ghdi/imbd-reviews-sample

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

• Train Loss: 5.9326
• Validation Loss: 6.3691
• 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': -887, '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
7.4384	7.2924	0
7.0231	6.9971	1
6.7445	6.7865	2
6.5201	6.6116	3
6.2942	6.4619	4
6.0867	6.3691	5
5.9325	6.3691	6
5.9331	6.3691	7
5.9327	6.3691	8
5.9318	6.3691	9
5.9309	6.3691	10
5.9304	6.3691	11
5.9312	6.3691	12
5.9339	6.3691	13
5.9322	6.3691	14
5.9351	6.3691	15
5.9311	6.3691	16
5.9328	6.3691	17
5.9307	6.3691	18
5.9326	6.3691	19

Framework versions

• Transformers 4.27.4
• TensorFlow 2.12.0
• Datasets 2.11.0
• Tokenizers 0.13.2