{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025,
      "grad_norm": 7.022058486938477,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.2871,
      "step": 5
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.1450326442718506,
      "learning_rate": 4.997050398198977e-06,
      "loss": 1.0775,
      "step": 10
    },
    {
      "epoch": 0.075,
      "grad_norm": 1.9242591857910156,
      "learning_rate": 4.979050253066064e-06,
      "loss": 0.9553,
      "step": 15
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.4348323345184326,
      "learning_rate": 4.944806430988927e-06,
      "loss": 0.8635,
      "step": 20
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.0105319023132324,
      "learning_rate": 4.894543310469968e-06,
      "loss": 0.8612,
      "step": 25
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.6607258319854736,
      "learning_rate": 4.828590234527107e-06,
      "loss": 0.8138,
      "step": 30
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.4061996638774872,
      "learning_rate": 4.747379352713489e-06,
      "loss": 0.7887,
      "step": 35
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.2776339054107666,
      "learning_rate": 4.651442789509813e-06,
      "loss": 0.7501,
      "step": 40
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.25159376859664917,
      "learning_rate": 4.541409157643027e-06,
      "loss": 0.7603,
      "step": 45
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.22889962792396545,
      "learning_rate": 4.417999439177465e-06,
      "loss": 0.7377,
      "step": 50
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.25352779030799866,
      "learning_rate": 4.282022261367074e-06,
      "loss": 0.7541,
      "step": 55
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.2564803957939148,
      "learning_rate": 4.134368598223132e-06,
      "loss": 0.7207,
      "step": 60
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.21964561939239502,
      "learning_rate": 3.976005932514807e-06,
      "loss": 0.7318,
      "step": 65
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.1952921450138092,
      "learning_rate": 3.807971916455325e-06,
      "loss": 0.7166,
      "step": 70
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.21189448237419128,
      "learning_rate": 3.631367572611348e-06,
      "loss": 0.7351,
      "step": 75
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.20247572660446167,
      "learning_rate": 3.4473500795857674e-06,
      "loss": 0.7192,
      "step": 80
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.1986052691936493,
      "learning_rate": 3.257125189744877e-06,
      "loss": 0.7018,
      "step": 85
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.20034098625183105,
      "learning_rate": 3.061939328671824e-06,
      "loss": 0.6939,
      "step": 90
    },
    {
      "epoch": 0.475,
      "grad_norm": 0.1981743723154068,
      "learning_rate": 2.8630714281137263e-06,
      "loss": 0.7129,
      "step": 95
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.2070968598127365,
      "learning_rate": 2.6618245459360896e-06,
      "loss": 0.6993,
      "step": 100
    },
    {
      "epoch": 0.525,
      "grad_norm": 0.19754789769649506,
      "learning_rate": 2.4595173279937464e-06,
      "loss": 0.7106,
      "step": 105
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.18637321889400482,
      "learning_rate": 2.25747536786338e-06,
      "loss": 0.6975,
      "step": 110
    },
    {
      "epoch": 0.575,
      "grad_norm": 0.1984306424856186,
      "learning_rate": 2.0570225210519433e-06,
      "loss": 0.7025,
      "step": 115
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.19408036768436432,
      "learning_rate": 1.8594722305935691e-06,
      "loss": 0.6748,
      "step": 120
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.19682057201862335,
      "learning_rate": 1.6661189208729492e-06,
      "loss": 0.7103,
      "step": 125
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.2067941576242447,
      "learning_rate": 1.4782295160661103e-06,
      "loss": 0.6787,
      "step": 130
    },
    {
      "epoch": 0.675,
      "grad_norm": 0.19579337537288666,
      "learning_rate": 1.2970351387729875e-06,
      "loss": 0.6844,
      "step": 135
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.19357725977897644,
      "learning_rate": 1.1237230432354912e-06,
      "loss": 0.6872,
      "step": 140
    },
    {
      "epoch": 0.725,
      "grad_norm": 0.19475950300693512,
      "learning_rate": 9.594288359976817e-07,
      "loss": 0.6843,
      "step": 145
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.19206686317920685,
      "learning_rate": 8.052290349812419e-07,
      "loss": 0.6983,
      "step": 150
    },
    {
      "epoch": 0.775,
      "grad_norm": 0.18994426727294922,
      "learning_rate": 6.621340157319998e-07,
      "loss": 0.6907,
      "step": 155
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.19607287645339966,
      "learning_rate": 5.310813910563645e-07,
      "loss": 0.6765,
      "step": 160
    },
    {
      "epoch": 0.825,
      "grad_norm": 0.18892605602741241,
      "learning_rate": 4.129298674268226e-07,
      "loss": 0.682,
      "step": 165
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.20095601677894592,
      "learning_rate": 3.08453618411631e-07,
      "loss": 0.6918,
      "step": 170
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.1872701197862625,
      "learning_rate": 2.1833721199614992e-07,
      "loss": 0.6782,
      "step": 175
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.1944805085659027,
      "learning_rate": 1.4317112503391433e-07,
      "loss": 0.6997,
      "step": 180
    },
    {
      "epoch": 0.925,
      "grad_norm": 0.19366849958896637,
      "learning_rate": 8.344787421847216e-08,
      "loss": 0.6741,
      "step": 185
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.18197080492973328,
      "learning_rate": 3.955878892731441e-08,
      "loss": 0.685,
      "step": 190
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.18788814544677734,
      "learning_rate": 1.1791447083465136e-08,
      "loss": 0.6769,
      "step": 195
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2002282291650772,
      "learning_rate": 3.277908359194948e-10,
      "loss": 0.693,
      "step": 200
    },
    {
      "epoch": 1.0,
      "step": 200,
      "total_flos": 4.0836188273115136e+18,
      "train_loss": 0.746429123878479,
      "train_runtime": 2870.5475,
      "train_samples_per_second": 1.114,
      "train_steps_per_second": 0.07
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.0836188273115136e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}