{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003900774059852502,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009751935149631255,
      "grad_norm": 0.7910805344581604,
      "learning_rate": 1e-05,
      "loss": 2.5797,
      "step": 1
    },
    {
      "epoch": 0.0009751935149631255,
      "eval_loss": 2.691208839416504,
      "eval_runtime": 157.9126,
      "eval_samples_per_second": 10.936,
      "eval_steps_per_second": 5.471,
      "step": 1
    },
    {
      "epoch": 0.001950387029926251,
      "grad_norm": 0.7521000504493713,
      "learning_rate": 2e-05,
      "loss": 2.6656,
      "step": 2
    },
    {
      "epoch": 0.001950387029926251,
      "eval_loss": 2.6853694915771484,
      "eval_runtime": 41.0966,
      "eval_samples_per_second": 42.023,
      "eval_steps_per_second": 21.024,
      "step": 2
    },
    {
      "epoch": 0.0029255805448893763,
      "grad_norm": 0.5974100828170776,
      "learning_rate": 3e-05,
      "loss": 2.6326,
      "step": 3
    },
    {
      "epoch": 0.003900774059852502,
      "grad_norm": 0.5876912474632263,
      "learning_rate": 4e-05,
      "loss": 2.4947,
      "step": 4
    },
    {
      "epoch": 0.003900774059852502,
      "eval_loss": 2.677004098892212,
      "eval_runtime": 41.0202,
      "eval_samples_per_second": 42.101,
      "eval_steps_per_second": 21.063,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 396900100472832.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}