|
|
--- |
|
|
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-fold1 |
|
|
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-fold1 |
|
|
|
|
|
This model is a fine-tuned version of [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) on the course-train-fold1 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0342 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.4401 | 0.0770 | 50 | 0.3166 | |
|
|
| 0.1222 | 0.1539 | 100 | 0.0882 | |
|
|
| 0.0887 | 0.2309 | 150 | 0.0669 | |
|
|
| 0.0749 | 0.3078 | 200 | 0.0571 | |
|
|
| 0.0607 | 0.3848 | 250 | 0.0536 | |
|
|
| 0.0595 | 0.4617 | 300 | 0.0538 | |
|
|
| 0.0569 | 0.5387 | 350 | 0.0479 | |
|
|
| 0.0692 | 0.6156 | 400 | 0.0517 | |
|
|
| 0.0384 | 0.6926 | 450 | 0.0476 | |
|
|
| 0.0339 | 0.7695 | 500 | 0.0445 | |
|
|
| 0.0515 | 0.8465 | 550 | 0.0412 | |
|
|
| 0.0423 | 0.9234 | 600 | 0.0403 | |
|
|
| 0.031 | 1.0004 | 650 | 0.0412 | |
|
|
| 0.0415 | 1.0773 | 700 | 0.0405 | |
|
|
| 0.0308 | 1.1543 | 750 | 0.0384 | |
|
|
| 0.0306 | 1.2312 | 800 | 0.0376 | |
|
|
| 0.0376 | 1.3082 | 850 | 0.0391 | |
|
|
| 0.024 | 1.3851 | 900 | 0.0384 | |
|
|
| 0.0406 | 1.4621 | 950 | 0.0392 | |
|
|
| 0.0398 | 1.5391 | 1000 | 0.0376 | |
|
|
| 0.0325 | 1.6160 | 1050 | 0.0356 | |
|
|
| 0.0396 | 1.6930 | 1100 | 0.0394 | |
|
|
| 0.0266 | 1.7699 | 1150 | 0.0388 | |
|
|
| 0.023 | 1.8469 | 1200 | 0.0392 | |
|
|
| 0.0315 | 1.9238 | 1250 | 0.0389 | |
|
|
| 0.0238 | 2.0008 | 1300 | 0.0342 | |
|
|
| 0.0189 | 2.0777 | 1350 | 0.0361 | |
|
|
| 0.0293 | 2.1547 | 1400 | 0.0367 | |
|
|
| 0.0128 | 2.2316 | 1450 | 0.0420 | |
|
|
| 0.0195 | 2.3086 | 1500 | 0.0385 | |
|
|
| 0.0174 | 2.3855 | 1550 | 0.0383 | |
|
|
| 0.0143 | 2.4625 | 1600 | 0.0415 | |
|
|
| 0.0249 | 2.5394 | 1650 | 0.0404 | |
|
|
| 0.0195 | 2.6164 | 1700 | 0.0383 | |
|
|
| 0.0266 | 2.6933 | 1750 | 0.0376 | |
|
|
| 0.0216 | 2.7703 | 1800 | 0.0365 | |
|
|
| 0.0236 | 2.8472 | 1850 | 0.0366 | |
|
|
| 0.0198 | 2.9242 | 1900 | 0.0369 | |
|
|
| 0.0311 | 3.0012 | 1950 | 0.0370 | |
|
|
| 0.0088 | 3.0781 | 2000 | 0.0424 | |
|
|
| 0.0126 | 3.1551 | 2050 | 0.0467 | |
|
|
| 0.0085 | 3.2320 | 2100 | 0.0463 | |
|
|
| 0.0083 | 3.3090 | 2150 | 0.0453 | |
|
|
| 0.0164 | 3.3859 | 2200 | 0.0470 | |
|
|
| 0.0115 | 3.4629 | 2250 | 0.0465 | |
|
|
| 0.0134 | 3.5398 | 2300 | 0.0469 | |
|
|
| 0.0052 | 3.6168 | 2350 | 0.0470 | |
|
|
| 0.0104 | 3.6937 | 2400 | 0.0448 | |
|
|
| 0.0075 | 3.7707 | 2450 | 0.0459 | |
|
|
| 0.0068 | 3.8476 | 2500 | 0.0485 | |
|
|
| 0.0089 | 3.9246 | 2550 | 0.0494 | |
|
|
| 0.0091 | 4.0015 | 2600 | 0.0476 | |
|
|
| 0.0021 | 4.0785 | 2650 | 0.0498 | |
|
|
| 0.0061 | 4.1554 | 2700 | 0.0529 | |
|
|
| 0.0011 | 4.2324 | 2750 | 0.0541 | |
|
|
| 0.0025 | 4.3093 | 2800 | 0.0549 | |
|
|
| 0.0029 | 4.3863 | 2850 | 0.0560 | |
|
|
| 0.0027 | 4.4633 | 2900 | 0.0570 | |
|
|
| 0.0017 | 4.5402 | 2950 | 0.0572 | |
|
|
| 0.0019 | 4.6172 | 3000 | 0.0574 | |
|
|
| 0.005 | 4.6941 | 3050 | 0.0575 | |
|
|
| 0.0033 | 4.7711 | 3100 | 0.0573 | |
|
|
| 0.005 | 4.8480 | 3150 | 0.0576 | |
|
|
| 0.0019 | 4.9250 | 3200 | 0.0575 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.46.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
