{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.850775959161584e-05,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9502586530538612e-05,
      "grad_norm": 35.17543029785156,
      "learning_rate": 2e-05,
      "loss": 16.2937,
      "step": 1
    },
    {
      "epoch": 1.9502586530538612e-05,
      "eval_loss": 3.3730227947235107,
      "eval_runtime": 694.1993,
      "eval_samples_per_second": 31.101,
      "eval_steps_per_second": 15.55,
      "step": 1
    },
    {
      "epoch": 3.9005173061077225e-05,
      "grad_norm": 20.761104583740234,
      "learning_rate": 4e-05,
      "loss": 15.3756,
      "step": 2
    },
    {
      "epoch": 5.850775959161584e-05,
      "grad_norm": 26.16556739807129,
      "learning_rate": 6e-05,
      "loss": 15.1367,
      "step": 3
    },
    {
      "epoch": 5.850775959161584e-05,
      "eval_loss": 3.341076612472534,
      "eval_runtime": 693.8398,
      "eval_samples_per_second": 31.117,
      "eval_steps_per_second": 15.558,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 525800935784448.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}