🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.
⚙️  Running in WANDB offline mode
🦥 Unsloth Zoo will now patch everything to make training faster!
==((====))==  Unsloth 2026.9.2: Fast Olmo3 patching. Transformers: 4.57.6.
   \\   /|    NVIDIA H100 80GB HBM3. Num GPUs = 1. Max memory: 79.179 GB. Platform: Linux.
O^O/ \_/ \    Torch: 2.11.0+cu128. CUDA: 9.0. CUDA Toolkit: 12.8. Triton: 3.6.0
\        /    Bfloat16 = TRUE. FA [Xformers = 0.0.35. FA2 = False]
 "-____-"     Free license: http://github.com/unslothai/unsloth
Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!
Unsloth: Dropout = 0 is supported for fast patching. You are using dropout = 0.05.
Unsloth will patch all other layers, except LoRA matrices, causing a performance hit.
Unsloth: QLoRA and full finetuning all not selected. Switching to 16bit LoRA.
Unsloth: Explicit target_modules are constrained by the finetune_(vision|language|attention|mlp) filters; adapters attach only where both select.
Unsloth: Allowing gradients for `base_model.model.model.embed_tokens` since it's in `modules_to_save`.
Unsloth: Allowing gradients for `base_model.model.lm_head` since it's in `modules_to_save`.

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 890 examples [00:00, 5468.65 examples/s]
Generating train split: 1781 examples [00:00, 2788.42 examples/s]
Generating train split: 2643 examples [00:00, 3415.43 examples/s]
Generating train split: 3587 examples [00:00, 3927.11 examples/s]
Generating train split: 4465 examples [00:01, 3700.10 examples/s]
Generating train split: 5410 examples [00:01, 2948.05 examples/s]
Generating train split: 6313 examples [00:01, 3379.38 examples/s]
Generating train split: 7214 examples [00:02, 3718.26 examples/s]
Generating train split: 8108 examples [00:02, 3922.74 examples/s]
Generating train split: 9017 examples [00:02, 3133.25 examples/s]
Generating train split: 9904 examples [00:02, 3626.47 examples/s]
Generating train split: 10797 examples [00:03, 3880.34 examples/s]
Generating train split: 11743 examples [00:03, 3104.78 examples/s]
Generating train split: 12646 examples [00:03, 3448.01 examples/s]
Generating train split: 13586 examples [00:03, 3834.57 examples/s]
Generating train split: 14510 examples [00:03, 4188.79 examples/s]
Generating train split: 15424 examples [00:04, 3227.55 examples/s]
Generating train split: 16339 examples [00:04, 3691.02 examples/s]
Generating train split: 17261 examples [00:04, 4213.35 examples/s]
Generating train split: 18165 examples [00:05, 3230.61 examples/s]
Generating train split: 18500 examples [00:05, 3521.17 examples/s]

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 5000 examples [00:00, 9138.96 examples/s]
Generating train split: 5000 examples [00:00, 8881.48 examples/s]

tokenizing (num_proc=8):   0%|          | 0/23500 [00:00<?, ? examples/s]
tokenizing (num_proc=8):   0%|          | 11/23500 [00:00<22:29, 17.41 examples/s]
tokenizing (num_proc=8):   0%|          | 47/23500 [00:00<04:52, 80.18 examples/s]
tokenizing (num_proc=8):   1%|          | 119/23500 [00:00<01:50, 211.36 examples/s]
tokenizing (num_proc=8):   1%|          | 214/23500 [00:00<01:02, 371.91 examples/s]
tokenizing (num_proc=8):   1%|▏         | 345/23500 [00:01<00:40, 576.65 examples/s]
tokenizing (num_proc=8):   2%|▏         | 486/23500 [00:01<00:30, 761.37 examples/s]
tokenizing (num_proc=8):   3%|▎         | 672/23500 [00:01<00:22, 1033.41 examples/s]
tokenizing (num_proc=8):   4%|▎         | 857/23500 [00:01<00:18, 1219.97 examples/s]
tokenizing (num_proc=8):   4%|▍         | 1054/23500 [00:01<00:16, 1371.78 examples/s]
tokenizing (num_proc=8):   5%|▌         | 1245/23500 [00:01<00:14, 1499.85 examples/s]
tokenizing (num_proc=8):   6%|▌         | 1425/23500 [00:01<00:14, 1550.96 examples/s]
tokenizing (num_proc=8):   7%|▋         | 1598/23500 [00:01<00:14, 1539.14 examples/s]
tokenizing (num_proc=8):   7%|▋         | 1759/23500 [00:01<00:14, 1543.47 examples/s]
tokenizing (num_proc=8):   8%|▊         | 1924/23500 [00:02<00:13, 1561.32 examples/s]
tokenizing (num_proc=8):   9%|▉         | 2091/23500 [00:02<00:13, 1582.42 examples/s]
tokenizing (num_proc=8):  10%|▉         | 2271/23500 [00:02<00:13, 1625.24 examples/s]
tokenizing (num_proc=8):  10%|█         | 2440/23500 [00:02<00:13, 1601.33 examples/s]
tokenizing (num_proc=8):  11%|█         | 2612/23500 [00:02<00:12, 1628.42 examples/s]
tokenizing (num_proc=8):  12%|█▏        | 2801/23500 [00:02<00:12, 1693.63 examples/s]
tokenizing (num_proc=8):  13%|█▎        | 2981/23500 [00:02<00:12, 1709.50 examples/s]
tokenizing (num_proc=8):  14%|█▎        | 3190/23500 [00:02<00:11, 1777.74 examples/s]
tokenizing (num_proc=8):  14%|█▍        | 3378/23500 [00:02<00:11, 1780.60 examples/s]
tokenizing (num_proc=8):  15%|█▌        | 3568/23500 [00:02<00:11, 1750.73 examples/s]
tokenizing (num_proc=8):  16%|█▌        | 3747/23500 [00:03<00:11, 1732.89 examples/s]
tokenizing (num_proc=8):  17%|█▋        | 3931/23500 [00:03<00:11, 1692.09 examples/s]
tokenizing (num_proc=8):  17%|█▋        | 4107/23500 [00:03<00:12, 1574.12 examples/s]
tokenizing (num_proc=8):  18%|█▊        | 4290/23500 [00:03<00:11, 1626.18 examples/s]
tokenizing (num_proc=8):  19%|█▉        | 4479/23500 [00:03<00:11, 1671.49 examples/s]
tokenizing (num_proc=8):  20%|█▉        | 4662/23500 [00:03<00:11, 1680.68 examples/s]
tokenizing (num_proc=8):  21%|██        | 4840/23500 [00:03<00:11, 1689.00 examples/s]
tokenizing (num_proc=8):  21%|██▏       | 5017/23500 [00:03<00:11, 1666.62 examples/s]
tokenizing (num_proc=8):  22%|██▏       | 5195/23500 [00:03<00:11, 1632.22 examples/s]
tokenizing (num_proc=8):  23%|██▎       | 5368/23500 [00:04<00:10, 1658.51 examples/s]
tokenizing (num_proc=8):  24%|██▎       | 5568/23500 [00:04<00:10, 1730.88 examples/s]
tokenizing (num_proc=8):  24%|██▍       | 5753/23500 [00:04<00:10, 1698.03 examples/s]
tokenizing (num_proc=8):  25%|██▌       | 5954/23500 [00:04<00:09, 1771.83 examples/s]
tokenizing (num_proc=8):  26%|██▌       | 6135/23500 [00:04<00:10, 1709.47 examples/s]
tokenizing (num_proc=8):  27%|██▋       | 6338/23500 [00:04<00:09, 1768.67 examples/s]
tokenizing (num_proc=8):  28%|██▊       | 6524/23500 [00:04<00:09, 1778.29 examples/s]
tokenizing (num_proc=8):  29%|██▊       | 6711/23500 [00:04<00:09, 1733.44 examples/s]
tokenizing (num_proc=8):  29%|██▉       | 6886/23500 [00:04<00:09, 1687.27 examples/s]
tokenizing (num_proc=8):  30%|███       | 7060/23500 [00:05<00:10, 1642.34 examples/s]
tokenizing (num_proc=8):  31%|███       | 7230/23500 [00:05<00:10, 1510.69 examples/s]
tokenizing (num_proc=8):  31%|███▏      | 7390/23500 [00:05<00:11, 1414.67 examples/s]
tokenizing (num_proc=8):  32%|███▏      | 7534/23500 [00:05<00:11, 1400.21 examples/s]
tokenizing (num_proc=8):  33%|███▎      | 7677/23500 [00:05<00:11, 1379.71 examples/s]
tokenizing (num_proc=8):  33%|███▎      | 7830/23500 [00:05<00:11, 1316.67 examples/s]
tokenizing (num_proc=8):  34%|███▍      | 7975/23500 [00:05<00:13, 1180.57 examples/s]
tokenizing (num_proc=8):  34%|███▍      | 8103/23500 [00:06<00:18, 848.23 examples/s] 
tokenizing (num_proc=8):  35%|███▍      | 8207/23500 [00:06<00:21, 718.25 examples/s]
tokenizing (num_proc=8):  35%|███▌      | 8296/23500 [00:06<00:21, 697.79 examples/s]
tokenizing (num_proc=8):  36%|███▌      | 8382/23500 [00:06<00:21, 716.06 examples/s]
tokenizing (num_proc=8):  36%|███▌      | 8494/23500 [00:06<00:18, 804.26 examples/s]
tokenizing (num_proc=8):  37%|███▋      | 8620/23500 [00:06<00:16, 886.34 examples/s]
tokenizing (num_proc=8):  37%|███▋      | 8760/23500 [00:06<00:14, 1010.01 examples/s]
tokenizing (num_proc=8):  38%|███▊      | 8911/23500 [00:06<00:13, 1121.40 examples/s]
tokenizing (num_proc=8):  39%|███▊      | 9083/23500 [00:07<00:11, 1276.19 examples/s]
tokenizing (num_proc=8):  39%|███▉      | 9258/23500 [00:07<00:10, 1377.23 examples/s]
tokenizing (num_proc=8):  40%|████      | 9441/23500 [00:07<00:09, 1494.46 examples/s]
tokenizing (num_proc=8):  41%|████      | 9614/23500 [00:07<00:08, 1559.55 examples/s]
tokenizing (num_proc=8):  42%|████▏     | 9793/23500 [00:07<00:08, 1610.38 examples/s]
tokenizing (num_proc=8):  42%|████▏     | 9969/23500 [00:07<00:08, 1640.86 examples/s]
tokenizing (num_proc=8):  43%|████▎     | 10152/23500 [00:07<00:08, 1666.94 examples/s]
tokenizing (num_proc=8):  44%|████▍     | 10385/23500 [00:07<00:07, 1834.00 examples/s]
tokenizing (num_proc=8):  45%|████▌     | 10587/23500 [00:07<00:06, 1849.53 examples/s]
tokenizing (num_proc=8):  46%|████▌     | 10782/23500 [00:08<00:06, 1862.17 examples/s]
tokenizing (num_proc=8):  47%|████▋     | 10969/23500 [00:08<00:06, 1834.07 examples/s]
tokenizing (num_proc=8):  48%|████▊     | 11165/23500 [00:08<00:06, 1815.04 examples/s]
tokenizing (num_proc=8):  48%|████▊     | 11351/23500 [00:08<00:06, 1794.44 examples/s]
tokenizing (num_proc=8):  49%|████▉     | 11533/23500 [00:08<00:06, 1786.91 examples/s]
tokenizing (num_proc=8):  50%|████▉     | 11748/23500 [00:08<00:06, 1848.60 examples/s]
tokenizing (num_proc=8):  51%|█████     | 11940/23500 [00:08<00:06, 1776.55 examples/s]
tokenizing (num_proc=8):  52%|█████▏    | 12137/23500 [00:08<00:06, 1790.78 examples/s]
tokenizing (num_proc=8):  52%|█████▏    | 12322/23500 [00:08<00:06, 1785.97 examples/s]
tokenizing (num_proc=8):  53%|█████▎    | 12503/23500 [00:08<00:06, 1745.66 examples/s]
tokenizing (num_proc=8):  54%|█████▍    | 12678/23500 [00:09<00:06, 1717.17 examples/s]
tokenizing (num_proc=8):  55%|█████▍    | 12853/23500 [00:09<00:06, 1711.08 examples/s]
tokenizing (num_proc=8):  56%|█████▌    | 13056/23500 [00:09<00:05, 1787.98 examples/s]
tokenizing (num_proc=8):  56%|█████▋    | 13248/23500 [00:09<00:05, 1785.16 examples/s]
tokenizing (num_proc=8):  57%|█████▋    | 13440/23500 [00:09<00:05, 1779.33 examples/s]
tokenizing (num_proc=8):  58%|█████▊    | 13631/23500 [00:09<00:05, 1770.90 examples/s]
tokenizing (num_proc=8):  59%|█████▉    | 13826/23500 [00:09<00:05, 1791.50 examples/s]
tokenizing (num_proc=8):  60%|█████▉    | 14010/23500 [00:09<00:05, 1725.27 examples/s]
tokenizing (num_proc=8):  60%|██████    | 14188/23500 [00:09<00:05, 1699.59 examples/s]
tokenizing (num_proc=8):  61%|██████    | 14363/23500 [00:10<00:05, 1692.38 examples/s]
tokenizing (num_proc=8):  62%|██████▏   | 14533/23500 [00:10<00:05, 1681.25 examples/s]
tokenizing (num_proc=8):  63%|██████▎   | 14714/23500 [00:10<00:05, 1647.30 examples/s]
tokenizing (num_proc=8):  63%|██████▎   | 14883/23500 [00:10<00:05, 1626.71 examples/s]
tokenizing (num_proc=8):  64%|██████▍   | 15046/23500 [00:10<00:05, 1597.14 examples/s]
tokenizing (num_proc=8):  65%|██████▍   | 15211/23500 [00:10<00:05, 1587.98 examples/s]
tokenizing (num_proc=8):  65%|██████▌   | 15385/23500 [00:10<00:05, 1602.31 examples/s]
tokenizing (num_proc=8):  66%|██████▌   | 15547/23500 [00:10<00:05, 1568.11 examples/s]
tokenizing (num_proc=8):  67%|██████▋   | 15715/23500 [00:10<00:05, 1554.37 examples/s]
tokenizing (num_proc=8):  68%|██████▊   | 15891/23500 [00:11<00:04, 1592.32 examples/s]
tokenizing (num_proc=8):  69%|██████▊   | 16099/23500 [00:11<00:04, 1688.37 examples/s]
tokenizing (num_proc=8):  69%|██████▉   | 16281/23500 [00:11<00:04, 1649.10 examples/s]
tokenizing (num_proc=8):  70%|███████   | 16476/23500 [00:11<00:04, 1702.46 examples/s]
tokenizing (num_proc=8):  71%|███████   | 16673/23500 [00:11<00:03, 1763.39 examples/s]
tokenizing (num_proc=8):  72%|███████▏  | 16852/23500 [00:11<00:03, 1745.52 examples/s]
tokenizing (num_proc=8):  72%|███████▏  | 17032/23500 [00:11<00:04, 1585.73 examples/s]
tokenizing (num_proc=8):  73%|███████▎  | 17198/23500 [00:11<00:04, 1488.60 examples/s]
tokenizing (num_proc=8):  74%|███████▍  | 17354/23500 [00:11<00:04, 1433.09 examples/s]
tokenizing (num_proc=8):  74%|███████▍  | 17503/23500 [00:12<00:04, 1422.45 examples/s]
tokenizing (num_proc=8):  75%|███████▌  | 17690/23500 [00:12<00:03, 1523.24 examples/s]
tokenizing (num_proc=8):  76%|███████▌  | 17855/23500 [00:12<00:03, 1502.66 examples/s]
tokenizing (num_proc=8):  77%|███████▋  | 18043/23500 [00:12<00:03, 1593.34 examples/s]
tokenizing (num_proc=8):  77%|███████▋  | 18209/23500 [00:12<00:03, 1544.92 examples/s]
tokenizing (num_proc=8):  78%|███████▊  | 18367/23500 [00:12<00:03, 1547.75 examples/s]
tokenizing (num_proc=8):  79%|███████▉  | 18525/23500 [00:12<00:03, 1523.43 examples/s]
tokenizing (num_proc=8):  80%|███████▉  | 18713/23500 [00:12<00:03, 1591.77 examples/s]
tokenizing (num_proc=8):  80%|████████  | 18906/23500 [00:12<00:02, 1677.45 examples/s]
tokenizing (num_proc=8):  81%|████████▏ | 19096/23500 [00:13<00:02, 1712.58 examples/s]
tokenizing (num_proc=8):  82%|████████▏ | 19288/23500 [00:13<00:02, 1752.97 examples/s]
tokenizing (num_proc=8):  83%|████████▎ | 19475/23500 [00:13<00:02, 1747.33 examples/s]
tokenizing (num_proc=8):  84%|████████▎ | 19657/23500 [00:13<00:02, 1742.35 examples/s]
tokenizing (num_proc=8):  84%|████████▍ | 19837/23500 [00:13<00:02, 1653.97 examples/s]
tokenizing (num_proc=8):  85%|████████▌ | 20027/23500 [00:13<00:02, 1711.89 examples/s]
tokenizing (num_proc=8):  86%|████████▌ | 20206/23500 [00:13<00:01, 1720.91 examples/s]
tokenizing (num_proc=8):  87%|████████▋ | 20382/23500 [00:13<00:01, 1699.48 examples/s]
tokenizing (num_proc=8):  87%|████████▋ | 20553/23500 [00:13<00:01, 1568.59 examples/s]
tokenizing (num_proc=8):  88%|████████▊ | 20715/23500 [00:14<00:01, 1548.12 examples/s]
tokenizing (num_proc=8):  89%|████████▉ | 20876/23500 [00:14<00:01, 1489.87 examples/s]
tokenizing (num_proc=8):  90%|████████▉ | 21050/23500 [00:14<00:01, 1550.35 examples/s]
tokenizing (num_proc=8):  90%|█████████ | 21210/23500 [00:14<00:01, 1513.42 examples/s]
tokenizing (num_proc=8):  91%|█████████ | 21371/23500 [00:14<00:01, 1386.23 examples/s]
tokenizing (num_proc=8):  92%|█████████▏| 21513/23500 [00:14<00:01, 1357.26 examples/s]
tokenizing (num_proc=8):  92%|█████████▏| 21651/23500 [00:14<00:01, 1137.72 examples/s]
tokenizing (num_proc=8):  93%|█████████▎| 21781/23500 [00:14<00:01, 1026.02 examples/s]
tokenizing (num_proc=8):  93%|█████████▎| 21894/23500 [00:15<00:01, 927.62 examples/s] 
tokenizing (num_proc=8):  94%|█████████▎| 21995/23500 [00:15<00:01, 869.22 examples/s]
tokenizing (num_proc=8):  94%|█████████▍| 22088/23500 [00:15<00:01, 849.31 examples/s]
tokenizing (num_proc=8):  94%|█████████▍| 22176/23500 [00:15<00:01, 824.85 examples/s]
tokenizing (num_proc=8):  95%|█████████▍| 22278/23500 [00:15<00:01, 848.52 examples/s]
tokenizing (num_proc=8):  95%|█████████▌| 22371/23500 [00:15<00:01, 846.27 examples/s]
tokenizing (num_proc=8):  96%|█████████▌| 22458/23500 [00:15<00:01, 815.95 examples/s]
tokenizing (num_proc=8):  96%|█████████▌| 22548/23500 [00:15<00:01, 796.08 examples/s]
tokenizing (num_proc=8):  96%|█████████▋| 22630/23500 [00:16<00:01, 782.99 examples/s]
tokenizing (num_proc=8):  97%|█████████▋| 22712/23500 [00:16<00:01, 785.62 examples/s]
tokenizing (num_proc=8):  97%|█████████▋| 22815/23500 [00:16<00:00, 848.04 examples/s]
tokenizing (num_proc=8):  97%|█████████▋| 22906/23500 [00:16<00:00, 831.53 examples/s]
tokenizing (num_proc=8):  98%|█████████▊| 22998/23500 [00:16<00:00, 827.13 examples/s]
tokenizing (num_proc=8):  98%|█████████▊| 23092/23500 [00:16<00:00, 729.56 examples/s]
tokenizing (num_proc=8):  99%|█████████▊| 23174/23500 [00:16<00:00, 671.40 examples/s]
tokenizing (num_proc=8):  99%|█████████▉| 23244/23500 [00:16<00:00, 669.34 examples/s]
tokenizing (num_proc=8):  99%|█████████▉| 23323/23500 [00:17<00:00, 604.99 examples/s]
tokenizing (num_proc=8): 100%|█████████▉| 23391/23500 [00:17<00:00, 485.45 examples/s]
tokenizing (num_proc=8): 100%|█████████▉| 23456/23500 [00:17<00:00, 376.59 examples/s]
tokenizing (num_proc=8): 100%|██████████| 23500/23500 [00:18<00:00, 1278.48 examples/s]

