---
library_name: peft
license: mit
base_model: deepset/gbert-base
tags:
- base_model:adapter:deepset/gbert-base
- lora
- transformers
metrics:
- accuracy
model-index:
- name: gbert_success4_lora
  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. -->

# gbert_success4_lora

This model is a fine-tuned version of [deepset/gbert-base](https://huggingface.co/deepset/gbert-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6821
- Accuracy: 0.5788
- Macro F1: 0.5714

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
| 0.7478        | 1.0   | 340  | 0.7106          | 0.5729   | 0.5461   |
| 0.6929        | 2.0   | 680  | 0.6870          | 0.5773   | 0.5744   |
| 0.6908        | 3.0   | 1020 | 0.6821          | 0.5788   | 0.5714   |


### Framework versions

- PEFT 0.17.1
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0