{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08138351983723296,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01627670396744659,
      "grad_norm": 2.6158394813537598,
      "learning_rate": 1e-05,
      "loss": 1.5912,
      "step": 1
    },
    {
      "epoch": 0.01627670396744659,
      "eval_loss": 2.214555263519287,
      "eval_runtime": 38.7687,
      "eval_samples_per_second": 2.683,
      "eval_steps_per_second": 1.341,
      "step": 1
    },
    {
      "epoch": 0.03255340793489318,
      "grad_norm": 2.710564374923706,
      "learning_rate": 2e-05,
      "loss": 1.7427,
      "step": 2
    },
    {
      "epoch": 0.03255340793489318,
      "eval_loss": 2.1650705337524414,
      "eval_runtime": 6.6771,
      "eval_samples_per_second": 15.576,
      "eval_steps_per_second": 7.788,
      "step": 2
    },
    {
      "epoch": 0.048830111902339775,
      "grad_norm": 3.012577772140503,
      "learning_rate": 3e-05,
      "loss": 1.764,
      "step": 3
    },
    {
      "epoch": 0.06510681586978637,
      "grad_norm": 2.4997215270996094,
      "learning_rate": 4e-05,
      "loss": 1.5808,
      "step": 4
    },
    {
      "epoch": 0.06510681586978637,
      "eval_loss": 2.0397536754608154,
      "eval_runtime": 6.7922,
      "eval_samples_per_second": 15.312,
      "eval_steps_per_second": 7.656,
      "step": 4
    },
    {
      "epoch": 0.08138351983723296,
      "grad_norm": 2.426286458969116,
      "learning_rate": 5e-05,
      "loss": 1.54,
      "step": 5
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1957911173529600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}