|
|
--- |
|
|
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-fold9 |
|
|
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-fold9 |
|
|
|
|
|
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-fold9 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0368 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.6165 | 0.0768 | 50 | 0.3983 | |
|
|
| 0.1035 | 0.1535 | 100 | 0.0830 | |
|
|
| 0.0746 | 0.2303 | 150 | 0.0682 | |
|
|
| 0.0591 | 0.3070 | 200 | 0.0593 | |
|
|
| 0.0716 | 0.3838 | 250 | 0.0530 | |
|
|
| 0.0571 | 0.4606 | 300 | 0.0475 | |
|
|
| 0.0499 | 0.5373 | 350 | 0.0483 | |
|
|
| 0.0421 | 0.6141 | 400 | 0.0470 | |
|
|
| 0.0514 | 0.6908 | 450 | 0.0473 | |
|
|
| 0.042 | 0.7676 | 500 | 0.0463 | |
|
|
| 0.0672 | 0.8444 | 550 | 0.0476 | |
|
|
| 0.0388 | 0.9211 | 600 | 0.0446 | |
|
|
| 0.0391 | 0.9979 | 650 | 0.0403 | |
|
|
| 0.0304 | 1.0746 | 700 | 0.0424 | |
|
|
| 0.0396 | 1.1514 | 750 | 0.0430 | |
|
|
| 0.0347 | 1.2282 | 800 | 0.0395 | |
|
|
| 0.0356 | 1.3049 | 850 | 0.0410 | |
|
|
| 0.0333 | 1.3817 | 900 | 0.0384 | |
|
|
| 0.0318 | 1.4585 | 950 | 0.0376 | |
|
|
| 0.0309 | 1.5352 | 1000 | 0.0383 | |
|
|
| 0.0216 | 1.6120 | 1050 | 0.0373 | |
|
|
| 0.0315 | 1.6887 | 1100 | 0.0370 | |
|
|
| 0.0273 | 1.7655 | 1150 | 0.0389 | |
|
|
| 0.0188 | 1.8423 | 1200 | 0.0379 | |
|
|
| 0.0362 | 1.9190 | 1250 | 0.0371 | |
|
|
| 0.0435 | 1.9958 | 1300 | 0.0368 | |
|
|
| 0.0212 | 2.0725 | 1350 | 0.0396 | |
|
|
| 0.0184 | 2.1493 | 1400 | 0.0393 | |
|
|
| 0.0205 | 2.2261 | 1450 | 0.0381 | |
|
|
| 0.0316 | 2.3028 | 1500 | 0.0390 | |
|
|
| 0.0234 | 2.3796 | 1550 | 0.0400 | |
|
|
| 0.0258 | 2.4563 | 1600 | 0.0387 | |
|
|
| 0.0273 | 2.5331 | 1650 | 0.0393 | |
|
|
| 0.0199 | 2.6099 | 1700 | 0.0385 | |
|
|
| 0.0167 | 2.6866 | 1750 | 0.0394 | |
|
|
| 0.0288 | 2.7634 | 1800 | 0.0427 | |
|
|
| 0.022 | 2.8401 | 1850 | 0.0376 | |
|
|
| 0.0237 | 2.9169 | 1900 | 0.0384 | |
|
|
| 0.0176 | 2.9937 | 1950 | 0.0372 | |
|
|
| 0.0057 | 3.0704 | 2000 | 0.0443 | |
|
|
| 0.0148 | 3.1472 | 2050 | 0.0436 | |
|
|
| 0.0153 | 3.2239 | 2100 | 0.0499 | |
|
|
| 0.0116 | 3.3007 | 2150 | 0.0444 | |
|
|
| 0.0116 | 3.3775 | 2200 | 0.0473 | |
|
|
| 0.0133 | 3.4542 | 2250 | 0.0502 | |
|
|
| 0.0095 | 3.5310 | 2300 | 0.0501 | |
|
|
| 0.011 | 3.6078 | 2350 | 0.0467 | |
|
|
| 0.0136 | 3.6845 | 2400 | 0.0513 | |
|
|
| 0.0074 | 3.7613 | 2450 | 0.0478 | |
|
|
| 0.0104 | 3.8380 | 2500 | 0.0492 | |
|
|
| 0.0131 | 3.9148 | 2550 | 0.0514 | |
|
|
| 0.0113 | 3.9916 | 2600 | 0.0484 | |
|
|
| 0.0028 | 4.0683 | 2650 | 0.0536 | |
|
|
| 0.0046 | 4.1451 | 2700 | 0.0576 | |
|
|
| 0.0038 | 4.2218 | 2750 | 0.0616 | |
|
|
| 0.0029 | 4.2986 | 2800 | 0.0621 | |
|
|
| 0.0025 | 4.3754 | 2850 | 0.0640 | |
|
|
| 0.0037 | 4.4521 | 2900 | 0.0638 | |
|
|
| 0.0071 | 4.5289 | 2950 | 0.0648 | |
|
|
| 0.0015 | 4.6056 | 3000 | 0.0653 | |
|
|
| 0.002 | 4.6824 | 3050 | 0.0651 | |
|
|
| 0.0073 | 4.7592 | 3100 | 0.0645 | |
|
|
| 0.0061 | 4.8359 | 3150 | 0.0640 | |
|
|
| 0.0024 | 4.9127 | 3200 | 0.0639 | |
|
|
| 0.0054 | 4.9894 | 3250 | 0.0639 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.46.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
