---
base_model: google/gemma-2-2b-it
datasets:
- GaetanMichelet/chat-60_ft_task-1_auto
- GaetanMichelet/chat-120_ft_task-1_auto
- GaetanMichelet/chat-180_ft_task-1_auto
library_name: peft
license: gemma
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Gemma-2-2B_task-1_180-samples_config-2_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-1_180-samples_config-2_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-1_auto, the GaetanMichelet/chat-120_ft_task-1_auto and the GaetanMichelet/chat-180_ft_task-1_auto datasets.
It achieves the following results on the evaluation set:
- Loss: 0.9777

## 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: 16
- total_train_batch_size: 16
- 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 |
|:-------------:|:-------:|:----:|:---------------:|
| 1.6536        | 0.9412  | 8    | 1.6148          |
| 1.2068        | 2.0     | 17   | 1.1807          |
| 1.099         | 2.9412  | 25   | 1.0637          |
| 0.9298        | 4.0     | 34   | 1.0063          |
| 0.831         | 4.9412  | 42   | 0.9777          |
| 0.7592        | 6.0     | 51   | 0.9821          |
| 0.5722        | 6.9412  | 59   | 1.0386          |
| 0.4793        | 8.0     | 68   | 1.2374          |
| 0.3157        | 8.9412  | 76   | 1.4530          |
| 0.2078        | 10.0    | 85   | 1.8075          |
| 0.1328        | 10.9412 | 93   | 2.0376          |
| 0.0699        | 12.0    | 102  | 2.2026          |


### Framework versions

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