|
|
--- |
|
|
library_name: peft |
|
|
license: other |
|
|
base_model: mistralai/Ministral-8B-Instruct-2410 |
|
|
tags: |
|
|
- llama-factory |
|
|
- lora |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: Ministral-8B-Instruct-2410-PsyCourse-fold9 |
|
|
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. --> |
|
|
|
|
|
# Ministral-8B-Instruct-2410-PsyCourse-fold9 |
|
|
|
|
|
This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) on the course-train-fold1 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0315 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.2581 | 0.0770 | 50 | 0.2416 | |
|
|
| 0.0851 | 0.1539 | 100 | 0.0693 | |
|
|
| 0.0612 | 0.2309 | 150 | 0.0587 | |
|
|
| 0.0576 | 0.3078 | 200 | 0.0537 | |
|
|
| 0.0438 | 0.3848 | 250 | 0.0431 | |
|
|
| 0.0407 | 0.4617 | 300 | 0.0459 | |
|
|
| 0.0433 | 0.5387 | 350 | 0.0451 | |
|
|
| 0.0473 | 0.6156 | 400 | 0.0430 | |
|
|
| 0.0303 | 0.6926 | 450 | 0.0393 | |
|
|
| 0.0293 | 0.7695 | 500 | 0.0389 | |
|
|
| 0.0421 | 0.8465 | 550 | 0.0357 | |
|
|
| 0.0347 | 0.9234 | 600 | 0.0358 | |
|
|
| 0.0305 | 1.0004 | 650 | 0.0356 | |
|
|
| 0.0338 | 1.0773 | 700 | 0.0380 | |
|
|
| 0.0278 | 1.1543 | 750 | 0.0351 | |
|
|
| 0.0283 | 1.2312 | 800 | 0.0342 | |
|
|
| 0.0276 | 1.3082 | 850 | 0.0352 | |
|
|
| 0.0218 | 1.3851 | 900 | 0.0343 | |
|
|
| 0.0366 | 1.4621 | 950 | 0.0344 | |
|
|
| 0.0325 | 1.5391 | 1000 | 0.0358 | |
|
|
| 0.0308 | 1.6160 | 1050 | 0.0317 | |
|
|
| 0.0327 | 1.6930 | 1100 | 0.0363 | |
|
|
| 0.0231 | 1.7699 | 1150 | 0.0331 | |
|
|
| 0.0195 | 1.8469 | 1200 | 0.0380 | |
|
|
| 0.028 | 1.9238 | 1250 | 0.0327 | |
|
|
| 0.021 | 2.0008 | 1300 | 0.0321 | |
|
|
| 0.0169 | 2.0777 | 1350 | 0.0315 | |
|
|
| 0.0226 | 2.1547 | 1400 | 0.0343 | |
|
|
| 0.01 | 2.2316 | 1450 | 0.0397 | |
|
|
| 0.019 | 2.3086 | 1500 | 0.0354 | |
|
|
| 0.0165 | 2.3855 | 1550 | 0.0386 | |
|
|
| 0.0112 | 2.4625 | 1600 | 0.0379 | |
|
|
| 0.0194 | 2.5394 | 1650 | 0.0348 | |
|
|
| 0.0221 | 2.6164 | 1700 | 0.0365 | |
|
|
| 0.0231 | 2.6933 | 1750 | 0.0342 | |
|
|
| 0.0178 | 2.7703 | 1800 | 0.0337 | |
|
|
| 0.0201 | 2.8472 | 1850 | 0.0329 | |
|
|
| 0.0178 | 2.9242 | 1900 | 0.0340 | |
|
|
| 0.025 | 3.0012 | 1950 | 0.0344 | |
|
|
| 0.009 | 3.0781 | 2000 | 0.0373 | |
|
|
| 0.0118 | 3.1551 | 2050 | 0.0420 | |
|
|
| 0.0091 | 3.2320 | 2100 | 0.0401 | |
|
|
| 0.0076 | 3.3090 | 2150 | 0.0398 | |
|
|
| 0.0127 | 3.3859 | 2200 | 0.0385 | |
|
|
| 0.0088 | 3.4629 | 2250 | 0.0376 | |
|
|
| 0.0096 | 3.5398 | 2300 | 0.0403 | |
|
|
| 0.0065 | 3.6168 | 2350 | 0.0405 | |
|
|
| 0.0111 | 3.6937 | 2400 | 0.0375 | |
|
|
| 0.0069 | 3.7707 | 2450 | 0.0396 | |
|
|
| 0.0084 | 3.8476 | 2500 | 0.0415 | |
|
|
| 0.0087 | 3.9246 | 2550 | 0.0423 | |
|
|
| 0.0092 | 4.0015 | 2600 | 0.0429 | |
|
|
| 0.002 | 4.0785 | 2650 | 0.0442 | |
|
|
| 0.0075 | 4.1554 | 2700 | 0.0475 | |
|
|
| 0.0018 | 4.2324 | 2750 | 0.0462 | |
|
|
| 0.0034 | 4.3093 | 2800 | 0.0483 | |
|
|
| 0.0028 | 4.3863 | 2850 | 0.0492 | |
|
|
| 0.004 | 4.4633 | 2900 | 0.0500 | |
|
|
| 0.0018 | 4.5402 | 2950 | 0.0496 | |
|
|
| 0.0039 | 4.6172 | 3000 | 0.0498 | |
|
|
| 0.0035 | 4.6941 | 3050 | 0.0503 | |
|
|
| 0.0054 | 4.7711 | 3100 | 0.0503 | |
|
|
| 0.0028 | 4.8480 | 3150 | 0.0502 | |
|
|
| 0.0041 | 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 |
