--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: V4_Image_classification__points_durs__google_vit-base-patch16-224-in21k results: [] --- # V4_Image_classification__points_durs__google_vit-base-patch16-224-in21k This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2221 - Accuracy: 0.9560 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.6743 | 1.0 | 13 | 0.6315 | 0.7566 | | 0.6051 | 2.0 | 26 | 0.4384 | 0.9150 | | 0.4588 | 3.0 | 39 | 0.2402 | 0.9326 | | 0.1818 | 4.0 | 52 | 0.1702 | 0.9384 | | 0.1102 | 5.0 | 65 | 0.1409 | 0.9413 | | 0.0733 | 6.0 | 78 | 0.1516 | 0.9501 | | 0.0423 | 7.0 | 91 | 0.1613 | 0.9560 | | 0.0286 | 8.0 | 104 | 0.1843 | 0.9501 | | 0.0192 | 9.0 | 117 | 0.1672 | 0.9560 | | 0.0159 | 10.0 | 130 | 0.1703 | 0.9589 | | 0.0173 | 11.0 | 143 | 0.1729 | 0.9560 | | 0.0143 | 12.0 | 156 | 0.1786 | 0.9560 | | 0.0105 | 13.0 | 169 | 0.1821 | 0.9560 | | 0.0091 | 14.0 | 182 | 0.1827 | 0.9589 | | 0.0096 | 15.0 | 195 | 0.1859 | 0.9560 | | 0.0081 | 16.0 | 208 | 0.1989 | 0.9560 | | 0.0075 | 17.0 | 221 | 0.2012 | 0.9560 | | 0.0347 | 18.0 | 234 | 0.2507 | 0.9384 | | 0.0232 | 19.0 | 247 | 0.2271 | 0.9413 | | 0.0065 | 20.0 | 260 | 0.1950 | 0.9589 | | 0.0102 | 21.0 | 273 | 0.2378 | 0.9472 | | 0.0064 | 22.0 | 286 | 0.2265 | 0.9501 | | 0.0058 | 23.0 | 299 | 0.2033 | 0.9560 | | 0.0055 | 24.0 | 312 | 0.2402 | 0.9501 | | 0.005 | 25.0 | 325 | 0.2500 | 0.9443 | | 0.0054 | 26.0 | 338 | 0.2450 | 0.9472 | | 0.0048 | 27.0 | 351 | 0.2431 | 0.9501 | | 0.0047 | 28.0 | 364 | 0.2439 | 0.9472 | | 0.0046 | 29.0 | 377 | 0.2445 | 0.9472 | | 0.0044 | 30.0 | 390 | 0.2434 | 0.9472 | | 0.0042 | 31.0 | 403 | 0.2441 | 0.9472 | | 0.0042 | 32.0 | 416 | 0.2426 | 0.9472 | | 0.0042 | 33.0 | 429 | 0.2414 | 0.9472 | | 0.004 | 34.0 | 442 | 0.2383 | 0.9472 | | 0.004 | 35.0 | 455 | 0.2349 | 0.9472 | | 0.0039 | 36.0 | 468 | 0.2340 | 0.9472 | | 0.0038 | 37.0 | 481 | 0.2325 | 0.9472 | | 0.0037 | 38.0 | 494 | 0.2311 | 0.9501 | | 0.0038 | 39.0 | 507 | 0.2280 | 0.9501 | | 0.0037 | 40.0 | 520 | 0.2263 | 0.9531 | | 0.0036 | 41.0 | 533 | 0.2248 | 0.9531 | | 0.0036 | 42.0 | 546 | 0.2242 | 0.9531 | | 0.0036 | 43.0 | 559 | 0.2236 | 0.9531 | | 0.0035 | 44.0 | 572 | 0.2231 | 0.9560 | | 0.0035 | 45.0 | 585 | 0.2224 | 0.9560 | | 0.0035 | 46.0 | 598 | 0.2223 | 0.9560 | | 0.0035 | 47.0 | 611 | 0.2220 | 0.9560 | | 0.0035 | 48.0 | 624 | 0.2221 | 0.9560 | | 0.0034 | 49.0 | 637 | 0.2221 | 0.9560 | | 0.0035 | 50.0 | 650 | 0.2221 | 0.9560 | ### Framework versions - Transformers 4.30.0 - Pytorch 2.1.1 - Datasets 2.15.0 - Tokenizers 0.13.3