metadata
license: cc-by-nc-4.0
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: 1.1287
- Accuracy: 0.8333
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: 1
- eval_batch_size: 1
- 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: 15200
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3638 | 0.02 | 304 | 0.9850 | 0.6118 |
| 0.9176 | 1.02 | 608 | 1.6993 | 0.3882 |
| 0.5243 | 2.02 | 912 | 1.1637 | 0.8026 |
| 0.0005 | 3.02 | 1216 | 0.8620 | 0.8092 |
| 0.5382 | 4.02 | 1520 | 0.9102 | 0.8092 |
| 0.0009 | 5.02 | 1824 | 1.2623 | 0.8355 |
| 0.0007 | 6.02 | 2128 | 1.4007 | 0.7829 |
| 0.254 | 7.02 | 2432 | 3.3258 | 0.4803 |
| 0.0005 | 8.02 | 2736 | 1.0090 | 0.8684 |
| 0.0003 | 9.02 | 3040 | 1.6322 | 0.7632 |
| 0.0015 | 10.02 | 3344 | 3.1927 | 0.5395 |
| 0.0006 | 11.02 | 3648 | 2.3243 | 0.7237 |
| 0.0004 | 12.02 | 3952 | 1.4877 | 0.7961 |
| 0.0007 | 13.02 | 4256 | 1.4014 | 0.8224 |
| 0.0001 | 14.02 | 4560 | 0.9946 | 0.8487 |
| 0.6249 | 15.02 | 4864 | 1.2847 | 0.7961 |
| 3.8326 | 16.02 | 5168 | 1.7870 | 0.7171 |
| 0.0646 | 17.02 | 5472 | 2.3504 | 0.6579 |
| 0.0003 | 18.02 | 5776 | 0.9367 | 0.8618 |
| 0.0004 | 19.02 | 6080 | 2.5710 | 0.6316 |
| 0.5626 | 20.02 | 6384 | 2.6711 | 0.6842 |
| 0.9002 | 21.02 | 6688 | 2.1456 | 0.7566 |
| 0.0002 | 22.02 | 6992 | 2.3488 | 0.7237 |
| 0.6977 | 23.02 | 7296 | 1.5013 | 0.8092 |
| 0.0001 | 24.02 | 7600 | 1.9442 | 0.7763 |
| 0.0003 | 25.02 | 7904 | 1.8732 | 0.8026 |
| 0.0001 | 26.02 | 8208 | 2.0295 | 0.7829 |
| 0.0001 | 27.02 | 8512 | 1.7623 | 0.8092 |
| 0.0001 | 28.02 | 8816 | 1.8035 | 0.8026 |
| 0.0 | 29.02 | 9120 | 1.7754 | 0.8092 |
| 0.0001 | 30.02 | 9424 | 1.7622 | 0.7961 |
| 0.0001 | 31.02 | 9728 | 1.7557 | 0.7895 |
| 0.0002 | 32.02 | 10032 | 1.5907 | 0.8224 |
| 0.0001 | 33.02 | 10336 | 1.6859 | 0.8158 |
| 0.0 | 34.02 | 10640 | 1.8641 | 0.7961 |
| 0.0 | 35.02 | 10944 | 1.7088 | 0.8224 |
| 0.0 | 36.02 | 11248 | 1.6140 | 0.8421 |
| 0.0 | 37.02 | 11552 | 1.6678 | 0.8355 |
| 0.0 | 38.02 | 11856 | 1.6991 | 0.8355 |
| 0.0 | 39.02 | 12160 | 1.7723 | 0.8224 |
| 0.0 | 40.02 | 12464 | 1.7865 | 0.8224 |
| 0.6067 | 41.02 | 12768 | 2.6848 | 0.7368 |
| 0.0001 | 42.02 | 13072 | 1.6834 | 0.8289 |
| 0.0 | 43.02 | 13376 | 1.7188 | 0.8289 |
| 0.9374 | 44.02 | 13680 | 1.5728 | 0.8421 |
| 0.0 | 45.02 | 13984 | 2.0988 | 0.7895 |
| 0.0 | 46.02 | 14288 | 2.0841 | 0.7829 |
| 0.0 | 47.02 | 14592 | 2.2198 | 0.7632 |
| 0.0 | 48.02 | 14896 | 2.2020 | 0.7632 |
| 0.0 | 49.02 | 15200 | 2.0693 | 0.7763 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2