|
|
---
|
|
|
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-fold3
|
|
|
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-fold3
|
|
|
|
|
|
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: 0.0318
|
|
|
|
|
|
## 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 |
|
|
|
|:-------------:|:------:|:----:|:---------------:|
|
|
|
| 0.8727 | 0.0770 | 50 | 0.6954 |
|
|
|
| 0.1562 | 0.1539 | 100 | 0.1078 |
|
|
|
| 0.0876 | 0.2309 | 150 | 0.0732 |
|
|
|
| 0.0737 | 0.3078 | 200 | 0.0559 |
|
|
|
| 0.0549 | 0.3848 | 250 | 0.0525 |
|
|
|
| 0.0519 | 0.4617 | 300 | 0.0490 |
|
|
|
| 0.0448 | 0.5387 | 350 | 0.0468 |
|
|
|
| 0.0605 | 0.6156 | 400 | 0.0437 |
|
|
|
| 0.0356 | 0.6926 | 450 | 0.0433 |
|
|
|
| 0.0304 | 0.7695 | 500 | 0.0394 |
|
|
|
| 0.0469 | 0.8465 | 550 | 0.0378 |
|
|
|
| 0.0368 | 0.9234 | 600 | 0.0370 |
|
|
|
| 0.0333 | 1.0004 | 650 | 0.0361 |
|
|
|
| 0.0359 | 1.0773 | 700 | 0.0380 |
|
|
|
| 0.0296 | 1.1543 | 750 | 0.0354 |
|
|
|
| 0.0299 | 1.2312 | 800 | 0.0345 |
|
|
|
| 0.0333 | 1.3082 | 850 | 0.0358 |
|
|
|
| 0.0202 | 1.3851 | 900 | 0.0339 |
|
|
|
| 0.0393 | 1.4621 | 950 | 0.0345 |
|
|
|
| 0.0338 | 1.5391 | 1000 | 0.0335 |
|
|
|
| 0.0333 | 1.6160 | 1050 | 0.0336 |
|
|
|
| 0.032 | 1.6930 | 1100 | 0.0353 |
|
|
|
| 0.0206 | 1.7699 | 1150 | 0.0338 |
|
|
|
| 0.0206 | 1.8469 | 1200 | 0.0347 |
|
|
|
| 0.0285 | 1.9238 | 1250 | 0.0343 |
|
|
|
| 0.0217 | 2.0008 | 1300 | 0.0319 |
|
|
|
| 0.0162 | 2.0777 | 1350 | 0.0335 |
|
|
|
| 0.0283 | 2.1547 | 1400 | 0.0357 |
|
|
|
| 0.0131 | 2.2316 | 1450 | 0.0363 |
|
|
|
| 0.0194 | 2.3086 | 1500 | 0.0337 |
|
|
|
| 0.0155 | 2.3855 | 1550 | 0.0360 |
|
|
|
| 0.017 | 2.4625 | 1600 | 0.0340 |
|
|
|
| 0.0215 | 2.5394 | 1650 | 0.0325 |
|
|
|
| 0.0185 | 2.6164 | 1700 | 0.0329 |
|
|
|
| 0.0275 | 2.6933 | 1750 | 0.0318 |
|
|
|
| 0.0243 | 2.7703 | 1800 | 0.0345 |
|
|
|
| 0.0231 | 2.8472 | 1850 | 0.0318 |
|
|
|
| 0.0157 | 2.9242 | 1900 | 0.0326 |
|
|
|
| 0.0287 | 3.0012 | 1950 | 0.0324 |
|
|
|
| 0.0123 | 3.0781 | 2000 | 0.0347 |
|
|
|
| 0.0079 | 3.1551 | 2050 | 0.0378 |
|
|
|
| 0.008 | 3.2320 | 2100 | 0.0400 |
|
|
|
| 0.011 | 3.3090 | 2150 | 0.0393 |
|
|
|
| 0.0141 | 3.3859 | 2200 | 0.0384 |
|
|
|
| 0.0088 | 3.4629 | 2250 | 0.0384 |
|
|
|
| 0.0113 | 3.5398 | 2300 | 0.0379 |
|
|
|
| 0.0048 | 3.6168 | 2350 | 0.0388 |
|
|
|
| 0.0136 | 3.6937 | 2400 | 0.0375 |
|
|
|
| 0.0069 | 3.7707 | 2450 | 0.0377 |
|
|
|
| 0.0113 | 3.8476 | 2500 | 0.0389 |
|
|
|
| 0.0117 | 3.9246 | 2550 | 0.0394 |
|
|
|
| 0.0086 | 4.0015 | 2600 | 0.0393 |
|
|
|
| 0.0016 | 4.0785 | 2650 | 0.0409 |
|
|
|
| 0.0049 | 4.1554 | 2700 | 0.0432 |
|
|
|
| 0.0027 | 4.2324 | 2750 | 0.0449 |
|
|
|
| 0.0025 | 4.3093 | 2800 | 0.0456 |
|
|
|
| 0.0022 | 4.3863 | 2850 | 0.0468 |
|
|
|
| 0.0032 | 4.4633 | 2900 | 0.0470 |
|
|
|
| 0.0021 | 4.5402 | 2950 | 0.0471 |
|
|
|
| 0.002 | 4.6172 | 3000 | 0.0475 |
|
|
|
| 0.0017 | 4.6941 | 3050 | 0.0478 |
|
|
|
| 0.0017 | 4.7711 | 3100 | 0.0480 |
|
|
|
| 0.0066 | 4.8480 | 3150 | 0.0478 |
|
|
|
| 0.0017 | 4.9250 | 3200 | 0.0480 |
|
|
|
|
|
|
|
|
|
### Framework versions
|
|
|
|
|
|
- PEFT 0.12.0
|
|
|
- Transformers 4.46.1
|
|
|
- Pytorch 2.5.1+cu124
|
|
|
- Datasets 3.1.0
|
|
|
- Tokenizers 0.20.3 |
