{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 300,
  "global_step": 273,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003663003663003663,
      "grad_norm": 165.0,
      "learning_rate": 2e-06,
      "loss": 9.1083,
      "step": 1
    },
    {
      "epoch": 0.018315018315018316,
      "grad_norm": 64.0,
      "learning_rate": 1.9998820020169668e-06,
      "loss": 8.3175,
      "step": 5
    },
    {
      "epoch": 0.03663003663003663,
      "grad_norm": 26.875,
      "learning_rate": 1.999402682936637e-06,
      "loss": 7.3293,
      "step": 10
    },
    {
      "epoch": 0.054945054945054944,
      "grad_norm": 16.75,
      "learning_rate": 1.998554844493029e-06,
      "loss": 6.8602,
      "step": 15
    },
    {
      "epoch": 0.07326007326007326,
      "grad_norm": 11.0,
      "learning_rate": 1.997338799317767e-06,
      "loss": 6.6054,
      "step": 20
    },
    {
      "epoch": 0.09157509157509157,
      "grad_norm": 8.4375,
      "learning_rate": 1.995754995814884e-06,
      "loss": 6.3957,
      "step": 25
    },
    {
      "epoch": 0.10989010989010989,
      "grad_norm": 6.9375,
      "learning_rate": 1.9938040179954784e-06,
      "loss": 6.256,
      "step": 30
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 6.15625,
      "learning_rate": 1.991486585262365e-06,
      "loss": 6.1321,
      "step": 35
    },
    {
      "epoch": 0.14652014652014653,
      "grad_norm": 5.1875,
      "learning_rate": 1.988803552144804e-06,
      "loss": 6.018,
      "step": 40
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 5.59375,
      "learning_rate": 1.9857559079834022e-06,
      "loss": 5.9438,
      "step": 45
    },
    {
      "epoch": 0.18315018315018314,
      "grad_norm": 6.5,
      "learning_rate": 1.982344776565302e-06,
      "loss": 5.8733,
      "step": 50
    },
    {
      "epoch": 0.20146520146520147,
      "grad_norm": 4.84375,
      "learning_rate": 1.978571415709799e-06,
      "loss": 5.8341,
      "step": 55
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 4.125,
      "learning_rate": 1.9744372168045322e-06,
      "loss": 5.793,
      "step": 60
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 3.8125,
      "learning_rate": 1.9699437042924264e-06,
      "loss": 5.7305,
      "step": 65
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 4.0,
      "learning_rate": 1.965092535109567e-06,
      "loss": 5.671,
      "step": 70
    },
    {
      "epoch": 0.27472527472527475,
      "grad_norm": 4.125,
      "learning_rate": 1.959885498074224e-06,
      "loss": 5.6563,
      "step": 75
    },
    {
      "epoch": 0.29304029304029305,
      "grad_norm": 3.765625,
      "learning_rate": 1.954324513227244e-06,
      "loss": 5.5778,
      "step": 80
    },
    {
      "epoch": 0.31135531135531136,
      "grad_norm": 3.75,
      "learning_rate": 1.948411631124053e-06,
      "loss": 5.5838,
      "step": 85
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 6.71875,
      "learning_rate": 1.942149032078538e-06,
      "loss": 5.5305,
      "step": 90
    },
    {
      "epoch": 0.34798534798534797,
      "grad_norm": 4.6875,
      "learning_rate": 1.935539025359077e-06,
      "loss": 5.5108,
      "step": 95
    },
    {
      "epoch": 0.3663003663003663,
      "grad_norm": 3.546875,
      "learning_rate": 1.928584048337022e-06,
      "loss": 5.494,
      "step": 100
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 3.75,
      "learning_rate": 1.9212866655879395e-06,
      "loss": 5.4749,
      "step": 105
    },
    {
      "epoch": 0.40293040293040294,
      "grad_norm": 4.5,
      "learning_rate": 1.9136495679459563e-06,
      "loss": 5.4473,
      "step": 110
    },
    {
      "epoch": 0.42124542124542125,
      "grad_norm": 4.34375,
      "learning_rate": 1.9056755715115372e-06,
      "loss": 5.4071,
      "step": 115
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 3.609375,
      "learning_rate": 1.8973676166130791e-06,
      "loss": 5.3994,
      "step": 120
    },
    {
      "epoch": 0.45787545787545786,
      "grad_norm": 3.859375,
      "learning_rate": 1.8887287667226963e-06,
      "loss": 5.3773,
      "step": 125
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 3.4375,
      "learning_rate": 1.8797622073265943e-06,
      "loss": 5.3734,
      "step": 130
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 3.8125,
      "learning_rate": 1.8704712447504579e-06,
      "loss": 5.323,
