|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: MCG-NJU/videomae-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: videomae-base-finetuned-SLT-subset |
|
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-SLT-subset |
|
|
|
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: 0.4622 |
|
- Accuracy: 0.975 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- 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: 960 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 3.8796 | 0.06 | 60 | 3.6666 | 0.05 | |
|
| 3.8535 | 1.06 | 120 | 3.4913 | 0.05 | |
|
| 3.7537 | 2.06 | 180 | 3.3941 | 0.075 | |
|
| 3.5163 | 3.06 | 240 | 3.3433 | 0.075 | |
|
| 3.4903 | 4.06 | 300 | 3.2711 | 0.075 | |
|
| 3.4318 | 5.06 | 360 | 3.2221 | 0.1 | |
|
| 3.0782 | 6.06 | 420 | 3.1301 | 0.225 | |
|
| 3.3261 | 7.06 | 480 | 2.9363 | 0.475 | |
|
| 2.8341 | 8.06 | 540 | 2.5592 | 0.5 | |
|
| 2.4863 | 9.06 | 600 | 1.8678 | 0.8 | |
|
| 1.7275 | 10.06 | 660 | 1.2153 | 0.925 | |
|
| 1.2468 | 11.06 | 720 | 0.9454 | 0.95 | |
|
| 0.871 | 12.06 | 780 | 0.7030 | 0.975 | |
|
| 0.6857 | 13.06 | 840 | 0.5486 | 0.95 | |
|
| 0.6182 | 14.06 | 900 | 0.4743 | 1.0 | |
|
| 0.3517 | 15.06 | 960 | 0.4622 | 0.975 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
