<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
plant-seedlings-freeze-0-6-aug-3
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2030
- Accuracy: 0.9401
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 11
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5655 | 0.2 | 100 | 0.7734 | 0.7520 |
| 0.663 | 0.39 | 200 | 0.5191 | 0.8276 |
| 0.4009 | 0.59 | 300 | 0.6602 | 0.7706 |
| 0.6175 | 0.79 | 400 | 0.5263 | 0.8129 |
| 0.2571 | 0.98 | 500 | 0.5162 | 0.8502 |
| 0.3698 | 1.18 | 600 | 0.4021 | 0.8684 |
| 0.4092 | 1.38 | 700 | 0.3559 | 0.8787 |
| 0.2506 | 1.57 | 800 | 0.4771 | 0.8571 |
| 0.2597 | 1.77 | 900 | 0.4663 | 0.8517 |
| 0.4016 | 1.96 | 1000 | 0.3367 | 0.8802 |
| 0.2899 | 2.16 | 1100 | 0.3276 | 0.8959 |
| 0.2713 | 2.36 | 1200 | 0.3035 | 0.8988 |
| 0.2707 | 2.55 | 1300 | 0.3661 | 0.8846 |
| 0.4251 | 2.75 | 1400 | 0.3720 | 0.8669 |
| 0.1669 | 2.95 | 1500 | 0.3323 | 0.8870 |
| 0.3079 | 3.14 | 1600 | 0.3322 | 0.8875 |
| 0.2596 | 3.34 | 1700 | 0.3666 | 0.8969 |
| 0.3019 | 3.54 | 1800 | 0.2772 | 0.9023 |
| 0.3429 | 3.73 | 1900 | 0.2936 | 0.9037 |
| 0.2508 | 3.93 | 2000 | 0.3525 | 0.8846 |
| 0.2212 | 4.13 | 2100 | 0.3199 | 0.8934 |
| 0.3104 | 4.32 | 2200 | 0.3546 | 0.8915 |
| 0.1682 | 4.52 | 2300 | 0.2823 | 0.8939 |
| 0.2014 | 4.72 | 2400 | 0.2813 | 0.9150 |
| 0.2805 | 4.91 | 2500 | 0.2907 | 0.9077 |
| 0.1471 | 5.11 | 2600 | 0.2811 | 0.9091 |
| 0.179 | 5.3 | 2700 | 0.2752 | 0.9106 |
| 0.1992 | 5.5 | 2800 | 0.2894 | 0.9072 |
| 0.1635 | 5.7 | 2900 | 0.2397 | 0.9194 |
| 0.2045 | 5.89 | 3000 | 0.2717 | 0.9037 |
| 0.1893 | 6.09 | 3100 | 0.2339 | 0.9273 |
| 0.2664 | 6.29 | 3200 | 0.2772 | 0.9131 |
| 0.1991 | 6.48 | 3300 | 0.2475 | 0.9234 |
| 0.0713 | 6.68 | 3400 | 0.2509 | 0.9185 |
| 0.1968 | 6.88 | 3500 | 0.2410 | 0.9194 |
| 0.1378 | 7.07 | 3600 | 0.2177 | 0.9288 |
| 0.1609 | 7.27 | 3700 | 0.2182 | 0.9214 |
| 0.1001 | 7.47 | 3800 | 0.2110 | 0.9317 |
| 0.097 | 7.66 | 3900 | 0.2949 | 0.9224 |
| 0.1234 | 7.86 | 4000 | 0.2365 | 0.9337 |
| 0.1572 | 8.06 | 4100 | 0.2352 | 0.9283 |
| 0.1402 | 8.25 | 4200 | 0.2299 | 0.9258 |
| 0.1089 | 8.45 | 4300 | 0.2465 | 0.9298 |
| 0.1376 | 8.64 | 4400 | 0.2257 | 0.9298 |
| 0.0911 | 8.84 | 4500 | 0.2057 | 0.9342 |
| 0.1406 | 9.04 | 4600 | 0.2064 | 0.9386 |
| 0.1318 | 9.23 | 4700 | 0.2241 | 0.9347 |
| 0.052 | 9.43 | 4800 | 0.1821 | 0.9425 |
| 0.106 | 9.63 | 4900 | 0.2407 | 0.9283 |
| 0.0975 | 9.82 | 5000 | 0.2013 | 0.9381 |
| 0.1277 | 10.02 | 5100 | 0.1717 | 0.9445 |
| 0.0859 | 10.22 | 5200 | 0.2233 | 0.9352 |
| 0.1242 | 10.41 | 5300 | 0.2232 | 0.9361 |
| 0.0355 | 10.61 | 5400 | 0.1898 | 0.9381 |
| 0.1613 | 10.81 | 5500 | 0.2030 | 0.9401 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
