{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011291460832745237,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022582921665490474,
      "grad_norm": Infinity,
      "learning_rate": 1e-05,
      "loss": 34.7305,
      "step": 1
    },
    {
      "epoch": 0.0022582921665490474,
      "eval_loss": 2.1850547790527344,
      "eval_runtime": 60.1674,
      "eval_samples_per_second": 12.399,
      "eval_steps_per_second": 6.199,
      "step": 1
    },
    {
      "epoch": 0.004516584333098095,
      "grad_norm": 15.04525375366211,
      "learning_rate": 2e-05,
      "loss": 38.2578,
      "step": 2
    },
    {
      "epoch": 0.004516584333098095,
      "eval_loss": 2.17636775970459,
      "eval_runtime": 15.3363,
      "eval_samples_per_second": 48.643,
      "eval_steps_per_second": 24.321,
      "step": 2
    },
    {
      "epoch": 0.006774876499647142,
      "grad_norm": 14.231776237487793,
      "learning_rate": 3e-05,
      "loss": 35.4102,
      "step": 3
    },
    {
      "epoch": 0.00903316866619619,
      "grad_norm": 15.738994598388672,
      "learning_rate": 4e-05,
      "loss": 34.0078,
      "step": 4
    },
    {
      "epoch": 0.00903316866619619,
      "eval_loss": 2.160700798034668,
      "eval_runtime": 15.3137,
      "eval_samples_per_second": 48.714,
      "eval_steps_per_second": 24.357,
      "step": 4
    },
    {
      "epoch": 0.011291460832745237,
      "grad_norm": 14.535213470458984,
      "learning_rate": 5e-05,
      "loss": 34.8828,
      "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": 174536943206400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}