---
license: gemma
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
base_model: google/gemma-1.1-2b-it
datasets:
- llama-duo/synth_summarize_dataset_dedup
model-index:
- name: gemma2b-it-1.1-summarize-gpt4o-256k
  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-it-1.1-summarize-gpt4o-256k

This model is a fine-tuned version of [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it) on the llama-duo/synth_summarize_dataset_dedup dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7127

## 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: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 32
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.9633        | 0.9976 | 206  | 2.6959          |
| 0.865         | 2.0    | 413  | 2.6511          |
| 0.8266        | 2.9976 | 619  | 2.6475          |
| 0.7953        | 4.0    | 826  | 2.6603          |
| 0.7708        | 4.9976 | 1032 | 2.6720          |
| 0.75          | 6.0    | 1239 | 2.6898          |
| 0.7446        | 6.9976 | 1445 | 2.7026          |
| 0.7301        | 8.0    | 1652 | 2.7081          |
| 0.7268        | 8.9976 | 1858 | 2.7128          |
| 0.7318        | 9.9758 | 2060 | 2.7127          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1