---
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta-v3-base-zeroshot-v1.1-all_except_nli
  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-v3-base-zeroshot-v1.1-all_except_nli

This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2417
- F1 Macro: 0.2126
- F1 Micro: 0.3007
- Accuracy Balanced: 0.2519
- Accuracy: 0.3007
- Precision Macro: 0.4936
- Recall Macro: 0.2519
- Precision Micro: 0.3007
- Recall Micro: 0.3007

## 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: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step  | Validation Loss | F1 Macro | F1 Micro | Accuracy Balanced | Accuracy | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
| 0.2189        | 1.0   | 27664 | 0.3587          | 0.8454   | 0.8604   | 0.8427            | 0.8604   | 0.8486          | 0.8427       | 0.8604          | 0.8604       |
| 0.1704        | 2.0   | 55328 | 0.3941          | 0.8525   | 0.8669   | 0.8493            | 0.8669   | 0.8561          | 0.8493       | 0.8669          | 0.8669       |
| 0.1219        | 3.0   | 82992 | 0.4436          | 0.8543   | 0.8679   | 0.8528            | 0.8679   | 0.8559          | 0.8528       | 0.8679          | 0.8679       |


### Framework versions

- Transformers 4.33.3
- Pytorch 1.11.0+cu113
- Datasets 2.14.6
- Tokenizers 0.12.1