voiceassistant-intent-bert-lora – AI Model by yuashi | AlphaNeural AI

You can deploy this model and start earning money today!

yuashi/
voiceassistant-intent-bert-lora

like

0

generated_from_trainer

clinc/clinc_oos

google-bert/bert-base-cased

Views

No views yet

voiceassistant-intent-bert-lora

This model is a fine-tuned version of bert-base-cased on clinc_oos dataset. It achieves the following results on the evaluation set:

Loss: 0.4182
Accuracy: 0.9081
F1 Macro: 0.9130

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: 0.0003
train_batch_size: 32
eval_batch_size: 64
seed: 42
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	F1 Macro
No log	1.0	477	2.4694	0.4748	0.4208
3.7133	2.0	954	1.3183	0.7181	0.7047
1.7805	3.0	1431	0.8659	0.8052	0.8030
1.0098	4.0	1908	0.6768	0.8461	0.8478
0.6774	5.0	2385	0.5619	0.8726	0.8758
0.5035	6.0	2862	0.4999	0.8881	0.8908
0.3952	7.0	3339	0.4620	0.8955	0.9007
0.3162	8.0	3816	0.4396	0.9006	0.9056
0.2796	9.0	4293	0.4250	0.9087	0.9134
0.261	10.0	4770	0.4182	0.9081	0.9130

Framework versions

PEFT 0.12.0
Transformers 4.44.2
Pytorch 2.13.0+cu126
Datasets 2.21.0
Tokenizers 0.19.1