Regression_bert_1500

This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.3665
Train Mae: 0.5651
Train Mse: 0.4539
Train R2-score: 0.5632
Validation Loss: 0.3640
Validation Mae: 0.6123
Validation Mse: 0.4470
Validation R2-score: 0.5765
Epoch: 22

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': 1e-04, '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	Validation Loss	Validation Mae	Validation Mse	Validation R2-score	Epoch
0.3911	0.5811	0.4875	0.5636	0.3808	0.6393	0.4778	0.4775	0
0.3669	0.5644	0.4527	0.6196	0.3524	0.5673	0.4286	0.6944	1
0.3652	0.5606	0.4457	0.6645	0.3711	0.6253	0.4600	0.5315	2
0.3669	0.5642	0.4490	0.5194	0.3525	0.5695	0.4286	0.6901	3
0.3693	0.5693	0.4580	0.6646	0.3558	0.5904	0.4329	0.6414	4
0.3682	0.5633	0.4540	0.7464	0.3602	0.5255	0.4485	0.7509	5
0.3712	0.5632	0.4527	0.6645	0.3650	0.6145	0.4489	0.5693	6
0.3781	0.5720	0.4661	0.5801	0.3545	0.5849	0.4309	0.6553	7
0.3659	0.5673	0.4564	0.1693	0.3723	0.6271	0.4621	0.5247	8
0.3693	0.5642	0.4487	0.7048	0.3524	0.5641	0.4289	0.7006	9
0.3656	0.5655	0.4495	0.6565	0.3575	0.5328	0.4425	0.7448	10
0.3685	0.5632	0.4540	0.7202	0.3551	0.5878	0.4319	0.6482	11
0.3702	0.5646	0.4543	0.7295	0.3528	0.5557	0.4306	0.7152	12
0.3661	0.5615	0.4450	0.6631	0.3683	0.5240	0.4664	0.7592	13
0.3835	0.5742	0.4757	0.7335	0.3531	0.5523	0.4316	0.7206	14
0.3641	0.5628	0.4472	0.7325	0.3559	0.5909	0.4331	0.6399	15
0.3764	0.5633	0.4566	0.7291	0.3549	0.5867	0.4315	0.6508	16
0.3625	0.5594	0.4443	0.5555	0.3648	0.6141	0.4486	0.5707	17
0.3816	0.5743	0.4693	0.6649	0.3559	0.5385	0.4385	0.7389	18
0.3721	0.5721	0.4618	0.6791	0.3529	0.5745	0.4288	0.6795	19
0.3711	0.5659	0.4586	0.2709	0.3610	0.5234	0.4505	0.7525	20
0.3693	0.5641	0.4501	0.7400	0.3525	0.5607	0.4294	0.7068	21
0.3665	0.5651	0.4539	0.5632	0.3640	0.6123	0.4470	0.5765	22

Framework versions

Transformers 4.27.4
TensorFlow 2.12.0
Datasets 2.11.0
Tokenizers 0.13.3

Regression_bert_1500

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

NSDT 3DConvert

UnrealSynth

DreamTexture.js