ts-g-4-fc-loss-8-10-epochs-5_class_1_p3_splited-1788934746.2713165
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: 0.0396
- Accuracy: 0.9367
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 14340
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0349 | 0.1001 | 1435 | 0.0458 | 0.7901 |
| 0.0204 | 1.1001 | 2870 | 0.0321 | 0.8884 |
| 0.0374 | 2.1001 | 4305 | 0.0305 | 0.8968 |
| 0.0151 | 3.1001 | 5740 | 0.0461 | 0.8919 |
| 0.0152 | 4.1001 | 7175 | 0.0328 | 0.9114 |
| 0.0143 | 5.1001 | 8610 | 0.0287 | 0.9303 |
| 0.0256 | 6.1001 | 10045 | 0.0643 | 0.9100 |
| 0.0114 | 7.1001 | 11480 | 0.0498 | 0.9310 |
| 0.0058 | 8.1001 | 12915 | 0.0624 | 0.9268 |
| 0.0152 | 9.0994 | 14340 | 0.0558 | 0.9261 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.14.0+cu126
- Datasets 5.0.1
- Tokenizers 0.23.2