---
base_model: google/gemma-2-27b-it
datasets:
- generator
library_name: peft
license: gemma
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: gemma2-27b-biomedical-5k
  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. -->

# gemma2-27b-biomedical-5k

This model is a fine-tuned version of [google/gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5773

## 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: 1
- eval_batch_size: 1
- seed: 42
- 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: 0.03
- num_epochs: 2

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.6151        | 0.1845 | 100  | 1.6014          |
| 1.58          | 0.3689 | 200  | 1.5931          |
| 1.6179        | 0.5534 | 300  | 1.5920          |
| 1.5615        | 0.7378 | 400  | 1.5806          |
| 1.5105        | 0.9223 | 500  | 1.5746          |
| 1.3345        | 1.1068 | 600  | 1.5904          |
| 1.3333        | 1.2912 | 700  | 1.5834          |
| 1.2613        | 1.4757 | 800  | 1.5847          |
| 1.2982        | 1.6601 | 900  | 1.5800          |
| 1.3027        | 1.8446 | 1000 | 1.5773          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.3.0
- Datasets 2.20.0
- Tokenizers 0.19.1