{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07332722273143905,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01466544454628781,
      "grad_norm": 11.944817543029785,
      "learning_rate": 1e-05,
      "loss": 10.4915,
      "step": 1
    },
    {
      "epoch": 0.01466544454628781,
      "eval_loss": 9.862154006958008,
      "eval_runtime": 101.4016,
      "eval_samples_per_second": 1.134,
      "eval_steps_per_second": 0.572,
      "step": 1
    },
    {
      "epoch": 0.02933088909257562,
      "grad_norm": 10.787004470825195,
      "learning_rate": 2e-05,
      "loss": 9.7621,
      "step": 2
    },
    {
      "epoch": 0.02933088909257562,
      "eval_loss": 9.550442695617676,
      "eval_runtime": 3.064,
      "eval_samples_per_second": 37.533,
      "eval_steps_per_second": 18.93,
      "step": 2
    },
    {
      "epoch": 0.043996333638863426,
      "grad_norm": 11.368886947631836,
      "learning_rate": 3e-05,
      "loss": 9.7941,
      "step": 3
    },
    {
      "epoch": 0.05866177818515124,
      "grad_norm": 11.855315208435059,
      "learning_rate": 4e-05,
      "loss": 9.6266,
      "step": 4
    },
    {
      "epoch": 0.05866177818515124,
      "eval_loss": 9.142111778259277,
      "eval_runtime": 2.9008,
      "eval_samples_per_second": 39.644,
      "eval_steps_per_second": 19.994,
      "step": 4
    },
    {
      "epoch": 0.07332722273143905,
      "grad_norm": 12.726892471313477,
      "learning_rate": 5e-05,
      "loss": 9.3341,
      "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": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}