697/3598 [47:58<14:16,  1.05it/s]
 75%|███████▍  | 2698/3598 [47:59<14:11,  1.06it/s]
 75%|███████▌  | 2699/3598 [48:01<16:14,  1.08s/it]
 75%|███████▌  | 2700/3598 [48:02<17:48,  1.19s/it]
                                                   

 75%|███████▌  | 2700/3598 [48:02<17:48,  1.19s/it]
{'loss': 0.7438, 'grad_norm': 1.2688491344451904, 'learning_rate': 5.956699824458748e-05, 'epoch': 0.72}
{'loss': 0.5903, 'grad_norm': 1.4485528469085693, 'learning_rate': 5.898186073727326e-05, 'epoch': 0.72}
{'loss': 0.6934, 'grad_norm': 1.8393375873565674, 'learning_rate': 5.8396723229959036e-05, 'epoch': 0.72}
{'loss': 0.781, 'grad_norm': 1.1079840660095215, 'learning_rate': 5.7811585722644824e-05, 'epoch': 0.73}
{'loss': 0.6871, 'grad_norm': 1.1297825574874878, 'learning_rate': 5.722644821533061e-05, 'epoch': 0.73}
{'loss': 0.563, 'grad_norm': 2.4137139320373535, 'learning_rate': 5.664131070801638e-05, 'epoch': 0.73}
{'loss': 0.6087, 'grad_norm': 1.1955472230911255, 'learning_rate': 5.6056173200702166e-05, 'epoch': 0.73}
{'loss': 0.8348, 'grad_norm': 1.0724763870239258, 'learning_rate': 5.5471035693387954e-05, 'epoch': 0.74}
{'loss': 0.5881, 'grad_norm': 1.2351850271224976, 'learning_rate': 5.488589818607373e-05, 'epoch': 0.74}
{'loss': 0.6355, 'grad_norm': 1.2210818529129028, 'learning_rate': 5.430076067875951e-05, 'epoch': 0.74}
{'loss': 0.6666, 'grad_norm': 1.2278271913528442, 'learning_rate': 5.37156231714453e-05, 'epoch': 0.74}
{'loss': 0.7498, 'grad_norm': 1.3193840980529785, 'learning_rate': 5.313048566413107e-05, 'epoch': 0.75}
{'loss': 0.6763, 'grad_norm': 1.2186802625656128, 'learning_rate': 5.254534815681685e-05, 'epoch': 0.75}


  0%|          | 0/4 [00:00<?, ?it/s]

 50%|█████     | 2/4 [00:13<00:13,  6.53s/it]

 75%|███████▌  | 3/4 [00:28<00:10, 10.21s/it]

100%|██████████| 4/4 [00:33<00:00,  8.19s/it]
                                                   

                                             

 75%|███████▌  | 2700/3598 [48:44<17:48,  1.19s/it]

100%|██████████| 4/4 [00:33<00:00,  8.19s/it]

                                             /opt/mobtranslate-v24-venv/lib/python3.11/site-packages/peft/utils/save_and_load.py:386: UserWarning: Setting `save_embedding_layers` to `True` as the embedding layer has been resized during finetuning.
  warnings.warn(

 75%|███████▌  | 2701/3598 [48:49<3:44:44, 15.03s/it]
 75%|███████▌  | 2702/3598 [48:50<2:41:25, 10.81s/it]
 75%|███████▌  | 2703/3598 [48:51<1:56:48,  7.83s/it]
 75%|███████▌  | 2704/3598 [48:52<1:25:46,  5.76s/it]
 75%|███████▌  | 2705/3598 [48:53<1:03:46,  4.29s/it]
 75%|███████▌  | 2706/3598 [48:54<49:17,  3.32s/it]  
 75%|███████▌  | 2707/3598 [48:55<38:12,  2.57s/it]
 75%|███████▌  | 2708/3598 [48:56<30:31,  2.06s/it]
 75%|███████▌  | 2709/3598 [48:57<27:07,  1.83s/it]
 75%|███████▌  | 2710/3598 [48:58<23:22,  1.58s/it]
                                                   

 75%|███████▌  | 2710/3598 [48:58<23:22,  1.58s/it]
 75%|███████▌  | 2711/3598 [48:59<21:13,  1.44s/it]
 75%|███████▌  | 2712/3598 [49:00<18:30,  1.25s/it]
 75%|███████▌  | 2713/3598 [49:01<18:40,  1.27s/it]
 75%|███████▌  | 2714/3598 [49:03<18:51,  1.28s/it]
 75%|███████▌  | 2715/3598 [49:04<17:20,  1.18s/it]
 75%|███████▌  | 2716/3598 [49:05<16:26,  1.12s/it]
 76%|███████▌  | 2717/3598 [49:06<17:09,  1.17s/it]
 76%|███████▌  | 2718/3598 [49:07<18:02,  1.23s/it]
 76%|███████▌  | 2719/3598 [49:08<16:28,  1.12s/it]
 76%|███████▌  | 2720/3598 [49:09<15:37,  1.07s/it]
                                                   

 76%|███████▌  | 2720/3598 [49:09<15:37,  1.07s/it]
 76%|███████▌  | 2721/3598 [49:10<17:04,  1.17s/it]
 76%|███████▌  | 2722/3598 [49:11<16:21,  1.12s/it]
 76%|███████▌  | 2723/3598 [49:12<15:15,  1.05s/it]
 76%|███████▌  | 2724/3598 [49:13<14:33,  1.00it/s]
 76%|███████▌  | 2725/3598 [49:14<14:26,  1.01it/s]
 76%|███████▌  | 2726/3598 [49:15<14:12,  1.02it/s]
 76%|███████▌  | 2727/3598 [49:16<14:04,  1.03it/s]
 76%|███████▌  | 2728/3598 [49:17<15:43,  1.08s/it]
 76%|███████▌  | 2729/3598 [49:19<16:47,  1.16s/it]
 76%|███████▌  | 2730/3598 [49:20<17:04,  1.18s/it]
                                                   

 76%|███████▌  | 2730/3598 [49:20<17:04,  1.18s/it]
 76%|███████▌  | 2731/3598 [49:21<15:53,  1.10s/it]
 76%|███████▌  | 2732/3598 [49:22<16:27,  1.14s/it]
 76%|███████▌  | 2733/3598 [49:23<15:46,  1.09s/it]
 76%|███████▌  | 2734/3598 [49:24<15:56,  1.11s/it]
 76%|███████▌  | 2735/3598 [49:25<15:06,  1.05s/it]
 76%|███████▌  | 2736/3598 [49:27<16:34,  1.15s/it]
 76%|███████▌  | 2737/3598 [49:28<17:28,  1.22s/it]
 76%|███████▌  | 2738/3598 [49:29<16:00,  1.12s/it]
 76%|███████▌  | 2739/3598 [49:30<14:56,  1.04s/it]
 76%|███████▌  | 2740/3598 [49:31<14:28,  1.01s/it]
                                                   

 76%|███████▌  | 2740/3598 [49:31<14:28,  1.01s/it]
 76%|███████▌  | 2741/3598 [49:32<14:10,  1.01it/s]
 76%|███████▌  | 2742/3598 [49:32<13:19,  1.07it/s]
 76%|███████▌  | 2743/3598 [49:33<13:05,  1.09it/s]
 76%|███████▋  | 2744/3598 [49:34<12:59,  1.10it/s]
 76%|███████▋  | 2745/3598 [49:35<13:06,  1.08it/s]
 76%|███████▋  | 2746/3598 [49:36<12:55,  1.10it/s]
 76%|███████▋  | 2747/3598 [49:37<13:26,  1.06it/s]
 76%|███████▋  | 2748/3598 [49:38<13:04,  1.08it/s]
 76%|███████▋  | 2749/3598 [49:39<12:57,  1.09it/s]
 76%|███████▋  | 2750/3598 [49:40<14:52,  1.05s/it]
                                                   

 76%|███████▋  | 2750/3598 [49:40<14:52,  1.05s/it]
 76%|███████▋  | 2751/3598 [49:41<14:40,  1.04s/it]
 76%|███████▋  | 2752/3598 [49:42<14:06,  1.00s/it]
 77%|███████▋  | 2753/3598 [49:43<14:28,  1.03s/it]
 77%|███████▋  | 2754/3598 [49:44<14:00,  1.00it/s]
 77%|███████▋  | 2755/3598 [49:45<13:19,  1.05it/s]
 77%|███████▋  | 2756/3598 [49:46<15:14,  1.09s/it]
 77%|███████▋  | 2757/3598 [49:47<15:17,  1.09s/it]
 77%|███████▋  | 2758/3598 [49:49<16:41,  1.19s/it]
 77%|███████▋  | 2759/3598 [49:50<15:29,  1.11s/it]
 77%|███████▋  | 2760/3598 [49:51<14:43,  1.05s/it]
                                                   

 77%|███████▋  | 2760/3598 [49:51<14:43,  1.05s/it]
 77%|███████▋  | 2761/3598 [49:52<14:49,  1.06s/it]
 77%|███████▋  | 2762/3598 [49:53<13:59,  1.00s/it]
 77%|███████▋  | 2763/3598 [49:54<13:48,  1.01it/s]
 77%|███████▋  | 2764/3598 [49:54<13:17,  1.05it/s]
 77%|███████▋  | 2765/3598 [49:56<15:03,  1.08s/it]
 77%|███████▋  | 2766/3598 [49:57<15:57,  1.15s/it]
 77%|███████▋  | 2767/3598 [49:58<15:02,  1.09s/it]
 77%|███████▋  | 2768/3598 [49:59<14:31,  1.05s/it]
 77%|███████▋  | 2769/3598 [50:00<14:11,  1.03s/it]
 77%|███████▋  | 2770/3598 [50:01<13:47,  1.00it/s]
                                                   

 77%|███████▋  | 2770/3598 [50:01<13:47,  1.00it/s]
 77%|███████▋  | 2771/3598 [50:02<13:34,  1.02it/s]
 77%|███████▋  | 2772/3598 [50:03<15:06,  1.10s/it]
 77%|███████▋  | 2773/3598 [50:04<14:15,  1.04s/it]
 77%|███████▋  | 2774/3598 [50:05<13:50,  1.01s/it]
 77%|███████▋  | 2775/3598 [50:06<14:07,  1.03s/it]
 77%|███████▋  | 2776/3598 [50:07<14:25,  1.05s/it]
 77%|███████▋  | 2777/3598 [50:08<13:52,  1.01s/it]
 77%|███████▋  | 2778/3598 [50:09<13:15,  1.03it/s]
 77%|███████▋  | 2779/3598 [50:11<14:59,  1.10s/it]
 77%|███████▋  | 2780/3598 [50:11<14:09,  1.04s/it]
                                                   

 77%|███████▋  | 2780/3598 [50:11<14:09,  1.04s/it]
 77%|███████▋  | 2781/3598 [50:12<13:32,  1.01it/s]
 77%|███████▋  | 2782/3598 [50:13<13:50,  1.02s/it]
 77%|███████▋  | 2783/3598 [50:14<13:35,  1.00s/it]
 77%|███████▋  | 2784/3598 [50:15<13:15,  1.02it/s]
 77%|███████▋  | 2785/3598 [50:17<14:38,  1.08s/it]
 77%|███████▋  | 2786/3598 [50:17<13:57,  1.03s/it]
 77%|███████▋  | 2787/3598 [50:18<13:26,  1.01it/s]
 77%|███████▋  | 2788/3598 [50:19<13:16,  1.02it/s]
 78%|███████▊  | 2789/3598 [50:21<14:53,  1.10s/it]
 78%|███████▊  | 2790/3598 [50:22<14:00,  1.04s/it]
                                                   

 78%|███████▊  | 2790/3598 [50:22<14:00,  1.04s/it]
 78%|███████▊  | 2791/3598 [50:22<13:03,  1.03it/s]
 78%|███████▊  | 2792/3598 [50:23<13:10,  1.02it/s]
 78%|███████▊  | 2793/3598 [50:24<12:59,  1.03it/s]
 78%|███████▊  | 2794/3598 [50:26<14:28,  1.08s/it]
 78%|███████▊  | 2795/3598 [50:27<15:49,  1.18s/it]
 78%|███████▊  | 2796/3598 [50:28<14:47,  1.11s/it]
 78%|███████▊  | 2797/3598 [50:30<16:00,  1.20s/it]
 78%|███████▊  | 2798/3598 [50:30<14:46,  1.11s/it]
 78%|███████▊  | 2799/3598 [50:32<15:54,  1.19s/it]
 78%|███████▊  | 2800/3598 [50:33<15:00,  1.13s/it]
                                                   

 78%|███████▊  | 2800/3598 [50:33<15:00,  1.13s/it]
 78%|███████▊  | 2801/3598 [50:34<14:14,  1.07s/it]
 78%|███████▊  | 2802/3598 [50:35<14:53,  1.12s/it]
 78%|███████▊  | 2803/3598 [50:36<13:42,  1.03s/it]
 78%|███████▊  | 2804/3598 [50:37<14:47,  1.12s/it]
 78%|███████▊  | 2805/3598 [50:38<14:07,  1.07s/it]
 78%|███████▊  | 2806/3598 [50:39<13:09,  1.00it/s]
 78%|███████▊  | 2807/3598 [50:40<12:47,  1.03it/s]
 78%|███████▊  | 2808/3598 [50:41<12:23,  1.06it/s]
 78%|███████▊  | 2809/3598 [50:42<12:44,  1.03it/s]
 78%|███████▊  | 2810/3598 [50:43<13:50,  1.05s/it]
                                                   

 78%|███████▊  | 2810/3598 [50:43<13:50,  1.05s/it]
 78%|███████▊  | 2811/3598 [50:44<13:18,  1.02s/it]
 78%|███████▊  | 2812/3598 [50:45<14:01,  1.07s/it]
 78%|███████▊  | 2813/3598 [50:46<13:20,  1.02s/it]
 78%|███████▊  | 2814/3598 [50:47<12:46,  1.02it/s]
 78%|███████▊  | 2815/3598 [50:48<14:25,  1.11s/it]
 78%|███████▊  | 2816/3598 [50:49<13:38,  1.05s/it]
 78%|███████▊  | 2817/3598 [50:50<14:23,  1.11s/it]
 78%|███████▊  | 2818/3598 [50:52<15:32,  1.20s/it]
 78%|███████▊  | 2819/3598 [50:53<16:16,  1.25s/it]
 78%|███████▊  | 2820/3598 [50:54<14:47,  1.14s/it]
                                                   

 78%|███████▊  | 2820/3598 [50:54<14:47,  1.14s/it]
 78%|███████▊  | 2821/3598 [50:55<14:58,  1.16s/it]
 78%|███████▊  | 2822/3598 [50:56<14:13,  1.10s/it]
 78%|███████▊  | 2823/3598 [50:58<15:06,  1.17s/it]
 78%|███████▊  | 2824/3598 [50:59<14:38,  1.14s/it]
 79%|███████▊  | 2825/3598 [51:00<14:29,  1.12s/it]
 79%|███████▊  | 2826/3598 [51:01<13:39,  1.06s/it]
 79%|███████▊  | 2827/3598 [51:02<13:08,  1.02s/it]
 79%|███████▊  | 2828/3598 [51:03<13:02,  1.02s/it]
 79%|███████▊  | 2829/3598 [51:04<13:49,  1.08s/it]
 79%|███████▊  | 2830/3598 [51:05<14:04,  1.10s/it]
                                                   

 79%|███████▊  | 2830/3598 [51:05<14:04,  1.10s/it]
 79%|███████▊  | 2831/3598 [51:06<14:14,  1.11s/it]
 79%|███████▊  | 2832/3598 [51:07<13:20,  1.05s/it]
 79%|███████▊  | 2833/3598 [51:08<12:54,  1.01s/it]
 79%|███████▉  | 2834/3598 [51:09<13:55,  1.09s/it]
 79%|███████▉  | 2835/3598 [51:10<12:54,  1.01s/it]
 79%|███████▉  | 2836/3598 [51:11<12:33,  1.01it/s]
 79%|███████▉  | 2837/3598 [51:12<13:31,  1.07s/it]
 79%|███████▉  | 2838/3598 [51:13<14:20,  1.13s/it]
 79%|███████▉  | 2839/3598 [51:15<15:11,  1.20s/it]
 79%|███████▉  | 2840/3598 [51:16<13:53,  1.10s/it]
                                                   

 79%|███████▉  | 2840/3598 [51:16<13:53,  1.10s/it]
 79%|███████▉  | 2841/3598 [51:17<14:50,  1.18s/it]
 79%|███████▉  | 2842/3598 [51:18<13:43,  1.09s/it]
 79%|███████▉  | 2843/3598 [51:19<13:18,  1.06s/it]
 79%|███████▉  | 2844/3598 [51:20<13:05,  1.04s/it]
 79%|███████▉  | 2845/3598 [51:21<13:43,  1.09s/it]
 79%|███████▉  | 2846/3598 [51:22<14:30,  1.16s/it]
 79%|███████▉  | 2847/3598 [51:23<13:35,  1.09s/it]
 79%|███████▉  | 2848/3598 [51:24<13:13,  1.06s/it]
 79%|███████▉  | 2849/3598 [51:25<13:16,  1.06s/it]
 79%|███████▉  | 2850/3598 [51:26<12:28,  1.00s/it]
                                                   

 79%|███████▉  | 2850/3598 [51:26<12:28,  1.00s/it]
 79%|███████▉  | 2851/3598 [51:27<11:46,  1.06it/s]
 79%|███████▉  | 2852/3598 [51:28<11:43,  1.06it/s]
 79%|███████▉  | 2853/3598 [51:29<11:24,  1.09it/s]
 79%|███████▉  | 2854/3598 [51:30<12:49,  1.03s/it]
 79%|███████▉  | 2855/3598 [51:31<12:52,  1.04s/it]
 79%|███████▉  | 2856/3598 [51:32<12:13,  1.01it/s]
 79%|███████▉  | 2857/3598 [51:34<13:39,  1.11s/it]
 79%|███████▉  | 2858/3598 [51:34<12:46,  1.04s/it]
 79%|███████▉  | 2859/3598 [51:35<12:10,  1.01it/s]
 79%|███████▉  | 2860/3598 [51:36<11:51,  1.04it/s]
                                                   

 79%|███████▉  | 2860/3598 [51:36<11:51,  1.04it/s]
 80%|███████▉  | 2861/3598 [51:37<11:57,  1.03it/s]
 80%|███████▉  | 2862/3598 [51:38<12:06,  1.01it/s]
 80%|███████▉  | 2863/3598 [51:39<12:01,  1.02it/s]
 80%|███████▉  | 2864/3598 [51:40<12:57,  1.06s/it]
 80%|███████▉  | 2865/3598 [51:41<11:58,  1.02it/s]
 80%|███████▉  | 2866/3598 [51:42<12:15,  1.00s/it]
 80%|███████▉  | 2867/3598 [51:44<13:25,  1.10s/it]
 80%|███████▉  | 2868/3598 [51:45<13:36,  1.12s/it]
 80%|███████▉  | 2869/3598 [51:46<12:53,  1.06s/it]
 80%|███████▉  | 2870/3598 [51:47<13:38,  1.12s/it]
                                                   

 80%|███████▉  | 2870/3598 [51:47<13:38,  1.12s/it]
 80%|███████▉  | 2871/3598 [51:48<12:44,  1.05s/it]
 80%|███████▉  | 2872/3598 [51:49<13:49,  1.14s/it]
 80%|███████▉  | 2873/3598 [51:50<12:55,  1.07s/it]
 80%|███████▉  | 2874/3598 [51:51<12:06,  1.00s/it]
 80%|███████▉  | 2875/3598 [51:52<11:40,  1.03it/s]
 80%|███████▉  | 2876/3598 [51:53<11:26,  1.05it/s]
 80%|███████▉  | 2877/3598 [51:54<11:23,  1.06it/s]
 80%|███████▉  | 2878/3598 [51:55<11:13,  1.07it/s]
 80%|████████  | 2879/3598 [51:55<10:53,  1.10it/s]
 80%|████████  | 2880/3598 [51:57<11:52,  1.01it/s]
                                                   

 80%|████████  | 2880/3598 [51:57<11:52,  1.01it/s]
 80%|████████  | 2881/3598 [51:57<11:27,  1.04it/s]
 80%|████████  | 2882/3598 [51:58<10:58,  1.09it/s]
 80%|████████  | 2883/3598 [51:59<10:40,  1.12it/s]
 80%|████████  | 2884/3598 [52:00<11:49,  1.01it/s]
 80%|████████  | 2885/3598 [52:02<12:25,  1.05s/it]
 80%|████████  | 2886/3598 [52:03<13:34,  1.14s/it]
 80%|████████  | 2887/3598 [52:04<14:13,  1.20s/it]
 80%|████████  | 2888/3598 [52:06<14:49,  1.25s/it]
 80%|████████  | 2889/3598 [52:07<15:12,  1.29s/it]
 80%|████████  | 2890/3598 [52:08<14:13,  1.21s/it]
                                                   

 80%|████████  | 2890/3598 [52:08<14:13,  1.21s/it]
 80%|████████  | 2891/3598 [52:09<14:43,  1.25s/it]
 80%|████████  | 2892/3598 [52:10<13:27,  1.14s/it]
 80%|████████  | 2893/3598 [52:11<12:05,  1.03s/it]
 80%|████████  | 2894/3598 [52:12<11:42,  1.00it/s]
 80%|████████  | 2895/3598 [52:13<11:00,  1.06it/s]
 80%|████████  | 2896/3598 [52:14<12:05,  1.03s/it]
 81%|████████  | 2897/3598 [52:15<12:56,  1.11s/it]
 81%|████████  | 2898/3598 [52:17<13:30,  1.16s/it]
 81%|████████  | 2899/3598 [52:18<12:53,  1.11s/it]
 81%|████████  | 2900/3598 [52:19<12:57,  1.11s/it]
                                                   

 81%|████████  | 2900/3598 [52:19<12:57,  1.11s/it]
 81%|████████  | 2901/3598 [52:20<12:16,  1.06s/it]
 81%|████████  | 2902/3598 [52:21<13:24,  1.16s/it]
 81%|████████  | 2903/3598 [52:22<12:24,  1.07s/it]
 81%|████████  | 2904/3598 [52:23<13:18,  1.15s/it]
 81%|████████  | 2905/3598 [52:24<12:34,  1.09s/it]
 81%|████████  | 2906/3598 [52:25<12:38,  1.10s/it]
 81%|████████  | 2907/3598 [52:27<13:33,  1.18s/it]
 81%|████████  | 2908/3598 [52:27<12:10,  1.06s/it]
 81%|████████  | 2909/3598 [52:29<13:05,  1.14s/it]
 81%|████████  | 2910/3598 [52:30<12:09,  1.06s/it]
                                                   

 81%|████████  | 2910/3598 [52:30<12:09,  1.06s/it]
 81%|████████  | 2911/3598 [52:31<11:56,  1.04s/it]
 81%|████████  | 2912/3598 [52:31<11:03,  1.03it/s]
 81%|████████  | 2913/3598 [52:32<10:41,  1.07it/s]
 81%|████████  | 2914/3598 [52:33<10:45,  1.06it/s]
 81%|████████  | 2915/3598 [52:34<10:38,  1.07it/s]
 81%|████████  | 2916/3598 [52:35<10:44,  1.06it/s]
 81%|████████  | 2917/3598 [52:36<12:03,  1.06s/it]
 81%|████████  | 2918/3598 [52:38<12:36,  1.11s/it]
 81%|████████  | 2919/3598 [52:39<11:49,  1.05s/it]
 81%|████████  | 2920/3598 [52:39<11:08,  1.01it/s]
                                                   

