trainer_state.json

{
  "best_metric": 0.28933333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0757/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": 0.0005,
      "loss": 3.4461,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17333333333333334,
      "eval_loss": 3.1200506687164307,
      "eval_runtime": 12.638,
      "eval_samples_per_second": 296.723,
      "eval_steps_per_second": 4.668,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 15.900571823120117,
      "learning_rate": 0.0005,
      "loss": 3.008,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.20853333333333332,
      "eval_loss": 2.989238977432251,
      "eval_runtime": 12.6313,
      "eval_samples_per_second": 296.881,
      "eval_steps_per_second": 4.671,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.925060272216797,
      "learning_rate": 0.0005,
      "loss": 2.8718,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2384,
      "eval_loss": 2.8612849712371826,
      "eval_runtime": 12.2013,
      "eval_samples_per_second": 307.344,
      "eval_steps_per_second": 4.836,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.509943962097168,
      "learning_rate": 0.0005,
      "loss": 2.7293,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.248,
      "eval_loss": 2.7808120250701904,
      "eval_runtime": 12.4141,
      "eval_samples_per_second": 302.075,
      "eval_steps_per_second": 4.753,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 17.841997146606445,
      "learning_rate": 0.0005,
      "loss": 2.6341,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.27066666666666667,
      "eval_loss": 2.6971516609191895,
      "eval_runtime": 12.3956,
      "eval_samples_per_second": 302.526,
      "eval_steps_per_second": 4.76,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 14.9351167678833,
      "learning_rate": 0.0005,
      "loss": 2.563,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.28933333333333333,
      "eval_loss": 2.6386373043060303,
      "eval_runtime": 12.5707,
      "eval_samples_per_second": 298.314,
      "eval_steps_per_second": 4.693,
      "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
}