videomae-base-ssv2-finetuned-rwf2000-epochs6
This model is a fine-tuned version of MCG-NJU/videomae-base-ssv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7920
- Accuracy: 0.4357
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: 2
- eval_batch_size: 2
- 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: 4800
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.841 | 0.17 | 800 | 0.7114 | 0.755 |
0.8781 | 1.17 | 1600 | 1.6078 | 0.5925 |
0.1951 | 2.17 | 2400 | 1.9190 | 0.5962 |
0.2094 | 3.17 | 3200 | 0.9991 | 0.7588 |
0.3594 | 4.17 | 4000 | 1.0306 | 0.7937 |
0.0019 | 5.17 | 4800 | 1.0982 | 0.7775 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.