---
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: google/gemma-2b-it
model-index:
- name: outputs
  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. -->

# outputs

This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0962

## 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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.5696        | 0.93  | 7    | 2.3790          |
| 1.7335        | 2.0   | 15   | 1.6733          |
| 1.5583        | 2.93  | 22   | 1.5446          |
| 1.1347        | 4.0   | 30   | 1.5097          |
| 1.0502        | 4.93  | 37   | 1.5663          |
| 0.7217        | 6.0   | 45   | 1.6769          |
| 0.6408        | 6.93  | 52   | 1.8386          |
| 0.43          | 8.0   | 60   | 1.9674          |
| 0.391         | 8.93  | 67   | 2.0831          |
| 0.2893        | 9.33  | 70   | 2.0962          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2