🦥 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 NVL. Num GPUs = 1. Max memory: 93.085 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: 5000 examples [00:00, 8091.85 examples/s]
Generating train split: 5000 examples [00:00, 7864.64 examples/s]

tokenizing (num_proc=8):   0%|          | 0/23500 [00:00<?, ? examples/s]
tokenizing (num_proc=8):   0%|          | 4/23500 [00:00<1:09:28,  5.64 examples/s]
tokenizing (num_proc=8):   0%|          | 42/23500 [00:00<05:45, 67.97 examples/s] 
tokenizing (num_proc=8):   0%|          | 91/23500 [00:00<02:38, 147.96 examples/s]
tokenizing (num_proc=8):   1%|          | 144/23500 [00:01<01:42, 227.60 examples/s]
tokenizing (num_proc=8):   1%|          | 214/23500 [00:01<01:09, 336.28 examples/s]
tokenizing (num_proc=8):   1%|▏         | 308/23500 [00:01<00:48, 479.52 examples/s]
tokenizing (num_proc=8):   2%|▏         | 436/23500 [00:01<00:33, 681.87 examples/s]
tokenizing (num_proc=8):   2%|▏         | 559/23500 [00:01<00:28, 800.90 examples/s]
tokenizing (num_proc=8):   3%|▎         | 671/23500 [00:01<00:25, 886.60 examples/s]
tokenizing (num_proc=8):   3%|▎         | 786/23500 [00:01<00:24, 941.87 examples/s]
tokenizing (num_proc=8):   4%|▍         | 893/23500 [00:01<00:23, 951.41 examples/s]
tokenizing (num_proc=8):   4%|▍         | 1021/23500 [00:01<00:21, 1041.49 examples/s]
tokenizing (num_proc=8):   5%|▍         | 1150/23500 [00:01<00:20, 1106.76 examples/s]
tokenizing (num_proc=8):   5%|▌         | 1273/23500 [00:02<00:20, 1069.69 examples/s]
tokenizing (num_proc=8):   6%|▌         | 1389/23500 [00:02<00:20, 1066.28 examples/s]
tokenizing (num_proc=8):   6%|▋         | 1498/23500 [00:02<00:20, 1058.59 examples/s]
tokenizing (num_proc=8):   7%|▋         | 1624/23500 [00:02<00:19, 1111.60 examples/s]
tokenizing (num_proc=8):   7%|▋         | 1750/23500 [00:02<00:19, 1105.52 examples/s]
tokenizing (num_proc=8):   8%|▊         | 1896/23500 [00:02<00:18, 1161.08 examples/s]
tokenizing (num_proc=8):   9%|▊         | 2025/23500 [00:02<00:18, 1169.16 examples/s]
tokenizing (num_proc=8):   9%|▉         | 2145/23500 [00:02<00:18, 1154.59 examples/s]
tokenizing (num_proc=8):  10%|▉         | 2269/23500 [00:02<00:18, 1143.44 examples/s]
tokenizing (num_proc=8):  10%|█         | 2386/23500 [00:03<00:18, 1118.32 examples/s]
tokenizing (num_proc=8):  11%|█         | 2535/23500 [00:03<00:17, 1210.10 examples/s]
tokenizing (num_proc=8):  11%|█▏        | 2683/23500 [00:03<00:16, 1270.71 examples/s]
tokenizing (num_proc=8):  12%|█▏        | 2823/23500 [00:03<00:15, 1294.14 examples/s]
tokenizing (num_proc=8):  13%|█▎        | 2961/23500 [00:03<00:16, 1266.90 examples/s]
tokenizing (num_proc=8):  13%|█▎        | 3100/23500 [00:03<00:16, 1212.38 examples/s]
tokenizing (num_proc=8):  14%|█▍        | 3236/23500 [00:03<00:16, 1238.76 examples/s]
tokenizing (num_proc=8):  14%|█▍        | 3371/23500 [00:03<00:16, 1255.94 examples/s]
tokenizing (num_proc=8):  15%|█▍        | 3516/23500 [00:03<00:15, 1291.03 examples/s]
tokenizing (num_proc=8):  16%|█▌        | 3647/23500 [00:04<00:15, 1286.86 examples/s]
tokenizing (num_proc=8):  16%|█▌        | 3805/23500 [00:04<00:14, 1344.91 examples/s]
tokenizing (num_proc=8):  17%|█▋        | 3946/23500 [00:04<00:14, 1334.37 examples/s]
tokenizing (num_proc=8):  17%|█▋        | 4087/23500 [00:04<00:14, 1349.10 examples/s]
tokenizing (num_proc=8):  18%|█▊        | 4234/23500 [00:04<00:14, 1358.50 examples/s]
tokenizing (num_proc=8):  19%|█▊        | 4374/23500 [00:04<00:14, 1320.03 examples/s]
tokenizing (num_proc=8):  19%|█▉        | 4507/23500 [00:04<00:14, 1305.55 examples/s]
tokenizing (num_proc=8):  20%|█▉        | 4654/23500 [00:04<00:14, 1320.82 examples/s]
tokenizing (num_proc=8):  20%|██        | 4801/23500 [00:04<00:13, 1345.18 examples/s]
tokenizing (num_proc=8):  21%|██        | 4943/23500 [00:04<00:13, 1358.12 examples/s]
tokenizing (num_proc=8):  22%|██▏       | 5086/23500 [00:05<00:13, 1366.98 examples/s]
tokenizing (num_proc=8):  22%|██▏       | 5225/23500 [00:05<00:13, 1369.97 examples/s]
tokenizing (num_proc=8):  23%|██▎       | 5368/23500 [00:05<00:13, 1367.76 examples/s]
tokenizing (num_proc=8):  24%|██▎       | 5542/23500 [00:05<00:12, 1406.50 examples/s]
tokenizing (num_proc=8):  24%|██▍       | 5683/23500 [00:05<00:13, 1360.50 examples/s]
tokenizing (num_proc=8):  25%|██▍       | 5828/23500 [00:05<00:12, 1366.25 examples/s]
tokenizing (num_proc=8):  25%|██▌       | 5972/23500 [00:05<00:13, 1314.23 examples/s]
tokenizing (num_proc=8):  26%|██▌       | 6108/23500 [00:05<00:13, 1316.17 examples/s]
tokenizing (num_proc=8):  27%|██▋       | 6276/23500 [00:05<00:12, 1411.13 examples/s]
tokenizing (num_proc=8):  27%|██▋       | 6420/23500 [00:06<00:12, 1412.11 examples/s]
tokenizing (num_proc=8):  28%|██▊       | 6571/23500 [00:06<00:12, 1369.79 examples/s]
tokenizing (num_proc=8):  29%|██▊       | 6712/23500 [00:06<00:13, 1275.24 examples/s]
tokenizing (num_proc=8):  29%|██▉       | 6846/23500 [00:06<00:14, 1164.88 examples/s]
tokenizing (num_proc=8):  30%|██▉       | 6975/23500 [00:06<00:14, 1139.96 examples/s]
tokenizing (num_proc=8):  30%|███       | 7095/23500 [00:06<00:15, 1086.84 examples/s]
tokenizing (num_proc=8):  31%|███       | 7217/23500 [00:06<00:14, 1118.80 examples/s]
tokenizing (num_proc=8):  31%|███       | 7333/23500 [00:06<00:15, 1069.68 examples/s]
tokenizing (num_proc=8):  32%|███▏      | 7444/23500 [00:07<00:16, 975.35 examples/s] 
tokenizing (num_proc=8):  32%|███▏      | 7552/23500 [00:07<00:16, 976.77 examples/s]
tokenizing (num_proc=8):  33%|███▎      | 7661/23500 [00:07<00:16, 951.11 examples/s]
tokenizing (num_proc=8):  33%|███▎      | 7778/23500 [00:07<00:15, 999.87 examples/s]
tokenizing (num_proc=8):  34%|███▎      | 7890/23500 [00:07<00:15, 994.34 examples/s]
tokenizing (num_proc=8):  34%|███▍      | 7992/23500 [00:07<00:16, 966.38 examples/s]
tokenizing (num_proc=8):  34%|███▍      | 8093/23500 [00:07<00:16, 941.32 examples/s]
tokenizing (num_proc=8):  35%|███▍      | 8191/23500 [00:07<00:19, 803.13 examples/s]
tokenizing (num_proc=8):  35%|███▌      | 8287/23500 [00:08<00:22, 668.99 examples/s]
tokenizing (num_proc=8):  36%|███▌      | 8365/23500 [00:08<00:23, 654.71 examples/s]
tokenizing (num_proc=8):  36%|███▌      | 8444/23500 [00:08<00:22, 682.79 examples/s]
tokenizing (num_proc=8):  36%|███▋      | 8520/23500 [00:08<00:21, 690.50 examples/s]
tokenizing (num_proc=8):  37%|███▋      | 8598/23500 [00:08<00:21, 688.22 examples/s]
tokenizing (num_proc=8):  37%|███▋      | 8675/23500 [00:08<00:21, 694.00 examples/s]
tokenizing (num_proc=8):  37%|███▋      | 8753/23500 [00:08<00:20, 707.31 examples/s]
tokenizing (num_proc=8):  38%|███▊      | 8863/23500 [00:08<00:18, 798.09 examples/s]
tokenizing (num_proc=8):  38%|███▊      | 8964/23500 [00:08<00:17, 850.42 examples/s]
tokenizing (num_proc=8):  39%|███▊      | 9071/23500 [00:09<00:15, 910.06 examples/s]
tokenizing (num_proc=8):  39%|███▉      | 9215/23500 [00:09<00:13, 1047.36 examples/s]
tokenizing (num_proc=8):  40%|███▉      | 9367/23500 [00:09<00:12, 1155.41 examples/s]
tokenizing (num_proc=8):  40%|████      | 9513/23500 [00:09<00:11, 1217.19 examples/s]
tokenizing (num_proc=8):  41%|████      | 9682/23500 [00:09<00:10, 1343.44 examples/s]
tokenizing (num_proc=8):  42%|████▏     | 9837/23500 [00:09<00:09, 1394.30 examples/s]
tokenizing (num_proc=8):  43%|████▎     | 10016/23500 [00:09<00:09, 1494.63 examples/s]
tokenizing (num_proc=8):  43%|████▎     | 10170/23500 [00:09<00:09, 1397.58 examples/s]
tokenizing (num_proc=8):  44%|████▍     | 10313/23500 [00:09<00:09, 1404.91 examples/s]
tokenizing (num_proc=8):  45%|████▍     | 10476/23500 [00:10<00:08, 1464.59 examples/s]
tokenizing (num_proc=8):  45%|████▌     | 10625/23500 [00:10<00:08, 1468.37 examples/s]
tokenizing (num_proc=8):  46%|████▌     | 10774/23500 [00:10<00:09, 1371.78 examples/s]
tokenizing (num_proc=8):  46%|████▋     | 10925/23500 [00:10<00:09, 1382.62 examples/s]
tokenizing (num_proc=8):  47%|████▋     | 11074/23500 [00:10<00:09, 1364.38 examples/s]
tokenizing (num_proc=8):  48%|████▊     | 11216/23500 [00:10<00:09, 1337.89 examples/s]
tokenizing (num_proc=8):  48%|████▊     | 11355/23500 [00:10<00:09, 1291.14 examples/s]
tokenizing (num_proc=8):  49%|████▉     | 11491/23500 [00:10<00:09, 1294.23 examples/s]
tokenizing (num_proc=8):  49%|████▉     | 11624/23500 [00:10<00:09, 1278.99 examples/s]
tokenizing (num_proc=8):  50%|█████     | 11757/23500 [00:11<00:09, 1286.71 examples/s]
tokenizing (num_proc=8):  51%|█████     | 11936/23500 [00:11<00:08, 1408.60 examples/s]
tokenizing (num_proc=8):  51%|█████▏    | 12095/23500 [00:11<00:08, 1412.41 examples/s]
tokenizing (num_proc=8):  52%|█████▏    | 12256/23500 [00:11<00:07, 1464.79 examples/s]
tokenizing (num_proc=8):  53%|█████▎    | 12405/23500 [00:11<00:07, 1425.15 examples/s]
tokenizing (num_proc=8):  53%|█████▎    | 12555/23500 [00:11<00:07, 1397.53 examples/s]
tokenizing (num_proc=8):  54%|█████▍    | 12700/23500 [00:11<00:07, 1379.14 examples/s]
tokenizing (num_proc=8):  55%|█████▍    | 12840/23500 [00:11<00:08, 1304.04 examples/s]
tokenizing (num_proc=8):  55%|█████▌    | 12982/23500 [00:11<00:08, 1265.80 examples/s]
tokenizing (num_proc=8):  56%|█████▌    | 13110/23500 [00:12<00:08, 1241.47 examples/s]
tokenizing (num_proc=8):  56%|█████▋    | 13235/23500 [00:12<00:08, 1224.51 examples/s]
tokenizing (num_proc=8):  57%|█████▋    | 13358/23500 [00:12<00:08, 1193.65 examples/s]
tokenizing (num_proc=8):  57%|█████▋    | 13484/23500 [00:12<00:08, 1181.30 examples/s]
tokenizing (num_proc=8):  58%|█████▊    | 13629/23500 [00:12<00:08, 1233.46 examples/s]
tokenizing (num_proc=8):  59%|█████▊    | 13770/23500 [00:12<00:07, 1232.83 examples/s]
tokenizing (num_proc=8):  59%|█████▉    | 13915/23500 [00:12<00:07, 1266.06 examples/s]
tokenizing (num_proc=8):  60%|█████▉    | 14044/23500 [00:12<00:08, 1164.34 examples/s]
tokenizing (num_proc=8):  60%|██████    | 14169/23500 [00:12<00:08, 1097.61 examples/s]
tokenizing (num_proc=8):  61%|██████    | 14291/23500 [00:13<00:08, 1047.32 examples/s]
tokenizing (num_proc=8):  61%|██████▏   | 14412/23500 [00:13<00:08, 1069.57 examples/s]
tokenizing (num_proc=8):  62%|██████▏   | 14537/23500 [00:13<00:08, 1103.32 examples/s]
tokenizing (num_proc=8):  62%|██████▏   | 14666/23500 [00:13<00:07, 1151.95 examples/s]
tokenizing (num_proc=8):  63%|██████▎   | 14790/23500 [00:13<00:07, 1116.95 examples/s]
tokenizing (num_proc=8):  64%|██████▎   | 14925/23500 [00:13<00:07, 1138.23 examples/s]
tokenizing (num_proc=8):  64%|██████▍   | 15053/23500 [00:13<00:07, 1162.82 examples/s]
tokenizing (num_proc=8):  65%|██████▍   | 15170/23500 [00:13<00:07, 1047.09 examples/s]
tokenizing (num_proc=8):  65%|██████▌   | 15306/23500 [00:13<00:07, 1100.73 examples/s]
tokenizing (num_proc=8):  66%|██████▌   | 15436/23500 [00:14<00:07, 1134.59 examples/s]
tokenizing (num_proc=8):  66%|██████▌   | 15565/23500 [00:14<00:06, 1147.28 examples/s]
tokenizing (num_proc=8):  67%|██████▋   | 15683/23500 [00:14<00:06, 1127.10 examples/s]
tokenizing (num_proc=8):  67%|██████▋   | 15798/23500 [00:14<00:07, 1092.39 examples/s]
tokenizing (num_proc=8):  68%|██████▊   | 15916/23500 [00:14<00:07, 1050.73 examples/s]
tokenizing (num_proc=8):  68%|██████▊   | 16022/23500 [00:14<00:07, 1041.13 examples/s]
tokenizing (num_proc=8):  69%|██████▊   | 16150/23500 [00:14<00:06, 1077.67 examples/s]
tokenizing (num_proc=8):  69%|██████▉   | 16265/23500 [00:14<00:06, 1049.10 examples/s]
tokenizing (num_proc=8):  70%|██████▉   | 16375/23500 [00:14<00:06, 1030.97 examples/s]
tokenizing (num_proc=8):  70%|███████   | 16504/23500 [00:15<00:06, 1029.08 examples/s]
tokenizing (num_proc=8):  71%|███████   | 16661/23500 [00:15<00:05, 1142.37 examples/s]
tokenizing (num_proc=8):  72%|███████▏  | 16815/23500 [00:15<00:05, 1222.12 examples/s]
tokenizing (num_proc=8):  72%|███████▏  | 16963/23500 [00:15<00:05, 1274.94 examples/s]
tokenizing (num_proc=8):  73%|███████▎  | 17103/23500 [00:15<00:04, 1299.60 examples/s]
tokenizing (num_proc=8):  74%|███████▎  | 17279/23500 [00:15<00:04, 1408.26 examples/s]
tokenizing (num_proc=8):  74%|███████▍  | 17423/23500 [00:15<00:04, 1383.33 examples/s]
tokenizing (num_proc=8):  75%|███████▍  | 17566/23500 [00:15<00:04, 1328.09 examples/s]
tokenizing (num_proc=8):  75%|███████▌  | 17707/23500 [00:15<00:04, 1232.76 examples/s]
tokenizing (num_proc=8):  76%|███████▌  | 17836/23500 [00:16<00:04, 1247.53 examples/s]
tokenizing (num_proc=8):  76%|███████▋  | 17975/23500 [00:16<00:04, 1262.93 examples/s]
tokenizing (num_proc=8):  77%|███████▋  | 18119/23500 [00:16<00:04, 1264.52 examples/s]
tokenizing (num_proc=8):  78%|███████▊  | 18271/23500 [00:16<00:03, 1324.72 examples/s]
tokenizing (num_proc=8):  78%|███████▊  | 18415/23500 [00:16<00:03, 1339.02 examples/s]
tokenizing (num_proc=8):  79%|███████▉  | 18605/23500 [00:16<00:03, 1428.24 examples/s]
tokenizing (num_proc=8):  80%|███████▉  | 18756/23500 [00:16<00:03, 1341.41 examples/s]
tokenizing (num_proc=8):  80%|████████  | 18899/23500 [00:16<00:03, 1326.18 examples/s]
tokenizing (num_proc=8):  81%|████████  | 19041/23500 [00:16<00:03, 1331.40 examples/s]
tokenizing (num_proc=8):  82%|████████▏ | 19187/23500 [00:17<00:03, 1335.26 examples/s]
tokenizing (num_proc=8):  82%|████████▏ | 19332/23500 [00:17<00:03, 1344.27 examples/s]
tokenizing (num_proc=8):  83%|████████▎ | 19472/23500 [00:17<00:02, 1351.57 examples/s]
tokenizing (num_proc=8):  83%|████████▎ | 19620/23500 [00:17<00:02, 1329.84 examples/s]
tokenizing (num_proc=8):  84%|████████▍ | 19785/23500 [00:17<00:02, 1401.40 examples/s]
tokenizing (num_proc=8):  85%|████████▍ | 19933/23500 [00:17<00:02, 1410.51 examples/s]
tokenizing (num_proc=8):  85%|████████▌ | 20090/23500 [00:17<00:02, 1440.60 examples/s]
tokenizing (num_proc=8):  86%|████████▌ | 20248/23500 [00:17<00:02, 1433.86 examples/s]
tokenizing (num_proc=8):  87%|████████▋ | 20394/23500 [00:17<00:02, 1429.43 examples/s]
tokenizing (num_proc=8):  87%|████████▋ | 20553/23500 [00:18<00:02, 1458.41 examples/s]
tokenizing (num_proc=8):  88%|████████▊ | 20704/23500 [00:18<00:01, 1464.74 examples/s]
tokenizing (num_proc=8):  89%|████████▉ | 20865/23500 [00:18<00:01, 1404.55 examples/s]
tokenizing (num_proc=8):  89%|████████▉ | 21008/23500 [00:18<00:01, 1371.60 examples/s]
tokenizing (num_proc=8):  90%|█████████ | 21159/23500 [00:18<00:01, 1247.01 examples/s]
tokenizing (num_proc=8):  91%|█████████ | 21293/23500 [00:18<00:01, 1251.72 examples/s]
tokenizing (num_proc=8):  91%|█████████ | 21438/23500 [00:18<00:01, 1261.41 examples/s]
tokenizing (num_proc=8):  92%|█████████▏| 21570/23500 [00:18<00:01, 1259.67 examples/s]
tokenizing (num_proc=8):  92%|█████████▏| 21697/23500 [00:18<00:01, 1201.26 examples/s]
tokenizing (num_proc=8):  93%|█████████▎| 21825/23500 [00:19<00:01, 1065.13 examples/s]
tokenizing (num_proc=8):  93%|█████████▎| 21944/23500 [00:19<00:01, 1045.65 examples/s]
tokenizing (num_proc=8):  94%|█████████▍| 22067/23500 [00:19<00:01, 1082.73 examples/s]
tokenizing (num_proc=8):  94%|█████████▍| 22183/23500 [00:19<00:01, 1034.80 examples/s]
tokenizing (num_proc=8):  95%|█████████▍| 22296/23500 [00:19<00:01, 964.02 examples/s] 
tokenizing (num_proc=8):  95%|█████████▌| 22398/23500 [00:19<00:01, 913.85 examples/s]
tokenizing (num_proc=8):  96%|█████████▌| 22493/23500 [00:19<00:01, 776.54 examples/s]
tokenizing (num_proc=8):  96%|█████████▌| 22578/23500 [00:20<00:01, 756.92 examples/s]
tokenizing (num_proc=8):  96%|█████████▋| 22663/23500 [00:20<00:01, 772.51 examples/s]
tokenizing (num_proc=8):  97%|█████████▋| 22751/23500 [00:20<00:01, 686.09 examples/s]
tokenizing (num_proc=8):  97%|█████████▋| 22823/23500 [00:20<00:01, 664.16 examples/s]
tokenizing (num_proc=8):  97%|█████████▋| 22902/23500 [00:20<00:00, 609.17 examples/s]
tokenizing (num_proc=8):  98%|█████████▊| 22972/23500 [00:20<00:00, 624.54 examples/s]
tokenizing (num_proc=8):  98%|█████████▊| 23037/23500 [00:20<00:00, 596.84 examples/s]
tokenizing (num_proc=8):  98%|█████████▊| 23100/23500 [00:20<00:00, 597.90 examples/s]
tokenizing (num_proc=8):  99%|█████████▊| 23161/23500 [00:21<00:00, 470.45 examples/s]
tokenizing (num_proc=8):  99%|█████████▉| 23214/23500 [00:21<00:00, 290.08 examples/s]
tokenizing (num_proc=8):  99%|█████████▉| 23261/23500 [00:21<00:01, 233.04 examples/s]
tokenizing (num_proc=8):  99%|█████████▉| 23300/23500 [00:22<00:00, 204.54 examples/s]
tokenizing (num_proc=8):  99%|█████████▉| 23330/23500 [00:22<00:00, 182.48 examples/s]
tokenizing (num_proc=8):  99%|█████████▉| 23354/23500 [00:22<00:00, 174.63 examples/s]
tokenizing (num_proc=8):  99%|█████████▉| 23375/23500 [00:22<00:00, 178.93 examples/s]
tokenizing (num_proc=8): 100%|█████████▉| 23398/23500 [00:22<00:00, 166.57 examples/s]
tokenizing (num_proc=8): 100%|█████████▉| 23422/23500 [00:22<00:00, 161.63 examples/s]
tokenizing (num_proc=8): 100%|█████████▉| 23444/23500 [00:23<00:00, 153.67 examples/s]
tokenizing (num_proc=8): 100%|█████████▉| 23467/23500 [00:23<00:00, 164.53 examples/s]
tokenizing (num_proc=8): 100%|█████████▉| 23487/23500 [00:23<00:00, 170.20 examples/s]
tokenizing (num_proc=8): 100%|██████████| 23500/23500 [00:23<00:00, 983.16 examples/s]

