---
base_model: google/gemma-2-2b-it
datasets:
- GaetanMichelet/chat-60_ft_task-2_auto
- GaetanMichelet/chat-120_ft_task-2_auto
library_name: peft
license: gemma
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Gemma-2-2B_task-2_120-samples_config-1_auto
  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-2_120-samples_config-1_auto

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-2_auto and the GaetanMichelet/chat-120_ft_task-2_auto datasets.
It achieves the following results on the evaluation set:
- Loss: 0.6440

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.9373        | 1.0   | 11   | 0.9925          |
| 0.7244        | 2.0   | 22   | 0.8189          |
| 0.6269        | 3.0   | 33   | 0.7204          |
| 0.588         | 4.0   | 44   | 0.6696          |
| 0.526         | 5.0   | 55   | 0.6440          |
| 0.4669        | 6.0   | 66   | 0.6452          |
| 0.3682        | 7.0   | 77   | 0.7009          |
| 0.2714        | 8.0   | 88   | 0.8050          |
| 0.1657        | 9.0   | 99   | 1.0494          |
| 0.076         | 10.0  | 110  | 1.1584          |
| 0.0507        | 11.0  | 121  | 1.3445          |
| 0.0346        | 12.0  | 132  | 1.3441          |


### Framework versions

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