metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-subset
results: []
videomae-base-finetuned-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: 0.8930
- Accuracy: 0.6296
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 6660
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6074 | 0.02 | 112 | 1.5690 | 0.3687 |
| 1.6001 | 1.02 | 224 | 1.5783 | 0.3041 |
| 1.4193 | 2.02 | 336 | 1.4874 | 0.3825 |
| 1.398 | 3.02 | 448 | 1.0197 | 0.6406 |
| 1.2217 | 4.02 | 560 | 1.3386 | 0.3917 |
| 1.2577 | 5.02 | 672 | 1.2196 | 0.5392 |
| 1.0121 | 6.02 | 784 | 1.2319 | 0.4793 |
| 1.2485 | 7.02 | 896 | 0.8230 | 0.7512 |
| 1.025 | 8.02 | 1008 | 0.8023 | 0.6866 |
| 1.2952 | 9.02 | 1120 | 0.9130 | 0.6037 |
| 0.9499 | 10.02 | 1232 | 1.0621 | 0.6037 |
| 0.8805 | 11.02 | 1344 | 0.8713 | 0.7051 |
| 1.2066 | 12.02 | 1456 | 0.9364 | 0.5853 |
| 0.9358 | 13.02 | 1568 | 0.9107 | 0.5853 |
| 0.9043 | 14.02 | 1680 | 0.9147 | 0.6359 |
| 0.8383 | 15.02 | 1792 | 0.9451 | 0.6359 |
| 0.7482 | 16.02 | 1904 | 0.8765 | 0.6221 |
| 0.9547 | 17.02 | 2016 | 0.7998 | 0.7650 |
| 0.7028 | 18.02 | 2128 | 0.9257 | 0.6406 |
| 0.8659 | 19.02 | 2240 | 1.0655 | 0.5853 |
| 0.5591 | 20.02 | 2352 | 1.2794 | 0.5760 |
| 0.8963 | 21.02 | 2464 | 1.0049 | 0.6959 |
| 0.9221 | 22.02 | 2576 | 1.1113 | 0.6083 |
| 0.7154 | 23.02 | 2688 | 0.9371 | 0.6406 |
| 0.8795 | 24.02 | 2800 | 0.6838 | 0.7235 |
| 0.631 | 25.02 | 2912 | 1.2093 | 0.6129 |
| 1.0489 | 26.02 | 3024 | 1.4720 | 0.5484 |
| 0.5881 | 27.02 | 3136 | 1.1905 | 0.6313 |
| 0.7919 | 28.02 | 3248 | 1.1292 | 0.5760 |
| 0.9158 | 29.02 | 3360 | 1.0214 | 0.6359 |
| 0.8319 | 30.02 | 3472 | 1.2862 | 0.6682 |
| 0.6775 | 31.02 | 3584 | 1.0971 | 0.6406 |
| 0.7191 | 32.02 | 3696 | 1.0264 | 0.6498 |
| 0.7662 | 33.02 | 3808 | 1.0589 | 0.6406 |
| 0.7313 | 34.02 | 3920 | 1.5076 | 0.5622 |
| 0.7539 | 35.02 | 4032 | 1.2265 | 0.5899 |
| 0.571 | 36.02 | 4144 | 1.1598 | 0.6267 |
| 0.3404 | 37.02 | 4256 | 1.0307 | 0.6359 |
| 0.5553 | 38.02 | 4368 | 0.8180 | 0.7235 |
| 0.8499 | 39.02 | 4480 | 1.0074 | 0.6498 |
| 0.5036 | 40.02 | 4592 | 1.1160 | 0.6313 |
| 0.814 | 41.02 | 4704 | 0.9032 | 0.6959 |
| 0.7293 | 42.02 | 4816 | 0.9331 | 0.7281 |
| 0.4402 | 43.02 | 4928 | 1.4190 | 0.5668 |
| 0.4625 | 44.02 | 5040 | 1.0268 | 0.7005 |
| 0.2266 | 45.02 | 5152 | 1.2808 | 0.6406 |
| 0.7424 | 46.02 | 5264 | 1.1821 | 0.6498 |
| 0.4852 | 47.02 | 5376 | 1.2434 | 0.6590 |
| 0.523 | 48.02 | 5488 | 1.2123 | 0.6267 |
| 0.8344 | 49.02 | 5600 | 1.1889 | 0.6636 |
| 0.6648 | 50.02 | 5712 | 1.2328 | 0.6406 |
| 0.6929 | 51.02 | 5824 | 1.3269 | 0.6129 |
| 0.4253 | 52.02 | 5936 | 1.1885 | 0.6820 |
| 0.7003 | 53.02 | 6048 | 1.1522 | 0.7005 |
| 0.4105 | 54.02 | 6160 | 1.0037 | 0.7373 |
| 0.5206 | 55.02 | 6272 | 1.0913 | 0.7189 |
| 0.7129 | 56.02 | 6384 | 1.1083 | 0.6866 |
| 0.4772 | 57.02 | 6496 | 1.1276 | 0.7143 |
| 0.4822 | 58.02 | 6608 | 1.0920 | 0.7235 |
| 0.6307 | 59.01 | 6660 | 1.0987 | 0.7189 |
Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1
- Datasets 2.16.1
- Tokenizers 0.15.0