---
license: gemma
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: google/gemma-7b
datasets:
- generator
model-index:
- name: gemma7b-summarize-gpt4o-8k
  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. -->

# gemma7b-summarize-gpt4o-8k

This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 4.5136

## 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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.7584        | 1.0   | 51   | 2.7736          |
| 1.0801        | 2.0   | 102  | 2.5391          |
| 0.9341        | 3.0   | 153  | 2.5877          |
| 0.7796        | 4.0   | 204  | 2.6409          |
| 0.6583        | 5.0   | 255  | 2.8397          |
| 0.4945        | 6.0   | 306  | 3.1891          |
| 0.3891        | 7.0   | 357  | 3.7245          |
| 0.3029        | 8.0   | 408  | 4.1951          |
| 0.259         | 9.0   | 459  | 4.4996          |
| 0.2532        | 10.0  | 510  | 4.5136          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1