trainer_state.json

{
  "best_metric": 0.9293333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0829/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": 0.5910030603408813,
      "learning_rate": 0.0001,
      "loss": 0.6141,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9242666666666667,
      "eval_loss": 0.27608931064605713,
      "eval_runtime": 12.8333,
      "eval_samples_per_second": 292.21,
      "eval_steps_per_second": 4.597,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.23439261317253113,
      "learning_rate": 0.0001,
      "loss": 0.1271,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9248,
      "eval_loss": 0.26177939772605896,
      "eval_runtime": 12.1458,
      "eval_samples_per_second": 308.75,
      "eval_steps_per_second": 4.858,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.05201209709048271,
      "learning_rate": 0.0001,
      "loss": 0.0675,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9210666666666667,
      "eval_loss": 0.3120349049568176,
      "eval_runtime": 12.0093,
      "eval_samples_per_second": 312.259,
      "eval_steps_per_second": 4.913,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.015926465392112732,
      "learning_rate": 0.0001,
      "loss": 0.0411,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9202666666666667,
      "eval_loss": 0.335945188999176,
      "eval_runtime": 11.9265,
      "eval_samples_per_second": 314.427,
      "eval_steps_per_second": 4.947,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.006203284487128258,
      "learning_rate": 0.0001,
      "loss": 0.0344,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9293333333333333,
      "eval_loss": 0.3075844943523407,
      "eval_runtime": 11.9258,
      "eval_samples_per_second": 314.444,
      "eval_steps_per_second": 4.947,
      "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
}