{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9714285714285715,
  "eval_steps": 500,
  "global_step": 129,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 0.9437829852104187,
      "learning_rate": 0.0002,
      "loss": 4.167,
      "step": 3
    },
    {
      "epoch": 0.13714285714285715,
      "grad_norm": 0.706287682056427,
      "learning_rate": 0.0002,
      "loss": 4.0218,
      "step": 6
    },
    {
      "epoch": 0.2057142857142857,
      "grad_norm": 0.9851099848747253,
      "learning_rate": 0.0002,
      "loss": 3.989,
      "step": 9
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 0.6341831088066101,
      "learning_rate": 0.0002,
      "loss": 3.6726,
      "step": 12
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4039613902568817,
      "learning_rate": 0.0002,
      "loss": 3.4053,
      "step": 15
    },
    {
      "epoch": 0.4114285714285714,
      "grad_norm": 0.44874435663223267,
      "learning_rate": 0.0002,
      "loss": 3.4123,
      "step": 18
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.4203323721885681,
      "learning_rate": 0.0002,
      "loss": 3.3871,
      "step": 21
    },
    {
      "epoch": 0.5485714285714286,
      "grad_norm": 0.4040702283382416,
      "learning_rate": 0.0002,
      "loss": 3.2221,
      "step": 24
    },
    {
      "epoch": 0.6171428571428571,
      "grad_norm": 0.40100640058517456,
      "learning_rate": 0.0002,
      "loss": 3.2005,
      "step": 27
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.6720607280731201,
      "learning_rate": 0.0002,
      "loss": 3.1844,
      "step": 30
    },
    {
      "epoch": 0.7542857142857143,
      "grad_norm": 0.3040887415409088,
      "learning_rate": 0.0002,
      "loss": 3.2236,
      "step": 33
    },
    {
      "epoch": 0.8228571428571428,
      "grad_norm": 0.3039924204349518,
      "learning_rate": 0.0002,
      "loss": 3.1461,
      "step": 36
    },
    {
      "epoch": 0.8914285714285715,
      "grad_norm": 0.5960268974304199,
      "learning_rate": 0.0002,
      "loss": 3.1462,
      "step": 39
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.22920484840869904,
      "learning_rate": 0.0002,
      "loss": 3.1491,
      "step": 42
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.21868771314620972,
      "learning_rate": 0.0002,
      "loss": 4.0082,
      "step": 45
    },
    {
      "epoch": 1.1085714285714285,
      "grad_norm": 0.2646636962890625,
      "learning_rate": 0.0002,
      "loss": 3.0884,
      "step": 48
    },
    {
      "epoch": 1.177142857142857,
      "grad_norm": 0.30294740200042725,
      "learning_rate": 0.0002,
      "loss": 3.0319,
      "step": 51
    },
    {
      "epoch": 1.2457142857142858,
      "grad_norm": 0.6299964785575867,
      "learning_rate": 0.0002,
      "loss": 3.0376,
      "step": 54
    },
    {
      "epoch": 1.3142857142857143,
      "grad_norm": 0.4104610085487366,
      "learning_rate": 0.0002,
      "loss": 3.1366,
      "step": 57
    },
    {
      "epoch": 1.3828571428571428,
      "grad_norm": 0.4743083715438843,
      "learning_rate": 0.0002,
      "loss": 3.0527,
      "step": 60
    },
    {
      "epoch": 1.4514285714285715,
      "grad_norm": 0.6701816916465759,
      "learning_rate": 0.0002,
      "loss": 3.069,
      "step": 63
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.321772962808609,
      "learning_rate": 0.0002,
      "loss": 3.0445,
      "step": 66
    },
    {
      "epoch": 1.5885714285714285,
      "grad_norm": 0.2866778075695038,
      "learning_rate": 0.0002,
      "loss": 2.9932,
      "step": 69
    },
    {
      "epoch": 1.657142857142857,
      "grad_norm": 0.45329466462135315,
      "learning_rate": 0.0002,
      "loss": 3.0257,
      "step": 72
    },
    {
      "epoch": 1.7257142857142858,
      "grad_norm": 0.38146278262138367,
      "learning_rate": 0.0002,
      "loss": 2.9753,
      "step": 75
    },
    {
      "epoch": 1.7942857142857143,
      "grad_norm": 0.25521424412727356,
      "learning_rate": 0.0002,
      "loss": 3.0399,
      "step": 78
    },
    {
      "epoch": 1.862857142857143,
      "grad_norm": 0.40487968921661377,
      "learning_rate": 0.0002,
      "loss": 3.0027,
      "step": 81
    },
    {
      "epoch": 1.9314285714285715,
      "grad_norm": 0.6657207012176514,
      "learning_rate": 0.0002,
      "loss": 3.0455,
      "step": 84
    },
    {
      "epoch": 2.0114285714285716,
      "grad_norm": 0.837748646736145,
      "learning_rate": 0.0002,
      "loss": 3.7381,
      "step": 87
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.4829089045524597,
      "learning_rate": 0.0002,
      "loss": 3.0417,
      "step": 90
    },
    {
      "epoch": 2.1485714285714286,
      "grad_norm": 0.30258846282958984,
      "learning_rate": 0.0002,
      "loss": 2.9999,
      "step": 93
    },
    {
      "epoch": 2.217142857142857,
      "grad_norm": 0.8457381129264832,
      "learning_rate": 0.0002,
      "loss": 2.9085,
      "step": 96
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.5655274391174316,
      "learning_rate": 0.0002,
      "loss": 2.9864,
      "step": 99
    },
    {
      "epoch": 2.354285714285714,
      "grad_norm": 0.34071195125579834,
      "learning_rate": 0.0002,
      "loss": 2.9532,
      "step": 102
    },
    {
      "epoch": 2.422857142857143,
      "grad_norm": 0.5198696255683899,
      "learning_rate": 0.0002,
      "loss": 2.9002,
      "step": 105
    },
    {
      "epoch": 2.4914285714285715,
      "grad_norm": 0.48464879393577576,
      "learning_rate": 0.0002,
      "loss": 2.9063,
      "step": 108
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.4100594222545624,
      "learning_rate": 0.0002,
      "loss": 3.0438,
      "step": 111
    },
    {
      "epoch": 2.6285714285714286,
      "grad_norm": 0.5050905346870422,
      "learning_rate": 0.0002,
      "loss": 2.9542,
      "step": 114
    },
    {
      "epoch": 2.697142857142857,
      "grad_norm": 0.5607490539550781,
      "learning_rate": 0.0002,
      "loss": 2.8878,
      "step": 117
    },
    {
      "epoch": 2.7657142857142856,
      "grad_norm": 0.31164994835853577,
      "learning_rate": 0.0002,
      "loss": 3.1095,
      "step": 120
    },
    {
      "epoch": 2.8342857142857145,
      "grad_norm": 0.37856680154800415,
      "learning_rate": 0.0002,
      "loss": 2.9569,
      "step": 123
    },
    {
      "epoch": 2.902857142857143,
      "grad_norm": 0.642971932888031,
      "learning_rate": 0.0002,
      "loss": 2.9127,
      "step": 126
    },
    {
      "epoch": 2.9714285714285715,
      "grad_norm": 0.6274252533912659,
      "learning_rate": 0.0002,
      "loss": 2.9586,
      "step": 129
    }
  ],
  "logging_steps": 3,
  "max_steps": 129,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.395590565882757e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}