{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 6.073261260986328,
      "learning_rate": 0.0,
      "loss": 3.3843,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 6.262120723724365,
      "learning_rate": 2e-05,
      "loss": 3.3645,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 6.109327793121338,
      "learning_rate": 4e-05,
      "loss": 3.3443,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 3.674955368041992,
      "learning_rate": 6e-05,
      "loss": 3.0356,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 2.2990496158599854,
      "learning_rate": 8e-05,
      "loss": 2.9234,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 1.569203495979309,
      "learning_rate": 0.0001,
      "loss": 2.8619,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.3937740325927734,
      "learning_rate": 9.705882352941177e-05,
      "loss": 2.661,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 1.4992576837539673,
      "learning_rate": 9.411764705882353e-05,
      "loss": 2.6468,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.4312055110931396,
      "learning_rate": 9.11764705882353e-05,
      "loss": 2.4891,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.2904211282730103,
      "learning_rate": 8.823529411764706e-05,
      "loss": 2.3533,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.2736907005310059,
      "learning_rate": 8.529411764705883e-05,
      "loss": 2.3755,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.1113113164901733,
      "learning_rate": 8.23529411764706e-05,
      "loss": 2.1892,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1955909729003906,
      "learning_rate": 7.941176470588235e-05,
      "loss": 2.1353,
      "step": 13
    },
    {
      "epoch": 1.0792079207920793,
      "grad_norm": 0.9447349309921265,
      "learning_rate": 7.647058823529411e-05,
      "loss": 2.0216,
      "step": 14
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 0.9992384314537048,
      "learning_rate": 7.352941176470589e-05,
      "loss": 1.9715,
      "step": 15
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 0.990057110786438,
      "learning_rate": 7.058823529411765e-05,
      "loss": 2.005,
      "step": 16
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 1.0047601461410522,
      "learning_rate": 6.764705882352942e-05,
      "loss": 1.9032,
      "step": 17
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 0.9631515741348267,
      "learning_rate": 6.470588235294118e-05,
      "loss": 1.8743,
      "step": 18
    },
    {
      "epoch": 1.4752475247524752,
      "grad_norm": 1.0364757776260376,
      "learning_rate": 6.176470588235295e-05,
      "loss": 1.9452,
      "step": 19
    },
    {
      "epoch": 1.5544554455445545,
      "grad_norm": 0.9972262978553772,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.9141,
      "step": 20
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 1.05035400390625,
      "learning_rate": 5.588235294117647e-05,
      "loss": 1.8159,
      "step": 21
    },
    {
      "epoch": 1.7128712871287128,
      "grad_norm": 0.9364991188049316,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.8371,
      "step": 22
    },
    {
      "epoch": 1.7920792079207921,
      "grad_norm": 1.0176726579666138,
      "learning_rate": 5e-05,
      "loss": 1.8923,
      "step": 23
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 1.1326942443847656,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.8377,
      "step": 24
    },
    {
      "epoch": 1.9504950495049505,
      "grad_norm": 0.9697809815406799,
      "learning_rate": 4.411764705882353e-05,
      "loss": 1.8397,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3207035064697266,
      "learning_rate": 4.11764705882353e-05,
      "loss": 1.9675,
      "step": 26
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 0.9500892758369446,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 1.6868,
      "step": 27
    },
    {
      "epoch": 2.1584158415841586,
      "grad_norm": 0.9513592720031738,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.6999,
      "step": 28
    },
    {
      "epoch": 2.237623762376238,
      "grad_norm": 1.0524265766143799,
      "learning_rate": 3.235294117647059e-05,
      "loss": 1.6809,
      "step": 29
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 0.9800081849098206,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.7577,
      "step": 30
    },
    {
      "epoch": 2.396039603960396,
      "grad_norm": 0.9853926301002502,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.7057,
      "step": 31
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 0.9770392775535583,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.637,
      "step": 32
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 0.9922024607658386,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.6348,
      "step": 33
    },
    {
      "epoch": 2.633663366336634,
      "grad_norm": 0.9778696298599243,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.6591,
      "step": 34
    },
    {
      "epoch": 2.7128712871287126,
      "grad_norm": 1.1014469861984253,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.7367,
      "step": 35
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 0.9784729480743408,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.6265,
      "step": 36
    },
    {
      "epoch": 2.871287128712871,
      "grad_norm": 0.99269038438797,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.5749,
      "step": 37
    },
    {
      "epoch": 2.9504950495049505,
      "grad_norm": 0.9722699522972107,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.6123,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.298532485961914,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.7333,
      "step": 39
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4253760744010752.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}