|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: ustc-community/dfine-small-coco |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: dfine-test |
|
|
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. --> |
|
|
|
|
|
# dfine-test |
|
|
|
|
|
This model is a fine-tuned version of [ustc-community/dfine-small-coco](https://huggingface.co/ustc-community/dfine-small-coco) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.0724 |
|
|
|
|
|
## 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: 0.0002 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 20.1936 | 1.0 | 712 | 2.6821 | |
|
|
| 19.1183 | 2.0 | 1424 | 2.3533 | |
|
|
| 16.1951 | 3.0 | 2136 | 1.7233 | |
|
|
| 14.4265 | 4.0 | 2848 | 1.9414 | |
|
|
| 14.3184 | 5.0 | 3560 | 2.3461 | |
|
|
| 14.5909 | 6.0 | 4272 | 2.0509 | |
|
|
| 14.6728 | 7.0 | 4984 | 2.0568 | |
|
|
| 14.3686 | 8.0 | 5696 | 2.1048 | |
|
|
| 14.6144 | 9.0 | 6408 | 2.0980 | |
|
|
| 14.4749 | 10.0 | 7120 | 2.0721 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.52.0.dev0 |
|
|
- Pytorch 2.7.0+cu126 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
