|
|
--- |
|
|
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-fold9 |
|
|
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-fold9 |
|
|
|
|
|
This model is a fine-tuned version of [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) on the course-train-fold9 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0367 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.5046 | 0.0768 | 50 | 0.3063 | |
|
|
| 0.1059 | 0.1535 | 100 | 0.0842 | |
|
|
| 0.0783 | 0.2303 | 150 | 0.0695 | |
|
|
| 0.0635 | 0.3070 | 200 | 0.0595 | |
|
|
| 0.075 | 0.3838 | 250 | 0.0530 | |
|
|
| 0.065 | 0.4606 | 300 | 0.0491 | |
|
|
| 0.0474 | 0.5373 | 350 | 0.0478 | |
|
|
| 0.0461 | 0.6141 | 400 | 0.0493 | |
|
|
| 0.0533 | 0.6908 | 450 | 0.0540 | |
|
|
| 0.048 | 0.7676 | 500 | 0.0457 | |
|
|
| 0.0694 | 0.8444 | 550 | 0.0475 | |
|
|
| 0.0396 | 0.9211 | 600 | 0.0416 | |
|
|
| 0.0412 | 0.9979 | 650 | 0.0386 | |
|
|
| 0.0339 | 1.0746 | 700 | 0.0457 | |
|
|
| 0.0357 | 1.1514 | 750 | 0.0434 | |
|
|
| 0.0336 | 1.2282 | 800 | 0.0408 | |
|
|
| 0.0342 | 1.3049 | 850 | 0.0414 | |
|
|
| 0.0307 | 1.3817 | 900 | 0.0407 | |
|
|
| 0.0312 | 1.4585 | 950 | 0.0379 | |
|
|
| 0.0314 | 1.5352 | 1000 | 0.0392 | |
|
|
| 0.0229 | 1.6120 | 1050 | 0.0367 | |
|
|
| 0.0337 | 1.6887 | 1100 | 0.0372 | |
|
|
| 0.028 | 1.7655 | 1150 | 0.0379 | |
|
|
| 0.0191 | 1.8423 | 1200 | 0.0388 | |
|
|
| 0.0348 | 1.9190 | 1250 | 0.0411 | |
|
|
| 0.0469 | 1.9958 | 1300 | 0.0399 | |
|
|
| 0.0193 | 2.0725 | 1350 | 0.0412 | |
|
|
| 0.0168 | 2.1493 | 1400 | 0.0416 | |
|
|
| 0.019 | 2.2261 | 1450 | 0.0390 | |
|
|
| 0.0268 | 2.3028 | 1500 | 0.0390 | |
|
|
| 0.0221 | 2.3796 | 1550 | 0.0412 | |
|
|
| 0.0264 | 2.4563 | 1600 | 0.0408 | |
|
|
| 0.0248 | 2.5331 | 1650 | 0.0390 | |
|
|
| 0.018 | 2.6099 | 1700 | 0.0397 | |
|
|
| 0.0148 | 2.6866 | 1750 | 0.0406 | |
|
|
| 0.0228 | 2.7634 | 1800 | 0.0416 | |
|
|
| 0.0216 | 2.8401 | 1850 | 0.0392 | |
|
|
| 0.021 | 2.9169 | 1900 | 0.0396 | |
|
|
| 0.016 | 2.9937 | 1950 | 0.0393 | |
|
|
| 0.0055 | 3.0704 | 2000 | 0.0446 | |
|
|
| 0.0128 | 3.1472 | 2050 | 0.0464 | |
|
|
| 0.0105 | 3.2239 | 2100 | 0.0466 | |
|
|
| 0.009 | 3.3007 | 2150 | 0.0450 | |
|
|
| 0.0087 | 3.3775 | 2200 | 0.0487 | |
|
|
| 0.0102 | 3.4542 | 2250 | 0.0473 | |
|
|
| 0.007 | 3.5310 | 2300 | 0.0486 | |
|
|
| 0.0113 | 3.6078 | 2350 | 0.0490 | |
|
|
| 0.0066 | 3.6845 | 2400 | 0.0522 | |
|
|
| 0.0064 | 3.7613 | 2450 | 0.0510 | |
|
|
| 0.0095 | 3.8380 | 2500 | 0.0514 | |
|
|
| 0.0089 | 3.9148 | 2550 | 0.0521 | |
|
|
| 0.0065 | 3.9916 | 2600 | 0.0524 | |
|
|
| 0.0034 | 4.0683 | 2650 | 0.0540 | |
|
|
| 0.0032 | 4.1451 | 2700 | 0.0563 | |
|
|
| 0.0026 | 4.2218 | 2750 | 0.0564 | |
|
|
| 0.0024 | 4.2986 | 2800 | 0.0586 | |
|
|
| 0.0021 | 4.3754 | 2850 | 0.0595 | |
|
|
| 0.0043 | 4.4521 | 2900 | 0.0604 | |
|
|
| 0.0019 | 4.5289 | 2950 | 0.0607 | |
|
|
| 0.0011 | 4.6056 | 3000 | 0.0610 | |
|
|
| 0.0018 | 4.6824 | 3050 | 0.0617 | |
|
|
| 0.0051 | 4.7592 | 3100 | 0.0614 | |
|
|
| 0.0032 | 4.8359 | 3150 | 0.0617 | |
|
|
| 0.001 | 4.9127 | 3200 | 0.0617 | |
|
|
| 0.0029 | 4.9894 | 3250 | 0.0618 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.46.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