Filter:   0%|          | 0/23500 [00:00<?, ? examples/s]
Filter:   4%|▍         | 1000/23500 [00:00<00:05, 3765.36 examples/s]
Filter:   9%|▊         | 2000/23500 [00:00<00:05, 3992.13 examples/s]
Filter:  13%|█▎        | 3000/23500 [00:00<00:05, 3962.68 examples/s]
Filter:  17%|█▋        | 4000/23500 [00:00<00:04, 4233.20 examples/s]
Filter:  21%|██▏       | 5000/23500 [00:01<00:04, 4133.12 examples/s]
Filter:  26%|██▌       | 6000/23500 [00:01<00:04, 4273.69 examples/s]
Filter:  30%|██▉       | 7000/23500 [00:01<00:03, 4350.94 examples/s]
Filter:  34%|███▍      | 8000/23500 [00:01<00:03, 4293.96 examples/s]
Filter:  38%|███▊      | 9000/23500 [00:02<00:03, 4275.71 examples/s]
Filter:  43%|████▎     | 10000/23500 [00:02<00:03, 4350.97 examples/s]
Filter:  47%|████▋     | 11000/23500 [00:02<00:02, 4296.58 examples/s]
Filter:  51%|█████     | 12000/23500 [00:02<00:02, 4293.70 examples/s]
Filter:  55%|█████▌    | 13000/23500 [00:03<00:02, 4265.56 examples/s]
Filter:  60%|█████▉    | 14000/23500 [00:03<00:02, 4185.12 examples/s]
Filter:  64%|██████▍   | 15000/23500 [00:03<00:02, 4197.43 examples/s]
Filter:  68%|██████▊   | 16000/23500 [00:03<00:01, 4411.62 examples/s]
Filter:  72%|███████▏  | 17000/23500 [00:03<00:01, 4712.85 examples/s]
Filter:  77%|███████▋  | 18000/23500 [00:04<00:01, 4997.75 examples/s]
Filter:  81%|████████  | 19000/23500 [00:04<00:00, 5232.62 examples/s]
Filter:  85%|████████▌ | 20000/23500 [00:04<00:00, 5303.41 examples/s]
Filter:  89%|████████▉ | 21000/23500 [00:04<00:00, 5372.07 examples/s]
Filter:  94%|█████████▎| 22000/23500 [00:04<00:00, 5403.62 examples/s]
Filter:  98%|█████████▊| 23000/23500 [00:05<00:00, 5440.29 examples/s]
Filter: 100%|██████████| 23500/23500 [00:05<00:00, 4618.95 examples/s]

Filter:   0%|          | 0/23500 [00:00<?, ? examples/s]
Filter:   4%|▍         | 1000/23500 [00:00<00:04, 5551.97 examples/s]
Filter:   9%|▊         | 2000/23500 [00:00<00:04, 4954.27 examples/s]
Filter:  13%|█▎        | 3000/23500 [00:00<00:04, 5051.64 examples/s]
Filter:  17%|█▋        | 4000/23500 [00:00<00:03, 5298.15 examples/s]
Filter:  21%|██▏       | 5000/23500 [00:00<00:03, 5181.79 examples/s]
Filter:  26%|██▌       | 6000/23500 [00:01<00:03, 5362.72 examples/s]
Filter:  30%|██▉       | 7000/23500 [00:01<00:03, 5248.20 examples/s]
Filter:  34%|███▍      | 8000/23500 [00:01<00:02, 5242.69 examples/s]
Filter:  38%|███▊      | 9000/23500 [00:01<00:02, 5246.60 examples/s]
Filter:  43%|████▎     | 10000/23500 [00:01<00:02, 5377.23 examples/s]
Filter:  47%|████▋     | 11000/23500 [00:02<00:02, 5340.63 examples/s]
Filter:  51%|█████     | 12000/23500 [00:02<00:02, 5253.38 examples/s]
Filter:  55%|█████▌    | 13000/23500 [00:02<00:01, 5276.49 examples/s]
Filter:  60%|█████▉    | 14000/23500 [00:02<00:01, 5004.39 examples/s]
Filter:  64%|██████▍   | 15000/23500 [00:02<00:01, 5070.68 examples/s]
Filter:  68%|██████▊   | 16000/23500 [00:03<00:01, 5118.89 examples/s]
Filter:  72%|███████▏  | 17000/23500 [00:03<00:01, 5159.28 examples/s]
Filter:  77%|███████▋  | 18000/23500 [00:03<00:01, 5224.42 examples/s]
Filter:  81%|████████  | 19000/23500 [00:03<00:00, 5124.44 examples/s]
Filter:  85%|████████▌ | 20000/23500 [00:03<00:00, 5193.48 examples/s]
Filter:  89%|████████▉ | 21000/23500 [00:04<00:00, 5205.11 examples/s]
Filter:  94%|█████████▎| 22000/23500 [00:04<00:00, 5216.84 examples/s]
Filter:  98%|█████████▊| 23000/23500 [00:04<00:00, 5221.32 examples/s]
Filter: 100%|██████████| 23500/23500 [00:04<00:00, 5215.44 examples/s]
supervised tokens: tool 4521017, replay 11007513 (70.9% replay)
replay capped to 25% of supervised tokens: kept 1506480 replay tokens, 1265 replay rows
rows: 23500 raw -> 15339 kept; by source: {'apigen': 4824, 'xlam': 5000, 'recovery': 3750, 'replay:urban_12738_cleaned': 1265, 'efficiency': 500}
[manifest] git=fedc86c2f311602b2ebdb86e609383ceee4786c0  data_sha256={'train_olmo-urban_replay50.jsonl': '5efef55a9b7c', 'xlam5000_max1call.jsonl': 'a8aae6cf5c36'}
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-urban/wandb/wandb/offline-run-20261012_205325-hbpaapsf
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 = 14,955 | 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 [00:44<11:27:53, 44.19s/it]
  0%|          | 2/935 [01:21<10:21:40, 39.98s/it]
  0%|          | 3/935 [01:51<9:13:56, 35.66s/it] 
  0%|          | 4/935 [02:22<8:45:05, 33.84s/it]
  1%|          | 5/935 [02:56<8:43:23, 33.77s/it]
                                                 

  1%|          | 5/935 [02:56<8:43:23, 33.77s/it]
  1%|          | 6/935 [03:21<7:54:59, 30.68s/it]
  1%|          | 7/935 [03:49<7:44:03, 30.00s/it]
  1%|          | 8/935 [04:25<8:09:30, 31.68s/it]
  1%|          | 9/935 [05:00<8:25:56, 32.78s/it]
  1%|          | 10/935 [05:30<8:12:33, 31.95s/it]
                                                  

  1%|          | 10/935 [05:30<8:12:33, 31.95s/it]
  1%|          | 11/935 [06:01<8:07:14, 31.64s/it]
  1%|▏         | 12/935 [06:33<8:07:36, 31.70s/it]
  1%|▏         | 13/935 [06:56<7:28:23, 29.18s/it]
  1%|▏         | 14/935 [07:20<7:06:01, 27.75s/it]
  2%|▏         | 15/935 [07:48<7:02:59, 27.59s/it]
                                                  

  2%|▏         | 15/935 [07:48<7:02:59, 27.59s/it]
  2%|▏         | 16/935 [08:14<6:56:34, 27.20s/it]
  2%|▏         | 17/935 [08:49<7:32:11, 29.55s/it]
  2%|▏         | 18/935 [09:19<7:35:50, 29.83s/it]
  2%|▏         | 19/935 [09:48<7:30:05, 29.48s/it]
  2%|▏         | 20/935 [10:15<7:20:04, 28.86s/it]
                                                  

  2%|▏         | 20/935 [10:15<7:20:04, 28.86s/it]
  2%|▏         | 21/935 [10:50<7:46:17, 30.61s/it]
  2%|▏         | 22/935 [11:22<7:49:06, 30.83s/it]
  2%|▏         | 23/935 [11:53<7:53:13, 31.13s/it]
  3%|▎         | 24/935 [12:19<7:25:57, 29.37s/it]
  3%|▎         | 25/935 [12:52<7:43:58, 30.59s/it]
                                                  

  3%|▎         | 25/935 [12:52<7:43:58, 30.59s/it]
  3%|▎         | 26/935 [13:21<7:36:22, 30.12s/it]
  3%|▎         | 27/935 [13:46<7:14:18, 28.70s/it]
  3%|▎         | 28/935 [14:16<7:18:02, 28.98s/it]
  3%|▎         | 29/935 [14:54<7:58:10, 31.67s/it]
  3%|▎         | 30/935 [15:28<8:06:03, 32.22s/it]
                                                  

  3%|▎         | 30/935 [15:28<8:06:03, 32.22s/it]
  3%|▎         | 31/935 [15:56<7:50:15, 31.21s/it]
  3%|▎         | 32/935 [16:27<7:45:53, 30.96s/it]
  4%|▎         | 33/935 [16:51<7:15:24, 28.96s/it]
  4%|▎         | 34/935 [17:22<7:25:42, 29.68s/it]
  4%|▎         | 35/935 [17:50<7:14:41, 28.98s/it]
                                                  

  4%|▎         | 35/935 [17:50<7:14:41, 28.98s/it]
  4%|▍         | 36/935 [18:19<7:16:56, 29.16s/it]
  4%|▍         | 37/935 [18:44<6:56:12, 27.81s/it]
  4%|▍         | 38/935 [19:09<6:43:30, 26.99s/it]
  4%|▍         | 39/935 [19:42<7:11:41, 28.91s/it]
  4%|▍         | 40/935 [20:08<6:55:53, 27.88s/it]
                                                  

  4%|▍         | 40/935 [20:08<6:55:53, 27.88s/it]
  4%|▍         | 41/935 [20:36<6:57:37, 28.03s/it]
  4%|▍         | 42/935 [21:06<7:05:53, 28.62s/it]
  5%|▍         | 43/935 [21:38<7:20:36, 29.64s/it]
  5%|▍         | 44/935 [21:59<6:40:14, 26.95s/it]
  5%|▍         | 45/935 [22:32<7:05:43, 28.70s/it]
                                                  

  5%|▍         | 45/935 [22:32<7:05:43, 28.70s/it]
  5%|▍         | 46/935 [23:06<7:30:38, 30.41s/it]
  5%|▌         | 47/935 [23:26<6:44:56, 27.36s/it]
  5%|▌         | 48/935 [23:55<6:51:28, 27.83s/it]
  5%|▌         | 49/935 [24:18<6:27:27, 26.24s/it]
  5%|▌         | 50/935 [24:42<6:17:25, 25.59s/it]
                                                  

  5%|▌         | 50/935 [24:42<6:17:25, 25.59s/it]Unsloth: Will smartly offload gradients to save VRAM!
Unsloth: Double buffering enabled (parallel H2D + compute) for backward pass.
{'loss': 7.0706, 'grad_norm': 11.332925796508789, 'learning_rate': 1.7021276595744682e-05, 'epoch': 0.01}
{'loss': 6.4977, 'grad_norm': 6.2103447914123535, 'learning_rate': 3.829787234042553e-05, 'epoch': 0.01}
{'loss': 5.6125, 'grad_norm': 4.533832550048828, 'learning_rate': 5.9574468085106384e-05, 'epoch': 0.02}
{'loss': 4.7692, 'grad_norm': 3.615572214126587, 'learning_rate': 8.085106382978723e-05, 'epoch': 0.02}
{'loss': 3.9879, 'grad_norm': 2.759181022644043, 'learning_rate': 0.00010212765957446809, 'epoch': 0.03}
{'loss': 3.339, 'grad_norm': 7.817636966705322, 'learning_rate': 0.00012340425531914893, 'epoch': 0.03}
{'loss': 2.782, 'grad_norm': 1.8590707778930664, 'learning_rate': 0.0001446808510638298, 'epoch': 0.04}
{'loss': 2.0399, 'grad_norm': 1.6293493509292603, 'learning_rate': 0.00016595744680851065, 'epoch': 0.04}
{'loss': 1.7934, 'grad_norm': 1.9784948825836182, 'learning_rate': 0.0001872340425531915, 'epoch': 0.05}
{'loss': 1.3086, 'grad_norm': 1.2116178274154663, 'learning_rate': 0.00019999749676283775, 'epoch': 0.05}


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

Filter: 100%|██████████| 384/384 [00:00<00:00, 1177.30 examples/s]
Filter: 100%|██████████| 384/384 [00:00<00:00, 1167.09 examples/s]


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

  1%|          | 2/192 [00:01<02:46,  1.14it/s]

  2%|▏         | 3/192 [00:03<03:36,  1.14s/it]

  2%|▏         | 4/192 [00:04<04:08,  1.32s/it]

  3%|▎         | 5/192 [00:06<04:12,  1.35s/it]

  3%|▎         | 6/192 [00:07<04:22,  1.41s/it]

  4%|▎         | 7/192 [00:08<03:52,  1.26s/it]

  4%|▍         | 8/192 [00:10<04:05,  1.34s/it]

  5%|▍         | 9/192 [00:12<04:34,  1.50s/it]

  5%|▌         | 10/192 [00:13<04:37,  1.53s/it]

  6%|▌         | 11/192 [00:15<04:37,  1.53s/it]

  6%|▋         | 12/192 [00:16<04:04,  1.36s/it]

  7%|▋         | 13/192 [00:17<04:04,  1.37s/it]

  7%|▋         | 14/192 [00:19<04:19,  1.46s/it]

  8%|▊         | 15/192 [00:20<04:01,  1.36s/it]

  8%|▊         | 16/192 [00:21<03:59,  1.36s/it]

  9%|▉         | 17/192 [00:23<04:12,  1.44s/it]

  9%|▉         | 18/192 [00:25<04:30,  1.56s/it]

 10%|▉         | 19/192 [00:26<04:09,  1.44s/it]

 10%|█         | 20/192 [00:27<03:49,  1.34s/it]

 11%|█         | 21/192 [00:28<03:51,  1.35s/it]

 11%|█▏        | 22/192 [00:30<03:58,  1.40s/it]

 12%|█▏        | 23/192 [00:31<03:38,  1.29s/it]

 12%|█▎        | 24/192 [00:32<03:06,  1.11s/it]

 13%|█▎        | 25/192 [00:32<02:44,  1.02it/s]

 14%|█▎        | 26/192 [00:33<02:31,  1.10it/s]

 14%|█▍        | 27/192 [00:34<02:23,  1.15it/s]

 15%|█▍        | 28/192 [00:35<02:30,  1.09it/s]

 15%|█▌        | 29/192 [00:36<02:34,  1.05it/s]

 16%|█▌        | 30/192 [00:36<01:53,  1.42it/s]

 16%|█▌        | 31/192 [00:37<02:14,  1.20it/s]

 17%|█▋        | 32/192 [00:38<02:22,  1.12it/s]

 17%|█▋        | 33/192 [00:40<03:06,  1.17s/it]

 18%|█▊        | 34/192 [00:42<03:42,  1.41s/it]

 18%|█▊        | 35/192 [00:44<03:52,  1.48s/it]

 19%|█▉        | 36/192 [00:45<03:45,  1.45s/it]

 19%|█▉        | 37/192 [00:46<03:13,  1.25s/it]

 20%|█▉        | 38/192 [00:47<02:59,  1.17s/it]

 20%|██        | 39/192 [00:48<02:50,  1.12s/it]

 21%|██        | 40/192 [00:49<03:09,  1.25s/it]

 21%|██▏       | 41/192 [00:51<03:21,  1.33s/it]

 22%|██▏       | 42/192 [00:52<03:03,  1.23s/it]

 22%|██▏       | 43/192 [00:53<03:20,  1.34s/it]

 23%|██▎       | 44/192 [00:55<03:19,  1.35s/it]

 23%|██▎       | 45/192 [00:55<02:26,  1.00it/s]

 24%|██▍       | 46/192 [00:56<02:44,  1.12s/it]

 24%|██▍       | 47/192 [00:58<03:12,  1.33s/it]

 25%|██▌       | 48/192 [00:59<03:09,  1.32s/it]

 26%|██▌       | 49/192 [01:01<02:56,  1.23s/it]

 26%|██▌       | 50/192 [01:01<02:34,  1.09s/it]

 27%|██▋       | 51/192 [01:03<02:47,  1.19s/it]

 27%|██▋       | 52/192 [01:04<02:43,  1.17s/it]

 28%|██▊       | 53/192 [01:04<02:01,  1.14it/s]

 28%|██▊       | 54/192 [01:05<02:17,  1.00it/s]

 29%|██▊       | 55/192 [01:07<02:43,  1.19s/it]

 29%|██▉       | 56/192 [01:08<02:49,  1.24s/it]

 30%|██▉       | 57/192 [01:10<03:06,  1.38s/it]

 30%|███       | 58/192 [01:11<02:49,  1.27s/it]

 31%|███       | 59/192 [01:13<03:04,  1.39s/it]

 31%|███▏      | 60/192 [01:15<03:31,  1.60s/it]

 32%|███▏      | 61/192 [01:16<02:56,  1.35s/it]

 32%|███▏      | 62/192 [01:17<02:43,  1.26s/it]

 33%|███▎      | 63/192 [01:18<02:40,  1.24s/it]

 33%|███▎      | 64/192 [01:19<02:27,  1.15s/it]

 34%|███▍      | 65/192 [01:20<02:30,  1.19s/it]

 34%|███▍      | 66/192 [01:21<02:20,  1.12s/it]

 35%|███▍      | 67/192 [01:22<02:06,  1.01s/it]

 35%|███▌      | 68/192 [01:22<01:55,  1.08it/s]

 36%|███▌      | 69/192 [01:24<02:18,  1.12s/it]

 36%|███▋      | 70/192 [01:25<02:21,  1.16s/it]

 37%|███▋      | 71/192 [01:26<02:17,  1.14s/it]

 38%|███▊      | 72/192 [01:28<02:41,  1.34s/it]

 38%|███▊      | 73/192 [01:30<03:07,  1.58s/it]

 39%|███▊      | 74/192 [01:31<02:30,  1.28s/it]

 39%|███▉      | 75/192 [01:32<02:13,  1.14s/it]

 40%|███▉      | 76/192 [01:33<02:23,  1.23s/it]

 40%|████      | 77/192 [01:35<02:33,  1.33s/it]

 41%|████      | 78/192 [01:36<02:35,  1.36s/it]

 41%|████      | 79/192 [01:37<02:05,  1.11s/it]

 42%|████▏     | 80/192 [01:38<02:04,  1.12s/it]

 42%|████▏     | 81/192 [01:39<02:17,  1.24s/it]

 43%|████▎     | 82/192 [01:41<02:24,  1.32s/it]

 43%|████▎     | 83/192 [01:43<02:41,  1.48s/it]

 44%|████▍     | 84/192 [01:44<02:28,  1.37s/it]

 44%|████▍     | 85/192 [01:45<02:21,  1.33s/it]

 45%|████▍     | 86/192 [01:46<02:13,  1.26s/it]

 45%|████▌     | 87/192 [01:47<02:07,  1.21s/it]

 46%|████▌     | 88/192 [01:48<01:59,  1.15s/it]

 46%|████▋     | 89/192 [01:49<01:53,  1.10s/it]

 47%|████▋     | 90/192 [01:51<02:02,  1.20s/it]

 47%|████▋     | 91/192 [01:52<02:06,  1.26s/it]

 48%|████▊     | 92/192 [01:54<02:20,  1.40s/it]

 48%|████▊     | 93/192 [01:55<02:02,  1.24s/it]

 49%|████▉     | 94/192 [01:56<02:03,  1.26s/it]

 49%|████▉     | 95/192 [01:57<02:00,  1.24s/it]

 50%|█████     | 96/192 [01:59<02:05,  1.31s/it]

 51%|█████     | 97/192 [01:59<01:43,  1.09s/it]

 51%|█████     | 98/192 [02:00<01:32,  1.01it/s]

 52%|█████▏    | 99/192 [02:01<01:38,  1.06s/it]

 52%|█████▏    | 100/192 [02:03<01:47,  1.17s/it]

 53%|█████▎    | 101/192 [02:05<02:07,  1.40s/it]

 53%|█████▎    | 102/192 [02:05<01:45,  1.17s/it]

 54%|█████▎    | 103/192 [02:06<01:45,  1.19s/it]

 54%|█████▍    | 104/192 [02:08<01:50,  1.26s/it]

 55%|█████▍    | 105/192 [02:09<01:46,  1.23s/it]

 55%|█████▌    | 106/192 [02:10<01:40,  1.17s/it]

 56%|█████▌    | 107/192 [02:11<01:40,  1.18s/it]

 56%|█████▋    | 108/192 [02:12<01:33,  1.11s/it]

 57%|█████▋    | 109/192 [02:14<01:55,  1.39s/it]

 57%|█████▋    | 110/192 [02:16<02:02,  1.50s/it]

 58%|█████▊    | 111/192 [02:18<02:03,  1.53s/it]

 58%|█████▊    | 112/192 [02:19<02:01,  1.52s/it]

 59%|█████▉    | 113/192 [02:20<01:38,  1.24s/it]

 59%|█████▉    | 114/192 [02:20<01:11,  1.09it/s]

 60%|█████▉    | 115/192 [02:20<01:02,  1.23it/s]

 60%|██████    | 116/192 [02:21<01:01,  1.23it/s]

 61%|██████    | 117/192 [02:22<00:52,  1.43it/s]

 61%|██████▏   | 118/192 [02:23<01:10,  1.05it/s]

 62%|██████▏   | 119/192 [02:25<01:22,  1.13s/it]

 62%|██████▎   | 120/192 [02:26<01:26,  1.20s/it]

 63%|██████▎   | 121/192 [02:28<01:37,  1.37s/it]

 64%|██████▎   | 122/192 [02:29<01:38,  1.41s/it]

 64%|██████▍   | 123/192 [02:30<01:19,  1.15s/it]

 65%|██████▍   | 124/192 [02:31<01:24,  1.25s/it]

 65%|██████▌   | 125/192 [02:33<01:35,  1.42s/it]

 66%|██████▌   | 126/192 [02:34<01:24,  1.28s/it]

 66%|██████▌   | 127/192 [02:36<01:27,  1.35s/it]

 67%|██████▋   | 128/192 [02:37<01:22,  1.29s/it]

