|
|
---
|
|
|
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-doc-fold6
|
|
|
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-doc-fold6
|
|
|
|
|
|
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the course-doc-train-fold6 dataset.
|
|
|
It achieves the following results on the evaluation set:
|
|
|
- Loss: 0.0172
|
|
|
|
|
|
## 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 |
|
|
|
|:-------------:|:------:|:----:|:---------------:|
|
|
|
| 0.1126 | 0.3951 | 10 | 0.1260 |
|
|
|
| 0.0588 | 0.7901 | 20 | 0.0599 |
|
|
|
| 0.0306 | 1.1852 | 30 | 0.0334 |
|
|
|
| 0.0232 | 1.5802 | 40 | 0.0254 |
|
|
|
| 0.0189 | 1.9753 | 50 | 0.0215 |
|
|
|
| 0.0168 | 2.3704 | 60 | 0.0198 |
|
|
|
| 0.0201 | 2.7654 | 70 | 0.0184 |
|
|
|
| 0.0171 | 3.1605 | 80 | 0.0180 |
|
|
|
| 0.0153 | 3.5556 | 90 | 0.0177 |
|
|
|
| 0.0131 | 3.9506 | 100 | 0.0173 |
|
|
|
| 0.0143 | 4.3457 | 110 | 0.0173 |
|
|
|
| 0.0156 | 4.7407 | 120 | 0.0172 |
|
|
|
|
|
|
|
|
|
### Framework versions
|
|
|
|
|
|
- PEFT 0.12.0
|
|
|
- Transformers 4.46.1
|
|
|
- Pytorch 2.5.1+cu124
|
|
|
- Datasets 3.1.0
|
|
|
- Tokenizers 0.20.3 |
