trainer_state.json

{
  "best_metric": 0.9584,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0633/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": 1.3899073600769043,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.7704,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9453333333333334,
      "eval_loss": 0.21124900877475739,
      "eval_runtime": 10.1167,
      "eval_samples_per_second": 370.673,
      "eval_steps_per_second": 5.832,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.13692191243171692,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.0949,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9498666666666666,
      "eval_loss": 0.1796284317970276,
      "eval_runtime": 10.313,
      "eval_samples_per_second": 363.618,
      "eval_steps_per_second": 5.721,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04422168806195259,
      "learning_rate": 3.335001668335002e-05,
      "loss": 0.0264,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9525333333333333,
      "eval_loss": 0.17974689602851868,
      "eval_runtime": 10.135,
      "eval_samples_per_second": 370.005,
      "eval_steps_per_second": 5.821,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.026702603325247765,
      "learning_rate": 2.7794461127794462e-05,
      "loss": 0.0074,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9549333333333333,
      "eval_loss": 0.17467175424098969,
      "eval_runtime": 10.4,
      "eval_samples_per_second": 360.576,
      "eval_steps_per_second": 5.673,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.022421611472964287,
      "learning_rate": 2.2238905572238907e-05,
      "loss": 0.003,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9584,
      "eval_loss": 0.16243326663970947,
      "eval_runtime": 9.8479,
      "eval_samples_per_second": 380.794,
      "eval_steps_per_second": 5.991,
      "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
}