Modelpublic

khadija69/roberta_ASE_clb_ACCURACY

sourceHugging Facemitupdated 2y agoView on Hugging Face

0likes14downloads

Model Card

khadija69/robertaASEclb_ACCURACY

This model is a fine-tuned version of khadija69/roberta_ASE_clb_large_layers_tail on an unknown dataset. It achieves the following results on the evaluation set:

—Train Loss: 0.1366
—Train Accuracy: 0.6940
—Validation Loss: 0.2910
—Validation Accuracy: 0.6609
—Epoch: 5

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:

—optimizer: {'name': 'AdamWeightDecay', 'learningrate': {'module': 'keras.optimizers.schedules', 'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 2e-05, 'decaysteps': 2400, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registeredname': None}, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weightdecayrate': 0.01}
—training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.2680	0.6558	0.2525	0.6643	0
0.2325	0.6609	0.2515	0.6654	1
0.1997	0.6755	0.2630	0.6556	2
0.1735	0.6763	0.2681	0.6652	3
0.1546	0.6789	0.2752	0.6586	4
0.1366	0.6940	0.2910	0.6609	5

Framework versions

—Transformers 4.41.1
—TensorFlow 2.15.0
—Datasets 2.19.2
—Tokenizers 0.19.1