{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.564826700898588,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5134788189987163,
      "grad_norm": NaN,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_runtime": 11.7794,
      "eval_samples_per_second": 42.447,
      "eval_steps_per_second": 2.717,
      "step": 195
    },
    {
      "epoch": 1.0256739409499358,
      "grad_norm": NaN,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 1.539152759948652,
      "grad_norm": NaN,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 2.0,
      "eval_loss": NaN,
      "eval_runtime": 11.7849,
      "eval_samples_per_second": 42.427,
      "eval_steps_per_second": 2.715,
      "step": 390
    },
    {
      "epoch": 2.0513478818998716,
      "grad_norm": NaN,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 2.564826700898588,
      "grad_norm": NaN,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 970,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5939653005803520.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}