bart-v2-dialouge

This model is a fine-tuned version of hyunwoongko/kobart on the naem1023/aihub-dialogue dataset.

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: 1e-05
• train_batch_size: 150
• eval_batch_size: 40
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 1200
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6.0

Training results

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.1
• Datasets 2.4.0
• Tokenizers 0.12.1