Regression_albert_5

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

• Train Loss: 0.1548
• Train Mae: 0.2765
• Train Mse: 0.1336
• Train R2-score: 0.7547
• Train Accuracy: 0.7462
• Validation Loss: 0.1908
• Validation Mae: 0.3787
• Validation Mse: 0.1894
• Validation R2-score: 0.8458
• Validation Accuracy: 0.4595
• 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: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 2e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Mae	Train Mse	Train R2-score	Train Accuracy	Validation Loss	Validation Mae	Validation Mse	Validation R2-score	Validation Accuracy	Epoch
0.5723	0.3984	0.2343	0.4755	0.5923	0.1856	0.3686	0.1843	0.8559	0.4324	0
0.1822	0.2906	0.1403	0.7246	0.6538	0.1577	0.3485	0.1561	0.8714	0.9459	1
0.1765	0.2865	0.1376	0.6770	0.6538	0.1356	0.3325	0.1337	0.8808	0.9459	2
0.1959	0.2945	0.1383	0.6806	0.7308	0.2115	0.4054	0.2104	0.8366	0.3243	3
0.1698	0.2906	0.1408	0.7195	0.6231	0.1489	0.3371	0.1472	0.8726	0.9459	4
0.2081	0.2687	0.1178	0.7632	0.8385	0.2547	0.4572	0.2539	0.8046	0.3243	5
0.1806	0.3087	0.1554	0.7168	0.6462	0.1477	0.3401	0.1460	0.8757	0.9459	6
0.1910	0.3102	0.1559	0.7295	0.6308	0.1726	0.3544	0.1711	0.8602	0.8919	7
0.1697	0.2609	0.1132	0.7876	0.8538	0.1856	0.3694	0.1843	0.8537	0.5946	8
0.1548	0.2765	0.1336	0.7547	0.7462	0.1908	0.3787	0.1894	0.8458	0.4595	9

Framework versions

• Transformers 4.27.2
• TensorFlow 2.11.0
• Datasets 2.10.1
• Tokenizers 0.13.2