 81%|████████  | 2920/3598 [52:39<11:08,  1.01it/s]
 81%|████████  | 2921/3598 [52:41<12:27,  1.10s/it]
 81%|████████  | 2922/3598 [52:42<11:29,  1.02s/it]
 81%|████████  | 2923/3598 [52:43<12:43,  1.13s/it]
 81%|████████▏ | 2924/3598 [52:44<12:49,  1.14s/it]
 81%|████████▏ | 2925/3598 [52:45<12:57,  1.16s/it]
 81%|████████▏ | 2926/3598 [52:46<12:19,  1.10s/it]
 81%|████████▏ | 2927/3598 [52:48<12:48,  1.14s/it]
 81%|████████▏ | 2928/3598 [52:49<13:10,  1.18s/it]
 81%|████████▏ | 2929/3598 [52:50<12:06,  1.09s/it]
 81%|████████▏ | 2930/3598 [52:51<11:19,  1.02s/it]
                                                   

 81%|████████▏ | 2930/3598 [52:51<11:19,  1.02s/it]
 81%|████████▏ | 2931/3598 [52:51<10:59,  1.01it/s]
 81%|████████▏ | 2932/3598 [52:52<11:02,  1.01it/s]
 82%|████████▏ | 2933/3598 [52:53<10:33,  1.05it/s]
 82%|████████▏ | 2934/3598 [52:54<10:18,  1.07it/s]
 82%|████████▏ | 2935/3598 [52:55<10:07,  1.09it/s]
 82%|████████▏ | 2936/3598 [52:56<10:01,  1.10it/s]
 82%|████████▏ | 2937/3598 [52:57<09:43,  1.13it/s]
 82%|████████▏ | 2938/3598 [52:58<09:54,  1.11it/s]
 82%|████████▏ | 2939/3598 [52:59<10:56,  1.00it/s]
 82%|████████▏ | 2940/3598 [53:00<10:36,  1.03it/s]
                                                   

 82%|████████▏ | 2940/3598 [53:00<10:36,  1.03it/s]
 82%|████████▏ | 2941/3598 [53:01<11:53,  1.09s/it]
 82%|████████▏ | 2942/3598 [53:02<11:06,  1.02s/it]
 82%|████████▏ | 2943/3598 [53:03<10:48,  1.01it/s]
 82%|████████▏ | 2944/3598 [53:04<10:59,  1.01s/it]
 82%|████████▏ | 2945/3598 [53:05<12:10,  1.12s/it]
 82%|████████▏ | 2946/3598 [53:07<12:49,  1.18s/it]
 82%|████████▏ | 2947/3598 [53:08<11:48,  1.09s/it]
 82%|████████▏ | 2948/3598 [53:09<11:21,  1.05s/it]
 82%|████████▏ | 2949/3598 [53:10<11:52,  1.10s/it]
 82%|████████▏ | 2950/3598 [53:11<12:28,  1.15s/it]
                                                   

 82%|████████▏ | 2950/3598 [53:11<12:28,  1.15s/it]
 82%|████████▏ | 2951/3598 [53:12<12:43,  1.18s/it]
 82%|████████▏ | 2952/3598 [53:13<11:49,  1.10s/it]
 82%|████████▏ | 2953/3598 [53:15<12:38,  1.18s/it]
 82%|████████▏ | 2954/3598 [53:16<11:56,  1.11s/it]
 82%|████████▏ | 2955/3598 [53:17<12:30,  1.17s/it]
 82%|████████▏ | 2956/3598 [53:18<11:41,  1.09s/it]
 82%|████████▏ | 2957/3598 [53:19<10:54,  1.02s/it]
 82%|████████▏ | 2958/3598 [53:20<10:47,  1.01s/it]
 82%|████████▏ | 2959/3598 [53:21<10:34,  1.01it/s]
 82%|████████▏ | 2960/3598 [53:22<10:28,  1.02it/s]
                                                   

 82%|████████▏ | 2960/3598 [53:22<10:28,  1.02it/s]
 82%|████████▏ | 2961/3598 [53:22<10:08,  1.05it/s]
 82%|████████▏ | 2962/3598 [53:24<10:49,  1.02s/it]
 82%|████████▏ | 2963/3598 [53:24<10:19,  1.03it/s]
 82%|████████▏ | 2964/3598 [53:25<10:23,  1.02it/s]
 82%|████████▏ | 2965/3598 [53:27<10:42,  1.01s/it]
 82%|████████▏ | 2966/3598 [53:28<10:38,  1.01s/it]
 82%|████████▏ | 2967/3598 [53:28<10:07,  1.04it/s]
 82%|████████▏ | 2968/3598 [53:29<09:52,  1.06it/s]
 83%|████████▎ | 2969/3598 [53:30<09:30,  1.10it/s]
 83%|████████▎ | 2970/3598 [53:31<09:38,  1.09it/s]
                                                   

 83%|████████▎ | 2970/3598 [53:31<09:38,  1.09it/s]
 83%|████████▎ | 2971/3598 [53:32<11:01,  1.05s/it]
 83%|████████▎ | 2972/3598 [53:33<10:40,  1.02s/it]
 83%|████████▎ | 2973/3598 [53:34<10:09,  1.03it/s]
 83%|████████▎ | 2974/3598 [53:35<10:30,  1.01s/it]
 83%|████████▎ | 2975/3598 [53:37<11:16,  1.09s/it]
 83%|████████▎ | 2976/3598 [53:38<10:39,  1.03s/it]
 83%|████████▎ | 2977/3598 [53:39<11:21,  1.10s/it]
 83%|████████▎ | 2978/3598 [53:40<11:08,  1.08s/it]
 83%|████████▎ | 2979/3598 [53:41<10:51,  1.05s/it]
 83%|████████▎ | 2980/3598 [53:42<10:52,  1.06s/it]
                                                   

 83%|████████▎ | 2980/3598 [53:42<10:52,  1.06s/it]
 83%|████████▎ | 2981/3598 [53:43<11:43,  1.14s/it]
 83%|████████▎ | 2982/3598 [53:44<11:02,  1.08s/it]
 83%|████████▎ | 2983/3598 [53:45<10:12,  1.00it/s]
 83%|████████▎ | 2984/3598 [53:46<10:11,  1.00it/s]
 83%|████████▎ | 2985/3598 [53:47<09:44,  1.05it/s]
 83%|████████▎ | 2986/3598 [53:48<09:15,  1.10it/s]
 83%|████████▎ | 2987/3598 [53:49<10:33,  1.04s/it]
 83%|████████▎ | 2988/3598 [53:50<10:52,  1.07s/it]
 83%|████████▎ | 2989/3598 [53:51<11:37,  1.15s/it]
 83%|████████▎ | 2990/3598 [53:52<10:58,  1.08s/it]
                                                   

 83%|████████▎ | 2990/3598 [53:52<10:58,  1.08s/it]
 83%|████████▎ | 2991/3598 [53:53<10:39,  1.05s/it]
 83%|████████▎ | 2992/3598 [53:54<10:32,  1.04s/it]
 83%|████████▎ | 2993/3598 [53:55<10:09,  1.01s/it]
 83%|████████▎ | 2994/3598 [53:57<11:15,  1.12s/it]
 83%|████████▎ | 2995/3598 [53:58<10:37,  1.06s/it]
 83%|████████▎ | 2996/3598 [53:59<11:29,  1.14s/it]
 83%|████████▎ | 2997/3598 [54:00<12:14,  1.22s/it]
 83%|████████▎ | 2998/3598 [54:01<11:49,  1.18s/it]
 83%|████████▎ | 2999/3598 [54:02<11:15,  1.13s/it]
 83%|████████▎ | 3000/3598 [54:03<10:50,  1.09s/it]
                                                   

 83%|████████▎ | 3000/3598 [54:03<10:50,  1.09s/it]
 83%|████████▎ | 3001/3598 [54:04<10:15,  1.03s/it]
 83%|████████▎ | 3002/3598 [54:05<09:50,  1.01it/s]
 83%|████████▎ | 3003/3598 [54:06<09:32,  1.04it/s]
 83%|████████▎ | 3004/3598 [54:07<09:30,  1.04it/s]
 84%|████████▎ | 3005/3598 [54:08<09:15,  1.07it/s]
 84%|████████▎ | 3006/3598 [54:09<09:04,  1.09it/s]
 84%|████████▎ | 3007/3598 [54:10<09:13,  1.07it/s]
 84%|████████▎ | 3008/3598 [54:11<10:18,  1.05s/it]
 84%|████████▎ | 3009/3598 [54:12<09:43,  1.01it/s]
 84%|████████▎ | 3010/3598 [54:13<09:29,  1.03it/s]
                                                   

 84%|████████▎ | 3010/3598 [54:13<09:29,  1.03it/s]
 84%|████████▎ | 3011/3598 [54:14<09:06,  1.07it/s]
 84%|████████▎ | 3012/3598 [54:15<09:34,  1.02it/s]
 84%|████████▎ | 3013/3598 [54:16<10:39,  1.09s/it]
 84%|████████▍ | 3014/3598 [54:17<10:47,  1.11s/it]
 84%|████████▍ | 3015/3598 [54:18<10:14,  1.05s/it]
 84%|████████▍ | 3016/3598 [54:19<09:53,  1.02s/it]
 84%|████████▍ | 3017/3598 [54:20<09:45,  1.01s/it]
 84%|████████▍ | 3018/3598 [54:21<09:06,  1.06it/s]
 84%|████████▍ | 3019/3598 [54:22<08:57,  1.08it/s]
 84%|████████▍ | 3020/3598 [54:23<08:45,  1.10it/s]
                                                   

 84%|████████▍ | 3020/3598 [54:23<08:45,  1.10it/s]
 84%|████████▍ | 3021/3598 [54:24<08:37,  1.12it/s]
 84%|████████▍ | 3022/3598 [54:25<08:43,  1.10it/s]
 84%|████████▍ | 3023/3598 [54:25<08:34,  1.12it/s]
 84%|████████▍ | 3024/3598 [54:26<08:50,  1.08it/s]
 84%|████████▍ | 3025/3598 [54:27<09:18,  1.03it/s]
 84%|████████▍ | 3026/3598 [54:28<08:55,  1.07it/s]
 84%|████████▍ | 3027/3598 [54:29<08:50,  1.08it/s]
 84%|████████▍ | 3028/3598 [54:31<09:51,  1.04s/it]
 84%|████████▍ | 3029/3598 [54:31<09:42,  1.02s/it]
 84%|████████▍ | 3030/3598 [54:33<09:53,  1.05s/it]
                                                   

 84%|████████▍ | 3030/3598 [54:33<09:53,  1.05s/it]
 84%|████████▍ | 3031/3598 [54:34<10:49,  1.15s/it]
 84%|████████▍ | 3032/3598 [54:35<10:13,  1.08s/it]
 84%|████████▍ | 3033/3598 [54:36<09:37,  1.02s/it]
 84%|████████▍ | 3034/3598 [54:37<10:35,  1.13s/it]
 84%|████████▍ | 3035/3598 [54:38<09:58,  1.06s/it]
 84%|████████▍ | 3036/3598 [54:39<10:52,  1.16s/it]
 84%|████████▍ | 3037/3598 [54:41<11:24,  1.22s/it]
 84%|████████▍ | 3038/3598 [54:42<10:38,  1.14s/it]
 84%|████████▍ | 3039/3598 [54:43<10:04,  1.08s/it]
 84%|████████▍ | 3040/3598 [54:44<10:25,  1.12s/it]
                                                   

 84%|████████▍ | 3040/3598 [54:44<10:25,  1.12s/it]
 85%|████████▍ | 3041/3598 [54:45<11:16,  1.21s/it]
 85%|████████▍ | 3042/3598 [54:46<10:42,  1.16s/it]
 85%|████████▍ | 3043/3598 [54:48<10:44,  1.16s/it]
 85%|████████▍ | 3044/3598 [54:49<11:02,  1.20s/it]
 85%|████████▍ | 3045/3598 [54:50<10:03,  1.09s/it]
 85%|████████▍ | 3046/3598 [54:51<10:49,  1.18s/it]
 85%|████████▍ | 3047/3598 [54:52<10:08,  1.10s/it]
 85%|████████▍ | 3048/3598 [54:53<09:37,  1.05s/it]
 85%|████████▍ | 3049/3598 [54:54<09:46,  1.07s/it]
 85%|████████▍ | 3050/3598 [54:55<09:10,  1.01s/it]
                                                   

 85%|████████▍ | 3050/3598 [54:55<09:10,  1.01s/it]
 85%|████████▍ | 3051/3598 [54:56<10:13,  1.12s/it]
 85%|████████▍ | 3052/3598 [54:58<10:44,  1.18s/it]
 85%|████████▍ | 3053/3598 [54:59<11:21,  1.25s/it]
 85%|████████▍ | 3054/3598 [55:00<11:45,  1.30s/it]
 85%|████████▍ | 3055/3598 [55:02<11:59,  1.33s/it]
 85%|████████▍ | 3056/3598 [55:03<11:08,  1.23s/it]
 85%|████████▍ | 3057/3598 [55:04<11:32,  1.28s/it]
 85%|████████▍ | 3058/3598 [55:06<11:49,  1.31s/it]
 85%|████████▌ | 3059/3598 [55:06<10:24,  1.16s/it]
 85%|████████▌ | 3060/3598 [55:07<09:36,  1.07s/it]
                                                   

 85%|████████▌ | 3060/3598 [55:07<09:36,  1.07s/it]
 85%|████████▌ | 3061/3598 [55:08<09:05,  1.02s/it]
 85%|████████▌ | 3062/3598 [55:09<08:37,  1.03it/s]
 85%|████████▌ | 3063/3598 [55:10<08:33,  1.04it/s]
 85%|████████▌ | 3064/3598 [55:11<08:28,  1.05it/s]
 85%|████████▌ | 3065/3598 [55:12<08:29,  1.05it/s]
 85%|████████▌ | 3066/3598 [55:13<08:24,  1.06it/s]
 85%|████████▌ | 3067/3598 [55:14<08:16,  1.07it/s]
 85%|████████▌ | 3068/3598 [55:15<08:43,  1.01it/s]
 85%|████████▌ | 3069/3598 [55:16<08:28,  1.04it/s]
 85%|████████▌ | 3070/3598 [55:17<09:09,  1.04s/it]
                                                   

 85%|████████▌ | 3070/3598 [55:17<09:09,  1.04s/it]
 85%|████████▌ | 3071/3598 [55:18<08:50,  1.01s/it]
 85%|████████▌ | 3072/3598 [55:19<09:39,  1.10s/it]
 85%|████████▌ | 3073/3598 [55:21<10:26,  1.19s/it]
 85%|████████▌ | 3074/3598 [55:22<10:24,  1.19s/it]
 85%|████████▌ | 3075/3598 [55:23<09:38,  1.11s/it]
 85%|████████▌ | 3076/3598 [55:24<09:05,  1.04s/it]
 86%|████████▌ | 3077/3598 [55:25<09:02,  1.04s/it]
 86%|████████▌ | 3078/3598 [55:26<09:34,  1.11s/it]
 86%|████████▌ | 3079/3598 [55:27<08:59,  1.04s/it]
 86%|████████▌ | 3080/3598 [55:28<08:46,  1.02s/it]
                                                   

 86%|████████▌ | 3080/3598 [55:28<08:46,  1.02s/it]
 86%|████████▌ | 3081/3598 [55:29<08:47,  1.02s/it]
 86%|████████▌ | 3082/3598 [55:30<08:21,  1.03it/s]
 86%|████████▌ | 3083/3598 [55:31<08:18,  1.03it/s]
 86%|████████▌ | 3084/3598 [55:32<08:17,  1.03it/s]
 86%|████████▌ | 3085/3598 [55:32<08:06,  1.05it/s]
 86%|████████▌ | 3086/3598 [55:33<08:06,  1.05it/s]
 86%|████████▌ | 3087/3598 [55:34<08:01,  1.06it/s]
 86%|████████▌ | 3088/3598 [55:35<07:51,  1.08it/s]
 86%|████████▌ | 3089/3598 [55:36<07:50,  1.08it/s]
 86%|████████▌ | 3090/3598 [55:37<08:50,  1.04s/it]
                                                   

 86%|████████▌ | 3090/3598 [55:37<08:50,  1.04s/it]
 86%|████████▌ | 3091/3598 [55:38<08:21,  1.01it/s]
 86%|████████▌ | 3092/3598 [55:40<08:57,  1.06s/it]
 86%|████████▌ | 3093/3598 [55:41<08:44,  1.04s/it]
 86%|████████▌ | 3094/3598 [55:41<08:18,  1.01it/s]
 86%|████████▌ | 3095/3598 [55:43<09:01,  1.08s/it]
 86%|████████▌ | 3096/3598 [55:44<08:31,  1.02s/it]
 86%|████████▌ | 3097/3598 [55:44<07:59,  1.04it/s]
 86%|████████▌ | 3098/3598 [55:46<09:04,  1.09s/it]
 86%|████████▌ | 3099/3598 [55:47<08:51,  1.07s/it]
 86%|████████▌ | 3100/3598 [55:48<08:46,  1.06s/it]
                                                   

 86%|████████▌ | 3100/3598 [55:48<08:46,  1.06s/it]
 86%|████████▌ | 3101/3598 [55:49<08:26,  1.02s/it]
 86%|████████▌ | 3102/3598 [55:50<08:16,  1.00s/it]
 86%|████████▌ | 3103/3598 [55:51<09:12,  1.12s/it]
 86%|████████▋ | 3104/3598 [55:52<08:33,  1.04s/it]
 86%|████████▋ | 3105/3598 [55:53<08:52,  1.08s/it]
 86%|████████▋ | 3106/3598 [55:54<08:54,  1.09s/it]
 86%|████████▋ | 3107/3598 [55:55<08:23,  1.02s/it]
 86%|████████▋ | 3108/3598 [55:56<09:13,  1.13s/it]
 86%|████████▋ | 3109/3598 [55:57<08:40,  1.07s/it]
 86%|████████▋ | 3110/3598 [55:58<08:15,  1.02s/it]
                                                   

 86%|████████▋ | 3110/3598 [55:58<08:15,  1.02s/it]
 86%|████████▋ | 3111/3598 [55:59<08:01,  1.01it/s]
 86%|████████▋ | 3112/3598 [56:00<07:59,  1.01it/s]
 87%|████████▋ | 3113/3598 [56:01<07:44,  1.05it/s]
 87%|████████▋ | 3114/3598 [56:02<07:33,  1.07it/s]
 87%|████████▋ | 3115/3598 [56:03<07:42,  1.04it/s]
 87%|████████▋ | 3116/3598 [56:04<07:30,  1.07it/s]
 87%|████████▋ | 3117/3598 [56:05<07:13,  1.11it/s]
 87%|████████▋ | 3118/3598 [56:06<07:07,  1.12it/s]
 87%|████████▋ | 3119/3598 [56:07<07:21,  1.08it/s]
 87%|████████▋ | 3120/3598 [56:08<07:42,  1.03it/s]
                                                   

 87%|████████▋ | 3120/3598 [56:08<07:42,  1.03it/s]
 87%|████████▋ | 3121/3598 [56:09<08:21,  1.05s/it]
 87%|████████▋ | 3122/3598 [56:10<07:52,  1.01it/s]
 87%|████████▋ | 3123/3598 [56:11<07:36,  1.04it/s]
 87%|████████▋ | 3124/3598 [56:12<07:35,  1.04it/s]
 87%|████████▋ | 3125/3598 [56:13<07:33,  1.04it/s]
 87%|████████▋ | 3126/3598 [56:13<07:20,  1.07it/s]
 87%|████████▋ | 3127/3598 [56:15<08:51,  1.13s/it]
 87%|████████▋ | 3128/3598 [56:16<08:15,  1.06s/it]
 87%|████████▋ | 3129/3598 [56:17<07:52,  1.01s/it]
 87%|████████▋ | 3130/3598 [56:18<07:39,  1.02it/s]
                                                   

 87%|████████▋ | 3130/3598 [56:18<07:39,  1.02it/s]
 87%|████████▋ | 3131/3598 [56:19<08:36,  1.11s/it]
 87%|████████▋ | 3132/3598 [56:20<08:57,  1.15s/it]
 87%|████████▋ | 3133/3598 [56:21<08:33,  1.10s/it]
 87%|████████▋ | 3134/3598 [56:22<08:05,  1.05s/it]
 87%|████████▋ | 3135/3598 [56:23<07:36,  1.02it/s]
 87%|████████▋ | 3136/3598 [56:24<08:22,  1.09s/it]
 87%|████████▋ | 3137/3598 [56:25<08:08,  1.06s/it]
 87%|████████▋ | 3138/3598 [56:26<07:53,  1.03s/it]
 87%|████████▋ | 3139/3598 [56:27<07:40,  1.00s/it]
 87%|████████▋ | 3140/3598 [56:28<07:23,  1.03it/s]
                                                   

 87%|████████▋ | 3140/3598 [56:28<07:23,  1.03it/s]
 87%|████████▋ | 3141/3598 [56:29<07:09,  1.07it/s]
 87%|████████▋ | 3142/3598 [56:30<07:36,  1.00s/it]
 87%|████████▋ | 3143/3598 [56:31<08:11,  1.08s/it]
 87%|████████▋ | 3144/3598 [56:33<08:17,  1.10s/it]
 87%|████████▋ | 3145/3598 [56:34<08:04,  1.07s/it]
 87%|████████▋ | 3146/3598 [56:34<07:32,  1.00s/it]
 87%|████████▋ | 3147/3598 [56:36<08:01,  1.07s/it]
 87%|████████▋ | 3148/3598 [56:37<08:34,  1.14s/it]
 88%|████████▊ | 3149/3598 [56:38<08:02,  1.07s/it]
 88%|████████▊ | 3150/3598 [56:39<07:52,  1.06s/it]
                                                   

 88%|████████▊ | 3150/3598 [56:39<07:52,  1.06s/it]
 88%|████████▊ | 3151/3598 [56:40<08:37,  1.16s/it]
 88%|████████▊ | 3152/3598 [56:41<08:05,  1.09s/it]
 88%|████████▊ | 3153/3598 [56:42<07:36,  1.03s/it]
 88%|████████▊ | 3154/3598 [56:43<08:19,  1.12s/it]
 88%|████████▊ | 3155/3598 [56:44<07:42,  1.04s/it]
 88%|████████▊ | 3156/3598 [56:46<08:04,  1.10s/it]
 88%|████████▊ | 3157/3598 [56:47<08:31,  1.16s/it]
 88%|████████▊ | 3158/3598 [56:48<07:43,  1.05s/it]
 88%|████████▊ | 3159/3598 [56:49<07:57,  1.09s/it]
 88%|████████▊ | 3160/3598 [56:50<07:42,  1.06s/it]
                                                   

