Regression_xlnet_aug_CustomLoss

This model is a fine-tuned version of xlnet-base-cased 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
0.2950	0.5789	0.4896	0.6909	0.2512	0.5341	0.4801	0.7603	0
0.2659	0.5516	0.4538	0.7145	0.2828	0.5680	0.5282	0.7477	1
0.2656	0.5492	0.4587	0.6858	0.2337	0.5345	0.4412	0.7431	2
0.2563	0.5484	0.4490	0.7247	0.2413	0.5202	0.4619	0.7581	3
0.2589	0.5511	0.4542	0.6757	0.2411	0.5199	0.4615	0.7580	4
0.2537	0.5407	0.4437	0.7605	0.2359	0.5244	0.4495	0.7517	5
0.2494	0.5385	0.4399	0.7668	0.2510	0.5821	0.4301	0.6621	6
0.2495	0.5403	0.4424	0.7765	0.2360	0.5242	0.4496	0.7519	7
0.2501	0.5394	0.4383	0.5209	0.2349	0.5279	0.4464	0.7491	8
0.2446	0.5343	0.4346	0.7534	0.2366	0.5585	0.4298	0.7105	9
0.2439	0.5316	0.4323	0.7561	0.2543	0.5376	0.4853	0.7599	10
0.2415	0.5348	0.4330	0.7928	0.2341	0.5316	0.4434	0.7459	11
0.2408	0.5323	0.4289	0.7827	0.2346	0.5291	0.4454	0.7481	12
0.2499	0.5392	0.4410	0.6008	0.2364	0.5230	0.4508	0.7527	13
0.2430	0.5316	0.4353	0.4207	0.2455	0.5751	0.4288	0.6784	14