trainer_state.json

{
  "best_metric": 0.9322666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0874/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": 11.130936622619629,
      "learning_rate": 7e-05,
      "loss": 0.7664,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9122666666666667,
      "eval_loss": 0.2931091785430908,
      "eval_runtime": 6.8654,
      "eval_samples_per_second": 546.22,
      "eval_steps_per_second": 8.594,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.3826475143432617,
      "learning_rate": 7e-05,
      "loss": 0.1705,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.2511810064315796,
      "eval_runtime": 6.5271,
      "eval_samples_per_second": 574.525,
      "eval_steps_per_second": 9.039,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.028629181906580925,
      "learning_rate": 7e-05,
      "loss": 0.0934,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9197333333333333,
      "eval_loss": 0.3059036433696747,
      "eval_runtime": 6.6237,
      "eval_samples_per_second": 566.152,
      "eval_steps_per_second": 8.907,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.232845306396484,
      "learning_rate": 7e-05,
      "loss": 0.0575,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9248,
      "eval_loss": 0.284106969833374,
      "eval_runtime": 6.5764,
      "eval_samples_per_second": 570.218,
      "eval_steps_per_second": 8.971,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.010161438956856728,
      "learning_rate": 7e-05,
      "loss": 0.0443,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9322666666666667,
      "eval_loss": 0.26974621415138245,
      "eval_runtime": 6.6277,
      "eval_samples_per_second": 565.809,
      "eval_steps_per_second": 8.902,
      "step": 1665
    }
  ],
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}