metadata
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: vivit-b-16x2-kinetics400-finetuned-cremad
results: []
vivit-b-16x2-kinetics400-finetuned-cremad
This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on CREMA-D dataset. It achieves the following results on the evaluation set:
- Loss: 1.1824
- Accuracy: 0.6575
- F1: 0.6595
- Recall: 0.6575
- Precision: 0.6676
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: 0.0001
- 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: 11906
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
|---|---|---|---|---|---|---|---|
| 1.54 | 0.5 | 5953 | 1.7615 | 0.4614 | 0.4420 | 0.4614 | 0.5095 |
| 0.7419 | 1.5 | 11906 | 1.1824 | 0.6575 | 0.6595 | 0.6575 | 0.6676 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1