metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf1012bovi-subset
results: []
videomae-base-finetuned-ucf1012bovi-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: 0.6819
- Accuracy: 0.6667
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: 280
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7118 | 0.13 | 36 | 0.6814 | 0.5714 |
| 0.8238 | 1.13 | 72 | 0.6641 | 0.5714 |
| 0.6892 | 2.13 | 108 | 0.6935 | 0.4762 |
| 0.7013 | 3.13 | 144 | 0.6819 | 0.6667 |
| 0.6871 | 4.13 | 180 | 0.6751 | 0.5714 |
| 0.7159 | 5.13 | 216 | 0.6854 | 0.5238 |
| 0.6884 | 6.13 | 252 | 0.6735 | 0.6667 |
| 0.6905 | 7.1 | 280 | 0.6739 | 0.6190 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2