amanneo/mail-generator-mini

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 5.4613
• Train Accuracy: 0.1611
• Validation Loss: 5.2617
• Validation Accuracy: 0.1386
• 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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': -925, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
• training_precision: mixed_float16

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
10.0053	0.1068	8.5247	0.1394	0
8.7772	0.1505	7.9685	0.1656	1
8.2057	0.1663	7.4436	0.1655	2
7.5786	0.1611	6.8572	0.1654	3
6.9698	0.1679	6.3646	0.1735	4
6.4911	0.1763	6.0124	0.1787	5
6.1632	0.1834	5.7751	0.1826	6
5.9057	0.1840	5.5786	0.1749	7
5.6874	0.1758	5.4023	0.1616	8
5.4613	0.1611	5.2617	0.1386	9

Framework versions

• Transformers 4.23.1
• TensorFlow 2.9.2
• Datasets 2.6.1
• Tokenizers 0.13.1