trainer_state.json

{
  "best_metric": 0.9482666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0884/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.1511114537715912,
      "learning_rate": 8.145560752888351e-05,
      "loss": 0.6508,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9210666666666667,
      "eval_loss": 0.26366910338401794,
      "eval_runtime": 7.6279,
      "eval_samples_per_second": 491.614,
      "eval_steps_per_second": 7.735,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 11.72927474975586,
      "learning_rate": 5.898649216615971e-05,
      "loss": 0.1394,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9298666666666666,
      "eval_loss": 0.23582999408245087,
      "eval_runtime": 7.3906,
      "eval_samples_per_second": 507.399,
      "eval_steps_per_second": 7.983,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.06760562211275101,
      "learning_rate": 3.117501217934705e-05,
      "loss": 0.0574,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9410666666666667,
      "eval_loss": 0.21668076515197754,
      "eval_runtime": 7.4555,
      "eval_samples_per_second": 502.985,
      "eval_steps_per_second": 7.914,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.017382284626364708,
      "learning_rate": 8.644207645970472e-06,
      "loss": 0.0187,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9469333333333333,
      "eval_loss": 0.1911221295595169,
      "eval_runtime": 7.3333,
      "eval_samples_per_second": 511.368,
      "eval_steps_per_second": 8.046,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.06071799620985985,
      "learning_rate": 8.010389962842535e-11,
      "loss": 0.0075,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9482666666666667,
      "eval_loss": 0.18525433540344238,
      "eval_runtime": 7.4421,
      "eval_samples_per_second": 503.889,
      "eval_steps_per_second": 7.928,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}