{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0032213529682468,
  "eval_steps": 28,
  "global_step": 136,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007363092498849517,
      "eval_loss": NaN,
      "eval_runtime": 19.7093,
      "eval_samples_per_second": 11.619,
      "eval_steps_per_second": 5.835,
      "step": 1
    },
    {
      "epoch": 0.20616658996778647,
      "eval_loss": NaN,
      "eval_runtime": 18.676,
      "eval_samples_per_second": 12.262,
      "eval_steps_per_second": 6.158,
      "step": 28
    },
    {
      "epoch": 0.29452369995398064,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.41233317993557295,
      "eval_loss": NaN,
      "eval_runtime": 18.631,
      "eval_samples_per_second": 12.291,
      "eval_steps_per_second": 6.173,
      "step": 56
    },
    {
      "epoch": 0.5890473999079613,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.6184997699033594,
      "eval_loss": NaN,
      "eval_runtime": 18.6277,
      "eval_samples_per_second": 12.294,
      "eval_steps_per_second": 6.174,
      "step": 84
    },
    {
      "epoch": 0.8246663598711459,
      "eval_loss": NaN,
      "eval_runtime": 18.7735,
      "eval_samples_per_second": 12.198,
      "eval_steps_per_second": 6.126,
      "step": 112
    },
    {
      "epoch": 0.883571099861942,
      "grad_norm": NaN,
      "learning_rate": 3.7651019814126656e-06,
      "loss": 0.0,
      "step": 120
    }
  ],
  "logging_steps": 40,
  "max_steps": 136,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 28,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.479940090730906e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}