trainer_state.json

{
  "best_metric": 0.19681768119335175,
  "best_model_checkpoint": "my_awesome_model/checkpoint-150",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.875,
      "eval_loss": 0.32908448576927185,
      "eval_runtime": 2.4393,
      "eval_samples_per_second": 81.991,
      "eval_steps_per_second": 5.329,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.91,
      "eval_loss": 0.2244468629360199,
      "eval_runtime": 2.4412,
      "eval_samples_per_second": 81.927,
      "eval_steps_per_second": 5.325,
      "step": 100
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.93,
      "eval_loss": 0.19681768119335175,
      "eval_runtime": 2.4185,
      "eval_samples_per_second": 82.697,
      "eval_steps_per_second": 5.375,
      "step": 150
    }
  ],
  "logging_steps": 500,
  "max_steps": 150,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 312780365864064.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}