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: 2.5195
- Accuracy: 0.3557
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|
| 4.2583 | 0.0325 | 27 | 4.2251 | 0.0157 |
| 4.2374 | 1.0325 | 54 | 4.2267 | 0.0134 |
| 4.2678 | 2.0325 | 81 | 4.2263 | 0.0134 |
| 4.2537 | 3.0325 | 108 | 4.2212 | 0.0157 |
| 4.2401 | 4.0325 | 135 | 4.2065 | 0.0157 |
| 4.2519 | 5.0325 | 162 | 4.2075 | 0.0179 |
| 4.2198 | 6.0325 | 189 | 4.2055 | 0.0134 |
| 4.2111 | 7.0325 | 216 | 4.1958 | 0.0179 |
| 4.1871 | 8.0325 | 243 | 4.1474 | 0.0470 |
| 4.0891 | 9.0325 | 270 | 4.0327 | 0.0447 |
| 3.7963 | 10.0325 | 297 | 3.8218 | 0.0828 |
| 3.4787 | 11.0325 | 324 | 3.7062 | 0.1119 |
| 3.1883 | 12.0325 | 351 | 3.5887 | 0.1119 |
| 3.0045 | 13.0325 | 378 | 3.3810 | 0.1432 |
| 2.8045 | 14.0325 | 405 | 3.2212 | 0.2192 |
| 2.5344 | 15.0325 | 432 | 3.2702 | 0.1588 |
| 2.3725 | 16.0325 | 459 | 3.3600 | 0.1409 |
| 2.2074 | 17.0325 | 486 | 2.9731 | 0.2371 |
| 2.1094 | 18.0325 | 513 | 2.8680 | 0.2617 |
| 1.9839 | 19.0325 | 540 | 2.8360 | 0.2707 |
| 1.7354 | 20.0325 | 567 | 2.7890 | 0.2819 |
| 1.6843 | 21.0325 | 594 | 2.7286 | 0.2998 |
| 1.6266 | 22.0325 | 621 | 2.8062 | 0.2841 |
| 1.4083 | 23.0325 | 648 | 2.8205 | 0.2595 |
| 1.4422 | 24.0325 | 675 | 2.6407 | 0.3065 |
| 1.3897 | 25.0325 | 702 | 2.5948 | 0.3468 |
| 1.3906 | 26.0325 | 729 | 2.6295 | 0.3154 |
| 1.2291 | 27.0325 | 756 | 2.5539 | 0.3378 |
| 1.3166 | 28.0325 | 783 | 2.5200 | 0.3557 |
| 1.2619 | 29.0325 | 810 | 2.5308 | 0.3557 |
| 1.1393 | 30.0264 | 832 | 2.5856 | 0.3244 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0