metadata
library_name: transformers
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-vivit-d1
results: []
vivit-vivit-d1
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: 1.5318
- Accuracy: 0.8134
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: 12010
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0323 | 0.1 | 1201 | 1.9695 | 0.6636 |
| 1.051 | 1.1 | 2402 | 1.8521 | 0.7380 |
| 0.0027 | 2.1 | 3603 | 1.9220 | 0.6500 |
| 0.0008 | 3.1 | 4804 | 1.3982 | 0.7767 |
| 1.1999 | 4.1 | 6005 | 1.5625 | 0.6924 |
| 0.0004 | 5.1 | 7206 | 1.4784 | 0.7614 |
| 0.0188 | 6.1 | 8407 | 1.3777 | 0.7882 |
| 0.6328 | 7.1 | 9608 | 1.6121 | 0.7761 |
| 0.8161 | 8.1 | 10809 | 1.7552 | 0.7670 |
| 0.0001 | 9.1 | 12010 | 1.5318 | 0.8134 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3