{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1953125,
  "eval_steps": 9,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00390625,
      "grad_norm": 0.9358924627304077,
      "learning_rate": 1e-05,
      "loss": 0.4079,
      "step": 1
    },
    {
      "epoch": 0.00390625,
      "eval_loss": 0.4379751980304718,
      "eval_runtime": 37.4931,
      "eval_samples_per_second": 5.761,
      "eval_steps_per_second": 0.72,
      "step": 1
    },
    {
      "epoch": 0.0078125,
      "grad_norm": 0.9645170569419861,
      "learning_rate": 2e-05,
      "loss": 0.3906,
      "step": 2
    },
    {
      "epoch": 0.01171875,
      "grad_norm": 1.000429630279541,
      "learning_rate": 3e-05,
      "loss": 0.4281,
      "step": 3
    },
    {
      "epoch": 0.015625,
      "grad_norm": 0.6437779664993286,
      "learning_rate": 4e-05,
      "loss": 0.3714,
      "step": 4
    },
    {
      "epoch": 0.01953125,
      "grad_norm": 0.8947291374206543,
      "learning_rate": 5e-05,
      "loss": 0.3801,
      "step": 5
    },
    {
      "epoch": 0.0234375,
      "grad_norm": 0.7578244805335999,
      "learning_rate": 6e-05,
      "loss": 0.3648,
      "step": 6
    },
    {
      "epoch": 0.02734375,
      "grad_norm": 0.6235212087631226,
      "learning_rate": 7e-05,
      "loss": 0.3909,
      "step": 7
    },
    {
      "epoch": 0.03125,
      "grad_norm": 0.4007953405380249,
      "learning_rate": 8e-05,
      "loss": 0.3141,
      "step": 8
    },
    {
      "epoch": 0.03515625,
      "grad_norm": 0.3965928554534912,
      "learning_rate": 9e-05,
      "loss": 0.2924,
      "step": 9
    },
    {
      "epoch": 0.03515625,
      "eval_loss": 0.2510845959186554,
      "eval_runtime": 37.7104,
      "eval_samples_per_second": 5.728,
      "eval_steps_per_second": 0.716,
      "step": 9
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 0.4188036322593689,
      "learning_rate": 0.0001,
      "loss": 0.2828,
      "step": 10
    },
    {
      "epoch": 0.04296875,
      "grad_norm": 0.3323066830635071,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.2415,
      "step": 11
    },
    {
      "epoch": 0.046875,
      "grad_norm": 0.2657626271247864,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.1928,
      "step": 12
    },
    {
      "epoch": 0.05078125,
      "grad_norm": 0.2819468080997467,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.1859,
      "step": 13
    },
    {
      "epoch": 0.0546875,
      "grad_norm": 0.21283726394176483,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.1895,
      "step": 14
    },
    {
      "epoch": 0.05859375,
      "grad_norm": 0.22380894422531128,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.1606,
      "step": 15
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.26086336374282837,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1618,
      "step": 16
    },
    {
      "epoch": 0.06640625,
      "grad_norm": 0.17846892774105072,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.1524,
      "step": 17
    },
    {
      "epoch": 0.0703125,
      "grad_norm": 0.16768787801265717,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1242,
      "step": 18
    },
    {
      "epoch": 0.0703125,
      "eval_loss": 0.14291226863861084,
      "eval_runtime": 37.7214,
      "eval_samples_per_second": 5.726,
      "eval_steps_per_second": 0.716,
      "step": 18
    },
    {
      "epoch": 0.07421875,
      "grad_norm": 0.16563105583190918,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1247,
      "step": 19
    },
    {
      "epoch": 0.078125,
      "grad_norm": 0.17445707321166992,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1217,
      "step": 20
    },
    {
      "epoch": 0.08203125,
      "grad_norm": 0.16826312243938446,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.118,
      "step": 21
    },
    {
      "epoch": 0.0859375,
      "grad_norm": 0.14247825741767883,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1009,
      "step": 22
    },
    {
      "epoch": 0.08984375,
      "grad_norm": 0.20849590003490448,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1035,
      "step": 23
    },
    {
      "epoch": 0.09375,
      "grad_norm": 0.17949005961418152,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.1156,
      "step": 24
    },
    {
      "epoch": 0.09765625,
      "grad_norm": 0.19471654295921326,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1187,
      "step": 25
    },
    {
      "epoch": 0.1015625,