 88%|████████▊ | 3160/3598 [56:50<07:42,  1.06s/it]
 88%|████████▊ | 3161/3598 [56:51<08:17,  1.14s/it]
 88%|████████▊ | 3162/3598 [56:52<08:40,  1.19s/it]
 88%|████████▊ | 3163/3598 [56:53<08:05,  1.12s/it]
 88%|████████▊ | 3164/3598 [56:54<07:57,  1.10s/it]
 88%|████████▊ | 3165/3598 [56:55<07:35,  1.05s/it]
 88%|████████▊ | 3166/3598 [56:57<07:57,  1.11s/it]
 88%|████████▊ | 3167/3598 [56:57<07:16,  1.01s/it]
 88%|████████▊ | 3168/3598 [56:59<07:26,  1.04s/it]
 88%|████████▊ | 3169/3598 [57:00<07:24,  1.04s/it]
 88%|████████▊ | 3170/3598 [57:01<07:12,  1.01s/it]
                                                   

 88%|████████▊ | 3170/3598 [57:01<07:12,  1.01s/it]
 88%|████████▊ | 3171/3598 [57:02<07:12,  1.01s/it]
 88%|████████▊ | 3172/3598 [57:03<07:05,  1.00it/s]
 88%|████████▊ | 3173/3598 [57:04<07:54,  1.12s/it]
 88%|████████▊ | 3174/3598 [57:05<07:19,  1.04s/it]
 88%|████████▊ | 3175/3598 [57:06<07:16,  1.03s/it]
 88%|████████▊ | 3176/3598 [57:07<07:31,  1.07s/it]
 88%|████████▊ | 3177/3598 [57:08<07:07,  1.02s/it]
 88%|████████▊ | 3178/3598 [57:09<07:50,  1.12s/it]
 88%|████████▊ | 3179/3598 [57:10<07:15,  1.04s/it]
 88%|████████▊ | 3180/3598 [57:11<06:51,  1.02it/s]
                                                   

 88%|████████▊ | 3180/3598 [57:11<06:51,  1.02it/s]
 88%|████████▊ | 3181/3598 [57:12<07:14,  1.04s/it]
 88%|████████▊ | 3182/3598 [57:13<06:58,  1.01s/it]
 88%|████████▊ | 3183/3598 [57:14<07:22,  1.07s/it]
 88%|████████▊ | 3184/3598 [57:15<06:55,  1.00s/it]
 89%|████████▊ | 3185/3598 [57:16<07:34,  1.10s/it]
 89%|████████▊ | 3186/3598 [57:18<07:56,  1.16s/it]
 89%|████████▊ | 3187/3598 [57:19<08:13,  1.20s/it]
 89%|████████▊ | 3188/3598 [57:20<07:51,  1.15s/it]
 89%|████████▊ | 3189/3598 [57:21<08:00,  1.17s/it]
 89%|████████▊ | 3190/3598 [57:22<07:24,  1.09s/it]
                                                   

 89%|████████▊ | 3190/3598 [57:22<07:24,  1.09s/it]
 89%|████████▊ | 3191/3598 [57:23<06:51,  1.01s/it]
 89%|████████▊ | 3192/3598 [57:24<07:14,  1.07s/it]
 89%|████████▊ | 3193/3598 [57:25<07:00,  1.04s/it]
 89%|████████▉ | 3194/3598 [57:26<06:36,  1.02it/s]
 89%|████████▉ | 3195/3598 [57:27<07:24,  1.10s/it]
 89%|████████▉ | 3196/3598 [57:29<07:57,  1.19s/it]
 89%|████████▉ | 3197/3598 [57:30<08:24,  1.26s/it]
 89%|████████▉ | 3198/3598 [57:32<08:31,  1.28s/it]
 89%|████████▉ | 3199/3598 [57:33<08:18,  1.25s/it]
 89%|████████▉ | 3200/3598 [57:34<07:31,  1.13s/it]
                                                   

 89%|████████▉ | 3200/3598 [57:34<07:31,  1.13s/it]
 89%|████████▉ | 3201/3598 [57:35<07:11,  1.09s/it]
 89%|████████▉ | 3202/3598 [57:35<06:51,  1.04s/it]
 89%|████████▉ | 3203/3598 [57:37<07:22,  1.12s/it]
 89%|████████▉ | 3204/3598 [57:38<06:54,  1.05s/it]
 89%|████████▉ | 3205/3598 [57:39<06:35,  1.01s/it]
 89%|████████▉ | 3206/3598 [57:40<06:59,  1.07s/it]
 89%|████████▉ | 3207/3598 [57:41<06:41,  1.03s/it]
 89%|████████▉ | 3208/3598 [57:42<06:34,  1.01s/it]
 89%|████████▉ | 3209/3598 [57:43<06:13,  1.04it/s]
 89%|████████▉ | 3210/3598 [57:44<06:23,  1.01it/s]
                                                   

 89%|████████▉ | 3210/3598 [57:44<06:23,  1.01it/s]
 89%|████████▉ | 3211/3598 [57:44<06:11,  1.04it/s]
 89%|████████▉ | 3212/3598 [57:46<06:20,  1.02it/s]
 89%|████████▉ | 3213/3598 [57:46<06:07,  1.05it/s]
 89%|████████▉ | 3214/3598 [57:47<06:00,  1.07it/s]
 89%|████████▉ | 3215/3598 [57:48<05:53,  1.08it/s]
 89%|████████▉ | 3216/3598 [57:49<05:40,  1.12it/s]
 89%|████████▉ | 3217/3598 [57:50<06:27,  1.02s/it]
 89%|████████▉ | 3218/3598 [57:51<06:19,  1.00it/s]
 89%|████████▉ | 3219/3598 [57:52<06:06,  1.03it/s]
 89%|████████▉ | 3220/3598 [57:53<06:03,  1.04it/s]
                                                   

 89%|████████▉ | 3220/3598 [57:53<06:03,  1.04it/s]
 90%|████████▉ | 3221/3598 [57:54<06:13,  1.01it/s]
 90%|████████▉ | 3222/3598 [57:55<05:56,  1.06it/s]
 90%|████████▉ | 3223/3598 [57:56<05:47,  1.08it/s]
 90%|████████▉ | 3224/3598 [57:57<06:00,  1.04it/s]
 90%|████████▉ | 3225/3598 [57:58<06:51,  1.10s/it]
 90%|████████▉ | 3226/3598 [57:59<06:39,  1.07s/it]
 90%|████████▉ | 3227/3598 [58:01<07:08,  1.16s/it]
 90%|████████▉ | 3228/3598 [58:02<07:21,  1.19s/it]
 90%|████████▉ | 3229/3598 [58:03<07:32,  1.23s/it]
 90%|████████▉ | 3230/3598 [58:04<07:00,  1.14s/it]
                                                   

 90%|████████▉ | 3230/3598 [58:04<07:00,  1.14s/it]
 90%|████████▉ | 3231/3598 [58:05<06:28,  1.06s/it]
 90%|████████▉ | 3232/3598 [58:06<06:09,  1.01s/it]
 90%|████████▉ | 3233/3598 [58:07<06:05,  1.00s/it]
 90%|████████▉ | 3234/3598 [58:08<05:53,  1.03it/s]
 90%|████████▉ | 3235/3598 [58:09<05:53,  1.03it/s]
 90%|████████▉ | 3236/3598 [58:10<05:40,  1.06it/s]
 90%|████████▉ | 3237/3598 [58:11<05:28,  1.10it/s]
 90%|████████▉ | 3238/3598 [58:12<05:33,  1.08it/s]
 90%|█████████ | 3239/3598 [58:12<05:27,  1.10it/s]
 90%|█████████ | 3240/3598 [58:13<05:11,  1.15it/s]
                                                   

 90%|█████████ | 3240/3598 [58:13<05:11,  1.15it/s]
 90%|█████████ | 3241/3598 [58:14<05:22,  1.11it/s]
 90%|█████████ | 3242/3598 [58:15<05:37,  1.05it/s]
 90%|█████████ | 3243/3598 [58:16<06:04,  1.03s/it]
 90%|█████████ | 3244/3598 [58:17<05:54,  1.00s/it]
 90%|█████████ | 3245/3598 [58:19<06:32,  1.11s/it]
 90%|█████████ | 3246/3598 [58:20<06:30,  1.11s/it]
 90%|█████████ | 3247/3598 [58:21<06:01,  1.03s/it]
 90%|█████████ | 3248/3598 [58:21<05:34,  1.04it/s]
 90%|█████████ | 3249/3598 [58:22<05:26,  1.07it/s]
 90%|█████████ | 3250/3598 [58:23<05:43,  1.01it/s]
                                                   

 90%|█████████ | 3250/3598 [58:23<05:43,  1.01it/s]
 90%|█████████ | 3251/3598 [58:25<06:07,  1.06s/it]
 90%|█████████ | 3252/3598 [58:26<05:51,  1.01s/it]
 90%|█████████ | 3253/3598 [58:26<05:35,  1.03it/s]
 90%|█████████ | 3254/3598 [58:27<05:34,  1.03it/s]
 90%|█████████ | 3255/3598 [58:28<05:17,  1.08it/s]
 90%|█████████ | 3256/3598 [58:29<05:09,  1.11it/s]
 91%|█████████ | 3257/3598 [58:30<05:10,  1.10it/s]
 91%|█████████ | 3258/3598 [58:31<05:14,  1.08it/s]
 91%|█████████ | 3259/3598 [58:32<05:13,  1.08it/s]
 91%|█████████ | 3260/3598 [58:33<05:16,  1.07it/s]
                                                   

 91%|█████████ | 3260/3598 [58:33<05:16,  1.07it/s]
 91%|█████████ | 3261/3598 [58:34<05:28,  1.03it/s]
 91%|█████████ | 3262/3598 [58:35<05:14,  1.07it/s]
 91%|█████████ | 3263/3598 [58:36<05:05,  1.10it/s]
 91%|█████████ | 3264/3598 [58:37<05:07,  1.08it/s]
 91%|█████████ | 3265/3598 [58:38<05:12,  1.07it/s]
 91%|█████████ | 3266/3598 [58:38<05:02,  1.10it/s]
 91%|█████████ | 3267/3598 [58:39<04:59,  1.11it/s]
 91%|█████████ | 3268/3598 [58:40<04:53,  1.13it/s]
 91%|█████████ | 3269/3598 [58:41<05:10,  1.06it/s]
 91%|█████████ | 3270/3598 [58:42<04:58,  1.10it/s]
                                                   

 91%|█████████ | 3270/3598 [58:42<04:58,  1.10it/s]
 91%|█████████ | 3271/3598 [58:43<05:05,  1.07it/s]
 91%|█████████ | 3272/3598 [58:44<05:00,  1.09it/s]
 91%|█████████ | 3273/3598 [58:45<05:41,  1.05s/it]
 91%|█████████ | 3274/3598 [58:46<05:25,  1.01s/it]
 91%|█████████ | 3275/3598 [58:47<05:13,  1.03it/s]
 91%|█████████ | 3276/3598 [58:48<05:44,  1.07s/it]
 91%|█████████ | 3277/3598 [58:49<05:29,  1.03s/it]
 91%|█████████ | 3278/3598 [58:50<05:13,  1.02it/s]
 91%|█████████ | 3279/3598 [58:52<05:44,  1.08s/it]
 91%|█████████ | 3280/3598 [58:53<06:10,  1.16s/it]
                                                   

 91%|█████████ | 3280/3598 [58:53<06:10,  1.16s/it]
 91%|█████████ | 3281/3598 [58:54<06:15,  1.19s/it]
 91%|█████████ | 3282/3598 [58:55<05:53,  1.12s/it]
 91%|█████████ | 3283/3598 [58:56<06:03,  1.15s/it]
 91%|█████████▏| 3284/3598 [58:57<05:36,  1.07s/it]
 91%|█████████▏| 3285/3598 [58:58<05:40,  1.09s/it]
 91%|█████████▏| 3286/3598 [59:00<06:02,  1.16s/it]
 91%|█████████▏| 3287/3598 [59:01<05:44,  1.11s/it]
 91%|█████████▏| 3288/3598 [59:02<05:23,  1.04s/it]
 91%|█████████▏| 3289/3598 [59:02<05:02,  1.02it/s]
 91%|█████████▏| 3290/3598 [59:04<05:38,  1.10s/it]
                                                   

 91%|█████████▏| 3290/3598 [59:04<05:38,  1.10s/it]
 91%|█████████▏| 3291/3598 [59:05<05:18,  1.04s/it]
 91%|█████████▏| 3292/3598 [59:06<05:17,  1.04s/it]
 92%|█████████▏| 3293/3598 [59:07<05:05,  1.00s/it]
 92%|█████████▏| 3294/3598 [59:07<04:50,  1.05it/s]
 92%|█████████▏| 3295/3598 [59:08<04:54,  1.03it/s]
 92%|█████████▏| 3296/3598 [59:10<05:03,  1.01s/it]
 92%|█████████▏| 3297/3598 [59:10<04:48,  1.04it/s]
 92%|█████████▏| 3298/3598 [59:11<04:34,  1.09it/s]
 92%|█████████▏| 3299/3598 [59:12<04:48,  1.04it/s]
 92%|█████████▏| 3300/3598 [59:13<04:38,  1.07it/s]
                                                   

 92%|█████████▏| 3300/3598 [59:13<04:38,  1.07it/s]
 92%|█████████▏| 3301/3598 [59:14<05:03,  1.02s/it]
 92%|█████████▏| 3302/3598 [59:15<04:55,  1.00it/s]
 92%|█████████▏| 3303/3598 [59:16<04:53,  1.00it/s]
 92%|█████████▏| 3304/3598 [59:17<04:39,  1.05it/s]
 92%|█████████▏| 3305/3598 [59:18<04:38,  1.05it/s]
 92%|█████████▏| 3306/3598 [59:19<04:34,  1.06it/s]
 92%|█████████▏| 3307/3598 [59:20<05:12,  1.07s/it]
 92%|█████████▏| 3308/3598 [59:21<04:59,  1.03s/it]
 92%|█████████▏| 3309/3598 [59:22<04:47,  1.01it/s]
 92%|█████████▏| 3310/3598 [59:23<04:42,  1.02it/s]
                                                   

 92%|█████████▏| 3310/3598 [59:23<04:42,  1.02it/s]
 92%|█████████▏| 3311/3598 [59:24<04:40,  1.02it/s]
 92%|█████████▏| 3312/3598 [59:25<05:01,  1.05s/it]
 92%|█████████▏| 3313/3598 [59:26<04:55,  1.04s/it]
 92%|█████████▏| 3314/3598 [59:27<04:48,  1.01s/it]
 92%|█████████▏| 3315/3598 [59:28<04:35,  1.03it/s]
 92%|█████████▏| 3316/3598 [59:29<04:40,  1.00it/s]
 92%|█████████▏| 3317/3598 [59:30<04:33,  1.03it/s]
 92%|█████████▏| 3318/3598 [59:31<04:27,  1.05it/s]
 92%|█████████▏| 3319/3598 [59:32<04:34,  1.02it/s]
 92%|█████████▏| 3320/3598 [59:34<05:04,  1.10s/it]
                                                   

 92%|█████████▏| 3320/3598 [59:34<05:04,  1.10s/it]
 92%|█████████▏| 3321/3598 [59:34<04:50,  1.05s/it]
 92%|█████████▏| 3322/3598 [59:35<04:33,  1.01it/s]
 92%|█████████▏| 3323/3598 [59:36<04:39,  1.02s/it]
 92%|█████████▏| 3324/3598 [59:37<04:33,  1.00it/s]
 92%|█████████▏| 3325/3598 [59:38<04:27,  1.02it/s]
 92%|█████████▏| 3326/3598 [59:39<04:28,  1.01it/s]
 92%|█████████▏| 3327/3598 [59:41<05:00,  1.11s/it]
 92%|█████████▏| 3328/3598 [59:42<04:43,  1.05s/it]
 93%|█████████▎| 3329/3598 [59:42<04:30,  1.01s/it]
 93%|█████████▎| 3330/3598 [59:43<04:25,  1.01it/s]
                                                   

 93%|█████████▎| 3330/3598 [59:43<04:25,  1.01it/s]
 93%|█████████▎| 3331/3598 [59:45<04:41,  1.05s/it]
 93%|█████████▎| 3332/3598 [59:46<04:25,  1.00it/s]
 93%|█████████▎| 3333/3598 [59:46<04:14,  1.04it/s]
 93%|█████████▎| 3334/3598 [59:47<04:08,  1.06it/s]
 93%|█████████▎| 3335/3598 [59:49<04:35,  1.05s/it]
 93%|█████████▎| 3336/3598 [59:50<04:53,  1.12s/it]
 93%|█████████▎| 3337/3598 [59:51<04:32,  1.05s/it]
 93%|█████████▎| 3338/3598 [59:52<04:19,  1.00it/s]
 93%|█████████▎| 3339/3598 [59:52<04:07,  1.05it/s]
 93%|█████████▎| 3340/3598 [59:54<04:28,  1.04s/it]
                                                   

 93%|█████████▎| 3340/3598 [59:54<04:28,  1.04s/it]
 93%|█████████▎| 3341/3598 [59:55<04:16,  1.00it/s]
 93%|█████████▎| 3342/3598 [59:56<04:13,  1.01it/s]
 93%|█████████▎| 3343/3598 [59:57<04:13,  1.01it/s]
 93%|█████████▎| 3344/3598 [59:58<04:17,  1.01s/it]
 93%|█████████▎| 3345/3598 [59:59<04:13,  1.00s/it]
 93%|█████████▎| 3346/3598 [1:00:00<04:36,  1.10s/it]
 93%|█████████▎| 3347/3598 [1:00:01<04:22,  1.04s/it]
 93%|█████████▎| 3348/3598 [1:00:02<04:19,  1.04s/it]
 93%|█████████▎| 3349/3598 [1:00:03<04:03,  1.02it/s]
 93%|█████████▎| 3350/3598 [1:00:04<04:08,  1.00s/it]
                                                     

 93%|█████████▎| 3350/3598 [1:00:04<04:08,  1.00s/it]
 93%|█████████▎| 3351/3598 [1:00:05<03:52,  1.06it/s]
 93%|█████████▎| 3352/3598 [1:00:05<03:47,  1.08it/s]
 93%|█████████▎| 3353/3598 [1:00:07<03:58,  1.03it/s]
 93%|█████████▎| 3354/3598 [1:00:08<03:56,  1.03it/s]
 93%|█████████▎| 3355/3598 [1:00:08<03:52,  1.05it/s]
 93%|█████████▎| 3356/3598 [1:00:09<03:38,  1.11it/s]
 93%|█████████▎| 3357/3598 [1:00:11<04:04,  1.02s/it]
 93%|█████████▎| 3358/3598 [1:00:11<03:47,  1.06it/s]
 93%|█████████▎| 3359/3598 [1:00:13<04:07,  1.04s/it]
 93%|█████████▎| 3360/3598 [1:00:14<04:19,  1.09s/it]
                                                     

 93%|█████████▎| 3360/3598 [1:00:14<04:19,  1.09s/it]
 93%|█████████▎| 3361/3598 [1:00:15<04:14,  1.07s/it]
 93%|█████████▎| 3362/3598 [1:00:16<04:01,  1.02s/it]
 93%|█████████▎| 3363/3598 [1:00:17<03:57,  1.01s/it]
 93%|█████████▎| 3364/3598 [1:00:18<04:09,  1.07s/it]
 94%|█████████▎| 3365/3598 [1:00:19<04:00,  1.03s/it]
 94%|█████████▎| 3366/3598 [1:00:20<04:12,  1.09s/it]
 94%|█████████▎| 3367/3598 [1:00:21<03:59,  1.04s/it]
 94%|█████████▎| 3368/3598 [1:00:22<03:47,  1.01it/s]
 94%|█████████▎| 3369/3598 [1:00:23<03:43,  1.02it/s]
 94%|█████████▎| 3370/3598 [1:00:24<03:40,  1.03it/s]
                                                     

 94%|█████████▎| 3370/3598 [1:00:24<03:40,  1.03it/s]
 94%|█████████▎| 3371/3598 [1:00:25<03:43,  1.01it/s]
 94%|█████████▎| 3372/3598 [1:00:26<03:31,  1.07it/s]
 94%|█████████▎| 3373/3598 [1:00:26<03:24,  1.10it/s]
 94%|█████████▍| 3374/3598 [1:00:27<03:18,  1.13it/s]
 94%|█████████▍| 3375/3598 [1:00:29<03:51,  1.04s/it]
 94%|█████████▍| 3376/3598 [1:00:30<03:47,  1.02s/it]
 94%|█████████▍| 3377/3598 [1:00:30<03:33,  1.04it/s]
 94%|█████████▍| 3378/3598 [1:00:32<03:59,  1.09s/it]
 94%|█████████▍| 3379/3598 [1:00:33<03:47,  1.04s/it]
 94%|█████████▍| 3380/3598 [1:00:34<04:01,  1.11s/it]
                                                     

 94%|█████████▍| 3380/3598 [1:00:34<04:01,  1.11s/it]
 94%|█████████▍| 3381/3598 [1:00:35<03:51,  1.07s/it]
 94%|█████████▍| 3382/3598 [1:00:36<03:55,  1.09s/it]
 94%|█████████▍| 3383/3598 [1:00:37<03:48,  1.06s/it]
 94%|█████████▍| 3384/3598 [1:00:38<03:44,  1.05s/it]
 94%|█████████▍| 3385/3598 [1:00:39<03:33,  1.00s/it]
 94%|█████████▍| 3386/3598 [1:00:40<03:24,  1.04it/s]
 94%|█████████▍| 3387/3598 [1:00:41<03:19,  1.06it/s]
 94%|█████████▍| 3388/3598 [1:00:42<03:20,  1.05it/s]
 94%|█████████▍| 3389/3598 [1:00:43<03:19,  1.05it/s]
 94%|█████████▍| 3390/3598 [1:00:44<03:45,  1.08s/it]
                                                     

 94%|█████████▍| 3390/3598 [1:00:44<03:45,  1.08s/it]
 94%|█████████▍| 3391/3598 [1:00:45<03:34,  1.04s/it]
 94%|█████████▍| 3392/3598 [1:00:46<03:20,  1.03it/s]
 94%|█████████▍| 3393/3598 [1:00:47<03:10,  1.08it/s]
 94%|█████████▍| 3394/3598 [1:00:48<03:06,  1.09it/s]
 94%|█████████▍| 3395/3598 [1:00:49<03:14,  1.04it/s]
 94%|█████████▍| 3396/3598 [1:00:50<03:18,  1.02it/s]
 94%|█████████▍| 3397/3598 [1:00:51<03:42,  1.11s/it]
 94%|█████████▍| 3398/3598 [1:00:52<03:31,  1.06s/it]
 94%|█████████▍| 3399/3598 [1:00:53<03:16,  1.01it/s]
 94%|█████████▍| 3400/3598 [1:00:54<03:32,  1.07s/it]
                                                     

