README.md

metadata

library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: bert-wellness-classifier
    results: []

bert-wellness-classifier

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

• Loss: 1.0555
• Accuracy: 0.624
• Auc: 0.867
• Precision Class 0: 0.4
• Precision Class 1: 0.762
• Precision Class 2: 0.429
• Precision Class 3: 0.72
• Precision Class 4: 0.7
• Precision Class 5: 0.5
• Recall Class 0: 0.421
• Recall Class 1: 0.696
• Recall Class 2: 0.444
• Recall Class 3: 0.766
• Recall Class 4: 0.766
• Recall Class 5: 0.364

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Auc	Precision Class 0	Precision Class 1	Precision Class 2	Precision Class 3	Precision Class 4	Precision Class 5	Recall Class 0	Recall Class 1	Recall Class 2	Recall Class 3	Recall Class 4	Recall Class 5
1.6248	1.0	62	1.4733	0.439	0.777	0.371	0.0	0.2	0.706	0.399	0.0	0.52	0.0	0.045	0.571	0.821	0.0
1.4241	2.0	124	1.3340	0.524	0.821	0.464	0.625	0.5	0.627	0.514	0.25	0.52	0.25	0.182	0.762	0.806	0.083
1.3082	3.0	186	1.2389	0.547	0.849	0.448	0.714	0.345	0.816	0.531	0.455	0.52	0.25	0.455	0.738	0.776	0.139
1.2177	4.0	248	1.1702	0.608	0.862	0.478	0.722	0.35	0.625	0.694	0.533	0.44	0.65	0.318	0.952	0.746	0.222
1.1415	5.0	310	1.1146	0.594	0.869	0.48	0.733	0.417	0.698	0.607	0.389	0.48	0.55	0.227	0.881	0.806	0.194
1.1024	6.0	372	1.0959	0.59	0.87	0.462	0.833	0.368	0.75	0.672	0.375	0.48	0.5	0.318	0.857	0.672	0.417
1.0609	7.0	434	1.0660	0.623	0.874	0.5	0.846	0.381	0.783	0.667	0.438	0.44	0.55	0.364	0.857	0.776	0.389
1.0444	8.0	496	1.0565	0.623	0.875	0.5	0.857	0.364	0.755	0.676	0.448	0.48	0.6	0.364	0.881	0.746	0.361
1.0295	9.0	558	1.0497	0.623	0.875	0.5	0.857	0.348	0.783	0.68	0.433	0.48	0.6	0.364	0.857	0.761	0.361
1.0067	10.0	620	1.0471	0.623	0.876	0.5	0.857	0.348	0.755	0.676	0.464	0.48	0.6	0.364	0.881	0.746	0.361

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0