Filter:   0%|          | 0/23500 [00:00<?, ? examples/s]
Filter:   4%|▍         | 1000/23500 [00:00<00:04, 5035.20 examples/s]
Filter:   9%|▊         | 2000/23500 [00:00<00:04, 5269.94 examples/s]
Filter:  13%|█▎        | 3000/23500 [00:00<00:03, 5369.72 examples/s]
Filter:  17%|█▋        | 4000/23500 [00:00<00:03, 5389.68 examples/s]
Filter:  21%|██▏       | 5000/23500 [00:00<00:03, 5469.60 examples/s]
Filter:  26%|██▌       | 6000/23500 [00:01<00:03, 5585.93 examples/s]
Filter:  30%|██▉       | 7000/23500 [00:01<00:02, 5620.47 examples/s]
Filter:  34%|███▍      | 8000/23500 [00:01<00:02, 5453.90 examples/s]
Filter:  38%|███▊      | 9000/23500 [00:01<00:02, 5644.27 examples/s]
Filter:  43%|████▎     | 10000/23500 [00:01<00:02, 5741.16 examples/s]
Filter:  47%|████▋     | 11000/23500 [00:01<00:02, 5539.54 examples/s]
Filter:  51%|█████     | 12000/23500 [00:02<00:02, 5484.09 examples/s]
Filter:  55%|█████▌    | 13000/23500 [00:02<00:01, 5602.28 examples/s]
Filter:  60%|█████▉    | 14000/23500 [00:02<00:01, 5577.88 examples/s]
Filter:  64%|██████▍   | 15000/23500 [00:02<00:01, 5658.36 examples/s]
Filter:  68%|██████▊   | 16000/23500 [00:02<00:01, 5672.86 examples/s]
Filter:  72%|███████▏  | 17000/23500 [00:03<00:01, 5699.12 examples/s]
Filter:  77%|███████▋  | 18000/23500 [00:03<00:00, 5867.99 examples/s]
Filter:  81%|████████  | 19000/23500 [00:03<00:00, 5846.49 examples/s]
Filter:  85%|████████▌ | 20000/23500 [00:03<00:00, 5910.77 examples/s]
Filter:  89%|████████▉ | 21000/23500 [00:03<00:00, 5910.20 examples/s]
Filter:  94%|█████████▎| 22000/23500 [00:03<00:00, 5929.60 examples/s]
Filter:  98%|█████████▊| 23000/23500 [00:04<00:00, 6094.96 examples/s]
Filter: 100%|██████████| 23500/23500 [00:04<00:00, 5709.92 examples/s]

Filter:   0%|          | 0/23500 [00:00<?, ? examples/s]
Filter:   4%|▍         | 1000/23500 [00:00<00:03, 6372.70 examples/s]
Filter:   9%|▊         | 2000/23500 [00:00<00:03, 5997.51 examples/s]
Filter:  13%|█▎        | 3000/23500 [00:00<00:03, 5703.49 examples/s]
Filter:  17%|█▋        | 4000/23500 [00:00<00:03, 5758.82 examples/s]
Filter:  21%|██▏       | 5000/23500 [00:00<00:03, 5840.02 examples/s]
Filter:  26%|██▌       | 6000/23500 [00:01<00:02, 6034.26 examples/s]
Filter:  30%|██▉       | 7000/23500 [00:01<00:02, 6095.80 examples/s]
Filter:  34%|███▍      | 8000/23500 [00:01<00:02, 5938.59 examples/s]
Filter:  38%|███▊      | 9000/23500 [00:01<00:02, 6002.75 examples/s]
Filter:  43%|████▎     | 10000/23500 [00:01<00:02, 5816.02 examples/s]
Filter:  47%|████▋     | 11000/23500 [00:01<00:02, 5927.48 examples/s]
Filter:  51%|█████     | 12000/23500 [00:02<00:01, 5849.24 examples/s]
Filter:  55%|█████▌    | 13000/23500 [00:02<00:01, 5876.70 examples/s]
Filter:  60%|█████▉    | 14000/23500 [00:02<00:01, 5848.63 examples/s]
Filter:  64%|██████▍   | 15000/23500 [00:02<00:01, 5640.14 examples/s]
Filter:  68%|██████▊   | 16000/23500 [00:02<00:01, 5663.73 examples/s]
Filter:  72%|███████▏  | 17000/23500 [00:02<00:01, 5716.08 examples/s]
Filter:  77%|███████▋  | 18000/23500 [00:03<00:00, 5925.53 examples/s]
Filter:  81%|████████  | 19000/23500 [00:03<00:00, 5964.45 examples/s]
Filter:  85%|████████▌ | 20000/23500 [00:03<00:00, 5913.97 examples/s]
Filter:  89%|████████▉ | 21000/23500 [00:03<00:00, 5937.10 examples/s]
Filter:  94%|█████████▎| 22000/23500 [00:03<00:00, 5747.49 examples/s]
Filter:  98%|█████████▊| 23000/23500 [00:03<00:00, 5940.50 examples/s]
Filter: 100%|██████████| 23500/23500 [00:03<00:00, 5881.50 examples/s]
supervised tokens: tool 4521017, replay 11056920 (71.0% replay)
replay capped to 25% of supervised tokens: kept 1506259 replay tokens, 1257 replay rows
rows: 23500 raw -> 15331 kept; by source: {'recovery': 3750, 'xlam': 5000, 'replay:compassion_12185_cleaned': 1257, 'apigen': 4824, 'efficiency': 500}
[manifest] git=f56d0c01687b3b599f164c8b826c3df524c66dbf  data_sha256={'train_olmo-compassion_replay50.jsonl': 'b43d87068505', 'xlam5000_max1call.jsonl': 'a8aae6cf5c36'}
wandb: WARNING git root /workspace/anchor/olmo-compassion/wandb does not exist
wandb: Tracking run with wandb version 0.30.0
wandb: W&B syncing is set to `offline` in this directory. Run `wandb online` or set WANDB_MODE=online to enable cloud syncing.
wandb: Run data is saved locally in /workspace/anchor/olmo-compassion/wandb/wandb/offline-run-20261013_000822-6sbhg1fn
wandb: View this run in the terminal with `wandb leet`
wandb: Detected [huggingface_hub.inference] in use.
wandb: Use W&B Weave for improved LLM call tracing. Install Weave with `pip install weave` then add `import weave` to the top of your script.
wandb: For more information, check out the docs at: https://weave-docs.wandb.ai
==((====))==  Unsloth - 2x faster free finetuning | Num GPUs used = 1
   \\   /|    Num examples = 14,947 | Num Epochs = 1 | Total steps = 935
O^O/ \_/ \    Batch size per device = 2 | Gradient accumulation steps = 8
\        /    Data Parallel GPUs = 1 | Total batch size (2 x 8 x 1) = 16
 "-____-"     Trainable parameters = 981,385,216 of 8,279,396,352 (11.85% trained)
Unsloth: Setting lr = 2.00e-05 instead of 2.00e-04 for embed_tokens.
Unsloth: Setting lr = 2.00e-05 instead of 2.00e-04 for lm_head.

  0%|          | 0/935 [00:00<?, ?it/s]
  0%|          | 1/935 [00:48<12:30:14, 48.20s/it]
  0%|          | 2/935 [01:16<9:26:37, 36.44s/it] 
  0%|          | 3/935 [01:39<7:48:26, 30.16s/it]
  0%|          | 4/935 [02:01<7:01:53, 27.19s/it]
  1%|          | 5/935 [02:27<6:51:55, 26.58s/it]
                                                 

  1%|          | 5/935 [02:27<6:51:55, 26.58s/it]
  1%|          | 6/935 [02:51<6:37:31, 25.67s/it]
  1%|          | 7/935 [03:14<6:24:02, 24.83s/it]
  1%|          | 8/935 [03:40<6:28:49, 25.17s/it]
  1%|          | 9/935 [04:04<6:23:08, 24.83s/it]
  1%|          | 10/935 [04:26<6:11:55, 24.12s/it]
                                                  

  1%|          | 10/935 [04:26<6:11:55, 24.12s/it]
  1%|          | 11/935 [04:46<5:53:08, 22.93s/it]
  1%|▏         | 12/935 [05:12<6:03:14, 23.61s/it]
  1%|▏         | 13/935 [05:34<5:56:26, 23.20s/it]
  1%|▏         | 14/935 [05:58<6:02:00, 23.58s/it]
  2%|▏         | 15/935 [06:21<5:59:29, 23.45s/it]
                                                  

  2%|▏         | 15/935 [06:21<5:59:29, 23.45s/it]
  2%|▏         | 16/935 [06:46<6:01:51, 23.63s/it]
  2%|▏         | 17/935 [07:10<6:05:20, 23.88s/it]
  2%|▏         | 18/935 [07:30<5:48:26, 22.80s/it]
  2%|▏         | 19/935 [07:54<5:50:26, 22.96s/it]
  2%|▏         | 20/935 [08:15<5:40:56, 22.36s/it]
                                                  

  2%|▏         | 20/935 [08:15<5:40:56, 22.36s/it]
  2%|▏         | 21/935 [08:38<5:44:24, 22.61s/it]
  2%|▏         | 22/935 [09:00<5:42:51, 22.53s/it]
  2%|▏         | 23/935 [09:23<5:44:42, 22.68s/it]
  3%|▎         | 24/935 [09:46<5:45:44, 22.77s/it]
  3%|▎         | 25/935 [10:09<5:46:52, 22.87s/it]
                                                  

  3%|▎         | 25/935 [10:09<5:46:52, 22.87s/it]
  3%|▎         | 26/935 [10:32<5:45:13, 22.79s/it]
  3%|▎         | 27/935 [10:54<5:41:26, 22.56s/it]
  3%|▎         | 28/935 [11:15<5:33:41, 22.07s/it]
  3%|▎         | 29/935 [11:37<5:32:00, 21.99s/it]
  3%|▎         | 30/935 [11:56<5:21:32, 21.32s/it]
                                                  

  3%|▎         | 30/935 [11:56<5:21:32, 21.32s/it]
  3%|▎         | 31/935 [12:18<5:24:43, 21.55s/it]
  3%|▎         | 32/935 [12:42<5:35:33, 22.30s/it]
  4%|▎         | 33/935 [13:06<5:42:23, 22.78s/it]
  4%|▎         | 34/935 [13:29<5:40:39, 22.69s/it]
  4%|▎         | 35/935 [13:56<6:00:09, 24.01s/it]
                                                  

  4%|▎         | 35/935 [13:56<6:00:09, 24.01s/it]
  4%|▍         | 36/935 [14:20<6:00:42, 24.07s/it]
  4%|▍         | 37/935 [14:44<5:59:10, 24.00s/it]
  4%|▍         | 38/935 [15:09<6:01:08, 24.16s/it]
  4%|▍         | 39/935 [15:28<5:41:55, 22.90s/it]
  4%|▍         | 40/935 [15:52<5:43:55, 23.06s/it]
                                                  

  4%|▍         | 40/935 [15:52<5:43:55, 23.06s/it]
  4%|▍         | 41/935 [16:14<5:37:23, 22.64s/it]
  4%|▍         | 42/935 [16:32<5:20:20, 21.52s/it]
  5%|▍         | 43/935 [16:50<5:02:37, 20.36s/it]
  5%|▍         | 44/935 [17:13<5:15:21, 21.24s/it]
  5%|▍         | 45/935 [17:35<5:14:46, 21.22s/it]
                                                  

  5%|▍         | 45/935 [17:35<5:14:46, 21.22s/it]
  5%|▍         | 46/935 [17:53<5:00:24, 20.28s/it]
  5%|▌         | 47/935 [18:11<4:50:47, 19.65s/it]
  5%|▌         | 48/935 [18:34<5:07:28, 20.80s/it]
  5%|▌         | 49/935 [18:56<5:12:55, 21.19s/it]
  5%|▌         | 50/935 [19:19<5:16:55, 21.49s/it]
                                                  

  5%|▌         | 50/935 [19:19<5:16:55, 21.49s/it]Unsloth: Will smartly offload gradients to save VRAM!
Unsloth: Double buffering enabled (parallel H2D + compute) for backward pass.
{'loss': 7.033, 'grad_norm': 7.84370756149292, 'learning_rate': 1.7021276595744682e-05, 'epoch': 0.01}
{'loss': 6.5074, 'grad_norm': 6.463988304138184, 'learning_rate': 3.829787234042553e-05, 'epoch': 0.01}
{'loss': 5.5202, 'grad_norm': 3.8663952350616455, 'learning_rate': 5.9574468085106384e-05, 'epoch': 0.02}
{'loss': 4.6312, 'grad_norm': 3.429267168045044, 'learning_rate': 8.085106382978723e-05, 'epoch': 0.02}
{'loss': 3.9047, 'grad_norm': 2.4048895835876465, 'learning_rate': 0.00010212765957446809, 'epoch': 0.03}
{'loss': 3.239, 'grad_norm': 1.6516971588134766, 'learning_rate': 0.00012340425531914893, 'epoch': 0.03}
{'loss': 2.8394, 'grad_norm': 1.9744592905044556, 'learning_rate': 0.0001446808510638298, 'epoch': 0.04}
{'loss': 1.9605, 'grad_norm': 1.9995774030685425, 'learning_rate': 0.00016595744680851065, 'epoch': 0.04}
{'loss': 1.4049, 'grad_norm': 1.9445796012878418, 'learning_rate': 0.0001872340425531915, 'epoch': 0.05}
{'loss': 1.1704, 'grad_norm': 1.7529069185256958, 'learning_rate': 0.00019999749676283775, 'epoch': 0.05}


Filter:   0%|          | 0/384 [00:00<?, ? examples/s]

Filter: 100%|██████████| 384/384 [00:00<00:00, 1447.59 examples/s]
Filter: 100%|██████████| 384/384 [00:00<00:00, 1434.88 examples/s]


  0%|          | 0/192 [00:00<?, ?it/s]

  1%|          | 2/192 [00:00<01:25,  2.23it/s]

  2%|▏         | 3/192 [00:01<02:01,  1.55it/s]

  2%|▏         | 4/192 [00:03<02:42,  1.16it/s]

  3%|▎         | 5/192 [00:04<02:53,  1.08it/s]

  3%|▎         | 6/192 [00:04<02:46,  1.12it/s]

  4%|▎         | 7/192 [00:05<02:11,  1.40it/s]

  4%|▍         | 8/192 [00:06<02:16,  1.35it/s]

  5%|▍         | 9/192 [00:07<02:38,  1.16it/s]

  5%|▌         | 10/192 [00:08<03:03,  1.01s/it]

  6%|▌         | 11/192 [00:09<03:05,  1.02s/it]

  6%|▋         | 12/192 [00:10<03:00,  1.00s/it]

  7%|▋         | 13/192 [00:11<03:02,  1.02s/it]

  7%|▋         | 14/192 [00:12<03:13,  1.09s/it]

  8%|▊         | 15/192 [00:13<03:08,  1.07s/it]

  8%|▊         | 16/192 [00:14<03:02,  1.04s/it]

  9%|▉         | 17/192 [00:15<02:38,  1.10it/s]

 10%|▉         | 19/192 [00:16<02:00,  1.43it/s]

 10%|█         | 20/192 [00:17<02:04,  1.38it/s]

 11%|█         | 21/192 [00:18<02:19,  1.23it/s]

 11%|█▏        | 22/192 [00:18<02:16,  1.25it/s]

 12%|█▏        | 23/192 [00:19<01:42,  1.65it/s]

 13%|█▎        | 25/192 [00:20<01:31,  1.82it/s]

 14%|█▎        | 26/192 [00:21<02:01,  1.37it/s]

 14%|█▍        | 27/192 [00:22<02:18,  1.19it/s]

 15%|█▍        | 28/192 [00:23<02:16,  1.20it/s]

 15%|█▌        | 29/192 [00:24<02:25,  1.12it/s]

 16%|█▌        | 30/192 [00:25<02:29,  1.08it/s]

 16%|█▌        | 31/192 [00:26<02:34,  1.04it/s]

 17%|█▋        | 32/192 [00:27<02:45,  1.04s/it]

 17%|█▋        | 33/192 [00:28<02:13,  1.19it/s]

 18%|█▊        | 34/192 [00:28<02:01,  1.30it/s]

 18%|█▊        | 35/192 [00:29<01:51,  1.41it/s]

 19%|█▉        | 36/192 [00:29<01:44,  1.50it/s]

 19%|█▉        | 37/192 [00:30<01:48,  1.43it/s]

 20%|█▉        | 38/192 [00:31<01:51,  1.38it/s]

 20%|██        | 39/192 [00:32<01:57,  1.30it/s]

 21%|██        | 40/192 [00:32<01:56,  1.30it/s]

 21%|██▏       | 41/192 [00:34<02:21,  1.07it/s]

 22%|██▏       | 42/192 [00:35<02:18,  1.08it/s]

 22%|██▏       | 43/192 [00:35<01:43,  1.45it/s]

 23%|██▎       | 44/192 [00:36<02:03,  1.20it/s]

 23%|██▎       | 45/192 [00:37<02:18,  1.06it/s]

 24%|██▍       | 46/192 [00:38<02:13,  1.09it/s]

 24%|██▍       | 47/192 [00:39<02:23,  1.01it/s]

 25%|██▌       | 48/192 [00:40<01:53,  1.27it/s]

 26%|██▌       | 49/192 [00:40<01:46,  1.34it/s]

 27%|██▋       | 51/192 [00:41<01:20,  1.75it/s]

 27%|██▋       | 52/192 [00:41<01:20,  1.74it/s]

 28%|██▊       | 53/192 [00:43<01:39,  1.39it/s]

 28%|██▊       | 54/192 [00:43<01:43,  1.33it/s]

 29%|██▊       | 55/192 [00:44<01:47,  1.27it/s]

 29%|██▉       | 56/192 [00:45<02:00,  1.12it/s]

 30%|██▉       | 57/192 [00:47<02:09,  1.04it/s]

 30%|███       | 58/192 [00:47<01:53,  1.18it/s]

 31%|███▏      | 60/192 [00:48<01:24,  1.56it/s]

 32%|███▏      | 61/192 [00:48<01:11,  1.83it/s]

 32%|███▏      | 62/192 [00:49<01:20,  1.62it/s]

 33%|███▎      | 63/192 [00:50<01:36,  1.34it/s]

 33%|███▎      | 64/192 [00:51<01:38,  1.30it/s]

 34%|███▍      | 65/192 [00:52<01:51,  1.14it/s]

 34%|███▍      | 66/192 [00:53<02:05,  1.01it/s]

 35%|███▍      | 67/192 [00:54<02:00,  1.04it/s]

 35%|███▌      | 68/192 [00:55<01:45,  1.18it/s]

 36%|███▌      | 69/192 [00:56<01:43,  1.19it/s]

 36%|███▋      | 70/192 [00:57<01:47,  1.14it/s]

 37%|███▋      | 71/192 [00:57<01:27,  1.39it/s]

 38%|███▊      | 72/192 [00:57<01:13,  1.64it/s]

 38%|███▊      | 73/192 [00:59<01:31,  1.29it/s]

 39%|███▊      | 74/192 [01:00<01:41,  1.16it/s]

 39%|███▉      | 75/192 [01:00<01:14,  1.57it/s]

 40%|███▉      | 76/192 [01:01<01:27,  1.33it/s]

 40%|████      | 77/192 [01:02<01:28,  1.29it/s]

 41%|████      | 79/192 [01:03<01:17,  1.46it/s]

 42%|████▏     | 80/192 [01:03<01:19,  1.41it/s]

 42%|████▏     | 81/192 [01:04<01:23,  1.33it/s]

 43%|████▎     | 82/192 [01:05<01:29,  1.23it/s]

 43%|████▎     | 83/192 [01:06<01:36,  1.13it/s]

 44%|████▍     | 85/192 [01:07<01:13,  1.45it/s]

 45%|████▍     | 86/192 [01:08<01:10,  1.51it/s]

 45%|████▌     | 87/192 [01:08<00:55,  1.91it/s]

 46%|████▌     | 88/192 [01:09<01:13,  1.42it/s]

 46%|████▋     | 89/192 [01:10<01:25,  1.21it/s]

 47%|████▋     | 90/192 [01:11<01:23,  1.22it/s]

 47%|████▋     | 91/192 [01:11<01:07,  1.49it/s]

 48%|████▊     | 92/192 [01:12<01:13,  1.36it/s]

 48%|████▊     | 93/192 [01:13<01:21,  1.22it/s]

 49%|████▉     | 94/192 [01:14<01:24,  1.16it/s]

 49%|████▉     | 95/192 [01:15<01:23,  1.16it/s]

 50%|█████     | 96/192 [01:16<01:15,  1.28it/s]

 51%|█████     | 97/192 [01:16<01:09,  1.37it/s]

 51%|█████     | 98/192 [01:17<01:05,  1.43it/s]

 52%|█████▏    | 99/192 [01:17<00:48,  1.92it/s]

 52%|█████▏    | 100/192 [01:18<00:57,  1.61it/s]

 53%|█████▎    | 102/192 [01:18<00:33,  2.70it/s]

 54%|█████▎    | 103/192 [01:19<00:48,  1.83it/s]

 54%|█████▍    | 104/192 [01:20<00:58,  1.50it/s]

 55%|█████▍    | 105/192 [01:21<01:03,  1.36it/s]

 55%|█████▌    | 106/192 [01:22<01:10,  1.22it/s]

 56%|█████▌    | 107/192 [01:23<01:18,  1.09it/s]

 56%|█████▋    | 108/192 [01:25<01:24,  1.01s/it]

 57%|█████▋    | 109/192 [01:26<01:32,  1.12s/it]

 57%|█████▋    | 110/192 [01:26<01:13,  1.12it/s]

 58%|█████▊    | 111/192 [01:27<01:11,  1.13it/s]

 58%|█████▊    | 112/192 [01:28<01:16,  1.04it/s]

 59%|█████▉    | 113/192 [01:29<01:20,  1.01s/it]

 59%|█████▉    | 114/192 [01:31<01:21,  1.04s/it]

 60%|█████▉    | 115/192 [01:31<01:16,  1.01it/s]

 61%|██████    | 117/192 [01:32<00:56,  1.33it/s]

 61%|██████▏   | 118/192 [01:34<01:03,  1.16it/s]

 62%|██████▏   | 119/192 [01:35<01:06,  1.10it/s]

 62%|██████▎   | 120/192 [01:35<01:03,  1.14it/s]

 63%|██████▎   | 121/192 [01:37<01:06,  1.07it/s]

 64%|██████▎   | 122/192 [01:38<01:09,  1.01it/s]

 64%|██████▍   | 123/192 [01:38<00:56,  1.22it/s]

 65%|██████▍   | 124/192 [01:39<01:00,  1.13it/s]

