---
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: cs221-deberta-v3-large-eng-pt
  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. -->

# cs221-deberta-v3-large-eng-pt

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: 0.3691
- F1: 0.7676
- Roc Auc: 0.8216
- Accuracy: 0.6034

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
| 0.4687        | 1.0   | 173  | 0.4601          | 0.4113 | 0.6309  | 0.3103   |
| 0.3504        | 2.0   | 346  | 0.3652          | 0.6879 | 0.7645  | 0.4397   |
| 0.2659        | 3.0   | 519  | 0.3636          | 0.7057 | 0.7616  | 0.4397   |
| 0.1696        | 4.0   | 692  | 0.3691          | 0.7676 | 0.8216  | 0.6034   |
| 0.1001        | 5.0   | 865  | 0.4142          | 0.7647 | 0.8246  | 0.5172   |
| 0.0699        | 6.0   | 1038 | 0.4698          | 0.7530 | 0.8034  | 0.4828   |
| 0.049         | 7.0   | 1211 | 0.5140          | 0.7219 | 0.7911  | 0.5      |
| 0.0253        | 8.0   | 1384 | 0.5917          | 0.7603 | 0.8191  | 0.5345   |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0