trainer_state.json

{
  "best_metric": 0.9576,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0109/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": 0.21340900659561157,
      "learning_rate": 4.752422169756048e-05,
      "loss": 0.7591,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9402666666666667,
      "eval_loss": 0.21474198997020721,
      "eval_runtime": 5.9781,
      "eval_samples_per_second": 627.294,
      "eval_steps_per_second": 9.869,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 4.0613573610928476e-05,
      "loss": 0.1123,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9504,
      "eval_loss": 0.1818617880344391,
      "eval_runtime": 6.2837,
      "eval_samples_per_second": 596.782,
      "eval_steps_per_second": 9.389,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.15936815738677979,
      "learning_rate": 3.059586713221479e-05,
      "loss": 0.0448,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9504,
      "eval_loss": 0.18304726481437683,
      "eval_runtime": 5.9381,
      "eval_samples_per_second": 631.516,
      "eval_steps_per_second": 9.936,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.028035372495651245,
      "learning_rate": 1.946983053915936e-05,
      "loss": 0.0161,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9522666666666667,
      "eval_loss": 0.18117138743400574,
      "eval_runtime": 6.7104,
      "eval_samples_per_second": 558.831,
      "eval_steps_per_second": 8.792,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.019218921661376953,
      "learning_rate": 9.43911183090096e-06,
      "loss": 0.0068,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9576,
      "eval_loss": 0.17116345465183258,
      "eval_runtime": 6.097,
      "eval_samples_per_second": 615.052,
      "eval_steps_per_second": 9.677,
      "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
}