 65%|██████▌   | 125/192 [01:40<01:08,  1.02s/it]

 66%|██████▌   | 126/192 [01:41<00:53,  1.23it/s]

 66%|██████▌   | 127/192 [01:42<00:54,  1.19it/s]

 67%|██████▋   | 129/192 [01:43<00:42,  1.49it/s]

 68%|██████▊   | 130/192 [01:44<00:53,  1.17it/s]

 68%|██████▊   | 131/192 [01:45<00:57,  1.06it/s]

 69%|██████▉   | 132/192 [01:46<00:57,  1.05it/s]

 69%|██████▉   | 133/192 [01:47<00:59,  1.00s/it]

 70%|██████▉   | 134/192 [01:48<00:54,  1.06it/s]

 70%|███████   | 135/192 [01:49<00:58,  1.02s/it]

 71%|███████   | 136/192 [01:50<00:57,  1.02s/it]

 71%|███████▏  | 137/192 [01:51<00:56,  1.02s/it]

 72%|███████▏  | 139/192 [01:52<00:31,  1.68it/s]

 73%|███████▎  | 140/192 [01:53<00:36,  1.42it/s]

 73%|███████▎  | 141/192 [01:53<00:33,  1.51it/s]

 74%|███████▍  | 142/192 [01:54<00:40,  1.22it/s]

 74%|███████▍  | 143/192 [01:56<00:48,  1.01it/s]

 75%|███████▌  | 144/192 [01:57<00:52,  1.09s/it]

 76%|███████▌  | 145/192 [01:58<00:52,  1.11s/it]

 76%|███████▌  | 146/192 [01:59<00:50,  1.09s/it]

 77%|███████▋  | 147/192 [02:00<00:46,  1.04s/it]

 77%|███████▋  | 148/192 [02:01<00:42,  1.02it/s]

 78%|███████▊  | 149/192 [02:02<00:44,  1.04s/it]

 78%|███████▊  | 150/192 [02:03<00:35,  1.19it/s]

 79%|███████▊  | 151/192 [02:03<00:27,  1.47it/s]

 79%|███████▉  | 152/192 [02:04<00:34,  1.16it/s]

 80%|███████▉  | 153/192 [02:06<00:40,  1.04s/it]

 80%|████████  | 154/192 [02:07<00:39,  1.05s/it]

 81%|████████  | 155/192 [02:08<00:40,  1.10s/it]

 81%|████████▏ | 156/192 [02:09<00:42,  1.17s/it]

 82%|████████▏ | 157/192 [02:10<00:38,  1.09s/it]

 82%|████████▏ | 158/192 [02:11<00:34,  1.00s/it]

 83%|████████▎ | 159/192 [02:12<00:34,  1.03s/it]

 83%|████████▎ | 160/192 [02:13<00:33,  1.05s/it]

 84%|████████▍ | 161/192 [02:14<00:31,  1.02s/it]

 84%|████████▍ | 162/192 [02:15<00:33,  1.11s/it]

 85%|████████▍ | 163/192 [02:17<00:36,  1.25s/it]

 85%|████████▌ | 164/192 [02:18<00:31,  1.13s/it]

 86%|████████▌ | 165/192 [02:20<00:34,  1.27s/it]

 86%|████████▋ | 166/192 [02:21<00:31,  1.22s/it]

 87%|████████▋ | 167/192 [02:22<00:29,  1.19s/it]

 88%|████████▊ | 168/192 [02:22<00:24,  1.01s/it]

 88%|████████▊ | 169/192 [02:23<00:24,  1.05s/it]

 89%|████████▊ | 170/192 [02:24<00:21,  1.01it/s]

 89%|████████▉ | 171/192 [02:25<00:20,  1.04it/s]

 90%|████████▉ | 172/192 [02:26<00:19,  1.00it/s]

 90%|█████████ | 173/192 [02:27<00:19,  1.02s/it]

 91%|█████████ | 174/192 [02:28<00:17,  1.03it/s]

 91%|█████████ | 175/192 [02:29<00:13,  1.27it/s]

 92%|█████████▏| 176/192 [02:30<00:14,  1.11it/s]

 92%|█████████▏| 177/192 [02:31<00:14,  1.02it/s]

 93%|█████████▎| 178/192 [02:32<00:13,  1.03it/s]

 93%|█████████▎| 179/192 [02:33<00:12,  1.02it/s]

 94%|█████████▍| 180/192 [02:34<00:11,  1.02it/s]

 94%|█████████▍| 181/192 [02:35<00:10,  1.02it/s]

 95%|█████████▍| 182/192 [02:35<00:07,  1.32it/s]

 95%|█████████▌| 183/192 [02:36<00:08,  1.12it/s]

 96%|█████████▌| 184/192 [02:38<00:08,  1.01s/it]

 96%|█████████▋| 185/192 [02:39<00:07,  1.07s/it]

 97%|█████████▋| 186/192 [02:39<00:04,  1.23it/s]

 97%|█████████▋| 187/192 [02:40<00:04,  1.21it/s]

 98%|█████████▊| 188/192 [02:41<00:03,  1.13it/s]

 98%|█████████▊| 189/192 [02:41<00:01,  1.51it/s]

 99%|█████████▉| 190/192 [02:42<00:01,  1.27it/s]

 99%|█████████▉| 191/192 [02:43<00:00,  1.15it/s]

100%|██████████| 192/192 [02:44<00:00,  1.28it/s]
                                                  

                                                 

  5%|▌         | 50/935 [22:08<5:16:55, 21.49s/it]

100%|██████████| 192/192 [02:44<00:00,  1.28it/s]

                                                 
  5%|▌         | 51/935 [22:25<17:23:15, 70.81s/it]
  6%|▌         | 52/935 [22:45<13:38:51, 55.64s/it]
  6%|▌         | 53/935 [23:02<10:48:35, 44.12s/it]
  6%|▌         | 54/935 [23:15<8:30:30, 34.77s/it] 
  6%|▌         | 55/935 [23:37<7:34:39, 31.00s/it]
                                                  

  6%|▌         | 55/935 [23:37<7:34:39, 31.00s/it]
  6%|▌         | 56/935 [23:58<6:50:05, 27.99s/it]
  6%|▌         | 57/935 [24:21<6:26:17, 26.40s/it]
  6%|▌         | 58/935 [24:46<6:20:40, 26.04s/it]
  6%|▋         | 59/935 [25:07<5:58:16, 24.54s/it]
  6%|▋         | 60/935 [25:24<5:22:53, 22.14s/it]
                                                  

  6%|▋         | 60/935 [25:24<5:22:53, 22.14s/it]
  7%|▋         | 61/935 [25:48<5:32:55, 22.86s/it]
  7%|▋         | 62/935 [26:10<5:29:50, 22.67s/it]
  7%|▋         | 63/935 [26:33<5:27:43, 22.55s/it]
  7%|▋         | 64/935 [26:52<5:13:09, 21.57s/it]
  7%|▋         | 65/935 [27:10<4:56:16, 20.43s/it]
                                                  

  7%|▋         | 65/935 [27:10<4:56:16, 20.43s/it]
  7%|▋         | 66/935 [27:30<4:53:33, 20.27s/it]
  7%|▋         | 67/935 [27:48<4:43:53, 19.62s/it]
  7%|▋         | 68/935 [28:07<4:43:48, 19.64s/it]
  7%|▋         | 69/935 [28:25<4:35:41, 19.10s/it]
  7%|▋         | 70/935 [28:45<4:37:12, 19.23s/it]
                                                  

  7%|▋         | 70/935 [28:45<4:37:12, 19.23s/it]
  8%|▊         | 71/935 [29:01<4:25:16, 18.42s/it]
  8%|▊         | 72/935 [29:22<4:33:55, 19.05s/it]
  8%|▊         | 73/935 [29:34<4:03:19, 16.94s/it]
  8%|▊         | 74/935 [29:59<4:38:25, 19.40s/it]
  8%|▊         | 75/935 [30:16<4:28:21, 18.72s/it]
                                                  

  8%|▊         | 75/935 [30:16<4:28:21, 18.72s/it]
  8%|▊         | 76/935 [30:35<4:27:18, 18.67s/it]
  8%|▊         | 77/935 [30:53<4:26:57, 18.67s/it]
  8%|▊         | 78/935 [31:13<4:32:28, 19.08s/it]
  8%|▊         | 79/935 [31:28<4:13:00, 17.73s/it]
  9%|▊         | 80/935 [31:56<4:55:43, 20.75s/it]
                                                  

  9%|▊         | 80/935 [31:56<4:55:43, 20.75s/it]
  9%|▊         | 81/935 [32:20<5:10:58, 21.85s/it]
  9%|▉         | 82/935 [32:39<4:58:10, 20.97s/it]
  9%|▉         | 83/935 [33:01<5:01:24, 21.23s/it]
  9%|▉         | 84/935 [33:22<5:00:05, 21.16s/it]
  9%|▉         | 85/935 [33:40<4:45:24, 20.15s/it]
                                                  

  9%|▉         | 85/935 [33:40<4:45:24, 20.15s/it]
  9%|▉         | 86/935 [33:55<4:25:48, 18.79s/it]
  9%|▉         | 87/935 [34:17<4:38:01, 19.67s/it]
  9%|▉         | 88/935 [34:32<4:18:26, 18.31s/it]
 10%|▉         | 89/935 [34:51<4:21:15, 18.53s/it]
 10%|▉         | 90/935 [35:14<4:39:32, 19.85s/it]
                                                  

 10%|▉         | 90/935 [35:14<4:39:32, 19.85s/it]
 10%|▉         | 91/935 [35:34<4:39:37, 19.88s/it]
 10%|▉         | 92/935 [35:48<4:15:29, 18.18s/it]
 10%|▉         | 93/935 [36:05<4:09:55, 17.81s/it]
 10%|█         | 94/935 [36:23<4:10:44, 17.89s/it]
 10%|█         | 95/935 [36:43<4:18:57, 18.50s/it]
                                                  

 10%|█         | 95/935 [36:43<4:18:57, 18.50s/it]
 10%|█         | 96/935 [37:00<4:10:13, 17.90s/it]
 10%|█         | 97/935 [37:22<4:28:49, 19.25s/it]
 10%|█         | 98/935 [37:38<4:13:22, 18.16s/it]
 11%|█         | 99/935 [37:59<4:25:17, 19.04s/it]
 11%|█         | 100/935 [38:14<4:10:48, 18.02s/it]
                                                   

 11%|█         | 100/935 [38:14<4:10:48, 18.02s/it]{'eval_loss': 0.7856047749519348, 'eval_runtime': 169.4008, 'eval_samples_per_second': 2.267, 'eval_steps_per_second': 1.133, 'epoch': 0.05}
{'loss': 0.8596, 'grad_norm': 1.2156940698623657, 'learning_rate': 0.00019996933678400946, 'epoch': 0.06}
{'loss': 0.8833, 'grad_norm': 1.3200056552886963, 'learning_rate': 0.00019990989662046818, 'epoch': 0.06}
{'loss': 0.8131, 'grad_norm': 1.5341733694076538, 'learning_rate': 0.00019981919487090972, 'epoch': 0.07}
{'loss': 0.6417, 'grad_norm': 1.1513314247131348, 'learning_rate': 0.00019969725991571128, 'epoch': 0.07}
{'loss': 0.8695, 'grad_norm': 0.8719304800033569, 'learning_rate': 0.00019954412990805107, 'epoch': 0.08}
{'loss': 0.6572, 'grad_norm': 0.7839741706848145, 'learning_rate': 0.0001993598527619703, 'epoch': 0.09}
{'loss': 0.782, 'grad_norm': 0.7421998381614685, 'learning_rate': 0.00019914448613738106, 'epoch': 0.09}
{'loss': 0.7823, 'grad_norm': 0.747768759727478, 'learning_rate': 0.00019889809742202455, 'epoch': 0.1}
{'loss': 0.6102, 'grad_norm': 0.7919906973838806, 'learning_rate': 0.0001986207637103857, 'epoch': 0.1}
{'loss': 0.7222, 'grad_norm': 0.6297110915184021, 'learning_rate': 0.00019831257177957044, 'epoch': 0.11}


  0%|          | 0/192 [00:00<?, ?it/s]

  1%|          | 2/192 [00:00<00:45,  4.15it/s]

  2%|▏         | 3/192 [00:01<01:14,  2.55it/s]

  2%|▏         | 4/192 [00:01<01:21,  2.30it/s]

  3%|▎         | 5/192 [00:01<01:14,  2.52it/s]

  3%|▎         | 6/192 [00:02<01:08,  2.72it/s]

  4%|▎         | 7/192 [00:02<01:06,  2.79it/s]

  5%|▍         | 9/192 [00:03<00:55,  3.28it/s]

  5%|▌         | 10/192 [00:03<01:09,  2.60it/s]

  6%|▌         | 11/192 [00:04<01:17,  2.33it/s]

  6%|▋         | 12/192 [00:04<01:06,  2.69it/s]

  7%|▋         | 13/192 [00:04<01:04,  2.79it/s]

  7%|▋         | 14/192 [00:05<01:11,  2.48it/s]

  8%|▊         | 15/192 [00:05<01:17,  2.29it/s]

  8%|▊         | 16/192 [00:06<01:05,  2.67it/s]

  9%|▉         | 17/192 [00:06<00:51,  3.39it/s]

 10%|▉         | 19/192 [00:06<00:34,  4.98it/s]

 10%|█         | 20/192 [00:06<00:39,  4.41it/s]

 11%|█         | 21/192 [00:07<00:52,  3.26it/s]

 11%|█▏        | 22/192 [00:07<00:50,  3.35it/s]

 12%|█▏        | 23/192 [00:07<00:41,  4.11it/s]

 13%|█▎        | 25/192 [00:07<00:39,  4.24it/s]

 14%|█▎        | 26/192 [00:08<00:52,  3.16it/s]

 14%|█▍        | 27/192 [00:09<01:06,  2.47it/s]

 15%|█▍        | 28/192 [00:09<01:02,  2.64it/s]

 15%|█▌        | 29/192 [00:09<00:59,  2.75it/s]

 16%|█▌        | 30/192 [00:10<01:05,  2.49it/s]

 16%|█▌        | 31/192 [00:10<01:11,  2.25it/s]

 17%|█▋        | 32/192 [00:11<01:13,  2.19it/s]

 17%|█▋        | 33/192 [00:11<01:08,  2.31it/s]

 18%|█▊        | 35/192 [00:11<00:42,  3.70it/s]

 19%|█▉        | 37/192 [00:12<00:35,  4.33it/s]

 20%|█▉        | 38/192 [00:12<00:36,  4.17it/s]

 20%|██        | 39/192 [00:12<00:32,  4.65it/s]

 21%|██        | 40/192 [00:12<00:34,  4.40it/s]

 21%|██▏       | 41/192 [00:13<00:50,  3.02it/s]

 22%|██▏       | 42/192 [00:13<00:50,  2.95it/s]

 22%|██▏       | 43/192 [00:14<00:42,  3.54it/s]

 23%|██▎       | 44/192 [00:14<00:47,  3.12it/s]

 23%|██▎       | 45/192 [00:15<01:02,  2.34it/s]

 24%|██▍       | 46/192 [00:15<00:59,  2.47it/s]

 24%|██▍       | 47/192 [00:15<00:58,  2.47it/s]

 25%|██▌       | 48/192 [00:16<00:54,  2.64it/s]

 26%|██▌       | 49/192 [00:16<00:42,  3.36it/s]

 27%|██▋       | 51/192 [00:16<00:29,  4.84it/s]

 28%|██▊       | 53/192 [00:17<00:30,  4.54it/s]

 28%|██▊       | 54/192 [00:17<00:33,  4.07it/s]

 29%|██▊       | 55/192 [00:17<00:30,  4.56it/s]

 29%|██▉       | 56/192 [00:17<00:36,  3.73it/s]

 30%|██▉       | 57/192 [00:18<00:41,  3.29it/s]

 31%|███       | 59/192 [00:18<00:26,  4.93it/s]

 31%|███▏      | 60/192 [00:18<00:27,  4.83it/s]

 32%|███▏      | 61/192 [00:18<00:28,  4.55it/s]

 32%|███▏      | 62/192 [00:19<00:32,  4.05it/s]

 33%|███▎      | 63/192 [00:19<00:35,  3.63it/s]

 34%|███▍      | 65/192 [00:20<00:33,  3.74it/s]

 34%|███▍      | 66/192 [00:20<00:42,  2.96it/s]

 35%|███▍      | 67/192 [00:21<00:43,  2.89it/s]

 36%|███▌      | 69/192 [00:21<00:34,  3.55it/s]

 36%|███▋      | 70/192 [00:21<00:39,  3.07it/s]

 37%|███▋      | 71/192 [00:22<00:40,  3.00it/s]

 38%|███▊      | 72/192 [00:22<00:40,  2.97it/s]

 38%|███▊      | 73/192 [00:23<00:50,  2.37it/s]

 39%|███▊      | 74/192 [00:23<00:47,  2.48it/s]

 39%|███▉      | 75/192 [00:23<00:37,  3.14it/s]

 40%|███▉      | 76/192 [00:23<00:35,  3.25it/s]

 40%|████      | 77/192 [00:24<00:35,  3.20it/s]

 41%|████      | 79/192 [00:24<00:30,  3.75it/s]

 42%|████▏     | 80/192 [00:25<00:30,  3.71it/s]

 42%|████▏     | 81/192 [00:25<00:32,  3.42it/s]

 43%|████▎     | 82/192 [00:25<00:38,  2.88it/s]

 43%|████▎     | 83/192 [00:26<00:37,  2.87it/s]

 44%|████▍     | 85/192 [00:26<00:24,  4.43it/s]

 45%|████▌     | 87/192 [00:26<00:18,  5.64it/s]

 46%|████▌     | 88/192 [00:27<00:24,  4.22it/s]

 46%|████▋     | 89/192 [00:27<00:28,  3.55it/s]

 47%|████▋     | 90/192 [00:27<00:29,  3.50it/s]

 47%|████▋     | 91/192 [00:28<00:29,  3.42it/s]

 48%|████▊     | 92/192 [00:28<00:31,  3.18it/s]

 48%|████▊     | 93/192 [00:28<00:36,  2.69it/s]

 49%|████▉     | 94/192 [00:29<00:32,  3.01it/s]

 49%|████▉     | 95/192 [00:29<00:26,  3.63it/s]

 51%|█████     | 97/192 [00:29<00:18,  5.23it/s]

 52%|█████▏    | 99/192 [00:29<00:14,  6.52it/s]

 53%|█████▎    | 101/192 [00:29<00:11,  7.87it/s]

 54%|█████▎    | 103/192 [00:30<00:13,  6.56it/s]

 54%|█████▍    | 104/192 [00:30<00:15,  5.69it/s]

 55%|█████▍    | 105/192 [00:30<00:19,  4.40it/s]

 55%|█████▌    | 106/192 [00:31<00:21,  4.01it/s]

 56%|█████▌    | 107/192 [00:31<00:25,  3.35it/s]

 56%|█████▋    | 108/192 [00:32<00:29,  2.84it/s]

 57%|█████▋    | 109/192 [00:32<00:35,  2.31it/s]

 57%|█████▋    | 110/192 [00:33<00:33,  2.42it/s]

 58%|█████▊    | 111/192 [00:33<00:26,  3.03it/s]

 58%|█████▊    | 112/192 [00:33<00:28,  2.85it/s]

 59%|█████▉    | 113/192 [00:34<00:28,  2.73it/s]

 59%|█████▉    | 114/192 [00:34<00:28,  2.75it/s]

 60%|█████▉    | 115/192 [00:34<00:28,  2.74it/s]

 61%|██████    | 117/192 [00:35<00:22,  3.35it/s]

 61%|██████▏   | 118/192 [00:35<00:25,  2.92it/s]

 62%|██████▏   | 119/192 [00:36<00:24,  2.99it/s]

 62%|██████▎   | 120/192 [00:36<00:23,  3.10it/s]

 63%|██████▎   | 121/192 [00:36<00:22,  3.09it/s]

 64%|██████▎   | 122/192 [00:37<00:24,  2.91it/s]

 64%|██████▍   | 123/192 [00:37<00:24,  2.80it/s]

 65%|██████▍   | 124/192 [00:37<00:23,  2.90it/s]

 65%|██████▌   | 125/192 [00:38<00:28,  2.36it/s]

 66%|██████▌   | 126/192 [00:38<00:26,  2.53it/s]

 66%|██████▌   | 127/192 [00:38<00:20,  3.11it/s]

 67%|██████▋   | 129/192 [00:39<00:17,  3.65it/s]

 68%|██████▊   | 130/192 [00:40<00:23,  2.65it/s]

 68%|██████▊   | 131/192 [00:40<00:28,  2.17it/s]

 69%|██████▉   | 132/192 [00:41<00:27,  2.14it/s]

 69%|██████▉   | 133/192 [00:41<00:30,  1.96it/s]

 70%|██████▉   | 134/192 [00:42<00:26,  2.21it/s]

 70%|███████   | 135/192 [00:42<00:26,  2.16it/s]

 71%|███████   | 136/192 [00:43<00:26,  2.12it/s]

 71%|███████▏  | 137/192 [00:43<00:23,  2.39it/s]

 72%|███████▏  | 139/192 [00:43<00:14,  3.72it/s]

 73%|███████▎  | 140/192 [00:43<00:14,  3.55it/s]

 73%|███████▎  | 141/192 [00:44<00:17,  2.88it/s]

 74%|███████▍  | 142/192 [00:44<00:19,  2.56it/s]

 74%|███████▍  | 143/192 [00:45<00:23,  2.08it/s]

 75%|███████▌  | 144/192 [00:46<00:24,  1.93it/s]

 76%|███████▌  | 145/192 [00:46<00:26,  1.80it/s]

 76%|███████▌  | 146/192 [00:47<00:22,  2.06it/s]