      "step": 135
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 3.4375,
      "learning_rate": 1.8608593049402752e-06,
      "loss": 5.2964,
      "step": 140
    },
    {
      "epoch": 0.5311355311355311,
      "grad_norm": 3.484375,
      "learning_rate": 1.850929932199058e-06,
      "loss": 5.2951,
      "step": 145
    },
    {
      "epoch": 0.5494505494505495,
      "grad_norm": 3.375,
      "learning_rate": 1.8406867878799152e-06,
      "loss": 5.2498,
      "step": 150
    },
    {
      "epoch": 0.5677655677655677,
      "grad_norm": 3.859375,
      "learning_rate": 1.8301336490359678e-06,
      "loss": 5.2432,
      "step": 155
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 3.90625,
      "learning_rate": 1.819274407027599e-06,
      "loss": 5.2436,
      "step": 160
    },
    {
      "epoch": 0.6043956043956044,
      "grad_norm": 4.6875,
      "learning_rate": 1.8081130660875555e-06,
      "loss": 5.2218,
      "step": 165
    },
    {
      "epoch": 0.6227106227106227,
      "grad_norm": 3.5625,
      "learning_rate": 1.79665374184443e-06,
      "loss": 5.2194,
      "step": 170
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 3.546875,
      "learning_rate": 1.7849006598050625e-06,
      "loss": 5.1988,
      "step": 175
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 3.9375,
      "learning_rate": 1.7728581537964318e-06,
      "loss": 5.1814,
      "step": 180
    },
    {
      "epoch": 0.6776556776556777,
      "grad_norm": 4.40625,
      "learning_rate": 1.7605306643676006e-06,
      "loss": 5.1318,
      "step": 185
    },
    {
      "epoch": 0.6959706959706959,
      "grad_norm": 3.4375,
      "learning_rate": 1.747922737152308e-06,
      "loss": 5.1609,
      "step": 190
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 4.125,
      "learning_rate": 1.7350390211928166e-06,
      "loss": 5.1395,
      "step": 195
    },
    {
      "epoch": 0.7326007326007326,
      "grad_norm": 3.375,
      "learning_rate": 1.721884267225624e-06,
      "loss": 5.0794,
      "step": 200
    },
    {
      "epoch": 0.7509157509157509,
      "grad_norm": 3.421875,
      "learning_rate": 1.7084633259296795e-06,
      "loss": 5.0974,
      "step": 205
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.46875,
      "learning_rate": 1.6947811461377467e-06,
      "loss": 5.1007,
      "step": 210
    },
    {
      "epoch": 0.7875457875457875,
      "grad_norm": 3.984375,
      "learning_rate": 1.6808427730115712e-06,
      "loss": 5.0777,
      "step": 215
    },
    {
      "epoch": 0.8058608058608059,
      "grad_norm": 3.828125,
      "learning_rate": 1.6666533461815323e-06,
      "loss": 5.0517,
      "step": 220
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 3.546875,
      "learning_rate": 1.6522180978514552e-06,
      "loss": 5.0462,
      "step": 225
    },
    {
      "epoch": 0.8424908424908425,
      "grad_norm": 3.78125,
      "learning_rate": 1.6375423508692912e-06,
      "loss": 5.0538,
      "step": 230
    },
    {
      "epoch": 0.8608058608058609,
      "grad_norm": 3.515625,
      "learning_rate": 1.622631516764372e-06,
      "loss": 5.0335,
      "step": 235
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 3.359375,
      "learning_rate": 1.607491093751966e-06,
      "loss": 5.0177,
      "step": 240
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 4.8125,
      "learning_rate": 1.592126664705868e-06,
      "loss": 4.998,
      "step": 245
    },
    {
      "epoch": 0.9157509157509157,
      "grad_norm": 3.671875,
      "learning_rate": 1.5765438950997703e-06,
      "loss": 4.992,
      "step": 250
    },
    {
      "epoch": 0.9340659340659341,
      "grad_norm": 3.828125,
      "learning_rate": 1.5607485309181812e-06,
      "loss": 4.9831,
      "step": 255
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 3.90625,
      "learning_rate": 1.544746396537651e-06,
      "loss": 4.9835,
      "step": 260
    },
    {
      "epoch": 0.9706959706959707,
      "grad_norm": 3.484375,
      "learning_rate": 1.5285433925790945e-06,
      "loss": 4.962,
      "step": 265
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 3.421875,
      "learning_rate": 1.5121454937319975e-06,
      "loss": 4.9708,
      "step": 270
    }
  ],
  "logging_steps": 5,
  "max_steps": 819,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7871723276837847e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}