{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 26.742956161499023,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 4.1563,
      "step": 1
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 26.336389541625977,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 4.0633,
      "step": 2
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 28.836008071899414,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 4.3575,
      "step": 3
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 27.459413528442383,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 4.1943,
      "step": 4
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 27.914960861206055,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 4.3336,
      "step": 5
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 27.47397232055664,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 4.2354,
      "step": 6
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 26.212989807128906,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 4.1001,
      "step": 7
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 26.80431365966797,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 4.1827,
      "step": 8
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 27.641605377197266,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 4.2596,
      "step": 9
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 27.783071517944336,
      "learning_rate": 5.000000000000001e-07,
      "loss": 4.2694,
      "step": 10
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 26.553335189819336,
      "learning_rate": 5.5e-07,
      "loss": 4.0739,
      "step": 11
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 26.77140998840332,
      "learning_rate": 6.000000000000001e-07,
      "loss": 4.1049,
      "step": 12
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 25.07087516784668,
      "learning_rate": 6.5e-07,
      "loss": 3.8982,
      "step": 13
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 25.834062576293945,
      "learning_rate": 7.000000000000001e-07,
      "loss": 4.0768,
      "step": 14
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 25.00474739074707,
      "learning_rate": 7.5e-07,
      "loss": 4.0104,
      "step": 15
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 23.692975997924805,
      "learning_rate": 8.000000000000001e-07,
      "loss": 3.8469,
      "step": 16
    },
    {
      "epoch": 0.40476190476190477,
      "grad_norm": 22.197919845581055,
      "learning_rate": 8.500000000000001e-07,
      "loss": 3.7738,
      "step": 17
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 20.92680549621582,
      "learning_rate": 9.000000000000001e-07,
      "loss": 3.6514,
      "step": 18
    },
    {
      "epoch": 0.4523809523809524,
      "grad_norm": 20.251178741455078,
      "learning_rate": 9.500000000000001e-07,
      "loss": 3.6739,
      "step": 19
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 17.55536460876465,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.2675,
      "step": 20
    },
    {
      "epoch": 0.5,
      "grad_norm": 17.066797256469727,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 3.4232,
      "step": 21
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 16.1475887298584,
      "learning_rate": 1.1e-06,
      "loss": 3.1988,
      "step": 22
    },
    {
      "epoch": 0.5476190476190477,
      "grad_norm": 15.61026382446289,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 3.1338,
      "step": 23
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 15.409480094909668,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 2.9836,
      "step": 24
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 15.391901969909668,
      "learning_rate": 1.25e-06,
      "loss": 2.9064,
      "step": 25
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 16.92401885986328,
      "learning_rate": 1.3e-06,
      "loss": 2.906,
      "step": 26
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 17.880958557128906,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 2.702,
      "step": 27
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 18.114517211914062,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 2.4876,
      "step": 28
    },
    {
      "epoch": 0.6904761904761905,
      "grad_norm": 17.608840942382812,
      "learning_rate": 1.45e-06,
      "loss": 2.2996,
      "step": 29
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 17.055673599243164,
      "learning_rate": 1.5e-06,
      "loss": 2.2709,
      "step": 30
    },
    {
      "epoch": 0.7380952380952381,
      "grad_norm": 14.92151927947998,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 2.0406,
      "step": 31
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 13.657073020935059,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.8564,
      "step": 32
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 13.274576187133789,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 1.7382,
      "step": 33
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 13.728348731994629,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 1.6629,
      "step": 34
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 13.521151542663574,
      "learning_rate": 1.75e-06,
      "loss": 1.5301,
      "step": 35
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 13.709525108337402,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 1.4122,
      "step": 36
    },
    {
      "epoch": 0.8809523809523809,
      "grad_norm": 12.587928771972656,
      "learning_rate": 1.85e-06,
      "loss": 1.2014,
      "step": 37
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 13.494888305664062,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 1.1793,
      "step": 38
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 13.417922019958496,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 1.0282,
      "step": 39
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 12.754359245300293,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.8525,
      "step": 40
    },
    {
      "epoch": 0.9761904761904762,
      "grad_norm": 12.766407012939453,
      "learning_rate": 2.05e-06,
      "loss": 0.7043,
      "step": 41
    },
    {
      "epoch": 1.0,
      "grad_norm": 11.440421104431152,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.6245,
      "step": 42
    }
  ],
  "logging_steps": 1,
  "max_steps": 252,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 42,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.408600616835482e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}