 94%|█████████▍| 3400/3598 [1:00:54<03:32,  1.07s/it]
 95%|█████████▍| 3401/3598 [1:00:55<03:32,  1.08s/it]
 95%|█████████▍| 3402/3598 [1:00:56<03:18,  1.01s/it]
 95%|█████████▍| 3403/3598 [1:00:57<03:09,  1.03it/s]
 95%|█████████▍| 3404/3598 [1:00:58<03:08,  1.03it/s]
 95%|█████████▍| 3405/3598 [1:00:59<03:23,  1.05s/it]
 95%|█████████▍| 3406/3598 [1:01:01<03:42,  1.16s/it]
 95%|█████████▍| 3407/3598 [1:01:02<03:46,  1.19s/it]
 95%|█████████▍| 3408/3598 [1:01:03<03:36,  1.14s/it]
 95%|█████████▍| 3409/3598 [1:01:04<03:35,  1.14s/it]
 95%|█████████▍| 3410/3598 [1:01:05<03:17,  1.05s/it]
                                                     

 95%|█████████▍| 3410/3598 [1:01:05<03:17,  1.05s/it]
 95%|█████████▍| 3411/3598 [1:01:06<03:02,  1.02it/s]
 95%|█████████▍| 3412/3598 [1:01:07<03:01,  1.03it/s]
 95%|█████████▍| 3413/3598 [1:01:08<02:57,  1.04it/s]
 95%|█████████▍| 3414/3598 [1:01:09<02:59,  1.02it/s]
 95%|█████████▍| 3415/3598 [1:01:09<02:52,  1.06it/s]
 95%|█████████▍| 3416/3598 [1:01:10<02:56,  1.03it/s]
 95%|█████████▍| 3417/3598 [1:01:11<02:55,  1.03it/s]
 95%|█████████▍| 3418/3598 [1:01:13<03:00,  1.00s/it]
 95%|█████████▌| 3419/3598 [1:01:13<02:48,  1.06it/s]
 95%|█████████▌| 3420/3598 [1:01:14<02:49,  1.05it/s]
                                                     

 95%|█████████▌| 3420/3598 [1:01:14<02:49,  1.05it/s]
 95%|█████████▌| 3421/3598 [1:01:16<03:07,  1.06s/it]
 95%|█████████▌| 3422/3598 [1:01:16<02:54,  1.01it/s]
 95%|█████████▌| 3423/3598 [1:01:17<02:46,  1.05it/s]
 95%|█████████▌| 3424/3598 [1:01:19<03:09,  1.09s/it]
 95%|█████████▌| 3425/3598 [1:01:20<03:01,  1.05s/it]
 95%|█████████▌| 3426/3598 [1:01:20<02:47,  1.03it/s]
 95%|█████████▌| 3427/3598 [1:01:22<03:09,  1.11s/it]
 95%|█████████▌| 3428/3598 [1:01:23<02:58,  1.05s/it]
 95%|█████████▌| 3429/3598 [1:01:24<02:43,  1.03it/s]
 95%|█████████▌| 3430/3598 [1:01:25<02:43,  1.03it/s]
                                                     

 95%|█████████▌| 3430/3598 [1:01:25<02:43,  1.03it/s]
 95%|█████████▌| 3431/3598 [1:01:25<02:40,  1.04it/s]
 95%|█████████▌| 3432/3598 [1:01:27<02:51,  1.03s/it]
 95%|█████████▌| 3433/3598 [1:01:28<02:44,  1.00it/s]
 95%|█████████▌| 3434/3598 [1:01:29<02:43,  1.00it/s]
 95%|█████████▌| 3435/3598 [1:01:30<02:40,  1.02it/s]
 95%|█████████▌| 3436/3598 [1:01:30<02:34,  1.05it/s]
 96%|█████████▌| 3437/3598 [1:01:31<02:27,  1.09it/s]
 96%|█████████▌| 3438/3598 [1:01:32<02:27,  1.09it/s]
 96%|█████████▌| 3439/3598 [1:01:33<02:28,  1.07it/s]
 96%|█████████▌| 3440/3598 [1:01:34<02:26,  1.08it/s]
                                                     

 96%|█████████▌| 3440/3598 [1:01:34<02:26,  1.08it/s]
 96%|█████████▌| 3441/3598 [1:01:35<02:26,  1.07it/s]
 96%|█████████▌| 3442/3598 [1:01:36<02:25,  1.08it/s]
 96%|█████████▌| 3443/3598 [1:01:37<02:24,  1.07it/s]
 96%|█████████▌| 3444/3598 [1:01:38<02:20,  1.10it/s]
 96%|█████████▌| 3445/3598 [1:01:39<02:42,  1.06s/it]
 96%|█████████▌| 3446/3598 [1:01:41<02:55,  1.15s/it]
 96%|█████████▌| 3447/3598 [1:01:41<02:41,  1.07s/it]
 96%|█████████▌| 3448/3598 [1:01:42<02:32,  1.02s/it]
 96%|█████████▌| 3449/3598 [1:01:44<02:49,  1.14s/it]
 96%|█████████▌| 3450/3598 [1:01:45<02:37,  1.06s/it]
                                                     

 96%|█████████▌| 3450/3598 [1:01:45<02:37,  1.06s/it]
 96%|█████████▌| 3451/3598 [1:01:46<02:31,  1.03s/it]
 96%|█████████▌| 3452/3598 [1:01:47<02:46,  1.14s/it]
 96%|█████████▌| 3453/3598 [1:01:48<02:40,  1.10s/it]
 96%|█████████▌| 3454/3598 [1:01:49<02:39,  1.11s/it]
 96%|█████████▌| 3455/3598 [1:01:50<02:29,  1.04s/it]
 96%|█████████▌| 3456/3598 [1:01:51<02:39,  1.12s/it]
 96%|█████████▌| 3457/3598 [1:01:52<02:33,  1.09s/it]
 96%|█████████▌| 3458/3598 [1:01:53<02:27,  1.05s/it]
 96%|█████████▌| 3459/3598 [1:01:54<02:26,  1.05s/it]
 96%|█████████▌| 3460/3598 [1:01:55<02:23,  1.04s/it]
                                                     

 96%|█████████▌| 3460/3598 [1:01:55<02:23,  1.04s/it]
 96%|█████████▌| 3461/3598 [1:01:56<02:14,  1.02it/s]
 96%|█████████▌| 3462/3598 [1:01:57<02:14,  1.01it/s]
 96%|█████████▌| 3463/3598 [1:01:58<02:10,  1.04it/s]
 96%|█████████▋| 3464/3598 [1:01:59<02:10,  1.03it/s]
 96%|█████████▋| 3465/3598 [1:02:00<02:26,  1.10s/it]
 96%|█████████▋| 3466/3598 [1:02:01<02:19,  1.06s/it]
 96%|█████████▋| 3467/3598 [1:02:03<02:31,  1.16s/it]
 96%|█████████▋| 3468/3598 [1:02:04<02:40,  1.23s/it]
 96%|█████████▋| 3469/3598 [1:02:06<02:45,  1.28s/it]
 96%|█████████▋| 3470/3598 [1:02:07<02:42,  1.27s/it]
                                                     
{'eval_loss': 0.7080053687095642, 'eval_bleu': 36.834191198203946, 'eval_chrf': 66.61229334586629, 'eval_runtime': 41.8487, 'eval_samples_per_second': 3.059, 'eval_steps_per_second': 0.096, 'epoch': 0.75}
{'loss': 0.5665, 'grad_norm': 1.5874916315078735, 'learning_rate': 5.196021064950264e-05, 'epoch': 0.75}
{'loss': 0.6897, 'grad_norm': 1.471414566040039, 'learning_rate': 5.1375073142188414e-05, 'epoch': 0.76}
{'loss': 0.6559, 'grad_norm': 0.9071055054664612, 'learning_rate': 5.0789935634874195e-05, 'epoch': 0.76}
{'loss': 0.7094, 'grad_norm': 1.334881067276001, 'learning_rate': 5.020479812755998e-05, 'epoch': 0.76}
{'loss': 0.6073, 'grad_norm': 1.105324149131775, 'learning_rate': 4.9619660620245763e-05, 'epoch': 0.76}
{'loss': 0.5923, 'grad_norm': 1.4565565586090088, 'learning_rate': 4.903452311293154e-05, 'epoch': 0.77}
{'loss': 0.5876, 'grad_norm': 1.5638223886489868, 'learning_rate': 4.844938560561732e-05, 'epoch': 0.77}
{'loss': 0.5577, 'grad_norm': 1.4914469718933105, 'learning_rate': 4.7864248098303106e-05, 'epoch': 0.77}
{'loss': 0.6794, 'grad_norm': 1.210353136062622, 'learning_rate': 4.727911059098889e-05, 'epoch': 0.78}
{'loss': 0.6647, 'grad_norm': 1.5976355075836182, 'learning_rate': 4.669397308367466e-05, 'epoch': 0.78}
{'loss': 0.5793, 'grad_norm': 1.2854108810424805, 'learning_rate': 4.610883557636045e-05, 'epoch': 0.78}
{'loss': 0.7555, 'grad_norm': 1.4772543907165527, 'learning_rate': 4.552369806904623e-05, 'epoch': 0.78}
{'loss': 0.6369, 'grad_norm': 1.509872317314148, 'learning_rate': 4.4938560561732004e-05, 'epoch': 0.79}
{'loss': 0.669, 'grad_norm': 2.4350647926330566, 'learning_rate': 4.435342305441779e-05, 'epoch': 0.79}
{'loss': 0.6086, 'grad_norm': 1.8682899475097656, 'learning_rate': 4.376828554710357e-05, 'epoch': 0.79}
{'loss': 0.5857, 'grad_norm': 1.8308444023132324, 'learning_rate': 4.3183148039789354e-05, 'epoch': 0.79}
{'loss': 0.6207, 'grad_norm': 1.4512547254562378, 'learning_rate': 4.2598010532475135e-05, 'epoch': 0.8}
{'loss': 0.5281, 'grad_norm': 1.0981119871139526, 'learning_rate': 4.2012873025160916e-05, 'epoch': 0.8}
{'loss': 0.6987, 'grad_norm': 1.1227097511291504, 'learning_rate': 4.1427735517846696e-05, 'epoch': 0.8}
{'loss': 0.6354, 'grad_norm': 1.349419116973877, 'learning_rate': 4.084259801053248e-05, 'epoch': 0.81}
{'loss': 0.6707, 'grad_norm': 1.6693001985549927, 'learning_rate': 4.025746050321826e-05, 'epoch': 0.81}
{'loss': 0.5555, 'grad_norm': 1.5549803972244263, 'learning_rate': 3.967232299590404e-05, 'epoch': 0.81}
{'loss': 0.591, 'grad_norm': 1.785648226737976, 'learning_rate': 3.908718548858982e-05, 'epoch': 0.81}
{'loss': 0.5992, 'grad_norm': 1.2887086868286133, 'learning_rate': 3.85020479812756e-05, 'epoch': 0.82}
{'loss': 0.7092, 'grad_norm': 1.1370317935943604, 'learning_rate': 3.791691047396138e-05, 'epoch': 0.82}
{'loss': 0.6683, 'grad_norm': 1.367082118988037, 'learning_rate': 3.733177296664716e-05, 'epoch': 0.82}
{'loss': 0.5731, 'grad_norm': 1.0612155199050903, 'learning_rate': 3.6746635459332944e-05, 'epoch': 0.83}
{'loss': 0.6481, 'grad_norm': 1.8601607084274292, 'learning_rate': 3.6161497952018725e-05, 'epoch': 0.83}
{'loss': 0.5889, 'grad_norm': 1.3319456577301025, 'learning_rate': 3.557636044470451e-05, 'epoch': 0.83}
{'loss': 0.6499, 'grad_norm': 1.5521312952041626, 'learning_rate': 3.499122293739029e-05, 'epoch': 0.83}
{'loss': 0.5202, 'grad_norm': 1.5546648502349854, 'learning_rate': 3.440608543007607e-05, 'epoch': 0.84}
{'loss': 0.5754, 'grad_norm': 0.7544180154800415, 'learning_rate': 3.3820947922761855e-05, 'epoch': 0.84}
{'loss': 0.5376, 'grad_norm': 1.0516163110733032, 'learning_rate': 3.323581041544763e-05, 'epoch': 0.84}
{'loss': 0.7268, 'grad_norm': 0.9787018299102783, 'learning_rate': 3.265067290813341e-05, 'epoch': 0.84}
{'loss': 0.6491, 'grad_norm': 1.4314815998077393, 'learning_rate': 3.20655354008192e-05, 'epoch': 0.85}
{'loss': 0.6874, 'grad_norm': 1.324827790260315, 'learning_rate': 3.148039789350498e-05, 'epoch': 0.85}
{'loss': 0.6082, 'grad_norm': 1.5152019262313843, 'learning_rate': 3.089526038619075e-05, 'epoch': 0.85}
{'loss': 0.7667, 'grad_norm': 1.2576498985290527, 'learning_rate': 3.031012287887654e-05, 'epoch': 0.86}
{'loss': 0.4844, 'grad_norm': 0.9412326812744141, 'learning_rate': 2.972498537156232e-05, 'epoch': 0.86}
{'loss': 0.6217, 'grad_norm': 1.187469244003296, 'learning_rate': 2.91398478642481e-05, 'epoch': 0.86}
{'loss': 0.6016, 'grad_norm': 1.1852264404296875, 'learning_rate': 2.8554710356933877e-05, 'epoch': 0.86}
{'loss': 0.4414, 'grad_norm': 1.1429516077041626, 'learning_rate': 2.796957284961966e-05, 'epoch': 0.87}
{'loss': 0.517, 'grad_norm': 1.570572853088379, 'learning_rate': 2.7384435342305442e-05, 'epoch': 0.87}
{'loss': 0.6303, 'grad_norm': 1.1809591054916382, 'learning_rate': 2.6799297834991223e-05, 'epoch': 0.87}
{'loss': 0.631, 'grad_norm': 1.0413581132888794, 'learning_rate': 2.6214160327677007e-05, 'epoch': 0.88}
{'loss': 0.6164, 'grad_norm': 1.1612534523010254, 'learning_rate': 2.5629022820362785e-05, 'epoch': 0.88}
{'loss': 0.6026, 'grad_norm': 1.1018447875976562, 'learning_rate': 2.5043885313048566e-05, 'epoch': 0.88}
{'loss': 0.6073, 'grad_norm': 1.2285889387130737, 'learning_rate': 2.445874780573435e-05, 'epoch': 0.88}
{'loss': 0.6716, 'grad_norm': 1.6262547969818115, 'learning_rate': 2.3873610298420128e-05, 'epoch': 0.89}
{'loss': 0.6884, 'grad_norm': 1.1921401023864746, 'learning_rate': 2.3288472791105912e-05, 'epoch': 0.89}
{'loss': 0.6217, 'grad_norm': 1.3749579191207886, 'learning_rate': 2.2703335283791693e-05, 'epoch': 0.89}
{'loss': 0.4955, 'grad_norm': 0.9302161931991577, 'learning_rate': 2.2118197776477474e-05, 'epoch': 0.89}
{'loss': 0.6861, 'grad_norm': 1.1946569681167603, 'learning_rate': 2.1533060269163255e-05, 'epoch': 0.9}
{'loss': 0.4447, 'grad_norm': 1.4691694974899292, 'learning_rate': 2.0947922761849036e-05, 'epoch': 0.9}
{'loss': 0.6073, 'grad_norm': 1.4222508668899536, 'learning_rate': 2.0362785254534817e-05, 'epoch': 0.9}
{'loss': 0.5341, 'grad_norm': 1.5230867862701416, 'learning_rate': 1.9777647747220598e-05, 'epoch': 0.91}
{'loss': 0.5286, 'grad_norm': 1.1844643354415894, 'learning_rate': 1.919251023990638e-05, 'epoch': 0.91}
{'loss': 0.7289, 'grad_norm': 1.1704039573669434, 'learning_rate': 1.860737273259216e-05, 'epoch': 0.91}
{'loss': 0.7212, 'grad_norm': 1.4930881261825562, 'learning_rate': 1.802223522527794e-05, 'epoch': 0.91}
{'loss': 0.5754, 'grad_norm': 1.3442230224609375, 'learning_rate': 1.743709771796372e-05, 'epoch': 0.92}
{'loss': 0.5899, 'grad_norm': 1.3578684329986572, 'learning_rate': 1.6851960210649502e-05, 'epoch': 0.92}
{'loss': 0.5864, 'grad_norm': 1.2579971551895142, 'learning_rate': 1.6266822703335287e-05, 'epoch': 0.92}
{'loss': 0.6355, 'grad_norm': 1.314341425895691, 'learning_rate': 1.5681685196021064e-05, 'epoch': 0.93}
{'loss': 0.601, 'grad_norm': 1.0620858669281006, 'learning_rate': 1.5096547688706847e-05, 'epoch': 0.93}
{'loss': 0.6049, 'grad_norm': 1.2325353622436523, 'learning_rate': 1.451141018139263e-05, 'epoch': 0.93}
{'loss': 0.5417, 'grad_norm': 0.9464172124862671, 'learning_rate': 1.3926272674078409e-05, 'epoch': 0.93}
{'loss': 0.6688, 'grad_norm': 1.453446865081787, 'learning_rate': 1.334113516676419e-05, 'epoch': 0.94}
{'loss': 0.6055, 'grad_norm': 1.1557977199554443, 'learning_rate': 1.2755997659449972e-05, 'epoch': 0.94}
{'loss': 0.6085, 'grad_norm': 1.08552885055542, 'learning_rate': 1.2170860152135752e-05, 'epoch': 0.94}
{'loss': 0.5834, 'grad_norm': 1.2602875232696533, 'learning_rate': 1.1585722644821534e-05, 'epoch': 0.94}
{'loss': 0.5876, 'grad_norm': 1.5725733041763306, 'learning_rate': 1.1000585137507315e-05, 'epoch': 0.95}
{'loss': 0.5752, 'grad_norm': 1.2837549448013306, 'learning_rate': 1.0415447630193096e-05, 'epoch': 0.95}
{'loss': 0.5663, 'grad_norm': 0.9232473373413086, 'learning_rate': 9.830310122878877e-06, 'epoch': 0.95}
{'loss': 0.5702, 'grad_norm': 1.2556686401367188, 'learning_rate': 9.245172615564658e-06, 'epoch': 0.96}
{'loss': 0.5578, 'grad_norm': 1.138568639755249, 'learning_rate': 8.660035108250439e-06, 'epoch': 0.96}
{'loss': 0.6894, 'grad_norm': 1.1079130172729492, 'learning_rate': 8.074897600936221e-06, 'epoch': 0.96}
{'loss': 0.6521, 'grad_norm': 1.0000965595245361, 'learning_rate': 7.4897600936220015e-06, 'epoch': 0.96}
 96%|█████████▋| 3470/3598 [1:02:07<02:42,  1.27s/it]
 96%|█████████▋| 3471/3598 [1:02:08<02:26,  1.15s/it]
 96%|█████████▋| 3472/3598 [1:02:09<02:33,  1.22s/it]
 97%|█████████▋| 3473/3598 [1:02:10<02:32,  1.22s/it]
 97%|█████████▋| 3474/3598 [1:02:12<02:30,  1.21s/it]
 97%|█████████▋| 3475/3598 [1:02:13<02:20,  1.15s/it]
 97%|█████████▋| 3476/3598 [1:02:13<02:13,  1.09s/it]
 97%|█████████▋| 3477/3598 [1:02:15<02:22,  1.18s/it]
 97%|█████████▋| 3478/3598 [1:02:16<02:12,  1.10s/it]
 97%|█████████▋| 3479/3598 [1:02:17<02:03,  1.04s/it]
 97%|█████████▋| 3480/3598 [1:02:18<02:01,  1.03s/it]
                                                     

 97%|█████████▋| 3480/3598 [1:02:18<02:01,  1.03s/it]
 97%|█████████▋| 3481/3598 [1:02:19<01:55,  1.02it/s]
 97%|█████████▋| 3482/3598 [1:02:19<01:50,  1.05it/s]
 97%|█████████▋| 3483/3598 [1:02:20<01:47,  1.07it/s]
 97%|█████████▋| 3484/3598 [1:02:21<01:45,  1.08it/s]
 97%|█████████▋| 3485/3598 [1:02:22<01:44,  1.08it/s]
 97%|█████████▋| 3486/3598 [1:02:23<01:41,  1.10it/s]
 97%|█████████▋| 3487/3598 [1:02:24<01:41,  1.09it/s]
 97%|█████████▋| 3488/3598 [1:02:25<01:41,  1.09it/s]
 97%|█████████▋| 3489/3598 [1:02:26<01:38,  1.11it/s]
 97%|█████████▋| 3490/3598 [1:02:27<01:33,  1.15it/s]
                                                     

 97%|█████████▋| 3490/3598 [1:02:27<01:33,  1.15it/s]
 97%|█████████▋| 3491/3598 [1:02:28<01:36,  1.11it/s]
 97%|█████████▋| 3492/3598 [1:02:29<01:38,  1.08it/s]
 97%|█████████▋| 3493/3598 [1:02:30<01:40,  1.04it/s]
 97%|█████████▋| 3494/3598 [1:02:30<01:38,  1.05it/s]
 97%|█████████▋| 3495/3598 [1:02:31<01:37,  1.06it/s]
 97%|█████████▋| 3496/3598 [1:02:32<01:34,  1.08it/s]
 97%|█████████▋| 3497/3598 [1:02:33<01:31,  1.11it/s]
 97%|█████████▋| 3498/3598 [1:02:34<01:32,  1.08it/s]
 97%|█████████▋| 3499/3598 [1:02:35<01:29,  1.10it/s]
 97%|█████████▋| 3500/3598 [1:02:36<01:29,  1.09it/s]
                                                     

 97%|█████████▋| 3500/3598 [1:02:36<01:29,  1.09it/s]
 97%|█████████▋| 3501/3598 [1:02:37<01:30,  1.07it/s]
 97%|█████████▋| 3502/3598 [1:02:38<01:27,  1.10it/s]
 97%|█████████▋| 3503/3598 [1:02:39<01:31,  1.03it/s]
 97%|█████████▋| 3504/3598 [1:02:40<01:29,  1.05it/s]
 97%|█████████▋| 3505/3598 [1:02:41<01:33,  1.00s/it]
 97%|█████████▋| 3506/3598 [1:02:42<01:31,  1.00it/s]
 97%|█████████▋| 3507/3598 [1:02:43<01:33,  1.03s/it]
 97%|█████████▋| 3508/3598 [1:02:44<01:33,  1.04s/it]
 98%|█████████▊| 3509/3598 [1:02:45<01:28,  1.01it/s]
 98%|█████████▊| 3510/3598 [1:02:46<01:39,  1.14s/it]
                                                     

 98%|█████████▊| 3510/3598 [1:02:46<01:39,  1.14s/it]
 98%|█████████▊| 3511/3598 [1:02:47<01:33,  1.08s/it]
 98%|█████████▊| 3512/3598 [1:02:48<01:28,  1.03s/it]
 98%|█████████▊| 3513/3598 [1:02:50<01:35,  1.13s/it]
 98%|█████████▊| 3514/3598 [1:02:51<01:37,  1.16s/it]
 98%|█████████▊| 3515/3598 [1:02:52<01:29,  1.08s/it]
 98%|█████████▊| 3516/3598 [1:02:53<01:25,  1.05s/it]
 98%|█████████▊| 3517/3598 [1:02:54<01:21,  1.01s/it]
 98%|█████████▊| 3518/3598 [1:02:55<01:18,  1.02it/s]
 98%|█████████▊| 3519/3598 [1:02:56<01:28,  1.12s/it]
 98%|█████████▊| 3520/3598 [1:02:57<01:21,  1.04s/it]
                                                     

