{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011603115436494699,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00023206230872989397,
      "grad_norm": 8.18132495880127,
      "learning_rate": 1e-05,
      "loss": 7.4765,
      "step": 1
    },
    {
      "epoch": 0.00023206230872989397,
      "eval_loss": 7.735864639282227,
      "eval_runtime": 1058.1043,
      "eval_samples_per_second": 6.859,
      "eval_steps_per_second": 3.43,
      "step": 1
    },
    {
      "epoch": 0.00046412461745978795,
      "grad_norm": 11.143102645874023,
      "learning_rate": 2e-05,
      "loss": 7.6895,
      "step": 2
    },
    {
      "epoch": 0.00046412461745978795,
      "eval_loss": 7.484991073608398,
      "eval_runtime": 863.5604,
      "eval_samples_per_second": 8.405,
      "eval_steps_per_second": 4.202,
      "step": 2
    },
    {
      "epoch": 0.0006961869261896819,
      "grad_norm": 8.622457504272461,
      "learning_rate": 3e-05,
      "loss": 7.5496,
      "step": 3
    },
    {
      "epoch": 0.0009282492349195759,
      "grad_norm": 10.59476375579834,
      "learning_rate": 4e-05,
      "loss": 7.1284,
      "step": 4
    },
    {
      "epoch": 0.0009282492349195759,
      "eval_loss": 7.084515571594238,
      "eval_runtime": 782.5546,
      "eval_samples_per_second": 9.275,
      "eval_steps_per_second": 4.637,
      "step": 4
    },
    {
      "epoch": 0.0011603115436494699,
      "grad_norm": 8.7980318069458,
      "learning_rate": 5e-05,
      "loss": 6.8361,
      "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": 4207758664531968.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}