trainer_state.json

{
  "best_metric": 0.964,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0799/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": 0.2078263759613037,
      "learning_rate": 6.531088913245535e-05,
      "loss": 0.6916,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9445333333333333,
      "eval_loss": 0.20866486430168152,
      "eval_runtime": 10.2928,
      "eval_samples_per_second": 364.331,
      "eval_steps_per_second": 5.732,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.09920937567949295,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.1034,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9530666666666666,
      "eval_loss": 0.18225885927677155,
      "eval_runtime": 10.2342,
      "eval_samples_per_second": 366.418,
      "eval_steps_per_second": 5.765,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04080478101968765,
      "learning_rate": 3.5e-05,
      "loss": 0.0321,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9562666666666667,
      "eval_loss": 0.16268284618854523,
      "eval_runtime": 10.3164,
      "eval_samples_per_second": 363.498,
      "eval_steps_per_second": 5.719,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.09346780180931091,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0084,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9618666666666666,
      "eval_loss": 0.15278470516204834,
      "eval_runtime": 10.2078,
      "eval_samples_per_second": 367.368,
      "eval_steps_per_second": 5.78,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.02637818083167076,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.0031,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.964,
      "eval_loss": 0.14532619714736938,
      "eval_runtime": 10.1952,
      "eval_samples_per_second": 367.822,
      "eval_steps_per_second": 5.787,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}