{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009436187780136825,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003145395926712275,
      "grad_norm": 0.026611553505063057,
      "learning_rate": 2e-05,
      "loss": 10.3693,
      "step": 1
    },
    {
      "epoch": 0.0003145395926712275,
      "eval_loss": 10.374354362487793,
      "eval_runtime": 4.0911,
      "eval_samples_per_second": 327.292,
      "eval_steps_per_second": 163.768,
      "step": 1
    },
    {
      "epoch": 0.000629079185342455,
      "grad_norm": 0.026462724432349205,
      "learning_rate": 4e-05,
      "loss": 10.3736,
      "step": 2
    },
    {
      "epoch": 0.0009436187780136825,
      "grad_norm": 0.022061211988329887,
      "learning_rate": 6e-05,
      "loss": 10.3805,
      "step": 3
    },
    {
      "epoch": 0.0009436187780136825,
      "eval_loss": 10.374333381652832,
      "eval_runtime": 4.0971,
      "eval_samples_per_second": 326.815,
      "eval_steps_per_second": 163.53,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 48490905600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}