metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/timesformer-base-finetuned-k400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-timesformer-d2
results: []
vivit-timesformer-d2
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: 2.8173
- Accuracy: 0.3661
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 6650
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.3794 | 0.1 | 665 | 2.4547 | 0.1440 |
| 2.5787 | 1.1 | 1330 | 2.5065 | 0.2607 |
| 2.4653 | 2.1 | 1995 | 2.1117 | 0.3874 |
| 2.3267 | 3.1 | 2660 | 2.3863 | 0.3567 |
| 1.6617 | 4.1 | 3325 | 2.2500 | 0.3956 |
| 1.3649 | 5.1 | 3990 | 2.7407 | 0.3711 |
| 0.2922 | 6.1 | 4655 | 2.5032 | 0.4152 |
| 0.6021 | 7.1 | 5320 | 3.3270 | 0.3529 |
| 0.7572 | 8.1 | 5985 | 2.9130 | 0.4129 |
| 1.1826 | 9.1 | 6650 | 2.8173 | 0.3661 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3