svenbl80/roberta-base-finetuned-new-mnli-run-1

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

• Train Loss: 0.0248
• Validation Loss: 0.7357
• Train Accuracy: 0.8661
• Epoch: 9

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': 245430, '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	Validation Loss	Train Accuracy	Epoch
0.4558	0.3972	0.8495	0
0.3309	0.3834	0.8520	1
0.2465	0.4150	0.8627	2
0.1784	0.4412	0.8670	3
0.1288	0.4816	0.8626	4
0.0926	0.5470	0.8647	5
0.0666	0.5634	0.8669	6
0.0477	0.6574	0.8648	7
0.0345	0.6919	0.8641	8
0.0248	0.7357	0.8661	9

Framework versions

• Transformers 4.28.0
• TensorFlow 2.9.1
• Datasets 2.15.0
• Tokenizers 0.13.3