{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.5,
      "grad_norm": 3.227240562438965,
      "learning_rate": 9.042397785550405e-06,
      "loss": 1.9625,
      "step": 100
    },
    {
      "epoch": 2.5,
      "eval_loss": 1.8376805782318115,
      "eval_runtime": 533.9255,
      "eval_samples_per_second": 0.101,
      "eval_steps_per_second": 0.101,
      "step": 100
    },
    {
      "epoch": 3.0,
      "step": 120,
      "total_flos": 994098989383680.0,
      "train_loss": 1.8405975977579752,
      "train_runtime": 23722.9763,
      "train_samples_per_second": 0.04,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 100,
  "max_steps": 120,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 994098989383680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}