|
--- |
|
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-fold3 |
|
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-doc-fold3 |
|
|
|
This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) on the course-doc-train-fold3 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.1116 | 0.3951 | 10 | 0.1196 | |
|
| 0.0543 | 0.7901 | 20 | 0.0717 | |
|
| 0.0747 | 1.1852 | 30 | 0.0615 | |
|
| 0.1014 | 1.5802 | 40 | 0.0576 | |
|
| 0.0608 | 1.9753 | 50 | 0.0554 | |
|
| 0.0319 | 2.3704 | 60 | 0.0546 | |
|
| 0.0476 | 2.7654 | 70 | 0.0532 | |
|
| 0.0866 | 3.1605 | 80 | 0.0536 | |
|
| 0.0563 | 3.5556 | 90 | 0.0540 | |
|
| 0.0158 | 3.9506 | 100 | 0.0535 | |
|
| 0.0306 | 4.3457 | 110 | 0.0539 | |
|
| 0.0565 | 4.7407 | 120 | 0.0538 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.46.1 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
