trainer_state.json

{
  "best_metric": 0.9176,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0574/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": 0.6751790642738342,
      "learning_rate": 2.401801801801802e-05,
      "loss": 0.8403,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8682666666666666,
      "eval_loss": 0.41923511028289795,
      "eval_runtime": 5.7542,
      "eval_samples_per_second": 651.693,
      "eval_steps_per_second": 10.253,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5900927186012268,
      "learning_rate": 1.801801801801802e-05,
      "loss": 0.2181,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8874666666666666,
      "eval_loss": 0.3511807322502136,
      "eval_runtime": 6.8887,
      "eval_samples_per_second": 544.371,
      "eval_steps_per_second": 8.565,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 14.711504936218262,
      "learning_rate": 1.2018018018018019e-05,
      "loss": 0.0887,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9,
      "eval_loss": 0.31943976879119873,
      "eval_runtime": 5.7168,
      "eval_samples_per_second": 655.958,
      "eval_steps_per_second": 10.32,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.6358219385147095,
      "learning_rate": 6.018018018018018e-06,
      "loss": 0.0309,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9141333333333334,
      "eval_loss": 0.3065057694911957,
      "eval_runtime": 5.6578,
      "eval_samples_per_second": 662.798,
      "eval_steps_per_second": 10.428,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.3897149562835693,
      "learning_rate": 1.8018018018018017e-08,
      "loss": 0.0086,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9176,
      "eval_loss": 0.30614718794822693,
      "eval_runtime": 5.7061,
      "eval_samples_per_second": 657.195,
      "eval_steps_per_second": 10.34,
      "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
}