metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-SSBD_Augm_v2
results: []
videomae-base-finetuned-SSBD_Augm_v2
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: 0.9006
- Accuracy: 0.6190
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: 12
- eval_batch_size: 12
- 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: 350
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0891 | 0.12 | 42 | 0.9088 | 0.6 |
| 1.0414 | 1.12 | 84 | 1.1233 | 0.4 |
| 0.7054 | 2.12 | 126 | 1.0407 | 0.44 |
| 1.0071 | 3.12 | 168 | 1.6254 | 0.2 |
| 0.2627 | 4.12 | 210 | 2.7735 | 0.24 |
| 0.0226 | 5.12 | 252 | 4.1474 | 0.12 |
| 0.0065 | 6.12 | 294 | 4.5980 | 0.08 |
| 0.012 | 7.12 | 336 | 4.6877 | 0.08 |
| 0.0027 | 8.04 | 350 | 4.6653 | 0.08 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3