---
library_name: peft
license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: Llama-3.1-8B-Instruct-PsyCourse-fold8
  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. -->

# Llama-3.1-8B-Instruct-PsyCourse-fold8

This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the course-train-fold8 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0354

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.6782        | 0.0758 | 50   | 0.4323          |
| 0.1528        | 0.1516 | 100  | 0.0901          |
| 0.0741        | 0.2275 | 150  | 0.0665          |
| 0.0544        | 0.3033 | 200  | 0.0563          |
| 0.053         | 0.3791 | 250  | 0.0572          |
| 0.0626        | 0.4549 | 300  | 0.0589          |
| 0.0646        | 0.5308 | 350  | 0.0462          |
| 0.0336        | 0.6066 | 400  | 0.0449          |
| 0.0426        | 0.6824 | 450  | 0.0435          |
| 0.0354        | 0.7582 | 500  | 0.0468          |
| 0.0506        | 0.8340 | 550  | 0.0444          |
| 0.0346        | 0.9099 | 600  | 0.0411          |
| 0.0514        | 0.9857 | 650  | 0.0443          |
| 0.0323        | 1.0615 | 700  | 0.0412          |
| 0.0261        | 1.1373 | 750  | 0.0431          |
| 0.0307        | 1.2132 | 800  | 0.0398          |
| 0.0284        | 1.2890 | 850  | 0.0416          |
| 0.0316        | 1.3648 | 900  | 0.0398          |
| 0.0288        | 1.4406 | 950  | 0.0397          |
| 0.0306        | 1.5164 | 1000 | 0.0411          |
| 0.0449        | 1.5923 | 1050 | 0.0384          |
| 0.0281        | 1.6681 | 1100 | 0.0385          |
| 0.038         | 1.7439 | 1150 | 0.0376          |
| 0.0277        | 1.8197 | 1200 | 0.0354          |
| 0.0381        | 1.8956 | 1250 | 0.0377          |
| 0.0278        | 1.9714 | 1300 | 0.0359          |
| 0.0194        | 2.0472 | 1350 | 0.0393          |
| 0.0149        | 2.1230 | 1400 | 0.0375          |
| 0.0243        | 2.1988 | 1450 | 0.0402          |
| 0.0234        | 2.2747 | 1500 | 0.0396          |
| 0.0189        | 2.3505 | 1550 | 0.0392          |
| 0.0195        | 2.4263 | 1600 | 0.0396          |
| 0.0221        | 2.5021 | 1650 | 0.0475          |
| 0.0179        | 2.5780 | 1700 | 0.0408          |
| 0.0225        | 2.6538 | 1750 | 0.0386          |
| 0.0207        | 2.7296 | 1800 | 0.0398          |
| 0.015         | 2.8054 | 1850 | 0.0410          |
| 0.0295        | 2.8812 | 1900 | 0.0372          |
| 0.0227        | 2.9571 | 1950 | 0.0380          |
| 0.0128        | 3.0329 | 2000 | 0.0398          |
| 0.0096        | 3.1087 | 2050 | 0.0432          |
| 0.0076        | 3.1845 | 2100 | 0.0488          |
| 0.0122        | 3.2604 | 2150 | 0.0451          |
| 0.0101        | 3.3362 | 2200 | 0.0467          |
| 0.0124        | 3.4120 | 2250 | 0.0464          |
| 0.0113        | 3.4878 | 2300 | 0.0480          |
| 0.0126        | 3.5636 | 2350 | 0.0480          |
| 0.0114        | 3.6395 | 2400 | 0.0436          |
| 0.0071        | 3.7153 | 2450 | 0.0472          |
| 0.0117        | 3.7911 | 2500 | 0.0490          |
| 0.0145        | 3.8669 | 2550 | 0.0475          |
| 0.008         | 3.9428 | 2600 | 0.0459          |
| 0.0044        | 4.0186 | 2650 | 0.0480          |
| 0.0061        | 4.0944 | 2700 | 0.0542          |
| 0.0048        | 4.1702 | 2750 | 0.0556          |
| 0.0043        | 4.2460 | 2800 | 0.0557          |
| 0.0049        | 4.3219 | 2850 | 0.0570          |
| 0.0019        | 4.3977 | 2900 | 0.0587          |
| 0.0053        | 4.4735 | 2950 | 0.0595          |
| 0.0072        | 4.5493 | 3000 | 0.0597          |
| 0.0047        | 4.6252 | 3050 | 0.0599          |
| 0.003         | 4.7010 | 3100 | 0.0602          |
| 0.0025        | 4.7768 | 3150 | 0.0603          |
| 0.0027        | 4.8526 | 3200 | 0.0604          |
| 0.0022        | 4.9284 | 3250 | 0.0604          |


### Framework versions

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