 67%|██████▋   | 129/192 [02:39<01:32,  1.46s/it]

 68%|██████▊   | 130/192 [02:40<01:31,  1.48s/it]

 68%|██████▊   | 131/192 [02:42<01:43,  1.69s/it]

 69%|██████▉   | 132/192 [02:44<01:38,  1.64s/it]

 69%|██████▉   | 133/192 [02:45<01:31,  1.55s/it]

 70%|██████▉   | 134/192 [02:47<01:28,  1.53s/it]

 70%|███████   | 135/192 [02:47<01:11,  1.26s/it]

 71%|███████   | 136/192 [02:49<01:09,  1.23s/it]

 71%|███████▏  | 137/192 [02:50<01:18,  1.43s/it]

 72%|███████▏  | 138/192 [02:52<01:16,  1.42s/it]

 72%|███████▏  | 139/192 [02:53<01:08,  1.29s/it]

 73%|███████▎  | 141/192 [02:54<00:50,  1.02it/s]

 74%|███████▍  | 142/192 [02:56<01:00,  1.21s/it]

 74%|███████▍  | 143/192 [02:57<00:53,  1.09s/it]

 75%|███████▌  | 144/192 [02:57<00:47,  1.00it/s]

 76%|███████▌  | 145/192 [02:58<00:40,  1.15it/s]

 76%|███████▌  | 146/192 [02:59<00:47,  1.04s/it]

 77%|███████▋  | 147/192 [03:01<00:48,  1.08s/it]

 77%|███████▋  | 148/192 [03:03<00:59,  1.36s/it]

 78%|███████▊  | 149/192 [03:05<01:07,  1.58s/it]

 78%|███████▊  | 150/192 [03:06<00:59,  1.42s/it]

 79%|███████▊  | 151/192 [03:06<00:42,  1.05s/it]

 79%|███████▉  | 152/192 [03:07<00:42,  1.07s/it]

 80%|███████▉  | 153/192 [03:08<00:35,  1.10it/s]

 80%|████████  | 154/192 [03:09<00:42,  1.11s/it]

 81%|████████  | 155/192 [03:10<00:42,  1.16s/it]

 81%|████████▏ | 156/192 [03:12<00:45,  1.27s/it]

 82%|████████▏ | 157/192 [03:13<00:38,  1.09s/it]

 82%|████████▏ | 158/192 [03:14<00:37,  1.10s/it]

 83%|████████▎ | 159/192 [03:15<00:36,  1.11s/it]

 83%|████████▎ | 160/192 [03:15<00:25,  1.23it/s]

 84%|████████▍ | 161/192 [03:16<00:26,  1.15it/s]

 84%|████████▍ | 162/192 [03:17<00:26,  1.12it/s]

 85%|████████▍ | 163/192 [03:17<00:19,  1.49it/s]

 85%|████████▌ | 164/192 [03:18<00:24,  1.15it/s]

 86%|████████▌ | 165/192 [03:19<00:24,  1.12it/s]

 86%|████████▋ | 166/192 [03:21<00:24,  1.05it/s]

 87%|████████▋ | 167/192 [03:22<00:25,  1.01s/it]

 88%|████████▊ | 168/192 [03:23<00:27,  1.15s/it]

 88%|████████▊ | 169/192 [03:25<00:28,  1.24s/it]

 89%|████████▊ | 170/192 [03:25<00:20,  1.10it/s]

 89%|████████▉ | 171/192 [03:26<00:19,  1.05it/s]

 90%|█████████ | 173/192 [03:27<00:16,  1.14it/s]

 91%|█████████ | 174/192 [03:29<00:20,  1.14s/it]

 91%|█████████ | 175/192 [03:31<00:20,  1.19s/it]

 92%|█████████▏| 176/192 [03:31<00:17,  1.06s/it]

 92%|█████████▏| 177/192 [03:32<00:15,  1.05s/it]

 93%|█████████▎| 178/192 [03:34<00:15,  1.13s/it]

 93%|█████████▎| 179/192 [03:35<00:15,  1.19s/it]

 94%|█████████▍| 180/192 [03:36<00:14,  1.19s/it]

 94%|█████████▍| 181/192 [03:37<00:12,  1.17s/it]

 95%|█████████▍| 182/192 [03:40<00:14,  1.47s/it]

 95%|█████████▌| 183/192 [03:40<00:10,  1.22s/it]

 96%|█████████▌| 184/192 [03:41<00:09,  1.18s/it]

 96%|█████████▋| 185/192 [03:42<00:07,  1.05s/it]

 97%|█████████▋| 186/192 [03:43<00:06,  1.12s/it]

 97%|█████████▋| 187/192 [03:45<00:05,  1.18s/it]

 98%|█████████▊| 188/192 [03:45<00:03,  1.17it/s]

 99%|█████████▉| 190/192 [03:46<00:01,  1.39it/s]

 99%|█████████▉| 191/192 [03:47<00:00,  1.19it/s]

100%|██████████| 192/192 [03:48<00:00,  1.32it/s]
                                                  

                                                 

  5%|▌         | 50/935 [28:33<6:17:25, 25.59s/it]

100%|██████████| 192/192 [03:48<00:00,  1.32it/s]

                                                 
  5%|▌         | 51/935 [29:06<23:52:21, 97.22s/it]
  6%|▌         | 52/935 [29:28<18:18:08, 74.62s/it]
  6%|▌         | 53/935 [29:55<14:44:16, 60.15s/it]
  6%|▌         | 54/935 [30:25<12:31:46, 51.20s/it]
  6%|▌         | 55/935 [30:50<10:34:37, 43.27s/it]
                                                   

  6%|▌         | 55/935 [30:50<10:34:37, 43.27s/it]
  6%|▌         | 56/935 [31:21<9:41:08, 39.67s/it] 
  6%|▌         | 57/935 [31:45<8:33:53, 35.12s/it]
  6%|▌         | 58/935 [32:13<7:58:40, 32.75s/it]
  6%|▋         | 59/935 [32:33<7:03:17, 28.99s/it]
  6%|▋         | 60/935 [32:55<6:30:56, 26.81s/it]
                                                  

  6%|▋         | 60/935 [32:55<6:30:56, 26.81s/it]
  7%|▋         | 61/935 [33:25<6:44:44, 27.79s/it]
  7%|▋         | 62/935 [33:49<6:30:42, 26.85s/it]
  7%|▋         | 63/935 [34:06<5:45:52, 23.80s/it]
  7%|▋         | 64/935 [34:16<4:44:07, 19.57s/it]
  7%|▋         | 65/935 [34:45<5:25:16, 22.43s/it]
                                                  

  7%|▋         | 65/935 [34:45<5:25:16, 22.43s/it]
  7%|▋         | 66/935 [35:14<5:53:16, 24.39s/it]
  7%|▋         | 67/935 [35:43<6:15:49, 25.98s/it]
  7%|▋         | 68/935 [36:12<6:27:31, 26.82s/it]
  7%|▋         | 69/935 [36:41<6:35:44, 27.42s/it]
  7%|▋         | 70/935 [37:13<6:53:28, 28.68s/it]
                                                  

  7%|▋         | 70/935 [37:13<6:53:28, 28.68s/it]
  8%|▊         | 71/935 [37:33<6:18:26, 26.28s/it]
  8%|▊         | 72/935 [38:04<6:34:52, 27.45s/it]
  8%|▊         | 73/935 [38:26<6:13:52, 26.02s/it]
  8%|▊         | 74/935 [38:59<6:42:16, 28.03s/it]
  8%|▊         | 75/935 [39:22<6:20:54, 26.57s/it]
                                                  

  8%|▊         | 75/935 [39:22<6:20:54, 26.57s/it]
  8%|▊         | 76/935 [39:45<6:05:40, 25.54s/it]
  8%|▊         | 77/935 [40:14<6:18:44, 26.49s/it]
  8%|▊         | 78/935 [40:45<6:35:42, 27.70s/it]
  8%|▊         | 79/935 [41:09<6:19:45, 26.62s/it]
  9%|▊         | 80/935 [41:28<5:49:36, 24.53s/it]
                                                  

  9%|▊         | 80/935 [41:28<5:49:36, 24.53s/it]
  9%|▊         | 81/935 [41:56<6:03:45, 25.56s/it]
  9%|▉         | 82/935 [42:24<6:12:25, 26.20s/it]
  9%|▉         | 83/935 [42:56<6:37:47, 28.01s/it]
  9%|▉         | 84/935 [43:23<6:33:55, 27.77s/it]
  9%|▉         | 85/935 [43:56<6:54:50, 29.28s/it]
                                                  

  9%|▉         | 85/935 [43:56<6:54:50, 29.28s/it]
  9%|▉         | 86/935 [44:21<6:33:39, 27.82s/it]
  9%|▉         | 87/935 [44:49<6:37:14, 28.11s/it]
  9%|▉         | 88/935 [45:12<6:14:34, 26.53s/it]
 10%|▉         | 89/935 [45:39<6:16:28, 26.70s/it]
 10%|▉         | 90/935 [46:07<6:18:34, 26.88s/it]
                                                  

 10%|▉         | 90/935 [46:07<6:18:34, 26.88s/it]
 10%|▉         | 91/935 [46:34<6:18:13, 26.89s/it]
 10%|▉         | 92/935 [47:00<6:17:14, 26.85s/it]
 10%|▉         | 93/935 [47:20<5:46:16, 24.68s/it]
 10%|█         | 94/935 [47:46<5:51:47, 25.10s/it]
 10%|█         | 95/935 [48:12<5:56:56, 25.50s/it]
                                                  

 10%|█         | 95/935 [48:12<5:56:56, 25.50s/it]
 10%|█         | 96/935 [48:48<6:37:20, 28.42s/it]
 10%|█         | 97/935 [49:14<6:26:13, 27.65s/it]
 10%|█         | 98/935 [49:36<6:05:03, 26.17s/it]
 11%|█         | 99/935 [49:59<5:49:07, 25.06s/it]
 11%|█         | 100/935 [50:21<5:35:38, 24.12s/it]
                                                   

 11%|█         | 100/935 [50:21<5:35:38, 24.12s/it]{'eval_loss': 0.8905913829803467, 'eval_runtime': 230.3688, 'eval_samples_per_second': 1.667, 'eval_steps_per_second': 0.833, 'epoch': 0.05}
{'loss': 1.1475, 'grad_norm': 1.6632639169692993, 'learning_rate': 0.00019996933678400946, 'epoch': 0.06}
{'loss': 0.9136, 'grad_norm': 1.2125474214553833, 'learning_rate': 0.00019990989662046818, 'epoch': 0.06}
{'loss': 0.8924, 'grad_norm': 1.0796895027160645, 'learning_rate': 0.00019981919487090972, 'epoch': 0.07}
{'loss': 0.8299, 'grad_norm': 0.9552472829818726, 'learning_rate': 0.00019969725991571128, 'epoch': 0.07}
{'loss': 0.7001, 'grad_norm': 0.7944055199623108, 'learning_rate': 0.00019954412990805107, 'epoch': 0.08}
{'loss': 0.8231, 'grad_norm': 0.7805637121200562, 'learning_rate': 0.0001993598527619703, 'epoch': 0.09}
{'loss': 0.8797, 'grad_norm': 0.6794283986091614, 'learning_rate': 0.00019914448613738106, 'epoch': 0.09}
{'loss': 0.6609, 'grad_norm': 0.6624935269355774, 'learning_rate': 0.00019889809742202455, 'epoch': 0.1}
{'loss': 0.8429, 'grad_norm': 0.8070583939552307, 'learning_rate': 0.0001986207637103857, 'epoch': 0.1}
{'loss': 0.6952, 'grad_norm': 0.7406468391418457, 'learning_rate': 0.00019831257177957044, 'epoch': 0.11}


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

  1%|          | 2/192 [00:00<00:48,  3.91it/s]

  2%|▏         | 3/192 [00:01<01:43,  1.82it/s]

  2%|▏         | 4/192 [00:02<01:56,  1.62it/s]

  3%|▎         | 5/192 [00:03<02:09,  1.44it/s]

  3%|▎         | 6/192 [00:03<02:13,  1.40it/s]

  4%|▎         | 7/192 [00:04<02:25,  1.27it/s]

  4%|▍         | 8/192 [00:05<02:37,  1.17it/s]

  5%|▍         | 9/192 [00:06<02:48,  1.09it/s]

  5%|▌         | 10/192 [00:07<02:53,  1.05it/s]

  6%|▌         | 11/192 [00:08<02:38,  1.14it/s]

  6%|▋         | 12/192 [00:08<02:09,  1.39it/s]

  7%|▋         | 13/192 [00:09<02:16,  1.32it/s]

  7%|▋         | 14/192 [00:10<02:21,  1.26it/s]

  8%|▊         | 15/192 [00:11<02:08,  1.38it/s]

  8%|▊         | 16/192 [00:11<01:56,  1.51it/s]

  9%|▉         | 17/192 [00:12<02:16,  1.28it/s]

  9%|▉         | 18/192 [00:13<02:27,  1.18it/s]

 10%|▉         | 19/192 [00:14<02:13,  1.30it/s]

 10%|█         | 20/192 [00:14<01:57,  1.46it/s]

 11%|█         | 21/192 [00:15<02:05,  1.36it/s]

 11%|█▏        | 22/192 [00:16<02:04,  1.37it/s]

 12%|█▏        | 23/192 [00:16<01:47,  1.56it/s]

 13%|█▎        | 25/192 [00:17<01:03,  2.62it/s]

 14%|█▎        | 26/192 [00:17<00:52,  3.14it/s]

 14%|█▍        | 27/192 [00:17<00:45,  3.65it/s]

 15%|█▍        | 28/192 [00:17<00:37,  4.40it/s]

 15%|█▌        | 29/192 [00:17<00:33,  4.88it/s]

 16%|█▌        | 30/192 [00:17<00:30,  5.34it/s]

 16%|█▌        | 31/192 [00:17<00:29,  5.38it/s]

 17%|█▋        | 32/192 [00:17<00:27,  5.83it/s]

 17%|█▋        | 33/192 [00:18<00:51,  3.10it/s]

 18%|█▊        | 34/192 [00:19<01:25,  1.84it/s]

 18%|█▊        | 35/192 [00:20<01:49,  1.43it/s]

 19%|█▉        | 36/192 [00:21<01:40,  1.55it/s]

 19%|█▉        | 37/192 [00:21<01:19,  1.96it/s]

 20%|██        | 39/192 [00:21<00:58,  2.60it/s]

 21%|██        | 40/192 [00:22<01:12,  2.09it/s]

 21%|██▏       | 41/192 [00:23<01:32,  1.63it/s]

 22%|██▏       | 42/192 [00:24<01:47,  1.40it/s]

 22%|██▏       | 43/192 [00:25<01:59,  1.24it/s]

 23%|██▎       | 44/192 [00:26<01:48,  1.37it/s]

 23%|██▎       | 45/192 [00:26<01:26,  1.71it/s]

 24%|██▍       | 46/192 [00:27<01:22,  1.76it/s]

 24%|██▍       | 47/192 [00:28<01:38,  1.48it/s]

 25%|██▌       | 48/192 [00:28<01:40,  1.43it/s]

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

 26%|██▌       | 50/192 [00:29<01:07,  2.10it/s]

 27%|██▋       | 51/192 [00:29<01:11,  1.96it/s]

 27%|██▋       | 52/192 [00:30<01:11,  1.95it/s]

 28%|██▊       | 53/192 [00:30<00:59,  2.35it/s]

 28%|██▊       | 54/192 [00:31<01:10,  1.96it/s]

 29%|██▊       | 55/192 [00:32<01:32,  1.48it/s]

 29%|██▉       | 56/192 [00:33<01:39,  1.37it/s]

 30%|██▉       | 57/192 [00:34<01:44,  1.29it/s]

 30%|███       | 58/192 [00:34<01:28,  1.51it/s]

 31%|███       | 59/192 [00:35<01:27,  1.51it/s]

 31%|███▏      | 60/192 [00:36<01:45,  1.26it/s]

 32%|███▏      | 61/192 [00:37<01:42,  1.28it/s]

 32%|███▏      | 62/192 [00:37<01:15,  1.71it/s]

 33%|███▎      | 63/192 [00:37<00:58,  2.21it/s]

 33%|███▎      | 64/192 [00:37<00:53,  2.41it/s]

 34%|███▍      | 65/192 [00:38<00:52,  2.41it/s]

 35%|███▍      | 67/192 [00:38<00:34,  3.61it/s]

 35%|███▌      | 68/192 [00:38<00:29,  4.17it/s]

 36%|███▌      | 69/192 [00:39<00:46,  2.66it/s]

 36%|███▋      | 70/192 [00:39<00:53,  2.27it/s]

 37%|███▋      | 71/192 [00:40<00:55,  2.18it/s]

 38%|███▊      | 72/192 [00:41<01:14,  1.61it/s]

 38%|███▊      | 73/192 [00:42<01:35,  1.25it/s]

 39%|███▊      | 74/192 [00:43<01:27,  1.34it/s]

 39%|███▉      | 75/192 [00:43<01:07,  1.73it/s]

 40%|███▉      | 76/192 [00:43<01:06,  1.73it/s]

 40%|████      | 77/192 [00:44<01:20,  1.42it/s]

 41%|████      | 78/192 [00:45<01:26,  1.31it/s]

 41%|████      | 79/192 [00:46<01:19,  1.42it/s]

 42%|████▏     | 80/192 [00:46<01:12,  1.54it/s]

 42%|████▏     | 81/192 [00:47<01:23,  1.33it/s]

 43%|████▎     | 82/192 [00:48<01:29,  1.23it/s]

 43%|████▎     | 83/192 [00:49<01:36,  1.13it/s]

 44%|████▍     | 84/192 [00:50<01:23,  1.29it/s]

 44%|████▍     | 85/192 [00:51<01:18,  1.37it/s]

 45%|████▍     | 86/192 [00:51<01:11,  1.47it/s]

 45%|████▌     | 87/192 [00:51<00:56,  1.85it/s]

 46%|████▋     | 89/192 [00:52<00:34,  3.00it/s]

 47%|████▋     | 90/192 [00:52<00:28,  3.53it/s]

 47%|████▋     | 91/192 [00:52<00:35,  2.85it/s]

 48%|████▊     | 92/192 [00:53<00:46,  2.13it/s]

 48%|████▊     | 93/192 [00:54<00:56,  1.76it/s]

 49%|████▉     | 94/192 [00:54<00:52,  1.87it/s]

 49%|████▉     | 95/192 [00:55<00:53,  1.81it/s]

 50%|█████     | 96/192 [00:56<01:04,  1.48it/s]

 51%|█████     | 97/192 [00:56<01:02,  1.52it/s]

 51%|█████     | 98/192 [00:57<00:47,  1.99it/s]

 52%|█████▏    | 99/192 [00:57<00:50,  1.84it/s]

 52%|█████▏    | 100/192 [00:58<00:58,  1.56it/s]

 53%|█████▎    | 101/192 [00:59<01:10,  1.29it/s]

 53%|█████▎    | 102/192 [01:00<01:07,  1.34it/s]

 54%|█████▎    | 103/192 [01:00<01:02,  1.43it/s]

 54%|█████▍    | 104/192 [01:01<01:06,  1.33it/s]

 55%|█████▍    | 105/192 [01:02<01:03,  1.37it/s]

 55%|█████▌    | 106/192 [01:02<00:47,  1.82it/s]

 56%|█████▌    | 107/192 [01:03<00:47,  1.78it/s]

 56%|█████▋    | 108/192 [01:04<00:56,  1.48it/s]

 57%|█████▋    | 109/192 [01:05<01:10,  1.18it/s]

 57%|█████▋    | 110/192 [01:06<01:17,  1.06it/s]

 58%|█████▊    | 111/192 [01:07<01:11,  1.14it/s]

 58%|█████▊    | 112/192 [01:07<01:04,  1.25it/s]

 59%|█████▉    | 113/192 [01:08<00:59,  1.33it/s]

 59%|█████▉    | 114/192 [01:08<00:44,  1.75it/s]

 60%|█████▉    | 115/192 [01:09<00:44,  1.74it/s]

 60%|██████    | 116/192 [01:10<00:48,  1.56it/s]

 61%|██████    | 117/192 [01:10<00:44,  1.69it/s]

 61%|██████▏   | 118/192 [01:11<00:46,  1.61it/s]

 62%|██████▏   | 119/192 [01:12<00:51,  1.41it/s]

 62%|██████▎   | 120/192 [01:12<00:50,  1.42it/s]

 63%|██████▎   | 121/192 [01:13<00:49,  1.44it/s]

 64%|██████▎   | 122/192 [01:14<00:45,  1.55it/s]

 64%|██████▍   | 123/192 [01:14<00:48,  1.42it/s]

 65%|██████▍   | 124/192 [01:15<00:47,  1.43it/s]

 65%|██████▌   | 125/192 [01:16<00:55,  1.20it/s]

 66%|██████▌   | 126/192 [01:17<00:59,  1.11it/s]

 66%|██████▌   | 127/192 [01:18<00:46,  1.40it/s]

 67%|██████▋   | 128/192 [01:18<00:43,  1.48it/s]

 67%|██████▋   | 129/192 [01:19<00:49,  1.26it/s]

 68%|██████▊   | 130/192 [01:20<00:52,  1.18it/s]

 68%|██████▊   | 131/192 [01:21<00:53,  1.14it/s]

 69%|██████▉   | 132/192 [01:22<00:48,  1.23it/s]

 69%|██████▉   | 133/192 [01:22<00:41,  1.42it/s]

 70%|██████▉   | 134/192 [01:23<00:40,  1.44it/s]

 70%|███████   | 135/192 [01:24<00:38,  1.48it/s]

 71%|███████   | 136/192 [01:24<00:36,  1.54it/s]

 71%|███████▏  | 137/192 [01:25<00:42,  1.30it/s]

 72%|███████▏  | 138/192 [01:26<00:37,  1.43it/s]

 72%|███████▏  | 139/192 [01:26<00:27,  1.90it/s]

 73%|███████▎  | 141/192 [01:27<00:21,  2.33it/s]

 74%|███████▍  | 142/192 [01:28<00:30,  1.66it/s]

 74%|███████▍  | 143/192 [01:28<00:31,  1.56it/s]

 75%|███████▌  | 144/192 [01:29<00:23,  2.00it/s]

 76%|███████▌  | 145/192 [01:29<00:24,  1.89it/s]

 76%|███████▌  | 146/192 [01:30<00:25,  1.82it/s]

 77%|███████▋  | 147/192 [01:30<00:25,  1.77it/s]

 77%|███████▋  | 148/192 [01:31<00:30,  1.42it/s]

 78%|███████▊  | 149/192 [01:32<00:30,  1.42it/s]

 78%|███████▊  | 150/192 [01:32<00:22,  1.86it/s]

 79%|███████▊  | 151/192 [01:32<00:17,  2.35it/s]

 79%|███████▉  | 152/192 [01:33<00:18,  2.13it/s]

