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: 1.6472
- Accuracy: 0.5994
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: 1
- eval_batch_size: 1
- 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: 3000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4112 | 0.1 | 300 | 4.3165 | 0.1141 |
| 2.1452 | 1.1 | 600 | 2.0349 | 0.3758 |
| 2.156 | 2.1 | 900 | 1.9146 | 0.2752 |
| 0.7848 | 3.1 | 1200 | 2.9334 | 0.2550 |
| 3.2405 | 4.1 | 1500 | 2.6900 | 0.3557 |
| 2.6131 | 5.1 | 1800 | 2.5973 | 0.3691 |
| 1.5998 | 6.1 | 2100 | 3.1545 | 0.4295 |
| 1.1689 | 7.1 | 2400 | 3.3012 | 0.2953 |
| 0.2398 | 8.1 | 2700 | 2.7231 | 0.4362 |
| 1.2448 | 9.1 | 3000 | 2.6949 | 0.4295 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 6
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for JackWong0911/timesformer-base-finetuned-k400-finetuned-ucf101-subset
Base model
facebook/timesformer-base-finetuned-k400