videomae-base-finetuned-ssv2-finetuned-samsung-subset
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-ssv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5762
- Accuracy: 0.8041
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: 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: 408
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.608 | 0.25 | 103 | 1.5651 | 0.5497 |
| 0.7421 | 1.25 | 206 | 0.9050 | 0.7271 |
| 0.6384 | 2.25 | 309 | 0.6470 | 0.7963 |
| 0.3902 | 3.24 | 408 | 0.5762 | 0.8041 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+rocm5.4.2
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 4
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 piplustheta/videomae-base-finetuned-ssv2-finetuned-samsung-subset
Base model
MCG-NJU/videomae-base-finetuned-ssv2