trainer_state.json

{
  "best_metric": 0.9376,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0384/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": 1.7496143579483032,
      "learning_rate": 7.210810810810811e-05,
      "loss": 0.7592,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8778666666666667,
      "eval_loss": 0.3917834758758545,
      "eval_runtime": 5.5153,
      "eval_samples_per_second": 679.929,
      "eval_steps_per_second": 10.698,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5.4162162162162165e-05,
      "loss": 0.1992,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.884,
      "eval_loss": 0.4024467468261719,
      "eval_runtime": 5.7005,
      "eval_samples_per_second": 657.839,
      "eval_steps_per_second": 10.35,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04582163691520691,
      "learning_rate": 3.616216216216217e-05,
      "loss": 0.0735,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.32128778100013733,
      "eval_runtime": 5.9209,
      "eval_samples_per_second": 633.354,
      "eval_steps_per_second": 9.965,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.739596185274422e-05,
      "learning_rate": 1.8162162162162164e-05,
      "loss": 0.0199,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9288,
      "eval_loss": 0.3003125786781311,
      "eval_runtime": 6.1144,
      "eval_samples_per_second": 613.309,
      "eval_steps_per_second": 9.649,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3240170478820801,
      "learning_rate": 1.6216216216216218e-07,
      "loss": 0.0034,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9376,
      "eval_loss": 0.2510766386985779,
      "eval_runtime": 5.4969,
      "eval_samples_per_second": 682.208,
      "eval_steps_per_second": 10.733,
      "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
}