trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 11.8125,
      "learning_rate": 1.568064746731156e-05,
      "loss": 1.402,
      "mean_token_accuracy": 0.6710869103670121,
      "num_tokens": 11266.0,
      "step": 10
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 8.5625,
      "learning_rate": 4.319352532688444e-06,
      "loss": 1.0703,
      "mean_token_accuracy": 0.7341621465981006,
      "num_tokens": 21735.0,
      "step": 20
    }
  ],
  "logging_steps": 10,
  "max_steps": 27,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1248400552329216.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}