 77%|███████▋  | 147/192 [00:47<00:16,  2.68it/s]

 78%|███████▊  | 149/192 [00:47<00:13,  3.08it/s]

 78%|███████▊  | 150/192 [00:48<00:14,  2.99it/s]

 79%|███████▊  | 151/192 [00:48<00:13,  3.06it/s]

 79%|███████▉  | 152/192 [00:49<00:15,  2.58it/s]

 80%|███████▉  | 153/192 [00:50<00:21,  1.83it/s]

 80%|████████  | 154/192 [00:50<00:15,  2.38it/s]

 81%|████████  | 155/192 [00:50<00:16,  2.26it/s]

 81%|████████▏ | 156/192 [00:51<00:17,  2.06it/s]

 82%|████████▏ | 157/192 [00:51<00:15,  2.21it/s]

 82%|████████▏ | 158/192 [00:51<00:13,  2.47it/s]

 83%|████████▎ | 159/192 [00:52<00:15,  2.14it/s]

 83%|████████▎ | 160/192 [00:52<00:13,  2.33it/s]

 84%|████████▍ | 161/192 [00:53<00:12,  2.44it/s]

 84%|████████▍ | 162/192 [00:53<00:13,  2.22it/s]

 85%|████████▍ | 163/192 [00:54<00:14,  1.98it/s]

 85%|████████▌ | 164/192 [00:54<00:13,  2.05it/s]

 86%|████████▌ | 165/192 [00:55<00:11,  2.29it/s]

 86%|████████▋ | 166/192 [00:55<00:10,  2.43it/s]

 87%|████████▋ | 167/192 [00:55<00:09,  2.57it/s]

 88%|████████▊ | 169/192 [00:56<00:07,  3.18it/s]

 89%|████████▊ | 170/192 [00:56<00:07,  3.10it/s]

 89%|████████▉ | 171/192 [00:56<00:05,  3.67it/s]

 90%|████████▉ | 172/192 [00:57<00:05,  3.52it/s]

 90%|█████████ | 173/192 [00:57<00:05,  3.39it/s]

 91%|█████████ | 174/192 [00:57<00:05,  3.18it/s]

 91%|█████████ | 175/192 [00:58<00:05,  3.03it/s]

 92%|█████████▏| 176/192 [00:58<00:05,  2.78it/s]

 92%|█████████▏| 177/192 [00:59<00:06,  2.23it/s]

 93%|█████████▎| 178/192 [00:59<00:06,  2.23it/s]

 93%|█████████▎| 179/192 [01:00<00:06,  2.14it/s]

 94%|█████████▍| 180/192 [01:00<00:05,  2.15it/s]

 94%|█████████▍| 181/192 [01:01<00:05,  2.08it/s]

 95%|█████████▍| 182/192 [01:01<00:04,  2.46it/s]

 95%|█████████▌| 183/192 [01:01<00:03,  2.32it/s]

 96%|█████████▌| 184/192 [01:02<00:03,  2.15it/s]

 96%|█████████▋| 185/192 [01:02<00:03,  2.15it/s]

 97%|█████████▋| 186/192 [01:03<00:02,  2.54it/s]

 97%|█████████▋| 187/192 [01:03<00:01,  2.66it/s]

 98%|█████████▊| 188/192 [01:03<00:01,  2.84it/s]

 98%|█████████▊| 189/192 [01:03<00:00,  3.46it/s]

 99%|█████████▉| 190/192 [01:04<00:00,  3.41it/s]

 99%|█████████▉| 191/192 [01:04<00:00,  3.36it/s]
                                                   

                                                 

 11%|█         | 100/935 [39:19<4:10:48, 18.02s/it]

100%|██████████| 192/192 [01:04<00:00,  3.36it/s]

                                                 wandb: WARNING URL not available in offline run

 11%|█         | 101/935 [39:43<9:02:53, 39.06s/it]
 11%|█         | 102/935 [39:59<7:27:51, 32.26s/it]
 11%|█         | 103/935 [40:18<6:30:06, 28.13s/it]
 11%|█         | 104/935 [41:03<7:43:17, 33.45s/it]
 11%|█         | 105/935 [41:50<8:38:08, 37.46s/it]
                                                   

 11%|█         | 105/935 [41:50<8:38:08, 37.46s/it]
 11%|█▏        | 106/935 [42:20<8:04:25, 35.06s/it]
 11%|█▏        | 107/935 [42:38<6:53:00, 29.93s/it]
 12%|█▏        | 108/935 [42:57<6:10:02, 26.85s/it]
 12%|█▏        | 109/935 [43:17<5:40:19, 24.72s/it]
 12%|█▏        | 110/935 [43:37<5:20:30, 23.31s/it]
                                                   

 12%|█▏        | 110/935 [43:37<5:20:30, 23.31s/it]
 12%|█▏        | 111/935 [44:10<5:59:52, 26.20s/it]
 12%|█▏        | 112/935 [44:30<5:33:46, 24.33s/it]
 12%|█▏        | 113/935 [44:59<5:52:15, 25.71s/it]
 12%|█▏        | 114/935 [45:34<6:31:42, 28.63s/it]
 12%|█▏        | 115/935 [45:53<5:51:24, 25.71s/it]
                                                   

 12%|█▏        | 115/935 [45:53<5:51:24, 25.71s/it]
 12%|█▏        | 116/935 [46:13<5:28:34, 24.07s/it]
 13%|█▎        | 117/935 [46:45<5:59:17, 26.35s/it]
 13%|█▎        | 118/935 [47:16<6:19:02, 27.84s/it]
 13%|█▎        | 119/935 [47:42<6:08:26, 27.09s/it]
 13%|█▎        | 120/935 [48:19<6:47:11, 29.98s/it]
                                                   

 13%|█▎        | 120/935 [48:19<6:47:11, 29.98s/it]
 13%|█▎        | 121/935 [48:38<6:05:06, 26.91s/it]
 13%|█▎        | 122/935 [49:17<6:54:15, 30.57s/it]
 13%|█▎        | 123/935 [49:43<6:34:03, 29.12s/it]
 13%|█▎        | 124/935 [50:09<6:21:25, 28.22s/it]
 13%|█▎        | 125/935 [50:46<6:54:14, 30.68s/it]
                                                   

 13%|█▎        | 125/935 [50:46<6:54:14, 30.68s/it]
 13%|█▎        | 126/935 [51:08<6:21:29, 28.29s/it]
 14%|█▎        | 127/935 [51:41<6:38:02, 29.56s/it]
 14%|█▎        | 128/935 [52:12<6:41:59, 29.89s/it]
 14%|█▍        | 129/935 [52:35<6:15:55, 27.98s/it]
 14%|█▍        | 130/935 [53:03<6:14:00, 27.88s/it]
                                                   

 14%|█▍        | 130/935 [53:03<6:14:00, 27.88s/it]
 14%|█▍        | 131/935 [53:33<6:24:13, 28.67s/it]
 14%|█▍        | 132/935 [54:11<7:02:01, 31.53s/it]
 14%|█▍        | 133/935 [54:30<6:10:47, 27.74s/it]
 14%|█▍        | 134/935 [54:58<6:10:43, 27.77s/it]
 14%|█▍        | 135/935 [55:29<6:23:43, 28.78s/it]
                                                   

 14%|█▍        | 135/935 [55:29<6:23:43, 28.78s/it]
 15%|█▍        | 136/935 [55:58<6:21:10, 28.62s/it]
 15%|█▍        | 137/935 [56:26<6:19:42, 28.55s/it]
 15%|█▍        | 138/935 [56:55<6:19:19, 28.56s/it]
 15%|█▍        | 139/935 [57:28<6:39:47, 30.14s/it]
 15%|█▍        | 140/935 [57:52<6:13:51, 28.22s/it]
                                                   

 15%|█▍        | 140/935 [57:52<6:13:51, 28.22s/it]
 15%|█▌        | 141/935 [58:15<5:50:51, 26.51s/it]
 15%|█▌        | 142/935 [58:43<5:56:16, 26.96s/it]
 15%|█▌        | 143/935 [59:08<5:48:26, 26.40s/it]
 15%|█▌        | 144/935 [59:37<5:57:55, 27.15s/it]
 16%|█▌        | 145/935 [59:50<5:03:45, 23.07s/it]
                                                   

 16%|█▌        | 145/935 [59:50<5:03:45, 23.07s/it]
 16%|█▌        | 146/935 [1:00:27<5:56:19, 27.10s/it]
 16%|█▌        | 147/935 [1:00:51<5:44:01, 26.19s/it]
 16%|█▌        | 148/935 [1:01:22<6:04:14, 27.77s/it]
 16%|█▌        | 149/935 [1:01:53<6:16:30, 28.74s/it]
 16%|█▌        | 150/935 [1:02:19<6:03:38, 27.79s/it]
                                                     

 16%|█▌        | 150/935 [1:02:19<6:03:38, 27.79s/it]{'eval_loss': 0.42398348450660706, 'eval_runtime': 64.9622, 'eval_samples_per_second': 5.911, 'eval_steps_per_second': 2.956, 'epoch': 0.11}
{'loss': 0.6892, 'grad_norm': 0.6574537754058838, 'learning_rate': 0.00019797361806215332, 'epoch': 0.11}
{'loss': 0.6953, 'grad_norm': 0.7165386080741882, 'learning_rate': 0.000197604008616004, 'epoch': 0.12}
{'loss': 0.7986, 'grad_norm': 0.7242662310600281, 'learning_rate': 0.00019720385909110198, 'epoch': 0.12}
{'loss': 0.7409, 'grad_norm': 0.6067697405815125, 'learning_rate': 0.0001967732946933499, 'epoch': 0.13}
{'loss': 0.4524, 'grad_norm': 0.723360002040863, 'learning_rate': 0.00019631245014539698, 'epoch': 0.13}
{'loss': 0.5135, 'grad_norm': 0.7545053362846375, 'learning_rate': 0.0001958214696444846, 'epoch': 0.14}
{'loss': 0.4958, 'grad_norm': 0.5811852812767029, 'learning_rate': 0.0001953005068173272, 'epoch': 0.14}
{'loss': 0.5611, 'grad_norm': 0.7165131568908691, 'learning_rate': 0.00019474972467204297, 'epoch': 0.15}
{'loss': 0.8686, 'grad_norm': 0.8769603371620178, 'learning_rate': 0.00019416929554714888, 'epoch': 0.16}
{'loss': 0.5971, 'grad_norm': 0.6099892258644104, 'learning_rate': 0.0001935594010576362, 'epoch': 0.16}


  0%|          | 0/192 [00:00<?, ?it/s]

  1%|          | 2/192 [00:01<01:39,  1.90it/s]

  2%|▏         | 3/192 [00:02<02:30,  1.25it/s]

  2%|▏         | 4/192 [00:03<02:53,  1.08it/s]

  3%|▎         | 5/192 [00:03<02:30,  1.24it/s]

  3%|▎         | 6/192 [00:04<02:20,  1.32it/s]

  4%|▎         | 7/192 [00:05<02:16,  1.36it/s]

  4%|▍         | 8/192 [00:05<01:44,  1.77it/s]

  5%|▍         | 9/192 [00:06<02:00,  1.51it/s]

  5%|▌         | 10/192 [00:07<02:40,  1.13it/s]

  6%|▌         | 11/192 [00:08<02:53,  1.04it/s]

  6%|▋         | 12/192 [00:09<02:23,  1.25it/s]

  7%|▋         | 13/192 [00:10<02:17,  1.30it/s]

  7%|▋         | 14/192 [00:11<02:37,  1.13it/s]

  8%|▊         | 15/192 [00:12<02:46,  1.07it/s]

  8%|▊         | 16/192 [00:12<02:18,  1.27it/s]

  9%|▉         | 17/192 [00:12<01:47,  1.62it/s]

  9%|▉         | 18/192 [00:13<01:25,  2.04it/s]

 10%|▉         | 19/192 [00:13<01:08,  2.53it/s]

 10%|█         | 20/192 [00:13<01:21,  2.11it/s]

 11%|█         | 21/192 [00:15<01:53,  1.51it/s]

 11%|█▏        | 22/192 [00:15<01:46,  1.60it/s]

 12%|█▏        | 23/192 [00:15<01:21,  2.07it/s]

 12%|█▎        | 24/192 [00:15<01:06,  2.51it/s]

 13%|█▎        | 25/192 [00:16<01:23,  2.00it/s]

 14%|█▎        | 26/192 [00:17<02:00,  1.38it/s]

 14%|█▍        | 27/192 [00:19<02:30,  1.10it/s]

 15%|█▍        | 28/192 [00:19<02:15,  1.21it/s]

 15%|█▌        | 29/192 [00:20<02:07,  1.28it/s]

 16%|█▌        | 30/192 [00:21<02:21,  1.15it/s]

 16%|█▌        | 31/192 [00:22<02:31,  1.06it/s]

 17%|█▋        | 32/192 [00:23<02:36,  1.02it/s]

 17%|█▋        | 33/192 [00:24<02:24,  1.10it/s]

 18%|█▊        | 34/192 [00:24<01:47,  1.47it/s]

 19%|█▉        | 36/192 [00:24<01:05,  2.37it/s]

 19%|█▉        | 37/192 [00:25<01:10,  2.20it/s]

 20%|█▉        | 38/192 [00:26<01:14,  2.06it/s]

 20%|██        | 39/192 [00:26<01:04,  2.38it/s]

 21%|██        | 40/192 [00:26<01:10,  2.15it/s]

 21%|██▏       | 41/192 [00:28<01:45,  1.43it/s]

 22%|██▏       | 42/192 [00:28<01:49,  1.37it/s]

 22%|██▏       | 43/192 [00:29<01:27,  1.70it/s]

 23%|██▎       | 44/192 [00:30<01:40,  1.47it/s]

 23%|██▎       | 45/192 [00:31<02:13,  1.10it/s]

 24%|██▍       | 46/192 [00:32<02:05,  1.16it/s]

 24%|██▍       | 47/192 [00:33<02:04,  1.16it/s]

 25%|██▌       | 48/192 [00:33<01:55,  1.25it/s]

 26%|██▌       | 49/192 [00:34<01:29,  1.60it/s]

 26%|██▌       | 50/192 [00:34<01:10,  2.01it/s]

 27%|██▋       | 51/192 [00:34<00:58,  2.41it/s]

 27%|██▋       | 52/192 [00:34<00:47,  2.92it/s]

 28%|██▊       | 53/192 [00:35<01:08,  2.02it/s]

 28%|██▊       | 54/192 [00:36<01:18,  1.76it/s]

 29%|██▊       | 55/192 [00:36<01:04,  2.13it/s]

 29%|██▉       | 56/192 [00:37<01:21,  1.66it/s]

 30%|██▉       | 57/192 [00:38<01:30,  1.49it/s]

 30%|███       | 58/192 [00:38<01:08,  1.95it/s]

 31%|███       | 59/192 [00:38<00:52,  2.53it/s]

 31%|███▏      | 60/192 [00:38<00:56,  2.35it/s]

 32%|███▏      | 61/192 [00:39<00:59,  2.21it/s]

 32%|███▏      | 62/192 [00:40<01:08,  1.90it/s]

 33%|███▎      | 63/192 [00:40<01:15,  1.70it/s]

 33%|███▎      | 64/192 [00:41<01:00,  2.10it/s]

 34%|███▍      | 65/192 [00:42<01:15,  1.68it/s]

 34%|███▍      | 66/192 [00:43<01:40,  1.25it/s]

 35%|███▍      | 67/192 [00:43<01:36,  1.30it/s]

 35%|███▌      | 68/192 [00:44<01:12,  1.70it/s]

 36%|███▌      | 69/192 [00:44<01:15,  1.63it/s]

 36%|███▋      | 70/192 [00:45<01:30,  1.35it/s]

 37%|███▋      | 71/192 [00:46<01:27,  1.38it/s]

 38%|███▊      | 72/192 [00:47<01:27,  1.38it/s]

 38%|███▊      | 73/192 [00:48<01:48,  1.10it/s]

 39%|███▊      | 74/192 [00:49<01:40,  1.17it/s]

 39%|███▉      | 75/192 [00:49<01:15,  1.55it/s]

 40%|███▉      | 76/192 [00:50<01:12,  1.59it/s]

 40%|████      | 77/192 [00:50<01:12,  1.58it/s]

 41%|████      | 78/192 [00:50<00:57,  1.98it/s]

 41%|████      | 79/192 [00:51<01:03,  1.77it/s]

 42%|████▏     | 80/192 [00:52<01:05,  1.72it/s]

 42%|████▏     | 81/192 [00:52<01:09,  1.61it/s]

 43%|████▎     | 82/192 [00:54<01:23,  1.32it/s]

 43%|████▎     | 83/192 [00:54<01:18,  1.39it/s]

 44%|████▍     | 84/192 [00:54<00:58,  1.85it/s]

 44%|████▍     | 85/192 [00:54<00:46,  2.30it/s]

 45%|████▍     | 86/192 [00:55<00:38,  2.74it/s]

 45%|████▌     | 87/192 [00:55<00:34,  3.05it/s]

 46%|████▌     | 88/192 [00:56<00:54,  1.91it/s]

 46%|████▋     | 89/192 [00:57<01:04,  1.59it/s]

 47%|████▋     | 90/192 [00:57<01:04,  1.58it/s]

 47%|████▋     | 91/192 [00:58<01:04,  1.57it/s]

 48%|████▊     | 92/192 [00:59<01:08,  1.47it/s]

 48%|████▊     | 93/192 [01:00<01:19,  1.25it/s]

 49%|████▉     | 94/192 [01:00<01:10,  1.40it/s]

 49%|████▉     | 95/192 [01:01<00:56,  1.73it/s]

 50%|█████     | 96/192 [01:01<00:43,  2.19it/s]

 51%|█████     | 97/192 [01:01<00:36,  2.61it/s]

 51%|█████     | 98/192 [01:01<00:30,  3.10it/s]

 52%|█████▏    | 99/192 [01:02<00:27,  3.40it/s]

 52%|█████▏    | 100/192 [01:02<00:23,  3.97it/s]

 53%|█████▎    | 101/192 [01:02<00:22,  4.08it/s]

 53%|█████▎    | 102/192 [01:02<00:18,  4.77it/s]

 54%|█████▎    | 103/192 [01:03<00:31,  2.84it/s]

 54%|█████▍    | 104/192 [01:03<00:37,  2.34it/s]

 55%|█████▍    | 105/192 [01:04<00:47,  1.81it/s]

 55%|█████▌    | 106/192 [01:05<00:50,  1.69it/s]

 56%|█████▌    | 107/192 [01:06<00:58,  1.44it/s]

 56%|█████▋    | 108/192 [01:07<01:09,  1.22it/s]

 57%|█████▋    | 109/192 [01:08<01:21,  1.02it/s]

 57%|█████▋    | 110/192 [01:09<01:15,  1.08it/s]

 58%|█████▊    | 111/192 [01:09<00:57,  1.41it/s]

 58%|█████▊    | 112/192 [01:10<00:59,  1.34it/s]

 59%|█████▉    | 113/192 [01:11<01:01,  1.29it/s]

 59%|█████▉    | 114/192 [01:12<01:00,  1.30it/s]

 60%|█████▉    | 115/192 [01:12<00:58,  1.31it/s]

 60%|██████    | 116/192 [01:13<00:43,  1.73it/s]

 61%|██████    | 117/192 [01:13<00:47,  1.56it/s]

 61%|██████▏   | 118/192 [01:14<00:56,  1.31it/s]

 62%|██████▏   | 119/192 [01:15<00:51,  1.42it/s]

 62%|██████▎   | 120/192 [01:16<00:48,  1.49it/s]

 63%|██████▎   | 121/192 [01:16<00:47,  1.49it/s]

 64%|██████▎   | 122/192 [01:17<00:51,  1.37it/s]

 64%|██████▍   | 123/192 [01:18<00:52,  1.32it/s]

 65%|██████▍   | 124/192 [01:19<00:50,  1.36it/s]

 65%|██████▌   | 125/192 [01:20<01:00,  1.10it/s]

 66%|██████▌   | 126/192 [01:21<00:56,  1.16it/s]

 66%|██████▌   | 127/192 [01:21<00:44,  1.47it/s]

 67%|██████▋   | 128/192 [01:21<00:34,  1.87it/s]

 67%|██████▋   | 129/192 [01:22<00:37,  1.68it/s]

 68%|██████▊   | 130/192 [01:23<00:54,  1.14it/s]

 68%|██████▊   | 131/192 [01:25<01:03,  1.04s/it]

 69%|██████▉   | 132/192 [01:26<01:02,  1.04s/it]

 69%|██████▉   | 133/192 [01:27<01:04,  1.10s/it]

 70%|██████▉   | 134/192 [01:28<00:55,  1.04it/s]

 70%|███████   | 135/192 [01:29<00:55,  1.03it/s]

 71%|███████   | 136/192 [01:30<00:56,  1.01s/it]

 71%|███████▏  | 137/192 [01:30<00:47,  1.15it/s]

 72%|███████▏  | 138/192 [01:31<00:35,  1.51it/s]

 72%|███████▏  | 139/192 [01:31<00:27,  1.91it/s]

 73%|███████▎  | 140/192 [01:31<00:29,  1.74it/s]

 73%|███████▎  | 141/192 [01:33<00:37,  1.36it/s]

 74%|███████▍  | 142/192 [01:34<00:42,  1.18it/s]

 74%|███████▍  | 143/192 [01:35<00:50,  1.04s/it]

 75%|███████▌  | 144/192 [01:37<00:54,  1.14s/it]

 76%|███████▌  | 145/192 [01:38<00:56,  1.19s/it]

 76%|███████▌  | 146/192 [01:38<00:47,  1.03s/it]

 77%|███████▋  | 147/192 [01:39<00:34,  1.30it/s]

 77%|███████▋  | 148/192 [01:39<00:26,  1.68it/s]

