{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008428238814146799,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016856477628293597,
      "grad_norm": 0.2820028066635132,
      "learning_rate": 1e-05,
      "loss": 0.5589,
      "step": 1
    },
    {
      "epoch": 0.00016856477628293597,
      "eval_loss": 0.6286614537239075,
      "eval_runtime": 1376.361,
      "eval_samples_per_second": 7.26,
      "eval_steps_per_second": 3.63,
      "step": 1
    },
    {
      "epoch": 0.00033712955256587194,
      "grad_norm": 0.2809765934944153,
      "learning_rate": 2e-05,
      "loss": 0.5714,
      "step": 2
    },
    {
      "epoch": 0.00033712955256587194,
      "eval_loss": 0.6214396357536316,
      "eval_runtime": 1313.3406,
      "eval_samples_per_second": 7.608,
      "eval_steps_per_second": 3.804,
      "step": 2
    },
    {
      "epoch": 0.0005056943288488079,
      "grad_norm": 0.28038594126701355,
      "learning_rate": 3e-05,
      "loss": 0.5803,
      "step": 3
    },
    {
      "epoch": 0.0006742591051317439,
      "grad_norm": 0.2775951027870178,
      "learning_rate": 4e-05,
      "loss": 0.6471,
      "step": 4
    },
    {
      "epoch": 0.0006742591051317439,
      "eval_loss": 0.6124629378318787,
      "eval_runtime": 1483.3986,
      "eval_samples_per_second": 6.736,
      "eval_steps_per_second": 3.368,
      "step": 4
    },
    {
      "epoch": 0.0008428238814146799,
      "grad_norm": 0.26057255268096924,
      "learning_rate": 5e-05,
      "loss": 0.5364,
      "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": 5132540788604928.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}