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_teacher
    results: []

bert-wellness-classifier_teacher

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: 0.7694
• Accuracy: 0.688
• Auc: 0.9
• Precision Class 0: 0.862
• Precision Class 1: 0.739
• Precision Class 2: 0.613
• Precision Class 3: 0.538
• Recall Class 0: 0.781
• Recall Class 1: 0.81
• Recall Class 2: 0.704
• Recall Class 3: 0.483

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: 8
• eval_batch_size: 8
• 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	Recall Class 0	Recall Class 1	Recall Class 2	Recall Class 3
1.3247	1.0	63	1.1856	0.569	0.819	0.759	0.727	0.414	0.727	0.688	0.381	0.889	0.276
1.0767	2.0	126	1.0166	0.587	0.857	0.667	0.643	1.0	0.462	0.75	0.429	0.259	0.828
0.9285	3.0	189	0.9616	0.633	0.875	0.846	0.486	1.0	0.528	0.688	0.857	0.37	0.655
0.8628	4.0	252	0.8910	0.624	0.885	0.88	0.514	0.64	0.5	0.688	0.857	0.593	0.414
0.7828	5.0	315	0.8369	0.679	0.888	0.88	0.667	0.75	0.514	0.688	0.857	0.556	0.655
0.7489	6.0	378	0.7962	0.706	0.899	0.857	0.762	0.704	0.545	0.75	0.762	0.704	0.621
0.6981	7.0	441	0.8118	0.679	0.896	0.88	0.708	0.633	0.533	0.688	0.81	0.704	0.552
0.6634	8.0	504	0.7915	0.688	0.898	0.889	0.708	0.655	0.517	0.75	0.81	0.704	0.517
0.6651	9.0	567	0.7777	0.67	0.9	0.862	0.739	0.576	0.5	0.781	0.81	0.704	0.414
0.6591	10.0	630	0.7694	0.688	0.9	0.862	0.739	0.613	0.538	0.781	0.81	0.704	0.483

Framework versions

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