|
|
--- |
|
|
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-fold10 |
|
|
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-fold10 |
|
|
|
|
|
This model is a fine-tuned version of [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) on the course-train-fold10 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0347 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.5221 | 0.0770 | 50 | 0.3092 | |
|
|
| 0.0971 | 0.1539 | 100 | 0.0860 | |
|
|
| 0.0873 | 0.2309 | 150 | 0.0607 | |
|
|
| 0.0616 | 0.3078 | 200 | 0.0565 | |
|
|
| 0.071 | 0.3848 | 250 | 0.0542 | |
|
|
| 0.0615 | 0.4618 | 300 | 0.0497 | |
|
|
| 0.0538 | 0.5387 | 350 | 0.0468 | |
|
|
| 0.0532 | 0.6157 | 400 | 0.0462 | |
|
|
| 0.0501 | 0.6926 | 450 | 0.0482 | |
|
|
| 0.0575 | 0.7696 | 500 | 0.0422 | |
|
|
| 0.0418 | 0.8466 | 550 | 0.0440 | |
|
|
| 0.048 | 0.9235 | 600 | 0.0398 | |
|
|
| 0.0559 | 1.0005 | 650 | 0.0397 | |
|
|
| 0.0358 | 1.0774 | 700 | 0.0431 | |
|
|
| 0.0277 | 1.1544 | 750 | 0.0392 | |
|
|
| 0.029 | 1.2314 | 800 | 0.0376 | |
|
|
| 0.0283 | 1.3083 | 850 | 0.0383 | |
|
|
| 0.035 | 1.3853 | 900 | 0.0371 | |
|
|
| 0.0367 | 1.4622 | 950 | 0.0373 | |
|
|
| 0.0272 | 1.5392 | 1000 | 0.0428 | |
|
|
| 0.0435 | 1.6162 | 1050 | 0.0367 | |
|
|
| 0.0379 | 1.6931 | 1100 | 0.0368 | |
|
|
| 0.0296 | 1.7701 | 1150 | 0.0378 | |
|
|
| 0.0423 | 1.8470 | 1200 | 0.0377 | |
|
|
| 0.0389 | 1.9240 | 1250 | 0.0347 | |
|
|
| 0.0349 | 2.0010 | 1300 | 0.0378 | |
|
|
| 0.0191 | 2.0779 | 1350 | 0.0376 | |
|
|
| 0.0252 | 2.1549 | 1400 | 0.0371 | |
|
|
| 0.016 | 2.2318 | 1450 | 0.0381 | |
|
|
| 0.0211 | 2.3088 | 1500 | 0.0362 | |
|
|
| 0.0223 | 2.3858 | 1550 | 0.0355 | |
|
|
| 0.0227 | 2.4627 | 1600 | 0.0385 | |
|
|
| 0.0268 | 2.5397 | 1650 | 0.0354 | |
|
|
| 0.0267 | 2.6166 | 1700 | 0.0349 | |
|
|
| 0.0158 | 2.6936 | 1750 | 0.0352 | |
|
|
| 0.0186 | 2.7706 | 1800 | 0.0384 | |
|
|
| 0.0155 | 2.8475 | 1850 | 0.0401 | |
|
|
| 0.0158 | 2.9245 | 1900 | 0.0365 | |
|
|
| 0.0185 | 3.0014 | 1950 | 0.0362 | |
|
|
| 0.0103 | 3.0784 | 2000 | 0.0401 | |
|
|
| 0.0111 | 3.1554 | 2050 | 0.0402 | |
|
|
| 0.0105 | 3.2323 | 2100 | 0.0448 | |
|
|
| 0.0077 | 3.3093 | 2150 | 0.0435 | |
|
|
| 0.0078 | 3.3862 | 2200 | 0.0476 | |
|
|
| 0.0072 | 3.4632 | 2250 | 0.0457 | |
|
|
| 0.0118 | 3.5402 | 2300 | 0.0452 | |
|
|
| 0.0107 | 3.6171 | 2350 | 0.0448 | |
|
|
| 0.01 | 3.6941 | 2400 | 0.0478 | |
|
|
| 0.0092 | 3.7710 | 2450 | 0.0471 | |
|
|
| 0.0166 | 3.8480 | 2500 | 0.0437 | |
|
|
| 0.0048 | 3.9250 | 2550 | 0.0444 | |
|
|
| 0.0057 | 4.0019 | 2600 | 0.0454 | |
|
|
| 0.0033 | 4.0789 | 2650 | 0.0484 | |
|
|
| 0.0032 | 4.1558 | 2700 | 0.0500 | |
|
|
| 0.005 | 4.2328 | 2750 | 0.0527 | |
|
|
| 0.004 | 4.3098 | 2800 | 0.0546 | |
|
|
| 0.0034 | 4.3867 | 2850 | 0.0554 | |
|
|
| 0.0023 | 4.4637 | 2900 | 0.0560 | |
|
|
| 0.0027 | 4.5406 | 2950 | 0.0564 | |
|
|
| 0.0025 | 4.6176 | 3000 | 0.0563 | |
|
|
| 0.0054 | 4.6946 | 3050 | 0.0568 | |
|
|
| 0.0016 | 4.7715 | 3100 | 0.0569 | |
|
|
| 0.0024 | 4.8485 | 3150 | 0.0567 | |
|
|
| 0.0018 | 4.9254 | 3200 | 0.0568 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.46.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
