{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0038554216867469878,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007710843373493976,
      "grad_norm": 4.906417369842529,
      "learning_rate": 1e-05,
      "loss": 177.625,
      "step": 1
    },
    {
      "epoch": 0.0007710843373493976,
      "eval_loss": 11.108753204345703,
      "eval_runtime": 27.3832,
      "eval_samples_per_second": 79.793,
      "eval_steps_per_second": 39.915,
      "step": 1
    },
    {
      "epoch": 0.001542168674698795,
      "grad_norm": 4.9877400398254395,
      "learning_rate": 2e-05,
      "loss": 177.6875,
      "step": 2
    },
    {
      "epoch": 0.001542168674698795,
      "eval_loss": 11.108695983886719,
      "eval_runtime": 10.2106,
      "eval_samples_per_second": 213.994,
      "eval_steps_per_second": 107.046,
      "step": 2
    },
    {
      "epoch": 0.0023132530120481927,
      "grad_norm": 4.781337738037109,
      "learning_rate": 3e-05,
      "loss": 177.6875,
      "step": 3
    },
    {
      "epoch": 0.00308433734939759,
      "grad_norm": 5.0924811363220215,
      "learning_rate": 4e-05,
      "loss": 177.6875,
      "step": 4
    },
    {
      "epoch": 0.00308433734939759,
      "eval_loss": 11.108638763427734,
      "eval_runtime": 10.4129,
      "eval_samples_per_second": 209.835,
      "eval_steps_per_second": 104.966,
      "step": 4
    },
    {
      "epoch": 0.0038554216867469878,
      "grad_norm": 5.005702018737793,
      "learning_rate": 5e-05,
      "loss": 177.6875,
      "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": 192896040960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}