|
--- |
|
license: mit |
|
base_model: microsoft/mdeberta-v3-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: acer_nitro_mdberta |
|
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. --> |
|
|
|
# acer_nitro_mdberta |
|
|
|
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7384 |
|
- F1: 0.7593 |
|
- Roc Auc: 0.8588 |
|
- Accuracy: 0.6506 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
|
| No log | 1.0 | 166 | 0.5907 | 0.7281 | 0.8497 | 0.5904 | |
|
| No log | 2.0 | 332 | 0.5260 | 0.6836 | 0.8576 | 0.5181 | |
|
| No log | 3.0 | 498 | 0.7023 | 0.7324 | 0.8381 | 0.6024 | |
|
| 0.3153 | 4.0 | 664 | 0.7848 | 0.7245 | 0.8168 | 0.5904 | |
|
| 0.3153 | 5.0 | 830 | 0.6979 | 0.7436 | 0.8666 | 0.5904 | |
|
| 0.3153 | 6.0 | 996 | 0.8550 | 0.7426 | 0.8337 | 0.6265 | |
|
| 0.1464 | 7.0 | 1162 | 0.7102 | 0.7830 | 0.8700 | 0.6747 | |
|
| 0.1464 | 8.0 | 1328 | 0.7172 | 0.7721 | 0.8662 | 0.6627 | |
|
| 0.1464 | 9.0 | 1494 | 0.7812 | 0.7664 | 0.8613 | 0.6506 | |
|
| 0.0781 | 10.0 | 1660 | 0.7384 | 0.7593 | 0.8588 | 0.6506 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
