| | --- |
| | library_name: peft |
| | license: other |
| | base_model: mistralai/Ministral-8B-Instruct-2410 |
| | tags: |
| | - llama-factory |
| | - generated_from_trainer |
| | model-index: |
| | - name: Ministral-8B-Instruct-2410-PsyCourse-fold7 |
| | 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-fold7 |
| |
|
| | This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.0477 |
| |
|
| | ## 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 | |
| | |:-------------:|:------:|:----:|:---------------:| |
| | | 0.2582 | 0.0770 | 50 | 0.2416 | |
| | | 0.0852 | 0.1539 | 100 | 0.0695 | |
| | | 0.0612 | 0.2309 | 150 | 0.0585 | |
| | | 0.0568 | 0.3078 | 200 | 0.0547 | |
| | | 0.0435 | 0.3848 | 250 | 0.0428 | |
| | | 0.0399 | 0.4617 | 300 | 0.0469 | |
| | | 0.0436 | 0.5387 | 350 | 0.0451 | |
| | | 0.0494 | 0.6156 | 400 | 0.0438 | |
| | | 0.0291 | 0.6926 | 450 | 0.0377 | |
| | | 0.0285 | 0.7695 | 500 | 0.0388 | |
| | | 0.0424 | 0.8465 | 550 | 0.0351 | |
| | | 0.0356 | 0.9234 | 600 | 0.0355 | |
| | | 0.0296 | 1.0004 | 650 | 0.0370 | |
| | | 0.0336 | 1.0773 | 700 | 0.0371 | |
| | | 0.0262 | 1.1543 | 750 | 0.0345 | |
| | | 0.0285 | 1.2312 | 800 | 0.0335 | |
| | | 0.0293 | 1.3082 | 850 | 0.0343 | |
| | | 0.0224 | 1.3851 | 900 | 0.0335 | |
| | | 0.0366 | 1.4621 | 950 | 0.0333 | |
| | | 0.0316 | 1.5391 | 1000 | 0.0365 | |
| | | 0.0296 | 1.6160 | 1050 | 0.0322 | |
| | | 0.0322 | 1.6930 | 1100 | 0.0353 | |
| | | 0.0222 | 1.7699 | 1150 | 0.0327 | |
| | | 0.0219 | 1.8469 | 1200 | 0.0355 | |
| | | 0.0273 | 1.9238 | 1250 | 0.0325 | |
| | | 0.0207 | 2.0008 | 1300 | 0.0310 | |
| | | 0.0173 | 2.0777 | 1350 | 0.0315 | |
| | | 0.022 | 2.1547 | 1400 | 0.0341 | |
| | | 0.0098 | 2.2316 | 1450 | 0.0381 | |
| | | 0.0196 | 2.3086 | 1500 | 0.0343 | |
| | | 0.0162 | 2.3855 | 1550 | 0.0386 | |
| | | 0.0129 | 2.4625 | 1600 | 0.0377 | |
| | | 0.0191 | 2.5394 | 1650 | 0.0336 | |
| | | 0.0206 | 2.6164 | 1700 | 0.0352 | |
| | | 0.0229 | 2.6933 | 1750 | 0.0325 | |
| | | 0.0196 | 2.7703 | 1800 | 0.0324 | |
| | | 0.0204 | 2.8472 | 1850 | 0.0318 | |
| | | 0.0187 | 2.9242 | 1900 | 0.0324 | |
| | | 0.023 | 3.0012 | 1950 | 0.0342 | |
| | | 0.0084 | 3.0781 | 2000 | 0.0376 | |
| | | 0.0104 | 3.1551 | 2050 | 0.0413 | |
| | | 0.008 | 3.2320 | 2100 | 0.0392 | |
| | | 0.0073 | 3.3090 | 2150 | 0.0386 | |
| | | 0.0153 | 3.3859 | 2200 | 0.0368 | |
| | | 0.0068 | 3.4629 | 2250 | 0.0363 | |
| | | 0.0115 | 3.5398 | 2300 | 0.0377 | |
| | | 0.0055 | 3.6168 | 2350 | 0.0394 | |
| | | 0.012 | 3.6937 | 2400 | 0.0376 | |
| | | 0.0072 | 3.7707 | 2450 | 0.0391 | |
| | | 0.007 | 3.8476 | 2500 | 0.0400 | |
| | | 0.0098 | 3.9246 | 2550 | 0.0394 | |
| | | 0.0079 | 4.0015 | 2600 | 0.0399 | |
| | | 0.0014 | 4.0785 | 2650 | 0.0418 | |
| | | 0.0071 | 4.1554 | 2700 | 0.0446 | |
| | | 0.0017 | 4.2324 | 2750 | 0.0446 | |
| | | 0.004 | 4.3093 | 2800 | 0.0466 | |
| | | 0.0034 | 4.3863 | 2850 | 0.0474 | |
| | | 0.0038 | 4.4633 | 2900 | 0.0478 | |
| | | 0.0018 | 4.5402 | 2950 | 0.0475 | |
| | | 0.0038 | 4.6172 | 3000 | 0.0477 | |
| | | 0.0046 | 4.6941 | 3050 | 0.0476 | |
| | | 0.0036 | 4.7711 | 3100 | 0.0477 | |
| | | 0.0033 | 4.8480 | 3150 | 0.0476 | |
| | | 0.003 | 4.9250 | 3200 | 0.0477 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - PEFT 0.12.0 |
| | - Transformers 4.46.1 |
| | - Pytorch 2.5.1+cu124 |
| | - Datasets 3.1.0 |
| | - Tokenizers 0.20.3 |
