---
license: gemma
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: google/gemma-2b
datasets:
- generator
model-index:
- name: gemma2b-summarize-claude3sonnet-2k
  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. -->

# gemma2b-summarize-claude3sonnet-2k

This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5640

## 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
- distributed_type: multi-GPU
- num_devices: 3
- gradient_accumulation_steps: 2
- total_train_batch_size: 48
- total_eval_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.777         | 0.9231 | 6    | 2.9954          |
| 2.4096        | 2.0    | 13   | 2.7120          |
| 2.0954        | 2.9231 | 19   | 2.6309          |
| 1.7235        | 4.0    | 26   | 2.5914          |
| 1.5996        | 4.9231 | 32   | 2.5729          |
| 1.5071        | 6.0    | 39   | 2.5704          |
| 1.4254        | 6.9231 | 45   | 2.5704          |
| 1.3939        | 8.0    | 52   | 2.5644          |
| 1.3833        | 8.9231 | 58   | 2.5642          |
| 1.3864        | 9.2308 | 60   | 2.5640          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1