 80%|███████▉  | 153/192 [01:34<00:19,  1.98it/s]

 80%|████████  | 154/192 [01:34<00:21,  1.76it/s]

 81%|████████  | 155/192 [01:35<00:22,  1.67it/s]

 81%|████████▏ | 156/192 [01:36<00:22,  1.58it/s]

 82%|████████▏ | 157/192 [01:36<00:23,  1.51it/s]

 82%|████████▏ | 158/192 [01:37<00:21,  1.61it/s]

 83%|████████▎ | 159/192 [01:38<00:20,  1.61it/s]

 83%|████████▎ | 160/192 [01:38<00:14,  2.13it/s]

 84%|████████▍ | 161/192 [01:38<00:11,  2.70it/s]

 85%|████████▍ | 163/192 [01:38<00:07,  3.90it/s]

 85%|████████▌ | 164/192 [01:39<00:08,  3.24it/s]

 86%|████████▌ | 165/192 [01:39<00:12,  2.17it/s]

 86%|████████▋ | 166/192 [01:40<00:12,  2.15it/s]

 87%|████████▋ | 167/192 [01:40<00:12,  2.03it/s]

 88%|████████▊ | 168/192 [01:41<00:15,  1.59it/s]

 88%|████████▊ | 169/192 [01:42<00:14,  1.59it/s]

 89%|████████▊ | 170/192 [01:42<00:10,  2.05it/s]

 89%|████████▉ | 171/192 [01:42<00:08,  2.59it/s]

 90%|█████████ | 173/192 [01:43<00:07,  2.63it/s]

 91%|█████████ | 174/192 [01:44<00:10,  1.78it/s]

 91%|█████████ | 175/192 [01:45<00:10,  1.67it/s]

 92%|█████████▏| 176/192 [01:45<00:07,  2.14it/s]

 92%|█████████▏| 177/192 [01:45<00:05,  2.68it/s]

 93%|█████████▎| 178/192 [01:46<00:05,  2.48it/s]

 93%|█████████▎| 179/192 [01:46<00:06,  1.89it/s]

 94%|█████████▍| 180/192 [01:47<00:05,  2.12it/s]

 94%|█████████▍| 181/192 [01:47<00:05,  2.01it/s]

 95%|█████████▍| 182/192 [01:48<00:06,  1.56it/s]

 95%|█████████▌| 183/192 [01:49<00:05,  1.59it/s]

 96%|█████████▌| 184/192 [01:49<00:03,  2.09it/s]

 96%|█████████▋| 185/192 [01:49<00:02,  2.67it/s]

 97%|█████████▋| 186/192 [01:50<00:02,  2.54it/s]

 97%|█████████▋| 187/192 [01:50<00:02,  2.48it/s]

 98%|█████████▊| 188/192 [01:50<00:01,  3.17it/s]

 99%|█████████▉| 190/192 [01:50<00:00,  4.46it/s]

 99%|█████████▉| 191/192 [01:51<00:00,  3.03it/s]

100%|██████████| 192/192 [01:52<00:00,  2.58it/s]
                                                   

                                                 

 11%|█         | 100/935 [52:13<5:35:38, 24.12s/it]

100%|██████████| 192/192 [01:52<00:00,  2.58it/s]

                                                 wandb: WARNING URL not available in offline run

 11%|█         | 101/935 [52:45<13:57:57, 60.28s/it]
 11%|█         | 102/935 [53:11<11:33:33, 49.96s/it]
 11%|█         | 103/935 [53:46<10:29:48, 45.42s/it]
 11%|█         | 104/935 [54:46<11:31:22, 49.92s/it]
 11%|█         | 105/935 [55:26<10:46:54, 46.76s/it]
                                                    

 11%|█         | 105/935 [55:26<10:46:54, 46.76s/it]
 11%|█▏        | 106/935 [55:53<9:24:45, 40.87s/it] 
 11%|█▏        | 107/935 [56:17<8:16:32, 35.98s/it]
 12%|█▏        | 108/935 [56:56<8:25:48, 36.70s/it]
 12%|█▏        | 109/935 [57:39<8:53:28, 38.75s/it]
 12%|█▏        | 110/935 [58:23<9:11:31, 40.11s/it]
                                                   

 12%|█▏        | 110/935 [58:23<9:11:31, 40.11s/it]
 12%|█▏        | 111/935 [59:31<11:05:32, 48.46s/it]
 12%|█▏        | 112/935 [1:00:09<10:24:26, 45.52s/it]
 12%|█▏        | 113/935 [1:00:59<10:39:03, 46.65s/it]
 12%|█▏        | 114/935 [1:01:42<10:26:30, 45.79s/it]
 12%|█▏        | 115/935 [1:02:12<9:19:51, 40.96s/it] 
                                                     

 12%|█▏        | 115/935 [1:02:12<9:19:51, 40.96s/it]
 12%|█▏        | 116/935 [1:03:02<9:54:26, 43.55s/it]
 13%|█▎        | 117/935 [1:03:36<9:15:28, 40.74s/it]
 13%|█▎        | 118/935 [1:04:07<8:33:59, 37.75s/it]
 13%|█▎        | 119/935 [1:04:38<8:06:43, 35.79s/it]
 13%|█▎        | 120/935 [1:05:19<8:27:34, 37.37s/it]
                                                     

 13%|█▎        | 120/935 [1:05:19<8:27:34, 37.37s/it]
 13%|█▎        | 121/935 [1:05:56<8:25:14, 37.24s/it]
 13%|█▎        | 122/935 [1:06:30<8:10:36, 36.21s/it]
 13%|█▎        | 123/935 [1:07:01<7:48:56, 34.65s/it]
 13%|█▎        | 124/935 [1:07:24<7:03:00, 31.30s/it]
 13%|█▎        | 125/935 [1:07:46<6:25:42, 28.57s/it]
                                                     

 13%|█▎        | 125/935 [1:07:46<6:25:42, 28.57s/it]
 13%|█▎        | 126/935 [1:08:07<5:55:17, 26.35s/it]
 14%|█▎        | 127/935 [1:08:31<5:41:41, 25.37s/it]
 14%|█▎        | 128/935 [1:09:01<6:01:29, 26.88s/it]
 14%|█▍        | 129/935 [1:09:25<5:50:10, 26.07s/it]
 14%|█▍        | 130/935 [1:09:52<5:51:30, 26.20s/it]
                                                     

 14%|█▍        | 130/935 [1:09:52<5:51:30, 26.20s/it]
 14%|█▍        | 131/935 [1:10:18<5:51:27, 26.23s/it]
 14%|█▍        | 132/935 [1:10:52<6:23:20, 28.64s/it]
 14%|█▍        | 133/935 [1:11:26<6:44:18, 30.25s/it]
 14%|█▍        | 134/935 [1:11:48<6:11:02, 27.79s/it]
 14%|█▍        | 135/935 [1:12:06<5:29:15, 24.69s/it]
                                                     

 14%|█▍        | 135/935 [1:12:06<5:29:15, 24.69s/it]
 15%|█▍        | 136/935 [1:12:32<5:36:35, 25.28s/it]
 15%|█▍        | 137/935 [1:12:55<5:23:50, 24.35s/it]
 15%|█▍        | 138/935 [1:13:20<5:29:36, 24.81s/it]
 15%|█▍        | 139/935 [1:13:45<5:28:52, 24.79s/it]
 15%|█▍        | 140/935 [1:14:11<5:33:32, 25.17s/it]
                                                     

 15%|█▍        | 140/935 [1:14:11<5:33:32, 25.17s/it]
 15%|█▌        | 141/935 [1:14:30<5:08:09, 23.29s/it]
 15%|█▌        | 142/935 [1:14:56<5:16:17, 23.93s/it]
 15%|█▌        | 143/935 [1:15:12<4:47:35, 21.79s/it]
 15%|█▌        | 144/935 [1:15:48<5:43:40, 26.07s/it]
 16%|█▌        | 145/935 [1:16:10<5:26:23, 24.79s/it]
                                                     

 16%|█▌        | 145/935 [1:16:10<5:26:23, 24.79s/it]
 16%|█▌        | 146/935 [1:16:38<5:36:31, 25.59s/it]
 16%|█▌        | 147/935 [1:17:03<5:33:16, 25.38s/it]
 16%|█▌        | 148/935 [1:17:35<5:59:36, 27.42s/it]
 16%|█▌        | 149/935 [1:18:05<6:09:07, 28.18s/it]
 16%|█▌        | 150/935 [1:18:34<6:11:42, 28.41s/it]
                                                     

 16%|█▌        | 150/935 [1:18:34<6:11:42, 28.41s/it]{'eval_loss': 0.4853295385837555, 'eval_runtime': 112.3115, 'eval_samples_per_second': 3.419, 'eval_steps_per_second': 1.71, 'epoch': 0.11}
{'loss': 0.4831, 'grad_norm': 0.672978937625885, 'learning_rate': 0.00019797361806215332, 'epoch': 0.11}
{'loss': 0.7488, 'grad_norm': 0.6432732939720154, 'learning_rate': 0.000197604008616004, 'epoch': 0.12}
{'loss': 0.6459, 'grad_norm': 0.8533371686935425, 'learning_rate': 0.00019720385909110198, 'epoch': 0.12}
{'loss': 0.6682, 'grad_norm': 0.7265816926956177, 'learning_rate': 0.0001967732946933499, 'epoch': 0.13}
{'loss': 0.6458, 'grad_norm': 0.7138218879699707, 'learning_rate': 0.00019631245014539698, 'epoch': 0.13}
{'loss': 0.7498, 'grad_norm': 0.681537389755249, 'learning_rate': 0.0001958214696444846, 'epoch': 0.14}
{'loss': 0.5161, 'grad_norm': 0.7001609206199646, 'learning_rate': 0.0001953005068173272, 'epoch': 0.14}
{'loss': 0.6795, 'grad_norm': 0.6696146130561829, 'learning_rate': 0.00019474972467204297, 'epoch': 0.15}
{'loss': 0.6418, 'grad_norm': 0.781279981136322, 'learning_rate': 0.00019416929554714888, 'epoch': 0.16}
{'loss': 0.5244, 'grad_norm': 0.5625928044319153, 'learning_rate': 0.0001935594010576362, 'epoch': 0.16}


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

  1%|          | 2/192 [00:00<00:49,  3.84it/s]

  2%|▏         | 3/192 [00:01<01:44,  1.81it/s]

  2%|▏         | 4/192 [00:02<01:57,  1.60it/s]

  3%|▎         | 5/192 [00:03<02:10,  1.43it/s]

  3%|▎         | 6/192 [00:03<02:14,  1.38it/s]

  4%|▎         | 7/192 [00:04<02:27,  1.25it/s]

  4%|▍         | 8/192 [00:05<02:38,  1.16it/s]

  5%|▍         | 9/192 [00:06<02:49,  1.08it/s]

  5%|▌         | 10/192 [00:07<02:55,  1.04it/s]

  6%|▌         | 11/192 [00:08<02:39,  1.13it/s]

  6%|▋         | 12/192 [00:08<02:10,  1.38it/s]

  7%|▋         | 13/192 [00:09<02:17,  1.30it/s]

  7%|▋         | 14/192 [00:10<02:22,  1.25it/s]

  8%|▊         | 15/192 [00:11<02:08,  1.37it/s]

  8%|▊         | 16/192 [00:11<01:57,  1.49it/s]

  9%|▉         | 17/192 [00:12<02:18,  1.27it/s]

  9%|▉         | 18/192 [00:13<02:29,  1.17it/s]

 10%|▉         | 19/192 [00:14<02:14,  1.29it/s]

 10%|█         | 20/192 [00:14<01:58,  1.45it/s]

 11%|█         | 21/192 [00:15<02:06,  1.35it/s]

 11%|█▏        | 22/192 [00:16<02:05,  1.36it/s]

 12%|█▏        | 23/192 [00:16<01:48,  1.56it/s]

 13%|█▎        | 25/192 [00:17<01:03,  2.62it/s]

 14%|█▎        | 26/192 [00:17<00:53,  3.13it/s]

 14%|█▍        | 27/192 [00:17<00:45,  3.62it/s]

 15%|█▍        | 28/192 [00:17<00:37,  4.37it/s]

 15%|█▌        | 29/192 [00:17<00:33,  4.89it/s]

 16%|█▌        | 30/192 [00:17<00:30,  5.35it/s]

 16%|█▌        | 31/192 [00:18<00:30,  5.27it/s]

 17%|█▋        | 32/192 [00:18<00:28,  5.57it/s]

 17%|█▋        | 33/192 [00:18<00:51,  3.09it/s]

 18%|█▊        | 34/192 [00:19<01:26,  1.84it/s]

 18%|█▊        | 35/192 [00:20<01:50,  1.42it/s]

 19%|█▉        | 36/192 [00:21<01:41,  1.54it/s]

 19%|█▉        | 37/192 [00:21<01:19,  1.96it/s]

 20%|██        | 39/192 [00:22<00:58,  2.60it/s]

 21%|██        | 40/192 [00:22<01:12,  2.10it/s]

 21%|██▏       | 41/192 [00:23<01:32,  1.63it/s]

 22%|██▏       | 42/192 [00:24<01:47,  1.40it/s]

 22%|██▏       | 43/192 [00:25<01:59,  1.25it/s]

 23%|██▎       | 44/192 [00:26<01:46,  1.39it/s]

 23%|██▎       | 45/192 [00:26<01:23,  1.76it/s]

 24%|██▍       | 46/192 [00:27<01:21,  1.79it/s]

 24%|██▍       | 47/192 [00:28<01:38,  1.48it/s]

 25%|██▌       | 48/192 [00:28<01:41,  1.42it/s]

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

 26%|██▌       | 50/192 [00:29<01:07,  2.10it/s]

 27%|██▋       | 51/192 [00:30<01:11,  1.98it/s]

 27%|██▋       | 52/192 [00:30<01:11,  1.95it/s]

 28%|██▊       | 53/192 [00:30<00:58,  2.38it/s]

 28%|██▊       | 54/192 [00:31<01:10,  1.95it/s]

 29%|██▊       | 55/192 [00:32<01:32,  1.49it/s]

 29%|██▉       | 56/192 [00:33<01:39,  1.37it/s]

 30%|██▉       | 57/192 [00:34<01:44,  1.30it/s]

 30%|███       | 58/192 [00:34<01:28,  1.52it/s]

 31%|███       | 59/192 [00:35<01:27,  1.52it/s]

 31%|███▏      | 60/192 [00:36<01:45,  1.25it/s]

 32%|███▏      | 61/192 [00:37<01:42,  1.27it/s]

 32%|███▏      | 62/192 [00:37<01:16,  1.71it/s]

 33%|███▎      | 63/192 [00:37<00:58,  2.21it/s]

 33%|███▎      | 64/192 [00:37<00:53,  2.41it/s]

 34%|███▍      | 65/192 [00:38<00:52,  2.41it/s]

 35%|███▍      | 67/192 [00:38<00:34,  3.61it/s]

 35%|███▌      | 68/192 [00:38<00:29,  4.16it/s]

 36%|███▌      | 69/192 [00:39<00:46,  2.66it/s]

 36%|███▋      | 70/192 [00:39<00:53,  2.26it/s]

 37%|███▋      | 71/192 [00:40<00:55,  2.16it/s]

 38%|███▊      | 72/192 [00:41<01:15,  1.60it/s]

 38%|███▊      | 73/192 [00:42<01:35,  1.24it/s]

 39%|███▊      | 74/192 [00:43<01:27,  1.35it/s]

 39%|███▉      | 75/192 [00:43<01:07,  1.73it/s]

 40%|███▉      | 76/192 [00:44<01:07,  1.73it/s]

 40%|████      | 77/192 [00:45<01:21,  1.42it/s]

 41%|████      | 78/192 [00:46<01:27,  1.31it/s]

 41%|████      | 79/192 [00:46<01:20,  1.41it/s]

 42%|████▏     | 80/192 [00:47<01:13,  1.52it/s]

 42%|████▏     | 81/192 [00:48<01:23,  1.33it/s]

 43%|████▎     | 82/192 [00:49<01:29,  1.23it/s]

 43%|████▎     | 83/192 [00:50<01:36,  1.13it/s]

 44%|████▍     | 84/192 [00:50<01:23,  1.29it/s]

 44%|████▍     | 85/192 [00:51<01:20,  1.34it/s]

 45%|████▍     | 86/192 [00:51<01:11,  1.48it/s]

 45%|████▌     | 87/192 [00:52<00:55,  1.88it/s]

 46%|████▌     | 88/192 [00:52<00:42,  2.47it/s]

 47%|████▋     | 90/192 [00:52<00:27,  3.72it/s]

 47%|████▋     | 91/192 [00:52<00:34,  2.96it/s]

 48%|████▊     | 92/192 [00:53<00:45,  2.21it/s]

 48%|████▊     | 93/192 [00:54<00:55,  1.79it/s]

 49%|████▉     | 94/192 [00:54<00:52,  1.88it/s]

 49%|████▉     | 95/192 [00:55<00:53,  1.81it/s]

 50%|█████     | 96/192 [00:56<01:04,  1.50it/s]

 51%|█████     | 97/192 [00:57<01:01,  1.54it/s]

 51%|█████     | 98/192 [00:57<00:46,  2.01it/s]

 52%|█████▏    | 99/192 [00:57<00:50,  1.85it/s]

 52%|█████▏    | 100/192 [00:58<00:58,  1.57it/s]

 53%|█████▎    | 101/192 [00:59<01:09,  1.30it/s]

 53%|█████▎    | 102/192 [01:00<01:06,  1.36it/s]

 54%|█████▎    | 103/192 [01:01<01:01,  1.44it/s]

 54%|█████▍    | 104/192 [01:02<01:06,  1.32it/s]

 55%|█████▍    | 105/192 [01:02<01:01,  1.41it/s]

 55%|█████▌    | 106/192 [01:02<00:46,  1.86it/s]

 56%|█████▌    | 107/192 [01:03<00:47,  1.77it/s]

 56%|█████▋    | 108/192 [01:04<00:57,  1.47it/s]

 57%|█████▋    | 109/192 [01:05<01:10,  1.18it/s]

 57%|█████▋    | 110/192 [01:06<01:18,  1.05it/s]

 58%|█████▊    | 111/192 [01:07<01:11,  1.14it/s]

 58%|█████▊    | 112/192 [01:08<01:04,  1.24it/s]

 59%|█████▉    | 113/192 [01:08<00:59,  1.32it/s]

 59%|█████▉    | 114/192 [01:08<00:44,  1.74it/s]

 60%|█████▉    | 115/192 [01:09<00:44,  1.72it/s]

 60%|██████    | 116/192 [01:10<00:48,  1.55it/s]

 61%|██████    | 117/192 [01:10<00:44,  1.70it/s]

 61%|██████▏   | 118/192 [01:11<00:45,  1.63it/s]

 62%|██████▏   | 119/192 [01:12<00:52,  1.40it/s]

 62%|██████▎   | 120/192 [01:13<00:51,  1.40it/s]

 63%|██████▎   | 121/192 [01:13<00:45,  1.56it/s]

 64%|██████▎   | 122/192 [01:14<00:43,  1.60it/s]

 64%|██████▍   | 123/192 [01:14<00:42,  1.62it/s]

 65%|██████▍   | 124/192 [01:15<00:40,  1.68it/s]

 65%|██████▌   | 125/192 [01:16<00:48,  1.39it/s]

 66%|██████▌   | 126/192 [01:17<00:52,  1.25it/s]

 66%|██████▌   | 127/192 [01:17<00:48,  1.34it/s]

 67%|██████▋   | 128/192 [01:18<00:44,  1.45it/s]

 67%|██████▋   | 129/192 [01:19<00:49,  1.26it/s]

 68%|██████▊   | 130/192 [01:20<00:53,  1.17it/s]

 68%|██████▊   | 131/192 [01:21<00:53,  1.13it/s]

 69%|██████▉   | 132/192 [01:22<00:48,  1.23it/s]

 69%|██████▉   | 133/192 [01:22<00:41,  1.41it/s]

 70%|██████▉   | 134/192 [01:23<00:40,  1.44it/s]

 70%|███████   | 135/192 [01:23<00:38,  1.48it/s]

 71%|███████   | 136/192 [01:24<00:36,  1.54it/s]

 71%|███████▏  | 137/192 [01:25<00:42,  1.30it/s]

 72%|███████▏  | 138/192 [01:26<00:37,  1.43it/s]

 72%|███████▏  | 139/192 [01:26<00:27,  1.91it/s]

 73%|███████▎  | 141/192 [01:26<00:21,  2.34it/s]

 74%|███████▍  | 142/192 [01:27<00:30,  1.65it/s]

 74%|███████▍  | 143/192 [01:28<00:31,  1.57it/s]

 75%|███████▌  | 144/192 [01:28<00:23,  2.01it/s]

 76%|███████▌  | 145/192 [01:29<00:24,  1.91it/s]

 76%|███████▌  | 146/192 [01:29<00:25,  1.80it/s]

 77%|███████▋  | 147/192 [01:30<00:25,  1.78it/s]

 77%|███████▋  | 148/192 [01:31<00:30,  1.43it/s]

 78%|███████▊  | 149/192 [01:32<00:30,  1.39it/s]

 78%|███████▊  | 150/192 [01:32<00:22,  1.83it/s]

 79%|███████▊  | 151/192 [01:32<00:17,  2.29it/s]

 79%|███████▉  | 152/192 [01:33<00:18,  2.17it/s]

 80%|███████▉  | 153/192 [01:33<00:19,  1.99it/s]

 80%|████████  | 154/192 [01:34<00:21,  1.80it/s]

 81%|████████  | 155/192 [01:35<00:22,  1.68it/s]

 81%|████████▏ | 156/192 [01:35<00:22,  1.59it/s]

 82%|████████▏ | 157/192 [01:36<00:22,  1.55it/s]

 82%|████████▏ | 158/192 [01:37<00:21,  1.61it/s]

 83%|████████▎ | 159/192 [01:37<00:20,  1.63it/s]

 83%|████████▎ | 160/192 [01:37<00:14,  2.17it/s]

 84%|████████▍ | 161/192 [01:37<00:11,  2.77it/s]

 85%|████████▍ | 163/192 [01:38<00:07,  4.07it/s]

 85%|████████▌ | 164/192 [01:38<00:08,  3.26it/s]

 86%|████████▌ | 165/192 [01:39<00:12,  2.21it/s]

 86%|████████▋ | 166/192 [01:40<00:12,  2.13it/s]

 87%|████████▋ | 167/192 [01:40<00:12,  2.01it/s]

 88%|████████▊ | 168/192 [01:41<00:15,  1.58it/s]

 88%|████████▊ | 169/192 [01:42<00:14,  1.58it/s]

 89%|████████▊ | 170/192 [01:42<00:10,  2.04it/s]

 89%|████████▉ | 171/192 [01:42<00:08,  2.58it/s]

 90%|█████████ | 173/192 [01:43<00:07,  2.61it/s]

