trainer_state.json

{
  "best_metric": 0.8432,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0174/checkpoints/checkpoint-666",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 666,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 21.14940071105957,
      "learning_rate": 0.0001,
      "loss": 0.9665,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7909333333333334,
      "eval_loss": 0.6880429983139038,
      "eval_runtime": 6.3326,
      "eval_samples_per_second": 592.169,
      "eval_steps_per_second": 9.317,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.4413,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8432,
      "eval_loss": 0.5381319522857666,
      "eval_runtime": 6.8368,
      "eval_samples_per_second": 548.504,
      "eval_steps_per_second": 8.63,
      "step": 666
    }
  ],
  "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": 3.29482641245184e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}