|
--- |
|
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-diagnose |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# videomae-base-finetuned-ucf101-subset-diagnose |
|
|
|
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8572 |
|
- Accuracy: 0.5573 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- 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: 850 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 0.8885 | 0.1012 | 86 | 1.0729 | 0.3385 | |
|
| 0.9537 | 1.1012 | 172 | 0.9109 | 0.4120 | |
|
| 0.9089 | 2.1012 | 258 | 1.0296 | 0.2957 | |
|
| 1.0412 | 3.1012 | 344 | 1.1838 | 0.2991 | |
|
| 0.8928 | 4.1012 | 430 | 0.7726 | 0.6154 | |
|
| 0.7793 | 5.1012 | 516 | 0.7928 | 0.6444 | |
|
| 0.8378 | 6.1012 | 602 | 0.9475 | 0.5248 | |
|
| 0.7738 | 7.1012 | 688 | 0.9032 | 0.5504 | |
|
| 0.6334 | 8.1012 | 774 | 0.9769 | 0.5385 | |
|
| 0.4142 | 9.0894 | 850 | 0.8572 | 0.5573 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
