---
language:
- zh
license: gemma
library_name: peft
tags:
- trl
- sft
- nycu-112-2-deeplearning-hw2
- generated_from_trainer
base_model: google/gemma-1.1-7b-it
datasets:
- DandinPower/ZH-Reading-Comprehension-gemma-it
model-index:
- name: gemma_7b_lora_completion_only
  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. -->

# gemma_7b_lora_completion_only

This model is a fine-tuned version of [google/gemma-1.1-7b-it](https://huggingface.co/google/gemma-1.1-7b-it) on the DandinPower/ZH-Reading-Comprehension-gemma-it dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0885

## 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 700
- num_epochs: 3.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.1172        | 0.3690 | 250  | 0.0932          |
| 0.1059        | 0.7380 | 500  | 0.0997          |
| 0.0913        | 1.1070 | 750  | 0.1225          |
| 0.074         | 1.4760 | 1000 | 0.1046          |
| 0.0619        | 1.8450 | 1250 | 0.1084          |
| 0.0375        | 2.2140 | 1500 | 0.1038          |
| 0.0128        | 2.5830 | 1750 | 0.0993          |
| 0.044         | 2.9520 | 2000 | 0.0885          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1