|
|
--- |
|
|
library_name: peft |
|
|
license: llama3 |
|
|
base_model: aaditya/Llama3-OpenBioLLM-8B |
|
|
tags: |
|
|
- llama-factory |
|
|
- lora |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: Llama3-OpenBioLLM-8B-PsyCourse-fold2 |
|
|
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. --> |
|
|
|
|
|
# Llama3-OpenBioLLM-8B-PsyCourse-fold2 |
|
|
|
|
|
This model is a fine-tuned version of [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) on the course-train-fold2 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0346 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.4179 | 0.0775 | 50 | 0.3434 | |
|
|
| 0.0933 | 0.1550 | 100 | 0.0820 | |
|
|
| 0.0662 | 0.2326 | 150 | 0.0668 | |
|
|
| 0.0584 | 0.3101 | 200 | 0.0589 | |
|
|
| 0.0666 | 0.3876 | 250 | 0.0527 | |
|
|
| 0.0448 | 0.4651 | 300 | 0.0521 | |
|
|
| 0.0474 | 0.5426 | 350 | 0.0490 | |
|
|
| 0.0546 | 0.6202 | 400 | 0.0431 | |
|
|
| 0.0432 | 0.6977 | 450 | 0.0393 | |
|
|
| 0.0526 | 0.7752 | 500 | 0.0401 | |
|
|
| 0.0506 | 0.8527 | 550 | 0.0400 | |
|
|
| 0.0622 | 0.9302 | 600 | 0.0419 | |
|
|
| 0.0363 | 1.0078 | 650 | 0.0380 | |
|
|
| 0.032 | 1.0853 | 700 | 0.0377 | |
|
|
| 0.0361 | 1.1628 | 750 | 0.0435 | |
|
|
| 0.0256 | 1.2403 | 800 | 0.0365 | |
|
|
| 0.0361 | 1.3178 | 850 | 0.0357 | |
|
|
| 0.0428 | 1.3953 | 900 | 0.0369 | |
|
|
| 0.0423 | 1.4729 | 950 | 0.0367 | |
|
|
| 0.0298 | 1.5504 | 1000 | 0.0382 | |
|
|
| 0.0357 | 1.6279 | 1050 | 0.0366 | |
|
|
| 0.0271 | 1.7054 | 1100 | 0.0375 | |
|
|
| 0.0325 | 1.7829 | 1150 | 0.0370 | |
|
|
| 0.0328 | 1.8605 | 1200 | 0.0346 | |
|
|
| 0.0373 | 1.9380 | 1250 | 0.0346 | |
|
|
| 0.0219 | 2.0155 | 1300 | 0.0351 | |
|
|
| 0.0179 | 2.0930 | 1350 | 0.0380 | |
|
|
| 0.018 | 2.1705 | 1400 | 0.0398 | |
|
|
| 0.0203 | 2.2481 | 1450 | 0.0382 | |
|
|
| 0.0257 | 2.3256 | 1500 | 0.0405 | |
|
|
| 0.0165 | 2.4031 | 1550 | 0.0382 | |
|
|
| 0.0212 | 2.4806 | 1600 | 0.0375 | |
|
|
| 0.0315 | 2.5581 | 1650 | 0.0373 | |
|
|
| 0.0155 | 2.6357 | 1700 | 0.0379 | |
|
|
| 0.0188 | 2.7132 | 1750 | 0.0379 | |
|
|
| 0.0195 | 2.7907 | 1800 | 0.0397 | |
|
|
| 0.0213 | 2.8682 | 1850 | 0.0373 | |
|
|
| 0.0171 | 2.9457 | 1900 | 0.0374 | |
|
|
| 0.0108 | 3.0233 | 1950 | 0.0390 | |
|
|
| 0.0125 | 3.1008 | 2000 | 0.0437 | |
|
|
| 0.0046 | 3.1783 | 2050 | 0.0459 | |
|
|
| 0.0059 | 3.2558 | 2100 | 0.0479 | |
|
|
| 0.0088 | 3.3333 | 2150 | 0.0432 | |
|
|
| 0.0074 | 3.4109 | 2200 | 0.0455 | |
|
|
| 0.0105 | 3.4884 | 2250 | 0.0493 | |
|
|
| 0.0116 | 3.5659 | 2300 | 0.0510 | |
|
|
| 0.01 | 3.6434 | 2350 | 0.0481 | |
|
|
| 0.0126 | 3.7209 | 2400 | 0.0474 | |
|
|
| 0.0061 | 3.7984 | 2450 | 0.0477 | |
|
|
| 0.0088 | 3.8760 | 2500 | 0.0487 | |
|
|
| 0.0074 | 3.9535 | 2550 | 0.0488 | |
|
|
| 0.0076 | 4.0310 | 2600 | 0.0499 | |
|
|
| 0.0051 | 4.1085 | 2650 | 0.0524 | |
|
|
| 0.0038 | 4.1860 | 2700 | 0.0556 | |
|
|
| 0.0031 | 4.2636 | 2750 | 0.0584 | |
|
|
| 0.0028 | 4.3411 | 2800 | 0.0602 | |
|
|
| 0.0037 | 4.4186 | 2850 | 0.0612 | |
|
|
| 0.0037 | 4.4961 | 2900 | 0.0620 | |
|
|
| 0.0013 | 4.5736 | 2950 | 0.0626 | |
|
|
| 0.0013 | 4.6512 | 3000 | 0.0631 | |
|
|
| 0.0023 | 4.7287 | 3050 | 0.0634 | |
|
|
| 0.0042 | 4.8062 | 3100 | 0.0635 | |
|
|
| 0.0053 | 4.8837 | 3150 | 0.0635 | |
|
|
| 0.0041 | 4.9612 | 3200 | 0.0634 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.46.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
