metadata
license: cc-by-nc-4.0
base_model: facebook/timesformer-base-finetuned-k400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: timesformer-base-finetuned-k400-finetuned-ucf101-subset
results: []
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: 0.0029
- Accuracy: 1.0
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: 3
- eval_batch_size: 3
- 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: 174
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1178 | 0.17 | 29 | 0.3686 | 0.6667 |
| 0.326 | 1.17 | 58 | 0.0904 | 1.0 |
| 0.1541 | 2.17 | 87 | 0.0164 | 1.0 |
| 0.2257 | 3.17 | 116 | 0.0054 | 1.0 |
| 0.2095 | 4.17 | 145 | 0.0029 | 1.0 |
| 0.0202 | 5.17 | 174 | 0.0029 | 1.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2