metadata
library_name: transformers
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: 0.7852
- Accuracy: 0.7857
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: 380
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3762 | 0.1 | 38 | 1.4490 | 0.2857 |
| 1.2421 | 1.1 | 76 | 1.3190 | 0.4286 |
| 0.8753 | 2.1 | 114 | 0.9506 | 0.5714 |
| 0.4285 | 3.1 | 152 | 0.5580 | 0.7857 |
| 0.3808 | 4.1 | 190 | 0.4951 | 0.8571 |
| 0.1368 | 5.1 | 228 | 0.1578 | 0.9286 |
| 0.043 | 6.1 | 266 | 0.0475 | 1.0 |
| 0.0842 | 7.1 | 304 | 0.0624 | 1.0 |
| 0.003 | 8.1 | 342 | 0.0557 | 1.0 |
| 0.0828 | 9.1 | 380 | 0.0446 | 1.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.0.1+cu117
- Datasets 3.1.0
- Tokenizers 0.19.1