{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00023879646581230599,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_loss": 2.839312791824341,
      "eval_runtime": 118.2817,
      "eval_samples_per_second": 44.724,
      "eval_steps_per_second": 22.362,
      "step": 0
    },
    {
      "epoch": 7.959882193743533e-05,
      "grad_norm": 1.007415533065796,
      "learning_rate": 0.0,
      "loss": 2.6187,
      "step": 1
    },
    {
      "epoch": 0.00015919764387487066,
      "grad_norm": 0.9872703552246094,
      "learning_rate": 2e-05,
      "loss": 2.7515,
      "step": 2
    },
    {
      "epoch": 0.00023879646581230599,
      "grad_norm": 1.001963496208191,
      "learning_rate": 4e-05,
      "loss": 2.7804,
      "step": 3
    },
    {
      "epoch": 0.00023879646581230599,
      "eval_loss": 2.833432912826538,
      "eval_runtime": 113.4791,
      "eval_samples_per_second": 46.617,
      "eval_steps_per_second": 23.308,
      "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": 72163654631424.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}