 98%|█████████▊| 3520/3598 [1:02:57<01:21,  1.04s/it]
 98%|█████████▊| 3521/3598 [1:02:58<01:14,  1.04it/s]
 98%|█████████▊| 3522/3598 [1:02:59<01:11,  1.07it/s]
 98%|█████████▊| 3523/3598 [1:03:00<01:17,  1.03s/it]
 98%|█████████▊| 3524/3598 [1:03:01<01:12,  1.03it/s]
 98%|█████████▊| 3525/3598 [1:03:02<01:19,  1.10s/it]
 98%|█████████▊| 3526/3598 [1:03:03<01:16,  1.06s/it]
 98%|█████████▊| 3527/3598 [1:03:04<01:13,  1.03s/it]
 98%|█████████▊| 3528/3598 [1:03:05<01:13,  1.04s/it]
 98%|█████████▊| 3529/3598 [1:03:06<01:10,  1.03s/it]
 98%|█████████▊| 3530/3598 [1:03:07<01:15,  1.10s/it]
                                                     

 98%|█████████▊| 3530/3598 [1:03:07<01:15,  1.10s/it]
 98%|█████████▊| 3531/3598 [1:03:08<01:13,  1.10s/it]
 98%|█████████▊| 3532/3598 [1:03:09<01:12,  1.10s/it]
 98%|█████████▊| 3533/3598 [1:03:11<01:17,  1.19s/it]
 98%|█████████▊| 3534/3598 [1:03:12<01:08,  1.08s/it]
 98%|█████████▊| 3535/3598 [1:03:13<01:08,  1.09s/it]
 98%|█████████▊| 3536/3598 [1:03:14<01:05,  1.05s/it]
 98%|█████████▊| 3537/3598 [1:03:15<01:00,  1.00it/s]
 98%|█████████▊| 3538/3598 [1:03:16<01:03,  1.05s/it]
 98%|█████████▊| 3539/3598 [1:03:17<00:58,  1.00it/s]
 98%|█████████▊| 3540/3598 [1:03:18<00:55,  1.05it/s]
                                                     

 98%|█████████▊| 3540/3598 [1:03:18<00:55,  1.05it/s]
 98%|█████████▊| 3541/3598 [1:03:18<00:52,  1.08it/s]
 98%|█████████▊| 3542/3598 [1:03:19<00:53,  1.05it/s]
 98%|█████████▊| 3543/3598 [1:03:20<00:51,  1.07it/s]
 98%|█████████▊| 3544/3598 [1:03:21<00:50,  1.06it/s]
 99%|█████████▊| 3545/3598 [1:03:22<00:48,  1.09it/s]
 99%|█████████▊| 3546/3598 [1:03:24<00:54,  1.06s/it]
 99%|█████████▊| 3547/3598 [1:03:24<00:50,  1.01it/s]
 99%|█████████▊| 3548/3598 [1:03:25<00:48,  1.04it/s]
 99%|█████████▊| 3549/3598 [1:03:26<00:47,  1.02it/s]
 99%|█████████▊| 3550/3598 [1:03:27<00:49,  1.04s/it]
                                                     

 99%|█████████▊| 3550/3598 [1:03:27<00:49,  1.04s/it]
 99%|█████████▊| 3551/3598 [1:03:28<00:48,  1.04s/it]
 99%|█████████▊| 3552/3598 [1:03:29<00:45,  1.02it/s]
 99%|█████████▊| 3553/3598 [1:03:30<00:43,  1.02it/s]
 99%|█████████▉| 3554/3598 [1:03:31<00:44,  1.02s/it]
 99%|█████████▉| 3555/3598 [1:03:32<00:42,  1.00it/s]
 99%|█████████▉| 3556/3598 [1:03:34<00:46,  1.11s/it]
 99%|█████████▉| 3557/3598 [1:03:35<00:43,  1.05s/it]
 99%|█████████▉| 3558/3598 [1:03:36<00:41,  1.03s/it]
 99%|█████████▉| 3559/3598 [1:03:37<00:39,  1.01s/it]
 99%|█████████▉| 3560/3598 [1:03:38<00:40,  1.08s/it]
                                                     

 99%|█████████▉| 3560/3598 [1:03:38<00:40,  1.08s/it]
 99%|█████████▉| 3561/3598 [1:03:39<00:38,  1.05s/it]
 99%|█████████▉| 3562/3598 [1:03:40<00:37,  1.05s/it]
 99%|█████████▉| 3563/3598 [1:03:41<00:39,  1.13s/it]
 99%|█████████▉| 3564/3598 [1:03:42<00:35,  1.06s/it]
 99%|█████████▉| 3565/3598 [1:03:43<00:33,  1.01s/it]
 99%|█████████▉| 3566/3598 [1:03:44<00:31,  1.01it/s]
 99%|█████████▉| 3567/3598 [1:03:45<00:29,  1.04it/s]
 99%|█████████▉| 3568/3598 [1:03:46<00:28,  1.06it/s]
 99%|█████████▉| 3569/3598 [1:03:47<00:26,  1.08it/s]
 99%|█████████▉| 3570/3598 [1:03:48<00:26,  1.05it/s]
                                                     

 99%|█████████▉| 3570/3598 [1:03:48<00:26,  1.05it/s]
 99%|█████████▉| 3571/3598 [1:03:49<00:27,  1.03s/it]
 99%|█████████▉| 3572/3598 [1:03:50<00:25,  1.00it/s]
 99%|█████████▉| 3573/3598 [1:03:51<00:23,  1.05it/s]
 99%|█████████▉| 3574/3598 [1:03:51<00:21,  1.10it/s]
 99%|█████████▉| 3575/3598 [1:03:53<00:23,  1.03s/it]
 99%|█████████▉| 3576/3598 [1:03:54<00:24,  1.10s/it]
 99%|█████████▉| 3577/3598 [1:03:55<00:25,  1.20s/it]
 99%|█████████▉| 3578/3598 [1:03:57<00:24,  1.24s/it]
 99%|█████████▉| 3579/3598 [1:03:58<00:21,  1.13s/it]
 99%|█████████▉| 3580/3598 [1:03:59<00:21,  1.18s/it]
                                                     

 99%|█████████▉| 3580/3598 [1:03:59<00:21,  1.18s/it]
100%|█████████▉| 3581/3598 [1:04:00<00:19,  1.12s/it]
100%|█████████▉| 3582/3598 [1:04:01<00:16,  1.05s/it]
100%|█████████▉| 3583/3598 [1:04:02<00:15,  1.03s/it]
100%|█████████▉| 3584/3598 [1:04:03<00:14,  1.07s/it]
100%|█████████▉| 3585/3598 [1:04:04<00:12,  1.01it/s]
100%|█████████▉| 3586/3598 [1:04:05<00:13,  1.11s/it]
100%|█████████▉| 3587/3598 [1:04:06<00:11,  1.09s/it]
100%|█████████▉| 3588/3598 [1:04:07<00:10,  1.09s/it]
100%|█████████▉| 3589/3598 [1:04:09<00:10,  1.17s/it]
100%|█████████▉| 3590/3598 [1:04:10<00:09,  1.23s/it]
                                                     

100%|█████████▉| 3590/3598 [1:04:10<00:09,  1.23s/it]
100%|█████████▉| 3591/3598 [1:04:11<00:08,  1.19s/it]
100%|█████████▉| 3592/3598 [1:04:12<00:06,  1.10s/it]
100%|█████████▉| 3593/3598 [1:04:13<00:05,  1.04s/it]
100%|█████████▉| 3594/3598 [1:04:14<00:04,  1.03s/it]
100%|█████████▉| 3595/3598 [1:04:15<00:02,  1.01it/s]
100%|█████████▉| 3596/3598 [1:04:16<00:01,  1.08it/s]
100%|█████████▉| 3597/3598 [1:04:17<00:01,  1.07s/it]
100%|██████████| 3598/3598 [1:04:18<00:00,  1.19s/it]/opt/mobtranslate-v24-venv/lib/python3.11/site-packages/peft/utils/save_and_load.py:386: UserWarning: Setting `save_embedding_layers` to `True` as the embedding layer has been resized during finetuning.
  warnings.warn(

                                                     

100%|██████████| 3598/3598 [1:04:23<00:00,  1.19s/it]
100%|██████████| 3598/3598 [1:04:23<00:00,  1.07s/it]
/opt/mobtranslate-v24-venv/lib/python3.11/site-packages/peft/utils/save_and_load.py:386: UserWarning: Setting `save_embedding_layers` to `True` as the embedding layer has been resized during finetuning.
  warnings.warn(

{'loss': 0.7117, 'grad_norm': 1.1308131217956543, 'learning_rate': 6.9046225863077825e-06, 'epoch': 0.97}
{'loss': 0.5305, 'grad_norm': 1.8153457641601562, 'learning_rate': 6.319485078993564e-06, 'epoch': 0.97}
{'loss': 0.5736, 'grad_norm': 1.1955033540725708, 'learning_rate': 5.734347571679345e-06, 'epoch': 0.97}
{'loss': 0.6073, 'grad_norm': 1.1305077075958252, 'learning_rate': 5.149210064365126e-06, 'epoch': 0.98}
{'loss': 0.5432, 'grad_norm': 1.875968098640442, 'learning_rate': 4.564072557050907e-06, 'epoch': 0.98}
{'loss': 0.6327, 'grad_norm': 1.0293177366256714, 'learning_rate': 3.978935049736688e-06, 'epoch': 0.98}
{'loss': 0.5867, 'grad_norm': 1.6121056079864502, 'learning_rate': 3.3937975424224693e-06, 'epoch': 0.98}
{'loss': 0.5826, 'grad_norm': 1.166865348815918, 'learning_rate': 2.8086600351082503e-06, 'epoch': 0.99}
{'loss': 0.6175, 'grad_norm': 1.2993223667144775, 'learning_rate': 2.223522527794032e-06, 'epoch': 0.99}
{'loss': 0.5528, 'grad_norm': 1.318895936012268, 'learning_rate': 1.638385020479813e-06, 'epoch': 0.99}
{'loss': 0.6268, 'grad_norm': 1.0751056671142578, 'learning_rate': 1.053247513165594e-06, 'epoch': 0.99}
{'loss': 0.6024, 'grad_norm': 1.1337924003601074, 'learning_rate': 4.681100058513751e-07, 'epoch': 1.0}
{'train_runtime': 3863.3048, 'train_samples_per_second': 29.802, 'train_steps_per_second': 0.931, 'train_loss': 0.9481710318130145, 'epoch': 1.0}

