metadata
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-b-16x2-kinetics400-finetuned-ucf101-subset-without-pretrained
results: []
vivit-b-16x2-kinetics400-finetuned-ucf101-subset-without-pretrained
This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1644
- Accuracy: 0.4138
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 |
|---|---|---|---|---|
| 3.2964 | 0.1 | 300 | 2.4749 | 0.1081 |
| 3.1346 | 1.1 | 600 | 2.4779 | 0.1081 |
| 1.9796 | 2.1 | 900 | 2.4339 | 0.2973 |
| 1.8692 | 3.1 | 1200 | 2.1774 | 0.3243 |
| 1.3617 | 4.1 | 1500 | 2.1613 | 0.3243 |
| 2.0821 | 5.1 | 1800 | 1.9207 | 0.2162 |
| 1.5534 | 6.1 | 2100 | 2.2003 | 0.3514 |
| 0.5632 | 7.1 | 2400 | 3.0211 | 0.3514 |
| 0.2806 | 8.1 | 2700 | 2.7735 | 0.3514 |
| 1.3832 | 9.1 | 3000 | 2.9315 | 0.3514 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2