| | --- |
| | 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-fold4 |
| | 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-fold4 |
| |
|
| | 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 | |
| | |:-------------:|:------:|:----:|:---------------:| |
| | | 0.2583 | 0.0770 | 50 | 0.2419 | |
| | | 0.0849 | 0.1539 | 100 | 0.0694 | |
| | | 0.061 | 0.2309 | 150 | 0.0582 | |
| | | 0.0578 | 0.3078 | 200 | 0.0538 | |
| | | 0.0434 | 0.3848 | 250 | 0.0429 | |
| | | 0.0405 | 0.4617 | 300 | 0.0481 | |
| | | 0.0438 | 0.5387 | 350 | 0.0454 | |
| | | 0.0486 | 0.6156 | 400 | 0.0445 | |
| | | 0.0286 | 0.6926 | 450 | 0.0389 | |
| | | 0.0307 | 0.7695 | 500 | 0.0375 | |
| | | 0.0424 | 0.8465 | 550 | 0.0347 | |
| | | 0.0372 | 0.9234 | 600 | 0.0355 | |
| | | 0.0293 | 1.0004 | 650 | 0.0354 | |
| | | 0.0349 | 1.0773 | 700 | 0.0368 | |
| | | 0.0273 | 1.1543 | 750 | 0.0357 | |
| | | 0.0284 | 1.2312 | 800 | 0.0339 | |
| | | 0.0299 | 1.3082 | 850 | 0.0335 | |
| | | 0.0218 | 1.3851 | 900 | 0.0329 | |
| | | 0.0368 | 1.4621 | 950 | 0.0346 | |
| | | 0.0314 | 1.5391 | 1000 | 0.0357 | |
| | | 0.0323 | 1.6160 | 1050 | 0.0325 | |
| | | 0.0337 | 1.6930 | 1100 | 0.0362 | |
| | | 0.0232 | 1.7699 | 1150 | 0.0335 | |
| | | 0.0209 | 1.8469 | 1200 | 0.0370 | |
| | | 0.0284 | 1.9238 | 1250 | 0.0332 | |
| | | 0.0218 | 2.0008 | 1300 | 0.0315 | |
| | | 0.0168 | 2.0777 | 1350 | 0.0317 | |
| | | 0.0227 | 2.1547 | 1400 | 0.0340 | |
| | | 0.0105 | 2.2316 | 1450 | 0.0377 | |
| | | 0.0195 | 2.3086 | 1500 | 0.0348 | |
| | | 0.0154 | 2.3855 | 1550 | 0.0367 | |
| | | 0.0125 | 2.4625 | 1600 | 0.0349 | |
| | | 0.0189 | 2.5394 | 1650 | 0.0343 | |
| | | 0.0211 | 2.6164 | 1700 | 0.0351 | |
| | | 0.0223 | 2.6933 | 1750 | 0.0328 | |
| | | 0.018 | 2.7703 | 1800 | 0.0329 | |
| | | 0.0199 | 2.8472 | 1850 | 0.0326 | |
| | | 0.0176 | 2.9242 | 1900 | 0.0327 | |
| | | 0.0235 | 3.0012 | 1950 | 0.0338 | |
| | | 0.008 | 3.0781 | 2000 | 0.0393 | |
| | | 0.0096 | 3.1551 | 2050 | 0.0409 | |
| | | 0.0077 | 3.2320 | 2100 | 0.0395 | |
| | | 0.0057 | 3.3090 | 2150 | 0.0418 | |
| | | 0.0115 | 3.3859 | 2200 | 0.0389 | |
| | | 0.0076 | 3.4629 | 2250 | 0.0371 | |
| | | 0.0114 | 3.5398 | 2300 | 0.0390 | |
| | | 0.0058 | 3.6168 | 2350 | 0.0413 | |
| | | 0.0118 | 3.6937 | 2400 | 0.0371 | |
| | | 0.0075 | 3.7707 | 2450 | 0.0379 | |
| | | 0.0072 | 3.8476 | 2500 | 0.0393 | |
| | | 0.0094 | 3.9246 | 2550 | 0.0396 | |
| | | 0.0096 | 4.0015 | 2600 | 0.0396 | |
| | | 0.0019 | 4.0785 | 2650 | 0.0407 | |
| | | 0.0074 | 4.1554 | 2700 | 0.0439 | |
| | | 0.0016 | 4.2324 | 2750 | 0.0444 | |
| | | 0.003 | 4.3093 | 2800 | 0.0454 | |
| | | 0.0034 | 4.3863 | 2850 | 0.0467 | |
| | | 0.0039 | 4.4633 | 2900 | 0.0475 | |
| | | 0.0019 | 4.5402 | 2950 | 0.0470 | |
| | | 0.003 | 4.6172 | 3000 | 0.0472 | |
| | | 0.0056 | 4.6941 | 3050 | 0.0474 | |
| | | 0.0036 | 4.7711 | 3100 | 0.0474 | |
| | | 0.0029 | 4.8480 | 3150 | 0.0473 | |
| | | 0.003 | 4.9250 | 3200 | 0.0474 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - PEFT 0.12.0 |
| | - Transformers 4.46.1 |
| | - Pytorch 2.5.1+cu124 |
| | - Datasets 3.1.0 |
| | - Tokenizers 0.20.3 |
