trainer_state.json

{
  "best_metric": 0.9328,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0442/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": Infinity,
      "learning_rate": 8.006006006006006e-05,
      "loss": 0.6562,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.3129458427429199,
      "eval_runtime": 6.9119,
      "eval_samples_per_second": 542.544,
      "eval_steps_per_second": 8.536,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5717719793319702,
      "learning_rate": 6.0060060060060066e-05,
      "loss": 0.1274,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9168,
      "eval_loss": 0.2714840769767761,
      "eval_runtime": 6.5674,
      "eval_samples_per_second": 570.999,
      "eval_steps_per_second": 8.984,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.03908513858914375,
      "learning_rate": 4.006006006006006e-05,
      "loss": 0.0395,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9264,
      "eval_loss": 0.2874329388141632,
      "eval_runtime": 6.3847,
      "eval_samples_per_second": 587.342,
      "eval_steps_per_second": 9.241,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.020474184304475784,
      "learning_rate": 2.006006006006006e-05,
      "loss": 0.0117,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9290666666666667,
      "eval_loss": 0.2741330862045288,
      "eval_runtime": 6.5022,
      "eval_samples_per_second": 576.731,
      "eval_steps_per_second": 9.074,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0824427604675293,
      "learning_rate": 6.006006006006006e-08,
      "loss": 0.0048,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9328,
      "eval_loss": 0.2700689733028412,
      "eval_runtime": 6.6382,
      "eval_samples_per_second": 564.912,
      "eval_steps_per_second": 8.888,
      "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
}