trainer_state.json

{
  "best_metric": 0.9389333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0268/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": 6.806421756744385,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.5769,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9245333333333333,
      "eval_loss": 0.2438744306564331,
      "eval_runtime": 4.6881,
      "eval_samples_per_second": 799.903,
      "eval_steps_per_second": 12.585,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 26.585203170776367,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1373,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9186666666666666,
      "eval_loss": 0.28523796796798706,
      "eval_runtime": 4.0032,
      "eval_samples_per_second": 936.757,
      "eval_steps_per_second": 14.738,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.022158142179250717,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0675,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9344,
      "eval_loss": 0.23654623329639435,
      "eval_runtime": 4.0225,
      "eval_samples_per_second": 932.255,
      "eval_steps_per_second": 14.667,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.5271358489990234,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0314,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9333333333333333,
      "eval_loss": 0.2541388273239136,
      "eval_runtime": 3.913,
      "eval_samples_per_second": 958.348,
      "eval_steps_per_second": 15.078,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.19241099059581757,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0096,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9389333333333333,
      "eval_loss": 0.2539045512676239,
      "eval_runtime": 3.9152,
      "eval_samples_per_second": 957.793,
      "eval_steps_per_second": 15.069,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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
}