{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "grad_norm": 3.8262860774993896,
      "learning_rate": 0.003,
      "loss": 0.7664,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.633,
      "eval_loss": 0.6625605225563049,
      "eval_runtime": 8.1161,
      "eval_samples_per_second": 2464.23,
      "eval_steps_per_second": 38.565,
      "step": 625
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.6861379146575928,
      "learning_rate": 0.001,
      "loss": 0.7026,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.633,
      "eval_loss": 0.6644296646118164,
      "eval_runtime": 7.1772,
      "eval_samples_per_second": 2786.585,
      "eval_steps_per_second": 43.61,
      "step": 1250
    },
    {
      "epoch": 2.0,
      "step": 1250,
      "total_flos": 1.0524442757169152e+16,
      "train_loss": 0.725837451171875,
      "train_runtime": 526.7042,
      "train_samples_per_second": 607.552,
      "train_steps_per_second": 2.373
    }
  ],
  "logging_steps": 500,
  "max_steps": 1250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0524442757169152e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}