trainer_state.json

{
  "best_metric": 0.9149333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0146/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "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": 0.0002501501501501501,
      "loss": 0.6687,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8504,
      "eval_loss": 0.4824514389038086,
      "eval_runtime": 6.9016,
      "eval_samples_per_second": 543.353,
      "eval_steps_per_second": 8.549,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5658709406852722,
      "learning_rate": 0.00020015015015015014,
      "loss": 0.2916,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8738666666666667,
      "eval_loss": 0.433513343334198,
      "eval_runtime": 6.5327,
      "eval_samples_per_second": 574.038,
      "eval_steps_per_second": 9.032,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.542783260345459,
      "learning_rate": 0.00015015015015015014,
      "loss": 0.1612,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8853333333333333,
      "eval_loss": 0.3978537619113922,
      "eval_runtime": 6.1951,
      "eval_samples_per_second": 605.317,
      "eval_steps_per_second": 9.524,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.10454828292131424,
      "learning_rate": 0.00010015015015015015,
      "loss": 0.0681,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8917333333333334,
      "eval_loss": 0.3912554681301117,
      "eval_runtime": 6.1109,
      "eval_samples_per_second": 613.659,
      "eval_steps_per_second": 9.655,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.01646995171904564,
      "learning_rate": 5.0150150150150145e-05,
      "loss": 0.0263,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9005333333333333,
      "eval_loss": 0.38224858045578003,
      "eval_runtime": 7.4299,
      "eval_samples_per_second": 504.72,
      "eval_steps_per_second": 7.941,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.007550355978310108,
      "learning_rate": 1.5015015015015014e-07,
      "loss": 0.0061,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9149333333333334,
      "eval_loss": 0.3405226469039917,
      "eval_runtime": 6.5567,
      "eval_samples_per_second": 571.93,
      "eval_steps_per_second": 8.998,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}