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-kinetic400-subset-epoch6-num_frame_10_myViT2window3_more_data_b4
results: []
timesformer-base-finetuned-k400-kinetic400-subset-epoch6-num_frame_10_myViT2window3_more_data_b4
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: 0.1298
- Accuracy: 0.96
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: 4
- eval_batch_size: 4
- 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: 372
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2031 | 0.17 | 63 | 0.1295 | 0.97 |
| 0.0389 | 1.17 | 126 | 0.3616 | 0.89 |
| 0.0023 | 2.17 | 189 | 0.1584 | 0.97 |
| 0.0026 | 3.17 | 252 | 0.2358 | 0.95 |
| 0.0007 | 4.17 | 315 | 0.1724 | 0.97 |
| 0.0014 | 5.15 | 372 | 0.1644 | 0.97 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2