{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0576,
  "eval_steps": 9,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0064,
      "eval_loss": 2.962462902069092,
      "eval_runtime": 14.3886,
      "eval_samples_per_second": 73.113,
      "eval_steps_per_second": 2.293,
      "step": 1
    },
    {
      "epoch": 0.0192,
      "grad_norm": 2.497889995574951,
      "learning_rate": 3e-05,
      "loss": 2.9509,
      "step": 3
    },
    {
      "epoch": 0.0384,
      "grad_norm": 1.9927830696105957,
      "learning_rate": 6e-05,
      "loss": 2.9487,
      "step": 6
    },
    {
      "epoch": 0.0576,
      "grad_norm": 1.110428810119629,
      "learning_rate": 9e-05,
      "loss": 2.6523,
      "step": 9
    },
    {
      "epoch": 0.0576,
      "eval_loss": 2.410982847213745,
      "eval_runtime": 4.6211,
      "eval_samples_per_second": 227.65,
      "eval_steps_per_second": 7.141,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4576824797364224e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}