 78%|███████▊  | 149/192 [01:40<00:30,  1.42it/s]

 78%|███████▊  | 150/192 [01:41<00:30,  1.36it/s]

 79%|███████▊  | 151/192 [01:41<00:28,  1.43it/s]

 79%|███████▉  | 152/192 [01:42<00:34,  1.18it/s]

 80%|███████▉  | 153/192 [01:44<00:40,  1.05s/it]

 80%|████████  | 154/192 [01:45<00:36,  1.04it/s]

 81%|████████  | 155/192 [01:46<00:36,  1.03it/s]

 81%|████████▏ | 156/192 [01:47<00:38,  1.08s/it]

 82%|████████▏ | 157/192 [01:48<00:33,  1.03it/s]

 82%|████████▏ | 158/192 [01:48<00:29,  1.15it/s]

 83%|████████▎ | 159/192 [01:50<00:32,  1.01it/s]

 83%|████████▎ | 160/192 [01:50<00:28,  1.11it/s]

 84%|████████▍ | 161/192 [01:51<00:26,  1.17it/s]

 84%|████████▍ | 162/192 [01:52<00:28,  1.04it/s]

 85%|████████▍ | 163/192 [01:54<00:30,  1.06s/it]

 85%|████████▌ | 164/192 [01:55<00:29,  1.04s/it]

 86%|████████▌ | 165/192 [01:55<00:24,  1.11it/s]

 86%|████████▋ | 166/192 [01:56<00:22,  1.16it/s]

 87%|████████▋ | 167/192 [01:57<00:20,  1.24it/s]

 88%|████████▊ | 169/192 [01:58<00:15,  1.53it/s]

 89%|████████▊ | 170/192 [01:58<00:14,  1.48it/s]

 89%|████████▉ | 171/192 [01:59<00:11,  1.77it/s]

 90%|████████▉ | 172/192 [01:59<00:11,  1.67it/s]

 90%|█████████ | 173/192 [02:00<00:11,  1.61it/s]

 91%|█████████ | 174/192 [02:01<00:11,  1.51it/s]

 91%|█████████ | 175/192 [02:01<00:11,  1.46it/s]

 92%|█████████▏| 176/192 [02:02<00:12,  1.33it/s]

 92%|█████████▏| 177/192 [02:04<00:14,  1.07it/s]

 93%|█████████▎| 178/192 [02:05<00:13,  1.05it/s]

 93%|█████████▎| 179/192 [02:06<00:12,  1.04it/s]

 94%|█████████▍| 180/192 [02:07<00:11,  1.02it/s]

 94%|█████████▍| 181/192 [02:08<00:11,  1.03s/it]

 95%|█████████▍| 182/192 [02:08<00:08,  1.16it/s]

 95%|█████████▌| 183/192 [02:09<00:08,  1.09it/s]

 96%|█████████▌| 184/192 [02:11<00:08,  1.01s/it]

 96%|█████████▋| 185/192 [02:12<00:06,  1.01it/s]

 97%|█████████▋| 186/192 [02:12<00:04,  1.21it/s]

 97%|█████████▋| 187/192 [02:13<00:03,  1.27it/s]

 98%|█████████▊| 188/192 [02:13<00:02,  1.35it/s]

 98%|█████████▊| 189/192 [02:14<00:01,  1.67it/s]

 99%|█████████▉| 190/192 [02:14<00:01,  1.62it/s]

 99%|█████████▉| 191/192 [02:15<00:00,  1.61it/s]

100%|██████████| 192/192 [02:15<00:00,  2.03it/s]
                                                     

                                                 

 16%|█▌        | 150/935 [1:04:35<6:03:38, 27.79s/it]

100%|██████████| 192/192 [02:15<00:00,  2.03it/s]

                                                 
 16%|█▌        | 151/935 [1:05:10<15:26:37, 70.91s/it]
 16%|█▋        | 152/935 [1:05:43<12:55:36, 59.43s/it]
 16%|█▋        | 153/935 [1:06:08<10:41:38, 49.23s/it]
 16%|█▋        | 154/935 [1:06:24<8:30:10, 39.19s/it] 
 17%|█▋        | 155/935 [1:06:47<7:27:14, 34.40s/it]
                                                     

 17%|█▋        | 155/935 [1:06:47<7:27:14, 34.40s/it]
 17%|█▋        | 156/935 [1:07:07<6:30:34, 30.08s/it]
 17%|█▋        | 157/935 [1:07:29<5:57:38, 27.58s/it]
 17%|█▋        | 158/935 [1:07:47<5:19:49, 24.70s/it]
 17%|█▋        | 159/935 [1:07:59<4:29:01, 20.80s/it]
 17%|█▋        | 160/935 [1:08:17<4:18:43, 20.03s/it]
                                                     

 17%|█▋        | 160/935 [1:08:17<4:18:43, 20.03s/it]
 17%|█▋        | 161/935 [1:08:35<4:09:48, 19.36s/it]
 17%|█▋        | 162/935 [1:08:54<4:08:41, 19.30s/it]
 17%|█▋        | 163/935 [1:09:10<3:56:14, 18.36s/it]
 18%|█▊        | 164/935 [1:09:28<3:52:08, 18.07s/it]
 18%|█▊        | 165/935 [1:09:39<3:25:56, 16.05s/it]
                                                     

 18%|█▊        | 165/935 [1:09:39<3:25:56, 16.05s/it]
 18%|█▊        | 166/935 [1:09:52<3:15:18, 15.24s/it]
 18%|█▊        | 167/935 [1:10:08<3:15:42, 15.29s/it]
 18%|█▊        | 168/935 [1:10:31<3:44:42, 17.58s/it]
 18%|█▊        | 169/935 [1:10:45<3:33:01, 16.69s/it]
 18%|█▊        | 170/935 [1:10:58<3:18:28, 15.57s/it]
                                                     

 18%|█▊        | 170/935 [1:10:58<3:18:28, 15.57s/it]
 18%|█▊        | 171/935 [1:11:14<3:21:14, 15.80s/it]
 18%|█▊        | 172/935 [1:11:36<3:41:10, 17.39s/it]
 19%|█▊        | 173/935 [1:11:57<3:57:10, 18.68s/it]
 19%|█▊        | 174/935 [1:12:12<3:40:15, 17.37s/it]
 19%|█▊        | 175/935 [1:12:31<3:46:31, 17.88s/it]
                                                     

 19%|█▊        | 175/935 [1:12:31<3:46:31, 17.88s/it]
 19%|█▉        | 176/935 [1:12:41<3:18:28, 15.69s/it]
 19%|█▉        | 177/935 [1:12:56<3:16:02, 15.52s/it]
 19%|█▉        | 178/935 [1:13:07<2:56:16, 13.97s/it]
 19%|█▉        | 179/935 [1:13:18<2:46:08, 13.19s/it]
 19%|█▉        | 180/935 [1:13:35<3:00:35, 14.35s/it]
                                                     

 19%|█▉        | 180/935 [1:13:35<3:00:35, 14.35s/it]
 19%|█▉        | 181/935 [1:13:52<3:09:35, 15.09s/it]
 19%|█▉        | 182/935 [1:14:06<3:06:01, 14.82s/it]
 20%|█▉        | 183/935 [1:14:21<3:04:38, 14.73s/it]
 20%|█▉        | 184/935 [1:14:34<3:00:08, 14.39s/it]
 20%|█▉        | 185/935 [1:14:50<3:06:36, 14.93s/it]
                                                     

 20%|█▉        | 185/935 [1:14:50<3:06:36, 14.93s/it]
 20%|█▉        | 186/935 [1:15:06<3:08:22, 15.09s/it]
 20%|██        | 187/935 [1:15:22<3:10:11, 15.26s/it]
 20%|██        | 188/935 [1:15:33<2:55:32, 14.10s/it]
 20%|██        | 189/935 [1:15:44<2:42:14, 13.05s/it]
 20%|██        | 190/935 [1:16:02<3:01:02, 14.58s/it]
                                                     

 20%|██        | 190/935 [1:16:02<3:01:02, 14.58s/it]
 20%|██        | 191/935 [1:16:19<3:11:24, 15.44s/it]
 21%|██        | 192/935 [1:16:36<3:17:16, 15.93s/it]
 21%|██        | 193/935 [1:16:47<2:58:33, 14.44s/it]
 21%|██        | 194/935 [1:17:00<2:52:22, 13.96s/it]
 21%|██        | 195/935 [1:17:17<3:02:07, 14.77s/it]
                                                     

 21%|██        | 195/935 [1:17:17<3:02:07, 14.77s/it]
 21%|██        | 196/935 [1:17:33<3:07:18, 15.21s/it]
 21%|██        | 197/935 [1:17:49<3:08:56, 15.36s/it]
 21%|██        | 198/935 [1:18:06<3:14:20, 15.82s/it]
 21%|██▏       | 199/935 [1:18:24<3:22:51, 16.54s/it]
 21%|██▏       | 200/935 [1:18:43<3:32:17, 17.33s/it]
                                                     

 21%|██▏       | 200/935 [1:18:43<3:32:17, 17.33s/it]{'eval_loss': 0.37071776390075684, 'eval_runtime': 136.3832, 'eval_samples_per_second': 2.816, 'eval_steps_per_second': 1.408, 'epoch': 0.16}
{'loss': 0.5999, 'grad_norm': 0.6321601867675781, 'learning_rate': 0.000192920232038144, 'epoch': 0.17}
{'loss': 0.6562, 'grad_norm': 0.6136798858642578, 'learning_rate': 0.0001922519884832469, 'epoch': 0.17}
{'loss': 0.533, 'grad_norm': 0.6746335625648499, 'learning_rate': 0.00019155487948487748, 'epoch': 0.18}
{'loss': 0.7409, 'grad_norm': 0.766614556312561, 'learning_rate': 0.0001908291231669019, 'epoch': 0.18}
{'loss': 0.4672, 'grad_norm': 0.5589352250099182, 'learning_rate': 0.00019007494661686935, 'epoch': 0.19}
{'loss': 0.5064, 'grad_norm': 0.59783935546875, 'learning_rate': 0.00018929258581495685, 'epoch': 0.19}
{'loss': 0.6937, 'grad_norm': 0.6479551792144775, 'learning_rate': 0.0001884822855601316, 'epoch': 0.2}
{'loss': 0.5394, 'grad_norm': 0.6843699812889099, 'learning_rate': 0.00018764429939355392, 'epoch': 0.2}
{'loss': 0.7568, 'grad_norm': 0.5675429105758667, 'learning_rate': 0.00018677888951924474, 'epoch': 0.21}
{'loss': 0.4871, 'grad_norm': 0.659488320350647, 'learning_rate': 0.00018588632672204264, 'epoch': 0.21}


  0%|          | 0/192 [00:00<?, ?it/s]

  1%|          | 2/192 [00:00<00:45,  4.16it/s]

  2%|▏         | 3/192 [00:01<01:13,  2.56it/s]

  2%|▏         | 4/192 [00:01<01:21,  2.30it/s]

  3%|▎         | 5/192 [00:01<01:14,  2.52it/s]

  3%|▎         | 6/192 [00:02<01:08,  2.72it/s]

  4%|▎         | 7/192 [00:02<01:06,  2.79it/s]

  5%|▍         | 9/192 [00:03<00:55,  3.29it/s]

  5%|▌         | 10/192 [00:03<01:09,  2.61it/s]

  6%|▌         | 11/192 [00:04<01:17,  2.34it/s]

  6%|▋         | 12/192 [00:04<01:06,  2.72it/s]

  7%|▋         | 13/192 [00:04<01:03,  2.81it/s]

  7%|▋         | 14/192 [00:05<01:11,  2.49it/s]

  8%|▊         | 15/192 [00:05<01:17,  2.29it/s]

  8%|▊         | 16/192 [00:06<01:05,  2.68it/s]

  9%|▉         | 18/192 [00:06<00:41,  4.15it/s]

 10%|▉         | 19/192 [00:06<00:35,  4.81it/s]

 10%|█         | 20/192 [00:06<00:40,  4.28it/s]

 11%|█         | 21/192 [00:07<00:53,  3.17it/s]

 11%|█▏        | 22/192 [00:07<00:51,  3.31it/s]

 12%|█▏        | 23/192 [00:07<00:41,  4.08it/s]

 13%|█▎        | 25/192 [00:07<00:39,  4.24it/s]

 14%|█▎        | 26/192 [00:08<00:52,  3.16it/s]

 14%|█▍        | 27/192 [00:09<01:07,  2.46it/s]

 15%|█▍        | 28/192 [00:09<01:02,  2.64it/s]

 15%|█▌        | 29/192 [00:09<00:59,  2.75it/s]

 16%|█▌        | 30/192 [00:10<01:05,  2.49it/s]

 16%|█▌        | 31/192 [00:10<01:11,  2.24it/s]

 17%|█▋        | 32/192 [00:11<01:13,  2.18it/s]

 17%|█▋        | 33/192 [00:11<01:09,  2.30it/s]

 18%|█▊        | 35/192 [00:11<00:42,  3.68it/s]

 19%|█▉        | 37/192 [00:12<00:35,  4.32it/s]

 20%|█▉        | 38/192 [00:12<00:37,  4.16it/s]

 20%|██        | 39/192 [00:12<00:33,  4.63it/s]

 21%|██        | 40/192 [00:12<00:34,  4.39it/s]

 21%|██▏       | 41/192 [00:13<00:49,  3.02it/s]

 22%|██▏       | 42/192 [00:13<00:50,  2.95it/s]

 22%|██▏       | 43/192 [00:14<00:42,  3.50it/s]

 23%|██▎       | 44/192 [00:14<00:47,  3.09it/s]

 23%|██▎       | 45/192 [00:15<01:03,  2.31it/s]

 24%|██▍       | 46/192 [00:15<00:59,  2.46it/s]

 24%|██▍       | 47/192 [00:15<00:59,  2.45it/s]

 25%|██▌       | 48/192 [00:16<00:54,  2.62it/s]

 26%|██▌       | 49/192 [00:16<00:43,  3.31it/s]

 27%|██▋       | 51/192 [00:16<00:29,  4.79it/s]

 28%|██▊       | 53/192 [00:17<00:30,  4.51it/s]

 28%|██▊       | 54/192 [00:17<00:33,  4.07it/s]

 29%|██▊       | 55/192 [00:17<00:30,  4.53it/s]

 29%|██▉       | 56/192 [00:17<00:36,  3.71it/s]

 30%|██▉       | 57/192 [00:18<00:41,  3.28it/s]

 31%|███       | 59/192 [00:18<00:26,  4.93it/s]

 31%|███▏      | 60/192 [00:18<00:27,  4.82it/s]

 32%|███▏      | 61/192 [00:18<00:28,  4.55it/s]

 32%|███▏      | 62/192 [00:19<00:32,  4.03it/s]

 33%|███▎      | 63/192 [00:19<00:35,  3.61it/s]

 34%|███▍      | 65/192 [00:20<00:34,  3.72it/s]

 34%|███▍      | 66/192 [00:20<00:42,  2.95it/s]

 35%|███▍      | 67/192 [00:21<00:43,  2.89it/s]

 36%|███▌      | 69/192 [00:21<00:34,  3.54it/s]

 36%|███▋      | 70/192 [00:21<00:39,  3.06it/s]

 37%|███▋      | 71/192 [00:22<00:40,  2.98it/s]

 38%|███▊      | 72/192 [00:22<00:40,  2.96it/s]

 38%|███▊      | 73/192 [00:23<00:50,  2.36it/s]

 39%|███▊      | 74/192 [00:23<00:47,  2.47it/s]

 39%|███▉      | 75/192 [00:23<00:37,  3.12it/s]

 40%|███▉      | 76/192 [00:24<00:35,  3.23it/s]

 40%|████      | 77/192 [00:24<00:35,  3.21it/s]

 41%|████      | 79/192 [00:24<00:30,  3.72it/s]

 42%|████▏     | 80/192 [00:25<00:30,  3.68it/s]

 42%|████▏     | 81/192 [00:25<00:32,  3.40it/s]

 43%|████▎     | 82/192 [00:25<00:38,  2.88it/s]

 43%|████▎     | 83/192 [00:26<00:38,  2.86it/s]

 44%|████▍     | 85/192 [00:26<00:24,  4.39it/s]

 45%|████▌     | 87/192 [00:26<00:18,  5.65it/s]

 46%|████▌     | 88/192 [00:27<00:24,  4.20it/s]

 46%|████▋     | 89/192 [00:27<00:41,  2.48it/s]

 47%|████▋     | 90/192 [00:28<00:38,  2.68it/s]

 47%|████▋     | 91/192 [00:28<00:36,  2.78it/s]

 48%|████▊     | 92/192 [00:28<00:36,  2.75it/s]

 48%|████▊     | 93/192 [00:29<00:40,  2.46it/s]

 49%|████▉     | 94/192 [00:29<00:34,  2.80it/s]

 49%|████▉     | 95/192 [00:29<00:28,  3.42it/s]

 51%|█████     | 97/192 [00:30<00:19,  5.00it/s]

 52%|█████▏    | 99/192 [00:30<00:14,  6.30it/s]

 53%|█████▎    | 101/192 [00:30<00:11,  7.67it/s]

 54%|█████▎    | 103/192 [00:30<00:13,  6.49it/s]

 54%|█████▍    | 104/192 [00:31<00:15,  5.64it/s]

 55%|█████▍    | 105/192 [00:31<00:19,  4.36it/s]

 55%|█████▌    | 106/192 [00:31<00:21,  3.96it/s]

 56%|█████▌    | 107/192 [00:32<00:25,  3.34it/s]

 56%|█████▋    | 108/192 [00:32<00:29,  2.84it/s]

 57%|█████▋    | 109/192 [00:33<00:36,  2.30it/s]

 57%|█████▋    | 110/192 [00:33<00:33,  2.41it/s]

 58%|█████▊    | 111/192 [00:33<00:26,  3.02it/s]

 58%|█████▊    | 112/192 [00:34<00:28,  2.85it/s]

 59%|█████▉    | 113/192 [00:34<00:28,  2.73it/s]

 59%|█████▉    | 114/192 [00:35<00:28,  2.76it/s]

 60%|█████▉    | 115/192 [00:35<00:28,  2.75it/s]

 61%|██████    | 117/192 [00:35<00:22,  3.36it/s]

 61%|██████▏   | 118/192 [00:36<00:25,  2.93it/s]

 62%|██████▏   | 119/192 [00:36<00:24,  3.00it/s]

 62%|██████▎   | 120/192 [00:36<00:23,  3.10it/s]

 63%|██████▎   | 121/192 [00:37<00:22,  3.09it/s]

 64%|██████▎   | 122/192 [00:37<00:24,  2.91it/s]

 64%|██████▍   | 123/192 [00:38<00:24,  2.80it/s]

 65%|██████▍   | 124/192 [00:38<00:23,  2.90it/s]

 65%|██████▌   | 125/192 [00:38<00:28,  2.37it/s]

 66%|██████▌   | 126/192 [00:39<00:25,  2.54it/s]

 66%|██████▌   | 127/192 [00:39<00:20,  3.12it/s]

 67%|██████▋   | 129/192 [00:39<00:17,  3.65it/s]

 68%|██████▊   | 130/192 [00:40<00:23,  2.65it/s]

 68%|██████▊   | 131/192 [00:41<00:28,  2.16it/s]

 69%|██████▉   | 132/192 [00:41<00:27,  2.14it/s]

 69%|██████▉   | 133/192 [00:42<00:30,  1.96it/s]

 70%|██████▉   | 134/192 [00:42<00:26,  2.21it/s]

 70%|███████   | 135/192 [00:43<00:29,  1.90it/s]

 71%|███████   | 136/192 [00:43<00:28,  1.94it/s]

 71%|███████▏  | 137/192 [00:44<00:24,  2.22it/s]

 72%|███████▏  | 139/192 [00:44<00:15,  3.49it/s]

 73%|███████▎  | 140/192 [00:44<00:15,  3.39it/s]

 73%|███████▎  | 141/192 [00:45<00:18,  2.79it/s]

 74%|███████▍  | 142/192 [00:45<00:19,  2.52it/s]

 74%|███████▍  | 143/192 [00:46<00:24,  2.02it/s]

 75%|███████▌  | 144/192 [00:47<00:24,  1.92it/s]

 76%|███████▌  | 145/192 [00:47<00:26,  1.79it/s]

 76%|███████▌  | 146/192 [00:47<00:22,  2.05it/s]

 77%|███████▋  | 147/192 [00:48<00:16,  2.66it/s]

 78%|███████▊  | 149/192 [00:48<00:14,  3.06it/s]

 78%|███████▊  | 150/192 [00:49<00:14,  2.97it/s]

 79%|███████▊  | 151/192 [00:49<00:13,  3.03it/s]

 79%|███████▉  | 152/192 [00:49<00:15,  2.58it/s]

 80%|███████▉  | 153/192 [00:50<00:18,  2.08it/s]

 80%|████████  | 154/192 [00:50<00:16,  2.29it/s]

 81%|████████  | 155/192 [00:51<00:16,  2.21it/s]

 81%|████████▏ | 156/192 [00:51<00:17,  2.03it/s]

 82%|████████▏ | 157/192 [00:52<00:15,  2.20it/s]

 82%|████████▏ | 158/192 [00:52<00:13,  2.45it/s]

 83%|████████▎ | 159/192 [00:53<00:15,  2.14it/s]

 83%|████████▎ | 160/192 [00:53<00:13,  2.32it/s]

 84%|████████▍ | 161/192 [00:53<00:12,  2.44it/s]

 84%|████████▍ | 162/192 [00:54<00:13,  2.22it/s]

 85%|████████▍ | 163/192 [00:55<00:14,  1.99it/s]

 85%|████████▌ | 164/192 [00:55<00:13,  2.05it/s]

 86%|████████▌ | 165/192 [00:55<00:11,  2.29it/s]

