videomae-base-finetuned-kinetics-finetuned-ucf101-subset-finetuned-N
This model is a fine-tuned version of sayakpaul/videomae-base-finetuned-kinetics-finetuned-ucf101-subset on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6134
- Accuracy: 0.8358
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: 171
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9407 | 0.33 | 57 | 0.7452 | 0.8022 |
| 0.4492 | 1.33 | 114 | 0.8826 | 0.8022 |
| 0.3679 | 2.33 | 171 | 0.7072 | 0.8022 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Tokenizers 0.15.0
- Downloads last month
- 8
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.