| --- |
| library_name: peft |
| license: mit |
| base_model: klyang/MentaLLaMA-chat-7B-hf |
| tags: |
| - llama-factory |
| - lora |
| - generated_from_trainer |
| model-index: |
| - name: MentaLLaMA-chat-7B-PsyCourse-info-fold3 |
| 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. --> |
|
|
| # MentaLLaMA-chat-7B-PsyCourse-info-fold3 |
|
|
| This model is a fine-tuned version of [klyang/MentaLLaMA-chat-7B-hf](https://huggingface.co/klyang/MentaLLaMA-chat-7B-hf) on the course-info-train-fold3 dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.1429 |
|
|
| ## 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 | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 0.7489 | 0.3951 | 10 | 0.6547 | |
| | 0.2511 | 0.7901 | 20 | 0.2636 | |
| | 0.1969 | 1.1852 | 30 | 0.1976 | |
| | 0.2206 | 1.5802 | 40 | 0.1709 | |
| | 0.1426 | 1.9753 | 50 | 0.1621 | |
| | 0.1305 | 2.3704 | 60 | 0.1543 | |
| | 0.0773 | 2.7654 | 70 | 0.1522 | |
| | 0.0848 | 3.1605 | 80 | 0.1463 | |
| | 0.1227 | 3.5556 | 90 | 0.1459 | |
| | 0.085 | 3.9506 | 100 | 0.1446 | |
| | 0.1099 | 4.3457 | 110 | 0.1436 | |
| | 0.1193 | 4.7407 | 120 | 0.1429 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.12.0 |
| - Transformers 4.46.1 |
| - Pytorch 2.5.1+cu124 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.3 |
