{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006318416604798837,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012636833209597674,
      "grad_norm": 1.466745138168335,
      "learning_rate": 1e-05,
      "loss": 2.9451,
      "step": 1
    },
    {
      "epoch": 0.00012636833209597674,
      "eval_loss": 3.341721773147583,
      "eval_runtime": 655.9504,
      "eval_samples_per_second": 20.319,
      "eval_steps_per_second": 10.159,
      "step": 1
    },
    {
      "epoch": 0.0002527366641919535,
      "grad_norm": 1.2805771827697754,
      "learning_rate": 2e-05,
      "loss": 2.782,
      "step": 2
    },
    {
      "epoch": 0.0002527366641919535,
      "eval_loss": 3.321028709411621,
      "eval_runtime": 430.9727,
      "eval_samples_per_second": 30.925,
      "eval_steps_per_second": 15.463,
      "step": 2
    },
    {
      "epoch": 0.00037910499628793026,
      "grad_norm": 1.2433732748031616,
      "learning_rate": 3e-05,
      "loss": 2.7993,
      "step": 3
    },
    {
      "epoch": 0.000505473328383907,
      "grad_norm": 1.4798873662948608,
      "learning_rate": 4e-05,
      "loss": 3.0205,
      "step": 4
    },
    {
      "epoch": 0.000505473328383907,
      "eval_loss": 3.204335927963257,
      "eval_runtime": 430.8181,
      "eval_samples_per_second": 30.936,
      "eval_steps_per_second": 15.468,
      "step": 4
    },
    {
      "epoch": 0.0006318416604798837,
      "grad_norm": 1.3459527492523193,
      "learning_rate": 5e-05,
      "loss": 2.8252,
      "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": 4412646277251072.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}