Ashraf-kasem/custom_gpt2_frames_text_original_tokenizer

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

• Train Loss: 1.1074
• Validation Loss: 1.6432
• Epoch: 29

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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 240780, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
4.3075	3.4095	0
3.1973	2.8234	1
2.7420	2.5057	2
2.4541	2.3022	3
2.2507	2.1648	4
2.0962	2.0612	5
1.9736	1.9885	6
1.8729	1.9286	7
1.7883	1.8823	8
1.7153	1.8448	9
1.6517	1.8113	10
1.5953	1.7864	11
1.5446	1.7624	12
1.4994	1.7459	13
1.4578	1.7294	14
1.4200	1.7171	15
1.3851	1.7026	16
1.3528	1.6958	17
1.3229	1.6846	18
1.2950	1.6760	19
1.2690	1.6704	20
1.2448	1.6650	21
1.2223	1.6599	22
1.2012	1.6539	23
1.1815	1.6534	24
1.1635	1.6486	25
1.1470	1.6457	26
1.1318	1.6443	27
1.1185	1.6434	28
1.1074	1.6432	29

Framework versions

• Transformers 4.25.1
• TensorFlow 2.9.0
• Datasets 2.8.0
• Tokenizers 0.13.2