---
title: test_lora
canonical_url: "https://www.modelscope.cn/models/walker31350430a/test_lora"
md_url: "https://www.modelscope.cn/models/walker31350430a/test_lora.md"
repository: walker31350430a/test_lora
last_updated: 2024-01-30
license: other
parameters: 1.9M
tensor_type:
  - F32
library_name:
  - lora
  - safetensors
downloads: 45
stars: 0
tags:
  - llama-factory
  - lora
  - generated_from_trainer
---

# test_lora

> test_lora - walker31350430a 在 ModelScope 开源的模型。This model is a fine-tuned version of /home/openlab/workspace/ModelZoo-PyTorch/PyTorch/built-in/foundation/ChatGLM2-6B/model on the clstestlr dataset.

walker31350430a/test_lora 是 ModelScope 魔搭社区上的 1.9M 参数机器学习模型，采用 other 许可。

- **Repository**: walker31350430a/test_lora
- **License**: other
- **Parameters**: 1.9M
- **Tags**: llama-factory, lora, generated_from_trainer
- **Downloads**: 45
- **Stars**: 0
- **Last updated**: 2024-01-30

Source: https://www.modelscope.cn/models/walker31350430a/test_lora

---

<!-- 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. -->

# glm2_fin_cls_diff_best

This model is a fine-tuned version of [/home/openlab/workspace/ModelZoo-PyTorch/PyTorch/built-in/foundation/ChatGLM2-6B/model](https://huggingface.co//home/openlab/workspace/ModelZoo-PyTorch/PyTorch/built-in/foundation/ChatGLM2-6B/model) on the cls_test_lr dataset.

## 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: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
- mixed_precision_training: Native AMP

### Training results



### Framework versions

- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.0
- Datasets 2.16.1
- Tokenizers 0.15.1