{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0472727272727274,
  "eval_steps": 4,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05818181818181818,
      "eval_loss": 0.9390416145324707,
      "eval_runtime": 1.7521,
      "eval_samples_per_second": 263.677,
      "eval_steps_per_second": 8.561,
      "step": 1
    },
    {
      "epoch": 0.23272727272727273,
      "eval_loss": 0.8904674053192139,
      "eval_runtime": 1.7546,
      "eval_samples_per_second": 263.311,
      "eval_steps_per_second": 8.549,
      "step": 4
    },
    {
      "epoch": 0.46545454545454545,
      "eval_loss": 0.8216497898101807,
      "eval_runtime": 1.7547,
      "eval_samples_per_second": 263.294,
      "eval_steps_per_second": 8.549,
      "step": 8
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.2278825044631958,
      "learning_rate": 5e-05,
      "loss": 0.8848,
      "step": 10
    },
    {
      "epoch": 0.6981818181818182,
      "eval_loss": 0.8009154796600342,
      "eval_runtime": 1.7539,
      "eval_samples_per_second": 263.42,
      "eval_steps_per_second": 8.553,
      "step": 12
    },
    {
      "epoch": 0.9309090909090909,
      "eval_loss": 0.7947056293487549,
      "eval_runtime": 1.7541,
      "eval_samples_per_second": 263.376,
      "eval_steps_per_second": 8.551,
      "step": 16
    }
  ],
  "logging_steps": 10,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.542168675693363e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}