  0%|          | 0/4 [00:00<?, ?it/s]
 50%|█████     | 2/4 [00:13<00:13,  6.72s/it]
 75%|███████▌  | 3/4 [00:29<00:10, 10.53s/it]
100%|██████████| 4/4 [00:33<00:00,  8.35s/it]
100%|██████████| 4/4 [00:34<00:00,  8.53s/it]
{
  "model_id": "mobtranslate/kuku-yalanji-nllb-lora",
  "version": "v24.3-J69-rerun1",
  "run_id": "v24.3-J69-seed17-rerun1",
  "created_at": "2026-07-15T17:33:31.582296+00:00",
  "base_model": "/workspace/v24.1-lexical-calibration/base_model/merged",
  "base_model_revision": null,
  "license": "research-only; source-specific rights and upstream NLLB CC-BY-NC apply",
  "direction": "eng-gvn",
  "source_lang": "eng_Latn",
  "target_lang": "gvn_Latn",
  "target_lang_init_from": null,
  "source_lang_token_id": 256047,
  "target_lang_token_id": 256204,
  "token_adaptation": {
    "additional_special_tokens": [
      {
        "token": "<lexeme>",
        "token_id": 256205,
        "round_trip": true,
        "single_encoded_id": true,
        "is_special": true,
        "status": "new_token_decomposition_mean",
        "old_token_id": null,
        "decomposition_ids": [
          45,
          20228,
          1633,
          248123
        ],
        "decomposition_tokens": [
          "\u2581<",
          "lex",
          "eme",
          ">"
        ]
      }
    ],
    "trainable_tokens": [
      {
        "token": "<lexeme>",
        "token_id": 256205
      }
    ],
    "trainable_token_wrapper_modules": [
      "base_model.model.model.shared",
      "base_model.model.model.encoder.embed_tokens",
      "base_model.model.model.decoder.embed_tokens",
      "base_model.model.lm_head"
    ],
    "embedding_row_delta_audit": [
      {
        "token": "</s>",
        "selected_for_training": false,
        "input_delta_l2": 0.0,
        "input_delta_max_abs": 0.0,
        "input_changed": false,
        "output_delta_l2": 0.0,
        "output_delta_max_abs": 0.0,
        "output_changed": false
      },
      {
        "token": "<lexeme>",
        "selected_for_training": true,
        "input_delta_l2": 0.1110018715262413,
        "input_delta_max_abs": 0.01171875,
        "input_changed": true,
        "output_delta_l2": 0.1110018715262413,
        "output_delta_max_abs": 0.01171875,
        "output_changed": true
      },
      {
        "token": "<pad>",
        "selected_for_training": false,
        "input_delta_l2": 0.0,
        "input_delta_max_abs": 0.0,
        "input_changed": false,
        "output_delta_l2": 0.0,
        "output_delta_max_abs": 0.0,
        "output_changed": false
      },
      {
        "token": "eng_Latn",
        "selected_for_training": false,
        "input_delta_l2": 0.0,
        "input_delta_max_abs": 0.0,
        "input_changed": false,
        "output_delta_l2": 0.0,
        "output_delta_max_abs": 0.0,
        "output_changed": false
      },
      {
        "token": "gvn_Latn",
        "selected_for_training": false,
        "input_delta_l2": 0.0,
        "input_delta_max_abs": 0.0,
        "input_changed": false,
        "output_delta_l2": 0.0,
        "output_delta_max_abs": 0.0,
        "output_changed": false
      }
    ],
    "unselected_audit_rows_unchanged": true
  },
  "dataset": {
    "dataset_id": "v24.3-joint-lexeme-dose29",
    "release_sha256": "b45cf115c03b41134e481071f6c324fe3180bd73a77720afb8d00529a8dfde1b",
    "train_file": "/workspace/v24.3-joint-lexeme-dose29-rerun1/data/joint/train.eng-gvn.jsonl",
    "validation_file": "/workspace/v24.3-joint-lexeme-dose29-rerun1/data/joint/validation.eng-gvn.jsonl",
    "test_file": null,
    "file_sha256": {
      "train": "9f99ea3c4f2a10b1dac8e4439bc8418c5589fa0dbbb21b79c994980d479b39d0",
      "validation": "52aaf4768554b97c3b9a664858ccc5683d255cc03de5569d9f559cd6fc8587a1",
      "test": null
    },
    "split_rows": {
      "train": 115136,
      "validation": 128
    },
    "token_inventory": {
      "train": {
        "examples": 115136,
        "source_tokens": 1268518,
        "target_tokens": 1122677,
        "non_padding_tokens": 2391195,
        "counts_are_post_truncation": true,
        "by_task": {
          "dictionary_lexeme": {
            "examples": 78996,
            "source_tokens": 441902,
            "target_tokens": 384569,
            "non_padding_tokens": 826471
          },
          "synthetic_academic_parallel": {
            "examples": 33284,
            "source_tokens": 713552,
            "target_tokens": 704692,
            "non_padding_tokens": 1418244
          },
          "usage_example": {
            "examples": 2856,
            "source_tokens": 113064,
            "target_tokens": 33416,
            "non_padding_tokens": 146480
          }
        }
      },
      "validation": {
        "examples": 128,
        "source_tokens": 1740,
        "target_tokens": 1682,
        "non_padding_tokens": 3422,
        "counts_are_post_truncation": true,
        "by_task": {
          "dictionary_lexeme": {
            "examples": 64,
            "source_tokens": 357,
            "target_tokens": 312,
            "non_padding_tokens": 669
          },
          "synthetic_academic_parallel": {
            "examples": 64,
            "source_tokens": 1383,
            "target_tokens": 1370,
            "non_padding_tokens": 2753
          }
        }
      }
    },
    "max_train_samples": null,
    "max_validation_samples": null,
    "max_test_samples": null,
    "shuffle_before_cap": false
  },
  "training_args": {
    "epochs": 999.0,
    "max_steps": 3598,
    "batch_size": 32,
    "gradient_accumulation_steps": 1,
    "learning_rate": 0.0002,
    "lora_r": 32,
    "lora_alpha": 64,
    "lora_dropout": 0.0,
    "lora_target_modules": [
      "q_proj",
      "k_proj",
      "v_proj",
      "out_proj",
      "fc1",
      "fc2"
    ],
    "modules_to_save": [],
    "additional_special_tokens": [
      "<lexeme>"
    ],
    "trainable_tokens": [
      {
        "token": "<lexeme>",
        "token_id": 256205
      }
    ],
    "seed": 17,
    "ensure_weight_tying": true,
    "effective_ensure_weight_tying": true,
    "generation_num_beams": 1,
    "generation_no_repeat_ngram_size": 0,
    "generation_repetition_penalty": 1.0,
    "generation_length_penalty": 1.0,
    "save_total_limit": 4,
    "gradient_checkpointing": false,
    "full_determinism": true,
    "resume_from_checkpoint": null,
    "stop_after_steps": null,
    "load_best_model_at_end": false
  },
  "metrics": {
    "train": {
      "train_runtime": 3863.3048,
      "train_samples_per_second": 29.802,
      "train_steps_per_second": 0.931,
      "total_flos": 4.295975851661722e+16,
      "train_loss": 0.9481710318130145,
      "epoch": 1.0
    },
    "validation": {
      "eval_loss": 0.6718003749847412,
      "eval_bleu": 40.86405804072553,
      "eval_chrf": 68.7685241355621,
      "eval_runtime": 42.4036,
      "eval_samples_per_second": 3.019,
      "eval_steps_per_second": 0.094,
      "epoch": 1.0
    }
  },
  "trainer_state": {
    "best_model_checkpoint": "/workspace/v24.3-joint-lexeme-dose29-rerun1/models/J69/checkpoint-2700",
    "best_metric": 66.61229334586629,
    "global_step": 3598,
    "epoch": 1.0,
    "log_history": [
      {
        "loss": 2.1046,
        "grad_norm": 0.4140295088291168,
        "learning_rate": 1.1111111111111112e-05,
        "epoch": 0.0027793218454697055,
        "step": 10
      },
      {
        "loss": 1.8483,
        "grad_norm": 0.46193182468414307,
        "learning_rate": 2.2222222222222223e-05,
        "epoch": 0.005558643690939411,
        "step": 20
      },
      {
        "loss": 1.9831,
        "grad_norm": 0.30134496092796326,
        "learning_rate": 3.3333333333333335e-05,
        "epoch": 0.008337965536409116,
        "step": 30
      },
      {
        "loss": 1.9877,
        "grad_norm": 0.28117668628692627,
        "learning_rate": 4.4444444444444447e-05,
        "epoch": 0.011117287381878822,
        "step": 40
      },
      {
        "loss": 1.9154,
        "grad_norm": 0.31306493282318115,
        "learning_rate": 5.555555555555556e-05,
        "epoch": 0.013896609227348526,
        "step": 50
      },
      {
        "loss": 1.9655,
        "grad_norm": 0.370194673538208,
        "learning_rate": 6.666666666666667e-05,
        "epoch": 0.016675931072818232,
        "step": 60
      },
      {
        "loss": 1.9722,
        "grad_norm": 0.45251625776290894,
        "learning_rate": 7.777777777777778e-05,
        "epoch": 0.019455252918287938,
        "step": 70
      },
      {
        "loss": 1.7918,
        "grad_norm": 0.4766435921192169,
        "learning_rate": 8.888888888888889e-05,
        "epoch": 0.022234574763757644,
        "step": 80
      },
      {
        "loss": 1.881,
        "grad_norm": 0.5220038294792175,
        "learning_rate": 0.0001,
        "epoch": 0.02501389660922735,
        "step": 90
      },
      {
        "loss": 1.8093,
        "grad_norm": 0.37182119488716125,
        "learning_rate": 0.00011111111111111112,
        "epoch": 0.027793218454697052,
        "step": 100
      },
      {
        "loss": 1.8168,
        "grad_norm": 0.528815507888794,
        "learning_rate": 0.00012222222222222224,
        "epoch": 0.030572540300166758,
        "step": 110
      },
      {
        "loss": 1.7512,
        "grad_norm": 0.5603467226028442,
        "learning_rate": 0.00013333333333333334,
        "epoch": 0.033351862145636464,
        "step": 120
      },
      {
        "loss": 1.8719,
        "grad_norm": 0.41087475419044495,
        "learning_rate": 0.00014444444444444444,
        "epoch": 0.03613118399110617,
        "step": 130
      },
      {
        "loss": 1.8271,
        "grad_norm": 0.5450639128684998,
        "learning_rate": 0.00015555555555555556,
        "epoch": 0.038910505836575876,
        "step": 140
      },
      {
        "loss": 1.9108,
        "grad_norm": 0.7078911066055298,
        "learning_rate": 0.0001666666666666667,
        "epoch": 0.04168982768204558,
        "step": 150
      },
      {
        "loss": 1.7895,
        "grad_norm": 0.5440416932106018,
        "learning_rate": 0.00017777777777777779,
        "epoch": 0.04446914952751529,
        "step": 160
      },
      {
        "loss": 1.8499,
        "grad_norm": 0.6741238236427307,
        "learning_rate": 0.00018888888888888888,
        "epoch": 0.04724847137298499,
        "step": 170
      },
      {
        "loss": 1.745,
        "grad_norm": 0.6223885416984558,
        "learning_rate": 0.0002,
        "epoch": 0.0500277932184547,
        "step": 180
      },
      {
        "loss": 1.637,
        "grad_norm": 0.654057502746582,
        "learning_rate": 0.0001994148624926858,
        "epoch": 0.0528071150639244,
        "step": 190
      },
      {
        "loss": 1.802,
        "grad_norm": 0.47887322306632996,
        "learning_rate": 0.00019882972498537157,
        "epoch": 0.055586436909394105,
        "step": 200
      },
      {
        "loss": 1.8009,
        "grad_norm": 0.783930778503418,
        "learning_rate": 0.00019824458747805734,
        "epoch": 0.058365758754863814,
        "step": 210
      },
      {
        "loss": 1.847,
        "grad_norm": 0.9810641407966614,
        "learning_rate": 0.00019765944997074313,
        "epoch": 0.061145080600333516,
        "step": 220
      },
      {
        "loss": 1.7683,
        "grad_norm": 0.6390312910079956,
        "learning_rate": 0.0001970743124634289,
        "epoch": 0.06392440244580322,
        "step": 230
      },
      {
        "loss": 1.5858,
        "grad_norm": 0.7976217865943909,
        "learning_rate": 0.0001964891749561147,
        "epoch": 0.06670372429127293,
        "step": 240
      },
      {
        "loss": 1.6725,
        "grad_norm": 0.9233970046043396,
        "learning_rate": 0.0001959040374488005,
        "epoch": 0.06948304613674264,
        "step": 250
      },
      {
        "loss": 1.5629,
        "grad_norm": 0.9889336228370667,
        "learning_rate": 0.00019531889994148626,
        "epoch": 0.07226236798221233,
        "step": 260
      },
      {
        "loss": 1.6842,
        "grad_norm": 0.8263123035430908,
        "learning_rate": 0.00019473376243417202,
        "epoch": 0.07504168982768204,
        "step": 270
      },
      {
        "loss": 1.6994,
        "grad_norm": 0.7401031851768494,
        "learning_rate": 0.00019414862492685782,
        "epoch": 0.07782101167315175,
        "step": 280
      },
      {
        "loss": 1.6662,
        "grad_norm": 0.6099547147750854,
        "learning_rate": 0.00019356348741954359,
        "epoch": 0.08060033351862146,
        "step": 290
      },
      {
        "loss": 1.7344,
        "grad_norm": 0.9664725065231323,
        "learning_rate": 0.00019297834991222938,
        "epoch": 0.08337965536409116,
        "step": 300
      },
      {
        "loss": 1.5765,
        "grad_norm": 1.102137565612793,
        "learning_rate": 0.00019239321240491518,
        "epoch": 0.08615897720956087,
        "step": 310
      },
      {
        "loss": 1.6127,
        "grad_norm": 0.8319466710090637,
        "learning_rate": 0.00019180807489760094,
        "epoch": 0.08893829905503058,
        "step": 320
      },
      {
        "loss": 1.6298,
        "grad_norm": 0.8705776333808899,
        "learning_rate": 0.0001912229373902867,
        "epoch": 0.09171762090050027,
        "step": 330
      },
      {
        "loss": 1.625,
        "grad_norm": 0.6215114593505859,
        "learning_rate": 0.0001906377998829725,
        "epoch": 0.09449694274596998,
        "step": 340
      },
      {
        "loss": 1.6475,
        "grad_norm": 0.9244978427886963,
        "learning_rate": 0.0001900526623756583,
        "epoch": 0.09727626459143969,
        "step": 350
      },
      {
        "loss": 1.6164,
        "grad_norm": 1.0081429481506348,
        "learning_rate": 0.00018946752486834407,
        "epoch": 0.1000555864369094,
        "step": 360
      },
      {
        "loss": 1.5784,
        "grad_norm": 0.9833176732063293,
        "learning_rate": 0.00018888238736102986,
        "epoch": 0.1028349082823791,
        "step": 370
      },
      {
        "loss": 1.4971,
        "grad_norm": 1.0448380708694458,
        "learning_rate": 0.00018829724985371563,
        "epoch": 0.1056142301278488,
        "step": 380
      },
      {
        "loss": 1.5317,
        "grad_norm": 0.963756799697876,
        "learning_rate": 0.0001877121123464014,
        "epoch": 0.10839355197331851,
        "step": 390
      },
      {
        "loss": 1.6251,
        "grad_norm": 0.7907305955886841,
        "learning_rate": 0.0001871269748390872,
        "epoch": 0.11117287381878821,
        "step": 400
      },
      {
        "loss": 1.4419,
        "grad_norm": 1.3546243906021118,
        "learning_rate": 0.00018654183733177298,
        "epoch": 0.11395219566425792,
        "step": 410
      },
      {
        "loss": 1.5571,
        "grad_norm": 0.9288954138755798,
        "learning_rate": 0.00018595669982445875,
        "epoch": 0.11673151750972763,
        "step": 420
      },
      {
        "loss": 1.5006,
        "grad_norm": 1.1262363195419312,
        "learning_rate": 0.00018537156231714455,
        "epoch": 0.11951083935519734,
        "step": 430
      },
      {
        "loss": 1.5663,
        "grad_norm": 0.9970844984054565,
        "learning_rate": 0.00018478642480983034,
        "epoch": 0.12229016120066703,
        "step": 440
      },
      {
        "loss": 1.458,
        "grad_norm": 1.299085259437561,
        "learning_rate": 0.00018420128730251608,
        "epoch": 0.12506948304613674,
        "step": 450
      },
      {
        "loss": 1.5316,
        "grad_norm": 0.9666916131973267,
        "learning_rate": 0.00018361614979520188,
        "epoch": 0.12784880489160644,
        "step": 460
      },
      {
        "loss": 1.4571,
        "grad_norm": 0.9775465726852417,
        "learning_rate": 0.00018303101228788767,
        "epoch": 0.13062812673707616,
        "step": 470
      },
      {
        "loss": 1.6143,
        "grad_norm": 1.0702718496322632,
        "learning_rate": 0.00018244587478057344,
        "epoch": 0.13340744858254586,
        "step": 480
      },
      {
        "loss": 1.4133,
        "grad_norm": 1.0198723077774048,
        "learning_rate": 0.00018186073727325923,
        "epoch": 0.13618677042801555,
        "step": 490
      },
      {
        "loss": 1.4449,
        "grad_norm": 1.1751333475112915,
        "learning_rate": 0.00018127559976594503,
        "epoch": 0.13896609227348528,
        "step": 500
      },
      {
        "loss": 1.58,
        "grad_norm": 1.124013900756836,
        "learning_rate": 0.00018069046225863077,
        "epoch": 0.14174541411895497,
        "step": 510
      },
      {
        "loss": 1.4243,
        "grad_norm": 1.1146219968795776,
        "learning_rate": 0.00018010532475131656,
        "epoch": 0.14452473596442467,
        "step": 520
      },
      {
        "loss": 1.3418,
        "grad_norm": 0.9221692085266113,
        "learning_rate": 0.00017952018724400236,
        "epoch": 0.1473040578098944,
        "step": 530
      },
      {
        "loss": 1.3914,
        "grad_norm": 1.2927697896957397,
        "learning_rate": 0.00017893504973668812,
        "epoch": 0.15008337965536409,
        "step": 540
      },
      {
        "loss": 1.4291,
        "grad_norm": 1.2189618349075317,
        "learning_rate": 0.00017834991222937392,
        "epoch": 0.1528627015008338,
        "step": 550
      },
      {
        "loss": 1.3442,
        "grad_norm": 1.2801870107650757,
        "learning_rate": 0.0001777647747220597,
        "epoch": 0.1556420233463035,
        "step": 560
      },
      {
        "loss": 1.313,
        "grad_norm": 1.3508485555648804,
        "learning_rate": 0.00017717963721474545,
        "epoch": 0.1584213451917732,
        "step": 570
      },
      {
        "loss": 1.4554,
        "grad_norm": 0.9896947145462036,
        "learning_rate": 0.00017659449970743125,
        "epoch": 0.16120066703724292,
        "step": 580
      },
      {
        "loss": 1.3431,
        "grad_norm": 0.8964052796363831,
        "learning_rate": 0.00017600936220011704,
        "epoch": 0.16397998888271262,
        "step": 590
      },
      {
        "loss": 1.4533,
        "grad_norm": 1.3584518432617188,
        "learning_rate": 0.0001754242246928028,
        "epoch": 0.16675931072818231,
        "step": 600
      },
      {
        "loss": 1.3523,
        "grad_norm": 1.092515468597412,
        "learning_rate": 0.0001748390871854886,
        "epoch": 0.16953863257365204,
        "step": 610
      },
      {
        "loss": 1.3369,
        "grad_norm": 1.2471967935562134,
        "learning_rate": 0.0001742539496781744,
        "epoch": 0.17231795441912173,
        "step": 620
      },
      {
        "loss": 1.3657,
        "grad_norm": 1.297553539276123,
        "learning_rate": 0.00017366881217086014,
        "epoch": 0.17509727626459143,
        "step": 630
      },
      {
        "loss": 1.2446,
        "grad_norm": 1.4945882558822632,
        "learning_rate": 0.00017308367466354593,
        "epoch": 0.17787659811006115,
        "step": 640
      },
      {
        "loss": 1.3642,
        "grad_norm": 1.7191970348358154,
        "learning_rate": 0.00017249853715623173,
        "epoch": 0.18065591995553085,
        "step": 650
      },
      {
        "loss": 1.2716,
        "grad_norm": 1.278106451034546,
        "learning_rate": 0.0001719133996489175,
        "epoch": 0.18343524180100054,
        "step": 660
      },
      {
        "loss": 1.2181,
        "grad_norm": 1.4567068815231323,
        "learning_rate": 0.0001713282621416033,
        "epoch": 0.18621456364647027,
        "step": 670
      },
      {
        "loss": 1.1919,
        "grad_norm": 1.1871955394744873,
        "learning_rate": 0.00017074312463428908,
        "epoch": 0.18899388549193996,
        "step": 680
      },
      {
        "loss": 1.3186,
        "grad_norm": 1.064318060874939,
        "learning_rate": 0.00017015798712697485,
        "epoch": 0.19177320733740968,
        "step": 690
      },
      {
        "loss": 1.2643,
        "grad_norm": 1.5443544387817383,
        "learning_rate": 0.00016957284961966062,
        "epoch": 0.19455252918287938,
        "step": 700
      },
      {
        "loss": 1.2199,
        "grad_norm": 1.0379834175109863,
        "learning_rate": 0.0001689877121123464,
        "epoch": 0.19733185102834908,
        "step": 710
      },
      {
        "loss": 1.2775,
        "grad_norm": 1.4339805841445923,
        "learning_rate": 0.00016840257460503218,
        "epoch": 0.2001111728738188,
        "step": 720
      },
      {
        "loss": 1.2689,
        "grad_norm": 1.7690389156341553,
        "learning_rate": 0.00016781743709771797,
        "epoch": 0.2028904947192885,
        "step": 730
      },
      {
        "loss": 1.1829,
        "grad_norm": 1.3799852132797241,
        "learning_rate": 0.00016723229959040377,
        "epoch": 0.2056698165647582,
        "step": 740
      },
      {
        "loss": 1.2952,
        "grad_norm": 1.0880959033966064,
        "learning_rate": 0.00016664716208308954,
        "epoch": 0.2084491384102279,
        "step": 750
      },
      {
        "loss": 1.1756,
        "grad_norm": 0.9457182884216309,
        "learning_rate": 0.0001660620245757753,
        "epoch": 0.2112284602556976,
        "step": 760
      },
      {
        "loss": 1.2704,
        "grad_norm": 1.383113145828247,
        "learning_rate": 0.0001654768870684611,
        "epoch": 0.2140077821011673,
        "step": 770
      },
      {
        "loss": 1.294,
        "grad_norm": 1.0459240674972534,
        "learning_rate": 0.0001648917495611469,
        "epoch": 0.21678710394663703,
        "step": 780
      },
      {
        "loss": 1.2052,
        "grad_norm": 1.2870111465454102,
        "learning_rate": 0.00016430661205383266,
        "epoch": 0.21956642579210672,
        "step": 790
      },
      {
        "loss": 1.2649,
        "grad_norm": 1.4526729583740234,
        "learning_rate": 0.00016372147454651845,
        "epoch": 0.22234574763757642,
        "step": 800
      },
      {
        "loss": 1.0921,
        "grad_norm": 1.846928358078003,
        "learning_rate": 0.00016313633703920422,
        "epoch": 0.22512506948304614,
        "step": 810
      },
      {
        "loss": 1.2423,
        "grad_norm": 1.5239036083221436,
        "learning_rate": 0.00016255119953189,
        "epoch": 0.22790439132851584,
        "step": 820
      },
      {
        "loss": 1.1756,
        "grad_norm": 1.3172131776809692,
        "learning_rate": 0.00016196606202457578,
        "epoch": 0.23068371317398556,
        "step": 830
      },
      {
        "loss": 1.1734,
        "grad_norm": 1.5167595148086548,
        "learning_rate": 0.00016138092451726158,
        "epoch": 0.23346303501945526,
        "step": 840
      },
      {
        "loss": 1.2039,
        "grad_norm": 1.349012851715088,
        "learning_rate": 0.00016079578700994735,
        "epoch": 0.23624235686492495,
        "step": 850
      },
      {
        "loss": 1.1005,
        "grad_norm": 1.1730643510818481,
        "learning_rate": 0.00016021064950263314,
        "epoch": 0.23902167871039467,
        "step": 860
      },
      {
        "loss": 1.1946,
        "grad_norm": 1.320278286933899,
        "learning_rate": 0.0001596255119953189,
        "epoch": 0.24180100055586437,
        "step": 870
      },
      {
        "loss": 1.09,
        "grad_norm": 0.9002246260643005,
        "learning_rate": 0.00015904037448800467,
        "epoch": 0.24458032240133407,
        "step": 880
      },
      {
        "loss": 1.0499,
        "grad_norm": 1.1015177965164185,
        "learning_rate": 0.00015845523698069047,
        "epoch": 0.2473596442468038,
        "step": 890
      },
      {
        "loss": 1.1817,
        "grad_norm": 1.7522237300872803,
        "learning_rate": 0.00015787009947337626,
        "epoch": 0.2501389660922735,
        "step": 900
      },
      {
        "eval_loss": 1.0395417213439941,
        "eval_bleu": 31.364990029729668,
        "eval_chrf": 58.3898577852921,
        "eval_runtime": 42.676,
        "eval_samples_per_second": 2.999,
        "eval_steps_per_second": 0.094,
        "epoch": 0.2501389660922735,
        "step": 900
      },
      {
        "loss": 1.1484,
        "grad_norm": 1.428255558013916,
        "learning_rate": 0.00015728496196606203,
        "epoch": 0.2529182879377432,
        "step": 910
      },
      {
        "loss": 1.0764,
        "grad_norm": 1.135252594947815,
        "learning_rate": 0.00015669982445874783,
        "epoch": 0.2556976097832129,
        "step": 920
      },
      {
        "loss": 1.2365,
        "grad_norm": 1.3112901449203491,
        "learning_rate": 0.0001561146869514336,
        "epoch": 0.2584769316286826,
        "step": 930
      },
      {
        "loss": 1.1562,
        "grad_norm": 1.7242013216018677,
        "learning_rate": 0.00015552954944411936,
        "epoch": 0.2612562534741523,
        "step": 940
      },
      {
        "loss": 1.1331,
        "grad_norm": 1.1144850254058838,
        "learning_rate": 0.00015494441193680515,
        "epoch": 0.264035575319622,
        "step": 950
      },
      {
        "loss": 1.1032,
        "grad_norm": 1.4144283533096313,
        "learning_rate": 0.00015435927442949095,
        "epoch": 0.2668148971650917,
        "step": 960
      },
      {
        "loss": 1.1417,
        "grad_norm": 1.3410099744796753,
        "learning_rate": 0.00015377413692217672,
        "epoch": 0.2695942190105614,
        "step": 970
      },
      {
        "loss": 1.1226,
        "grad_norm": 1.7101255655288696,
        "learning_rate": 0.0001531889994148625,
        "epoch": 0.2723735408560311,
        "step": 980
      },
      {
