---
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-fold7
  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-fold7

This model is a fine-tuned version of [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) on the course-train-fold7 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0343

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.5143        | 0.0764 | 50   | 0.3069          |
| 0.1115        | 0.1528 | 100  | 0.0800          |
| 0.0781        | 0.2292 | 150  | 0.0636          |
| 0.0677        | 0.3056 | 200  | 0.0595          |
| 0.0609        | 0.3820 | 250  | 0.0500          |
| 0.0442        | 0.4584 | 300  | 0.0519          |
| 0.0605        | 0.5348 | 350  | 0.0530          |
| 0.0415        | 0.6112 | 400  | 0.0427          |
| 0.0616        | 0.6875 | 450  | 0.0430          |
| 0.0412        | 0.7639 | 500  | 0.0389          |
| 0.0306        | 0.8403 | 550  | 0.0385          |
| 0.0579        | 0.9167 | 600  | 0.0378          |
| 0.0625        | 0.9931 | 650  | 0.0424          |
| 0.0363        | 1.0695 | 700  | 0.0368          |
| 0.024         | 1.1459 | 750  | 0.0377          |
| 0.0331        | 1.2223 | 800  | 0.0374          |
| 0.0368        | 1.2987 | 850  | 0.0383          |
| 0.039         | 1.3751 | 900  | 0.0359          |
| 0.0428        | 1.4515 | 950  | 0.0387          |
| 0.0285        | 1.5279 | 1000 | 0.0350          |
| 0.0292        | 1.6043 | 1050 | 0.0368          |
| 0.0317        | 1.6807 | 1100 | 0.0365          |
| 0.0506        | 1.7571 | 1150 | 0.0349          |
| 0.0329        | 1.8335 | 1200 | 0.0353          |
| 0.0352        | 1.9099 | 1250 | 0.0377          |
| 0.0289        | 1.9862 | 1300 | 0.0365          |
| 0.0202        | 2.0626 | 1350 | 0.0356          |
| 0.0174        | 2.1390 | 1400 | 0.0357          |
| 0.0134        | 2.2154 | 1450 | 0.0395          |
| 0.02          | 2.2918 | 1500 | 0.0361          |
| 0.0189        | 2.3682 | 1550 | 0.0374          |
| 0.0162        | 2.4446 | 1600 | 0.0348          |
| 0.0252        | 2.5210 | 1650 | 0.0371          |
| 0.0175        | 2.5974 | 1700 | 0.0366          |
| 0.0222        | 2.6738 | 1750 | 0.0346          |
| 0.0274        | 2.7502 | 1800 | 0.0347          |
| 0.0215        | 2.8266 | 1850 | 0.0362          |
| 0.0201        | 2.9030 | 1900 | 0.0378          |
| 0.016         | 2.9794 | 1950 | 0.0343          |
| 0.009         | 3.0558 | 2000 | 0.0372          |
| 0.0106        | 3.1322 | 2050 | 0.0389          |
| 0.0061        | 3.2086 | 2100 | 0.0432          |
| 0.0075        | 3.2850 | 2150 | 0.0434          |
| 0.0089        | 3.3613 | 2200 | 0.0434          |
| 0.0102        | 3.4377 | 2250 | 0.0462          |
| 0.0083        | 3.5141 | 2300 | 0.0465          |
| 0.0131        | 3.5905 | 2350 | 0.0443          |
| 0.0054        | 3.6669 | 2400 | 0.0424          |
| 0.0038        | 3.7433 | 2450 | 0.0428          |
| 0.0074        | 3.8197 | 2500 | 0.0429          |
| 0.0056        | 3.8961 | 2550 | 0.0426          |
| 0.007         | 3.9725 | 2600 | 0.0428          |
| 0.0034        | 4.0489 | 2650 | 0.0434          |
| 0.0051        | 4.1253 | 2700 | 0.0460          |
| 0.0043        | 4.2017 | 2750 | 0.0464          |
| 0.0023        | 4.2781 | 2800 | 0.0472          |
| 0.0035        | 4.3545 | 2850 | 0.0477          |
| 0.0021        | 4.4309 | 2900 | 0.0488          |
| 0.0021        | 4.5073 | 2950 | 0.0497          |
| 0.0024        | 4.5837 | 3000 | 0.0501          |
| 0.0013        | 4.6600 | 3050 | 0.0505          |
| 0.0031        | 4.7364 | 3100 | 0.0511          |
| 0.0031        | 4.8128 | 3150 | 0.0511          |
| 0.0023        | 4.8892 | 3200 | 0.0512          |
| 0.0023        | 4.9656 | 3250 | 0.0511          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3