 86%|████████▋ | 166/192 [00:56<00:10,  2.43it/s]

 87%|████████▋ | 167/192 [00:56<00:09,  2.57it/s]

 88%|████████▊ | 169/192 [00:57<00:07,  3.19it/s]

 89%|████████▊ | 170/192 [00:57<00:07,  3.11it/s]

 89%|████████▉ | 171/192 [00:57<00:05,  3.67it/s]

 90%|████████▉ | 172/192 [00:57<00:05,  3.52it/s]

 90%|█████████ | 173/192 [00:58<00:05,  3.39it/s]

 91%|█████████ | 174/192 [00:58<00:05,  3.18it/s]

 91%|█████████ | 175/192 [00:58<00:05,  3.04it/s]

 92%|█████████▏| 176/192 [00:59<00:05,  2.77it/s]

 92%|█████████▏| 177/192 [00:59<00:06,  2.24it/s]

 93%|█████████▎| 178/192 [01:00<00:06,  2.23it/s]

 93%|█████████▎| 179/192 [01:00<00:06,  2.13it/s]

 94%|█████████▍| 180/192 [01:01<00:05,  2.15it/s]

 94%|█████████▍| 181/192 [01:01<00:05,  2.08it/s]

 95%|█████████▍| 182/192 [01:02<00:04,  2.47it/s]

 95%|█████████▌| 183/192 [01:02<00:03,  2.32it/s]

 96%|█████████▌| 184/192 [01:03<00:03,  2.15it/s]

 96%|█████████▋| 185/192 [01:03<00:03,  2.16it/s]

 97%|█████████▋| 186/192 [01:03<00:02,  2.55it/s]

 97%|█████████▋| 187/192 [01:04<00:01,  2.66it/s]

 98%|█████████▊| 188/192 [01:04<00:01,  2.86it/s]

 98%|█████████▊| 189/192 [01:04<00:00,  3.49it/s]

 99%|█████████▉| 190/192 [01:04<00:00,  3.42it/s]

 99%|█████████▉| 191/192 [01:05<00:00,  3.39it/s]
                                                     

                                                 

 21%|██▏       | 200/935 [1:19:49<3:32:17, 17.33s/it]

100%|██████████| 192/192 [01:05<00:00,  3.39it/s]

                                                 wandb: WARNING URL not available in offline run

 21%|██▏       | 201/935 [1:20:15<8:05:14, 39.67s/it]
 22%|██▏       | 202/935 [1:20:39<7:07:05, 34.96s/it]
 22%|██▏       | 203/935 [1:21:06<6:39:17, 32.73s/it]
 22%|██▏       | 204/935 [1:21:32<6:14:08, 30.71s/it]
 22%|██▏       | 205/935 [1:22:03<6:13:50, 30.73s/it]
                                                     

 22%|██▏       | 205/935 [1:22:03<6:13:50, 30.73s/it]
 22%|██▏       | 206/935 [1:22:22<5:31:47, 27.31s/it]
 22%|██▏       | 207/935 [1:22:40<4:55:09, 24.33s/it]
 22%|██▏       | 208/935 [1:22:53<4:16:29, 21.17s/it]
 22%|██▏       | 209/935 [1:23:18<4:29:57, 22.31s/it]
 22%|██▏       | 210/935 [1:23:48<4:54:27, 24.37s/it]
                                                     

 22%|██▏       | 210/935 [1:23:48<4:54:27, 24.37s/it]
 23%|██▎       | 211/935 [1:24:24<5:38:35, 28.06s/it]
 23%|██▎       | 212/935 [1:24:47<5:17:07, 26.32s/it]
 23%|██▎       | 213/935 [1:25:24<5:56:57, 29.66s/it]
 23%|██▎       | 214/935 [1:25:45<5:26:06, 27.14s/it]
 23%|██▎       | 215/935 [1:26:14<5:31:44, 27.64s/it]
                                                     

 23%|██▎       | 215/935 [1:26:14<5:31:44, 27.64s/it]
 23%|██▎       | 216/935 [1:26:44<5:38:46, 28.27s/it]
 23%|██▎       | 217/935 [1:27:13<5:40:56, 28.49s/it]
 23%|██▎       | 218/935 [1:27:39<5:30:50, 27.69s/it]
 23%|██▎       | 219/935 [1:28:05<5:26:46, 27.38s/it]
 24%|██▎       | 220/935 [1:28:25<4:58:05, 25.01s/it]
                                                     

 24%|██▎       | 220/935 [1:28:25<4:58:05, 25.01s/it]
 24%|██▎       | 221/935 [1:28:50<4:59:47, 25.19s/it]
 24%|██▎       | 222/935 [1:29:23<5:27:07, 27.53s/it]
 24%|██▍       | 223/935 [1:29:47<5:14:32, 26.51s/it]
 24%|██▍       | 224/935 [1:30:23<5:45:55, 29.19s/it]
 24%|██▍       | 225/935 [1:30:44<5:16:34, 26.75s/it]
                                                     

 24%|██▍       | 225/935 [1:30:44<5:16:34, 26.75s/it]
 24%|██▍       | 226/935 [1:31:05<4:55:42, 25.02s/it]
 24%|██▍       | 227/935 [1:31:36<5:15:49, 26.76s/it]
 24%|██▍       | 228/935 [1:31:57<4:55:34, 25.08s/it]
 24%|██▍       | 229/935 [1:32:22<4:54:50, 25.06s/it]
 25%|██▍       | 230/935 [1:32:54<5:20:20, 27.26s/it]
                                                     

 25%|██▍       | 230/935 [1:32:54<5:20:20, 27.26s/it]
 25%|██▍       | 231/935 [1:33:19<5:09:19, 26.36s/it]
 25%|██▍       | 232/935 [1:33:52<5:34:03, 28.51s/it]
 25%|██▍       | 233/935 [1:34:22<5:37:39, 28.86s/it]
 25%|██▌       | 234/935 [1:34:45<5:15:45, 27.03s/it]
 25%|██▌       | 235/935 [1:35:13<5:20:19, 27.46s/it]
                                                     

 25%|██▌       | 235/935 [1:35:13<5:20:19, 27.46s/it]
 25%|██▌       | 236/935 [1:35:36<5:04:43, 26.16s/it]
 25%|██▌       | 237/935 [1:36:05<5:14:24, 27.03s/it]
 25%|██▌       | 238/935 [1:36:38<5:33:29, 28.71s/it]
 26%|██▌       | 239/935 [1:36:59<5:06:27, 26.42s/it]
 26%|██▌       | 240/935 [1:37:30<5:23:09, 27.90s/it]
                                                     

 26%|██▌       | 240/935 [1:37:30<5:23:09, 27.90s/it]
 26%|██▌       | 241/935 [1:37:51<4:58:38, 25.82s/it]
 26%|██▌       | 242/935 [1:38:17<4:57:11, 25.73s/it]
 26%|██▌       | 243/935 [1:38:40<4:47:29, 24.93s/it]
 26%|██▌       | 244/935 [1:38:57<4:20:03, 22.58s/it]
 26%|██▌       | 245/935 [1:39:22<4:27:00, 23.22s/it]
                                                     

 26%|██▌       | 245/935 [1:39:22<4:27:00, 23.22s/it]
 26%|██▋       | 246/935 [1:39:56<5:04:29, 26.52s/it]
 26%|██▋       | 247/935 [1:40:18<4:47:33, 25.08s/it]
 27%|██▋       | 248/935 [1:40:38<4:29:46, 23.56s/it]
 27%|██▋       | 249/935 [1:41:03<4:35:29, 24.10s/it]
 27%|██▋       | 250/935 [1:41:33<4:56:26, 25.97s/it]
                                                     

 27%|██▋       | 250/935 [1:41:33<4:56:26, 25.97s/it]{'eval_loss': 0.35487493872642517, 'eval_runtime': 65.702, 'eval_samples_per_second': 5.845, 'eval_steps_per_second': 2.922, 'epoch': 0.21}
{'loss': 0.6566, 'grad_norm': 0.6328405141830444, 'learning_rate': 0.00018496689028287572, 'epoch': 0.22}
{'loss': 0.4068, 'grad_norm': 0.4488189220428467, 'learning_rate': 0.00018402086789137546, 'epoch': 0.22}
{'loss': 0.6886, 'grad_norm': 0.5511447787284851, 'learning_rate': 0.00018304855555585894, 'epoch': 0.23}
{'loss': 0.4343, 'grad_norm': 0.5694918632507324, 'learning_rate': 0.00018205025751070875, 'epoch': 0.24}
{'loss': 0.6427, 'grad_norm': 0.7412458658218384, 'learning_rate': 0.00018102628612117865, 'epoch': 0.24}
{'loss': 0.5227, 'grad_norm': 0.570604145526886, 'learning_rate': 0.0001799769617856552, 'epoch': 0.25}
{'loss': 0.4459, 'grad_norm': 0.4664093852043152, 'learning_rate': 0.00017890261283540562, 'epoch': 0.25}
{'loss': 0.5747, 'grad_norm': 0.5674915313720703, 'learning_rate': 0.00017780357543184397, 'epoch': 0.26}
{'loss': 0.485, 'grad_norm': 0.6507865190505981, 'learning_rate': 0.0001766801934613467, 'epoch': 0.26}
{'loss': 0.6842, 'grad_norm': 0.6156233549118042, 'learning_rate': 0.00017553281842765169, 'epoch': 0.27}


  0%|          | 0/192 [00:00<?, ?it/s]

  1%|          | 2/192 [00:00<01:33,  2.04it/s]

  2%|▏         | 3/192 [00:02<02:21,  1.33it/s]

  2%|▏         | 4/192 [00:03<02:43,  1.15it/s]

  3%|▎         | 5/192 [00:03<02:22,  1.32it/s]

  3%|▎         | 6/192 [00:04<02:12,  1.40it/s]

  4%|▎         | 7/192 [00:04<02:07,  1.45it/s]

  4%|▍         | 8/192 [00:05<01:37,  1.88it/s]

  5%|▍         | 9/192 [00:05<01:53,  1.61it/s]

  5%|▌         | 10/192 [00:07<02:30,  1.21it/s]

  6%|▌         | 11/192 [00:08<02:43,  1.11it/s]

  6%|▋         | 12/192 [00:08<02:14,  1.33it/s]

  7%|▋         | 13/192 [00:09<02:09,  1.38it/s]

  7%|▋         | 14/192 [00:10<02:28,  1.20it/s]

  8%|▊         | 15/192 [00:11<02:36,  1.13it/s]

  8%|▊         | 16/192 [00:11<02:10,  1.34it/s]

  9%|▉         | 17/192 [00:12<01:38,  1.77it/s]

  9%|▉         | 18/192 [00:12<01:18,  2.23it/s]

 10%|▉         | 19/192 [00:12<01:03,  2.74it/s]

 10%|█         | 20/192 [00:13<01:15,  2.27it/s]

 11%|█         | 21/192 [00:14<01:47,  1.60it/s]

 11%|█▏        | 22/192 [00:14<01:41,  1.68it/s]

 12%|█▏        | 23/192 [00:14<01:17,  2.17it/s]

 12%|█▎        | 24/192 [00:14<01:04,  2.62it/s]

 13%|█▎        | 25/192 [00:15<01:20,  2.08it/s]

 14%|█▎        | 26/192 [00:16<01:55,  1.43it/s]

 14%|█▍        | 27/192 [00:18<02:24,  1.14it/s]

 15%|█▍        | 28/192 [00:18<02:10,  1.25it/s]

 15%|█▌        | 29/192 [00:19<02:03,  1.32it/s]

 16%|█▌        | 30/192 [00:20<02:17,  1.18it/s]

 16%|█▌        | 31/192 [00:21<02:26,  1.10it/s]

 17%|█▋        | 32/192 [00:22<02:30,  1.06it/s]

 17%|█▋        | 33/192 [00:23<02:18,  1.15it/s]

 18%|█▊        | 34/192 [00:23<01:43,  1.53it/s]

 19%|█▉        | 36/192 [00:23<01:03,  2.47it/s]

 19%|█▉        | 37/192 [00:24<01:07,  2.30it/s]

 20%|█▉        | 38/192 [00:24<01:10,  2.17it/s]

 20%|██        | 39/192 [00:24<01:00,  2.51it/s]

 21%|██        | 40/192 [00:25<01:06,  2.28it/s]

 21%|██▏       | 41/192 [00:26<01:38,  1.53it/s]

 22%|██▏       | 42/192 [00:27<01:42,  1.46it/s]

 22%|██▏       | 43/192 [00:27<01:21,  1.82it/s]

 23%|██▎       | 44/192 [00:28<01:34,  1.57it/s]

 23%|██▎       | 45/192 [00:29<02:05,  1.17it/s]

 24%|██▍       | 46/192 [00:30<01:57,  1.25it/s]

 24%|██▍       | 47/192 [00:31<01:56,  1.25it/s]

 25%|██▌       | 48/192 [00:31<01:47,  1.33it/s]

 26%|██▌       | 49/192 [00:32<01:23,  1.72it/s]

 26%|██▌       | 50/192 [00:32<01:05,  2.16it/s]

 27%|██▋       | 51/192 [00:32<00:54,  2.59it/s]

 27%|██▋       | 52/192 [00:32<00:44,  3.12it/s]

 28%|██▊       | 53/192 [00:33<01:04,  2.16it/s]

 28%|██▊       | 54/192 [00:34<01:13,  1.89it/s]

 29%|██▊       | 55/192 [00:34<01:00,  2.28it/s]

 29%|██▉       | 56/192 [00:35<01:16,  1.78it/s]

 30%|██▉       | 57/192 [00:36<01:24,  1.59it/s]

 30%|███       | 58/192 [00:36<01:04,  2.08it/s]

 31%|███       | 59/192 [00:36<00:49,  2.71it/s]

 31%|███▏      | 60/192 [00:36<00:52,  2.52it/s]

 32%|███▏      | 61/192 [00:37<00:55,  2.36it/s]

 32%|███▏      | 62/192 [00:37<01:04,  2.02it/s]

 33%|███▎      | 63/192 [00:38<01:10,  1.82it/s]

 33%|███▎      | 64/192 [00:38<00:57,  2.25it/s]

 34%|███▍      | 65/192 [00:39<01:10,  1.79it/s]

 34%|███▍      | 66/192 [00:40<01:34,  1.34it/s]

 35%|███▍      | 67/192 [00:41<01:30,  1.38it/s]

 35%|███▌      | 68/192 [00:41<01:08,  1.82it/s]

 36%|███▌      | 69/192 [00:42<01:10,  1.75it/s]

 36%|███▋      | 70/192 [00:43<01:24,  1.44it/s]

 37%|███▋      | 71/192 [00:43<01:22,  1.47it/s]

 38%|███▊      | 72/192 [00:44<01:21,  1.46it/s]

 38%|███▊      | 73/192 [00:45<01:42,  1.16it/s]

 39%|███▊      | 74/192 [00:46<01:35,  1.23it/s]

 39%|███▉      | 75/192 [00:46<01:11,  1.64it/s]

 40%|███▉      | 76/192 [00:47<01:09,  1.68it/s]

 40%|████      | 77/192 [00:47<01:09,  1.66it/s]

 41%|████      | 78/192 [00:48<00:54,  2.08it/s]

 41%|████      | 79/192 [00:48<01:01,  1.85it/s]

 42%|████▏     | 80/192 [00:49<01:02,  1.80it/s]

 42%|████▏     | 81/192 [00:50<01:06,  1.68it/s]

 43%|████▎     | 82/192 [00:51<01:19,  1.38it/s]

 43%|████▎     | 83/192 [00:51<01:15,  1.45it/s]

 44%|████▍     | 84/192 [00:51<00:55,  1.93it/s]

 44%|████▍     | 85/192 [00:51<00:44,  2.41it/s]

 45%|████▍     | 86/192 [00:52<00:36,  2.87it/s]

 45%|████▌     | 87/192 [00:52<00:32,  3.20it/s]

 46%|████▌     | 88/192 [00:53<00:52,  2.00it/s]

 46%|████▋     | 89/192 [00:54<01:02,  1.66it/s]

 47%|████▋     | 90/192 [00:54<01:02,  1.64it/s]

 47%|████▋     | 91/192 [00:55<01:01,  1.64it/s]

 48%|████▊     | 92/192 [00:56<01:05,  1.53it/s]

 48%|████▊     | 93/192 [00:57<01:15,  1.32it/s]

 49%|████▉     | 94/192 [00:57<01:06,  1.48it/s]

 49%|████▉     | 95/192 [00:57<00:52,  1.84it/s]

 50%|█████     | 96/192 [00:58<00:41,  2.34it/s]

 51%|█████     | 97/192 [00:58<00:33,  2.80it/s]

 51%|█████     | 98/192 [00:58<00:28,  3.33it/s]

 52%|█████▏    | 99/192 [00:58<00:25,  3.68it/s]

 52%|█████▏    | 100/192 [00:58<00:21,  4.27it/s]

 53%|█████▎    | 101/192 [00:58<00:17,  5.10it/s]

 53%|█████▎    | 102/192 [00:59<00:16,  5.31it/s]

 54%|█████▎    | 103/192 [00:59<00:33,  2.68it/s]

 54%|█████▍    | 104/192 [01:00<00:37,  2.34it/s]

 55%|█████▍    | 105/192 [01:01<00:46,  1.88it/s]

 55%|█████▌    | 106/192 [01:01<00:48,  1.78it/s]

 56%|█████▌    | 107/192 [01:02<00:55,  1.54it/s]

 56%|█████▋    | 108/192 [01:03<01:04,  1.31it/s]

 57%|█████▋    | 109/192 [01:04<01:15,  1.11it/s]

 57%|█████▋    | 110/192 [01:05<01:09,  1.18it/s]

 58%|█████▊    | 111/192 [01:05<00:52,  1.53it/s]

 58%|█████▊    | 112/192 [01:06<00:55,  1.45it/s]

 59%|█████▉    | 113/192 [01:07<00:56,  1.40it/s]

 59%|█████▉    | 114/192 [01:08<00:55,  1.41it/s]

 60%|█████▉    | 115/192 [01:08<00:54,  1.42it/s]

 60%|██████    | 116/192 [01:08<00:40,  1.88it/s]

 61%|██████    | 117/192 [01:09<00:44,  1.70it/s]

 61%|██████▏   | 118/192 [01:10<00:51,  1.43it/s]

 62%|██████▏   | 119/192 [01:11<00:47,  1.55it/s]

 62%|██████▎   | 120/192 [01:11<00:44,  1.62it/s]

 63%|██████▎   | 121/192 [01:12<00:43,  1.63it/s]

 64%|██████▎   | 122/192 [01:13<00:46,  1.49it/s]

 64%|██████▍   | 123/192 [01:13<00:48,  1.44it/s]

 65%|██████▍   | 124/192 [01:14<00:45,  1.48it/s]

 65%|██████▌   | 125/192 [01:15<00:55,  1.20it/s]

 66%|██████▌   | 126/192 [01:16<00:52,  1.27it/s]

 66%|██████▌   | 127/192 [01:16<00:40,  1.59it/s]

 67%|██████▋   | 128/192 [01:16<00:31,  2.04it/s]

 67%|██████▋   | 129/192 [01:17<00:34,  1.83it/s]

 68%|██████▊   | 130/192 [01:18<00:49,  1.24it/s]

 68%|██████▊   | 131/192 [01:20<00:58,  1.03it/s]

 69%|██████▉   | 132/192 [01:21<00:57,  1.04it/s]

 69%|██████▉   | 133/192 [01:22<01:00,  1.02s/it]

 70%|██████▉   | 134/192 [01:22<00:51,  1.12it/s]

 70%|███████   | 135/192 [01:23<00:51,  1.10it/s]

 71%|███████   | 136/192 [01:24<00:52,  1.06it/s]

 71%|███████▏  | 137/192 [01:25<00:44,  1.22it/s]

 72%|███████▏  | 138/192 [01:25<00:33,  1.61it/s]

 72%|███████▏  | 139/192 [01:25<00:26,  2.03it/s]

 73%|███████▎  | 140/192 [01:26<00:28,  1.86it/s]

 73%|███████▎  | 141/192 [01:27<00:34,  1.49it/s]

 74%|███████▍  | 142/192 [01:28<00:38,  1.31it/s]

 74%|███████▍  | 143/192 [01:29<00:45,  1.08it/s]

 75%|███████▌  | 144/192 [01:30<00:48,  1.01s/it]

 76%|███████▌  | 145/192 [01:32<00:49,  1.06s/it]

 76%|███████▌  | 146/192 [01:32<00:41,  1.10it/s]

 77%|███████▋  | 147/192 [01:32<00:30,  1.46it/s]

 77%|███████▋  | 148/192 [01:32<00:23,  1.89it/s]

 78%|███████▊  | 149/192 [01:33<00:27,  1.57it/s]

 78%|███████▊  | 150/192 [01:34<00:27,  1.53it/s]

 79%|███████▊  | 151/192 [01:35<00:25,  1.61it/s]

 79%|███████▉  | 152/192 [01:35<00:25,  1.56it/s]

 80%|███████▉  | 153/192 [01:36<00:25,  1.51it/s]

 80%|████████  | 154/192 [01:36<00:21,  1.77it/s]

 81%|████████  | 155/192 [01:37<00:20,  1.84it/s]

 81%|████████▏ | 156/192 [01:37<00:20,  1.80it/s]

 82%|████████▏ | 157/192 [01:38<00:18,  1.84it/s]

 82%|████████▏ | 158/192 [01:38<00:15,  2.14it/s]

 83%|████████▎ | 159/192 [01:39<00:18,  1.83it/s]

 83%|████████▎ | 160/192 [01:39<00:15,  2.07it/s]

 84%|████████▍ | 161/192 [01:40<00:13,  2.24it/s]

 84%|████████▍ | 162/192 [01:40<00:14,  2.10it/s]

