bert-uncased-massive-intent-classification-finetuned-banking-1

This model is a fine-tuned version of gokuls/bert-uncased-massive-intent-classification on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.6447
• Accuracy: 0.1822

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: 2e-05
• train_batch_size: 6
• eval_batch_size: 6
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.9685	1.0	3	2.7310	0.1422
2.8056	2.0	6	2.6970	0.1467
2.5004	3.0	9	2.6680	0.1511
2.445	4.0	12	2.6515	0.1778
2.3977	5.0	15	2.6447	0.1822

Framework versions

• Transformers 4.24.0
• Pytorch 1.12.1
• Datasets 2.3.2
• Tokenizers 0.12.1