|
|
--- |
|
|
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-fold6 |
|
|
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-fold6 |
|
|
|
|
|
This model is a fine-tuned version of [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) on the course-train-fold6 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0381 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.4971 | 0.0751 | 50 | 0.3237 | |
|
|
| 0.1179 | 0.1502 | 100 | 0.0942 | |
|
|
| 0.0891 | 0.2254 | 150 | 0.0797 | |
|
|
| 0.0539 | 0.3005 | 200 | 0.0598 | |
|
|
| 0.065 | 0.3756 | 250 | 0.0575 | |
|
|
| 0.052 | 0.4507 | 300 | 0.0530 | |
|
|
| 0.0535 | 0.5258 | 350 | 0.0545 | |
|
|
| 0.0512 | 0.6009 | 400 | 0.0466 | |
|
|
| 0.0597 | 0.6761 | 450 | 0.0495 | |
|
|
| 0.0509 | 0.7512 | 500 | 0.0469 | |
|
|
| 0.0624 | 0.8263 | 550 | 0.0431 | |
|
|
| 0.035 | 0.9014 | 600 | 0.0458 | |
|
|
| 0.0546 | 0.9765 | 650 | 0.0444 | |
|
|
| 0.0404 | 1.0516 | 700 | 0.0443 | |
|
|
| 0.0342 | 1.1268 | 750 | 0.0434 | |
|
|
| 0.0298 | 1.2019 | 800 | 0.0428 | |
|
|
| 0.0348 | 1.2770 | 850 | 0.0407 | |
|
|
| 0.0291 | 1.3521 | 900 | 0.0397 | |
|
|
| 0.0373 | 1.4272 | 950 | 0.0397 | |
|
|
| 0.0289 | 1.5023 | 1000 | 0.0406 | |
|
|
| 0.0339 | 1.5775 | 1050 | 0.0450 | |
|
|
| 0.0244 | 1.6526 | 1100 | 0.0412 | |
|
|
| 0.0288 | 1.7277 | 1150 | 0.0402 | |
|
|
| 0.036 | 1.8028 | 1200 | 0.0395 | |
|
|
| 0.0334 | 1.8779 | 1250 | 0.0392 | |
|
|
| 0.0568 | 1.9531 | 1300 | 0.0428 | |
|
|
| 0.0206 | 2.0282 | 1350 | 0.0409 | |
|
|
| 0.0226 | 2.1033 | 1400 | 0.0408 | |
|
|
| 0.0257 | 2.1784 | 1450 | 0.0407 | |
|
|
| 0.0138 | 2.2535 | 1500 | 0.0414 | |
|
|
| 0.0167 | 2.3286 | 1550 | 0.0409 | |
|
|
| 0.0217 | 2.4038 | 1600 | 0.0388 | |
|
|
| 0.0195 | 2.4789 | 1650 | 0.0427 | |
|
|
| 0.0223 | 2.5540 | 1700 | 0.0437 | |
|
|
| 0.0195 | 2.6291 | 1750 | 0.0428 | |
|
|
| 0.0218 | 2.7042 | 1800 | 0.0409 | |
|
|
| 0.0189 | 2.7793 | 1850 | 0.0401 | |
|
|
| 0.0195 | 2.8545 | 1900 | 0.0381 | |
|
|
| 0.0188 | 2.9296 | 1950 | 0.0399 | |
|
|
| 0.0105 | 3.0047 | 2000 | 0.0412 | |
|
|
| 0.0073 | 3.0798 | 2050 | 0.0443 | |
|
|
| 0.0082 | 3.1549 | 2100 | 0.0466 | |
|
|
| 0.0107 | 3.2300 | 2150 | 0.0490 | |
|
|
| 0.0143 | 3.3052 | 2200 | 0.0447 | |
|
|
| 0.005 | 3.3803 | 2250 | 0.0471 | |
|
|
| 0.0079 | 3.4554 | 2300 | 0.0481 | |
|
|
| 0.0085 | 3.5305 | 2350 | 0.0501 | |
|
|
| 0.0073 | 3.6056 | 2400 | 0.0468 | |
|
|
| 0.0034 | 3.6808 | 2450 | 0.0481 | |
|
|
| 0.0053 | 3.7559 | 2500 | 0.0496 | |
|
|
| 0.0052 | 3.8310 | 2550 | 0.0498 | |
|
|
| 0.0117 | 3.9061 | 2600 | 0.0501 | |
|
|
| 0.0082 | 3.9812 | 2650 | 0.0500 | |
|
|
| 0.0054 | 4.0563 | 2700 | 0.0516 | |
|
|
| 0.0019 | 4.1315 | 2750 | 0.0546 | |
|
|
| 0.0048 | 4.2066 | 2800 | 0.0565 | |
|
|
| 0.0026 | 4.2817 | 2850 | 0.0583 | |
|
|
| 0.001 | 4.3568 | 2900 | 0.0608 | |
|
|
| 0.0022 | 4.4319 | 2950 | 0.0609 | |
|
|
| 0.0036 | 4.5070 | 3000 | 0.0615 | |
|
|
| 0.0006 | 4.5822 | 3050 | 0.0621 | |
|
|
| 0.0019 | 4.6573 | 3100 | 0.0624 | |
|
|
| 0.0027 | 4.7324 | 3150 | 0.0628 | |
|
|
| 0.0022 | 4.8075 | 3200 | 0.0629 | |
|
|
| 0.002 | 4.8826 | 3250 | 0.0630 | |
|
|
| 0.0063 | 4.9577 | 3300 | 0.0628 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.46.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
