{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.978723404255319,
  "eval_steps": 500,
  "global_step": 186,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05319148936170213,
      "grad_norm": 2.484375,
      "learning_rate": 7.72058090429322e-06,
      "loss": 1.0185,
      "step": 5
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 1.921875,
      "learning_rate": 1.7371307034659745e-05,
      "loss": 0.9887,
      "step": 10
    },
    {
      "epoch": 0.1595744680851064,
      "grad_norm": 1.609375,
      "learning_rate": 2.702203316502627e-05,
      "loss": 0.9219,
      "step": 15
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 2.0,
      "learning_rate": 3.667275929539279e-05,
      "loss": 0.9248,
      "step": 20
    },
    {
      "epoch": 0.26595744680851063,
      "grad_norm": 1.71875,
      "learning_rate": 4.632348542575932e-05,
      "loss": 0.8551,
      "step": 25
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 1.8125,
      "learning_rate": 5.597421155612585e-05,
      "loss": 0.8737,
      "step": 30
    },
    {
      "epoch": 0.3723404255319149,
      "grad_norm": 1.859375,
      "learning_rate": 6.562493768649237e-05,
      "loss": 0.834,
      "step": 35
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 1.6953125,
      "learning_rate": 6.746968406392054e-05,
      "loss": 0.8323,
      "step": 40
    },
    {
      "epoch": 0.4787234042553192,
      "grad_norm": 1.484375,
      "learning_rate": 6.712373778909143e-05,
      "loss": 0.8278,
      "step": 45
    },
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 1.4921875,
      "learning_rate": 6.651554705487648e-05,
      "loss": 0.7397,
      "step": 50
    },
    {
      "epoch": 0.5851063829787234,
      "grad_norm": 1.375,
      "learning_rate": 6.565151680308889e-05,
      "loss": 0.8036,
      "step": 55
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 1.515625,
      "learning_rate": 6.454074625733765e-05,
      "loss": 0.7971,
      "step": 60
    },
    {
      "epoch": 0.6914893617021277,
      "grad_norm": 1.390625,
      "learning_rate": 6.319493309782911e-05,
      "loss": 0.7346,
      "step": 65
    },
    {
      "epoch": 0.7446808510638298,
      "grad_norm": 1.3828125,
      "learning_rate": 6.162825027145833e-05,
      "loss": 0.7127,
      "step": 70
    },
    {
      "epoch": 0.7978723404255319,
      "grad_norm": 1.3359375,
      "learning_rate": 5.985719673451993e-05,
      "loss": 0.6861,
      "step": 75
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 1.2265625,
      "learning_rate": 5.790042369988838e-05,
      "loss": 0.6625,
      "step": 80
    },
    {
      "epoch": 0.9042553191489362,
      "grad_norm": 1.2265625,
      "learning_rate": 5.577853821848267e-05,
      "loss": 0.6033,
      "step": 85
    },
    {
      "epoch": 0.9574468085106383,
      "grad_norm": 1.5234375,
      "learning_rate": 5.351388616352658e-05,
      "loss": 0.5906,
      "step": 90
    },
    {
      "epoch": 0.9893617021276596,
      "eval_loss": 0.6196732521057129,
      "eval_runtime": 18.6318,
      "eval_samples_per_second": 15.672,
      "eval_steps_per_second": 7.836,
      "step": 93
    },
    {
      "epoch": 1.0106382978723405,
      "grad_norm": 1.078125,
      "learning_rate": 5.1130316903027684e-05,
      "loss": 0.5445,
      "step": 95
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 1.328125,
      "learning_rate": 4.865293213874228e-05,
      "loss": 0.3503,
      "step": 100
    },
    {
      "epoch": 1.1170212765957448,
      "grad_norm": 0.98046875,
      "learning_rate": 4.610782155663802e-05,
      "loss": 0.3896,
      "step": 105
    },
    {
      "epoch": 1.1702127659574468,
      "grad_norm": 1.1796875,
      "learning_rate": 4.352178807275659e-05,
      "loss": 0.3792,
      "step": 110
    },
    {
      "epoch": 1.2234042553191489,
      "grad_norm": 1.03125,
      "learning_rate": 4.09220655679505e-05,
      "loss": 0.3483,
      "step": 115
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 1.1875,
      "learning_rate": 3.833603208406907e-05,
      "loss": 0.3657,
      "step": 120
    },
    {
      "epoch": 1.3297872340425532,
      "grad_norm": 1.21875,
      "learning_rate": 3.579092150196482e-05,
      "loss": 0.3025,
      "step": 125
    },
    {
      "epoch": 1.3829787234042552,
      "grad_norm": 0.96484375,
      "learning_rate": 3.3313536737679405e-05,
      "loss": 0.3495,
      "step": 130
    },
    {
      "epoch": 1.4361702127659575,
      "grad_norm": 1.0703125,
      "learning_rate": 3.0929967477180524e-05,
      "loss": 0.288,
      "step": 135
    },
    {
      "epoch": 1.4893617021276595,
      "grad_norm": 0.93359375,
      "learning_rate": 2.866531542222443e-05,
      "loss": 0.3082,
      "step": 140
    },
    {
      "epoch": 1.5425531914893615,
      "grad_norm": 1.03125,
      "learning_rate": 2.6543429940818712e-05,
      "loss": 0.3197,
      "step": 145
    },
    {
      "epoch": 1.5957446808510638,
      "grad_norm": 1.03125,
      "learning_rate": 2.4586656906187163e-05,
      "loss": 0.3072,
      "step": 150
    },
    {
      "epoch": 1.648936170212766,
      "grad_norm": 1.0625,
      "learning_rate": 2.2815603369248764e-05,
      "loss": 0.3164,
      "step": 155
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 1.2578125,
      "learning_rate": 2.1248920542877975e-05,
      "loss": 0.2973,
      "step": 160
    },
    {
      "epoch": 1.7553191489361701,
      "grad_norm": 0.87109375,
      "learning_rate": 1.990310738336945e-05,
      "loss": 0.2977,
      "step": 165
    },
    {
      "epoch": 1.8085106382978724,
      "grad_norm": 0.8984375,
      "learning_rate": 1.8792336837618205e-05,
      "loss": 0.2914,
      "step": 170
    },
    {
      "epoch": 1.8617021276595744,
      "grad_norm": 1.015625,
      "learning_rate": 1.7928306585830618e-05,
      "loss": 0.3164,
      "step": 175
    },
    {
      "epoch": 1.9148936170212765,
      "grad_norm": 1.046875,
      "learning_rate": 1.732011585161567e-05,
      "loss": 0.2888,
      "step": 180
    },
    {
      "epoch": 1.9680851063829787,
      "grad_norm": 0.87890625,
      "learning_rate": 1.6974169576786553e-05,
      "loss": 0.3215,
      "step": 185
    },
    {
      "epoch": 1.978723404255319,
      "eval_loss": 0.44498831033706665,
      "eval_runtime": 18.5042,
      "eval_samples_per_second": 15.78,
      "eval_steps_per_second": 7.89,
      "step": 186
    }
  ],
  "logging_steps": 5,
  "max_steps": 188,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 9.049813249163264e+17,
  "train_batch_size": 14,
  "trial_name": null,
  "trial_params": null
}