Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


my-szw-model - bnb 4bits
- Model creator: https://huggingface.co/marc4gov/
- Original model: https://huggingface.co/marc4gov/my-szw-model/




Original model description:
---
library_name: transformers
license: mit
base_model: BramVanroy/fietje-2-instruct
tags:
- generated_from_trainer
model-index:
- name: my-szw-model
  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. -->

# my-szw-model

This model is a fine-tuned version of [BramVanroy/fietje-2-instruct](https://huggingface.co/BramVanroy/fietje-2-instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3317

## 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
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log        | 1.0   | 67   | 1.1677          |
| No log        | 2.0   | 134  | 1.2020          |
| No log        | 3.0   | 201  | 1.3317          |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3