metadata

license: apache-2.0
base_model: google-bert/bert-large-cased-whole-word-masking
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: Intent-classification-BERT-Large-Ashuv5
    results: []

Intent-classification-BERT-Large-Ashuv5

This model is a fine-tuned version of google-bert/bert-large-cased-whole-word-masking on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.7988
Accuracy: 0.1420
F1: 0.0414
Precision: 0.0237
Recall: 0.1667

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: 0.0005
train_batch_size: 16
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
2.1123	0.24	10	1.8066	0.2174	0.0595	0.0362	0.1667
1.8577	0.49	20	1.9500	0.1242	0.0368	0.0207	0.1667
1.8864	0.73	30	1.7999	0.1801	0.0509	0.0300	0.1667
1.8516	0.98	40	1.8570	0.1429	0.0417	0.0238	0.1667
1.8664	1.22	50	1.8667	0.1242	0.0368	0.0207	0.1667
1.8207	1.46	60	1.9616	0.1180	0.0352	0.0197	0.1667
1.8652	1.71	70	1.7831	0.2174	0.0595	0.0362	0.1667
1.8372	1.95	80	1.8018	0.2174	0.0595	0.0362	0.1667
1.8671	2.2	90	1.8436	0.1180	0.0352	0.0197	0.1667
1.8484	2.44	100	1.7722	0.2174	0.0595	0.0362	0.1667
1.8262	2.68	110	1.7752	0.2174	0.0595	0.0362	0.1667
1.8292	2.93	120	1.8064	0.1242	0.0368	0.0207	0.1667

Framework versions

Transformers 4.38.2
Pytorch 2.1.2
Datasets 2.1.0
Tokenizers 0.15.2