Mursel/turkishReviews-ds-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: 6.9491
• Validation Loss: 8.2449
• 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': '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': -896, '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
10.3116	9.9951	0
9.6734	9.6486	1
9.1872	9.2715	2
8.6895	8.9614	3
8.3149	8.7701	4
8.0652	8.6205	5
7.8347	8.5185	6
7.5944	8.3560	7
7.3397	8.2770	8
7.0877	8.2449	9
6.9492	8.2449	10
6.9488	8.2449	11
6.9486	8.2449	12
6.9483	8.2449	13
6.9483	8.2449	14
6.9473	8.2449	15
6.9495	8.2449	16
6.9491	8.2449	17

Framework versions

• Transformers 4.30.2
• TensorFlow 2.12.0
• Datasets 2.13.1
• Tokenizers 0.13.3