|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: MCG-NJU/videomae-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: videomae-base-finetuned-elderf1 |
|
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-elderf1 |
|
|
|
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: 1.7031 |
|
- Accuracy: 0.3481 |
|
|
|
## 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: 0.001 |
|
- 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: 720 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.7358 | 0.1 | 73 | 1.6923 | 0.3408 | |
|
| 1.7163 | 1.1 | 146 | 1.6662 | 0.3373 | |
|
| 1.7018 | 2.1 | 219 | 1.6378 | 0.3408 | |
|
| 1.7334 | 3.1 | 292 | 1.6563 | 0.3401 | |
|
| 1.672 | 4.1 | 365 | 1.6568 | 0.2398 | |
|
| 1.7095 | 5.1 | 438 | 1.6313 | 0.3387 | |
|
| 1.7119 | 6.1 | 511 | 1.6309 | 0.3408 | |
|
| 1.6981 | 7.1 | 584 | 1.6518 | 0.3289 | |
|
| 1.7066 | 8.1 | 657 | 1.6313 | 0.3310 | |
|
| 1.6476 | 9.09 | 720 | 1.6338 | 0.3289 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
