| --- |
| 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-doc-info-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-doc-info-fold1 |
|
|
| This model is a fine-tuned version of [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) on the course-doc-info-train-fold1 dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0625 |
|
|
| ## 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 | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 0.2938 | 0.3951 | 10 | 0.2596 | |
| | 0.1405 | 0.7901 | 20 | 0.1402 | |
| | 0.0894 | 1.1852 | 30 | 0.1057 | |
| | 0.0836 | 1.5802 | 40 | 0.0878 | |
| | 0.0632 | 1.9753 | 50 | 0.0771 | |
| | 0.0616 | 2.3704 | 60 | 0.0709 | |
| | 0.0534 | 2.7654 | 70 | 0.0676 | |
| | 0.0435 | 3.1605 | 80 | 0.0655 | |
| | 0.0402 | 3.5556 | 90 | 0.0642 | |
| | 0.046 | 3.9506 | 100 | 0.0631 | |
| | 0.0391 | 4.3457 | 110 | 0.0627 | |
| | 0.0555 | 4.7407 | 120 | 0.0625 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.12.0 |
| - Transformers 4.46.1 |
| - Pytorch 2.5.1+cu124 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.3 |
