--- license: apache-2.0 base_model: google/vit-base-patch16-224-in21k tags: - image-classification - vision - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: vit-letter-identification-v3 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.15306122448979592 --- # vit-letter-identification-v3 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 3.6435 - Accuracy: 0.1531 ## 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: 2e-05 - train_batch_size: 80 - eval_batch_size: 80 - seed: 1337 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 100.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 7 | 3.9452 | 0.0306 | | 3.9498 | 2.0 | 14 | 3.9438 | 0.0510 | | 3.9413 | 3.0 | 21 | 3.9437 | 0.0408 | | 3.9413 | 4.0 | 28 | 3.9431 | 0.0408 | | 3.9255 | 5.0 | 35 | 3.9424 | 0.0408 | | 3.9132 | 6.0 | 42 | 3.9401 | 0.0306 | | 3.9132 | 7.0 | 49 | 3.9373 | 0.0306 | | 3.8913 | 8.0 | 56 | 3.9351 | 0.0204 | | 3.8685 | 9.0 | 63 | 3.9312 | 0.0204 | | 3.8413 | 10.0 | 70 | 3.9259 | 0.0306 | | 3.8413 | 11.0 | 77 | 3.9219 | 0.0306 | | 3.8163 | 12.0 | 84 | 3.9183 | 0.0204 | | 3.7912 | 13.0 | 91 | 3.9151 | 0.0408 | | 3.7912 | 14.0 | 98 | 3.9116 | 0.0306 | | 3.7616 | 15.0 | 105 | 3.9074 | 0.0408 | | 3.734 | 16.0 | 112 | 3.9029 | 0.0408 | | 3.734 | 17.0 | 119 | 3.8969 | 0.0612 | | 3.7014 | 18.0 | 126 | 3.8907 | 0.0714 | | 3.6707 | 19.0 | 133 | 3.8845 | 0.0714 | | 3.6307 | 20.0 | 140 | 3.8779 | 0.0816 | | 3.6307 | 21.0 | 147 | 3.8704 | 0.0816 | | 3.596 | 22.0 | 154 | 3.8646 | 0.0918 | | 3.5875 | 23.0 | 161 | 3.8604 | 0.0918 | | 3.5875 | 24.0 | 168 | 3.8561 | 0.0918 | | 3.5532 | 25.0 | 175 | 3.8510 | 0.0918 | | 3.5374 | 26.0 | 182 | 3.8442 | 0.0918 | | 3.5374 | 27.0 | 189 | 3.8399 | 0.1020 | | 3.51 | 28.0 | 196 | 3.8350 | 0.1122 | | 3.4842 | 29.0 | 203 | 3.8296 | 0.1224 | | 3.4495 | 30.0 | 210 | 3.8243 | 0.1224 | | 3.4495 | 31.0 | 217 | 3.8213 | 0.1224 | | 3.4155 | 32.0 | 224 | 3.8158 | 0.1224 | | 3.4257 | 33.0 | 231 | 3.8118 | 0.1224 | | 3.4257 | 34.0 | 238 | 3.8061 | 0.1327 | | 3.395 | 35.0 | 245 | 3.8030 | 0.1327 | | 3.3693 | 36.0 | 252 | 3.7957 | 0.1429 | | 3.3693 | 37.0 | 259 | 3.7904 | 0.1224 | | 3.35 | 38.0 | 266 | 3.7834 | 0.1224 | | 3.3453 | 39.0 | 273 | 3.7787 | 0.1224 | | 3.2977 | 40.0 | 280 | 3.7727 | 0.1224 | | 3.2977 | 41.0 | 287 | 3.7681 | 0.1224 | | 3.2875 | 42.0 | 294 | 3.7628 | 0.1224 | | 3.2504 | 43.0 | 301 | 3.7582 | 0.1224 | | 3.2504 | 44.0 | 308 | 3.7527 | 0.1224 | | 3.2772 | 45.0 | 315 | 3.7493 | 0.1224 | | 3.2353 | 46.0 | 322 | 3.7462 | 0.1122 | | 3.2353 | 47.0 | 329 | 3.7431 | 0.1327 | | 3.2198 | 48.0 | 336 | 3.7392 | 0.1327 | | 3.204 | 49.0 | 343 | 3.7370 | 0.1429 | | 3.1762 | 50.0 | 350 | 3.7339 | 0.1429 | | 3.1762 | 51.0 | 357 | 3.7306 | 0.1429 | | 3.1741 | 52.0 | 364 | 3.7267 | 0.1633 | | 3.1757 | 53.0 | 371 | 3.7222 | 0.1633 | | 3.1757 | 54.0 | 378 | 3.7180 | 0.1531 | | 3.1492 | 55.0 | 385 | 3.7149 | 0.1531 | | 3.1442 | 56.0 | 392 | 3.7107 | 0.1531 | | 3.1442 | 57.0 | 399 | 3.7085 | 0.1531 | | 3.1174 | 58.0 | 406 | 3.7059 | 0.1531 | | 3.0962 | 59.0 | 413 | 3.7031 | 0.1531 | | 3.1237 | 60.0 | 420 | 3.7019 | 0.1531 | | 3.1237 | 61.0 | 427 | 3.6996 | 0.1531 | | 3.1229 | 62.0 | 434 | 3.6956 | 0.1531 | | 3.0946 | 63.0 | 441 | 3.6930 | 0.1531 | | 3.0946 | 64.0 | 448 | 3.6916 | 0.1531 | | 3.0861 | 65.0 | 455 | 3.6893 | 0.1531 | | 3.0406 | 66.0 | 462 | 3.6859 | 0.1531 | | 3.0406 | 67.0 | 469 | 3.6839 | 0.1531 | | 3.077 | 68.0 | 476 | 3.6816 | 0.1531 | | 3.0555 | 69.0 | 483 | 3.6782 | 0.1531 | | 3.035 | 70.0 | 490 | 3.6763 | 0.1531 | | 3.035 | 71.0 | 497 | 3.6729 | 0.1531 | | 3.0246 | 72.0 | 504 | 3.6719 | 0.1531 | | 3.0282 | 73.0 | 511 | 3.6708 | 0.1531 | | 3.0282 | 74.0 | 518 | 3.6683 | 0.1429 | | 3.0293 | 75.0 | 525 | 3.6652 | 0.1429 | | 2.9893 | 76.0 | 532 | 3.6640 | 0.1429 | | 2.9893 | 77.0 | 539 | 3.6635 | 0.1429 | | 2.9888 | 78.0 | 546 | 3.6618 | 0.1429 | | 2.9833 | 79.0 | 553 | 3.6595 | 0.1429 | | 2.9739 | 80.0 | 560 | 3.6578 | 0.1429 | | 2.9739 | 81.0 | 567 | 3.6562 | 0.1429 | | 2.9513 | 82.0 | 574 | 3.6552 | 0.1429 | | 2.9503 | 83.0 | 581 | 3.6539 | 0.1429 | | 2.9503 | 84.0 | 588 | 3.6532 | 0.1531 | | 2.9792 | 85.0 | 595 | 3.6517 | 0.1531 | | 2.9561 | 86.0 | 602 | 3.6497 | 0.1531 | | 2.9561 | 87.0 | 609 | 3.6486 | 0.1531 | | 2.964 | 88.0 | 616 | 3.6476 | 0.1531 | | 2.9665 | 89.0 | 623 | 3.6470 | 0.1531 | | 2.9439 | 90.0 | 630 | 3.6462 | 0.1531 | | 2.9439 | 91.0 | 637 | 3.6453 | 0.1531 | | 2.9369 | 92.0 | 644 | 3.6451 | 0.1531 | | 2.9619 | 93.0 | 651 | 3.6451 | 0.1531 | | 2.9619 | 94.0 | 658 | 3.6449 | 0.1531 | | 2.955 | 95.0 | 665 | 3.6444 | 0.1531 | | 2.9323 | 96.0 | 672 | 3.6441 | 0.1531 | | 2.9323 | 97.0 | 679 | 3.6438 | 0.1531 | | 2.9466 | 98.0 | 686 | 3.6437 | 0.1531 | | 2.945 | 99.0 | 693 | 3.6436 | 0.1531 | | 2.9665 | 100.0 | 700 | 3.6435 | 0.1531 | ### Framework versions - Transformers 4.37.0.dev0 - Pytorch 2.1.0+cu121 - Datasets 2.4.0 - Tokenizers 0.15.0