GPT2_MentalHealth_ChatBot

<!-- 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. -->

Model description

This model is a fine-tuned version of openai-community/gpt2 on an MentalHealthConversational dataset. It is designed to generate text based on provided depression related prompts and can be used for a variety of natural language generation tasks. It's been trained on question-answer pairs, including unanswerable questions, for the task of Depression related Conversations for 10 Epochs and obtained following loss:

• Training Loss: 1.6727

Model Training

• Training Dataset: MentalHealthConversational Dataset
• Pretrained Model: GPT-2

Evaluation

The model's performance can be evaluated using various metrics such as F1 score, BLEU score, and ROUGE score.

• F1 Score: 0.0908
• BLEU Score: 2.910400064753437e-05
• ROUGE Score: 0.1498

Example Usage

from transformers import pipeline, GPT2Tokenizer, GPT2LMHeadModel

# Load tokenizer and model
model_name = "Kiran2004/GPT2_MentalHealth_ChatBot"
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
model = GPT2LMHeadModel.from_pretrained(model_name)

# Generate text
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
prompt = "Your prompt goes here"
output = generator(prompt, max_length=50, num_return_sequences=1)
print(output[0]["generated_text"])

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 3
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Tokenizers 0.15.2