trainer_state.json

{
  "best_metric": 0.8970666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0171/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": 2.5523481369018555,
      "learning_rate": 3e-05,
      "loss": 0.7822,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8842666666666666,
      "eval_loss": 0.38341566920280457,
      "eval_runtime": 11.9614,
      "eval_samples_per_second": 313.509,
      "eval_steps_per_second": 4.933,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.058368444442749,
      "learning_rate": 3e-05,
      "loss": 0.1659,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8784,
      "eval_loss": 0.41350528597831726,
      "eval_runtime": 11.7401,
      "eval_samples_per_second": 319.417,
      "eval_steps_per_second": 5.026,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.0725,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8970666666666667,
      "eval_loss": 0.3737628757953644,
      "eval_runtime": 12.3966,
      "eval_samples_per_second": 302.502,
      "eval_steps_per_second": 4.759,
      "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
}