|
--- |
|
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ai-doctor-mental-health-ft |
|
results: [] |
|
language: |
|
- en |
|
datasets: |
|
- heliosbrahma/mental_health_chatbot_dataset |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# ai-doctor-mental-health-ft |
|
|
|
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.1807 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.6533 | 0.9730 | 9 | 3.1807 | |
|
| 2.6383 | 1.9459 | 18 | 3.1807 | |
|
| 2.6153 | 2.9189 | 27 | 3.1807 | |
|
| 2.3762 | 4.0 | 37 | 3.1807 | |
|
| 2.6248 | 4.9730 | 46 | 3.1807 | |
|
| 2.6247 | 5.9459 | 55 | 3.1807 | |
|
| 2.6254 | 6.9189 | 64 | 3.1807 | |
|
| 2.3817 | 8.0 | 74 | 3.1807 | |
|
| 2.6391 | 8.9730 | 83 | 3.1807 | |
|
| 2.4431 | 9.7297 | 90 | 3.1807 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.2.2+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