        "loss": 1.0927,
        "grad_norm": 1.9083212614059448,
        "learning_rate": 0.00015260386190754828,
        "epoch": 0.27515286270150086,
        "step": 990
      },
      {
        "loss": 1.1131,
        "grad_norm": 1.3412920236587524,
        "learning_rate": 0.00015201872440023405,
        "epoch": 0.27793218454697055,
        "step": 1000
      },
      {
        "loss": 1.0512,
        "grad_norm": 1.5229618549346924,
        "learning_rate": 0.00015143358689291984,
        "epoch": 0.28071150639244025,
        "step": 1010
      },
      {
        "loss": 0.9792,
        "grad_norm": 1.5586941242218018,
        "learning_rate": 0.00015084844938560564,
        "epoch": 0.28349082823790994,
        "step": 1020
      },
      {
        "loss": 1.0279,
        "grad_norm": 1.6615018844604492,
        "learning_rate": 0.0001502633118782914,
        "epoch": 0.28627015008337964,
        "step": 1030
      },
      {
        "loss": 1.0815,
        "grad_norm": 1.12063729763031,
        "learning_rate": 0.0001496781743709772,
        "epoch": 0.28904947192884933,
        "step": 1040
      },
      {
        "loss": 1.0282,
        "grad_norm": 1.9666633605957031,
        "learning_rate": 0.00014909303686366296,
        "epoch": 0.2918287937743191,
        "step": 1050
      },
      {
        "loss": 0.9798,
        "grad_norm": 1.6202434301376343,
        "learning_rate": 0.00014850789935634876,
        "epoch": 0.2946081156197888,
        "step": 1060
      },
      {
        "loss": 1.0827,
        "grad_norm": 1.3234361410140991,
        "learning_rate": 0.00014792276184903453,
        "epoch": 0.2973874374652585,
        "step": 1070
      },
      {
        "loss": 0.957,
        "grad_norm": 1.2288326025009155,
        "learning_rate": 0.00014733762434172032,
        "epoch": 0.30016675931072817,
        "step": 1080
      },
      {
        "loss": 0.8825,
        "grad_norm": 1.2778434753417969,
        "learning_rate": 0.0001467524868344061,
        "epoch": 0.30294608115619787,
        "step": 1090
      },
      {
        "loss": 1.1411,
        "grad_norm": 1.1895047426223755,
        "learning_rate": 0.00014616734932709186,
        "epoch": 0.3057254030016676,
        "step": 1100
      },
      {
        "loss": 1.0162,
        "grad_norm": 1.9118584394454956,
        "learning_rate": 0.00014558221181977765,
        "epoch": 0.3085047248471373,
        "step": 1110
      },
      {
        "loss": 1.0447,
        "grad_norm": 1.5872502326965332,
        "learning_rate": 0.00014499707431246344,
        "epoch": 0.311284046692607,
        "step": 1120
      },
      {
        "loss": 1.0535,
        "grad_norm": 1.7727245092391968,
        "learning_rate": 0.0001444119368051492,
        "epoch": 0.3140633685380767,
        "step": 1130
      },
      {
        "loss": 1.0742,
        "grad_norm": 1.2673349380493164,
        "learning_rate": 0.000143826799297835,
        "epoch": 0.3168426903835464,
        "step": 1140
      },
      {
        "loss": 1.0535,
        "grad_norm": 1.6242469549179077,
        "learning_rate": 0.00014324166179052077,
        "epoch": 0.3196220122290161,
        "step": 1150
      },
      {
        "loss": 0.8432,
        "grad_norm": 1.7397310733795166,
        "learning_rate": 0.00014265652428320654,
        "epoch": 0.32240133407448585,
        "step": 1160
      },
      {
        "loss": 1.0957,
        "grad_norm": 1.0805168151855469,
        "learning_rate": 0.00014207138677589234,
        "epoch": 0.32518065591995554,
        "step": 1170
      },
      {
        "loss": 1.0128,
        "grad_norm": 1.5562666654586792,
        "learning_rate": 0.00014148624926857813,
        "epoch": 0.32795997776542524,
        "step": 1180
      },
      {
        "loss": 0.9449,
        "grad_norm": 1.4101382493972778,
        "learning_rate": 0.0001409011117612639,
        "epoch": 0.33073929961089493,
        "step": 1190
      },
      {
        "loss": 0.9858,
        "grad_norm": 1.4961520433425903,
        "learning_rate": 0.0001403159742539497,
        "epoch": 0.33351862145636463,
        "step": 1200
      },
      {
        "loss": 1.0111,
        "grad_norm": 1.5171849727630615,
        "learning_rate": 0.00013973083674663549,
        "epoch": 0.3362979433018344,
        "step": 1210
      },
      {
        "loss": 0.9343,
        "grad_norm": 1.8383678197860718,
        "learning_rate": 0.00013914569923932123,
        "epoch": 0.3390772651473041,
        "step": 1220
      },
      {
        "loss": 1.0233,
        "grad_norm": 1.9662550687789917,
        "learning_rate": 0.00013856056173200702,
        "epoch": 0.34185658699277377,
        "step": 1230
      },
      {
        "loss": 1.0285,
        "grad_norm": 1.3497370481491089,
        "learning_rate": 0.00013797542422469282,
        "epoch": 0.34463590883824347,
        "step": 1240
      },
      {
        "loss": 1.0515,
        "grad_norm": 1.725982904434204,
        "learning_rate": 0.00013739028671737858,
        "epoch": 0.34741523068371316,
        "step": 1250
      },
      {
        "loss": 1.0562,
        "grad_norm": 1.6530572175979614,
        "learning_rate": 0.00013680514921006438,
        "epoch": 0.35019455252918286,
        "step": 1260
      },
      {
        "loss": 0.9152,
        "grad_norm": 1.6330093145370483,
        "learning_rate": 0.00013622001170275017,
        "epoch": 0.3529738743746526,
        "step": 1270
      },
      {
        "loss": 0.9699,
        "grad_norm": 1.0460683107376099,
        "learning_rate": 0.0001356348741954359,
        "epoch": 0.3557531962201223,
        "step": 1280
      },
      {
        "loss": 0.9806,
        "grad_norm": 1.5580418109893799,
        "learning_rate": 0.0001350497366881217,
        "epoch": 0.358532518065592,
        "step": 1290
      },
      {
        "loss": 1.007,
        "grad_norm": 2.0592973232269287,
        "learning_rate": 0.0001344645991808075,
        "epoch": 0.3613118399110617,
        "step": 1300
      },
      {
        "loss": 0.9665,
        "grad_norm": 1.3635998964309692,
        "learning_rate": 0.00013387946167349327,
        "epoch": 0.3640911617565314,
        "step": 1310
      },
      {
        "loss": 1.1398,
        "grad_norm": 1.568021297454834,
        "learning_rate": 0.00013329432416617906,
        "epoch": 0.3668704836020011,
        "step": 1320
      },
      {
        "loss": 0.9148,
        "grad_norm": 2.066228151321411,
        "learning_rate": 0.00013270918665886486,
        "epoch": 0.36964980544747084,
        "step": 1330
      },
      {
        "loss": 0.9977,
        "grad_norm": 1.1922526359558105,
        "learning_rate": 0.0001321240491515506,
        "epoch": 0.37242912729294053,
        "step": 1340
      },
      {
        "loss": 0.8754,
        "grad_norm": 2.051551103591919,
        "learning_rate": 0.0001315389116442364,
        "epoch": 0.3752084491384102,
        "step": 1350
      },
      {
        "loss": 0.9025,
        "grad_norm": 1.1191948652267456,
        "learning_rate": 0.0001309537741369222,
        "epoch": 0.3779877709838799,
        "step": 1360
      },
      {
        "loss": 0.9634,
        "grad_norm": 1.243485927581787,
        "learning_rate": 0.00013036863662960795,
        "epoch": 0.3807670928293496,
        "step": 1370
      },
      {
        "loss": 0.8412,
        "grad_norm": 1.4225202798843384,
        "learning_rate": 0.00012978349912229375,
        "epoch": 0.38354641467481937,
        "step": 1380
      },
      {
        "loss": 1.0081,
        "grad_norm": 1.2499719858169556,
        "learning_rate": 0.00012919836161497954,
        "epoch": 0.38632573652028906,
        "step": 1390
      },
      {
        "loss": 0.9025,
        "grad_norm": 1.6100412607192993,
        "learning_rate": 0.0001286132241076653,
        "epoch": 0.38910505836575876,
        "step": 1400
      },
      {
        "loss": 0.8203,
        "grad_norm": 1.9911744594573975,
        "learning_rate": 0.00012802808660035108,
        "epoch": 0.39188438021122846,
        "step": 1410
      },
      {
        "loss": 0.8276,
        "grad_norm": 1.4758795499801636,
        "learning_rate": 0.00012744294909303687,
        "epoch": 0.39466370205669815,
        "step": 1420
      },
      {
        "loss": 1.0634,
        "grad_norm": 1.4166537523269653,
        "learning_rate": 0.00012685781158572264,
        "epoch": 0.39744302390216785,
        "step": 1430
      },
      {
        "loss": 0.866,
        "grad_norm": 1.478798508644104,
        "learning_rate": 0.00012627267407840843,
        "epoch": 0.4002223457476376,
        "step": 1440
      },
      {
        "loss": 0.8046,
        "grad_norm": 1.518876552581787,
        "learning_rate": 0.00012568753657109423,
        "epoch": 0.4030016675931073,
        "step": 1450
      },
      {
        "loss": 0.9057,
        "grad_norm": 1.5666396617889404,
        "learning_rate": 0.00012510239906378,
        "epoch": 0.405780989438577,
        "step": 1460
      },
      {
        "loss": 0.9224,
        "grad_norm": 1.593050241470337,
        "learning_rate": 0.00012451726155646576,
        "epoch": 0.4085603112840467,
        "step": 1470
      },
      {
        "loss": 0.8986,
        "grad_norm": 2.082044839859009,
        "learning_rate": 0.00012393212404915156,
        "epoch": 0.4113396331295164,
        "step": 1480
      },
      {
        "loss": 0.888,
        "grad_norm": 2.0891640186309814,
        "learning_rate": 0.00012334698654183735,
        "epoch": 0.41411895497498613,
        "step": 1490
      },
      {
        "loss": 0.8905,
        "grad_norm": 1.358191967010498,
        "learning_rate": 0.00012276184903452312,
        "epoch": 0.4168982768204558,
        "step": 1500
      },
      {
        "loss": 0.8238,
        "grad_norm": 1.4863574504852295,
        "learning_rate": 0.00012217671152720891,
        "epoch": 0.4196775986659255,
        "step": 1510
      },
      {
        "loss": 0.9423,
        "grad_norm": 1.2066727876663208,
        "learning_rate": 0.00012159157401989467,
        "epoch": 0.4224569205113952,
        "step": 1520
      },
      {
        "loss": 0.7907,
        "grad_norm": 1.4324455261230469,
        "learning_rate": 0.00012100643651258046,
        "epoch": 0.4252362423568649,
        "step": 1530
      },
      {
        "loss": 0.9682,
        "grad_norm": 1.3111741542816162,
        "learning_rate": 0.00012042129900526624,
        "epoch": 0.4280155642023346,
        "step": 1540
      },
      {
        "loss": 0.875,
        "grad_norm": 2.182124376296997,
        "learning_rate": 0.00011983616149795202,
        "epoch": 0.43079488604780436,
        "step": 1550
      },
      {
        "loss": 0.8221,
        "grad_norm": 1.8315985202789307,
        "learning_rate": 0.0001192510239906378,
        "epoch": 0.43357420789327406,
        "step": 1560
      },
      {
        "loss": 0.9896,
        "grad_norm": 1.3867039680480957,
        "learning_rate": 0.0001186658864833236,
        "epoch": 0.43635352973874375,
        "step": 1570
      },
      {
        "loss": 0.9384,
        "grad_norm": 1.614179253578186,
        "learning_rate": 0.00011808074897600935,
        "epoch": 0.43913285158421345,
        "step": 1580
      },
      {
        "loss": 0.7823,
        "grad_norm": 1.388555884361267,
        "learning_rate": 0.00011749561146869515,
        "epoch": 0.44191217342968314,
        "step": 1590
      },
      {
        "loss": 0.7731,
        "grad_norm": 1.1316096782684326,
        "learning_rate": 0.00011691047396138093,
        "epoch": 0.44469149527515284,
        "step": 1600
      },
      {
        "loss": 0.7917,
        "grad_norm": 1.9281110763549805,
        "learning_rate": 0.00011632533645406671,
        "epoch": 0.4474708171206226,
        "step": 1610
      },
      {
        "loss": 0.935,
        "grad_norm": 1.7171776294708252,
        "learning_rate": 0.0001157401989467525,
        "epoch": 0.4502501389660923,
        "step": 1620
      },
      {
        "loss": 0.9694,
        "grad_norm": 1.5820637941360474,
        "learning_rate": 0.00011515506143943829,
        "epoch": 0.453029460811562,
        "step": 1630
      },
      {
        "loss": 0.8795,
        "grad_norm": 1.323703646659851,
        "learning_rate": 0.00011456992393212404,
        "epoch": 0.4558087826570317,
        "step": 1640
      },
      {
        "loss": 0.7887,
        "grad_norm": 1.4957565069198608,
        "learning_rate": 0.00011398478642480983,
        "epoch": 0.45858810450250137,
        "step": 1650
      },
      {
        "loss": 0.8062,
        "grad_norm": 1.8945534229278564,
        "learning_rate": 0.00011339964891749561,
        "epoch": 0.4613674263479711,
        "step": 1660
      },
      {
        "loss": 0.714,
        "grad_norm": 1.5251452922821045,
        "learning_rate": 0.0001128145114101814,
        "epoch": 0.4641467481934408,
        "step": 1670
      },
      {
        "loss": 0.8684,
        "grad_norm": 1.431054711341858,
        "learning_rate": 0.00011222937390286719,
        "epoch": 0.4669260700389105,
        "step": 1680
      },
      {
        "loss": 0.824,
        "grad_norm": 1.121795654296875,
        "learning_rate": 0.00011164423639555297,
        "epoch": 0.4697053918843802,
        "step": 1690
      },
      {
        "loss": 0.7963,
        "grad_norm": 1.7896941900253296,
        "learning_rate": 0.00011105909888823874,
        "epoch": 0.4724847137298499,
        "step": 1700
      },
      {
        "loss": 0.7842,
        "grad_norm": 1.2749794721603394,
        "learning_rate": 0.00011047396138092452,
        "epoch": 0.4752640355753196,
        "step": 1710
      },
      {
        "loss": 0.7423,
        "grad_norm": 1.5560483932495117,
        "learning_rate": 0.0001098888238736103,
        "epoch": 0.47804335742078935,
        "step": 1720
      },
      {
        "loss": 0.9013,
        "grad_norm": 1.4849023818969727,
        "learning_rate": 0.00010930368636629608,
        "epoch": 0.48082267926625905,
        "step": 1730
      },
      {
        "loss": 0.8111,
        "grad_norm": 1.5528464317321777,
        "learning_rate": 0.00010871854885898188,
        "epoch": 0.48360200111172874,
        "step": 1740
      },
      {
        "loss": 0.8145,
        "grad_norm": 1.897931456565857,
        "learning_rate": 0.00010813341135166766,
        "epoch": 0.48638132295719844,
        "step": 1750
      },
      {
        "loss": 0.7912,
        "grad_norm": 1.4603521823883057,
        "learning_rate": 0.00010754827384435342,
        "epoch": 0.48916064480266813,
        "step": 1760
      },
      {
        "loss": 0.7772,
        "grad_norm": 1.7950726747512817,
        "learning_rate": 0.0001069631363370392,
        "epoch": 0.4919399666481378,
        "step": 1770
      },
      {
        "loss": 0.6913,
        "grad_norm": 1.4596202373504639,
        "learning_rate": 0.00010637799882972499,
        "epoch": 0.4947192884936076,
        "step": 1780
      },
      {
        "loss": 0.801,
        "grad_norm": 1.0710797309875488,
        "learning_rate": 0.00010579286132241078,
        "epoch": 0.4974986103390773,
        "step": 1790
      },
      {
        "loss": 0.7098,
        "grad_norm": 1.7335723638534546,
        "learning_rate": 0.00010520772381509656,
        "epoch": 0.500277932184547,
        "step": 1800
      },
      {
        "eval_loss": 0.7931228876113892,
        "eval_bleu": 34.04529754823484,
        "eval_chrf": 64.48607517273312,
        "eval_runtime": 42.7183,
        "eval_samples_per_second": 2.996,
        "eval_steps_per_second": 0.094,
        "epoch": 0.500277932184547,
        "step": 1800
      },
      {
        "loss": 0.9306,
        "grad_norm": 1.0163995027542114,
        "learning_rate": 0.00010462258630778234,
        "epoch": 0.5030572540300167,
        "step": 1810
      },
      {
        "loss": 0.8217,
        "grad_norm": 2.198115825653076,
        "learning_rate": 0.00010403744880046811,
        "epoch": 0.5058365758754864,
        "step": 1820
      },
      {
        "loss": 0.8926,
        "grad_norm": 1.5556522607803345,
        "learning_rate": 0.00010345231129315389,
        "epoch": 0.5086158977209561,
        "step": 1830
      },
      {
        "loss": 0.8042,
        "grad_norm": 1.499470591545105,
        "learning_rate": 0.00010286717378583967,
        "epoch": 0.5113952195664258,
        "step": 1840
      },
      {
        "loss": 0.7806,
        "grad_norm": 1.47234308719635,
        "learning_rate": 0.00010228203627852547,
        "epoch": 0.5141745414118954,
        "step": 1850
      },
      {
        "loss": 0.914,
        "grad_norm": 1.721991777420044,
        "learning_rate": 0.00010169689877121125,
        "epoch": 0.5169538632573653,
        "step": 1860
      },
      {
        "loss": 0.8043,
        "grad_norm": 1.593459963798523,
        "learning_rate": 0.00010111176126389703,
        "epoch": 0.519733185102835,
        "step": 1870
      },
      {
        "loss": 0.8101,
        "grad_norm": 1.5574313402175903,
        "learning_rate": 0.0001005266237565828,
        "epoch": 0.5225125069483046,
        "step": 1880
      },
      {
        "loss": 0.6948,
        "grad_norm": 1.370987892150879,
        "learning_rate": 9.994148624926858e-05,
        "epoch": 0.5252918287937743,
        "step": 1890
      },
      {
        "loss": 0.7938,
        "grad_norm": 1.3755780458450317,
        "learning_rate": 9.935634874195436e-05,
        "epoch": 0.528071150639244,
        "step": 1900
      },
      {
        "loss": 0.7416,
        "grad_norm": 1.7554758787155151,
        "learning_rate": 9.877121123464015e-05,
        "epoch": 0.5308504724847137,
        "step": 1910
      },
      {
        "loss": 0.8454,
        "grad_norm": 1.7844148874282837,
        "learning_rate": 9.818607372732592e-05,
        "epoch": 0.5336297943301834,
        "step": 1920
      },
      {
        "loss": 0.8501,
        "grad_norm": 1.3822129964828491,
        "learning_rate": 9.760093622001171e-05,
        "epoch": 0.5364091161756531,
        "step": 1930
      },
      {
        "loss": 0.7248,
        "grad_norm": 1.7859715223312378,
        "learning_rate": 9.70157987126975e-05,
        "epoch": 0.5391884380211228,
        "step": 1940
      },
      {
        "loss": 0.7495,
        "grad_norm": 1.0760029554367065,
        "learning_rate": 9.643066120538326e-05,
        "epoch": 0.5419677598665925,
        "step": 1950
      },
      {
        "loss": 0.9286,
        "grad_norm": 1.3241146802902222,
        "learning_rate": 9.584552369806906e-05,
        "epoch": 0.5447470817120622,
        "step": 1960
      },
      {
        "loss": 0.8068,
        "grad_norm": 1.3033974170684814,
        "learning_rate": 9.526038619075484e-05,
        "epoch": 0.547526403557532,
        "step": 1970
      },
      {
        "loss": 0.8309,
        "grad_norm": 1.403512954711914,
        "learning_rate": 9.46752486834406e-05,
        "epoch": 0.5503057254030017,
        "step": 1980
      },
      {
        "loss": 0.8311,
        "grad_norm": 1.3144944906234741,
        "learning_rate": 9.40901111761264e-05,
        "epoch": 0.5530850472484714,
        "step": 1990
      },
      {
        "loss": 0.6458,
        "grad_norm": 1.645932674407959,
        "learning_rate": 9.350497366881218e-05,
        "epoch": 0.5558643690939411,
        "step": 2000
      },
      {
        "loss": 0.6814,
        "grad_norm": 2.137310028076172,
        "learning_rate": 9.291983616149795e-05,
        "epoch": 0.5586436909394108,
        "step": 2010
      },
      {
        "loss": 0.6609,
        "grad_norm": 1.8444314002990723,
        "learning_rate": 9.233469865418374e-05,
        "epoch": 0.5614230127848805,
        "step": 2020
      },
      {
        "loss": 0.8411,
        "grad_norm": 1.7156598567962646,
        "learning_rate": 9.174956114686952e-05,
        "epoch": 0.5642023346303502,
        "step": 2030
      },
      {
        "loss": 0.7718,
        "grad_norm": 2.0496068000793457,
        "learning_rate": 9.116442363955529e-05,
        "epoch": 0.5669816564758199,
        "step": 2040
      },
      {
        "loss": 0.7309,
        "grad_norm": 1.2874308824539185,
        "learning_rate": 9.057928613224108e-05,
        "epoch": 0.5697609783212896,
        "step": 2050
      },
      {
        "loss": 0.755,
        "grad_norm": 1.6933300495147705,
        "learning_rate": 8.999414862492687e-05,
        "epoch": 0.5725403001667593,
        "step": 2060
      },
      {
        "loss": 0.6792,
        "grad_norm": 1.5075557231903076,
        "learning_rate": 8.940901111761265e-05,
        "epoch": 0.575319622012229,
        "step": 2070
      },
      {
        "loss": 0.717,
        "grad_norm": 1.6459001302719116,
        "learning_rate": 8.882387361029843e-05,
        "epoch": 0.5780989438576987,
        "step": 2080
      },
      {
        "loss": 0.7334,
        "grad_norm": 1.4591081142425537,
        "learning_rate": 8.823873610298421e-05,
        "epoch": 0.5808782657031685,
        "step": 2090
      },
      {
        "loss": 0.82,
        "grad_norm": 1.903427004814148,
        "learning_rate": 8.765359859566999e-05,
        "epoch": 0.5836575875486382,
        "step": 2100
      },
      {
        "loss": 0.7907,
        "grad_norm": 1.269168496131897,
        "learning_rate": 8.706846108835577e-05,
        "epoch": 0.5864369093941079,
        "step": 2110
      },
      {
        "loss": 0.5817,
        "grad_norm": 1.237375259399414,
        "learning_rate": 8.648332358104155e-05,
        "epoch": 0.5892162312395776,
        "step": 2120
      },
      {
        "loss": 0.7943,
        "grad_norm": 1.5938820838928223,
        "learning_rate": 8.589818607372733e-05,
        "epoch": 0.5919955530850473,
        "step": 2130
      },
      {
        "loss": 0.7878,
        "grad_norm": 1.3069621324539185,
        "learning_rate": 8.531304856641311e-05,
        "epoch": 0.594774874930517,
        "step": 2140
      },
      {
        "loss": 0.641,
        "grad_norm": 1.2887060642242432,
        "learning_rate": 8.47279110590989e-05,
        "epoch": 0.5975541967759866,
        "step": 2150
      },
      {
        "loss": 0.7156,
        "grad_norm": 1.7033811807632446,
        "learning_rate": 8.414277355178467e-05,
        "epoch": 0.6003335186214563,
        "step": 2160
      },
      {
        "loss": 0.6544,
        "grad_norm": 1.3568116426467896,
        "learning_rate": 8.355763604447046e-05,
        "epoch": 0.603112840466926,
        "step": 2170
      },
      {
        "loss": 0.6654,
        "grad_norm": 0.8526349663734436,
        "learning_rate": 8.297249853715624e-05,
        "epoch": 0.6058921623123957,
        "step": 2180
      },
      {
        "loss": 0.7027,
        "grad_norm": 2.007845878601074,
        "learning_rate": 8.238736102984202e-05,
        "epoch": 0.6086714841578654,
        "step": 2190
      },
      {
        "loss": 0.6089,
        "grad_norm": 1.4187250137329102,
        "learning_rate": 8.18022235225278e-05,
        "epoch": 0.6114508060033352,
        "step": 2200
      },
      {
        "loss": 0.6562,
        "grad_norm": 1.5305442810058594,
        "learning_rate": 8.121708601521358e-05,
        "epoch": 0.6142301278488049,
        "step": 2210
      },
      {
        "loss": 0.6893,
        "grad_norm": 1.2007344961166382,
        "learning_rate": 8.063194850789936e-05,
        "epoch": 0.6170094496942746,
        "step": 2220
      },
      {
        "loss": 0.7424,
        "grad_norm": 1.8552879095077515,
        "learning_rate": 8.004681100058514e-05,
        "epoch": 0.6197887715397443,
        "step": 2230
      },
      {
        "loss": 0.6859,
        "grad_norm": 1.5317975282669067,
        "learning_rate": 7.946167349327092e-05,
        "epoch": 0.622568093385214,
        "step": 2240
      },
      {
        "loss": 0.6576,
        "grad_norm": 2.109940528869629,
        "learning_rate": 7.88765359859567e-05,
        "epoch": 0.6253474152306837,
        "step": 2250
      },
      {
        "loss": 0.7508,
        "grad_norm": 1.2298418283462524,
        "learning_rate": 7.829139847864248e-05,
        "epoch": 0.6281267370761534,
        "step": 2260
      },
      {
        "loss": 0.6816,
        "grad_norm": 1.3538986444473267,
        "learning_rate": 7.770626097132827e-05,
        "epoch": 0.6309060589216231,
        "step": 2270
      },
      {
        "loss": 0.746,
        "grad_norm": 1.1908177137374878,
        "learning_rate": 7.712112346401405e-05,
        "epoch": 0.6336853807670928,
        "step": 2280
      },
      {
        "loss": 0.7993,
        "grad_norm": 1.1318070888519287,
        "learning_rate": 7.653598595669983e-05,
        "epoch": 0.6364647026125625,
        "step": 2290
      },
      {
        "loss": 0.8078,
        "grad_norm": 1.5441361665725708,
        "learning_rate": 7.595084844938561e-05,
        "epoch": 0.6392440244580322,
        "step": 2300
      },
      {
        "loss": 0.7411,
        "grad_norm": 1.4957458972930908,
        "learning_rate": 7.536571094207139e-05,
        "epoch": 0.642023346303502,
        "step": 2310
      },
      {
        "loss": 0.6281,
        "grad_norm": 1.059766411781311,
        "learning_rate": 7.478057343475717e-05,
        "epoch": 0.6448026681489717,
        "step": 2320
      },
      {
        "loss": 0.5841,
        "grad_norm": 1.3983445167541504,
        "learning_rate": 7.419543592744296e-05,
        "epoch": 0.6475819899944414,
        "step": 2330
      },
      {
        "loss": 0.7042,
        "grad_norm": 1.3938812017440796,
        "learning_rate": 7.361029842012873e-05,
        "epoch": 0.6503613118399111,
        "step": 2340
      },
      {
        "loss": 0.8477,
