{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9999677207630812,
  "eval_steps": 5000,
  "global_step": 11617,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43038982558452316,
      "grad_norm": 0.08002949506044388,
      "learning_rate": 0.002435250975888257,
      "loss": 3.9051,
      "step": 5000
    },
    {
      "epoch": 0.43038982558452316,
      "eval_loss": 3.567183256149292,
      "eval_runtime": 2597.1809,
      "eval_samples_per_second": 1627.689,
      "eval_steps_per_second": 6.358,
      "step": 5000
    },
    {
      "epoch": 0.8607796511690463,
      "grad_norm": 0.08467405289411545,
      "learning_rate": 0.0001985225254765198,
      "loss": 3.4025,
      "step": 10000
    },
    {
      "epoch": 0.8607796511690463,
      "eval_loss": 3.306668519973755,
      "eval_runtime": 2590.715,
      "eval_samples_per_second": 1631.751,
      "eval_steps_per_second": 6.374,
      "step": 10000
    }
  ],
  "logging_steps": 5000,
  "max_steps": 11617,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.795854363058504e+18,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}