videomae-base-groub11-12-finetuned-SLT-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: 3.3226
- Accuracy: 0.1190
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: 4
- eval_batch_size: 4
- 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: 80
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.8585 | 0.14 | 11 | 3.6444 | 0.0714 |
| 3.7726 | 1.14 | 22 | 3.5972 | 0.0952 |
| 3.679 | 2.14 | 33 | 3.5197 | 0.0714 |
| 3.6781 | 3.14 | 44 | 3.4598 | 0.0952 |
| 3.3857 | 4.14 | 55 | 3.3870 | 0.1190 |
| 3.4777 | 5.14 | 66 | 3.3394 | 0.1190 |
| 3.4625 | 6.14 | 77 | 3.3240 | 0.1190 |
| 3.342 | 7.04 | 80 | 3.3226 | 0.1190 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0+cpu
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 62
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for asmaa1/videomae-base-groub11-12-finetuned-SLT-subset
Base model
MCG-NJU/videomae-base