metadata

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

output

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

Loss: 0.8310
Accuracy: 0.7919
Precision: 0.8030
Recall: 0.7919
F1: 0.7889

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: 5e-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: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	495	1.0327	0.7253	0.7362	0.7253	0.7090
1.68	2.0	990	0.8310	0.7919	0.8030	0.7919	0.7889
0.8242	3.0	1485	0.8599	0.8091	0.8106	0.8091	0.8013
0.6748	4.0	1980	0.8628	0.8263	0.8125	0.8263	0.8158
0.4822	5.0	2475	1.0139	0.8162	0.8065	0.8162	0.8070
0.3781	6.0	2970	1.0535	0.8081	0.8013	0.8081	0.8011
0.3832	7.0	3465	1.1459	0.8081	0.8039	0.8081	0.8034
0.3101	8.0	3960	1.3831	0.7788	0.8079	0.7788	0.7847
0.2665	9.0	4455	1.2051	0.8222	0.8263	0.8222	0.8197
0.2286	10.0	4950	1.4487	0.7980	0.8064	0.7980	0.7962
0.2163	11.0	5445	1.4848	0.8121	0.8240	0.8121	0.8123
0.1965	12.0	5940	1.4572	0.7919	0.8051	0.7919	0.7919

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Tokenizers 0.15.0