checkpoint-1407/trainer_state.json

{
  "best_metric": 2.4606270790100098,
  "best_model_checkpoint": "cat_breed_image_detection/checkpoint-1407",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1407,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.35536602700781805,
      "grad_norm": 3.2397959232330322,
      "learning_rate": 2.0051584377302874e-07,
      "loss": 2.4446,
      "step": 500
    },
    {
      "epoch": 0.7107320540156361,
      "grad_norm": 2.8648812770843506,
      "learning_rate": 8.997789240972734e-08,
      "loss": 2.4403,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4256333333333333,
      "eval_loss": 2.4606270790100098,
      "eval_runtime": 705.6918,
      "eval_samples_per_second": 85.023,
      "eval_steps_per_second": 2.657,
      "step": 1407
    }
  ],
  "logging_steps": 500,
  "max_steps": 1407,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 6.97715444514816e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}