|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: MCG-NJU/videomae-base-finetuned-ssv2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: videomae-base-finetuned-ssv2-finetuned-traffic-dataset-mae |
|
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-ssv2-finetuned-traffic-dataset-mae |
|
|
|
This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-ssv2](https://huggingface.co/MCG-NJU/videomae-base-finetuned-ssv2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.1259 |
|
- Accuracy: 0.41 |
|
|
|
## 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: 608 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.0309 | 0.12 | 76 | 0.3008 | 0.9130 | |
|
| 0.0002 | 1.12 | 152 | 2.1030 | 0.6667 | |
|
| 0.0001 | 2.12 | 228 | 1.8458 | 0.7101 | |
|
| 0.0 | 3.12 | 304 | 1.5200 | 0.7391 | |
|
| 0.0001 | 4.12 | 380 | 1.4569 | 0.7536 | |
|
| 0.0 | 5.12 | 456 | 0.3941 | 0.9275 | |
|
| 0.0001 | 6.12 | 532 | 0.9658 | 0.8696 | |
|
| 0.0001 | 7.12 | 608 | 0.9836 | 0.8406 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.2 |
|
|
