metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-large-finetuned-kinetics
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: MAE-CT-CPC-Dicotomized-v8-n0-m1
results: []
MAE-CT-CPC-Dicotomized-v8-n0-m1
This model is a fine-tuned version of MCG-NJU/videomae-large-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5946
- Accuracy: 0.5753
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: 1e-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: 2500
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6826 | 0.0204 | 51 | 0.6157 | 0.7625 |
| 0.6549 | 1.0204 | 102 | 0.5930 | 0.7625 |
| 0.6486 | 2.0204 | 153 | 0.6797 | 0.5125 |
| 0.5595 | 3.0204 | 204 | 0.4902 | 0.6625 |
| 0.5586 | 4.0204 | 255 | 0.8195 | 0.475 |
| 0.4565 | 5.0204 | 306 | 0.5872 | 0.75 |
| 0.3697 | 6.0204 | 357 | 0.5017 | 0.775 |
| 0.6201 | 7.0204 | 408 | 0.6555 | 0.7 |
| 0.4333 | 8.0204 | 459 | 1.2277 | 0.6125 |
| 0.2148 | 9.0204 | 510 | 0.8115 | 0.7625 |
| 0.9458 | 10.0204 | 561 | 0.9873 | 0.6625 |
| 0.0651 | 11.0204 | 612 | 1.0840 | 0.7625 |
| 0.5756 | 12.0204 | 663 | 1.0489 | 0.8 |
| 0.354 | 13.0204 | 714 | 1.1601 | 0.7875 |
| 0.2888 | 14.0204 | 765 | 1.8144 | 0.625 |
| 0.2449 | 15.0204 | 816 | 1.3988 | 0.7125 |
| 0.1326 | 16.0204 | 867 | 1.7152 | 0.7125 |
| 0.0018 | 17.0204 | 918 | 2.1475 | 0.6375 |
| 0.3631 | 18.0204 | 969 | 1.8957 | 0.65 |
| 0.1252 | 19.0204 | 1020 | 1.1246 | 0.825 |
| 0.0943 | 20.0204 | 1071 | 1.9498 | 0.6625 |
| 0.3488 | 21.0204 | 1122 | 1.3457 | 0.7875 |
| 0.0008 | 22.0204 | 1173 | 1.7872 | 0.7125 |
| 0.009 | 23.0204 | 1224 | 1.5437 | 0.75 |
| 0.0274 | 24.0204 | 1275 | 1.9865 | 0.6875 |
| 0.0004 | 25.0204 | 1326 | 1.5100 | 0.7625 |
| 0.1007 | 26.0204 | 1377 | 1.9590 | 0.6875 |
| 0.0006 | 27.0204 | 1428 | 1.8346 | 0.7125 |
| 0.0006 | 28.0204 | 1479 | 1.4669 | 0.825 |
| 0.0001 | 29.0204 | 1530 | 1.5396 | 0.7875 |
| 0.0002 | 30.0204 | 1581 | 1.5716 | 0.7875 |
| 0.0001 | 31.0204 | 1632 | 1.6614 | 0.7625 |
| 0.0002 | 32.0204 | 1683 | 1.6356 | 0.7625 |
| 0.0001 | 33.0204 | 1734 | 1.5731 | 0.8 |
| 0.0001 | 34.0204 | 1785 | 2.0020 | 0.725 |
| 0.0001 | 35.0204 | 1836 | 1.8886 | 0.75 |
| 0.0001 | 36.0204 | 1887 | 1.8363 | 0.75 |
| 0.0001 | 37.0204 | 1938 | 1.6848 | 0.7625 |
| 0.0001 | 38.0204 | 1989 | 1.7188 | 0.75 |
| 0.0001 | 39.0204 | 2040 | 1.5820 | 0.8 |
| 0.0001 | 40.0204 | 2091 | 1.6061 | 0.7875 |
| 0.0001 | 41.0204 | 2142 | 2.2817 | 0.7 |
| 0.0001 | 42.0204 | 2193 | 2.1015 | 0.725 |
| 0.0001 | 43.0204 | 2244 | 1.6356 | 0.775 |
| 0.0001 | 44.0204 | 2295 | 1.5849 | 0.8125 |
| 0.0001 | 45.0204 | 2346 | 1.6463 | 0.775 |
| 0.0001 | 46.0204 | 2397 | 1.6641 | 0.775 |
| 0.0001 | 47.0204 | 2448 | 1.6123 | 0.7875 |
| 0.0001 | 48.0204 | 2499 | 1.6145 | 0.7875 |
| 0.0001 | 49.0004 | 2500 | 1.6145 | 0.7875 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.0.1+cu117
- Datasets 3.0.1
- Tokenizers 0.20.0