 85%|████████▍ | 163/192 [01:41<00:15,  1.92it/s]

 85%|████████▌ | 164/192 [01:41<00:13,  2.01it/s]

 86%|████████▌ | 165/192 [01:41<00:11,  2.26it/s]

 86%|████████▋ | 166/192 [01:42<00:10,  2.41it/s]

 87%|████████▋ | 167/192 [01:42<00:09,  2.56it/s]

 88%|████████▊ | 169/192 [01:43<00:07,  3.17it/s]

 89%|████████▊ | 170/192 [01:43<00:07,  3.11it/s]

 89%|████████▉ | 171/192 [01:43<00:05,  3.68it/s]

 90%|████████▉ | 172/192 [01:43<00:05,  3.51it/s]

 90%|█████████ | 173/192 [01:44<00:05,  3.40it/s]

 91%|█████████ | 174/192 [01:44<00:05,  3.18it/s]

 91%|█████████ | 175/192 [01:44<00:05,  3.04it/s]

 92%|█████████▏| 176/192 [01:45<00:05,  2.77it/s]

 92%|█████████▏| 177/192 [01:46<00:06,  2.24it/s]

 93%|█████████▎| 178/192 [01:46<00:06,  2.23it/s]

 93%|█████████▎| 179/192 [01:47<00:06,  2.13it/s]

 94%|█████████▍| 180/192 [01:47<00:05,  2.14it/s]

 94%|█████████▍| 181/192 [01:48<00:06,  1.83it/s]

 95%|█████████▍| 182/192 [01:48<00:04,  2.22it/s]

 95%|█████████▌| 183/192 [01:48<00:04,  2.15it/s]

 96%|█████████▌| 184/192 [01:49<00:03,  2.05it/s]

 96%|█████████▋| 185/192 [01:49<00:03,  2.05it/s]

 97%|█████████▋| 186/192 [01:50<00:02,  2.49it/s]

 97%|█████████▋| 187/192 [01:50<00:02,  2.39it/s]

 98%|█████████▊| 188/192 [01:50<00:01,  2.61it/s]

 98%|█████████▊| 189/192 [01:51<00:00,  3.19it/s]

 99%|█████████▉| 190/192 [01:51<00:00,  3.22it/s]

 99%|█████████▉| 191/192 [01:51<00:00,  3.21it/s]
                                                     

                                                 

 27%|██▋       | 250/935 [1:43:26<4:56:26, 25.97s/it]

100%|██████████| 192/192 [01:51<00:00,  3.21it/s]

                                                 
 27%|██▋       | 251/935 [1:43:41<10:43:37, 56.46s/it]
 27%|██▋       | 252/935 [1:44:01<8:39:38, 45.65s/it] 
 27%|██▋       | 253/935 [1:44:19<7:02:45, 37.19s/it]
 27%|██▋       | 254/935 [1:44:33<5:44:29, 30.35s/it]
 27%|██▋       | 255/935 [1:44:53<5:08:35, 27.23s/it]
                                                     

 27%|██▋       | 255/935 [1:44:53<5:08:35, 27.23s/it]
 27%|██▋       | 256/935 [1:45:12<4:40:30, 24.79s/it]
 27%|██▋       | 257/935 [1:45:32<4:21:37, 23.15s/it]
 28%|██▊       | 258/935 [1:45:51<4:07:52, 21.97s/it]
 28%|██▊       | 259/935 [1:46:06<3:43:41, 19.85s/it]
 28%|██▊       | 260/935 [1:46:28<3:52:22, 20.66s/it]
                                                     

 28%|██▊       | 260/935 [1:46:28<3:52:22, 20.66s/it]
 28%|██▊       | 261/935 [1:46:44<3:35:11, 19.16s/it]
 28%|██▊       | 262/935 [1:47:05<3:41:31, 19.75s/it]
 28%|██▊       | 263/935 [1:47:32<4:05:23, 21.91s/it]
 28%|██▊       | 264/935 [1:47:52<4:00:16, 21.49s/it]
 28%|██▊       | 265/935 [1:48:10<3:46:57, 20.33s/it]
                                                     

 28%|██▊       | 265/935 [1:48:10<3:46:57, 20.33s/it]
 28%|██▊       | 266/935 [1:48:22<3:19:08, 17.86s/it]
 29%|██▊       | 267/935 [1:48:37<3:08:13, 16.91s/it]
 29%|██▊       | 268/935 [1:48:54<3:10:01, 17.09s/it]
 29%|██▉       | 269/935 [1:49:04<2:44:49, 14.85s/it]
 29%|██▉       | 270/935 [1:49:23<2:59:31, 16.20s/it]
                                                     

 29%|██▉       | 270/935 [1:49:23<2:59:31, 16.20s/it]
 29%|██▉       | 271/935 [1:49:38<2:53:46, 15.70s/it]
 29%|██▉       | 272/935 [1:49:59<3:10:11, 17.21s/it]
 29%|██▉       | 273/935 [1:50:19<3:21:18, 18.25s/it]
 29%|██▉       | 274/935 [1:50:35<3:11:36, 17.39s/it]
 29%|██▉       | 275/935 [1:50:58<3:29:42, 19.07s/it]
                                                     

 29%|██▉       | 275/935 [1:50:58<3:29:42, 19.07s/it]
 30%|██▉       | 276/935 [1:51:10<3:07:21, 17.06s/it]
 30%|██▉       | 277/935 [1:51:25<3:01:06, 16.51s/it]
 30%|██▉       | 278/935 [1:51:42<3:02:40, 16.68s/it]
 30%|██▉       | 279/935 [1:52:00<3:04:56, 16.91s/it]
 30%|██▉       | 280/935 [1:52:15<2:58:20, 16.34s/it]
                                                     

 30%|██▉       | 280/935 [1:52:15<2:58:20, 16.34s/it]
 30%|███       | 281/935 [1:52:29<2:52:21, 15.81s/it]
 30%|███       | 282/935 [1:52:48<3:02:48, 16.80s/it]
 30%|███       | 283/935 [1:53:02<2:50:48, 15.72s/it]
 30%|███       | 284/935 [1:53:14<2:38:54, 14.65s/it]
 30%|███       | 285/935 [1:53:33<2:54:39, 16.12s/it]
                                                     

 30%|███       | 285/935 [1:53:33<2:54:39, 16.12s/it]
 31%|███       | 286/935 [1:53:50<2:56:33, 16.32s/it]
 31%|███       | 287/935 [1:54:05<2:50:48, 15.82s/it]
 31%|███       | 288/935 [1:54:17<2:40:15, 14.86s/it]
 31%|███       | 289/935 [1:54:33<2:43:19, 15.17s/it]
 31%|███       | 290/935 [1:54:51<2:50:41, 15.88s/it]
                                                     

 31%|███       | 290/935 [1:54:51<2:50:41, 15.88s/it]
 31%|███       | 291/935 [1:55:07<2:51:35, 15.99s/it]
 31%|███       | 292/935 [1:55:18<2:33:57, 14.37s/it]
 31%|███▏      | 293/935 [1:55:30<2:26:50, 13.72s/it]
 31%|███▏      | 294/935 [1:55:45<2:31:35, 14.19s/it]
 32%|███▏      | 295/935 [1:55:55<2:17:12, 12.86s/it]
                                                     

 32%|███▏      | 295/935 [1:55:55<2:17:12, 12.86s/it]
 32%|███▏      | 296/935 [1:56:08<2:19:11, 13.07s/it]
 32%|███▏      | 297/935 [1:56:21<2:15:37, 12.75s/it]
 32%|███▏      | 298/935 [1:56:35<2:20:35, 13.24s/it]
 32%|███▏      | 299/935 [1:56:51<2:28:11, 13.98s/it]
 32%|███▏      | 300/935 [1:57:03<2:21:59, 13.42s/it]
                                                     

 32%|███▏      | 300/935 [1:57:03<2:21:59, 13.42s/it]{'eval_loss': 0.3379444181919098, 'eval_runtime': 112.4829, 'eval_samples_per_second': 3.414, 'eval_steps_per_second': 1.707, 'epoch': 0.27}
{'loss': 0.5986, 'grad_norm': 0.7011458873748779, 'learning_rate': 0.00017436180934187308, 'epoch': 0.27}
{'loss': 0.488, 'grad_norm': 0.4791603684425354, 'learning_rate': 0.00017316753261016783, 'epoch': 0.28}
{'loss': 0.4339, 'grad_norm': 0.4457736909389496, 'learning_rate': 0.00017195036191908797, 'epoch': 0.28}
{'loss': 0.3714, 'grad_norm': 0.622725784778595, 'learning_rate': 0.00017071067811865476, 'epoch': 0.29}
{'loss': 0.3445, 'grad_norm': 0.4370780289173126, 'learning_rate': 0.00016944886910319173, 'epoch': 0.29}
{'loss': 0.6308, 'grad_norm': 0.4771464467048645, 'learning_rate': 0.00016816532968995328, 'epoch': 0.3}
{'loss': 0.5753, 'grad_norm': 0.5418441295623779, 'learning_rate': 0.00016686046149558736, 'epoch': 0.31}
{'loss': 0.481, 'grad_norm': 0.4074549674987793, 'learning_rate': 0.0001655346728104704, 'epoch': 0.31}
{'loss': 0.8114, 'grad_norm': 0.6757243275642395, 'learning_rate': 0.0001641883784709541, 'epoch': 0.32}
{'loss': 0.3812, 'grad_norm': 0.5381545424461365, 'learning_rate': 0.00016282199972956425, 'epoch': 0.32}


  0%|          | 0/192 [00:00<?, ?it/s]

  1%|          | 2/192 [00:00<00:46,  4.11it/s]

  2%|▏         | 3/192 [00:01<01:14,  2.55it/s]

  2%|▏         | 4/192 [00:01<01:22,  2.29it/s]

  3%|▎         | 5/192 [00:01<01:14,  2.51it/s]

  3%|▎         | 6/192 [00:02<01:08,  2.71it/s]

  4%|▎         | 7/192 [00:02<01:06,  2.78it/s]

  5%|▍         | 9/192 [00:03<00:55,  3.28it/s]

  5%|▌         | 10/192 [00:03<01:10,  2.60it/s]

  6%|▌         | 11/192 [00:04<01:17,  2.33it/s]

  6%|▋         | 12/192 [00:04<01:06,  2.70it/s]

  7%|▋         | 13/192 [00:04<01:03,  2.80it/s]

  7%|▋         | 14/192 [00:05<01:11,  2.48it/s]

  8%|▊         | 15/192 [00:05<01:17,  2.28it/s]

  8%|▊         | 16/192 [00:06<01:05,  2.67it/s]

  9%|▉         | 18/192 [00:06<00:42,  4.12it/s]

 10%|▉         | 19/192 [00:06<00:36,  4.78it/s]

 10%|█         | 20/192 [00:06<00:40,  4.26it/s]

 11%|█         | 21/192 [00:07<00:53,  3.17it/s]

 11%|█▏        | 22/192 [00:07<00:51,  3.29it/s]

 12%|█▎        | 24/192 [00:07<00:35,  4.74it/s]

 13%|█▎        | 25/192 [00:07<00:41,  4.04it/s]

 14%|█▎        | 26/192 [00:08<00:54,  3.03it/s]

 14%|█▍        | 27/192 [00:09<01:09,  2.39it/s]

 15%|█▍        | 28/192 [00:09<01:03,  2.58it/s]

 15%|█▌        | 29/192 [00:09<01:00,  2.71it/s]

 16%|█▌        | 30/192 [00:10<01:05,  2.46it/s]

 16%|█▌        | 31/192 [00:10<01:12,  2.23it/s]

 17%|█▋        | 32/192 [00:11<01:13,  2.17it/s]

 17%|█▋        | 33/192 [00:12<01:22,  1.94it/s]

 18%|█▊        | 35/192 [00:12<00:48,  3.21it/s]

 19%|█▉        | 37/192 [00:12<00:39,  3.92it/s]

 20%|█▉        | 38/192 [00:12<00:39,  3.86it/s]

 20%|██        | 39/192 [00:12<00:34,  4.39it/s]

 21%|██        | 40/192 [00:13<00:35,  4.23it/s]

 21%|██▏       | 41/192 [00:13<00:51,  2.96it/s]

 22%|██▏       | 42/192 [00:14<00:51,  2.89it/s]

 22%|██▏       | 43/192 [00:14<00:42,  3.48it/s]

 23%|██▎       | 44/192 [00:14<00:47,  3.09it/s]

 23%|██▎       | 45/192 [00:15<01:03,  2.31it/s]

 24%|██▍       | 46/192 [00:15<00:59,  2.45it/s]

 24%|██▍       | 47/192 [00:16<00:59,  2.45it/s]

 25%|██▌       | 48/192 [00:16<00:54,  2.63it/s]

 26%|██▌       | 49/192 [00:16<00:42,  3.35it/s]

 27%|██▋       | 51/192 [00:16<00:29,  4.84it/s]

 28%|██▊       | 53/192 [00:17<00:30,  4.53it/s]

 28%|██▊       | 54/192 [00:17<00:33,  4.07it/s]

 29%|██▊       | 55/192 [00:17<00:30,  4.57it/s]

 29%|██▉       | 56/192 [00:18<00:36,  3.73it/s]

 30%|██▉       | 57/192 [00:18<00:41,  3.29it/s]

 31%|███       | 59/192 [00:18<00:26,  4.94it/s]

 31%|███▏      | 60/192 [00:18<00:27,  4.85it/s]

 32%|███▏      | 61/192 [00:19<00:29,  4.51it/s]

 32%|███▏      | 62/192 [00:19<00:32,  4.05it/s]

 33%|███▎      | 63/192 [00:19<00:35,  3.63it/s]

 34%|███▍      | 65/192 [00:20<00:33,  3.74it/s]

 34%|███▍      | 66/192 [00:20<00:42,  2.96it/s]

 35%|███▍      | 67/192 [00:21<00:43,  2.90it/s]

 36%|███▌      | 69/192 [00:21<00:34,  3.55it/s]

 36%|███▋      | 70/192 [00:22<00:39,  3.07it/s]

 37%|███▋      | 71/192 [00:22<00:40,  3.01it/s]

 38%|███▊      | 72/192 [00:22<00:40,  2.99it/s]

 38%|███▊      | 73/192 [00:23<00:50,  2.37it/s]

 39%|███▊      | 74/192 [00:23<00:47,  2.48it/s]

 39%|███▉      | 75/192 [00:23<00:37,  3.14it/s]

 40%|███▉      | 76/192 [00:24<00:35,  3.24it/s]

 40%|████      | 77/192 [00:24<00:35,  3.24it/s]

 41%|████      | 79/192 [00:24<00:30,  3.76it/s]

 42%|████▏     | 80/192 [00:25<00:30,  3.71it/s]

 42%|████▏     | 81/192 [00:25<00:32,  3.42it/s]

 43%|████▎     | 82/192 [00:26<00:38,  2.87it/s]

 43%|████▎     | 83/192 [00:26<00:38,  2.87it/s]

 44%|████▍     | 85/192 [00:26<00:24,  4.41it/s]

 45%|████▌     | 87/192 [00:26<00:18,  5.65it/s]

 46%|████▌     | 88/192 [00:27<00:24,  4.23it/s]

 46%|████▋     | 89/192 [00:27<00:29,  3.52it/s]

 47%|████▋     | 90/192 [00:27<00:29,  3.50it/s]

 47%|████▋     | 91/192 [00:28<00:30,  3.35it/s]

 48%|████▊     | 92/192 [00:28<00:31,  3.16it/s]

 48%|████▊     | 93/192 [00:29<00:36,  2.68it/s]

 49%|████▉     | 94/192 [00:29<00:32,  3.01it/s]

 49%|████▉     | 95/192 [00:29<00:26,  3.65it/s]

 51%|█████     | 97/192 [00:29<00:18,  5.25it/s]

 52%|█████▏    | 99/192 [00:29<00:14,  6.51it/s]

 53%|█████▎    | 101/192 [00:30<00:11,  7.78it/s]

 54%|█████▎    | 103/192 [00:30<00:13,  6.49it/s]

 54%|█████▍    | 104/192 [00:30<00:15,  5.61it/s]

 55%|█████▍    | 105/192 [00:31<00:19,  4.38it/s]

 55%|█████▌    | 106/192 [00:31<00:21,  3.97it/s]

 56%|█████▌    | 107/192 [00:31<00:25,  3.35it/s]

 56%|█████▋    | 108/192 [00:32<00:29,  2.84it/s]

 57%|█████▋    | 109/192 [00:33<00:36,  2.30it/s]

 57%|█████▋    | 110/192 [00:33<00:33,  2.41it/s]

 58%|█████▊    | 111/192 [00:33<00:26,  3.02it/s]

 58%|█████▊    | 112/192 [00:33<00:28,  2.85it/s]

 59%|█████▉    | 113/192 [00:34<00:28,  2.73it/s]

 59%|█████▉    | 114/192 [00:34<00:28,  2.76it/s]

 60%|█████▉    | 115/192 [00:35<00:28,  2.74it/s]

 61%|██████    | 117/192 [00:35<00:22,  3.34it/s]

 61%|██████▏   | 118/192 [00:36<00:25,  2.93it/s]

 62%|██████▏   | 119/192 [00:36<00:24,  2.99it/s]

 62%|██████▎   | 120/192 [00:36<00:23,  3.09it/s]

 63%|██████▎   | 121/192 [00:36<00:23,  3.07it/s]

 64%|██████▎   | 122/192 [00:37<00:24,  2.91it/s]

 64%|██████▍   | 123/192 [00:37<00:24,  2.80it/s]

 65%|██████▍   | 124/192 [00:38<00:23,  2.91it/s]

 65%|██████▌   | 125/192 [00:38<00:28,  2.36it/s]

 66%|██████▌   | 126/192 [00:39<00:26,  2.53it/s]

 66%|██████▌   | 127/192 [00:39<00:20,  3.11it/s]

 67%|██████▋   | 129/192 [00:39<00:17,  3.65it/s]

 68%|██████▊   | 130/192 [00:40<00:23,  2.65it/s]

 68%|██████▊   | 131/192 [00:40<00:28,  2.17it/s]

 69%|██████▉   | 132/192 [00:41<00:27,  2.15it/s]

 69%|██████▉   | 133/192 [00:42<00:30,  1.96it/s]

 70%|██████▉   | 134/192 [00:42<00:26,  2.21it/s]

 70%|███████   | 135/192 [00:42<00:26,  2.17it/s]

 71%|███████   | 136/192 [00:43<00:26,  2.13it/s]

 71%|███████▏  | 137/192 [00:43<00:23,  2.39it/s]

 72%|███████▏  | 139/192 [00:43<00:14,  3.72it/s]

 73%|███████▎  | 140/192 [00:44<00:14,  3.56it/s]

 73%|███████▎  | 141/192 [00:44<00:17,  2.87it/s]

 74%|███████▍  | 142/192 [00:45<00:19,  2.56it/s]

 74%|███████▍  | 143/192 [00:45<00:23,  2.08it/s]

 75%|███████▌  | 144/192 [00:46<00:24,  1.93it/s]

 76%|███████▌  | 145/192 [00:47<00:26,  1.80it/s]

 76%|███████▌  | 146/192 [00:47<00:22,  2.06it/s]

 77%|███████▋  | 147/192 [00:47<00:16,  2.67it/s]

 78%|███████▊  | 149/192 [00:48<00:13,  3.08it/s]

 78%|███████▊  | 150/192 [00:48<00:14,  2.97it/s]

 79%|███████▊  | 151/192 [00:48<00:13,  3.04it/s]

 79%|███████▉  | 152/192 [00:49<00:15,  2.57it/s]

 80%|███████▉  | 153/192 [00:50<00:18,  2.07it/s]

 80%|████████  | 154/192 [00:50<00:16,  2.27it/s]

 81%|████████  | 155/192 [00:50<00:16,  2.19it/s]

 81%|████████▏ | 156/192 [00:51<00:17,  2.02it/s]

 82%|████████▏ | 157/192 [00:51<00:16,  2.18it/s]

 82%|████████▏ | 158/192 [00:52<00:13,  2.45it/s]

 83%|████████▎ | 159/192 [00:52<00:15,  2.14it/s]

 83%|████████▎ | 160/192 [00:53<00:13,  2.32it/s]

 84%|████████▍ | 161/192 [00:53<00:12,  2.45it/s]

 84%|████████▍ | 162/192 [00:54<00:13,  2.22it/s]

 85%|████████▍ | 163/192 [00:54<00:14,  1.99it/s]

 85%|████████▌ | 164/192 [00:55<00:13,  2.06it/s]

 86%|████████▌ | 165/192 [00:55<00:11,  2.30it/s]

 86%|████████▋ | 166/192 [00:55<00:10,  2.45it/s]

 87%|████████▋ | 167/192 [00:56<00:09,  2.57it/s]

 88%|████████▊ | 169/192 [00:56<00:07,  3.17it/s]

 89%|████████▊ | 170/192 [00:56<00:07,  3.10it/s]

 89%|████████▉ | 171/192 [00:57<00:05,  3.65it/s]

 90%|████████▉ | 172/192 [00:57<00:05,  3.54it/s]

 90%|█████████ | 173/192 [00:57<00:05,  3.39it/s]

 91%|█████████ | 174/192 [00:58<00:05,  3.18it/s]

 91%|█████████ | 175/192 [00:58<00:05,  3.06it/s]

 92%|█████████▏| 176/192 [00:58<00:05,  2.81it/s]

 92%|█████████▏| 177/192 [00:59<00:06,  2.25it/s]

 93%|█████████▎| 178/192 [00:59<00:06,  2.23it/s]

 93%|█████████▎| 179/192 [01:00<00:06,  2.14it/s]

 94%|█████████▍| 180/192 [01:00<00:05,  2.14it/s]

