|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: MCG-NJU/videomae-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: videomae-base-finetuned-chickenbehaviour |
|
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-chickenbehaviour |
|
|
|
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: 1.1091 |
|
- Accuracy: 0.6676 |
|
|
|
## 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: 25448 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 1.3916 | 0.12 | 3181 | 1.5101 | 0.5662 | |
|
| 1.566 | 1.12 | 6362 | 1.2704 | 0.6318 | |
|
| 1.5383 | 2.12 | 9543 | 1.2007 | 0.6452 | |
|
| 1.0339 | 3.12 | 12724 | 1.2358 | 0.6450 | |
|
| 1.0752 | 4.12 | 15905 | 1.1753 | 0.6641 | |
|
| 0.7721 | 5.12 | 19086 | 1.1413 | 0.6777 | |
|
| 0.9696 | 6.12 | 22267 | 1.2086 | 0.6733 | |
|
| 0.8068 | 7.12 | 25448 | 1.2041 | 0.6688 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.1 |
|
- Pytorch 2.1.0 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
