{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 2.5627,
      "step": 1
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.5872,
      "step": 2
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019986740898848306,
      "loss": 0.2394,
      "step": 3
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001994699875614589,
      "loss": 0.3004,
      "step": 4
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019880878960910772,
      "loss": 0.2071,
      "step": 5
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001978855685095358,
      "loss": 0.2135,
      "step": 6
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019670277247913205,
      "loss": 0.1922,
      "step": 7
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019526353808033825,
      "loss": 0.211,
      "step": 8
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019357168190404936,
      "loss": 0.1895,
      "step": 9
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001916316904487005,
      "loss": 0.1772,
      "step": 10
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018944870822287956,
      "loss": 0.1635,
      "step": 11
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018702852410301554,
      "loss": 0.1521,
      "step": 12
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018437755598231856,
      "loss": 0.2165,
      "step": 13
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018150283375168114,
      "loss": 0.1462,
      "step": 14
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017841198065767107,
      "loss": 0.1535,
      "step": 15
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017511319308705198,
      "loss": 0.1654,
      "step": 16
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017161521883143934,
      "loss": 0.1542,
      "step": 17
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016792733388972932,
      "loss": 0.1482,
      "step": 18
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016405931786981755,
      "loss": 0.1389,
      "step": 19
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00016002142805483685,
      "loss": 0.1234,
      "step": 20
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015582437220268647,
      "loss": 0.1184,
      "step": 21
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001514792801509831,
      "loss": 0.11,
      "step": 22
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.000146997674302732,
      "loss": 0.1085,
      "step": 23
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001423914390709861,
      "loss": 0.108,
      "step": 24
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013767278936351854,
      "loss": 0.1044,
      "step": 25
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001328542381910835,
      "loss": 0.0888,
      "step": 26
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012794856348516095,
      "loss": 0.1162,
      "step": 27
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001229687742131796,
      "loss": 0.0989,
      "step": 28
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011792807588107357,
      "loss": 0.0849,
      "step": 29
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00011283983551465511,
      "loss": 0.1005,
      "step": 30
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010771754621266466,
      "loss": 0.0979,
      "step": 31
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00010257479136549889,
      "loss": 0.0917,
      "step": 32
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.742520863450115e-05,
      "loss": 0.0946,
      "step": 33
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.228245378733537e-05,
      "loss": 0.0871,
      "step": 34
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.71601644853449e-05,
      "loss": 0.0733,
      "step": 35
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.207192411892646e-05,
      "loss": 0.0797,
      "step": 36
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.703122578682046e-05,
      "loss": 0.0914,
      "step": 37
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.205143651483906e-05,
      "loss": 0.0562,
      "step": 38
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.714576180891654e-05,
      "loss": 0.0735,
      "step": 39
    },
    {
      "epoch": 1.9,
      "learning_rate": 6.232721063648148e-05,
      "loss": 0.048,
      "step": 40
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.7608560929013946e-05,
      "loss": 0.0603,
      "step": 41
    },
    {
      "epoch": 2.0,
      "learning_rate": 5.300232569726804e-05,
      "loss": 0.0856,
      "step": 42
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.852071984901696e-05,
      "loss": 0.0655,
      "step": 43
    },
    {
      "epoch": 2.1,
      "learning_rate": 4.417562779731355e-05,
      "loss": 0.0494,
      "step": 44
    },
    {
      "epoch": 2.14,
      "learning_rate": 3.997857194516319e-05,
      "loss": 0.0334,
      "step": 45
    },
    {
      "epoch": 2.19,
      "learning_rate": 3.594068213018249e-05,
      "loss": 0.0378,
      "step": 46
    },
    {
      "epoch": 2.24,
      "learning_rate": 3.207266611027069e-05,
      "loss": 0.0425,
      "step": 47
    },
    {
      "epoch": 2.29,
      "learning_rate": 2.8384781168560693e-05,
      "loss": 0.0272,
      "step": 48
    },
    {
      "epoch": 2.33,
      "learning_rate": 2.4886806912948035e-05,
      "loss": 0.0511,
      "step": 49
    },
    {
      "epoch": 2.38,
      "learning_rate": 2.1588019342328968e-05,
      "loss": 0.0393,
      "step": 50
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.8497166248318876e-05,
      "loss": 0.0265,
      "step": 51
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.562244401768144e-05,
      "loss": 0.0442,
      "step": 52
    },
    {
      "epoch": 2.52,
      "learning_rate": 1.2971475896984475e-05,
      "loss": 0.0196,
      "step": 53
    },
    {
      "epoch": 2.57,
      "learning_rate": 1.0551291777120464e-05,
      "loss": 0.0296,
      "step": 54
    },
    {
      "epoch": 2.62,
      "learning_rate": 8.368309551299536e-06,
      "loss": 0.0482,
      "step": 55
    },
    {
      "epoch": 2.67,
      "learning_rate": 6.428318095950647e-06,
      "loss": 0.0442,
      "step": 56
    },
    {
      "epoch": 2.71,
      "learning_rate": 4.7364619196617495e-06,
      "loss": 0.0442,
      "step": 57
    },
    {
      "epoch": 2.76,
      "learning_rate": 3.2972275208679625e-06,
      "loss": 0.027,
      "step": 58
    },
    {
      "epoch": 2.81,
      "learning_rate": 2.1144314904642195e-06,
      "loss": 0.053,
      "step": 59
    },
    {
      "epoch": 2.86,
      "learning_rate": 1.1912103908922945e-06,
      "loss": 0.037,
      "step": 60
    },
    {
      "epoch": 2.9,
      "learning_rate": 5.300124385410943e-07,
      "loss": 0.0439,
      "step": 61
    },
    {
      "epoch": 2.95,
      "learning_rate": 1.3259101151694708e-07,
      "loss": 0.0234,
      "step": 62
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.0241,
      "step": 63
    },
    {
      "epoch": 3.0,
      "step": 63,
      "total_flos": 3251608289280.0,
      "train_loss": 0.1782660081923481,
      "train_runtime": 283.1757,
      "train_samples_per_second": 27.947,
      "train_steps_per_second": 0.222
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50000,
  "total_flos": 3251608289280.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}