        "grad_norm": 1.8146742582321167,
        "learning_rate": 7.302516091281451e-05,
        "epoch": 0.6531406336853808,
        "step": 2350
      },
      {
        "loss": 0.7584,
        "grad_norm": 1.1325688362121582,
        "learning_rate": 7.244002340550031e-05,
        "epoch": 0.6559199555308505,
        "step": 2360
      },
      {
        "loss": 0.8167,
        "grad_norm": 1.1988415718078613,
        "learning_rate": 7.185488589818607e-05,
        "epoch": 0.6586992773763202,
        "step": 2370
      },
      {
        "loss": 0.7592,
        "grad_norm": 0.8537703156471252,
        "learning_rate": 7.126974839087186e-05,
        "epoch": 0.6614785992217899,
        "step": 2380
      },
      {
        "loss": 0.6157,
        "grad_norm": 1.336398959159851,
        "learning_rate": 7.068461088355765e-05,
        "epoch": 0.6642579210672596,
        "step": 2390
      },
      {
        "loss": 0.6364,
        "grad_norm": 1.6869962215423584,
        "learning_rate": 7.009947337624342e-05,
        "epoch": 0.6670372429127293,
        "step": 2400
      },
      {
        "loss": 0.7279,
        "grad_norm": 1.4955002069473267,
        "learning_rate": 6.95143358689292e-05,
        "epoch": 0.669816564758199,
        "step": 2410
      },
      {
        "loss": 0.7611,
        "grad_norm": 0.9639846682548523,
        "learning_rate": 6.892919836161499e-05,
        "epoch": 0.6725958866036688,
        "step": 2420
      },
      {
        "loss": 0.658,
        "grad_norm": 1.3936442136764526,
        "learning_rate": 6.834406085430076e-05,
        "epoch": 0.6753752084491385,
        "step": 2430
      },
      {
        "loss": 0.6369,
        "grad_norm": 1.0887020826339722,
        "learning_rate": 6.775892334698654e-05,
        "epoch": 0.6781545302946081,
        "step": 2440
      },
      {
        "loss": 0.6722,
        "grad_norm": 1.2021764516830444,
        "learning_rate": 6.717378583967232e-05,
        "epoch": 0.6809338521400778,
        "step": 2450
      },
      {
        "loss": 0.58,
        "grad_norm": 1.4362479448318481,
        "learning_rate": 6.65886483323581e-05,
        "epoch": 0.6837131739855475,
        "step": 2460
      },
      {
        "loss": 0.6546,
        "grad_norm": 1.6736342906951904,
        "learning_rate": 6.600351082504388e-05,
        "epoch": 0.6864924958310172,
        "step": 2470
      },
      {
        "loss": 0.6311,
        "grad_norm": 1.3882834911346436,
        "learning_rate": 6.541837331772966e-05,
        "epoch": 0.6892718176764869,
        "step": 2480
      },
      {
        "loss": 0.8076,
        "grad_norm": 1.1238460540771484,
        "learning_rate": 6.483323581041545e-05,
        "epoch": 0.6920511395219566,
        "step": 2490
      },
      {
        "loss": 0.725,
        "grad_norm": 1.5184351205825806,
        "learning_rate": 6.424809830310124e-05,
        "epoch": 0.6948304613674263,
        "step": 2500
      },
      {
        "loss": 0.6874,
        "grad_norm": 1.5520931482315063,
        "learning_rate": 6.366296079578701e-05,
        "epoch": 0.697609783212896,
        "step": 2510
      },
      {
        "loss": 0.6594,
        "grad_norm": 1.1347784996032715,
        "learning_rate": 6.307782328847279e-05,
        "epoch": 0.7003891050583657,
        "step": 2520
      },
      {
        "loss": 0.5981,
        "grad_norm": 1.0782485008239746,
        "learning_rate": 6.249268578115858e-05,
        "epoch": 0.7031684269038355,
        "step": 2530
      },
      {
        "loss": 0.7258,
        "grad_norm": 1.3466250896453857,
        "learning_rate": 6.190754827384435e-05,
        "epoch": 0.7059477487493052,
        "step": 2540
      },
      {
        "loss": 0.5458,
        "grad_norm": 1.4698735475540161,
        "learning_rate": 6.132241076653013e-05,
        "epoch": 0.7087270705947749,
        "step": 2550
      },
      {
        "loss": 0.6835,
        "grad_norm": 1.6065407991409302,
        "learning_rate": 6.073727325921592e-05,
        "epoch": 0.7115063924402446,
        "step": 2560
      },
      {
        "loss": 0.7253,
        "grad_norm": 0.9917827248573303,
        "learning_rate": 6.015213575190169e-05,
        "epoch": 0.7142857142857143,
        "step": 2570
      },
      {
        "loss": 0.7438,
        "grad_norm": 1.2688491344451904,
        "learning_rate": 5.956699824458748e-05,
        "epoch": 0.717065036131184,
        "step": 2580
      },
      {
        "loss": 0.5903,
        "grad_norm": 1.4485528469085693,
        "learning_rate": 5.898186073727326e-05,
        "epoch": 0.7198443579766537,
        "step": 2590
      },
      {
        "loss": 0.6934,
        "grad_norm": 1.8393375873565674,
        "learning_rate": 5.8396723229959036e-05,
        "epoch": 0.7226236798221234,
        "step": 2600
      },
      {
        "loss": 0.781,
        "grad_norm": 1.1079840660095215,
        "learning_rate": 5.7811585722644824e-05,
        "epoch": 0.7254030016675931,
        "step": 2610
      },
      {
        "loss": 0.6871,
        "grad_norm": 1.1297825574874878,
        "learning_rate": 5.722644821533061e-05,
        "epoch": 0.7281823235130628,
        "step": 2620
      },
      {
        "loss": 0.563,
        "grad_norm": 2.4137139320373535,
        "learning_rate": 5.664131070801638e-05,
        "epoch": 0.7309616453585325,
        "step": 2630
      },
      {
        "loss": 0.6087,
        "grad_norm": 1.1955472230911255,
        "learning_rate": 5.6056173200702166e-05,
        "epoch": 0.7337409672040022,
        "step": 2640
      },
      {
        "loss": 0.8348,
        "grad_norm": 1.0724763870239258,
        "learning_rate": 5.5471035693387954e-05,
        "epoch": 0.736520289049472,
        "step": 2650
      },
      {
        "loss": 0.5881,
        "grad_norm": 1.2351850271224976,
        "learning_rate": 5.488589818607373e-05,
        "epoch": 0.7392996108949417,
        "step": 2660
      },
      {
        "loss": 0.6355,
        "grad_norm": 1.2210818529129028,
        "learning_rate": 5.430076067875951e-05,
        "epoch": 0.7420789327404114,
        "step": 2670
      },
      {
        "loss": 0.6666,
        "grad_norm": 1.2278271913528442,
        "learning_rate": 5.37156231714453e-05,
        "epoch": 0.7448582545858811,
        "step": 2680
      },
      {
        "loss": 0.7498,
        "grad_norm": 1.3193840980529785,
        "learning_rate": 5.313048566413107e-05,
        "epoch": 0.7476375764313508,
        "step": 2690
      },
      {
        "loss": 0.6763,
        "grad_norm": 1.2186802625656128,
        "learning_rate": 5.254534815681685e-05,
        "epoch": 0.7504168982768205,
        "step": 2700
      },
      {
        "eval_loss": 0.7080053687095642,
        "eval_bleu": 36.834191198203946,
        "eval_chrf": 66.61229334586629,
        "eval_runtime": 41.8487,
        "eval_samples_per_second": 3.059,
        "eval_steps_per_second": 0.096,
        "epoch": 0.7504168982768205,
        "step": 2700
      },
      {
        "loss": 0.5665,
        "grad_norm": 1.5874916315078735,
        "learning_rate": 5.196021064950264e-05,
        "epoch": 0.7531962201222901,
        "step": 2710
      },
      {
        "loss": 0.6897,
        "grad_norm": 1.471414566040039,
        "learning_rate": 5.1375073142188414e-05,
        "epoch": 0.7559755419677598,
        "step": 2720
      },
      {
        "loss": 0.6559,
        "grad_norm": 0.9071055054664612,
        "learning_rate": 5.0789935634874195e-05,
        "epoch": 0.7587548638132295,
        "step": 2730
      },
      {
        "loss": 0.7094,
        "grad_norm": 1.334881067276001,
        "learning_rate": 5.020479812755998e-05,
        "epoch": 0.7615341856586992,
        "step": 2740
      },
      {
        "loss": 0.6073,
        "grad_norm": 1.105324149131775,
        "learning_rate": 4.9619660620245763e-05,
        "epoch": 0.7643135075041689,
        "step": 2750
      },
      {
        "loss": 0.5923,
        "grad_norm": 1.4565565586090088,
        "learning_rate": 4.903452311293154e-05,
        "epoch": 0.7670928293496387,
        "step": 2760
      },
      {
        "loss": 0.5876,
        "grad_norm": 1.5638223886489868,
        "learning_rate": 4.844938560561732e-05,
        "epoch": 0.7698721511951084,
        "step": 2770
      },
      {
        "loss": 0.5577,
        "grad_norm": 1.4914469718933105,
        "learning_rate": 4.7864248098303106e-05,
        "epoch": 0.7726514730405781,
        "step": 2780
      },
      {
        "loss": 0.6794,
        "grad_norm": 1.210353136062622,
        "learning_rate": 4.727911059098889e-05,
        "epoch": 0.7754307948860478,
        "step": 2790
      },
      {
        "loss": 0.6647,
        "grad_norm": 1.5976355075836182,
        "learning_rate": 4.669397308367466e-05,
        "epoch": 0.7782101167315175,
        "step": 2800
      },
      {
        "loss": 0.5793,
        "grad_norm": 1.2854108810424805,
        "learning_rate": 4.610883557636045e-05,
        "epoch": 0.7809894385769872,
        "step": 2810
      },
      {
        "loss": 0.7555,
        "grad_norm": 1.4772543907165527,
        "learning_rate": 4.552369806904623e-05,
        "epoch": 0.7837687604224569,
        "step": 2820
      },
      {
        "loss": 0.6369,
        "grad_norm": 1.509872317314148,
        "learning_rate": 4.4938560561732004e-05,
        "epoch": 0.7865480822679266,
        "step": 2830
      },
      {
        "loss": 0.669,
        "grad_norm": 2.4350647926330566,
        "learning_rate": 4.435342305441779e-05,
        "epoch": 0.7893274041133963,
        "step": 2840
      },
      {
        "loss": 0.6086,
        "grad_norm": 1.8682899475097656,
        "learning_rate": 4.376828554710357e-05,
        "epoch": 0.792106725958866,
        "step": 2850
      },
      {
        "loss": 0.5857,
        "grad_norm": 1.8308444023132324,
        "learning_rate": 4.3183148039789354e-05,
        "epoch": 0.7948860478043357,
        "step": 2860
      },
      {
        "loss": 0.6207,
        "grad_norm": 1.4512547254562378,
        "learning_rate": 4.2598010532475135e-05,
        "epoch": 0.7976653696498055,
        "step": 2870
      },
      {
        "loss": 0.5281,
        "grad_norm": 1.0981119871139526,
        "learning_rate": 4.2012873025160916e-05,
        "epoch": 0.8004446914952752,
        "step": 2880
      },
      {
        "loss": 0.6987,
        "grad_norm": 1.1227097511291504,
        "learning_rate": 4.1427735517846696e-05,
        "epoch": 0.8032240133407449,
        "step": 2890
      },
      {
        "loss": 0.6354,
        "grad_norm": 1.349419116973877,
        "learning_rate": 4.084259801053248e-05,
        "epoch": 0.8060033351862146,
        "step": 2900
      },
      {
        "loss": 0.6707,
        "grad_norm": 1.6693001985549927,
        "learning_rate": 4.025746050321826e-05,
        "epoch": 0.8087826570316843,
        "step": 2910
      },
      {
        "loss": 0.5555,
        "grad_norm": 1.5549803972244263,
        "learning_rate": 3.967232299590404e-05,
        "epoch": 0.811561978877154,
        "step": 2920
      },
      {
        "loss": 0.591,
        "grad_norm": 1.785648226737976,
        "learning_rate": 3.908718548858982e-05,
        "epoch": 0.8143413007226237,
        "step": 2930
      },
      {
        "loss": 0.5992,
        "grad_norm": 1.2887086868286133,
        "learning_rate": 3.85020479812756e-05,
        "epoch": 0.8171206225680934,
        "step": 2940
      },
      {
        "loss": 0.7092,
        "grad_norm": 1.1370317935943604,
        "learning_rate": 3.791691047396138e-05,
        "epoch": 0.8198999444135631,
        "step": 2950
      },
      {
        "loss": 0.6683,
        "grad_norm": 1.367082118988037,
        "learning_rate": 3.733177296664716e-05,
        "epoch": 0.8226792662590328,
        "step": 2960
      },
      {
        "loss": 0.5731,
        "grad_norm": 1.0612155199050903,
        "learning_rate": 3.6746635459332944e-05,
        "epoch": 0.8254585881045025,
        "step": 2970
      },
      {
        "loss": 0.6481,
        "grad_norm": 1.8601607084274292,
        "learning_rate": 3.6161497952018725e-05,
        "epoch": 0.8282379099499723,
        "step": 2980
      },
      {
        "loss": 0.5889,
        "grad_norm": 1.3319456577301025,
        "learning_rate": 3.557636044470451e-05,
        "epoch": 0.831017231795442,
        "step": 2990
      },
      {
        "loss": 0.6499,
        "grad_norm": 1.5521312952041626,
        "learning_rate": 3.499122293739029e-05,
        "epoch": 0.8337965536409117,
        "step": 3000
      },
      {
        "loss": 0.5202,
        "grad_norm": 1.5546648502349854,
        "learning_rate": 3.440608543007607e-05,
        "epoch": 0.8365758754863813,
        "step": 3010
      },
      {
        "loss": 0.5754,
        "grad_norm": 0.7544180154800415,
        "learning_rate": 3.3820947922761855e-05,
        "epoch": 0.839355197331851,
        "step": 3020
      },
      {
        "loss": 0.5376,
        "grad_norm": 1.0516163110733032,
        "learning_rate": 3.323581041544763e-05,
        "epoch": 0.8421345191773207,
        "step": 3030
      },
      {
        "loss": 0.7268,
        "grad_norm": 0.9787018299102783,
        "learning_rate": 3.265067290813341e-05,
        "epoch": 0.8449138410227904,
        "step": 3040
      },
      {
        "loss": 0.6491,
        "grad_norm": 1.4314815998077393,
        "learning_rate": 3.20655354008192e-05,
        "epoch": 0.8476931628682601,
        "step": 3050
      },
      {
        "loss": 0.6874,
        "grad_norm": 1.324827790260315,
        "learning_rate": 3.148039789350498e-05,
        "epoch": 0.8504724847137298,
        "step": 3060
      },
      {
        "loss": 0.6082,
        "grad_norm": 1.5152019262313843,
        "learning_rate": 3.089526038619075e-05,
        "epoch": 0.8532518065591995,
        "step": 3070
      },
      {
        "loss": 0.7667,
        "grad_norm": 1.2576498985290527,
        "learning_rate": 3.031012287887654e-05,
        "epoch": 0.8560311284046692,
        "step": 3080
      },
      {
        "loss": 0.4844,
        "grad_norm": 0.9412326812744141,
        "learning_rate": 2.972498537156232e-05,
        "epoch": 0.8588104502501389,
        "step": 3090
      },
      {
        "loss": 0.6217,
        "grad_norm": 1.187469244003296,
        "learning_rate": 2.91398478642481e-05,
        "epoch": 0.8615897720956087,
        "step": 3100
      },
      {
        "loss": 0.6016,
        "grad_norm": 1.1852264404296875,
        "learning_rate": 2.8554710356933877e-05,
        "epoch": 0.8643690939410784,
        "step": 3110
      },
      {
        "loss": 0.4414,
        "grad_norm": 1.1429516077041626,
        "learning_rate": 2.796957284961966e-05,
        "epoch": 0.8671484157865481,
        "step": 3120
      },
      {
        "loss": 0.517,
        "grad_norm": 1.570572853088379,
        "learning_rate": 2.7384435342305442e-05,
        "epoch": 0.8699277376320178,
        "step": 3130
      },
      {
        "loss": 0.6303,
        "grad_norm": 1.1809591054916382,
        "learning_rate": 2.6799297834991223e-05,
        "epoch": 0.8727070594774875,
        "step": 3140
      },
      {
        "loss": 0.631,
        "grad_norm": 1.0413581132888794,
        "learning_rate": 2.6214160327677007e-05,
        "epoch": 0.8754863813229572,
        "step": 3150
      },
      {
        "loss": 0.6164,
        "grad_norm": 1.1612534523010254,
        "learning_rate": 2.5629022820362785e-05,
        "epoch": 0.8782657031684269,
        "step": 3160
      },
      {
        "loss": 0.6026,
        "grad_norm": 1.1018447875976562,
        "learning_rate": 2.5043885313048566e-05,
        "epoch": 0.8810450250138966,
        "step": 3170
      },
      {
        "loss": 0.6073,
        "grad_norm": 1.2285889387130737,
        "learning_rate": 2.445874780573435e-05,
        "epoch": 0.8838243468593663,
        "step": 3180
      },
      {
        "loss": 0.6716,
        "grad_norm": 1.6262547969818115,
        "learning_rate": 2.3873610298420128e-05,
        "epoch": 0.886603668704836,
        "step": 3190
      },
      {
        "loss": 0.6884,
        "grad_norm": 1.1921401023864746,
        "learning_rate": 2.3288472791105912e-05,
        "epoch": 0.8893829905503057,
        "step": 3200
      },
      {
        "loss": 0.6217,
        "grad_norm": 1.3749579191207886,
        "learning_rate": 2.2703335283791693e-05,
        "epoch": 0.8921623123957755,
        "step": 3210
      },
      {
        "loss": 0.4955,
        "grad_norm": 0.9302161931991577,
        "learning_rate": 2.2118197776477474e-05,
        "epoch": 0.8949416342412452,
        "step": 3220
      },
      {
        "loss": 0.6861,
        "grad_norm": 1.1946569681167603,
        "learning_rate": 2.1533060269163255e-05,
        "epoch": 0.8977209560867149,
        "step": 3230
      },
      {
        "loss": 0.4447,
        "grad_norm": 1.4691694974899292,
        "learning_rate": 2.0947922761849036e-05,
        "epoch": 0.9005002779321846,
        "step": 3240
      },
      {
        "loss": 0.6073,
        "grad_norm": 1.4222508668899536,
        "learning_rate": 2.0362785254534817e-05,
        "epoch": 0.9032795997776543,
        "step": 3250
      },
      {
        "loss": 0.5341,
        "grad_norm": 1.5230867862701416,
        "learning_rate": 1.9777647747220598e-05,
        "epoch": 0.906058921623124,
        "step": 3260
      },
      {
        "loss": 0.5286,
        "grad_norm": 1.1844643354415894,
        "learning_rate": 1.919251023990638e-05,
        "epoch": 0.9088382434685937,
        "step": 3270
      },
      {
        "loss": 0.7289,
        "grad_norm": 1.1704039573669434,
        "learning_rate": 1.860737273259216e-05,
        "epoch": 0.9116175653140633,
        "step": 3280
      },
      {
        "loss": 0.7212,
        "grad_norm": 1.4930881261825562,
        "learning_rate": 1.802223522527794e-05,
        "epoch": 0.914396887159533,
        "step": 3290
      },
      {
        "loss": 0.5754,
        "grad_norm": 1.3442230224609375,
        "learning_rate": 1.743709771796372e-05,
        "epoch": 0.9171762090050027,
        "step": 3300
      },
      {
        "loss": 0.5899,
        "grad_norm": 1.3578684329986572,
        "learning_rate": 1.6851960210649502e-05,
        "epoch": 0.9199555308504724,
        "step": 3310
      },
      {
        "loss": 0.5864,
        "grad_norm": 1.2579971551895142,
        "learning_rate": 1.6266822703335287e-05,
        "epoch": 0.9227348526959422,
        "step": 3320
      },
      {
        "loss": 0.6355,
        "grad_norm": 1.314341425895691,
        "learning_rate": 1.5681685196021064e-05,
        "epoch": 0.9255141745414119,
        "step": 3330
      },
      {
        "loss": 0.601,
        "grad_norm": 1.0620858669281006,
        "learning_rate": 1.5096547688706847e-05,
        "epoch": 0.9282934963868816,
        "step": 3340
      },
      {
        "loss": 0.6049,
        "grad_norm": 1.2325353622436523,
        "learning_rate": 1.451141018139263e-05,
        "epoch": 0.9310728182323513,
        "step": 3350
      },
      {
        "loss": 0.5417,
        "grad_norm": 0.9464172124862671,
        "learning_rate": 1.3926272674078409e-05,
        "epoch": 0.933852140077821,
        "step": 3360
      },
      {
        "loss": 0.6688,
        "grad_norm": 1.453446865081787,
        "learning_rate": 1.334113516676419e-05,
        "epoch": 0.9366314619232907,
        "step": 3370
      },
      {
        "loss": 0.6055,
        "grad_norm": 1.1557977199554443,
        "learning_rate": 1.2755997659449972e-05,
        "epoch": 0.9394107837687604,
        "step": 3380
      },
      {
        "loss": 0.6085,
        "grad_norm": 1.08552885055542,
        "learning_rate": 1.2170860152135752e-05,
        "epoch": 0.9421901056142301,
        "step": 3390
      },
      {
        "loss": 0.5834,
        "grad_norm": 1.2602875232696533,
        "learning_rate": 1.1585722644821534e-05,
        "epoch": 0.9449694274596998,
        "step": 3400
      },
      {
        "loss": 0.5876,
        "grad_norm": 1.5725733041763306,
        "learning_rate": 1.1000585137507315e-05,
        "epoch": 0.9477487493051695,
        "step": 3410
      },
      {
        "loss": 0.5752,
        "grad_norm": 1.2837549448013306,
        "learning_rate": 1.0415447630193096e-05,
        "epoch": 0.9505280711506392,
        "step": 3420
      },
      {
        "loss": 0.5663,
        "grad_norm": 0.9232473373413086,
        "learning_rate": 9.830310122878877e-06,
        "epoch": 0.953307392996109,
        "step": 3430
      },
      {
        "loss": 0.5702,
        "grad_norm": 1.2556686401367188,
        "learning_rate": 9.245172615564658e-06,
        "epoch": 0.9560867148415787,
        "step": 3440
      },
      {
        "loss": 0.5578,
        "grad_norm": 1.138568639755249,
        "learning_rate": 8.660035108250439e-06,
        "epoch": 0.9588660366870484,
        "step": 3450
      },
      {
        "loss": 0.6894,
        "grad_norm": 1.1079130172729492,
        "learning_rate": 8.074897600936221e-06,
        "epoch": 0.9616453585325181,
        "step": 3460
      },
      {
        "loss": 0.6521,
        "grad_norm": 1.0000965595245361,
        "learning_rate": 7.4897600936220015e-06,
        "epoch": 0.9644246803779878,
        "step": 3470
      },
      {
        "loss": 0.7117,
        "grad_norm": 1.1308131217956543,
        "learning_rate": 6.9046225863077825e-06,
        "epoch": 0.9672040022234575,
        "step": 3480
      },
      {
        "loss": 0.5305,
        "grad_norm": 1.8153457641601562,
        "learning_rate": 6.319485078993564e-06,
        "epoch": 0.9699833240689272,
        "step": 3490
      },
      {
        "loss": 0.5736,
        "grad_norm": 1.1955033540725708,
        "learning_rate": 5.734347571679345e-06,
        "epoch": 0.9727626459143969,
        "step": 3500
      },
      {
        "loss": 0.6073,
        "grad_norm": 1.1305077075958252,
        "learning_rate": 5.149210064365126e-06,
        "epoch": 0.9755419677598666,
        "step": 3510
      },
      {
        "loss": 0.5432,
        "grad_norm": 1.875968098640442,
        "learning_rate": 4.564072557050907e-06,
        "epoch": 0.9783212896053363,
        "step": 3520
      },
      {
        "loss": 0.6327,
        "grad_norm": 1.0293177366256714,
        "learning_rate": 3.978935049736688e-06,
        "epoch": 0.981100611450806,
        "step": 3530
      },
      {
        "loss": 0.5867,
        "grad_norm": 1.6121056079864502,
        "learning_rate": 3.3937975424224693e-06,
        "epoch": 0.9838799332962757,
        "step": 3540
      },
      {
        "loss": 0.5826,
        "grad_norm": 1.166865348815918,
        "learning_rate": 2.8086600351082503e-06,
        "epoch": 0.9866592551417455,
        "step": 3550
      },
      {
        "loss": 0.6175,
        "grad_norm": 1.2993223667144775,
        "learning_rate": 2.223522527794032e-06,
        "epoch": 0.9894385769872152,
        "step": 3560
      },
      {
        "loss": 0.5528,
        "grad_norm": 1.318895936012268,
        "learning_rate": 1.638385020479813e-06,
        "epoch": 0.9922178988326849,
        "step": 3570
      },
      {
        "loss": 0.6268,
        "grad_norm": 1.0751056671142578,
        "learning_rate": 1.053247513165594e-06,
        "epoch": 0.9949972206781545,
        "step": 3580
      },
      {
        "loss": 0.6024,
        "grad_norm": 1.1337924003601074,
        "learning_rate": 4.681100058513751e-07,
        "epoch": 0.9977765425236242,
        "step": 3590
      },
      {
        "train_runtime": 3863.3048,
        "train_samples_per_second": 29.802,
        "train_steps_per_second": 0.931,
        "total_flos": 4.295975851661722e+16,
        "train_loss": 0.9481710318130145,
        "epoch": 1.0,
        "step": 3598
      },
      {
        "eval_loss": 0.6718003749847412,
        "eval_bleu": 40.86405804072553,
        "eval_chrf": 68.7685241355621,
        "eval_runtime": 42.4036,
        "eval_samples_per_second": 3.019,
        "eval_steps_per_second": 0.094,
        "epoch": 1.0,
        "step": 3598
      }
    ],
    "actual_training_exposure": {
      "examples": 115136,
      "source_tokens": 1268518,
      "target_tokens": 1122677,
      "non_padding_tokens": 2391195,
      "by_task": {
        "dictionary_lexeme": {
          "examples": 78996,
          "source_tokens": 441902,
          "target_tokens": 384569,
          "non_padding_tokens": 826471
        },
        "synthetic_academic_parallel": {
          "examples": 33284,
          "source_tokens": 713552,
          "target_tokens": 704692,
          "non_padding_tokens": 1418244
        },
        "usage_example": {
          "examples": 2856,
          "source_tokens": 113064,
          "target_tokens": 33416,
          "non_padding_tokens": 146480
        }
      },
      "unique_rows_seen": 115136,
      "presentations_per_seen_row": {
        "minimum": 1,
        "maximum": 1,
        "mean": 1.0
      },
      "accounting_scope": "current trainer process",
      "world_size": 1
    }
  },
  "artifacts": {
    "adapter_dir": "/workspace/v24.3-joint-lexeme-dose29-rerun1/models/J69/adapter",
    "merged_dir": null,
    "merge_embedding_canonicalization": null
  },
  "environment": {
    "python": "3.11.10",
    "platform": "Linux-5.15.0-139-generic-x86_64-with-glibc2.35",
    "torch": "2.4.1+cu124",
    "cuda_runtime": "12.4",
    "cuda_available": true,
    "gpu": "NVIDIA RTX A6000",
    "packages": {
      "accelerate": "1.14.0",
      "datasets": "4.8.5",
      "peft": "0.19.1",
      "sacrebleu": "2.6.0",
      "sentencepiece": "0.2.2",
      "transformers": "4.48.3"
    }
  }
}