{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000498085483921178,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001245213709802945,
      "grad_norm": 5.8626837730407715,
      "learning_rate": 1e-05,
      "loss": 14.0429,
      "step": 1
    },
    {
      "epoch": 0.0001245213709802945,
      "eval_loss": 14.586152076721191,
      "eval_runtime": 759.1356,
      "eval_samples_per_second": 17.818,
      "eval_steps_per_second": 8.909,
      "step": 1
    },
    {
      "epoch": 0.000249042741960589,
      "grad_norm": 5.588228702545166,
      "learning_rate": 2e-05,
      "loss": 15.2054,
      "step": 2
    },
    {
      "epoch": 0.000249042741960589,
      "eval_loss": 14.379773139953613,
      "eval_runtime": 866.1188,
      "eval_samples_per_second": 15.617,
      "eval_steps_per_second": 7.808,
      "step": 2
    },
    {
      "epoch": 0.0003735641129408835,
      "grad_norm": 5.994800090789795,
      "learning_rate": 3e-05,
      "loss": 14.7771,
      "step": 3
    },
    {
      "epoch": 0.000498085483921178,
      "grad_norm": 5.892805576324463,
      "learning_rate": 4e-05,
      "loss": 14.1154,
      "step": 4
    },
    {
      "epoch": 0.000498085483921178,
      "eval_loss": 14.16848087310791,
      "eval_runtime": 503.4284,
      "eval_samples_per_second": 26.868,
      "eval_steps_per_second": 13.434,
      "step": 4
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4443721917530112.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}