{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016406890894175553,
  "eval_steps": 10,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008203445447087777,
      "grad_norm": 0.23545275628566742,
      "learning_rate": 0.00013420201433256689,
      "loss": 0.6594,
      "step": 10
    },
    {
      "epoch": 0.008203445447087777,
      "eval_loss": 0.48451828956604004,
      "eval_runtime": 19.7025,
      "eval_samples_per_second": 50.755,
      "eval_steps_per_second": 0.812,
      "step": 10
    },
    {
      "epoch": 0.016406890894175553,
      "grad_norm": 0.146519273519516,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 0.4624,
      "step": 20
    },
    {
      "epoch": 0.016406890894175553,
      "eval_loss": 0.44331175088882446,
      "eval_runtime": 19.2624,
      "eval_samples_per_second": 51.915,
      "eval_steps_per_second": 0.831,
      "step": 20
    },
    {
      "epoch": 0.016406890894175553,
      "step": 20,
      "total_flos": 1.30070668640256e+16,
      "train_loss": 0.5609269142150879,
      "train_runtime": 110.7,
      "train_samples_per_second": 5.781,
      "train_steps_per_second": 0.181
    }
  ],
  "logging_steps": 10,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.30070668640256e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}