---
license: gemma
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
base_model: google/gemma-2b
datasets:
- llama-duo/synth_summarize_dataset_dedup
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 llama-duo/synth_summarize_dataset_dedup dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5425

## 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: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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: 15

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 1.2724        | 0.9952  | 104  | 2.5531          |
| 1.0792        | 2.0     | 209  | 2.4752          |
| 1.0312        | 2.9952  | 313  | 2.4632          |
| 0.9957        | 4.0     | 418  | 2.4705          |
| 0.9775        | 4.9952  | 522  | 2.4764          |
| 0.9584        | 6.0     | 627  | 2.4870          |
| 0.9368        | 6.9952  | 731  | 2.4975          |
| 0.93          | 8.0     | 836  | 2.5067          |
| 0.9195        | 8.9952  | 940  | 2.5168          |
| 0.912         | 10.0    | 1045 | 2.5271          |
| 0.9003        | 10.9952 | 1149 | 2.5356          |
| 0.9032        | 12.0    | 1254 | 2.5401          |
| 0.9006        | 12.9952 | 1358 | 2.5426          |
| 0.9007        | 14.0    | 1463 | 2.5433          |
| 0.896         | 14.9282 | 1560 | 2.5425          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.40.1
- Pytorch 2.2.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1