{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006521739130434782,
  "eval_steps": 1,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002173913043478261,
      "grad_norm": 3.4586541652679443,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 3.1186,
      "step": 1
    },
    {
      "epoch": 0.002173913043478261,
      "eval_loss": 2.910125255584717,
      "eval_runtime": 9.3365,
      "eval_samples_per_second": 51.411,
      "eval_steps_per_second": 1.607,
      "step": 1
    },
    {
      "epoch": 0.004347826086956522,
      "grad_norm": 3.0273189544677734,
      "learning_rate": 4.9e-05,
      "loss": 2.9823,
      "step": 2
    },
    {
      "epoch": 0.004347826086956522,
      "eval_loss": 2.720604658126831,
      "eval_runtime": 9.3759,
      "eval_samples_per_second": 51.195,
      "eval_steps_per_second": 1.6,
      "step": 2
    },
    {
      "epoch": 0.006521739130434782,
      "grad_norm": 2.8461098670959473,
      "learning_rate": 4.85e-05,
      "loss": 2.743,
      "step": 3
    },
    {
      "epoch": 0.006521739130434782,
      "eval_loss": 2.527026414871216,
      "eval_runtime": 9.4179,
      "eval_samples_per_second": 50.967,
      "eval_steps_per_second": 1.593,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 556817978228736.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}