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-check10
results: []
videomae-base-finetuned-subset-check10
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: 0.6927
- Accuracy: 0.6667
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: 8
- eval_batch_size: 8
- 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: 1110
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6348 | 0.05 | 56 | 1.5443 | 0.5115 |
| 1.6015 | 1.05 | 112 | 1.5298 | 0.4793 |
| 1.5683 | 2.05 | 168 | 1.5289 | 0.3272 |
| 1.512 | 3.05 | 224 | 1.3029 | 0.6313 |
| 1.2309 | 4.05 | 280 | 1.2181 | 0.5207 |
| 1.1949 | 5.05 | 336 | 1.0441 | 0.6590 |
| 1.0987 | 6.05 | 392 | 1.0041 | 0.6129 |
| 1.148 | 7.05 | 448 | 1.0259 | 0.6175 |
| 0.9958 | 8.05 | 504 | 0.9508 | 0.6728 |
| 1.0856 | 9.05 | 560 | 1.0041 | 0.5945 |
| 0.8809 | 10.05 | 616 | 0.9638 | 0.6359 |
| 0.9185 | 11.05 | 672 | 0.9248 | 0.6820 |
| 0.9136 | 12.05 | 728 | 1.0136 | 0.6728 |
| 0.8537 | 13.05 | 784 | 0.8515 | 0.7189 |
| 0.7921 | 14.05 | 840 | 0.8222 | 0.7005 |
| 0.7313 | 15.05 | 896 | 0.7512 | 0.7419 |
| 0.5998 | 16.05 | 952 | 0.9410 | 0.6129 |
| 0.8093 | 17.05 | 1008 | 0.8145 | 0.7051 |
| 0.604 | 18.05 | 1064 | 0.9014 | 0.6820 |
| 0.7066 | 19.04 | 1110 | 0.8935 | 0.6682 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.1
- Datasets 2.16.1
- Tokenizers 0.15.0