<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
videomae-base-fight
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: 1.7465
- Accuracy: 0.5481
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: 10
- eval_batch_size: 10
- 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: 7120
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.4036 | 0.1 | 713 | 0.4406 | 0.8189 |
0.2263 | 1.1 | 1426 | 0.6400 | 0.7950 |
0.2391 | 2.1 | 2139 | 0.4807 | 0.8233 |
0.3241 | 3.1 | 2852 | 0.5920 | 0.8167 |
0.255 | 4.1 | 3565 | 0.6452 | 0.8026 |
0.1256 | 5.1 | 4278 | 0.5889 | 0.8244 |
0.2026 | 6.1 | 4991 | 0.7288 | 0.8059 |
0.2262 | 7.1 | 5704 | 0.6861 | 0.8151 |
0.1367 | 8.1 | 6417 | 0.7288 | 0.8140 |
0.0803 | 9.1 | 7120 | 0.8737 | 0.8064 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1