metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-subset
results: []
videomae-base-finetuned-subset
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: 0.5077
- Accuracy: 0.8362
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: 8
- eval_batch_size: 8
- 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: 572
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.537 | 0.13 | 72 | 1.3526 | 0.3691 |
| 1.3677 | 1.13 | 144 | 1.0690 | 0.6094 |
| 1.0818 | 2.13 | 216 | 0.6865 | 0.8069 |
| 1.1608 | 3.13 | 288 | 0.6642 | 0.7682 |
| 0.9544 | 4.13 | 360 | 0.6866 | 0.7511 |
| 0.896 | 5.13 | 432 | 0.5387 | 0.8112 |
| 0.9193 | 6.13 | 504 | 0.5693 | 0.7897 |
| 0.6941 | 7.12 | 572 | 0.4813 | 0.8541 |
Framework versions
- Transformers 4.35.2
- Pytorch 1.13.1
- Datasets 2.15.0
- Tokenizers 0.15.0