trainer_state.json

{
  "best_metric": 0.8232,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0028/checkpoints/checkpoint-999",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 999,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.9586864709854126,
      "learning_rate": 0.0005,
      "loss": 0.778,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7904,
      "eval_loss": 0.7103226780891418,
      "eval_runtime": 13.3681,
      "eval_samples_per_second": 280.519,
      "eval_steps_per_second": 4.413,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.7540736198425293,
      "learning_rate": 0.0005,
      "loss": 0.4639,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8032,
      "eval_loss": 0.6773135662078857,
      "eval_runtime": 13.4464,
      "eval_samples_per_second": 278.885,
      "eval_steps_per_second": 4.388,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.676389217376709,
      "learning_rate": 0.0005,
      "loss": 0.3515,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8232,
      "eval_loss": 0.6174121499061584,
      "eval_runtime": 12.5591,
      "eval_samples_per_second": 298.589,
      "eval_steps_per_second": 4.698,
      "step": 999
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 4.94223961867776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}