trainer_state.json

{
  "best_metric": 0.9418666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0389/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 3e-05,
      "loss": 1.1644,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.92,
      "eval_loss": 0.33060652017593384,
      "eval_runtime": 7.4724,
      "eval_samples_per_second": 501.849,
      "eval_steps_per_second": 7.896,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.857006072998047,
      "learning_rate": 3e-05,
      "loss": 0.2005,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.2322571873664856,
      "eval_runtime": 7.2634,
      "eval_samples_per_second": 516.291,
      "eval_steps_per_second": 8.123,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8964175581932068,
      "learning_rate": 3e-05,
      "loss": 0.0944,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9354666666666667,
      "eval_loss": 0.21938438713550568,
      "eval_runtime": 6.7096,
      "eval_samples_per_second": 558.9,
      "eval_steps_per_second": 8.793,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.07651789486408234,
      "learning_rate": 3e-05,
      "loss": 0.0508,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.936,
      "eval_loss": 0.2302604466676712,
      "eval_runtime": 7.0216,
      "eval_samples_per_second": 534.069,
      "eval_steps_per_second": 8.403,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.042064815759658813,
      "learning_rate": 3e-05,
      "loss": 0.0292,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9394666666666667,
      "eval_loss": 0.23764844238758087,
      "eval_runtime": 7.0206,
      "eval_samples_per_second": 534.145,
      "eval_steps_per_second": 8.404,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.04181906580924988,
      "learning_rate": 3e-05,
      "loss": 0.0196,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.2548416256904602,
      "eval_runtime": 7.1529,
      "eval_samples_per_second": 524.26,
      "eval_steps_per_second": 8.248,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.024964477866888046,
      "learning_rate": 3e-05,
      "loss": 0.0151,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.94,
      "eval_loss": 0.25718510150909424,
      "eval_runtime": 6.7631,
      "eval_samples_per_second": 554.476,
      "eval_steps_per_second": 8.724,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.05270157754421234,
      "learning_rate": 3e-05,
      "loss": 0.0095,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9418666666666666,
      "eval_loss": 0.25374531745910645,
      "eval_runtime": 7.37,
      "eval_samples_per_second": 508.818,
      "eval_steps_per_second": 8.005,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}