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-info-fold5
results: []
Ministral-8B-Instruct-2410-PsyCourse-info-fold5
This model is a fine-tuned version of mistralai/Ministral-8B-Instruct-2410 on the course-info-train-fold5 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1420
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 |
|---|---|---|---|
| 0.4174 | 0.3951 | 10 | 0.3537 |
| 0.1926 | 0.7901 | 20 | 0.1861 |
| 0.1219 | 1.1852 | 30 | 0.1573 |
| 0.1156 | 1.5802 | 40 | 0.1453 |
| 0.1196 | 1.9753 | 50 | 0.1509 |
| 0.0994 | 2.3704 | 60 | 0.1486 |
| 0.0806 | 2.7654 | 70 | 0.1455 |
| 0.058 | 3.1605 | 80 | 0.1420 |
| 0.0492 | 3.5556 | 90 | 0.1440 |
| 0.041 | 3.9506 | 100 | 0.1470 |
| 0.0391 | 4.3457 | 110 | 0.1494 |
| 0.0489 | 4.7407 | 120 | 0.1479 |
Framework versions
- PEFT 0.12.0
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3