---
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- lora
- generated_from_trainer
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
model-index:
- name: Qwen2.5-7B-Instruct-PsyCourse-fold10
  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. -->

# Qwen2.5-7B-Instruct-PsyCourse-fold10

This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the course-train-fold1 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0316

## 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
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.8737        | 0.0770 | 50   | 0.6946          |
| 0.1557        | 0.1539 | 100  | 0.1078          |
| 0.0875        | 0.2309 | 150  | 0.0731          |
| 0.0735        | 0.3078 | 200  | 0.0561          |
| 0.0547        | 0.3848 | 250  | 0.0530          |
| 0.052         | 0.4617 | 300  | 0.0499          |
| 0.047         | 0.5387 | 350  | 0.0469          |
| 0.0618        | 0.6156 | 400  | 0.0442          |
| 0.0357        | 0.6926 | 450  | 0.0448          |
| 0.0314        | 0.7695 | 500  | 0.0402          |
| 0.0476        | 0.8465 | 550  | 0.0388          |
| 0.0367        | 0.9234 | 600  | 0.0375          |
| 0.031         | 1.0004 | 650  | 0.0365          |
| 0.0368        | 1.0773 | 700  | 0.0376          |
| 0.0299        | 1.1543 | 750  | 0.0356          |
| 0.0296        | 1.2312 | 800  | 0.0348          |
| 0.0345        | 1.3082 | 850  | 0.0345          |
| 0.0203        | 1.3851 | 900  | 0.0336          |
| 0.0406        | 1.4621 | 950  | 0.0341          |
| 0.0333        | 1.5391 | 1000 | 0.0332          |
| 0.0327        | 1.6160 | 1050 | 0.0328          |
| 0.0329        | 1.6930 | 1100 | 0.0344          |
| 0.021         | 1.7699 | 1150 | 0.0330          |
| 0.021         | 1.8469 | 1200 | 0.0348          |
| 0.0293        | 1.9238 | 1250 | 0.0337          |
| 0.0229        | 2.0008 | 1300 | 0.0316          |
| 0.0163        | 2.0777 | 1350 | 0.0331          |
| 0.0355        | 2.1547 | 1400 | 0.0345          |
| 0.0129        | 2.2316 | 1450 | 0.0364          |
| 0.0188        | 2.3086 | 1500 | 0.0345          |
| 0.0158        | 2.3855 | 1550 | 0.0369          |
| 0.0158        | 2.4625 | 1600 | 0.0337          |
| 0.0219        | 2.5394 | 1650 | 0.0327          |
| 0.0171        | 2.6164 | 1700 | 0.0321          |
| 0.0266        | 2.6933 | 1750 | 0.0318          |
| 0.0244        | 2.7703 | 1800 | 0.0336          |
| 0.0231        | 2.8472 | 1850 | 0.0317          |
| 0.0186        | 2.9242 | 1900 | 0.0319          |
| 0.0296        | 3.0012 | 1950 | 0.0318          |
| 0.0102        | 3.0781 | 2000 | 0.0352          |
| 0.0088        | 3.1551 | 2050 | 0.0395          |
| 0.0099        | 3.2320 | 2100 | 0.0376          |
| 0.0088        | 3.3090 | 2150 | 0.0391          |
| 0.0138        | 3.3859 | 2200 | 0.0379          |
| 0.008         | 3.4629 | 2250 | 0.0388          |
| 0.0112        | 3.5398 | 2300 | 0.0395          |
| 0.0045        | 3.6168 | 2350 | 0.0386          |
| 0.0127        | 3.6937 | 2400 | 0.0393          |
| 0.0074        | 3.7707 | 2450 | 0.0397          |
| 0.0102        | 3.8476 | 2500 | 0.0399          |
| 0.0105        | 3.9246 | 2550 | 0.0410          |
| 0.0085        | 4.0015 | 2600 | 0.0412          |
| 0.002         | 4.0785 | 2650 | 0.0426          |
| 0.0051        | 4.1554 | 2700 | 0.0453          |
| 0.0024        | 4.2324 | 2750 | 0.0468          |
| 0.0022        | 4.3093 | 2800 | 0.0478          |
| 0.0031        | 4.3863 | 2850 | 0.0489          |
| 0.0042        | 4.4633 | 2900 | 0.0493          |
| 0.0017        | 4.5402 | 2950 | 0.0495          |
| 0.0025        | 4.6172 | 3000 | 0.0499          |
| 0.0025        | 4.6941 | 3050 | 0.0499          |
| 0.0022        | 4.7711 | 3100 | 0.0500          |
| 0.0048        | 4.8480 | 3150 | 0.0500          |
| 0.002         | 4.9250 | 3200 | 0.0501          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3