banking-intent-distilbert-classifier

This model is a fine-tuned version of distilbert-base-uncased on the banking77 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3307
• Accuracy: 0.925

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-06
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0124	1.0	313	0.3307	0.925
0.0102	2.0	626	0.3331	0.9289
0.0077	3.0	939	0.3381	0.9282
0.0062	4.0	1252	0.3406	0.9276
0.0059	5.0	1565	0.3423	0.9282
0.0045	6.0	1878	0.3445	0.9282
0.0046	7.0	2191	0.3458	0.9286
0.0041	8.0	2504	0.3470	0.9286
0.0038	9.0	2817	0.3472	0.9286
0.0034	10.0	3130	0.3475	0.9286

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0