{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010375865736297373,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010375865736297373,
      "grad_norm": 1.1692744493484497,
      "learning_rate": 2e-05,
      "loss": 2.1367,
      "step": 1
    },
    {
      "epoch": 0.00010375865736297373,
      "eval_loss": 2.0775890350341797,
      "eval_runtime": 82.7906,
      "eval_samples_per_second": 49.015,
      "eval_steps_per_second": 24.508,
      "step": 1
    },
    {
      "epoch": 0.00020751731472594745,
      "grad_norm": 1.2241393327713013,
      "learning_rate": 4e-05,
      "loss": 2.0164,
      "step": 2
    },
    {
      "epoch": 0.00031127597208892115,
      "grad_norm": 1.2750980854034424,
      "learning_rate": 6e-05,
      "loss": 2.1287,
      "step": 3
    },
    {
      "epoch": 0.00031127597208892115,
      "eval_loss": 2.0742063522338867,
      "eval_runtime": 82.9457,
      "eval_samples_per_second": 48.924,
      "eval_steps_per_second": 24.462,
      "step": 3
    },
    {
      "epoch": 0.0004150346294518949,
      "grad_norm": 1.0608762502670288,
      "learning_rate": 8e-05,
      "loss": 1.9332,
      "step": 4
    },
    {
      "epoch": 0.0005187932868148687,
      "grad_norm": 1.3354967832565308,
      "learning_rate": 0.0001,
      "loss": 2.0546,
      "step": 5
    },
    {
      "epoch": 0.0006225519441778423,
      "grad_norm": 1.0933064222335815,
      "learning_rate": 0.00012,
      "loss": 2.1397,
      "step": 6
    },
    {
      "epoch": 0.0006225519441778423,
      "eval_loss": 2.0400583744049072,
      "eval_runtime": 81.8934,
      "eval_samples_per_second": 49.552,
      "eval_steps_per_second": 24.776,
      "step": 6
    },
    {
      "epoch": 0.000726310601540816,
      "grad_norm": 1.1842681169509888,
      "learning_rate": 0.00014,
      "loss": 1.9763,
      "step": 7
    },
    {
      "epoch": 0.0008300692589037898,
      "grad_norm": 1.0433040857315063,
      "learning_rate": 0.00016,
      "loss": 1.7398,
      "step": 8
    },
    {
      "epoch": 0.0009338279162667636,
      "grad_norm": 1.1187955141067505,
      "learning_rate": 0.00018,
      "loss": 1.8651,
      "step": 9
    },
    {
      "epoch": 0.0009338279162667636,
      "eval_loss": 1.977981448173523,
      "eval_runtime": 81.5656,
      "eval_samples_per_second": 49.751,
      "eval_steps_per_second": 24.876,
      "step": 9
    },
    {
      "epoch": 0.0010375865736297373,
      "grad_norm": 0.9800434112548828,
      "learning_rate": 0.0002,
      "loss": 1.7416,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 126879383420928.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}