ghdi/history-model

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

• Train Loss: 7.7920
• Validation Loss: 8.0670
• Epoch: 19

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', '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': -985, '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}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
10.9056	10.8226	0
10.7307	10.5379	1
10.4261	10.2113	2
10.1010	9.9371	3
9.8444	9.7434	4
9.6557	9.6059	5
9.5159	9.5011	6
9.3981	9.4071	7
9.2842	9.3113	8
9.1686	9.2134	9
9.0484	9.1090	10
8.9229	8.9987	11
8.7890	8.8852	12
8.6514	8.7654	13
8.5102	8.6470	14
8.3639	8.5240	15
8.2187	8.4040	16
8.0724	8.2869	17
7.9284	8.1745	18
7.7920	8.0670	19

Framework versions

• Transformers 4.27.4
• TensorFlow 2.12.0
• Datasets 2.11.0
• Tokenizers 0.13.3