|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: answerdotai/ModernBERT-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: ModernBERT_wine_quality_reviews_ft |
|
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. --> |
|
|
|
# ModernBERT_wine_quality_reviews_ft |
|
|
|
This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6800 |
|
- Accuracy: 0.6953 |
|
- F1: 0.6945 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:| |
|
| 1.2688 | 0.0590 | 250 | 1.1315 | 0.4781 | 0.4463 | |
|
| 1.0574 | 0.1181 | 500 | 0.9664 | 0.5575 | 0.5412 | |
|
| 0.9229 | 0.1771 | 750 | 0.8647 | 0.6070 | 0.6007 | |
|
| 0.8654 | 0.2361 | 1000 | 0.8665 | 0.6089 | 0.5922 | |
|
| 0.8229 | 0.2952 | 1250 | 0.7857 | 0.6448 | 0.6448 | |
|
| 0.8054 | 0.3542 | 1500 | 0.8515 | 0.6218 | 0.5993 | |
|
| 0.786 | 0.4132 | 1750 | 0.7533 | 0.6601 | 0.6552 | |
|
| 0.781 | 0.4723 | 2000 | 0.8133 | 0.6305 | 0.6278 | |
|
| 0.7563 | 0.5313 | 2250 | 0.7770 | 0.6480 | 0.6473 | |
|
| 0.7638 | 0.5903 | 2500 | 0.7248 | 0.6767 | 0.6769 | |
|
| 0.7384 | 0.6494 | 2750 | 0.7520 | 0.6597 | 0.6574 | |
|
| 0.7405 | 0.7084 | 3000 | 0.7615 | 0.6545 | 0.6515 | |
|
| 0.7222 | 0.7674 | 3250 | 0.7191 | 0.6790 | 0.6716 | |
|
| 0.7184 | 0.8264 | 3500 | 0.7037 | 0.6862 | 0.6837 | |
|
| 0.6984 | 0.8855 | 3750 | 0.7264 | 0.6716 | 0.6678 | |
|
| 0.6995 | 0.9445 | 4000 | 0.7455 | 0.6663 | 0.6646 | |
|
| 0.713 | 1.0035 | 4250 | 0.7294 | 0.6752 | 0.6701 | |
|
| 0.6508 | 1.0626 | 4500 | 0.6938 | 0.6872 | 0.6871 | |
|
| 0.642 | 1.1216 | 4750 | 0.7266 | 0.6716 | 0.6691 | |
|
| 0.635 | 1.1806 | 5000 | 0.6868 | 0.6913 | 0.6900 | |
|
| 0.6278 | 1.2397 | 5250 | 0.6800 | 0.6953 | 0.6945 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.1 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
