trainer_state.json

{
  "best_metric": 0.3704,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0603/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002803729487402998,
      "loss": 3.4978,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17813333333333334,
      "eval_loss": 3.1269896030426025,
      "eval_runtime": 12.6746,
      "eval_samples_per_second": 295.868,
      "eval_steps_per_second": 4.655,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.23625373840332,
      "learning_rate": 0.00022581553795296964,
      "loss": 2.9932,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2312,
      "eval_loss": 2.9332687854766846,
      "eval_runtime": 11.9066,
      "eval_samples_per_second": 314.95,
      "eval_steps_per_second": 4.955,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 25.06657600402832,
      "learning_rate": 0.00015094341499741014,
      "loss": 2.7238,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.27786666666666665,
      "eval_loss": 2.6953978538513184,
      "eval_runtime": 11.9325,
      "eval_samples_per_second": 314.268,
      "eval_steps_per_second": 4.944,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 63.01470184326172,
      "learning_rate": 7.58185047551672e-05,
      "loss": 2.4349,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.336,
      "eval_loss": 2.4913697242736816,
      "eval_runtime": 11.6879,
      "eval_samples_per_second": 320.844,
      "eval_steps_per_second": 5.048,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 59.03237533569336,
      "learning_rate": 2.0570466257110352e-05,
      "loss": 2.0858,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3672,
      "eval_loss": 2.3750057220458984,
      "eval_runtime": 11.674,
      "eval_samples_per_second": 321.227,
      "eval_steps_per_second": 5.054,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 43.62342834472656,
      "learning_rate": 2.9668021975126634e-09,
      "loss": 1.7455,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3704,
      "eval_loss": 2.4407315254211426,
      "eval_runtime": 12.1037,
      "eval_samples_per_second": 309.822,
      "eval_steps_per_second": 4.875,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}