 91%|█████████ | 174/192 [01:44<00:10,  1.77it/s]

 91%|█████████ | 175/192 [01:45<00:10,  1.67it/s]

 92%|█████████▏| 176/192 [01:45<00:07,  2.14it/s]

 92%|█████████▏| 177/192 [01:45<00:05,  2.67it/s]

 93%|█████████▎| 178/192 [01:45<00:05,  2.51it/s]

 93%|█████████▎| 179/192 [01:46<00:06,  2.01it/s]

 94%|█████████▍| 180/192 [01:46<00:05,  2.18it/s]

 94%|█████████▍| 181/192 [01:47<00:05,  2.07it/s]

 95%|█████████▍| 182/192 [01:48<00:06,  1.59it/s]

 95%|█████████▌| 183/192 [01:48<00:05,  1.62it/s]

 96%|█████████▌| 184/192 [01:49<00:03,  2.13it/s]

 96%|█████████▋| 185/192 [01:49<00:02,  2.70it/s]

 97%|█████████▋| 186/192 [01:49<00:02,  2.57it/s]

 97%|█████████▋| 187/192 [01:50<00:01,  2.50it/s]

 98%|█████████▊| 188/192 [01:50<00:01,  3.20it/s]

 99%|█████████▉| 190/192 [01:50<00:00,  4.49it/s]

 99%|█████████▉| 191/192 [01:51<00:00,  3.06it/s]

100%|██████████| 192/192 [01:51<00:00,  2.58it/s]
                                                     

                                                 

 16%|█▌        | 150/935 [1:20:26<6:11:42, 28.41s/it]

100%|██████████| 192/192 [01:51<00:00,  2.58it/s]

                                                 
 16%|█▌        | 151/935 [1:20:51<13:18:23, 61.10s/it]
 16%|█▋        | 152/935 [1:21:12<10:39:16, 48.99s/it]
 16%|█▋        | 153/935 [1:21:39<9:13:33, 42.47s/it] 
 16%|█▋        | 154/935 [1:21:55<7:30:43, 34.63s/it]
 17%|█▋        | 155/935 [1:22:16<6:36:17, 30.48s/it]
                                                     

 17%|█▋        | 155/935 [1:22:16<6:36:17, 30.48s/it]
 17%|█▋        | 156/935 [1:22:40<6:09:04, 28.43s/it]
 17%|█▋        | 157/935 [1:23:04<5:50:20, 27.02s/it]
 17%|█▋        | 158/935 [1:23:30<5:46:32, 26.76s/it]
 17%|█▋        | 159/935 [1:23:51<5:25:55, 25.20s/it]
 17%|█▋        | 160/935 [1:24:13<5:13:54, 24.30s/it]
                                                     

 17%|█▋        | 160/935 [1:24:13<5:13:54, 24.30s/it]
 17%|█▋        | 161/935 [1:24:37<5:09:30, 23.99s/it]
 17%|█▋        | 162/935 [1:25:01<5:09:08, 24.00s/it]
 17%|█▋        | 163/935 [1:25:25<5:08:35, 23.98s/it]
 18%|█▊        | 164/935 [1:25:55<5:33:04, 25.92s/it]
 18%|█▊        | 165/935 [1:26:22<5:36:39, 26.23s/it]
                                                     

 18%|█▊        | 165/935 [1:26:22<5:36:39, 26.23s/it]
 18%|█▊        | 166/935 [1:26:41<5:06:37, 23.92s/it]
 18%|█▊        | 167/935 [1:27:07<5:14:45, 24.59s/it]
 18%|█▊        | 168/935 [1:27:35<5:27:06, 25.59s/it]
 18%|█▊        | 169/935 [1:27:56<5:10:28, 24.32s/it]
 18%|█▊        | 170/935 [1:28:13<4:40:19, 21.99s/it]
                                                     

 18%|█▊        | 170/935 [1:28:13<4:40:19, 21.99s/it]
 18%|█▊        | 171/935 [1:28:43<5:10:35, 24.39s/it]
 18%|█▊        | 172/935 [1:29:05<5:01:07, 23.68s/it]
 19%|█▊        | 173/935 [1:29:34<5:23:35, 25.48s/it]
 19%|█▊        | 174/935 [1:29:55<5:04:06, 23.98s/it]
 19%|█▊        | 175/935 [1:30:24<5:22:37, 25.47s/it]
                                                     

 19%|█▊        | 175/935 [1:30:24<5:22:37, 25.47s/it]
 19%|█▉        | 176/935 [1:30:49<5:22:52, 25.52s/it]
 19%|█▉        | 177/935 [1:31:23<5:55:10, 28.11s/it]
 19%|█▉        | 178/935 [1:31:41<5:12:57, 24.81s/it]
 19%|█▉        | 179/935 [1:32:00<4:53:44, 23.31s/it]
 19%|█▉        | 180/935 [1:32:18<4:32:14, 21.63s/it]
                                                     

 19%|█▉        | 180/935 [1:32:18<4:32:14, 21.63s/it]
 19%|█▉        | 181/935 [1:32:50<5:08:50, 24.58s/it]
 19%|█▉        | 182/935 [1:33:14<5:06:04, 24.39s/it]
 20%|█▉        | 183/935 [1:33:31<4:39:45, 22.32s/it]
 20%|█▉        | 184/935 [1:33:59<5:00:48, 24.03s/it]
 20%|█▉        | 185/935 [1:34:23<5:00:24, 24.03s/it]
                                                     

 20%|█▉        | 185/935 [1:34:23<5:00:24, 24.03s/it]
 20%|█▉        | 186/935 [1:34:46<4:54:47, 23.61s/it]
 20%|██        | 187/935 [1:35:16<5:18:38, 25.56s/it]
 20%|██        | 188/935 [1:35:38<5:04:23, 24.45s/it]
 20%|██        | 189/935 [1:36:03<5:06:04, 24.62s/it]
 20%|██        | 190/935 [1:36:18<4:31:21, 21.85s/it]
                                                     

 20%|██        | 190/935 [1:36:18<4:31:21, 21.85s/it]
 20%|██        | 191/935 [1:36:46<4:54:25, 23.74s/it]
 21%|██        | 192/935 [1:37:12<5:02:36, 24.44s/it]
 21%|██        | 193/935 [1:37:34<4:50:21, 23.48s/it]
 21%|██        | 194/935 [1:37:58<4:53:07, 23.73s/it]
 21%|██        | 195/935 [1:38:17<4:36:16, 22.40s/it]
                                                     

 21%|██        | 195/935 [1:38:17<4:36:16, 22.40s/it]
 21%|██        | 196/935 [1:38:38<4:31:26, 22.04s/it]
 21%|██        | 197/935 [1:39:11<5:12:02, 25.37s/it]
 21%|██        | 198/935 [1:39:35<5:05:15, 24.85s/it]
 21%|██▏       | 199/935 [1:40:02<5:10:40, 25.33s/it]
 21%|██▏       | 200/935 [1:40:33<5:33:53, 27.26s/it]
                                                     

 21%|██▏       | 200/935 [1:40:33<5:33:53, 27.26s/it]{'eval_loss': 0.4266001880168915, 'eval_runtime': 111.8623, 'eval_samples_per_second': 3.433, 'eval_steps_per_second': 1.716, 'epoch': 0.16}
{'loss': 0.7282, 'grad_norm': 0.5409214496612549, 'learning_rate': 0.000192920232038144, 'epoch': 0.17}
{'loss': 0.8597, 'grad_norm': 0.6080542206764221, 'learning_rate': 0.0001922519884832469, 'epoch': 0.17}
{'loss': 0.4898, 'grad_norm': 0.650615930557251, 'learning_rate': 0.00019155487948487748, 'epoch': 0.18}
{'loss': 0.6313, 'grad_norm': 0.5822589993476868, 'learning_rate': 0.0001908291231669019, 'epoch': 0.18}
{'loss': 0.5673, 'grad_norm': 0.5433451533317566, 'learning_rate': 0.00019007494661686935, 'epoch': 0.19}
{'loss': 0.5888, 'grad_norm': 0.6697724461555481, 'learning_rate': 0.00018929258581495685, 'epoch': 0.19}
{'loss': 0.5925, 'grad_norm': 0.7195097208023071, 'learning_rate': 0.0001884822855601316, 'epoch': 0.2}
{'loss': 0.6258, 'grad_norm': 0.704847514629364, 'learning_rate': 0.00018764429939355392, 'epoch': 0.2}
{'loss': 0.6023, 'grad_norm': 0.7211595177650452, 'learning_rate': 0.00018677888951924474, 'epoch': 0.21}
{'loss': 0.4632, 'grad_norm': 0.5733616948127747, 'learning_rate': 0.00018588632672204264, 'epoch': 0.21}


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

  1%|          | 2/192 [00:00<00:48,  3.94it/s]

  2%|▏         | 3/192 [00:01<01:45,  1.80it/s]

  2%|▏         | 4/192 [00:02<01:57,  1.59it/s]

  3%|▎         | 5/192 [00:03<02:10,  1.43it/s]

  3%|▎         | 6/192 [00:03<02:14,  1.38it/s]

  4%|▎         | 7/192 [00:04<02:27,  1.25it/s]

  4%|▍         | 8/192 [00:05<02:39,  1.16it/s]

  5%|▍         | 9/192 [00:06<02:50,  1.07it/s]

  5%|▌         | 10/192 [00:07<02:56,  1.03it/s]

  6%|▌         | 11/192 [00:08<02:40,  1.13it/s]

  6%|▋         | 12/192 [00:08<02:10,  1.38it/s]

  7%|▋         | 13/192 [00:09<02:17,  1.30it/s]

  7%|▋         | 14/192 [00:10<02:22,  1.25it/s]

  8%|▊         | 15/192 [00:11<02:08,  1.38it/s]

  8%|▊         | 16/192 [00:11<01:57,  1.50it/s]

  9%|▉         | 17/192 [00:12<02:17,  1.27it/s]

  9%|▉         | 18/192 [00:13<02:28,  1.17it/s]

 10%|▉         | 19/192 [00:14<02:14,  1.29it/s]

 10%|█         | 20/192 [00:14<01:58,  1.46it/s]

 11%|█         | 21/192 [00:15<02:07,  1.34it/s]

 11%|█▏        | 22/192 [00:16<02:05,  1.36it/s]

 12%|█▏        | 23/192 [00:17<01:50,  1.52it/s]

 12%|█▎        | 24/192 [00:17<01:22,  2.04it/s]

 13%|█▎        | 25/192 [00:17<01:02,  2.66it/s]

 14%|█▎        | 26/192 [00:17<00:50,  3.32it/s]

 14%|█▍        | 27/192 [00:17<00:42,  3.89it/s]

 15%|█▌        | 29/192 [00:17<00:30,  5.28it/s]

 16%|█▌        | 30/192 [00:17<00:28,  5.61it/s]

 16%|█▌        | 31/192 [00:18<00:28,  5.56it/s]

 17%|█▋        | 32/192 [00:18<00:27,  5.91it/s]

 17%|█▋        | 33/192 [00:18<00:49,  3.20it/s]

 18%|█▊        | 34/192 [00:19<01:23,  1.89it/s]

 18%|█▊        | 35/192 [00:21<01:47,  1.46it/s]

 19%|█▉        | 36/192 [00:21<01:40,  1.56it/s]

 19%|█▉        | 37/192 [00:21<01:18,  1.97it/s]

 20%|██        | 39/192 [00:22<00:58,  2.61it/s]

 21%|██        | 40/192 [00:23<01:12,  2.09it/s]

 21%|██▏       | 41/192 [00:23<01:32,  1.63it/s]

 22%|██▏       | 42/192 [00:24<01:47,  1.40it/s]

 22%|██▏       | 43/192 [00:26<01:59,  1.25it/s]

 23%|██▎       | 44/192 [00:26<01:46,  1.39it/s]

 23%|██▎       | 45/192 [00:26<01:23,  1.77it/s]

 24%|██▍       | 46/192 [00:27<01:21,  1.78it/s]

 24%|██▍       | 47/192 [00:28<01:38,  1.48it/s]

 25%|██▌       | 48/192 [00:28<01:40,  1.43it/s]

 26%|██▌       | 49/192 [00:29<01:28,  1.61it/s]

 26%|██▌       | 50/192 [00:29<01:07,  2.11it/s]

 27%|██▋       | 51/192 [00:30<01:11,  1.98it/s]

 27%|██▋       | 52/192 [00:30<01:11,  1.95it/s]

 28%|██▊       | 53/192 [00:30<00:59,  2.34it/s]

 28%|██▊       | 54/192 [00:31<01:09,  1.98it/s]

 29%|██▊       | 55/192 [00:32<01:31,  1.49it/s]

 29%|██▉       | 56/192 [00:33<01:39,  1.37it/s]

 30%|██▉       | 57/192 [00:34<01:44,  1.29it/s]

 30%|███       | 58/192 [00:34<01:28,  1.52it/s]

 31%|███       | 59/192 [00:35<01:27,  1.52it/s]

 31%|███▏      | 60/192 [00:36<01:45,  1.25it/s]

 32%|███▏      | 61/192 [00:37<01:43,  1.27it/s]

 32%|███▏      | 62/192 [00:37<01:16,  1.70it/s]

 33%|███▎      | 63/192 [00:37<00:58,  2.20it/s]

 33%|███▎      | 64/192 [00:37<00:53,  2.40it/s]

 34%|███▍      | 65/192 [00:38<00:52,  2.41it/s]

 35%|███▍      | 67/192 [00:38<00:34,  3.60it/s]

 35%|███▌      | 68/192 [00:38<00:29,  4.17it/s]

 36%|███▌      | 69/192 [00:39<00:46,  2.66it/s]

 36%|███▋      | 70/192 [00:40<00:53,  2.26it/s]

 37%|███▋      | 71/192 [00:40<00:54,  2.21it/s]

 38%|███▊      | 72/192 [00:41<01:14,  1.62it/s]

 38%|███▊      | 73/192 [00:42<01:35,  1.25it/s]

 39%|███▊      | 74/192 [00:43<01:27,  1.35it/s]

 39%|███▉      | 75/192 [00:43<01:07,  1.73it/s]

 40%|███▉      | 76/192 [00:44<01:07,  1.73it/s]

 40%|████      | 77/192 [00:45<01:21,  1.42it/s]

 41%|████      | 78/192 [00:46<01:27,  1.31it/s]

 41%|████      | 79/192 [00:46<01:20,  1.40it/s]

 42%|████▏     | 80/192 [00:47<01:12,  1.54it/s]

 42%|████▏     | 81/192 [00:48<01:24,  1.32it/s]

 43%|████▎     | 82/192 [00:49<01:29,  1.22it/s]

 43%|████▎     | 83/192 [00:50<01:37,  1.12it/s]

 44%|████▍     | 84/192 [00:50<01:28,  1.22it/s]

 44%|████▍     | 85/192 [00:51<01:20,  1.32it/s]

 45%|████▍     | 86/192 [00:51<01:13,  1.44it/s]

 45%|████▌     | 87/192 [00:52<00:57,  1.83it/s]

 46%|████▌     | 88/192 [00:52<00:43,  2.41it/s]

 47%|████▋     | 90/192 [00:52<00:27,  3.65it/s]

 47%|████▋     | 91/192 [00:53<00:34,  2.95it/s]

 48%|████▊     | 92/192 [00:53<00:45,  2.20it/s]

 48%|████▊     | 93/192 [00:54<00:55,  1.79it/s]

 49%|████▉     | 94/192 [00:55<00:51,  1.91it/s]

 49%|████▉     | 95/192 [00:55<00:53,  1.82it/s]

 50%|█████     | 96/192 [00:56<01:04,  1.49it/s]

 51%|█████     | 97/192 [00:57<01:01,  1.54it/s]

 51%|█████     | 98/192 [00:57<00:46,  2.01it/s]

 52%|█████▏    | 99/192 [00:58<00:50,  1.83it/s]

 52%|█████▏    | 100/192 [00:58<00:59,  1.56it/s]

 53%|█████▎    | 101/192 [01:00<01:10,  1.30it/s]

 53%|█████▎    | 102/192 [01:00<01:06,  1.36it/s]

 54%|█████▎    | 103/192 [01:01<01:02,  1.43it/s]

 54%|█████▍    | 104/192 [01:02<01:06,  1.32it/s]

 55%|█████▍    | 105/192 [01:02<01:01,  1.41it/s]

 55%|█████▌    | 106/192 [01:02<00:46,  1.87it/s]

 56%|█████▌    | 107/192 [01:03<00:48,  1.77it/s]

 56%|█████▋    | 108/192 [01:04<00:57,  1.46it/s]

 57%|█████▋    | 109/192 [01:05<01:09,  1.19it/s]

 57%|█████▋    | 110/192 [01:06<01:18,  1.05it/s]

 58%|█████▊    | 111/192 [01:07<01:11,  1.14it/s]

 58%|█████▊    | 112/192 [01:08<01:04,  1.25it/s]

 59%|█████▉    | 113/192 [01:08<00:59,  1.33it/s]

 59%|█████▉    | 114/192 [01:09<00:44,  1.75it/s]

 60%|█████▉    | 115/192 [01:09<00:44,  1.73it/s]

 60%|██████    | 116/192 [01:10<00:49,  1.55it/s]

 61%|██████    | 117/192 [01:10<00:44,  1.69it/s]

 61%|██████▏   | 118/192 [01:11<00:45,  1.64it/s]

 62%|██████▏   | 119/192 [01:12<00:52,  1.40it/s]

 62%|██████▎   | 120/192 [01:13<00:51,  1.41it/s]

 63%|██████▎   | 121/192 [01:13<00:45,  1.58it/s]

 64%|██████▎   | 122/192 [01:14<00:43,  1.61it/s]

 64%|██████▍   | 123/192 [01:14<00:42,  1.64it/s]

 65%|██████▍   | 124/192 [01:15<00:40,  1.69it/s]

 65%|██████▌   | 125/192 [01:16<00:48,  1.39it/s]

 66%|██████▌   | 126/192 [01:17<00:52,  1.26it/s]

 66%|██████▌   | 127/192 [01:18<00:48,  1.35it/s]

 67%|██████▋   | 128/192 [01:18<00:44,  1.45it/s]

 67%|██████▋   | 129/192 [01:19<00:49,  1.26it/s]

 68%|██████▊   | 130/192 [01:20<00:53,  1.17it/s]

 68%|██████▊   | 131/192 [01:21<00:54,  1.13it/s]

 69%|██████▉   | 132/192 [01:22<00:49,  1.22it/s]

 69%|██████▉   | 133/192 [01:22<00:42,  1.40it/s]

 70%|██████▉   | 134/192 [01:23<00:40,  1.43it/s]

 70%|███████   | 135/192 [01:23<00:38,  1.47it/s]

 71%|███████   | 136/192 [01:24<00:36,  1.53it/s]

 71%|███████▏  | 137/192 [01:25<00:42,  1.29it/s]

 72%|███████▏  | 138/192 [01:26<00:37,  1.42it/s]

 72%|███████▏  | 139/192 [01:26<00:27,  1.90it/s]

 73%|███████▎  | 141/192 [01:26<00:21,  2.33it/s]

 74%|███████▍  | 142/192 [01:28<00:30,  1.64it/s]

 74%|███████▍  | 143/192 [01:28<00:31,  1.56it/s]

 75%|███████▌  | 144/192 [01:28<00:24,  1.99it/s]

 76%|███████▌  | 145/192 [01:29<00:24,  1.89it/s]

 76%|███████▌  | 146/192 [01:30<00:25,  1.83it/s]

 77%|███████▋  | 147/192 [01:30<00:25,  1.78it/s]

 77%|███████▋  | 148/192 [01:31<00:31,  1.42it/s]

 78%|███████▊  | 149/192 [01:32<00:30,  1.42it/s]

 78%|███████▊  | 150/192 [01:32<00:22,  1.87it/s]

 79%|███████▊  | 151/192 [01:32<00:17,  2.36it/s]

 79%|███████▉  | 152/192 [01:33<00:18,  2.12it/s]

 80%|███████▉  | 153/192 [01:33<00:19,  1.99it/s]

 80%|████████  | 154/192 [01:34<00:21,  1.78it/s]

 81%|████████  | 155/192 [01:35<00:22,  1.66it/s]

 81%|████████▏ | 156/192 [01:36<00:22,  1.59it/s]

 82%|████████▏ | 157/192 [01:36<00:22,  1.55it/s]

 82%|████████▏ | 158/192 [01:37<00:21,  1.61it/s]

 83%|████████▎ | 159/192 [01:37<00:20,  1.63it/s]

 83%|████████▎ | 160/192 [01:37<00:14,  2.17it/s]

 84%|████████▍ | 161/192 [01:38<00:11,  2.76it/s]

 85%|████████▍ | 163/192 [01:38<00:07,  4.06it/s]

 85%|████████▌ | 164/192 [01:38<00:08,  3.30it/s]

 86%|████████▌ | 165/192 [01:39<00:12,  2.23it/s]

 86%|████████▋ | 166/192 [01:40<00:12,  2.14it/s]

 87%|████████▋ | 167/192 [01:40<00:12,  2.03it/s]

 88%|████████▊ | 168/192 [01:41<00:15,  1.58it/s]

 88%|████████▊ | 169/192 [01:42<00:14,  1.58it/s]

 89%|████████▊ | 170/192 [01:42<00:10,  2.04it/s]

 89%|████████▉ | 171/192 [01:42<00:08,  2.58it/s]

 90%|█████████ | 173/192 [01:43<00:07,  2.63it/s]

 91%|█████████ | 174/192 [01:44<00:10,  1.77it/s]

 91%|█████████ | 175/192 [01:45<00:10,  1.67it/s]

 92%|█████████▏| 176/192 [01:45<00:07,  2.13it/s]

 92%|█████████▏| 177/192 [01:45<00:05,  2.67it/s]

 93%|█████████▎| 178/192 [01:45<00:05,  2.53it/s]

 93%|█████████▎| 179/192 [01:46<00:06,  2.02it/s]

 94%|█████████▍| 180/192 [01:47<00:05,  2.20it/s]

 94%|█████████▍| 181/192 [01:47<00:05,  2.08it/s]

 95%|█████████▍| 182/192 [01:48<00:06,  1.59it/s]

 95%|█████████▌| 183/192 [01:49<00:05,  1.62it/s]

 96%|█████████▌| 184/192 [01:49<00:03,  2.12it/s]

 96%|█████████▋| 185/192 [01:49<00:02,  2.69it/s]

 97%|█████████▋| 186/192 [01:49<00:02,  2.56it/s]

 97%|█████████▋| 187/192 [01:50<00:02,  2.42it/s]

 98%|█████████▊| 188/192 [01:50<00:01,  3.12it/s]

 99%|█████████▉| 190/192 [01:50<00:00,  4.41it/s]

 99%|█████████▉| 191/192 [01:51<00:00,  3.06it/s]

100%|██████████| 192/192 [01:51<00:00,  2.56it/s]
                                                     

                                                 

