Regression_bert_7

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

Model description

More information needed

More information needed

More information needed

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': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: float32

Train Loss	Train Mae	Train Mse	Train R2-score	Validation Loss	Validation Mae	Validation Mse	Validation R2-score	Epoch
0.5303	0.3176	0.1540	0.7493	0.6752	0.3537	0.1857	0.6758	0
0.2316	0.2775	0.1261	0.7746	0.2451	0.3060	0.1466	0.7473	1
0.2780	0.2930	0.1373	0.8061	0.1807	0.2593	0.1127	0.8102	2
0.1776	0.2673	0.1177	0.6536	0.1407	0.2617	0.1181	0.7975	3
0.2248	0.2906	0.1349	0.7639	0.1896	0.2915	0.1364	0.7665	4
0.2295	0.2718	0.1196	0.7991	0.2038	0.2757	0.1248	0.7882	5
0.2443	0.2460	0.0975	0.7298	0.1509	0.2779	0.1301	0.7783	6
0.2538	0.2907	0.1343	0.7783	0.1930	0.2984	0.1426	0.7559	7
0.2067	0.2777	0.1281	0.7605	0.1537	0.2809	0.1318	0.7756	8
0.1702	0.2696	0.1221	0.7766	0.3290	0.2756	0.1076	0.8214	9