trainer_state.json

{
  "best_metric": 0.9514666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0745/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": 0.41207146644592285,
      "learning_rate": 5e-05,
      "loss": 0.7857,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.944,
      "eval_loss": 0.21642445027828217,
      "eval_runtime": 13.822,
      "eval_samples_per_second": 271.307,
      "eval_steps_per_second": 4.269,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5703745484352112,
      "learning_rate": 5e-05,
      "loss": 0.1084,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9501333333333334,
      "eval_loss": 0.1750032603740692,
      "eval_runtime": 11.2054,
      "eval_samples_per_second": 334.659,
      "eval_steps_per_second": 5.265,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.4155433475971222,
      "learning_rate": 5e-05,
      "loss": 0.0508,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9490666666666666,
      "eval_loss": 0.2040877342224121,
      "eval_runtime": 11.6879,
      "eval_samples_per_second": 320.845,
      "eval_steps_per_second": 5.048,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.016502993181347847,
      "learning_rate": 5e-05,
      "loss": 0.0322,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9453333333333334,
      "eval_loss": 0.22366292774677277,
      "eval_runtime": 11.122,
      "eval_samples_per_second": 337.17,
      "eval_steps_per_second": 5.305,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.1915009319782257,
      "learning_rate": 5e-05,
      "loss": 0.0263,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9514666666666667,
      "eval_loss": 0.21106629073619843,
      "eval_runtime": 11.7765,
      "eval_samples_per_second": 318.43,
      "eval_steps_per_second": 5.01,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}