 21%|██▏       | 200/935 [1:42:25<5:33:53, 27.26s/it]

100%|██████████| 192/192 [01:51<00:00,  2.56it/s]

                                                 wandb: WARNING URL not available in offline run

 21%|██▏       | 201/935 [1:42:50<12:15:19, 60.11s/it]
 22%|██▏       | 202/935 [1:43:14<10:03:24, 49.39s/it]
 22%|██▏       | 203/935 [1:43:31<8:02:21, 39.54s/it] 
 22%|██▏       | 204/935 [1:44:13<8:10:26, 40.25s/it]
 22%|██▏       | 205/935 [1:45:07<8:58:27, 44.26s/it]
                                                     

 22%|██▏       | 205/935 [1:45:07<8:58:27, 44.26s/it]
 22%|██▏       | 206/935 [1:45:29<7:36:27, 37.57s/it]
 22%|██▏       | 207/935 [1:45:55<6:54:49, 34.19s/it]
 22%|██▏       | 208/935 [1:46:15<6:04:23, 30.07s/it]
 22%|██▏       | 209/935 [1:46:47<6:10:58, 30.66s/it]
 22%|██▏       | 210/935 [1:47:44<7:45:24, 38.52s/it]
                                                     

 22%|██▏       | 210/935 [1:47:44<7:45:24, 38.52s/it]
 23%|██▎       | 211/935 [1:48:28<8:05:41, 40.25s/it]
 23%|██▎       | 212/935 [1:49:06<7:55:27, 39.46s/it]
 23%|██▎       | 213/935 [1:49:38<7:27:30, 37.19s/it]
 23%|██▎       | 214/935 [1:50:20<7:45:26, 38.73s/it]
 23%|██▎       | 215/935 [1:50:56<7:32:33, 37.71s/it]
                                                     

 23%|██▎       | 215/935 [1:50:56<7:32:33, 37.71s/it]
 23%|██▎       | 216/935 [1:51:37<7:43:24, 38.67s/it]
 23%|██▎       | 217/935 [1:52:12<7:30:58, 37.69s/it]
 23%|██▎       | 218/935 [1:52:51<7:36:20, 38.19s/it]
 23%|██▎       | 219/935 [1:53:30<7:36:09, 38.23s/it]
 24%|██▎       | 220/935 [1:54:02<7:14:13, 36.44s/it]
                                                     

 24%|██▎       | 220/935 [1:54:02<7:14:13, 36.44s/it]
 24%|██▎       | 221/935 [1:54:44<7:33:29, 38.11s/it]
 24%|██▎       | 222/935 [1:55:01<6:16:43, 31.70s/it]
 24%|██▍       | 223/935 [1:55:38<6:37:08, 33.47s/it]
 24%|██▍       | 224/935 [1:56:20<7:04:50, 35.85s/it]
 24%|██▍       | 225/935 [1:56:55<7:03:11, 35.76s/it]
                                                     

 24%|██▍       | 225/935 [1:56:55<7:03:11, 35.76s/it]
 24%|██▍       | 226/935 [1:57:31<7:02:40, 35.77s/it]
 24%|██▍       | 227/935 [1:58:03<6:47:24, 34.53s/it]
 24%|██▍       | 228/935 [1:58:50<7:31:47, 38.34s/it]
 24%|██▍       | 229/935 [1:59:22<7:09:04, 36.47s/it]
 25%|██▍       | 230/935 [1:59:46<6:25:45, 32.83s/it]
                                                     

 25%|██▍       | 230/935 [1:59:46<6:25:45, 32.83s/it]
 25%|██▍       | 231/935 [2:00:30<7:03:23, 36.08s/it]
 25%|██▍       | 232/935 [2:01:01<6:45:16, 34.59s/it]
 25%|██▍       | 233/935 [2:01:28<6:18:47, 32.38s/it]
 25%|██▌       | 234/935 [2:02:16<7:12:29, 37.02s/it]
 25%|██▌       | 235/935 [2:02:44<6:40:53, 34.36s/it]
                                                     

 25%|██▌       | 235/935 [2:02:44<6:40:53, 34.36s/it]
 25%|██▌       | 236/935 [2:03:28<7:13:36, 37.22s/it]
 25%|██▌       | 237/935 [2:03:55<6:35:49, 34.02s/it]
 25%|██▌       | 238/935 [2:04:23<6:15:23, 32.31s/it]
 26%|██▌       | 239/935 [2:04:58<6:22:44, 32.99s/it]
 26%|██▌       | 240/935 [2:05:27<6:11:11, 32.05s/it]
                                                     

 26%|██▌       | 240/935 [2:05:27<6:11:11, 32.05s/it]
 26%|██▌       | 241/935 [2:06:02<6:18:39, 32.74s/it]
 26%|██▌       | 242/935 [2:06:36<6:22:23, 33.11s/it]
 26%|██▌       | 243/935 [2:07:11<6:30:32, 33.86s/it]
 26%|██▌       | 244/935 [2:07:46<6:31:13, 33.97s/it]
 26%|██▌       | 245/935 [2:08:29<7:02:47, 36.77s/it]
                                                     

 26%|██▌       | 245/935 [2:08:29<7:02:47, 36.77s/it]
 26%|██▋       | 246/935 [2:09:09<7:12:41, 37.68s/it]
 26%|██▋       | 247/935 [2:09:45<7:06:40, 37.21s/it]
 27%|██▋       | 248/935 [2:10:13<6:34:23, 34.44s/it]
 27%|██▋       | 249/935 [2:10:32<5:42:44, 29.98s/it]
 27%|██▋       | 250/935 [2:10:42<4:32:38, 23.88s/it]
                                                     

 27%|██▋       | 250/935 [2:10:42<4:32:38, 23.88s/it]{'eval_loss': 0.4046805799007416, 'eval_runtime': 112.0258, 'eval_samples_per_second': 3.428, 'eval_steps_per_second': 1.714, 'epoch': 0.21}
{'loss': 0.6243, 'grad_norm': 0.6266054511070251, 'learning_rate': 0.00018496689028287572, 'epoch': 0.22}
{'loss': 0.6397, 'grad_norm': 0.4841332733631134, 'learning_rate': 0.00018402086789137546, 'epoch': 0.22}
{'loss': 0.5517, 'grad_norm': 0.566580057144165, 'learning_rate': 0.00018304855555585894, 'epoch': 0.23}
{'loss': 0.5346, 'grad_norm': 0.411471426486969, 'learning_rate': 0.00018205025751070875, 'epoch': 0.24}
{'loss': 0.3205, 'grad_norm': 0.48397207260131836, 'learning_rate': 0.00018102628612117865, 'epoch': 0.24}
{'loss': 0.6892, 'grad_norm': 0.6768320798873901, 'learning_rate': 0.0001799769617856552, 'epoch': 0.25}
{'loss': 0.541, 'grad_norm': 0.6652664542198181, 'learning_rate': 0.00017890261283540562, 'epoch': 0.25}
{'loss': 0.4365, 'grad_norm': 0.4666398763656616, 'learning_rate': 0.00017780357543184397, 'epoch': 0.26}
{'loss': 0.598, 'grad_norm': 0.5831547975540161, 'learning_rate': 0.0001766801934613467, 'epoch': 0.26}
{'loss': 0.5548, 'grad_norm': 0.5607553124427795, 'learning_rate': 0.00017553281842765169, 'epoch': 0.27}


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

  1%|          | 2/192 [00:00<00:45,  4.21it/s]

  2%|▏         | 3/192 [00:01<01:43,  1.83it/s]

  2%|▏         | 4/192 [00:02<01:55,  1.63it/s]

  3%|▎         | 5/192 [00:03<02:09,  1.45it/s]

  3%|▎         | 6/192 [00:03<02:13,  1.39it/s]

  4%|▎         | 7/192 [00:04<02:26,  1.26it/s]

  4%|▍         | 8/192 [00:05<02:38,  1.16it/s]

  5%|▍         | 9/192 [00:06<02:48,  1.08it/s]

  5%|▌         | 10/192 [00:07<02:55,  1.04it/s]

  6%|▌         | 11/192 [00:08<02:39,  1.13it/s]

  6%|▋         | 12/192 [00:08<02:10,  1.38it/s]

  7%|▋         | 13/192 [00:09<02:17,  1.31it/s]

  7%|▋         | 14/192 [00:10<02:23,  1.24it/s]

  8%|▊         | 15/192 [00:11<02:08,  1.38it/s]

  8%|▊         | 16/192 [00:11<01:57,  1.49it/s]

  9%|▉         | 17/192 [00:12<02:18,  1.26it/s]

  9%|▉         | 18/192 [00:13<02:29,  1.16it/s]

 10%|▉         | 19/192 [00:14<02:15,  1.28it/s]

 10%|█         | 20/192 [00:14<01:59,  1.44it/s]

 11%|█         | 21/192 [00:15<02:07,  1.34it/s]

 11%|█▏        | 22/192 [00:16<02:05,  1.36it/s]

 12%|█▏        | 23/192 [00:16<01:48,  1.56it/s]

 13%|█▎        | 25/192 [00:17<01:03,  2.63it/s]

 14%|█▎        | 26/192 [00:17<00:52,  3.13it/s]

 14%|█▍        | 27/192 [00:17<00:45,  3.63it/s]

 15%|█▍        | 28/192 [00:17<00:37,  4.38it/s]

 15%|█▌        | 29/192 [00:17<00:33,  4.90it/s]

 16%|█▌        | 30/192 [00:17<00:30,  5.33it/s]

 16%|█▌        | 31/192 [00:17<00:30,  5.35it/s]

 17%|█▋        | 32/192 [00:18<00:27,  5.80it/s]

 17%|█▋        | 33/192 [00:18<00:51,  3.11it/s]

 18%|█▊        | 34/192 [00:19<01:25,  1.84it/s]

 18%|█▊        | 35/192 [00:20<01:49,  1.44it/s]

 19%|█▉        | 36/192 [00:21<01:40,  1.55it/s]

 19%|█▉        | 37/192 [00:21<01:18,  1.97it/s]

 20%|██        | 39/192 [00:22<00:58,  2.61it/s]

 21%|██        | 40/192 [00:22<01:12,  2.10it/s]

 21%|██▏       | 41/192 [00:23<01:32,  1.63it/s]

 22%|██▏       | 42/192 [00:24<01:47,  1.40it/s]

 22%|██▏       | 43/192 [00:25<01:59,  1.25it/s]

 23%|██▎       | 44/192 [00:26<01:46,  1.39it/s]

 23%|██▎       | 45/192 [00:26<01:23,  1.77it/s]

 24%|██▍       | 46/192 [00:27<01:21,  1.79it/s]

 24%|██▍       | 47/192 [00:28<01:37,  1.48it/s]

 25%|██▌       | 48/192 [00:28<01:40,  1.43it/s]

 26%|██▌       | 49/192 [00:29<01:28,  1.61it/s]

 26%|██▌       | 50/192 [00:29<01:07,  2.12it/s]

 27%|██▋       | 51/192 [00:29<01:11,  1.98it/s]

 27%|██▋       | 52/192 [00:30<01:11,  1.96it/s]

 28%|██▊       | 53/192 [00:30<00:58,  2.39it/s]

 28%|██▊       | 54/192 [00:31<01:10,  1.96it/s]

 29%|██▊       | 55/192 [00:32<01:32,  1.49it/s]

 29%|██▉       | 56/192 [00:33<01:39,  1.37it/s]

 30%|██▉       | 57/192 [00:34<01:44,  1.29it/s]

 30%|███       | 58/192 [00:34<01:28,  1.51it/s]

 31%|███       | 59/192 [00:35<01:27,  1.52it/s]

 31%|███▏      | 60/192 [00:36<01:45,  1.25it/s]

 32%|███▏      | 61/192 [00:37<01:42,  1.28it/s]

 32%|███▏      | 62/192 [00:37<01:15,  1.72it/s]

 33%|███▎      | 63/192 [00:37<00:58,  2.22it/s]

 33%|███▎      | 64/192 [00:37<00:52,  2.42it/s]

 34%|███▍      | 65/192 [00:38<00:52,  2.41it/s]

 35%|███▍      | 67/192 [00:38<00:34,  3.62it/s]

 35%|███▌      | 68/192 [00:38<00:29,  4.17it/s]

 36%|███▌      | 69/192 [00:39<00:46,  2.66it/s]

 36%|███▋      | 70/192 [00:39<00:53,  2.27it/s]

 37%|███▋      | 71/192 [00:40<00:54,  2.21it/s]

 38%|███▊      | 72/192 [00:41<01:14,  1.61it/s]

 38%|███▊      | 73/192 [00:42<01:36,  1.23it/s]

 39%|███▊      | 74/192 [00:43<01:28,  1.34it/s]

 39%|███▉      | 75/192 [00:43<01:08,  1.72it/s]

 40%|███▉      | 76/192 [00:44<01:07,  1.73it/s]

 40%|████      | 77/192 [00:45<01:21,  1.41it/s]

 41%|████      | 78/192 [00:45<01:27,  1.30it/s]

 41%|████      | 79/192 [00:46<01:20,  1.41it/s]

 42%|████▏     | 80/192 [00:47<01:12,  1.54it/s]

 42%|████▏     | 81/192 [00:48<01:23,  1.32it/s]

 43%|████▎     | 82/192 [00:48<01:29,  1.23it/s]

 43%|████▎     | 83/192 [00:50<01:36,  1.13it/s]

 44%|████▍     | 84/192 [00:50<01:23,  1.29it/s]

 44%|████▍     | 85/192 [00:51<01:18,  1.37it/s]

 45%|████▍     | 86/192 [00:51<01:11,  1.47it/s]

 45%|████▌     | 87/192 [00:51<00:55,  1.88it/s]

 46%|████▌     | 88/192 [00:52<00:42,  2.46it/s]

 47%|████▋     | 90/192 [00:52<00:27,  3.72it/s]

 47%|████▋     | 91/192 [00:52<00:34,  2.96it/s]

 48%|████▊     | 92/192 [00:53<00:45,  2.22it/s]

 48%|████▊     | 93/192 [00:54<00:54,  1.81it/s]

 49%|████▉     | 94/192 [00:54<00:51,  1.92it/s]

 49%|████▉     | 95/192 [00:55<00:53,  1.83it/s]

 50%|█████     | 96/192 [00:56<01:04,  1.50it/s]

 51%|█████     | 97/192 [00:56<01:01,  1.54it/s]

 51%|█████     | 98/192 [00:57<00:46,  2.02it/s]

 52%|█████▏    | 99/192 [00:57<00:50,  1.85it/s]

 52%|█████▏    | 100/192 [00:58<00:58,  1.57it/s]

 53%|█████▎    | 101/192 [00:59<01:10,  1.30it/s]

 53%|█████▎    | 102/192 [01:00<01:06,  1.35it/s]

 54%|█████▎    | 103/192 [01:00<01:01,  1.44it/s]

 54%|█████▍    | 104/192 [01:01<01:06,  1.33it/s]

 55%|█████▍    | 105/192 [01:02<01:01,  1.42it/s]

 55%|█████▌    | 106/192 [01:02<00:45,  1.88it/s]

 56%|█████▌    | 107/192 [01:03<00:47,  1.78it/s]

 56%|█████▋    | 108/192 [01:04<00:57,  1.47it/s]

 57%|█████▋    | 109/192 [01:05<01:09,  1.19it/s]

 57%|█████▋    | 110/192 [01:06<01:18,  1.05it/s]

 58%|█████▊    | 111/192 [01:07<01:11,  1.14it/s]

 58%|█████▊    | 112/192 [01:07<01:04,  1.25it/s]

 59%|█████▉    | 113/192 [01:08<00:59,  1.33it/s]

 59%|█████▉    | 114/192 [01:08<00:44,  1.75it/s]

 60%|█████▉    | 115/192 [01:09<00:44,  1.73it/s]

 60%|██████    | 116/192 [01:10<00:48,  1.56it/s]

 61%|██████    | 117/192 [01:10<00:44,  1.70it/s]

 61%|██████▏   | 118/192 [01:11<00:45,  1.64it/s]

 62%|██████▏   | 119/192 [01:12<00:51,  1.41it/s]

 62%|██████▎   | 120/192 [01:12<00:50,  1.41it/s]

 63%|██████▎   | 121/192 [01:13<00:44,  1.58it/s]

 64%|██████▎   | 122/192 [01:13<00:43,  1.59it/s]

 64%|██████▍   | 123/192 [01:14<00:41,  1.66it/s]

 65%|██████▍   | 124/192 [01:15<00:39,  1.70it/s]

 65%|██████▌   | 125/192 [01:16<00:47,  1.40it/s]

 66%|██████▌   | 126/192 [01:17<00:52,  1.26it/s]

 66%|██████▌   | 127/192 [01:17<00:48,  1.35it/s]

 67%|██████▋   | 128/192 [01:18<00:43,  1.46it/s]

 67%|██████▋   | 129/192 [01:19<00:49,  1.26it/s]

 68%|██████▊   | 130/192 [01:20<00:52,  1.17it/s]

 68%|██████▊   | 131/192 [01:21<00:53,  1.14it/s]

 69%|██████▉   | 132/192 [01:21<00:48,  1.23it/s]

 69%|██████▉   | 133/192 [01:22<00:41,  1.41it/s]

 70%|██████▉   | 134/192 [01:22<00:40,  1.44it/s]

 70%|███████   | 135/192 [01:23<00:38,  1.48it/s]

 71%|███████   | 136/192 [01:24<00:36,  1.54it/s]

 71%|███████▏  | 137/192 [01:25<00:42,  1.30it/s]

 72%|███████▏  | 138/192 [01:25<00:38,  1.42it/s]

 72%|███████▏  | 139/192 [01:25<00:27,  1.90it/s]

 73%|███████▎  | 141/192 [01:26<00:21,  2.32it/s]

 74%|███████▍  | 142/192 [01:27<00:30,  1.65it/s]

 74%|███████▍  | 143/192 [01:28<00:31,  1.57it/s]

 75%|███████▌  | 144/192 [01:28<00:23,  2.00it/s]

 76%|███████▌  | 145/192 [01:29<00:24,  1.91it/s]

 76%|███████▌  | 146/192 [01:29<00:25,  1.84it/s]

 77%|███████▋  | 147/192 [01:30<00:25,  1.79it/s]

 77%|███████▋  | 148/192 [01:31<00:30,  1.43it/s]

 78%|███████▊  | 149/192 [01:32<00:30,  1.43it/s]

 78%|███████▊  | 150/192 [01:32<00:22,  1.87it/s]

 79%|███████▊  | 151/192 [01:32<00:17,  2.36it/s]

 79%|███████▉  | 152/192 [01:32<00:18,  2.13it/s]

 80%|███████▉  | 153/192 [01:33<00:20,  1.94it/s]

 80%|████████  | 154/192 [01:34<00:21,  1.77it/s]

 81%|████████  | 155/192 [01:34<00:22,  1.62it/s]

 81%|████████▏ | 156/192 [01:35<00:22,  1.60it/s]

 82%|████████▏ | 157/192 [01:36<00:22,  1.55it/s]

 82%|████████▏ | 158/192 [01:36<00:21,  1.61it/s]

 83%|████████▎ | 159/192 [01:37<00:21,  1.57it/s]

 84%|████████▍ | 161/192 [01:37<00:12,  2.58it/s]

 85%|████████▍ | 163/192 [01:37<00:08,  3.60it/s]

 85%|████████▌ | 164/192 [01:38<00:08,  3.11it/s]

 86%|████████▌ | 165/192 [01:39<00:12,  2.21it/s]

 86%|████████▋ | 166/192 [01:39<00:12,  2.14it/s]

 87%|████████▋ | 167/192 [01:40<00:12,  2.03it/s]

 88%|████████▊ | 168/192 [01:41<00:14,  1.60it/s]

 88%|████████▊ | 169/192 [01:41<00:14,  1.60it/s]

 89%|████████▊ | 170/192 [01:42<00:10,  2.06it/s]

 89%|████████▉ | 171/192 [01:42<00:08,  2.59it/s]

 90%|█████████ | 173/192 [01:43<00:07,  2.63it/s]

 91%|█████████ | 174/192 [01:44<00:10,  1.78it/s]

 91%|█████████ | 175/192 [01:44<00:10,  1.68it/s]

 92%|█████████▏| 176/192 [01:44<00:07,  2.15it/s]

 92%|█████████▏| 177/192 [01:45<00:05,  2.69it/s]

 93%|█████████▎| 178/192 [01:45<00:05,  2.52it/s]

 93%|█████████▎| 179/192 [01:46<00:06,  2.02it/s]

 94%|█████████▍| 180/192 [01:46<00:05,  2.18it/s]

 94%|█████████▍| 181/192 [01:47<00:05,  2.08it/s]

 95%|█████████▍| 182/192 [01:48<00:06,  1.59it/s]

 95%|█████████▌| 183/192 [01:48<00:05,  1.61it/s]

 96%|█████████▌| 184/192 [01:48<00:03,  2.13it/s]

 96%|█████████▋| 185/192 [01:48<00:02,  2.71it/s]

 97%|█████████▋| 186/192 [01:49<00:02,  2.57it/s]

 97%|█████████▋| 187/192 [01:50<00:02,  2.20it/s]

 98%|█████████▊| 188/192 [01:50<00:01,  2.85it/s]

 99%|█████████▉| 190/192 [01:50<00:00,  4.12it/s]

 99%|█████████▉| 191/192 [01:51<00:00,  2.98it/s]

100%|██████████| 192/192 [01:51<00:00,  2.51it/s]
                                                     

                                                 

 27%|██▋       | 250/935 [2:12:34<4:32:38, 23.88s/it]

100%|██████████| 192/192 [01:51<00:00,  2.51it/s]

                                                 
 27%|██▋       | 251/935 [2:12:52<10:35:28, 55.74s/it]
 27%|██▋       | 252/935 [2:13:19<8:54:59, 47.00s/it] 
 27%|██▋       | 253/935 [2:13:36<7:13:36, 38.15s/it]
 27%|██▋       | 254/935 [2:14:02<6:30:16, 34.38s/it]
 27%|██▋       | 255/935 [2:14:20<5:34:48, 29.54s/it]
                                                     

 27%|██▋       | 255/935 [2:14:20<5:34:48, 29.54s/it]
 27%|██▋       | 256/935 [2:14:38<4:53:23, 25.93s/it]
 27%|██▋       | 257/935 [2:15:03<4:52:18, 25.87s/it]
 28%|██▊       | 258/935 [2:15:25<4:38:11, 24.66s/it]
 28%|██▊       | 259/935 [2:15:41<4:08:19, 22.04s/it]
 28%|██▊       | 260/935 [2:16:10<4:30:09, 24.01s/it]
                                                     

 28%|██▊       | 260/935 [2:16:10<4:30:09, 24.01s/it]
 28%|██▊       | 261/935 [2:16:41<4:53:54, 26.16s/it]
 28%|██▊       | 262/935 [2:17:00<4:29:07, 23.99s/it]
 28%|██▊       | 263/935 [2:17:20<4:15:53, 22.85s/it]
 28%|██▊       | 264/935 [2:17:42<4:14:02, 22.72s/it]
 28%|██▊       | 265/935 [2:18:04<4:09:35, 22.35s/it]
                                                     

