# glm4-lora-gitee-docs-9b

**Repository Path**: stringify/glm4-lora-gitee-docs-9b

## Basic Information

- **Project Name**: glm4-lora-gitee-docs-9b
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2024-07-30
- **Last Updated**: 2024-10-14

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

---
base_model: hf-models/glm-4-9b-chat
library_name: peft
license: other
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: glm4-lora-gitee-docs-9b
  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. -->

# glm4-lora-gitee-docs-9b

This model is a fine-tuned version of [hf-models/glm-4-9b-chat](https://huggingface.co/hf-models/glm-4-9b-chat) on the gitee-docs-alpaca dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1982

## 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: 8e-06
- 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: 0.1
- num_epochs: 8.2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.3907        | 1.4286 | 100  | 1.4320          |
| 1.2718        | 2.8571 | 200  | 1.2930          |
| 1.2982        | 4.2857 | 300  | 1.2303          |
| 1.1174        | 5.7143 | 400  | 1.1990          |
| 1.1523        | 7.1429 | 500  | 1.1966          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.43.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1