{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004672214921886407,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.344429843772814e-05,
      "grad_norm": 1.0654993057250977,
      "learning_rate": 1e-05,
      "loss": 1.4941,
      "step": 1
    },
    {
      "epoch": 9.344429843772814e-05,
      "eval_loss": 1.4126410484313965,
      "eval_runtime": 891.5398,
      "eval_samples_per_second": 20.217,
      "eval_steps_per_second": 10.108,
      "step": 1
    },
    {
      "epoch": 0.00018688859687545628,
      "grad_norm": 0.9405075311660767,
      "learning_rate": 2e-05,
      "loss": 1.4641,
      "step": 2
    },
    {
      "epoch": 0.00018688859687545628,
      "eval_loss": 1.40297532081604,
      "eval_runtime": 1089.9315,
      "eval_samples_per_second": 16.537,
      "eval_steps_per_second": 8.268,
      "step": 2
    },
    {
      "epoch": 0.00028033289531318443,
      "grad_norm": 0.8317659497261047,
      "learning_rate": 3e-05,
      "loss": 1.1806,
      "step": 3
    },
    {
      "epoch": 0.00037377719375091255,
      "grad_norm": 0.7077718377113342,
      "learning_rate": 4e-05,
      "loss": 1.4649,
      "step": 4
    },
    {
      "epoch": 0.00037377719375091255,
      "eval_loss": 1.3796457052230835,
      "eval_runtime": 1040.0168,
      "eval_samples_per_second": 17.33,
      "eval_steps_per_second": 8.665,
      "step": 4
    },
    {
      "epoch": 0.0004672214921886407,
      "grad_norm": 0.776381254196167,
      "learning_rate": 5e-05,
      "loss": 1.4353,
      "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": 3822182832537600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}