timesformer-base-finetuned-k400-finetuned-ucf101-subset
This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4148
- Accuracy: 0.8630
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: 3530
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9335 | 0.0989 | 349 | 0.6504 | 0.7532 |
| 0.6968 | 1.0989 | 698 | 0.5347 | 0.7989 |
| 0.5171 | 2.0989 | 1047 | 0.4950 | 0.8298 |
| 0.3982 | 3.0989 | 1396 | 0.4791 | 0.8436 |
| 0.4689 | 4.0989 | 1745 | 0.5896 | 0.8298 |
| 0.4611 | 5.0989 | 2094 | 0.3638 | 0.8809 |
| 0.3267 | 6.0989 | 2443 | 0.4403 | 0.8585 |
| 0.2757 | 7.0989 | 2792 | 0.3612 | 0.8947 |
| 0.2668 | 8.0989 | 3141 | 0.3553 | 0.8915 |
| 0.1432 | 9.0989 | 3490 | 0.3601 | 0.8968 |
| 0.3437 | 10.0113 | 3530 | 0.3581 | 0.8968 |
Framework versions
- Transformers 4.44.1
- Pytorch 2.0.1+cu117
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 0
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 hernawanvano/timesformer-base-finetuned-k400-finetuned-ucf101-subset
Base model
facebook/timesformer-base-finetuned-k400