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-ucf101-subset
results: []
videomae-base-finetuned-ucf101-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: 0.4111
- Accuracy: 0.8710
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: 16
- eval_batch_size: 16
- 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: 148
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.3295 | 0.13 | 19 | 2.1178 | 0.3 |
| 1.991 | 1.13 | 38 | 1.5624 | 0.5143 |
| 1.227 | 2.13 | 57 | 0.8621 | 0.7714 |
| 0.5665 | 3.13 | 76 | 0.6212 | 0.8 |
| 0.3487 | 4.13 | 95 | 0.3554 | 0.9286 |
| 0.1701 | 5.13 | 114 | 0.3597 | 0.8857 |
| 0.1036 | 6.13 | 133 | 0.2277 | 0.9286 |
| 0.089 | 7.1 | 148 | 0.1989 | 0.9143 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.2.0+cu121
- Datasets 2.11.0
- Tokenizers 0.15.1