svenbl80/roberta-large-finetuned-mnli

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

• Train Loss: 0.0360
• Validation Loss: 0.5873
• Train Accuracy: 0.8758
• Epoch: 17

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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 736290, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, '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
0.4137	0.3492	0.8715	0
0.3226	0.3720	0.8733	1
0.2768	0.4048	0.8728	2
0.2267	0.3649	0.8808	3
0.1890	0.4397	0.8646	4
0.1621	0.4422	0.8772	5
0.1378	0.4529	0.8758	6
0.1191	0.4992	0.8642	7
0.1102	0.4681	0.8693	8
0.0970	0.4758	0.8779	9
0.0851	0.4850	0.8630	10
0.0884	0.5140	0.8767	11
0.0644	0.5284	0.8801	12
0.0605	0.5239	0.8765	13
0.0554	0.7088	0.8433	14
0.0460	0.5774	0.8722	15
0.0386	0.5296	0.8741	16
0.0360	0.5873	0.8758	17

Framework versions

• Transformers 4.35.2
• TensorFlow 2.11.0
• Datasets 2.15.0
• Tokenizers 0.15.0