---
license: gemma
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
base_model: google/gemma-7b
datasets:
- chansung/mental_health_counseling_conversations
model-index:
- name: mental_health_counseling_v0.1
  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. -->

# mental_health_counseling_v0.1

This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the chansung/mental_health_counseling_conversations dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0755

## 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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.357         | 1.0   | 120  | 2.2527          |
| 1.8805        | 2.0   | 240  | 1.8901          |
| 1.5884        | 3.0   | 360  | 1.6506          |
| 0.976         | 4.0   | 480  | 1.4923          |
| 0.494         | 5.0   | 600  | 1.4527          |
| 0.6722        | 6.0   | 720  | 1.5256          |
| 0.4155        | 7.0   | 840  | 1.6937          |
| 0.3646        | 8.0   | 960  | 1.9389          |
| 0.1977        | 9.0   | 1080 | 2.0741          |
| 0.072         | 10.0  | 1200 | 2.0755          |


### Framework versions

- PEFT 0.11.0
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1