metadata
library_name: transformers
license: apache-2.0
base_model: albert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
Model Card for Model ID
Fine tuned model to classify customer support request
Model Details
Model Description
- Model type: ALBERT
- Language(s) (NLP): English
- License: apache-2.0
- Finetuned from model : https://huggingface.co./vineetsharma/customer-support-intent-albert
Uses
How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
Training Details
Training Data
https://huggingface.co./datasets/bitext/Bitext-customer-support-llm-chatbot-training-dataset
Training Procedure
https://colab.research.google.com/drive/1RllMjMO_41l0pf0di1guQePpl97Z6M9A#scrollTo=SVjaVFshS-ox
Preprocessing [optional]
Dividing dataset 80/20% for finetuning and evaluation
Training Hyperparameters
- evaluation_strategy:epoch
- learning_rate: 2e-5
- per_device_train_batch_size: 16
- per_device_eval_batch_size: 16
- num_train_epochs: 3
- weight_decay: 0.01
Metrics & Evaluation
- eval_loss: 0.005226992070674896
- eval_accuracy: 0.9990697674418605
- eval_runtime: 10.7178
- eval_samples_per_second: 501.504
- eval_steps_per_second: 31.35
- epoch: 3.0
Testing Data, Factors & Metrics
Testing Data
20% of "https://huggingface.co./vineetsharma/customer-support-intent-albert" dataset
accuracy