Modelpublic

liqi6811/tBERT_big_AUD_USD_M15

sourceHugging Faceupdated 3y agoView on Hugging Face

0likes6downloads

Model Card

tBERTbigAUDUSDM15

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set:

—Train Loss: 3.8267
—Validation Loss: 4.1189
—Epoch: 20

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': 'AdamW', 'weightdecay': 0.004, 'clipnorm': None, 'globalclipnorm': None, 'clipvalue': None, 'useema': False, 'emamomentum': 0.99, 'emaoverwritefrequency': None, 'jitcompile': False, 'islegacyoptimizer': False, 'learningrate': 5e-05, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
—training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
0.0158	0.0710	0
0.0151	0.0729	1
0.0159	0.0729	2
2.3811	3.1534	3
2.7825	2.4722	4
2.2866	2.4094	5
2.2834	2.3846	6
2.0984	2.0451	7
2.0839	2.0866	8
2.1224	1.5450	9
1.9191	1.6559	10
1.8116	1.3405	11
1.4663	1.1409	12
1.1174	0.9641	13
0.9987	0.9052	14
1.9402	3.8288	15
3.8278	3.8280	16
3.8274	3.8277	17
3.8272	3.8295	18
3.8269	3.8295	19
3.8267	4.1189	20

Framework versions

—Transformers 4.30.0.dev0
—TensorFlow 2.12.0
—Datasets 2.12.0
—Tokenizers 0.13.3