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-lift-data-resize
results: []
videomae-base-finetuned-lift-data-resize
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: 0.7926
- Accuracy: 0.7972
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: 76
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6087 | 0.1316 | 10 | 1.8483 | 0.2597 |
| 1.3273 | 1.1316 | 20 | 1.4452 | 0.2983 |
| 1.2351 | 2.1316 | 30 | 1.5890 | 0.2799 |
| 1.1635 | 3.1316 | 40 | 1.3830 | 0.2910 |
| 1.0374 | 4.1316 | 50 | 1.3682 | 0.3002 |
| 0.9699 | 5.1316 | 60 | 1.2128 | 0.5322 |
| 0.8748 | 6.1316 | 70 | 1.0850 | 0.5562 |
| 0.8748 | 7.0789 | 76 | 1.0721 | 0.5599 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.1.1+cu118
- Datasets 3.0.1
- Tokenizers 0.20.1