{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06140620202640467,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002456248081056187,
      "grad_norm": 1.075522780418396,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.3319,
      "step": 1
    },
    {
      "epoch": 0.002456248081056187,
      "eval_loss": 0.40377190709114075,
      "eval_runtime": 96.687,
      "eval_samples_per_second": 3.548,
      "eval_steps_per_second": 1.779,
      "step": 1
    },
    {
      "epoch": 0.004912496162112374,
      "grad_norm": 0.9468379020690918,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.2987,
      "step": 2
    },
    {
      "epoch": 0.00736874424316856,
      "grad_norm": 1.2837846279144287,
      "learning_rate": 0.0001,
      "loss": 0.4162,
      "step": 3
    },
    {
      "epoch": 0.009824992324224747,
      "grad_norm": 0.7427715063095093,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.3942,
      "step": 4
    },
    {
      "epoch": 0.012281240405280933,
      "grad_norm": 0.455293208360672,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.2755,
      "step": 5
    },
    {
      "epoch": 0.01473748848633712,
      "grad_norm": 0.6595093607902527,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.2189,
      "step": 6
    },
    {
      "epoch": 0.017193736567393307,
      "grad_norm": 0.5849353075027466,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.2198,
      "step": 7
    },
    {
      "epoch": 0.019649984648449494,
      "grad_norm": 0.4098145365715027,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.1351,
      "step": 8
    },
    {
      "epoch": 0.02210623272950568,
      "grad_norm": 0.5752076506614685,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.2128,
      "step": 9
    },
    {
      "epoch": 0.024562480810561865,
      "grad_norm": 0.3932249844074249,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.1435,
      "step": 10
    },
    {
      "epoch": 0.027018728891618052,
      "grad_norm": 0.333332896232605,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1337,
      "step": 11
    },
    {
      "epoch": 0.02947497697267424,
      "grad_norm": 0.25759759545326233,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1202,
      "step": 12
    },
    {
      "epoch": 0.03193122505373042,
      "grad_norm": 0.24304305016994476,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.1099,
      "step": 13
    },
    {
      "epoch": 0.034387473134786614,
      "grad_norm": 0.18120177090168,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.0935,
      "step": 14
    },
    {
      "epoch": 0.0368437212158428,
      "grad_norm": 0.18426595628261566,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0999,
      "step": 15
    },
    {
      "epoch": 0.03929996929689899,
      "grad_norm": 0.41276195645332336,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.1368,
      "step": 16
    },
    {
      "epoch": 0.04175621737795517,
      "grad_norm": 0.22144843637943268,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.1015,
      "step": 17
    },
    {
      "epoch": 0.04421246545901136,
      "grad_norm": 0.27295783162117004,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.1443,
      "step": 18
    },
    {
      "epoch": 0.04666871354006755,
      "grad_norm": 0.15916624665260315,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0799,
      "step": 19
    },
    {
      "epoch": 0.04912496162112373,
      "grad_norm": 0.20824064314365387,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.1086,
      "step": 20
    },
    {
      "epoch": 0.05158120970217992,
      "grad_norm": 0.17067670822143555,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.089,
      "step": 21
    },
    {
      "epoch": 0.054037457783236105,
      "grad_norm": 0.2052849531173706,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0873,
      "step": 22
    },
    {
      "epoch": 0.056493705864292296,
      "grad_norm": 0.14692534506320953,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0732,
      "step": 23
    },
    {
      "epoch": 0.05894995394534848,
      "grad_norm": 0.17746412754058838,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0665,
      "step": 24
    },
    {
      "epoch": 0.06140620202640467,
      "grad_norm": 0.2051028162240982,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.118,
      "step": 25
    },
    {
      "epoch": 0.06140620202640467,
      "eval_loss": 0.10138817876577377,
      "eval_runtime": 97.3932,
      "eval_samples_per_second": 3.522,
      "eval_steps_per_second": 1.766,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 3.969096967048397e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}