 94%|█████████▍| 181/192 [01:01<00:05,  2.09it/s]

 95%|█████████▍| 182/192 [01:01<00:04,  2.47it/s]

 95%|█████████▌| 183/192 [01:02<00:03,  2.32it/s]

 96%|█████████▌| 184/192 [01:02<00:03,  2.15it/s]

 96%|█████████▋| 185/192 [01:03<00:03,  2.16it/s]

 97%|█████████▋| 186/192 [01:03<00:02,  2.54it/s]

 97%|█████████▋| 187/192 [01:03<00:01,  2.66it/s]

 98%|█████████▊| 188/192 [01:04<00:01,  2.85it/s]

 98%|█████████▊| 189/192 [01:04<00:00,  3.47it/s]

 99%|█████████▉| 190/192 [01:04<00:00,  3.44it/s]

 99%|█████████▉| 191/192 [01:04<00:00,  3.39it/s]
                                                     

                                                 

 32%|███▏      | 300/935 [1:58:08<2:21:59, 13.42s/it]

100%|██████████| 192/192 [01:04<00:00,  3.39it/s]

                                                 wandb: WARNING URL not available in offline run

 32%|███▏      | 301/935 [1:58:29<6:11:19, 35.14s/it]
 32%|███▏      | 302/935 [1:58:46<5:15:28, 29.90s/it]
 32%|███▏      | 303/935 [1:59:07<4:47:29, 27.29s/it]
 33%|███▎      | 304/935 [1:59:54<5:46:38, 32.96s/it]
 33%|███▎      | 305/935 [2:00:18<5:18:55, 30.37s/it]
                                                     

 33%|███▎      | 305/935 [2:00:18<5:18:55, 30.37s/it]
 33%|███▎      | 306/935 [2:00:23<3:59:38, 22.86s/it]
 33%|███▎      | 307/935 [2:00:41<3:43:09, 21.32s/it]
 33%|███▎      | 308/935 [2:01:00<3:35:13, 20.60s/it]
 33%|███▎      | 309/935 [2:01:16<3:19:33, 19.13s/it]
 33%|███▎      | 310/935 [2:01:44<3:48:38, 21.95s/it]
                                                     

 33%|███▎      | 310/935 [2:01:44<3:48:38, 21.95s/it]
 33%|███▎      | 311/935 [2:02:11<4:04:11, 23.48s/it]
 33%|███▎      | 312/935 [2:02:30<3:50:37, 22.21s/it]
 33%|███▎      | 313/935 [2:02:58<4:06:28, 23.78s/it]
 34%|███▎      | 314/935 [2:03:10<3:28:39, 20.16s/it]
 34%|███▎      | 315/935 [2:03:42<4:07:54, 23.99s/it]
                                                     

 34%|███▎      | 315/935 [2:03:43<4:07:54, 23.99s/it]
 34%|███▍      | 316/935 [2:04:03<3:55:54, 22.87s/it]
 34%|███▍      | 317/935 [2:04:36<4:26:56, 25.92s/it]
 34%|███▍      | 318/935 [2:05:02<4:27:18, 25.99s/it]
 34%|███▍      | 319/935 [2:05:35<4:47:40, 28.02s/it]
 34%|███▍      | 320/935 [2:06:07<5:00:38, 29.33s/it]
                                                     

 34%|███▍      | 320/935 [2:06:07<5:00:38, 29.33s/it]
 34%|███▍      | 321/935 [2:06:30<4:39:26, 27.31s/it]
 34%|███▍      | 322/935 [2:06:52<4:25:10, 25.95s/it]
 35%|███▍      | 323/935 [2:07:15<4:14:50, 24.98s/it]
 35%|███▍      | 324/935 [2:07:33<3:53:41, 22.95s/it]
 35%|███▍      | 325/935 [2:08:07<4:24:54, 26.06s/it]
                                                     

 35%|███▍      | 325/935 [2:08:07<4:24:54, 26.06s/it]
 35%|███▍      | 326/935 [2:08:45<5:01:15, 29.68s/it]
 35%|███▍      | 327/935 [2:09:12<4:53:05, 28.92s/it]
 35%|███▌      | 328/935 [2:09:36<4:38:16, 27.51s/it]
 35%|███▌      | 329/935 [2:10:07<4:48:09, 28.53s/it]
 35%|███▌      | 330/935 [2:10:31<4:34:10, 27.19s/it]
                                                     

 35%|███▌      | 330/935 [2:10:31<4:34:10, 27.19s/it]
 35%|███▌      | 331/935 [2:10:49<4:04:57, 24.33s/it]
 36%|███▌      | 332/935 [2:11:06<3:44:14, 22.31s/it]
 36%|███▌      | 333/935 [2:11:22<3:22:25, 20.17s/it]
 36%|███▌      | 334/935 [2:11:54<3:58:23, 23.80s/it]
 36%|███▌      | 335/935 [2:12:23<4:13:51, 25.39s/it]
                                                     

 36%|███▌      | 335/935 [2:12:23<4:13:51, 25.39s/it]
 36%|███▌      | 336/935 [2:12:44<4:00:43, 24.11s/it]
 36%|███▌      | 337/935 [2:13:01<3:37:35, 21.83s/it]
 36%|███▌      | 338/935 [2:13:16<3:19:04, 20.01s/it]
 36%|███▋      | 339/935 [2:13:43<3:37:00, 21.85s/it]
 36%|███▋      | 340/935 [2:14:12<3:59:00, 24.10s/it]
                                                     

 36%|███▋      | 340/935 [2:14:12<3:59:00, 24.10s/it]
 36%|███▋      | 341/935 [2:14:38<4:03:35, 24.60s/it]
 37%|███▋      | 342/935 [2:15:04<4:09:24, 25.24s/it]
 37%|███▋      | 343/935 [2:15:19<3:36:39, 21.96s/it]
 37%|███▋      | 344/935 [2:15:34<3:17:41, 20.07s/it]
 37%|███▋      | 345/935 [2:15:52<3:09:10, 19.24s/it]
                                                     

 37%|███▋      | 345/935 [2:15:52<3:09:10, 19.24s/it]
 37%|███▋      | 346/935 [2:16:17<3:26:25, 21.03s/it]
 37%|███▋      | 347/935 [2:16:33<3:12:36, 19.65s/it]
 37%|███▋      | 348/935 [2:16:43<2:42:58, 16.66s/it]
 37%|███▋      | 349/935 [2:16:50<2:15:11, 13.84s/it]
 37%|███▋      | 350/935 [2:17:09<2:28:45, 15.26s/it]
                                                     

 37%|███▋      | 350/935 [2:17:09<2:28:45, 15.26s/it]{'eval_loss': 0.33034276962280273, 'eval_runtime': 65.2007, 'eval_samples_per_second': 5.89, 'eval_steps_per_second': 2.945, 'epoch': 0.32}
{'loss': 0.5419, 'grad_norm': 0.40816760063171387, 'learning_rate': 0.0001614359641231916, 'epoch': 0.33}
{'loss': 0.3992, 'grad_norm': 0.5720945000648499, 'learning_rate': 0.00016003070533931657, 'epoch': 0.33}
{'loss': 0.6731, 'grad_norm': 0.6349712014198303, 'learning_rate': 0.00015860666308030932, 'epoch': 0.34}
{'loss': 0.5419, 'grad_norm': 0.5889337062835693, 'learning_rate': 0.00015716428292584787, 'epoch': 0.34}
{'loss': 0.5926, 'grad_norm': 0.499977707862854, 'learning_rate': 0.00015570401619349736, 'epoch': 0.35}
{'loss': 0.5331, 'grad_norm': 0.5134796500205994, 'learning_rate': 0.00015422631979749354, 'epoch': 0.35}
{'loss': 0.4486, 'grad_norm': 0.6799819469451904, 'learning_rate': 0.00015273165610577542, 'epoch': 0.36}
{'loss': 0.7224, 'grad_norm': 0.5893351435661316, 'learning_rate': 0.00015122049279531143, 'epoch': 0.36}
{'loss': 0.4064, 'grad_norm': 0.5354906916618347, 'learning_rate': 0.00014969330270576427, 'epoch': 0.37}
{'loss': 0.5007, 'grad_norm': 0.5472406148910522, 'learning_rate': 0.00014815056369154038, 'epoch': 0.37}


  0%|          | 0/192 [00:00<?, ?it/s]

  1%|          | 2/192 [00:00<00:46,  4.12it/s]

  2%|▏         | 3/192 [00:01<01:14,  2.54it/s]

  2%|▏         | 4/192 [00:01<01:22,  2.29it/s]

  3%|▎         | 5/192 [00:01<01:14,  2.51it/s]

  3%|▎         | 6/192 [00:02<01:08,  2.71it/s]

  4%|▎         | 7/192 [00:02<01:06,  2.77it/s]

  5%|▍         | 9/192 [00:03<00:55,  3.29it/s]

  5%|▌         | 10/192 [00:03<01:09,  2.60it/s]

  6%|▌         | 11/192 [00:04<01:17,  2.34it/s]

  6%|▋         | 12/192 [00:04<01:06,  2.71it/s]

  7%|▋         | 13/192 [00:04<01:04,  2.77it/s]

  7%|▋         | 14/192 [00:05<01:12,  2.47it/s]

  8%|▊         | 15/192 [00:05<01:17,  2.29it/s]

  8%|▊         | 16/192 [00:06<01:05,  2.68it/s]

  9%|▉         | 18/192 [00:06<00:42,  4.14it/s]

 10%|▉         | 19/192 [00:06<00:36,  4.80it/s]

 10%|█         | 20/192 [00:06<00:40,  4.28it/s]

 11%|█         | 21/192 [00:07<00:53,  3.17it/s]

 11%|█▏        | 22/192 [00:07<00:51,  3.28it/s]

 12%|█▎        | 24/192 [00:07<00:35,  4.74it/s]

 13%|█▎        | 25/192 [00:07<00:41,  4.03it/s]

 14%|█▎        | 26/192 [00:08<00:54,  3.03it/s]

 14%|█▍        | 27/192 [00:09<01:09,  2.39it/s]

 15%|█▍        | 28/192 [00:09<01:03,  2.58it/s]

 15%|█▌        | 29/192 [00:09<01:00,  2.70it/s]

 16%|█▌        | 30/192 [00:10<01:05,  2.46it/s]

 16%|█▌        | 31/192 [00:10<01:12,  2.23it/s]

 17%|█▋        | 32/192 [00:11<01:13,  2.17it/s]

 17%|█▋        | 33/192 [00:11<01:09,  2.29it/s]

 18%|█▊        | 35/192 [00:11<00:42,  3.68it/s]

 19%|█▉        | 37/192 [00:12<00:35,  4.33it/s]

 20%|█▉        | 38/192 [00:12<00:37,  4.15it/s]

 20%|██        | 39/192 [00:12<00:32,  4.69it/s]

 21%|██        | 40/192 [00:12<00:34,  4.42it/s]

 21%|██▏       | 41/192 [00:13<00:49,  3.03it/s]

 22%|██▏       | 42/192 [00:13<00:50,  2.96it/s]

 22%|██▏       | 43/192 [00:14<00:41,  3.55it/s]

 23%|██▎       | 44/192 [00:14<00:47,  3.14it/s]

 23%|██▎       | 45/192 [00:15<01:02,  2.34it/s]

 24%|██▍       | 46/192 [00:15<00:58,  2.47it/s]

 24%|██▍       | 47/192 [00:15<00:58,  2.47it/s]

 25%|██▌       | 48/192 [00:16<00:54,  2.64it/s]

 26%|██▌       | 49/192 [00:16<00:42,  3.37it/s]

 27%|██▋       | 51/192 [00:16<00:29,  4.85it/s]

 28%|██▊       | 53/192 [00:16<00:30,  4.55it/s]

 28%|██▊       | 54/192 [00:17<00:33,  4.09it/s]

 29%|██▊       | 55/192 [00:17<00:29,  4.57it/s]

 29%|██▉       | 56/192 [00:17<00:36,  3.72it/s]

 30%|██▉       | 57/192 [00:18<00:41,  3.28it/s]

 31%|███       | 59/192 [00:18<00:26,  4.93it/s]

 31%|███▏      | 60/192 [00:18<00:27,  4.85it/s]

 32%|███▏      | 61/192 [00:18<00:28,  4.56it/s]

 32%|███▏      | 62/192 [00:19<00:31,  4.07it/s]

 33%|███▎      | 63/192 [00:19<00:35,  3.64it/s]

 34%|███▍      | 65/192 [00:20<00:33,  3.75it/s]

 34%|███▍      | 66/192 [00:20<00:42,  2.96it/s]

 35%|███▍      | 67/192 [00:20<00:43,  2.90it/s]

 36%|███▌      | 69/192 [00:21<00:34,  3.54it/s]

 36%|███▋      | 70/192 [00:21<00:39,  3.08it/s]

 37%|███▋      | 71/192 [00:22<00:40,  3.00it/s]

 38%|███▊      | 72/192 [00:22<00:40,  2.99it/s]

 38%|███▊      | 73/192 [00:23<00:50,  2.37it/s]

 39%|███▊      | 74/192 [00:23<00:47,  2.48it/s]

 39%|███▉      | 75/192 [00:23<00:37,  3.12it/s]

 40%|███▉      | 76/192 [00:23<00:35,  3.23it/s]

 40%|████      | 77/192 [00:24<00:35,  3.22it/s]

 41%|████      | 79/192 [00:24<00:34,  3.32it/s]

 42%|████▏     | 80/192 [00:24<00:29,  3.84it/s]

 42%|████▏     | 81/192 [00:25<00:32,  3.46it/s]

 43%|████▎     | 82/192 [00:25<00:37,  2.93it/s]

 43%|████▎     | 83/192 [00:26<00:37,  2.91it/s]

 44%|████▍     | 85/192 [00:26<00:23,  4.47it/s]

 45%|████▌     | 87/192 [00:26<00:18,  5.70it/s]

 46%|████▌     | 88/192 [00:26<00:24,  4.26it/s]

 46%|████▋     | 89/192 [00:27<00:28,  3.58it/s]

 47%|████▋     | 90/192 [00:27<00:28,  3.54it/s]

 47%|████▋     | 91/192 [00:28<00:29,  3.44it/s]

 48%|████▊     | 92/192 [00:28<00:31,  3.20it/s]

 48%|████▊     | 93/192 [00:28<00:36,  2.70it/s]

 49%|████▉     | 94/192 [00:29<00:32,  3.02it/s]

 49%|████▉     | 95/192 [00:29<00:26,  3.66it/s]

 51%|█████     | 97/192 [00:29<00:18,  5.26it/s]

 52%|█████▏    | 99/192 [00:29<00:14,  6.54it/s]

 53%|█████▎    | 101/192 [00:29<00:11,  7.85it/s]

 54%|█████▎    | 103/192 [00:30<00:13,  6.58it/s]

 54%|█████▍    | 104/192 [00:30<00:15,  5.67it/s]

 55%|█████▍    | 105/192 [00:30<00:19,  4.41it/s]

 55%|█████▌    | 106/192 [00:31<00:21,  4.01it/s]

 56%|█████▌    | 107/192 [00:31<00:25,  3.36it/s]

 56%|█████▋    | 108/192 [00:32<00:29,  2.85it/s]

 57%|█████▋    | 109/192 [00:32<00:35,  2.33it/s]

 57%|█████▋    | 110/192 [00:33<00:33,  2.43it/s]

 58%|█████▊    | 111/192 [00:33<00:26,  3.05it/s]

 58%|█████▊    | 112/192 [00:33<00:27,  2.87it/s]

 59%|█████▉    | 113/192 [00:34<00:28,  2.73it/s]

 59%|█████▉    | 114/192 [00:34<00:28,  2.76it/s]

 60%|█████▉    | 115/192 [00:34<00:27,  2.75it/s]

 61%|██████    | 117/192 [00:35<00:22,  3.37it/s]

 61%|██████▏   | 118/192 [00:35<00:25,  2.94it/s]

 62%|██████▏   | 119/192 [00:36<00:24,  3.02it/s]

 62%|██████▎   | 120/192 [00:36<00:23,  3.09it/s]

 63%|██████▎   | 121/192 [00:36<00:23,  3.08it/s]

 64%|██████▎   | 122/192 [00:37<00:23,  2.92it/s]

 64%|██████▍   | 123/192 [00:37<00:24,  2.79it/s]

 65%|██████▍   | 124/192 [00:37<00:23,  2.90it/s]

 65%|██████▌   | 125/192 [00:38<00:28,  2.37it/s]

 66%|██████▌   | 126/192 [00:38<00:26,  2.53it/s]

 66%|██████▌   | 127/192 [00:38<00:20,  3.10it/s]

 67%|██████▋   | 129/192 [00:39<00:17,  3.65it/s]

 68%|██████▊   | 130/192 [00:39<00:23,  2.64it/s]

 68%|██████▊   | 131/192 [00:40<00:28,  2.16it/s]

 69%|██████▉   | 132/192 [00:41<00:27,  2.14it/s]

 69%|██████▉   | 133/192 [00:41<00:30,  1.96it/s]

 70%|██████▉   | 134/192 [00:42<00:26,  2.21it/s]

 70%|███████   | 135/192 [00:42<00:26,  2.18it/s]

 71%|███████   | 136/192 [00:43<00:26,  2.13it/s]

 71%|███████▏  | 137/192 [00:43<00:22,  2.39it/s]

 72%|███████▏  | 139/192 [00:43<00:14,  3.72it/s]

 73%|███████▎  | 140/192 [00:43<00:14,  3.57it/s]

 73%|███████▎  | 141/192 [00:44<00:17,  2.88it/s]

 74%|███████▍  | 142/192 [00:44<00:19,  2.57it/s]

 74%|███████▍  | 143/192 [00:45<00:23,  2.08it/s]

 75%|███████▌  | 144/192 [00:46<00:24,  1.93it/s]

 76%|███████▌  | 145/192 [00:46<00:26,  1.80it/s]

 76%|███████▌  | 146/192 [00:47<00:22,  2.06it/s]

 77%|███████▋  | 147/192 [00:47<00:16,  2.67it/s]

 78%|███████▊  | 149/192 [00:47<00:14,  3.07it/s]

 78%|███████▊  | 150/192 [00:48<00:14,  2.98it/s]

 79%|███████▊  | 151/192 [00:48<00:13,  3.05it/s]

 79%|███████▉  | 152/192 [00:49<00:15,  2.59it/s]

 80%|███████▉  | 153/192 [00:49<00:18,  2.09it/s]

 80%|████████  | 154/192 [00:50<00:16,  2.29it/s]

 81%|████████  | 155/192 [00:50<00:16,  2.21it/s]

 81%|████████▏ | 156/192 [00:51<00:17,  2.03it/s]

 82%|████████▏ | 157/192 [00:51<00:15,  2.20it/s]

 82%|████████▏ | 158/192 [00:51<00:13,  2.46it/s]

 83%|████████▎ | 159/192 [00:52<00:15,  2.15it/s]

 83%|████████▎ | 160/192 [00:52<00:13,  2.33it/s]

 84%|████████▍ | 161/192 [00:53<00:12,  2.46it/s]

 84%|████████▍ | 162/192 [00:53<00:13,  2.23it/s]

 85%|████████▍ | 163/192 [00:54<00:14,  1.97it/s]

 85%|████████▌ | 164/192 [00:54<00:13,  2.07it/s]

 86%|████████▌ | 165/192 [00:55<00:11,  2.30it/s]

 86%|████████▋ | 166/192 [00:55<00:10,  2.46it/s]

 87%|████████▋ | 167/192 [00:55<00:09,  2.59it/s]

 88%|████████▊ | 169/192 [00:56<00:07,  3.22it/s]

 89%|████████▊ | 170/192 [00:56<00:07,  3.13it/s]

 89%|████████▉ | 171/192 [00:56<00:05,  3.71it/s]

 90%|████████▉ | 172/192 [00:56<00:05,  3.54it/s]

 90%|█████████ | 173/192 [00:57<00:05,  3.41it/s]

 91%|█████████ | 174/192 [00:57<00:05,  3.21it/s]

 91%|█████████ | 175/192 [00:58<00:05,  3.08it/s]

 92%|█████████▏| 176/192 [00:58<00:05,  2.82it/s]

 92%|█████████▏| 177/192 [00:59<00:06,  2.25it/s]

 93%|█████████▎| 178/192 [00:59<00:06,  2.24it/s]

 93%|█████████▎| 179/192 [01:00<00:06,  2.15it/s]

 94%|█████████▍| 180/192 [01:00<00:05,  2.16it/s]

 94%|█████████▍| 181/192 [01:01<00:05,  2.10it/s]

 95%|█████████▍| 182/192 [01:01<00:04,  2.49it/s]

 95%|█████████▌| 183/192 [01:01<00:03,  2.33it/s]

 96%|█████████▌| 184/192 [01:02<00:03,  2.16it/s]

 96%|█████████▋| 185/192 [01:02<00:03,  2.16it/s]

 97%|█████████▋| 186/192 [01:02<00:02,  2.55it/s]

 97%|█████████▋| 187/192 [01:03<00:01,  2.66it/s]

 98%|█████████▊| 188/192 [01:03<00:01,  2.85it/s]

 98%|█████████▊| 189/192 [01:03<00:00,  3.48it/s]

 99%|█████████▉| 190/192 [01:04<00:00,  3.44it/s]

 99%|█████████▉| 191/192 [01:04<00:00,  3.40it/s]
                                                     

                                                 

 37%|███▋      | 350/935 [2:18:14<2:28:45, 15.26s/it]

100%|██████████| 192/192 [01:04<00:00,  3.40it/s]

                                                 
 38%|███▊      | 351/935 [2:18:31<5:43:36, 35.30s/it]
 38%|███▊      | 352/935 [2:18:46<4:44:52, 29.32s/it]
 38%|███▊      | 353/935 [2:19:03<4:09:15, 25.70s/it]Terminated