metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-ssbd-trim-yolo
results: []
videomae-base-ssbd-trim-yolo
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3670
- Accuracy: 0.7949
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: 2
- eval_batch_size: 2
- 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: 630
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9077 | 0.0683 | 43 | 1.1114 | 0.5278 |
| 1.0662 | 1.0683 | 86 | 1.4397 | 0.25 |
| 0.7166 | 2.0683 | 129 | 1.1111 | 0.5556 |
| 0.5385 | 3.0683 | 172 | 1.4677 | 0.6111 |
| 0.5025 | 4.0683 | 215 | 1.3852 | 0.6667 |
| 0.8695 | 5.0683 | 258 | 0.8738 | 0.8056 |
| 0.5152 | 6.0683 | 301 | 1.6813 | 0.6944 |
| 0.1175 | 7.0683 | 344 | 1.2260 | 0.8333 |
| 0.5459 | 8.0683 | 387 | 1.5197 | 0.75 |
| 0.0563 | 9.0683 | 430 | 1.8295 | 0.7222 |
| 0.2366 | 10.0683 | 473 | 1.2773 | 0.7778 |
| 0.0009 | 11.0683 | 516 | 1.4973 | 0.7778 |
| 0.143 | 12.0683 | 559 | 1.5192 | 0.7778 |
| 0.0016 | 13.0683 | 602 | 1.8634 | 0.7222 |
| 0.0185 | 14.0444 | 630 | 1.8943 | 0.7222 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1