{
  "best_global_step": 83,
  "best_metric": 0.3655608594417572,
  "best_model_checkpoint": "./math_ner_roberta/checkpoint-83",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 83,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6024096385542169,
      "grad_norm": 4.988605499267578,
      "learning_rate": 2.4096385542168674e-05,
      "loss": 1.4176820373535157,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.3655608594417572,
      "eval_runtime": 3.3968,
      "eval_samples_per_second": 68.595,
      "eval_steps_per_second": 4.416,
      "step": 83
    }
  ],
  "logging_steps": 50,
  "max_steps": 249,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 247812985784160.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}