---
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-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. -->

# Llama-3.1-8B-Instruct-PsyCourse-fold10

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-fold10 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.6238        | 0.0770 | 50   | 0.3911          |
| 0.0941        | 0.1539 | 100  | 0.0845          |
| 0.087         | 0.2309 | 150  | 0.0577          |
| 0.0643        | 0.3078 | 200  | 0.0540          |
| 0.0718        | 0.3848 | 250  | 0.0550          |
| 0.0561        | 0.4618 | 300  | 0.0480          |
| 0.0517        | 0.5387 | 350  | 0.0457          |
| 0.0473        | 0.6157 | 400  | 0.0444          |
| 0.0486        | 0.6926 | 450  | 0.0480          |
| 0.0579        | 0.7696 | 500  | 0.0443          |
| 0.0433        | 0.8466 | 550  | 0.0422          |
| 0.0464        | 0.9235 | 600  | 0.0384          |
| 0.0542        | 1.0005 | 650  | 0.0373          |
| 0.0365        | 1.0774 | 700  | 0.0419          |
| 0.0303        | 1.1544 | 750  | 0.0383          |
| 0.0281        | 1.2314 | 800  | 0.0357          |
| 0.0293        | 1.3083 | 850  | 0.0360          |
| 0.0408        | 1.3853 | 900  | 0.0362          |
| 0.0358        | 1.4622 | 950  | 0.0379          |
| 0.0277        | 1.5392 | 1000 | 0.0406          |
| 0.0401        | 1.6162 | 1050 | 0.0346          |
| 0.0366        | 1.6931 | 1100 | 0.0379          |
| 0.0292        | 1.7701 | 1150 | 0.0357          |
| 0.0408        | 1.8470 | 1200 | 0.0368          |
| 0.0354        | 1.9240 | 1250 | 0.0367          |
| 0.0374        | 2.0010 | 1300 | 0.0378          |
| 0.0216        | 2.0779 | 1350 | 0.0356          |
| 0.0272        | 2.1549 | 1400 | 0.0355          |
| 0.0207        | 2.2318 | 1450 | 0.0360          |
| 0.0275        | 2.3088 | 1500 | 0.0357          |
| 0.0236        | 2.3858 | 1550 | 0.0361          |
| 0.0263        | 2.4627 | 1600 | 0.0371          |
| 0.0306        | 2.5397 | 1650 | 0.0352          |
| 0.0264        | 2.6166 | 1700 | 0.0349          |
| 0.0192        | 2.6936 | 1750 | 0.0347          |
| 0.0239        | 2.7706 | 1800 | 0.0359          |
| 0.0158        | 2.8475 | 1850 | 0.0374          |
| 0.019         | 2.9245 | 1900 | 0.0362          |
| 0.0218        | 3.0014 | 1950 | 0.0355          |
| 0.014         | 3.0784 | 2000 | 0.0406          |
| 0.0125        | 3.1554 | 2050 | 0.0427          |
| 0.0163        | 3.2323 | 2100 | 0.0419          |
| 0.0118        | 3.3093 | 2150 | 0.0408          |
| 0.0119        | 3.3862 | 2200 | 0.0422          |
| 0.0109        | 3.4632 | 2250 | 0.0453          |
| 0.013         | 3.5402 | 2300 | 0.0447          |
| 0.0108        | 3.6171 | 2350 | 0.0428          |
| 0.0132        | 3.6941 | 2400 | 0.0471          |
| 0.0098        | 3.7710 | 2450 | 0.0445          |
| 0.017         | 3.8480 | 2500 | 0.0410          |
| 0.0115        | 3.9250 | 2550 | 0.0408          |
| 0.0121        | 4.0019 | 2600 | 0.0412          |
| 0.0061        | 4.0789 | 2650 | 0.0451          |
| 0.0076        | 4.1558 | 2700 | 0.0485          |
| 0.0066        | 4.2328 | 2750 | 0.0524          |
| 0.0053        | 4.3098 | 2800 | 0.0534          |
| 0.0073        | 4.3867 | 2850 | 0.0541          |
| 0.0033        | 4.4637 | 2900 | 0.0533          |
| 0.004         | 4.5406 | 2950 | 0.0537          |
| 0.0055        | 4.6176 | 3000 | 0.0541          |
| 0.0106        | 4.6946 | 3050 | 0.0545          |
| 0.0025        | 4.7715 | 3100 | 0.0543          |
| 0.0053        | 4.8485 | 3150 | 0.0545          |
| 0.0033        | 4.9254 | 3200 | 0.0545          |


### Framework versions

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