---
base_model: google/gemma-2-2b-it
datasets:
- GaetanMichelet/chat-60_ft_task-3
library_name: peft
license: gemma
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Gemma-2-2B_task-3_60-samples_config-1
  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. -->

# Gemma-2-2B_task-3_60-samples_config-1

This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the GaetanMichelet/chat-60_ft_task-3 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4227

## 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 3.2369        | 0.8696  | 5    | 3.1359          |
| 2.5226        | 1.9130  | 11   | 1.7106          |
| 1.1016        | 2.9565  | 17   | 0.7912          |
| 0.45          | 4.0     | 23   | 0.5232          |
| 0.3492        | 4.8696  | 28   | 0.4661          |
| 0.2407        | 5.9130  | 34   | 0.4271          |
| 0.2032        | 6.9565  | 40   | 0.4227          |
| 0.2575        | 8.0     | 46   | 0.4339          |
| 0.1486        | 8.8696  | 51   | 0.4843          |
| 0.0961        | 9.9130  | 57   | 0.5847          |
| 0.0285        | 10.9565 | 63   | 0.7613          |
| 0.0231        | 12.0    | 69   | 0.8747          |
| 0.0118        | 12.8696 | 74   | 0.9379          |
| 0.0095        | 13.9130 | 80   | 1.0329          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1