|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: deberta-large-ReqORNot |
|
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. --> |
|
|
|
# deberta-large-ReqORNot |
|
|
|
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5297 |
|
- Accuracy: 0.9135 |
|
- Weighted precision: 0.9135 |
|
- Weighted recall: 0.9135 |
|
- Weighted f1: 0.9134 |
|
- Macro precision: 0.9135 |
|
- Macro recall: 0.9128 |
|
- Macro f1: 0.9131 |
|
|
|
## 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: 3 |
|
- eval_batch_size: 3 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted precision | Weighted recall | Weighted f1 | Macro precision | Macro recall | Macro f1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------------------:|:---------------:|:-----------:|:---------------:|:------------:|:--------:| |
|
| 0.4826 | 1.0 | 1896 | 0.4286 | 0.9020 | 0.9020 | 0.9020 | 0.9019 | 0.9018 | 0.9014 | 0.9016 | |
|
| 0.3429 | 2.0 | 3792 | 0.4274 | 0.9077 | 0.9091 | 0.9077 | 0.9078 | 0.9076 | 0.9089 | 0.9076 | |
|
| 0.1299 | 3.0 | 5688 | 0.5297 | 0.9135 | 0.9135 | 0.9135 | 0.9134 | 0.9135 | 0.9128 | 0.9131 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
