metadata

license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: training-4
    results: []

training-4

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

Loss: 0.0335
Accuracy: 0.9931
Precision: 0.9982
Recall: 0.9875
F1: 0.9928

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: 1e-05
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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	0.25	85	0.0511	0.9819	0.9821	0.9804	0.9813
No log	0.5	170	0.0752	0.9836	0.9982	0.9679	0.9828
No log	0.75	255	0.0550	0.9888	0.9841	0.9929	0.9885
0.1064	1.0	340	0.0383	0.9923	0.9964	0.9875	0.9919
0.1064	1.25	425	0.0485	0.9923	0.9982	0.9857	0.9919
0.1064	1.5	510	0.0468	0.9914	0.9964	0.9857	0.9910
0.1064	1.76	595	0.0477	0.9914	1.0	0.9822	0.9910
0.0322	2.01	680	0.0506	0.9931	1.0	0.9857	0.9928
0.0322	2.26	765	0.0455	0.9914	0.9928	0.9893	0.9911
0.0322	2.51	850	0.0466	0.9914	0.9946	0.9875	0.9911
0.0322	2.76	935	0.0491	0.9931	1.0	0.9857	0.9928
0.0217	3.01	1020	0.0517	0.9923	0.9964	0.9875	0.9919
0.0217	3.26	1105	0.0455	0.9931	1.0	0.9857	0.9928
0.0217	3.51	1190	0.0338	0.9931	0.9982	0.9875	0.9928
0.0217	3.76	1275	0.0385	0.9940	1.0	0.9875	0.9937
0.024	4.01	1360	0.0376	0.9931	1.0	0.9857	0.9928
0.024	4.26	1445	0.0332	0.9931	0.9982	0.9875	0.9928
0.024	4.51	1530	0.0343	0.9923	0.9946	0.9893	0.9920
0.024	4.76	1615	0.0335	0.9931	0.9982	0.9875	0.9928

Framework versions

Transformers 4.33.1
Pytorch 2.2.0.dev20230913+cu121
Tokenizers 0.13.3