---
license: gemma
library_name: peft
tags:
- trl
- sft
- alignment-handbook
- generated_from_trainer
base_model: google/gemma-2b
datasets:
- generator
model-index:
- name: gemma2b-summarize-gemini1_5flash-64k
  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-gemini1_5flash-64k

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: 2.7154

## 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: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- total_eval_batch_size: 128
- 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 |
|:-------------:|:-------:|:----:|:---------------:|
| 1.518         | 0.9905  | 52   | 2.7709          |
| 1.1423        | 2.0     | 105  | 2.6595          |
| 1.0681        | 2.9905  | 157  | 2.6406          |
| 1.0335        | 4.0     | 210  | 2.6427          |
| 1.0079        | 4.9905  | 262  | 2.6459          |
| 0.9837        | 6.0     | 315  | 2.6574          |
| 0.966         | 6.9905  | 367  | 2.6700          |
| 0.9474        | 8.0     | 420  | 2.6799          |
| 0.9406        | 8.9905  | 472  | 2.6883          |
| 0.9245        | 10.0    | 525  | 2.6975          |
| 0.9208        | 10.9905 | 577  | 2.7079          |
| 0.9195        | 12.0    | 630  | 2.7148          |
| 0.9212        | 12.9905 | 682  | 2.7154          |


### Framework versions

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