cchs-bert-visit-uncased-wordlevel-block512-batch4-ep30 – AI Model by hsohn3 | AlphaNeural AI

You can deploy this model and start earning money today!

hsohn3/
cchs-bert-visit-uncased-wordlevel-block512-batch4-ep30

like

0

generated_from_keras_callback

autotrain_compatible

endpoints_compatible

Views

No views yet

hsohn3/cchs-bert-visit-uncased-wordlevel-block512-batch4-ep30

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

Train Loss: 1.6958
Epoch: 29

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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Training results

Train Loss	Epoch
3.8594	0
3.0596	1
3.0244	2
3.0092	3
2.9900	4
2.9930	5
2.9806	6
2.9839	7
2.9784	8
2.9755	9
2.9733	10
2.9670	11
2.9607	12
2.9569	13
2.9176	14
2.8893	15
2.8539	16
2.8335	17
2.8110	18
2.7907	19
2.7756	20
2.7486	21
2.7169	22
2.6725	23
2.6094	24
2.5099	25
2.3102	26
2.0934	27
1.8858	28
1.6958	29

Framework versions

Transformers 4.20.1
TensorFlow 2.8.2
Datasets 2.3.2
Tokenizers 0.12.1