{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004280066127021663,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.560132254043325e-05,
      "grad_norm": 4.492642402648926,
      "learning_rate": 1e-05,
      "loss": 3.651,
      "step": 1
    },
    {
      "epoch": 8.560132254043325e-05,
      "eval_loss": 3.5893633365631104,
      "eval_runtime": 701.2123,
      "eval_samples_per_second": 28.06,
      "eval_steps_per_second": 14.03,
      "step": 1
    },
    {
      "epoch": 0.0001712026450808665,
      "grad_norm": 4.441797256469727,
      "learning_rate": 2e-05,
      "loss": 3.4923,
      "step": 2
    },
    {
      "epoch": 0.0001712026450808665,
      "eval_loss": 3.4451215267181396,
      "eval_runtime": 702.8867,
      "eval_samples_per_second": 27.993,
      "eval_steps_per_second": 13.997,
      "step": 2
    },
    {
      "epoch": 0.00025680396762129976,
      "grad_norm": 3.9653892517089844,
      "learning_rate": 3e-05,
      "loss": 3.3246,
      "step": 3
    },
    {
      "epoch": 0.000342405290161733,
      "grad_norm": 4.707035064697266,
      "learning_rate": 4e-05,
      "loss": 3.1096,
      "step": 4
    },
    {
      "epoch": 0.000342405290161733,
      "eval_loss": 3.2205007076263428,
      "eval_runtime": 698.1994,
      "eval_samples_per_second": 28.181,
      "eval_steps_per_second": 14.091,
      "step": 4
    },
    {
      "epoch": 0.0004280066127021663,
      "grad_norm": 3.9862098693847656,
      "learning_rate": 5e-05,
      "loss": 3.0265,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3699192920801280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}