bigbird-dialogue-score

This model is a fine-tuned version of google/bigbird-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.2129
• eval_f1: 0.9290
• eval_precision: 0.9173
• eval_recall: 0.9410
• eval_runtime: 311.0516
• eval_samples_per_second: 49.304
• eval_steps_per_second: 6.163
• epoch: 1.0
• step: 5432

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: 5e-06
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 6
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.7.1
• Tokenizers 0.13.2