metadata
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-b-16x2-kinetics400-finetuned-temp-original
results: []
vivit-b-16x2-kinetics400-finetuned-temp-original
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: 1.1267
- Accuracy: 0.64
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: 420
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.3132 | 0.25 | 105 | 2.3486 | 0.14 |
| 1.8975 | 1.25 | 210 | 1.6591 | 0.42 |
| 1.423 | 2.25 | 315 | 1.2563 | 0.58 |
| 0.456 | 3.25 | 420 | 1.1267 | 0.64 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Tokenizers 0.19.1