ai-doctor-mental-health-ft

This model is a fine-tuned version of 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