metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset
results: []
videomae-base-finetuned-ucf101-subset
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0844
- Accuracy: 0.7320
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 832
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.238 | 0.0168 | 14 | 4.2235 | 0.0180 |
| 4.2658 | 1.0168 | 28 | 4.2075 | 0.0203 |
| 4.219 | 2.0168 | 42 | 4.2053 | 0.0158 |
| 4.2146 | 3.0168 | 56 | 4.2098 | 0.0225 |
| 4.1925 | 4.0168 | 70 | 4.1824 | 0.0225 |
| 4.1192 | 5.0168 | 84 | 4.0819 | 0.0383 |
| 4.0297 | 6.0168 | 98 | 3.9819 | 0.0698 |
| 3.7134 | 7.0168 | 112 | 3.7340 | 0.1036 |
| 3.5289 | 8.0168 | 126 | 3.4205 | 0.1802 |
| 3.0625 | 9.0168 | 140 | 3.1970 | 0.2613 |
| 2.8776 | 10.0168 | 154 | 2.9350 | 0.3018 |
| 2.6375 | 11.0168 | 168 | 2.7630 | 0.3604 |
| 2.2954 | 12.0168 | 182 | 2.4991 | 0.4279 |
| 2.1337 | 13.0168 | 196 | 2.3827 | 0.4324 |
| 1.8195 | 14.0168 | 210 | 2.2312 | 0.4820 |
| 1.6436 | 15.0168 | 224 | 2.3629 | 0.4459 |
| 1.6289 | 16.0168 | 238 | 2.1512 | 0.4752 |
| 1.2957 | 17.0168 | 252 | 2.0142 | 0.5023 |
| 1.2761 | 18.0168 | 266 | 1.9061 | 0.5270 |
| 1.1118 | 19.0168 | 280 | 1.8113 | 0.5495 |
| 0.9642 | 20.0168 | 294 | 1.7280 | 0.6036 |
| 0.894 | 21.0168 | 308 | 1.8723 | 0.5383 |
| 0.7974 | 22.0168 | 322 | 1.6585 | 0.6059 |
| 0.833 | 23.0168 | 336 | 1.5996 | 0.6149 |
| 0.6431 | 24.0168 | 350 | 1.5609 | 0.6149 |
| 0.5873 | 25.0168 | 364 | 1.6108 | 0.6171 |
| 0.5554 | 26.0168 | 378 | 1.4014 | 0.6532 |
| 0.4786 | 27.0168 | 392 | 1.4335 | 0.6622 |
| 0.4252 | 28.0168 | 406 | 1.4445 | 0.6509 |
| 0.382 | 29.0168 | 420 | 1.3915 | 0.6622 |
| 0.365 | 30.0168 | 434 | 1.2978 | 0.6847 |
| 0.319 | 31.0168 | 448 | 1.3218 | 0.6824 |
| 0.3167 | 32.0168 | 462 | 1.3496 | 0.6644 |
| 0.2797 | 33.0168 | 476 | 1.2806 | 0.6802 |
| 0.2864 | 34.0168 | 490 | 1.2191 | 0.7072 |
| 0.2927 | 35.0168 | 504 | 1.2135 | 0.7207 |
| 0.2698 | 36.0168 | 518 | 1.2507 | 0.6914 |
| 0.2333 | 37.0168 | 532 | 1.2038 | 0.7095 |
| 0.2366 | 38.0168 | 546 | 1.1517 | 0.7207 |
| 0.1886 | 39.0168 | 560 | 1.2074 | 0.7095 |
| 0.1804 | 40.0168 | 574 | 1.1658 | 0.7027 |
| 0.1778 | 41.0168 | 588 | 1.2350 | 0.6824 |
| 0.1728 | 42.0168 | 602 | 1.1638 | 0.7162 |
| 0.1998 | 43.0168 | 616 | 1.2359 | 0.6959 |
| 0.1727 | 44.0168 | 630 | 1.2321 | 0.6937 |
| 0.1564 | 45.0168 | 644 | 1.1605 | 0.7140 |
| 0.1888 | 46.0168 | 658 | 1.1609 | 0.7095 |
| 0.1227 | 47.0168 | 672 | 1.1588 | 0.7117 |
| 0.134 | 48.0168 | 686 | 1.1698 | 0.7072 |
| 0.1622 | 49.0168 | 700 | 1.2014 | 0.6982 |
| 0.1391 | 50.0168 | 714 | 1.1006 | 0.7162 |
| 0.1276 | 51.0168 | 728 | 1.1485 | 0.6892 |
| 0.1222 | 52.0168 | 742 | 1.0802 | 0.7140 |
| 0.1024 | 53.0168 | 756 | 1.1243 | 0.7050 |
| 0.1186 | 54.0168 | 770 | 1.0909 | 0.7297 |
| 0.1121 | 55.0168 | 784 | 1.1351 | 0.7095 |
| 0.1284 | 56.0168 | 798 | 1.1095 | 0.7275 |
| 0.0893 | 57.0168 | 812 | 1.0844 | 0.7320 |
| 0.0878 | 58.0168 | 826 | 1.0804 | 0.7297 |
| 0.0887 | 59.0072 | 832 | 1.0809 | 0.7297 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0