      "grad_norm": 0.18970464169979095,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1302,
      "step": 26
    },
    {
      "epoch": 0.10546875,
      "grad_norm": 0.13743029534816742,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.103,
      "step": 27
    },
    {
      "epoch": 0.10546875,
      "eval_loss": 0.11523790657520294,
      "eval_runtime": 37.6775,
      "eval_samples_per_second": 5.733,
      "eval_steps_per_second": 0.717,
      "step": 27
    },
    {
      "epoch": 0.109375,
      "grad_norm": 0.16887696087360382,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0911,
      "step": 28
    },
    {
      "epoch": 0.11328125,
      "grad_norm": 0.1817857027053833,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.1184,
      "step": 29
    },
    {
      "epoch": 0.1171875,
      "grad_norm": 0.39407843351364136,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1714,
      "step": 30
    },
    {
      "epoch": 0.12109375,
      "grad_norm": 0.14840836822986603,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0822,
      "step": 31
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.12886931002140045,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0924,
      "step": 32
    },
    {
      "epoch": 0.12890625,
      "grad_norm": 0.131106898188591,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1126,
      "step": 33
    },
    {
      "epoch": 0.1328125,
      "grad_norm": 0.20917432010173798,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1214,
      "step": 34
    },
    {
      "epoch": 0.13671875,
      "grad_norm": 0.13371144235134125,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1085,
      "step": 35
    },
    {
      "epoch": 0.140625,
      "grad_norm": 0.16854634881019592,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1154,
      "step": 36
    },
    {
      "epoch": 0.140625,
      "eval_loss": 0.10245885699987411,
      "eval_runtime": 37.6755,
      "eval_samples_per_second": 5.733,
      "eval_steps_per_second": 0.717,
      "step": 36
    },
    {
      "epoch": 0.14453125,
      "grad_norm": 0.12487249076366425,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.109,
      "step": 37
    },
    {
      "epoch": 0.1484375,
      "grad_norm": 0.1517653465270996,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0798,
      "step": 38
    },
    {
      "epoch": 0.15234375,
      "grad_norm": 0.16995568573474884,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1015,
      "step": 39
    },
    {
      "epoch": 0.15625,
      "grad_norm": 0.09856864809989929,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1026,
      "step": 40
    },
    {
      "epoch": 0.16015625,
      "grad_norm": 0.11969555914402008,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.099,
      "step": 41
    },
    {
      "epoch": 0.1640625,
      "grad_norm": 0.1942385733127594,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.069,
      "step": 42
    },
    {
      "epoch": 0.16796875,
      "grad_norm": 0.12041034549474716,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.1015,
      "step": 43
    },
    {
      "epoch": 0.171875,
      "grad_norm": 0.1598462611436844,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0893,
      "step": 44
    },
    {
      "epoch": 0.17578125,
      "grad_norm": 0.17382952570915222,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1179,
      "step": 45
    },
    {
      "epoch": 0.17578125,
      "eval_loss": 0.09511082619428635,
      "eval_runtime": 37.6196,
      "eval_samples_per_second": 5.742,
      "eval_steps_per_second": 0.718,
      "step": 45
    },
    {
      "epoch": 0.1796875,
      "grad_norm": 0.1521601378917694,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0992,
      "step": 46
    },
    {
      "epoch": 0.18359375,
      "grad_norm": 0.18973639607429504,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0867,
      "step": 47
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.1595524698495865,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.1163,
      "step": 48
    },
    {
      "epoch": 0.19140625,
      "grad_norm": 0.2963557243347168,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0805,
      "step": 49
    },
    {
      "epoch": 0.1953125,
      "grad_norm": 0.09695882350206375,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0806,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.487081170141184e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}