{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 830,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4939759036144578,
      "grad_norm": NaN,
      "learning_rate": 1.9012048192771087e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.9879518072289156,
      "grad_norm": NaN,
      "learning_rate": 1.802409638554217e-05,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.09523809523809523,
      "eval_f1": 0.016563146997929608,
      "eval_loss": NaN,
      "eval_runtime": 2.8332,
      "eval_samples_per_second": 37.061,
      "eval_steps_per_second": 4.941,
      "step": 83
    },
    {
      "epoch": 1.4819277108433735,
      "grad_norm": NaN,
      "learning_rate": 1.7036144578313254e-05,
      "loss": 0.0,
      "step": 123
    },
    {
      "epoch": 1.9759036144578315,
      "grad_norm": NaN,
      "learning_rate": 1.604819277108434e-05,
      "loss": 0.0,
      "step": 164
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.09523809523809523,
      "eval_f1": 0.016563146997929608,
      "eval_loss": NaN,
      "eval_runtime": 2.8629,
      "eval_samples_per_second": 36.676,
      "eval_steps_per_second": 4.89,
      "step": 166
    },
    {
      "epoch": 2.4698795180722892,
      "grad_norm": NaN,
      "learning_rate": 1.5060240963855424e-05,
      "loss": 0.0,
      "step": 205
    },
    {
      "epoch": 2.963855421686747,
      "grad_norm": NaN,
      "learning_rate": 1.4072289156626506e-05,
      "loss": 0.0,
      "step": 246
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.09523809523809523,
      "eval_f1": 0.016563146997929608,
      "eval_loss": NaN,
      "eval_runtime": 2.8905,
      "eval_samples_per_second": 36.326,
      "eval_steps_per_second": 4.843,
      "step": 249
    },
    {
      "epoch": 3.4578313253012047,
      "grad_norm": NaN,
      "learning_rate": 1.3084337349397591e-05,
      "loss": 0.0,
      "step": 287
    },
    {
      "epoch": 3.9518072289156625,
      "grad_norm": NaN,
      "learning_rate": 1.2096385542168677e-05,
      "loss": 0.0,
      "step": 328
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.09523809523809523,
      "eval_f1": 0.016563146997929608,
      "eval_loss": NaN,
      "eval_runtime": 2.8626,
      "eval_samples_per_second": 36.68,
      "eval_steps_per_second": 4.891,
      "step": 332
    },
    {
      "epoch": 4.445783132530121,
      "grad_norm": NaN,
      "learning_rate": 1.110843373493976e-05,
      "loss": 0.0,
      "step": 369
    },
    {
      "epoch": 4.9397590361445785,
      "grad_norm": NaN,
      "learning_rate": 1.0120481927710844e-05,
      "loss": 0.0,
      "step": 410
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.09523809523809523,
      "eval_f1": 0.016563146997929608,
      "eval_loss": NaN,
      "eval_runtime": 2.8494,
      "eval_samples_per_second": 36.849,
      "eval_steps_per_second": 4.913,
      "step": 415
    },
    {
      "epoch": 5.433734939759036,
      "grad_norm": NaN,
      "learning_rate": 9.132530120481929e-06,
      "loss": 0.0,
      "step": 451
    },
    {
      "epoch": 5.927710843373494,
      "grad_norm": NaN,
      "learning_rate": 8.144578313253012e-06,
      "loss": 0.0,
      "step": 492
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.09523809523809523,
      "eval_f1": 0.016563146997929608,
      "eval_loss": NaN,
      "eval_runtime": 2.8675,
      "eval_samples_per_second": 36.617,
      "eval_steps_per_second": 4.882,
      "step": 498
    },
    {
      "epoch": 6.421686746987952,
      "grad_norm": NaN,
      "learning_rate": 7.156626506024097e-06,
      "loss": 0.0,
      "step": 533
    },
    {
      "epoch": 6.9156626506024095,
      "grad_norm": NaN,
      "learning_rate": 6.168674698795182e-06,
      "loss": 0.0,
      "step": 574
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.09523809523809523,
      "eval_f1": 0.016563146997929608,
      "eval_loss": NaN,
      "eval_runtime": 2.8441,
      "eval_samples_per_second": 36.919,
      "eval_steps_per_second": 4.922,
      "step": 581
    },
    {
      "epoch": 7.409638554216867,
      "grad_norm": NaN,
      "learning_rate": 5.180722891566266e-06,
      "loss": 0.0,
      "step": 615
    },
    {
      "epoch": 7.903614457831325,
      "grad_norm": NaN,
      "learning_rate": 4.19277108433735e-06,
      "loss": 0.0,
      "step": 656
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.09523809523809523,
      "eval_f1": 0.016563146997929608,
      "eval_loss": NaN,
      "eval_runtime": 2.8258,
      "eval_samples_per_second": 37.157,
      "eval_steps_per_second": 4.954,
      "step": 664
    },
    {
      "epoch": 8.397590361445783,
      "grad_norm": NaN,
      "learning_rate": 3.204819277108434e-06,
      "loss": 0.0,
      "step": 697
    },
    {
      "epoch": 8.891566265060241,
      "grad_norm": NaN,
      "learning_rate": 2.2168674698795183e-06,
      "loss": 0.0,
      "step": 738
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.09523809523809523,
      "eval_f1": 0.016563146997929608,
      "eval_loss": NaN,
      "eval_runtime": 2.8829,
      "eval_samples_per_second": 36.422,
      "eval_steps_per_second": 4.856,
      "step": 747
    },
    {
      "epoch": 9.385542168674698,
      "grad_norm": NaN,
      "learning_rate": 1.2289156626506025e-06,
      "loss": 0.0,
      "step": 779
    },
    {
      "epoch": 9.879518072289157,
      "grad_norm": NaN,
      "learning_rate": 2.409638554216868e-07,
      "loss": 0.0,
      "step": 820
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.09523809523809523,
      "eval_f1": 0.016563146997929608,
      "eval_loss": NaN,
      "eval_runtime": 2.8484,
      "eval_samples_per_second": 36.863,
      "eval_steps_per_second": 4.915,
      "step": 830
    },
    {
      "epoch": 10.0,
      "step": 830,
      "total_flos": 5.130291560557363e+17,
      "train_loss": 0.0,
      "train_runtime": 548.693,
      "train_samples_per_second": 12.065,
      "train_steps_per_second": 1.513
    }
  ],
  "logging_steps": 41,
  "max_steps": 830,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.130291560557363e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}