XLMRobertaTrainedOnSWEz – AI Model by kevinbror | AlphaNeural AI

You can deploy this model and start earning money today!

kevinbror/
XLMRobertaTrainedOnSWEz

like

0

question-answering

generated_from_keras_callback

endpoints_compatible

Views

No views yet

XLMRobertaTrainedOnSWEz

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

Train Loss: 0.5177
Train End Logits Accuracy: 0.8335
Train Start Logits Accuracy: 0.8275
Validation Loss: 1.0855
Validation End Logits Accuracy: 0.7143
Validation Start Logits Accuracy: 0.7089
Epoch: 3

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': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 29248, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
1.3112	0.6049	0.5996	0.9920	0.6931	0.6899	0
0.8736	0.7267	0.7230	0.9677	0.7119	0.7100	1
0.6621	0.7879	0.7839	1.0244	0.7074	0.7058	2
0.5177	0.8335	0.8275	1.0855	0.7143	0.7089	3

Framework versions

Transformers 4.20.1
TensorFlow 2.6.4
Datasets 2.1.0
Tokenizers 0.12.1