metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-short-finetuned-ssv2-finetuned-rwf2000-epochs8-sample8
results: []
videomae-base-short-finetuned-ssv2-finetuned-rwf2000-epochs8-sample8
This model is a fine-tuned version of MCG-NJU/videomae-base-short-finetuned-ssv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2493
- Accuracy: 0.3857
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: 6400
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6783 | 0.12 | 800 | 0.5823 | 0.8175 |
| 0.7397 | 1.12 | 1600 | 2.2365 | 0.5475 |
| 0.206 | 2.12 | 2400 | 1.4244 | 0.6375 |
| 0.0431 | 3.12 | 3200 | 0.9144 | 0.7525 |
| 0.0033 | 4.12 | 4000 | 0.7622 | 0.825 |
| 0.0011 | 5.12 | 4800 | 1.0658 | 0.775 |
| 0.001 | 6.12 | 5600 | 1.6892 | 0.6875 |
| 0.2392 | 7.12 | 6400 | 1.1574 | 0.7825 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.2