{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02113718030014796,
  "eval_steps": 63,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.454872120059185e-05,
      "eval_loss": NaN,
      "eval_runtime": 228.2507,
      "eval_samples_per_second": 10.909,
      "eval_steps_per_second": 5.455,
      "step": 1
    },
    {
      "epoch": 0.0008454872120059184,
      "grad_norm": NaN,
      "learning_rate": 0.00019979453927503364,
      "loss": 5.6754,
      "step": 10
    },
    {
      "epoch": 0.0016909744240118367,
      "grad_norm": NaN,
      "learning_rate": 0.00019815591569910654,
      "loss": 6.8971,
      "step": 20
    },
    {
      "epoch": 0.0025364616360177552,
      "grad_norm": NaN,
      "learning_rate": 0.00019490557470106686,
      "loss": 3.6576,
      "step": 30
    },
    {
      "epoch": 0.0033819488480236735,
      "grad_norm": NaN,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.6001,
      "step": 40
    },
    {
      "epoch": 0.004227436060029592,
      "grad_norm": NaN,
      "learning_rate": 0.00018380881048918405,
      "loss": 1.2811,
      "step": 50
    },
    {
      "epoch": 0.0050729232720355105,
      "grad_norm": NaN,
      "learning_rate": 0.00017614459583691346,
      "loss": 7.1498,
      "step": 60
    },
    {
      "epoch": 0.005326569435637286,
      "eval_loss": NaN,
      "eval_runtime": 227.6495,
      "eval_samples_per_second": 10.938,
      "eval_steps_per_second": 5.469,
      "step": 63
    },
    {
      "epoch": 0.005918410484041429,
      "grad_norm": NaN,
      "learning_rate": 0.0001672300890261317,
      "loss": 0.6174,
      "step": 70
    },
    {
      "epoch": 0.006763897696047347,
      "grad_norm": NaN,
      "learning_rate": 0.00015721166601221698,
      "loss": 4.0369,
      "step": 80
    },
    {
      "epoch": 0.007609384908053266,
      "grad_norm": NaN,
      "learning_rate": 0.00014625382902408356,
      "loss": 1.1157,
      "step": 90
    },
    {
      "epoch": 0.008454872120059184,
      "grad_norm": NaN,
      "learning_rate": 0.00013453650544213076,
      "loss": 6.5497,
      "step": 100
    },
    {
      "epoch": 0.009300359332065102,
      "grad_norm": NaN,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.010145846544071021,
      "grad_norm": NaN,
      "learning_rate": 0.00010960230259076818,
      "loss": 0.7933,
      "step": 120
    },
    {
      "epoch": 0.010653138871274573,
      "eval_loss": NaN,
      "eval_runtime": 227.7675,
      "eval_samples_per_second": 10.932,
      "eval_steps_per_second": 5.466,
      "step": 126
    },
    {
      "epoch": 0.01099133375607694,
      "grad_norm": NaN,
      "learning_rate": 9.679484224283449e-05,
      "loss": 0.7588,
      "step": 130
    },
    {
      "epoch": 0.011836820968082858,
      "grad_norm": NaN,
      "learning_rate": 8.404001049666211e-05,
      "loss": 0.5221,
      "step": 140
    },
    {
      "epoch": 0.012682308180088777,
      "grad_norm": NaN,
      "learning_rate": 7.154724133689677e-05,
      "loss": 4.1784,
      "step": 150
    },
    {
      "epoch": 0.013527795392094694,
      "grad_norm": NaN,
      "learning_rate": 5.952166568776062e-05,
      "loss": 3.9385,
      "step": 160
    },
    {
      "epoch": 0.014373282604100613,
      "grad_norm": NaN,
      "learning_rate": 4.8160743168947496e-05,
      "loss": 5.192,
      "step": 170
    },
    {
      "epoch": 0.015218769816106531,
      "grad_norm": NaN,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 2.3736,
      "step": 180
    },
    {
      "epoch": 0.01597970830691186,
      "eval_loss": NaN,
      "eval_runtime": 227.75,
      "eval_samples_per_second": 10.933,
      "eval_steps_per_second": 5.467,
      "step": 189
    },
    {
      "epoch": 0.01606425702811245,
      "grad_norm": NaN,
      "learning_rate": 2.8165064990227252e-05,
      "loss": 2.412,
      "step": 190
    },
    {
      "epoch": 0.016909744240118367,
      "grad_norm": NaN,
      "learning_rate": 1.985863781320435e-05,
      "loss": 0.9332,
      "step": 200
    },
    {
      "epoch": 0.017755231452124286,
      "grad_norm": NaN,
      "learning_rate": 1.286812958766106e-05,
      "loss": 5.4573,
      "step": 210
    },
    {
      "epoch": 0.018600718664130204,
      "grad_norm": NaN,
      "learning_rate": 7.308324265397836e-06,
      "loss": 0.4817,
      "step": 220
    },
    {
      "epoch": 0.019446205876136123,
      "grad_norm": NaN,
      "learning_rate": 3.270513696097055e-06,
      "loss": 5.9903,
      "step": 230
    },
    {
      "epoch": 0.020291693088142042,
      "grad_norm": NaN,
      "learning_rate": 8.209986176753948e-07,
      "loss": 4.2354,
      "step": 240
    },
    {
      "epoch": 0.02113718030014796,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.5421,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 63,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.059746184593408e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}