|
|
--- |
|
|
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-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. --> |
|
|
|
|
|
# Llama-3.1-8B-Instruct-PsyCourse-fold7 |
|
|
|
|
|
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-fold7 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0324 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.6247 | 0.0764 | 50 | 0.4018 | |
|
|
| 0.1081 | 0.1528 | 100 | 0.0778 | |
|
|
| 0.0687 | 0.2292 | 150 | 0.0614 | |
|
|
| 0.0565 | 0.3056 | 200 | 0.0577 | |
|
|
| 0.0612 | 0.3820 | 250 | 0.0510 | |
|
|
| 0.0426 | 0.4584 | 300 | 0.0490 | |
|
|
| 0.0657 | 0.5348 | 350 | 0.0489 | |
|
|
| 0.0423 | 0.6112 | 400 | 0.0453 | |
|
|
| 0.056 | 0.6875 | 450 | 0.0438 | |
|
|
| 0.0393 | 0.7639 | 500 | 0.0396 | |
|
|
| 0.0321 | 0.8403 | 550 | 0.0387 | |
|
|
| 0.0493 | 0.9167 | 600 | 0.0400 | |
|
|
| 0.0578 | 0.9931 | 650 | 0.0393 | |
|
|
| 0.0371 | 1.0695 | 700 | 0.0376 | |
|
|
| 0.0228 | 1.1459 | 750 | 0.0364 | |
|
|
| 0.0301 | 1.2223 | 800 | 0.0388 | |
|
|
| 0.0383 | 1.2987 | 850 | 0.0371 | |
|
|
| 0.0403 | 1.3751 | 900 | 0.0364 | |
|
|
| 0.0446 | 1.4515 | 950 | 0.0381 | |
|
|
| 0.0282 | 1.5279 | 1000 | 0.0352 | |
|
|
| 0.0303 | 1.6043 | 1050 | 0.0363 | |
|
|
| 0.0287 | 1.6807 | 1100 | 0.0400 | |
|
|
| 0.0562 | 1.7571 | 1150 | 0.0355 | |
|
|
| 0.0354 | 1.8335 | 1200 | 0.0350 | |
|
|
| 0.0379 | 1.9099 | 1250 | 0.0377 | |
|
|
| 0.0272 | 1.9862 | 1300 | 0.0353 | |
|
|
| 0.0232 | 2.0626 | 1350 | 0.0356 | |
|
|
| 0.0203 | 2.1390 | 1400 | 0.0356 | |
|
|
| 0.0156 | 2.2154 | 1450 | 0.0388 | |
|
|
| 0.0207 | 2.2918 | 1500 | 0.0344 | |
|
|
| 0.0202 | 2.3682 | 1550 | 0.0345 | |
|
|
| 0.0196 | 2.4446 | 1600 | 0.0345 | |
|
|
| 0.0244 | 2.5210 | 1650 | 0.0345 | |
|
|
| 0.0199 | 2.5974 | 1700 | 0.0355 | |
|
|
| 0.0221 | 2.6738 | 1750 | 0.0338 | |
|
|
| 0.0271 | 2.7502 | 1800 | 0.0324 | |
|
|
| 0.0265 | 2.8266 | 1850 | 0.0324 | |
|
|
| 0.0214 | 2.9030 | 1900 | 0.0343 | |
|
|
| 0.0214 | 2.9794 | 1950 | 0.0354 | |
|
|
| 0.0159 | 3.0558 | 2000 | 0.0351 | |
|
|
| 0.0147 | 3.1322 | 2050 | 0.0364 | |
|
|
| 0.0125 | 3.2086 | 2100 | 0.0382 | |
|
|
| 0.0135 | 3.2850 | 2150 | 0.0398 | |
|
|
| 0.0138 | 3.3613 | 2200 | 0.0406 | |
|
|
| 0.0143 | 3.4377 | 2250 | 0.0450 | |
|
|
| 0.0082 | 3.5141 | 2300 | 0.0436 | |
|
|
| 0.0177 | 3.5905 | 2350 | 0.0426 | |
|
|
| 0.0119 | 3.6669 | 2400 | 0.0396 | |
|
|
| 0.0061 | 3.7433 | 2450 | 0.0407 | |
|
|
| 0.0101 | 3.8197 | 2500 | 0.0403 | |
|
|
| 0.0105 | 3.8961 | 2550 | 0.0398 | |
|
|
| 0.0087 | 3.9725 | 2600 | 0.0390 | |
|
|
| 0.0058 | 4.0489 | 2650 | 0.0419 | |
|
|
| 0.0065 | 4.1253 | 2700 | 0.0461 | |
|
|
| 0.0072 | 4.2017 | 2750 | 0.0491 | |
|
|
| 0.0018 | 4.2781 | 2800 | 0.0508 | |
|
|
| 0.0053 | 4.3545 | 2850 | 0.0508 | |
|
|
| 0.0024 | 4.4309 | 2900 | 0.0524 | |
|
|
| 0.0042 | 4.5073 | 2950 | 0.0534 | |
|
|
| 0.0056 | 4.5837 | 3000 | 0.0535 | |
|
|
| 0.0023 | 4.6600 | 3050 | 0.0541 | |
|
|
| 0.0028 | 4.7364 | 3100 | 0.0541 | |
|
|
| 0.0063 | 4.8128 | 3150 | 0.0538 | |
|
|
| 0.0034 | 4.8892 | 3200 | 0.0534 | |
|
|
| 0.0077 | 4.9656 | 3250 | 0.0536 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.46.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
