metadata
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-doc-info-fold1
results: []
Ministral-8B-Instruct-2410-PsyCourse-doc-info-fold1
This model is a fine-tuned version of mistralai/Ministral-8B-Instruct-2410 on the course-doc-info-train-fold1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0532
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 |
|---|---|---|---|
| 0.2635 | 0.3951 | 10 | 0.2265 |
| 0.1024 | 0.7901 | 20 | 0.1080 |
| 0.0661 | 1.1852 | 30 | 0.0811 |
| 0.0661 | 1.5802 | 40 | 0.0710 |
| 0.0513 | 1.9753 | 50 | 0.0638 |
| 0.0444 | 2.3704 | 60 | 0.0597 |
| 0.0386 | 2.7654 | 70 | 0.0573 |
| 0.0312 | 3.1605 | 80 | 0.0550 |
| 0.0306 | 3.5556 | 90 | 0.0544 |
| 0.0332 | 3.9506 | 100 | 0.0537 |
| 0.0325 | 4.3457 | 110 | 0.0533 |
| 0.0363 | 4.7407 | 120 | 0.0532 |
Framework versions
- PEFT 0.12.0
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3