{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 234,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 27.017040252685547,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.7692,
      "step": 5
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 5.609267234802246,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.3809,
      "step": 10
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 4.588617324829102,
      "learning_rate": 9.998079135987437e-06,
      "loss": 0.2151,
      "step": 15
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 4.914970874786377,
      "learning_rate": 9.98634586692894e-06,
      "loss": 0.1584,
      "step": 20
    },
    {
      "epoch": 0.21367521367521367,
      "grad_norm": 2.268480062484741,
      "learning_rate": 9.963971484502247e-06,
      "loss": 0.1381,
      "step": 25
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 2.878901481628418,
      "learning_rate": 9.931003736767013e-06,
      "loss": 0.1172,
      "step": 30
    },
    {
      "epoch": 0.29914529914529914,
      "grad_norm": 1.802026629447937,
      "learning_rate": 9.887512978558329e-06,
      "loss": 0.1212,
      "step": 35
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 1.587371826171875,
      "learning_rate": 9.833592021345938e-06,
      "loss": 0.1167,
      "step": 40
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 1.4036160707473755,
      "learning_rate": 9.76935593516989e-06,
      "loss": 0.1169,
      "step": 45
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 1.2294965982437134,
      "learning_rate": 9.694941803075285e-06,
      "loss": 0.1076,
      "step": 50
    },
    {
      "epoch": 0.4700854700854701,
      "grad_norm": 1.9422516822814941,
      "learning_rate": 9.610508428570122e-06,
      "loss": 0.1137,
      "step": 55
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 1.1019206047058105,
      "learning_rate": 9.516235996730645e-06,
      "loss": 0.1033,
      "step": 60
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.2963364124298096,
      "learning_rate": 9.41232568967728e-06,
      "loss": 0.1081,
      "step": 65
    },
    {
      "epoch": 0.5982905982905983,
      "grad_norm": 1.0511146783828735,
      "learning_rate": 9.298999257241862e-06,
      "loss": 0.107,
      "step": 70
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 1.2040799856185913,
      "learning_rate": 9.176498543742328e-06,
      "loss": 0.1025,
      "step": 75
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 1.0622382164001465,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.0969,
      "step": 80
    },
    {
      "epoch": 0.7264957264957265,
      "grad_norm": 1.3135966062545776,
      "learning_rate": 8.905038984824079e-06,
      "loss": 0.1076,
      "step": 85
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 2.7178003787994385,
      "learning_rate": 8.756659447784367e-06,
      "loss": 0.1024,
      "step": 90
    },
    {
      "epoch": 0.811965811965812,
      "grad_norm": 1.091944932937622,
      "learning_rate": 8.600263010165275e-06,
      "loss": 0.0976,
      "step": 95
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 1.0061477422714233,
      "learning_rate": 8.436183429846314e-06,
      "loss": 0.105,
      "step": 100
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 1.1543011665344238,
      "learning_rate": 8.264770860920722e-06,
      "loss": 0.108,
      "step": 105
    },
    {
      "epoch": 0.9401709401709402,
      "grad_norm": 65.75935363769531,
      "learning_rate": 8.086391106448965e-06,
      "loss": 0.0986,
      "step": 110
    },
    {
      "epoch": 0.9829059829059829,
      "grad_norm": 1.127467393875122,
      "learning_rate": 7.90142483781658e-06,
      "loss": 0.0991,
      "step": 115
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.7937602996826172,
      "learning_rate": 7.710266782362248e-06,
      "loss": 0.0652,
      "step": 120
    },
    {
      "epoch": 1.0683760683760684,
      "grad_norm": 2.004312038421631,
      "learning_rate": 7.513324881009769e-06,
      "loss": 0.0442,
      "step": 125
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 2.4858341217041016,
      "learning_rate": 7.311019417701567e-06,
      "loss": 0.0419,
      "step": 130
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 1.7025681734085083,
      "learning_rate": 7.103782122491577e-06,
      "loss": 0.0419,
      "step": 135
    },
    {
      "epoch": 1.1965811965811965,
      "grad_norm": 1.0340570211410522,
      "learning_rate": 6.892055250211552e-06,
      "loss": 0.0364,
      "step": 140
    },
    {
      "epoch": 1.2393162393162394,
      "grad_norm": 1.6218270063400269,
      "learning_rate": 6.67629063667697e-06,
      "loss": 0.0369,
      "step": 145
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 1.1693732738494873,
      "learning_rate": 6.456948734446624e-06,
      "loss": 0.0381,
      "step": 150
    },
    {
      "epoch": 1.3247863247863247,
      "grad_norm": 0.899215042591095,
      "learning_rate": 6.234497630193666e-06,
      "loss": 0.0401,
      "step": 155
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 2.424380302429199,
      "learning_rate": 6.009412045785051e-06,
      "loss": 0.0408,
      "step": 160
    },
    {
      "epoch": 1.4102564102564101,
      "grad_norm": 0.7970224618911743,
      "learning_rate": 5.782172325201155e-06,
      "loss": 0.0386,
      "step": 165
    },
    {
      "epoch": 1.452991452991453,
      "grad_norm": 0.8833101391792297,
      "learning_rate": 5.553263409457504e-06,
      "loss": 0.0337,
      "step": 170
    },
    {
      "epoch": 1.4957264957264957,
      "grad_norm": 1.1074434518814087,
      "learning_rate": 5.323173801716222e-06,
      "loss": 0.037,
      "step": 175
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.9152804613113403,
      "learning_rate": 5.09239452479565e-06,
      "loss": 0.0358,
      "step": 180
    },
    {
      "epoch": 1.5811965811965814,
      "grad_norm": 0.9139125943183899,
      "learning_rate": 4.861418073302919e-06,
      "loss": 0.0358,
      "step": 185
    },
    {
      "epoch": 1.623931623931624,
      "grad_norm": 1.1984926462173462,
      "learning_rate": 4.630737362625631e-06,
      "loss": 0.0365,
      "step": 190
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.0415434837341309,
      "learning_rate": 4.400844677025585e-06,
      "loss": 0.0395,
      "step": 195
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 2.2899038791656494,
      "learning_rate": 4.17223061907935e-06,
      "loss": 0.0382,
      "step": 200
    },
    {
      "epoch": 1.7521367521367521,
      "grad_norm": 1.3134256601333618,
      "learning_rate": 3.945383062707652e-06,
      "loss": 0.035,
      "step": 205
    },
    {
      "epoch": 1.7948717948717947,
      "grad_norm": 0.7779367566108704,
      "learning_rate": 3.720786112027822e-06,
      "loss": 0.0331,
      "step": 210
    },
    {
      "epoch": 1.8376068376068377,
      "grad_norm": 1.0426898002624512,
      "learning_rate": 3.498919068251237e-06,
      "loss": 0.0371,
      "step": 215
    },
    {
      "epoch": 1.8803418803418803,
      "grad_norm": 6.495502948760986,
      "learning_rate": 3.2802554068303595e-06,
      "loss": 0.0359,
      "step": 220
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 1.00557541847229,
      "learning_rate": 3.0652617670382745e-06,
      "loss": 0.0339,
      "step": 225
    },
    {
      "epoch": 1.965811965811966,
      "grad_norm": 2.1927056312561035,
      "learning_rate": 2.8543969561369556e-06,
      "loss": 0.034,
      "step": 230
    }
  ],
  "logging_steps": 5,
  "max_steps": 351,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8207299650715648e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}