 28%|██▊       | 265/935 [2:18:04<4:09:35, 22.35s/it]
 28%|██▊       | 266/935 [2:18:29<4:19:40, 23.29s/it]
 29%|██▊       | 267/935 [2:18:55<4:28:16, 24.10s/it]
 29%|██▊       | 268/935 [2:19:05<3:40:58, 19.88s/it]
 29%|██▉       | 269/935 [2:19:13<2:59:32, 16.18s/it]
 29%|██▉       | 270/935 [2:19:37<3:26:39, 18.65s/it]
                                                     

 29%|██▉       | 270/935 [2:19:37<3:26:39, 18.65s/it]
 29%|██▉       | 271/935 [2:19:56<3:27:47, 18.78s/it]
 29%|██▉       | 272/935 [2:20:23<3:52:04, 21.00s/it]
 29%|██▉       | 273/935 [2:20:56<4:31:34, 24.61s/it]
 29%|██▉       | 274/935 [2:21:17<4:20:21, 23.63s/it]
 29%|██▉       | 275/935 [2:21:43<4:28:24, 24.40s/it]
                                                     

 29%|██▉       | 275/935 [2:21:43<4:28:24, 24.40s/it]
 30%|██▉       | 276/935 [2:22:05<4:20:41, 23.74s/it]
 30%|██▉       | 277/935 [2:22:24<4:05:02, 22.34s/it]
 30%|██▉       | 278/935 [2:22:41<3:46:09, 20.65s/it]
 30%|██▉       | 279/935 [2:23:00<3:39:21, 20.06s/it]
 30%|██▉       | 280/935 [2:23:18<3:33:16, 19.54s/it]
                                                     

 30%|██▉       | 280/935 [2:23:18<3:33:16, 19.54s/it]
 30%|███       | 281/935 [2:23:50<4:14:07, 23.31s/it]
 30%|███       | 282/935 [2:24:02<3:35:09, 19.77s/it]
 30%|███       | 283/935 [2:24:23<3:40:34, 20.30s/it]
 30%|███       | 284/935 [2:24:40<3:27:17, 19.11s/it]
 30%|███       | 285/935 [2:25:10<4:03:37, 22.49s/it]
                                                     

 30%|███       | 285/935 [2:25:10<4:03:37, 22.49s/it]
 31%|███       | 286/935 [2:25:24<3:34:48, 19.86s/it]
 31%|███       | 287/935 [2:25:49<3:50:27, 21.34s/it]
 31%|███       | 288/935 [2:26:18<4:17:59, 23.93s/it]
 31%|███       | 289/935 [2:26:44<4:22:51, 24.41s/it]
 31%|███       | 290/935 [2:27:08<4:20:49, 24.26s/it]
                                                     

 31%|███       | 290/935 [2:27:08<4:20:49, 24.26s/it]
 31%|███       | 291/935 [2:27:28<4:05:22, 22.86s/it]
 31%|███       | 292/935 [2:27:42<3:38:32, 20.39s/it]
 31%|███▏      | 293/935 [2:27:57<3:20:02, 18.70s/it]
 31%|███▏      | 294/935 [2:28:18<3:27:41, 19.44s/it]
 32%|███▏      | 295/935 [2:28:34<3:16:51, 18.46s/it]
                                                     

 32%|███▏      | 295/935 [2:28:34<3:16:51, 18.46s/it]
 32%|███▏      | 296/935 [2:29:00<3:39:50, 20.64s/it]
 32%|███▏      | 297/935 [2:29:19<3:34:26, 20.17s/it]
 32%|███▏      | 298/935 [2:29:42<3:42:28, 20.95s/it]
 32%|███▏      | 299/935 [2:30:05<3:49:36, 21.66s/it]
 32%|███▏      | 300/935 [2:30:31<4:03:11, 22.98s/it]
                                                     

 32%|███▏      | 300/935 [2:30:31<4:03:11, 22.98s/it]{'eval_loss': 0.3891582489013672, 'eval_runtime': 111.8073, 'eval_samples_per_second': 3.434, 'eval_steps_per_second': 1.717, 'epoch': 0.27}
{'loss': 0.4506, 'grad_norm': 0.5996724367141724, 'learning_rate': 0.00017436180934187308, 'epoch': 0.27}
{'loss': 0.526, 'grad_norm': 0.5043736100196838, 'learning_rate': 0.00017316753261016783, 'epoch': 0.28}
{'loss': 0.3911, 'grad_norm': 0.5816839337348938, 'learning_rate': 0.00017195036191908797, 'epoch': 0.28}
{'loss': 0.6858, 'grad_norm': 0.5987787842750549, 'learning_rate': 0.00017071067811865476, 'epoch': 0.29}
{'loss': 0.5402, 'grad_norm': 0.5184270739555359, 'learning_rate': 0.00016944886910319173, 'epoch': 0.29}
{'loss': 0.6015, 'grad_norm': 0.7627037763595581, 'learning_rate': 0.00016816532968995328, 'epoch': 0.3}
{'loss': 0.4313, 'grad_norm': 0.572108805179596, 'learning_rate': 0.00016686046149558736, 'epoch': 0.3}
{'loss': 0.475, 'grad_norm': 0.5677588582038879, 'learning_rate': 0.0001655346728104704, 'epoch': 0.31}
{'loss': 0.6212, 'grad_norm': 0.5855934619903564, 'learning_rate': 0.0001641883784709541, 'epoch': 0.32}
{'loss': 0.6327, 'grad_norm': 0.5541160106658936, 'learning_rate': 0.00016282199972956425, 'epoch': 0.32}


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

  1%|          | 2/192 [00:00<00:48,  3.88it/s]

  2%|▏         | 3/192 [00:01<01:44,  1.82it/s]

  2%|▏         | 4/192 [00:02<01:57,  1.60it/s]

  3%|▎         | 5/192 [00:03<02:10,  1.43it/s]

  3%|▎         | 6/192 [00:03<02:14,  1.39it/s]

  4%|▎         | 7/192 [00:04<02:26,  1.26it/s]

  4%|▍         | 8/192 [00:05<02:38,  1.16it/s]

  5%|▍         | 9/192 [00:06<02:48,  1.08it/s]

  5%|▌         | 10/192 [00:07<02:55,  1.04it/s]

  6%|▌         | 11/192 [00:08<02:39,  1.13it/s]

  6%|▋         | 12/192 [00:08<02:10,  1.38it/s]

  7%|▋         | 13/192 [00:09<02:17,  1.30it/s]

  7%|▋         | 14/192 [00:10<02:23,  1.24it/s]

  8%|▊         | 15/192 [00:11<02:09,  1.37it/s]

  8%|▊         | 16/192 [00:11<01:57,  1.49it/s]

  9%|▉         | 17/192 [00:12<02:18,  1.26it/s]

  9%|▉         | 18/192 [00:13<02:30,  1.16it/s]

 10%|▉         | 19/192 [00:14<02:15,  1.28it/s]

 10%|█         | 20/192 [00:14<01:59,  1.44it/s]

 11%|█         | 21/192 [00:15<02:08,  1.34it/s]

 11%|█▏        | 22/192 [00:16<02:06,  1.35it/s]

 12%|█▏        | 23/192 [00:17<01:48,  1.55it/s]

 13%|█▎        | 25/192 [00:17<01:03,  2.62it/s]

 14%|█▎        | 26/192 [00:17<00:53,  3.12it/s]

 14%|█▍        | 27/192 [00:17<00:45,  3.62it/s]

 15%|█▍        | 28/192 [00:17<00:37,  4.37it/s]

 15%|█▌        | 29/192 [00:17<00:38,  4.21it/s]

 16%|█▌        | 30/192 [00:17<00:32,  5.03it/s]

 16%|█▌        | 31/192 [00:18<00:30,  5.27it/s]

 17%|█▋        | 32/192 [00:18<00:27,  5.80it/s]

 17%|█▋        | 33/192 [00:18<00:52,  3.04it/s]

 18%|█▊        | 34/192 [00:19<01:26,  1.82it/s]

 18%|█▊        | 35/192 [00:21<01:49,  1.43it/s]

 19%|█▉        | 36/192 [00:21<01:40,  1.54it/s]

 19%|█▉        | 37/192 [00:21<01:18,  1.97it/s]

 20%|██        | 39/192 [00:22<00:58,  2.62it/s]

 21%|██        | 40/192 [00:22<01:12,  2.09it/s]

 21%|██▏       | 41/192 [00:23<01:32,  1.64it/s]

 22%|██▏       | 42/192 [00:24<01:47,  1.40it/s]

 22%|██▏       | 43/192 [00:25<01:59,  1.25it/s]

 23%|██▎       | 44/192 [00:26<01:46,  1.39it/s]

 23%|██▎       | 45/192 [00:26<01:23,  1.77it/s]

 24%|██▍       | 46/192 [00:27<01:21,  1.79it/s]

 24%|██▍       | 47/192 [00:28<01:37,  1.48it/s]

 25%|██▌       | 48/192 [00:28<01:40,  1.43it/s]

 26%|██▌       | 49/192 [00:29<01:28,  1.61it/s]

 26%|██▌       | 50/192 [00:29<01:07,  2.12it/s]

 27%|██▋       | 51/192 [00:30<01:11,  1.98it/s]

 27%|██▋       | 52/192 [00:30<01:11,  1.95it/s]

 28%|██▊       | 53/192 [00:30<00:58,  2.37it/s]

 28%|██▊       | 54/192 [00:31<01:10,  1.96it/s]

 29%|██▊       | 55/192 [00:32<01:32,  1.48it/s]

 29%|██▉       | 56/192 [00:33<01:39,  1.37it/s]

 30%|██▉       | 57/192 [00:34<01:44,  1.29it/s]

 30%|███       | 58/192 [00:34<01:28,  1.52it/s]

 31%|███       | 59/192 [00:35<01:27,  1.52it/s]

 31%|███▏      | 60/192 [00:36<01:45,  1.25it/s]

 32%|███▏      | 61/192 [00:37<01:42,  1.28it/s]

 32%|███▏      | 62/192 [00:37<01:16,  1.71it/s]

 33%|███▎      | 63/192 [00:37<00:58,  2.20it/s]

 33%|███▎      | 64/192 [00:37<00:53,  2.41it/s]

 34%|███▍      | 65/192 [00:38<00:52,  2.41it/s]

 35%|███▍      | 67/192 [00:38<00:34,  3.61it/s]

 35%|███▌      | 68/192 [00:38<00:29,  4.18it/s]

 36%|███▌      | 69/192 [00:39<00:46,  2.65it/s]

 36%|███▋      | 70/192 [00:39<00:53,  2.27it/s]

 37%|███▋      | 71/192 [00:40<00:54,  2.20it/s]

 38%|███▊      | 72/192 [00:41<01:14,  1.61it/s]

 38%|███▊      | 73/192 [00:42<01:35,  1.25it/s]

 39%|███▊      | 74/192 [00:43<01:27,  1.35it/s]

 39%|███▉      | 75/192 [00:43<01:07,  1.74it/s]

 40%|███▉      | 76/192 [00:44<01:06,  1.74it/s]

 40%|████      | 77/192 [00:45<01:20,  1.42it/s]

 41%|████      | 78/192 [00:46<01:26,  1.31it/s]

 41%|████      | 79/192 [00:46<01:19,  1.42it/s]

 42%|████▏     | 80/192 [00:47<01:12,  1.54it/s]

 42%|████▏     | 81/192 [00:48<01:23,  1.33it/s]

 43%|████▎     | 82/192 [00:49<01:29,  1.23it/s]

 43%|████▎     | 83/192 [00:50<01:36,  1.13it/s]

 44%|████▍     | 84/192 [00:50<01:23,  1.29it/s]

 44%|████▍     | 85/192 [00:51<01:17,  1.37it/s]

 45%|████▍     | 86/192 [00:51<01:11,  1.47it/s]

 45%|████▌     | 87/192 [00:52<00:55,  1.88it/s]

 46%|████▌     | 88/192 [00:52<00:42,  2.46it/s]

 47%|████▋     | 90/192 [00:52<00:27,  3.72it/s]

 47%|████▋     | 91/192 [00:52<00:33,  2.97it/s]

 48%|████▊     | 92/192 [00:53<00:45,  2.22it/s]

 48%|████▊     | 93/192 [00:54<00:54,  1.81it/s]

 49%|████▉     | 94/192 [00:54<00:51,  1.92it/s]

 49%|████▉     | 95/192 [00:55<00:52,  1.83it/s]

 50%|█████     | 96/192 [00:56<01:04,  1.50it/s]

 51%|█████     | 97/192 [00:57<01:01,  1.54it/s]

 51%|█████     | 98/192 [00:57<00:46,  2.01it/s]

 52%|█████▏    | 99/192 [00:57<00:50,  1.85it/s]

 52%|█████▏    | 100/192 [00:58<00:58,  1.56it/s]

 53%|█████▎    | 101/192 [00:59<01:09,  1.31it/s]

 53%|█████▎    | 102/192 [01:00<01:05,  1.36it/s]

 54%|█████▎    | 103/192 [01:01<01:01,  1.44it/s]

 54%|█████▍    | 104/192 [01:01<01:06,  1.33it/s]

 55%|█████▍    | 105/192 [01:02<01:01,  1.42it/s]

 55%|█████▌    | 106/192 [01:02<00:45,  1.87it/s]

 56%|█████▌    | 107/192 [01:03<00:47,  1.77it/s]

 56%|█████▋    | 108/192 [01:04<00:57,  1.47it/s]

 57%|█████▋    | 109/192 [01:05<01:09,  1.19it/s]

 57%|█████▋    | 110/192 [01:06<01:17,  1.06it/s]

 58%|█████▊    | 111/192 [01:07<01:10,  1.14it/s]

 58%|█████▊    | 112/192 [01:08<01:04,  1.25it/s]

 59%|█████▉    | 113/192 [01:08<00:59,  1.33it/s]

 59%|█████▉    | 114/192 [01:08<00:44,  1.76it/s]

 60%|█████▉    | 115/192 [01:09<00:44,  1.73it/s]

 60%|██████    | 116/192 [01:10<00:48,  1.56it/s]

 61%|██████    | 117/192 [01:10<00:44,  1.70it/s]

 61%|██████▏   | 118/192 [01:11<00:44,  1.64it/s]

 62%|██████▏   | 119/192 [01:12<00:51,  1.40it/s]

 62%|██████▎   | 120/192 [01:12<00:50,  1.41it/s]

 63%|██████▎   | 121/192 [01:13<00:44,  1.58it/s]

 64%|██████▎   | 122/192 [01:13<00:43,  1.62it/s]

 64%|██████▍   | 123/192 [01:14<00:41,  1.65it/s]

 65%|██████▍   | 124/192 [01:15<00:40,  1.69it/s]

 65%|██████▌   | 125/192 [01:16<00:47,  1.40it/s]

 66%|██████▌   | 126/192 [01:17<00:52,  1.26it/s]

 66%|██████▌   | 127/192 [01:17<00:48,  1.35it/s]

 67%|██████▋   | 128/192 [01:18<00:43,  1.46it/s]

 67%|██████▋   | 129/192 [01:19<00:49,  1.27it/s]

 68%|██████▊   | 130/192 [01:20<00:52,  1.17it/s]

 68%|██████▊   | 131/192 [01:21<00:53,  1.14it/s]

 69%|██████▉   | 132/192 [01:21<00:48,  1.22it/s]

 69%|██████▉   | 133/192 [01:22<00:41,  1.41it/s]

 70%|██████▉   | 134/192 [01:23<00:40,  1.44it/s]

 70%|███████   | 135/192 [01:23<00:38,  1.46it/s]

 71%|███████   | 136/192 [01:24<00:36,  1.54it/s]

 71%|███████▏  | 137/192 [01:25<00:42,  1.30it/s]

 72%|███████▏  | 138/192 [01:25<00:37,  1.43it/s]

 72%|███████▏  | 139/192 [01:25<00:27,  1.90it/s]

 73%|███████▎  | 141/192 [01:26<00:21,  2.33it/s]

 74%|███████▍  | 142/192 [01:27<00:30,  1.66it/s]

 74%|███████▍  | 143/192 [01:28<00:31,  1.57it/s]

 75%|███████▌  | 144/192 [01:28<00:23,  2.01it/s]

 76%|███████▌  | 145/192 [01:29<00:24,  1.91it/s]

 76%|███████▌  | 146/192 [01:29<00:25,  1.84it/s]

 77%|███████▋  | 147/192 [01:30<00:25,  1.79it/s]

 77%|███████▋  | 148/192 [01:31<00:30,  1.42it/s]

 78%|███████▊  | 149/192 [01:32<00:30,  1.43it/s]

 78%|███████▊  | 150/192 [01:32<00:22,  1.87it/s]

 79%|███████▊  | 151/192 [01:32<00:17,  2.36it/s]

 79%|███████▉  | 152/192 [01:32<00:18,  2.13it/s]

 80%|███████▉  | 153/192 [01:33<00:19,  1.98it/s]

 80%|████████  | 154/192 [01:34<00:21,  1.78it/s]

 81%|████████  | 155/192 [01:34<00:22,  1.67it/s]

 81%|████████▏ | 156/192 [01:35<00:22,  1.59it/s]

 82%|████████▏ | 157/192 [01:36<00:22,  1.56it/s]

 82%|████████▏ | 158/192 [01:36<00:21,  1.61it/s]

 83%|████████▎ | 159/192 [01:37<00:20,  1.64it/s]

 83%|████████▎ | 160/192 [01:37<00:14,  2.18it/s]

 84%|████████▍ | 161/192 [01:37<00:11,  2.78it/s]

 85%|████████▍ | 163/192 [01:37<00:07,  4.07it/s]

 85%|████████▌ | 164/192 [01:38<00:08,  3.27it/s]

 86%|████████▌ | 165/192 [01:39<00:12,  2.21it/s]

 86%|████████▋ | 166/192 [01:39<00:12,  2.14it/s]

 87%|████████▋ | 167/192 [01:40<00:12,  2.02it/s]

 88%|████████▊ | 168/192 [01:41<00:15,  1.58it/s]

 88%|████████▊ | 169/192 [01:41<00:14,  1.58it/s]

 89%|████████▊ | 170/192 [01:42<00:10,  2.05it/s]

 89%|████████▉ | 171/192 [01:42<00:08,  2.59it/s]

 90%|█████████ | 173/192 [01:43<00:07,  2.62it/s]

 91%|█████████ | 174/192 [01:44<00:10,  1.78it/s]

 91%|█████████ | 175/192 [01:44<00:10,  1.67it/s]

 92%|█████████▏| 176/192 [01:44<00:07,  2.15it/s]

 92%|█████████▏| 177/192 [01:45<00:05,  2.69it/s]

 93%|█████████▎| 178/192 [01:45<00:05,  2.52it/s]

 93%|█████████▎| 179/192 [01:46<00:06,  2.03it/s]

 94%|█████████▍| 180/192 [01:46<00:05,  2.20it/s]

 94%|█████████▍| 181/192 [01:47<00:05,  2.09it/s]

 95%|█████████▍| 182/192 [01:48<00:06,  1.60it/s]

 95%|█████████▌| 183/192 [01:48<00:05,  1.63it/s]

 96%|█████████▌| 184/192 [01:48<00:03,  2.13it/s]

 96%|█████████▋| 185/192 [01:48<00:02,  2.70it/s]

 97%|█████████▋| 186/192 [01:49<00:02,  2.60it/s]

 97%|█████████▋| 187/192 [01:49<00:01,  2.53it/s]

 98%|█████████▊| 188/192 [01:49<00:01,  3.22it/s]

 99%|█████████▉| 190/192 [01:50<00:00,  4.52it/s]

 99%|█████████▉| 191/192 [01:50<00:00,  3.06it/s]

100%|██████████| 192/192 [01:51<00:00,  2.58it/s]
                                                     

                                                 

 32%|███▏      | 300/935 [2:32:23<4:03:11, 22.98s/it]

100%|██████████| 192/192 [01:51<00:00,  2.58it/s]

                                                 wandb: WARNING URL not available in offline run

 32%|███▏      | 301/935 [2:32:55<10:26:59, 59.34s/it]
 32%|███▏      | 302/935 [2:33:17<8:26:26, 48.00s/it] 
 32%|███▏      | 303/935 [2:34:09<8:38:40, 49.24s/it]
 33%|███▎      | 304/935 [2:34:43<7:51:01, 44.79s/it]
 33%|███▎      | 305/935 [2:35:07<6:42:01, 38.29s/it]
                                                     

 33%|███▎      | 305/935 [2:35:07<6:42:01, 38.29s/it]
 33%|███▎      | 306/935 [2:35:21<5:26:18, 31.13s/it]
 33%|███▎      | 307/935 [2:35:37<4:36:50, 26.45s/it]
 33%|███▎      | 308/935 [2:35:54<4:09:12, 23.85s/it]
 33%|███▎      | 309/935 [2:36:24<4:25:50, 25.48s/it]
 33%|███▎      | 310/935 [2:36:48<4:22:18, 25.18s/it]
                                                     

 33%|███▎      | 310/935 [2:36:48<4:22:18, 25.18s/it]
 33%|███▎      | 311/935 [2:37:36<5:31:52, 31.91s/it]
 33%|███▎      | 312/935 [2:38:12<5:46:05, 33.33s/it]
 33%|███▎      | 313/935 [2:39:02<6:37:41, 38.36s/it]
 34%|███▎      | 314/935 [2:39:40<6:33:25, 38.01s/it]
 34%|███▎      | 315/935 [2:40:33<7:20:43, 42.65s/it]
                                                     

 34%|███▎      | 315/935 [2:40:33<7:20:43, 42.65s/it]
 34%|███▍      | 316/935 [2:41:04<6:42:50, 39.05s/it]
 34%|███▍      | 317/935 [2:41:56<7:22:46, 42.99s/it]
 34%|███▍      | 318/935 [2:42:26<6:42:04, 39.10s/it]
 34%|███▍      | 319/935 [2:43:07<6:46:47, 39.62s/it]
 34%|███▍      | 320/935 [2:43:50<6:56:27, 40.63s/it]
                                                     

 34%|███▍      | 320/935 [2:43:50<6:56:27, 40.63s/it]
 34%|███▍      | 321/935 [2:44:29<6:50:19, 40.10s/it]
 34%|███▍      | 322/935 [2:45:12<7:00:47, 41.19s/it]
 35%|███▍      | 323/935 [2:45:53<6:57:27, 40.93s/it]
 35%|███▍      | 324/935 [2:46:31<6:48:15, 40.09s/it]
 35%|███▍      | 325/935 [2:47:20<7:15:20, 42.82s/it]
                                                     

