---
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: SanjiWatsuki/zephyrnt-3.8b
model-index:
- name: Neuvil
  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. -->

# Neuvil

This model is a fine-tuned version of [SanjiWatsuki/zephyrnt-3.8b](https://huggingface.co/SanjiWatsuki/zephyrnt-3.8b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9512

## 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: 3e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 100
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.1364        | 2.3256 | 50   | 1.3813          |
| 1.1532        | 4.6512 | 100  | 0.9512          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1