{
  "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": 1.8937808275222778,
      "learning_rate": 0.0,
      "loss": 2.9855,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 1.9232189655303955,
      "learning_rate": 2e-05,
      "loss": 2.9717,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 1.8999687433242798,
      "learning_rate": 4e-05,
      "loss": 2.9694,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 1.7276859283447266,
      "learning_rate": 6e-05,
      "loss": 2.9272,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 1.9599796533584595,
      "learning_rate": 8e-05,
      "loss": 2.8772,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 1.7746745347976685,
      "learning_rate": 0.0001,
      "loss": 2.8094,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.645308494567871,
      "learning_rate": 9.705882352941177e-05,
      "loss": 2.6156,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 1.481805443763733,
      "learning_rate": 9.411764705882353e-05,
      "loss": 2.6603,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.3814828395843506,
      "learning_rate": 9.11764705882353e-05,
      "loss": 2.5032,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.234440565109253,
      "learning_rate": 8.823529411764706e-05,
      "loss": 2.4455,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.8254350423812866,
      "learning_rate": 8.529411764705883e-05,
      "loss": 2.5193,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.4534820318222046,
      "learning_rate": 8.23529411764706e-05,
      "loss": 2.3786,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.419603943824768,
      "learning_rate": 7.941176470588235e-05,
      "loss": 2.3535,
      "step": 13
    },
    {
      "epoch": 1.0792079207920793,
      "grad_norm": 1.2410346269607544,
      "learning_rate": 7.647058823529411e-05,
      "loss": 2.246,
      "step": 14
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 1.1370760202407837,
      "learning_rate": 7.352941176470589e-05,
      "loss": 2.2056,
      "step": 15
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 1.1719858646392822,
      "learning_rate": 7.058823529411765e-05,
      "loss": 2.2816,
      "step": 16
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 1.1416893005371094,
      "learning_rate": 6.764705882352942e-05,
      "loss": 2.1747,
      "step": 17
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 1.210598111152649,
      "learning_rate": 6.470588235294118e-05,
      "loss": 2.158,
      "step": 18
    },
    {
      "epoch": 1.4752475247524752,
      "grad_norm": 1.0852152109146118,
      "learning_rate": 6.176470588235295e-05,
      "loss": 2.2083,
      "step": 19
    },
    {
      "epoch": 1.5544554455445545,
      "grad_norm": 1.139453411102295,
      "learning_rate": 5.882352941176471e-05,
      "loss": 2.2147,
      "step": 20
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 1.1596145629882812,
      "learning_rate": 5.588235294117647e-05,
      "loss": 2.1261,
      "step": 21
    },
    {
      "epoch": 1.7128712871287128,
      "grad_norm": 1.148011326789856,
      "learning_rate": 5.294117647058824e-05,
      "loss": 2.1938,
      "step": 22
    },
    {
      "epoch": 1.7920792079207921,
      "grad_norm": 1.181815505027771,
      "learning_rate": 5e-05,
      "loss": 2.1944,
      "step": 23
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 1.2467199563980103,
      "learning_rate": 4.705882352941177e-05,
      "loss": 2.1312,
      "step": 24
    },
    {
      "epoch": 1.9504950495049505,
      "grad_norm": 1.086547613143921,
      "learning_rate": 4.411764705882353e-05,
      "loss": 2.1473,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.5191813707351685,
      "learning_rate": 4.11764705882353e-05,
      "loss": 2.2585,
      "step": 26
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 1.081872582435608,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 2.0712,
      "step": 27
    },
    {
      "epoch": 2.1584158415841586,
      "grad_norm": 1.0870336294174194,
      "learning_rate": 3.529411764705883e-05,
      "loss": 2.0155,
      "step": 28
    },
    {
      "epoch": 2.237623762376238,
      "grad_norm": 1.14115309715271,
      "learning_rate": 3.235294117647059e-05,
      "loss": 2.0304,
      "step": 29
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 1.1861549615859985,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 2.0872,
      "step": 30
    },
    {
      "epoch": 2.396039603960396,
      "grad_norm": 1.1073037385940552,
      "learning_rate": 2.647058823529412e-05,
      "loss": 2.0321,
      "step": 31
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 1.1062642335891724,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.9772,
      "step": 32
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 1.1854885816574097,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.9635,
      "step": 33
    },
    {
      "epoch": 2.633663366336634,
      "grad_norm": 1.1124718189239502,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.9738,
      "step": 34
    },
    {
      "epoch": 2.7128712871287126,
      "grad_norm": 1.128793478012085,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 2.0594,
      "step": 35
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 1.1796002388000488,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.9796,
      "step": 36
    },
    {
      "epoch": 2.871287128712871,
      "grad_norm": 1.1448339223861694,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.9463,
      "step": 37
    },
    {
      "epoch": 2.9504950495049505,
      "grad_norm": 1.1534873247146606,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.9453,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.526010513305664,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 2.0768,
      "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": 1754681714534400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}