 35%|███▍      | 325/935 [2:47:20<7:15:20, 42.82s/it]
 35%|███▍      | 326/935 [2:48:14<7:49:39, 46.27s/it]
 35%|███▍      | 327/935 [2:48:58<7:40:05, 45.40s/it]
 35%|███▌      | 328/935 [2:49:40<7:29:28, 44.43s/it]
 35%|███▌      | 329/935 [2:50:19<7:13:22, 42.91s/it]
 35%|███▌      | 330/935 [2:50:50<6:34:44, 39.15s/it]
                                                     

 35%|███▌      | 330/935 [2:50:50<6:34:44, 39.15s/it]
 35%|███▌      | 331/935 [2:51:18<6:01:43, 35.93s/it]
 36%|███▌      | 332/935 [2:52:00<6:17:50, 37.60s/it]
 36%|███▌      | 333/935 [2:52:27<5:46:21, 34.52s/it]
 36%|███▌      | 334/935 [2:52:57<5:31:06, 33.06s/it]
 36%|███▌      | 335/935 [2:53:28<5:26:29, 32.65s/it]
                                                     

 36%|███▌      | 335/935 [2:53:28<5:26:29, 32.65s/it]
 36%|███▌      | 336/935 [2:53:59<5:19:24, 31.99s/it]
 36%|███▌      | 337/935 [2:54:31<5:20:45, 32.18s/it]
 36%|███▌      | 338/935 [2:55:11<5:43:16, 34.50s/it]
 36%|███▋      | 339/935 [2:55:53<6:05:26, 36.79s/it]
 36%|███▋      | 340/935 [2:56:21<5:36:47, 33.96s/it]
                                                     

 36%|███▋      | 340/935 [2:56:21<5:36:47, 33.96s/it]
 36%|███▋      | 341/935 [2:56:57<5:44:38, 34.81s/it]
 37%|███▋      | 342/935 [2:57:16<4:55:45, 29.93s/it]
 37%|███▋      | 343/935 [2:58:08<6:00:44, 36.56s/it]
 37%|███▋      | 344/935 [2:58:42<5:53:03, 35.84s/it]
 37%|███▋      | 345/935 [2:59:24<6:09:08, 37.54s/it]
                                                     

 37%|███▋      | 345/935 [2:59:24<6:09:08, 37.54s/it]
 37%|███▋      | 346/935 [3:00:16<6:52:52, 42.06s/it]
 37%|███▋      | 347/935 [3:00:40<5:58:17, 36.56s/it]
 37%|███▋      | 348/935 [3:01:14<5:48:42, 35.64s/it]
 37%|███▋      | 349/935 [3:01:34<5:04:04, 31.13s/it]
 37%|███▋      | 350/935 [3:02:21<5:48:21, 35.73s/it]
                                                     

 37%|███▋      | 350/935 [3:02:21<5:48:21, 35.73s/it]{'eval_loss': 0.37665891647338867, 'eval_runtime': 111.5698, 'eval_samples_per_second': 3.442, 'eval_steps_per_second': 1.721, 'epoch': 0.32}
{'loss': 0.5158, 'grad_norm': 0.5770624876022339, 'learning_rate': 0.0001614359641231916, 'epoch': 0.33}
{'loss': 0.3828, 'grad_norm': 0.48272597789764404, 'learning_rate': 0.00016003070533931657, 'epoch': 0.33}
{'loss': 0.5803, 'grad_norm': 0.6361212730407715, 'learning_rate': 0.00015860666308030932, 'epoch': 0.34}
{'loss': 0.5262, 'grad_norm': 0.5693181157112122, 'learning_rate': 0.00015716428292584787, 'epoch': 0.34}
{'loss': 0.5053, 'grad_norm': 0.6022228598594666, 'learning_rate': 0.00015570401619349736, 'epoch': 0.35}
{'loss': 0.5833, 'grad_norm': 0.44118747115135193, 'learning_rate': 0.00015422631979749354, 'epoch': 0.35}
{'loss': 0.7714, 'grad_norm': 0.5451855659484863, 'learning_rate': 0.00015273165610577542, 'epoch': 0.36}
{'loss': 0.5547, 'grad_norm': 0.7061304450035095, 'learning_rate': 0.00015122049279531143, 'epoch': 0.36}
{'loss': 0.5838, 'grad_norm': 0.5038750171661377, 'learning_rate': 0.00014969330270576427, 'epoch': 0.37}
{'loss': 0.6429, 'grad_norm': 0.5525210499763489, 'learning_rate': 0.00014815056369154038, 'epoch': 0.37}


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

  1%|          | 2/192 [00:01<01:42,  1.86it/s]

  2%|▏         | 3/192 [00:02<03:24,  1.08s/it]

  2%|▏         | 4/192 [00:04<03:42,  1.19s/it]

  3%|▎         | 5/192 [00:05<04:03,  1.30s/it]

  3%|▎         | 6/192 [00:07<04:10,  1.35s/it]

  4%|▎         | 7/192 [00:08<04:32,  1.47s/it]

  4%|▍         | 8/192 [00:10<04:53,  1.60s/it]

  5%|▍         | 9/192 [00:12<05:14,  1.72s/it]

  5%|▌         | 10/192 [00:14<05:29,  1.81s/it]

  6%|▌         | 11/192 [00:15<04:50,  1.60s/it]

  6%|▋         | 12/192 [00:16<04:02,  1.35s/it]

  7%|▋         | 13/192 [00:18<04:12,  1.41s/it]

  7%|▋         | 14/192 [00:19<04:26,  1.49s/it]

  8%|▊         | 15/192 [00:21<03:59,  1.35s/it]

  8%|▊         | 16/192 [00:22<03:43,  1.27s/it]

  9%|▉         | 17/192 [00:24<04:19,  1.48s/it]

  9%|▉         | 18/192 [00:25<04:40,  1.61s/it]

 10%|▉         | 19/192 [00:27<04:10,  1.45s/it]

 10%|█         | 20/192 [00:27<03:42,  1.30s/it]

 11%|█         | 21/192 [00:29<03:56,  1.38s/it]

 11%|█▏        | 22/192 [00:30<03:54,  1.38s/it]

 12%|█▏        | 23/192 [00:31<03:19,  1.18s/it]

 12%|█▎        | 24/192 [00:31<02:26,  1.15it/s]

 13%|█▎        | 25/192 [00:32<01:52,  1.48it/s]

 14%|█▎        | 26/192 [00:32<01:33,  1.78it/s]

 14%|█▍        | 27/192 [00:32<01:17,  2.12it/s]

 15%|█▍        | 28/192 [00:32<01:05,  2.49it/s]

 15%|█▌        | 29/192 [00:33<00:59,  2.76it/s]

 16%|█▌        | 30/192 [00:33<00:55,  2.90it/s]

 16%|█▌        | 31/192 [00:33<00:55,  2.93it/s]

 17%|█▋        | 32/192 [00:33<00:50,  3.14it/s]

 17%|█▋        | 33/192 [00:35<01:38,  1.61it/s]

 18%|█▊        | 34/192 [00:37<02:48,  1.07s/it]

 18%|█▊        | 35/192 [00:39<03:31,  1.34s/it]

 19%|█▉        | 36/192 [00:40<03:12,  1.24s/it]

 19%|█▉        | 37/192 [00:40<02:26,  1.06it/s]

 20%|█▉        | 38/192 [00:40<01:52,  1.37it/s]

 20%|██        | 39/192 [00:41<01:53,  1.35it/s]

 21%|██        | 40/192 [00:43<02:24,  1.05it/s]

 21%|██▏       | 41/192 [00:44<03:05,  1.23s/it]

 22%|██▏       | 42/192 [00:46<03:31,  1.41s/it]

 22%|██▏       | 43/192 [00:48<03:49,  1.54s/it]

 23%|██▎       | 44/192 [00:49<03:22,  1.37s/it]

 23%|██▎       | 45/192 [00:49<02:34,  1.05s/it]

 24%|██▍       | 46/192 [00:51<02:35,  1.07s/it]

 24%|██▍       | 47/192 [00:52<03:07,  1.29s/it]

 25%|██▌       | 48/192 [00:54<03:11,  1.33s/it]

 26%|██▌       | 49/192 [00:55<02:46,  1.17s/it]

 26%|██▌       | 50/192 [00:55<02:06,  1.12it/s]

 27%|██▋       | 51/192 [00:56<02:15,  1.04it/s]

 27%|██▋       | 52/192 [00:57<02:17,  1.02it/s]

 28%|██▊       | 53/192 [00:57<01:50,  1.26it/s]

 28%|██▊       | 54/192 [00:59<02:09,  1.07it/s]

 29%|██▊       | 55/192 [01:00<02:46,  1.22s/it]

 29%|██▉       | 56/192 [01:02<02:58,  1.31s/it]

 30%|██▉       | 57/192 [01:04<03:08,  1.39s/it]

 30%|███       | 58/192 [01:04<02:44,  1.23s/it]

 31%|███       | 59/192 [01:06<02:42,  1.22s/it]

 31%|███▏      | 60/192 [01:08<03:18,  1.51s/it]

 32%|███▏      | 61/192 [01:09<03:11,  1.46s/it]

 32%|███▏      | 62/192 [01:09<02:23,  1.10s/it]

 33%|███▎      | 63/192 [01:10<01:48,  1.19it/s]

 33%|███▎      | 64/192 [01:10<01:39,  1.28it/s]

 34%|███▍      | 65/192 [01:11<01:35,  1.33it/s]

 34%|███▍      | 66/192 [01:11<01:13,  1.72it/s]

 35%|███▍      | 67/192 [01:11<01:02,  2.01it/s]

 35%|███▌      | 68/192 [01:12<00:52,  2.35it/s]

 36%|███▌      | 69/192 [01:13<01:29,  1.37it/s]

 36%|███▋      | 70/192 [01:14<01:46,  1.14it/s]

 37%|███▋      | 71/192 [01:15<01:46,  1.14it/s]

 38%|███▊      | 72/192 [01:17<02:24,  1.21s/it]

 38%|███▊      | 73/192 [01:20<03:06,  1.57s/it]

 39%|███▊      | 74/192 [01:21<02:49,  1.44s/it]

 39%|███▉      | 75/192 [01:21<02:09,  1.11s/it]

 40%|███▉      | 76/192 [01:22<02:10,  1.13s/it]

 40%|████      | 77/192 [01:24<02:35,  1.36s/it]

 41%|████      | 78/192 [01:26<02:44,  1.44s/it]

 41%|████      | 79/192 [01:27<02:27,  1.30s/it]

 42%|████▏     | 80/192 [01:28<02:15,  1.21s/it]

 42%|████▏     | 81/192 [01:30<02:35,  1.40s/it]

 43%|████▎     | 82/192 [01:31<02:46,  1.51s/it]

 43%|████▎     | 83/192 [01:33<02:55,  1.61s/it]

 44%|████▍     | 84/192 [01:34<02:34,  1.43s/it]

 44%|████▍     | 85/192 [01:35<02:23,  1.34s/it]

 45%|████▍     | 86/192 [01:36<02:10,  1.23s/it]

 45%|████▌     | 87/192 [01:37<01:41,  1.04it/s]

 46%|████▌     | 88/192 [01:37<01:16,  1.35it/s]

 46%|████▋     | 89/192 [01:37<00:59,  1.73it/s]

 47%|████▋     | 90/192 [01:37<00:50,  2.04it/s]

 47%|████▋     | 91/192 [01:38<01:04,  1.56it/s]

 48%|████▊     | 92/192 [01:40<01:29,  1.12it/s]

 48%|████▊     | 93/192 [01:41<01:49,  1.11s/it]

 49%|████▉     | 94/192 [01:42<01:42,  1.05s/it]

 49%|████▉     | 95/192 [01:44<01:43,  1.07s/it]

 50%|█████     | 96/192 [01:45<02:02,  1.28s/it]

 51%|█████     | 97/192 [01:46<01:54,  1.20s/it]

 51%|█████     | 98/192 [01:47<01:27,  1.07it/s]

 52%|█████▏    | 99/192 [01:48<01:34,  1.01s/it]

 52%|█████▏    | 100/192 [01:49<01:50,  1.20s/it]

 53%|█████▎    | 101/192 [01:51<02:11,  1.45s/it]

 53%|█████▎    | 102/192 [01:53<02:05,  1.39s/it]

 54%|█████▎    | 103/192 [01:54<01:57,  1.32s/it]

 54%|█████▍    | 104/192 [01:56<02:05,  1.42s/it]

 55%|█████▍    | 105/192 [01:57<01:53,  1.30s/it]

 55%|█████▌    | 106/192 [01:57<01:25,  1.00it/s]

 56%|█████▌    | 107/192 [01:58<01:29,  1.05s/it]

 56%|█████▋    | 108/192 [02:00<01:47,  1.28s/it]

 57%|█████▋    | 109/192 [02:02<02:11,  1.59s/it]

 57%|█████▋    | 110/192 [02:04<02:26,  1.79s/it]

 58%|█████▊    | 111/192 [02:06<02:11,  1.63s/it]

 58%|█████▊    | 112/192 [02:07<02:00,  1.51s/it]

 59%|█████▉    | 113/192 [02:08<01:51,  1.41s/it]

 59%|█████▉    | 114/192 [02:08<01:24,  1.08s/it]

 60%|█████▉    | 115/192 [02:10<01:24,  1.09s/it]

 60%|██████    | 116/192 [02:11<01:32,  1.21s/it]

 61%|██████    | 117/192 [02:12<01:21,  1.09s/it]

 61%|██████▏   | 118/192 [02:13<01:25,  1.15s/it]

 62%|██████▏   | 119/192 [02:15<01:37,  1.34s/it]

 62%|██████▎   | 120/192 [02:16<01:35,  1.32s/it]

 63%|██████▎   | 121/192 [02:17<01:23,  1.18s/it]

 64%|██████▎   | 122/192 [02:18<01:20,  1.15s/it]

 64%|██████▍   | 123/192 [02:19<01:17,  1.12s/it]

 65%|██████▍   | 124/192 [02:20<01:15,  1.12s/it]

 65%|██████▌   | 125/192 [02:22<01:31,  1.36s/it]

 66%|██████▌   | 126/192 [02:24<01:41,  1.54s/it]

 66%|██████▌   | 127/192 [02:25<01:32,  1.43s/it]

 67%|██████▋   | 128/192 [02:26<01:24,  1.32s/it]

 67%|██████▋   | 129/192 [02:28<01:34,  1.51s/it]

 68%|██████▊   | 130/192 [02:30<01:40,  1.62s/it]

 68%|██████▊   | 131/192 [02:32<01:40,  1.65s/it]

 69%|██████▉   | 132/192 [02:33<01:33,  1.56s/it]

 69%|██████▉   | 133/192 [02:34<01:20,  1.36s/it]

 70%|██████▉   | 134/192 [02:35<01:17,  1.33s/it]

 70%|███████   | 135/192 [02:37<01:13,  1.29s/it]

 71%|███████   | 136/192 [02:38<01:08,  1.23s/it]

 71%|███████▏  | 137/192 [02:40<01:19,  1.45s/it]

 72%|███████▏  | 138/192 [02:41<01:10,  1.30s/it]

 72%|███████▏  | 139/192 [02:41<00:51,  1.04it/s]

 73%|███████▎  | 140/192 [02:41<00:37,  1.37it/s]

 73%|███████▎  | 141/192 [02:42<00:42,  1.19it/s]

 74%|███████▍  | 142/192 [02:44<01:01,  1.22s/it]

 74%|███████▍  | 143/192 [02:46<01:01,  1.25s/it]

 75%|███████▌  | 144/192 [02:46<00:45,  1.06it/s]

 76%|███████▌  | 145/192 [02:47<00:46,  1.01it/s]

 76%|███████▌  | 146/192 [02:48<00:45,  1.00it/s]

 77%|███████▋  | 147/192 [02:49<00:45,  1.02s/it]

 77%|███████▋  | 148/192 [02:51<00:56,  1.29s/it]

 78%|███████▊  | 149/192 [02:52<00:55,  1.28s/it]

 78%|███████▊  | 150/192 [02:52<00:41,  1.01it/s]

 79%|███████▊  | 151/192 [02:53<00:32,  1.27it/s]

 79%|███████▉  | 152/192 [02:54<00:34,  1.16it/s]

 80%|███████▉  | 153/192 [02:55<00:35,  1.10it/s]

 80%|████████  | 154/192 [02:56<00:39,  1.04s/it]

 81%|████████  | 155/192 [02:57<00:41,  1.12s/it]

 81%|████████▏ | 156/192 [02:59<00:42,  1.19s/it]

 82%|████████▏ | 157/192 [03:00<00:42,  1.20s/it]

 82%|████████▏ | 158/192 [03:01<00:39,  1.16s/it]

 83%|████████▎ | 159/192 [03:02<00:36,  1.11s/it]

 83%|████████▎ | 160/192 [03:02<00:27,  1.17it/s]

 84%|████████▍ | 161/192 [03:03<00:20,  1.51it/s]

 84%|████████▍ | 162/192 [03:03<00:15,  1.92it/s]

 85%|████████▍ | 163/192 [03:03<00:13,  2.17it/s]

 85%|████████▌ | 164/192 [03:04<00:16,  1.66it/s]

 86%|████████▌ | 165/192 [03:06<00:25,  1.07it/s]

 86%|████████▋ | 166/192 [03:07<00:24,  1.08it/s]

 87%|████████▋ | 167/192 [03:08<00:24,  1.01it/s]

 88%|████████▊ | 168/192 [03:09<00:29,  1.22s/it]

 88%|████████▊ | 169/192 [03:11<00:26,  1.17s/it]

 89%|████████▊ | 170/192 [03:11<00:19,  1.11it/s]

 89%|████████▉ | 171/192 [03:11<00:14,  1.42it/s]

 90%|████████▉ | 172/192 [03:11<00:11,  1.79it/s]

 90%|█████████ | 173/192 [03:13<00:14,  1.33it/s]

 91%|█████████ | 174/192 [03:15<00:21,  1.18s/it]

 91%|█████████ | 175/192 [03:16<00:20,  1.22s/it]

 92%|█████████▏| 176/192 [03:16<00:14,  1.08it/s]

 92%|█████████▏| 177/192 [03:16<00:10,  1.38it/s]

 93%|█████████▎| 178/192 [03:17<00:11,  1.27it/s]

 93%|█████████▎| 179/192 [03:19<00:12,  1.04it/s]

 94%|█████████▍| 180/192 [03:19<00:10,  1.16it/s]

 94%|█████████▍| 181/192 [03:20<00:09,  1.12it/s]

 95%|█████████▍| 182/192 [03:22<00:11,  1.16s/it]

 95%|█████████▌| 183/192 [03:23<00:10,  1.13s/it]

 96%|█████████▌| 184/192 [03:23<00:06,  1.15it/s]

 96%|█████████▋| 185/192 [03:24<00:04,  1.47it/s]

 97%|█████████▋| 186/192 [03:25<00:04,  1.36it/s]

 97%|█████████▋| 187/192 [03:25<00:03,  1.33it/s]

 98%|█████████▊| 188/192 [03:26<00:02,  1.71it/s]

 98%|█████████▊| 189/192 [03:26<00:01,  2.13it/s]

 99%|█████████▉| 190/192 [03:26<00:00,  2.40it/s]

 99%|█████████▉| 191/192 [03:27<00:00,  1.59it/s]

100%|██████████| 192/192 [03:28<00:00,  1.33it/s]
                                                     

                                                 

 37%|███▋      | 350/935 [3:05:50<5:48:21, 35.73s/it]

100%|██████████| 192/192 [03:28<00:00,  1.33it/s]

                                                 
 38%|███▊      | 351/935 [3:06:16<15:31:59, 95.75s/it]
 38%|███▊      | 352/935 [3:06:42<12:06:41, 74.79s/it]
 38%|███▊      | 353/935 [3:07:13<9:57:54, 61.64s/it] 
 38%|███▊      | 354/935 [3:07:50<8:44:22, 54.15s/it]
 38%|███▊      | 355/935 [3:08:37<8:21:56, 51.93s/it]
                                                     

 38%|███▊      | 355/935 [3:08:37<8:21:56, 51.93s/it]
 38%|███▊      | 356/935 [3:09:20<7:55:31, 49.28s/it]
 38%|███▊      | 357/935 [3:09:48<6:54:34, 43.04s/it]
 38%|███▊      | 358/935 [3:10:24<6:32:40, 40.83s/it]
 38%|███▊      | 359/935 [3:10:57<6:10:42, 38.61s/it]
 39%|███▊      | 360/935 [3:11:33<6:00:50, 37.65s/it]
                                                     

 39%|███▊      | 360/935 [3:11:33<6:00:50, 37.65s/it]
 39%|███▊      | 361/935 [3:12:20<6:27:15, 40.48s/it]
 39%|███▊      | 362/935 [3:13:04<6:37:48, 41.66s/it]
 39%|███▉      | 363/935 [3:13:40<6:18:49, 39.74s/it]
 39%|███▉      | 364/935 [3:13:58<5:16:08, 33.22s/it]
 39%|███▉      | 365/935 [3:14:31<5:15:12, 33.18s/it]
                                                     

 39%|███▉      | 365/935 [3:14:31<5:15:12, 33.18s/it]
 39%|███▉      | 366/935 [3:14:58<4:56:47, 31.30s/it]
 39%|███▉      | 367/935 [3:15:33<5:07:11, 32.45s/it]
 39%|███▉      | 368/935 [3:16:12<5:24:55, 34.38s/it]
 39%|███▉      | 369/935 [3:16:59<6:00:40, 38.23s/it]
 40%|███▉      | 370/935 [3:17:20<5:11:04, 33.04s/it]
                                                     

 40%|███▉      | 370/935 [3:17:20<5:11:04, 33.04s/it]
 40%|███▉      | 371/935 [3:17:36<4:21:57, 27.87s/it]
 40%|███▉      | 372/935 [3:17:58<4:06:01, 26.22s/it]
 40%|███▉      | 373/935 [3:18:12<3:32:40, 22.71s/it]
 40%|████      | 374/935 [3:18:39<3:42:26, 23.79s/it]
 40%|████      | 375/935 [3:19:13<4:12:08, 27.02s/it]
                                                     

 40%|████      | 375/935 [3:19:13<4:12:08, 27.02s/it]
 40%|████      | 376/935 [3:19:30<3:43:42, 24.01s/it]
 40%|████      | 377/935 [3:19:49<3:27:25, 22.30s/it]
 40%|████      | 378/935 [3:20:10<3:23:48, 21.95s/it]
 41%|████      | 379/935 [3:20:31<3:21:18, 21.72s/it]
 41%|████      | 380/935 [3:20:44<2:56:56, 19.13s/it]
                                                     

 41%|████      | 380/935 [3:20:44<2:56:56, 19.13s/it]
 41%|████      | 381/935 [3:21:03<2:55:14, 18.98s/it]
 41%|████      | 382/935 [3:21:11<2:25:40, 15.81s/it]
 41%|████      | 383/935 [3:21:30<2:33:45, 16.71s/it]Terminated