{
  "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": 8.278907775878906,
      "learning_rate": 0.0,
      "loss": 3.4953,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 8.597126007080078,
      "learning_rate": 2e-05,
      "loss": 3.4594,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 7.616092681884766,
      "learning_rate": 4e-05,
      "loss": 3.3833,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 4.109858989715576,
      "learning_rate": 6e-05,
      "loss": 2.9817,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 2.2449841499328613,
      "learning_rate": 8e-05,
      "loss": 2.8494,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 2.243119955062866,
      "learning_rate": 0.0001,
      "loss": 2.7936,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.263944387435913,
      "learning_rate": 9.705882352941177e-05,
      "loss": 2.5195,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 2.257138729095459,
      "learning_rate": 9.411764705882353e-05,
      "loss": 2.4989,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.4803467988967896,
      "learning_rate": 9.11764705882353e-05,
      "loss": 2.4051,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.342012643814087,
      "learning_rate": 8.823529411764706e-05,
      "loss": 2.321,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.3045903444290161,
      "learning_rate": 8.529411764705883e-05,
      "loss": 2.3265,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.1042195558547974,
      "learning_rate": 8.23529411764706e-05,
      "loss": 2.1449,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1532036066055298,
      "learning_rate": 7.941176470588235e-05,
      "loss": 2.1405,
      "step": 13
    },
    {
      "epoch": 1.0792079207920793,
      "grad_norm": 0.9440450668334961,
      "learning_rate": 7.647058823529411e-05,
      "loss": 2.0103,
      "step": 14
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 0.9817442893981934,
      "learning_rate": 7.352941176470589e-05,
      "loss": 1.9725,
      "step": 15
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 1.0224950313568115,
      "learning_rate": 7.058823529411765e-05,
      "loss": 1.9913,
      "step": 16
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 1.0060229301452637,
      "learning_rate": 6.764705882352942e-05,
      "loss": 1.8842,
      "step": 17
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 1.0625827312469482,
      "learning_rate": 6.470588235294118e-05,
      "loss": 1.8876,
      "step": 18
    },
    {
      "epoch": 1.4752475247524752,
      "grad_norm": 1.0620535612106323,
      "learning_rate": 6.176470588235295e-05,
      "loss": 1.9572,
      "step": 19
    },
    {
      "epoch": 1.5544554455445545,
      "grad_norm": 1.0438231229782104,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.904,
      "step": 20
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 1.0874717235565186,
      "learning_rate": 5.588235294117647e-05,
      "loss": 1.8032,
      "step": 21
    },
    {
      "epoch": 1.7128712871287128,
      "grad_norm": 1.0076180696487427,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.8666,
      "step": 22
    },
    {
      "epoch": 1.7920792079207921,
      "grad_norm": 1.080075979232788,
      "learning_rate": 5e-05,
      "loss": 1.9253,
      "step": 23
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 1.2296780347824097,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.8225,
      "step": 24
    },
    {
      "epoch": 1.9504950495049505,
      "grad_norm": 0.9789160490036011,
      "learning_rate": 4.411764705882353e-05,
      "loss": 1.8196,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.5162479877471924,
      "learning_rate": 4.11764705882353e-05,
      "loss": 2.0176,
      "step": 26
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 1.0328166484832764,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 1.7033,
      "step": 27
    },
    {
      "epoch": 2.1584158415841586,
      "grad_norm": 0.9679973125457764,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.7035,
      "step": 28
    },
    {
      "epoch": 2.237623762376238,
      "grad_norm": 1.0854283571243286,
      "learning_rate": 3.235294117647059e-05,
      "loss": 1.6717,
      "step": 29
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 1.0717378854751587,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.7806,
      "step": 30
    },
    {
      "epoch": 2.396039603960396,
      "grad_norm": 0.9930298924446106,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.7284,
      "step": 31
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 1.06831955909729,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.6425,
      "step": 32
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 1.1817028522491455,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.668,
      "step": 33
    },
    {
      "epoch": 2.633663366336634,
      "grad_norm": 0.997107207775116,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.6489,
      "step": 34
    },
    {
      "epoch": 2.7128712871287126,
      "grad_norm": 1.1331177949905396,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.7461,
      "step": 35
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 1.0102354288101196,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.6428,
      "step": 36
    },
    {
      "epoch": 2.871287128712871,
      "grad_norm": 1.023819923400879,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.5943,
      "step": 37
    },
    {
      "epoch": 2.9504950495049505,
      "grad_norm": 0.9876952171325684,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.6124,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.383870005607605,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.7666,
      "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
}