bert-large-cased-finetuned-lowR10-0-cased-DA-20 – AI Model by jojoUla | AlphaNeural AI

You can deploy this model and start earning money today!

jojoUla/
bert-large-cased-finetuned-lowR10-0-cased-DA-20

like

0

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

bert-large-cased-finetuned-lowR10-0-cased-DA-20

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

Loss: 3.8706

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:

learning_rate: 2e-05
train_batch_size: 30
eval_batch_size: 30
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.534	1.0	1	3.3267
3.4023	2.0	2	1.9169
3.9478	3.0	3	4.7299
2.7598	4.0	4	1.9790
3.5718	5.0	5	2.9120
2.554	6.0	6	4.7168
2.3288	7.0	7	3.0791
4.2772	8.0	8	5.0675
3.0613	9.0	9	2.8924
2.6295	10.0	10	4.0580
1.1492	11.0	11	1.9058
2.4894	12.0	12	3.3881
1.0674	13.0	13	4.1820
1.0408	14.0	14	1.3132
2.4876	15.0	15	1.8314
1.8407	16.0	16	2.4077
2.3834	17.0	17	2.9627
3.0375	18.0	18	2.5811
1.8393	19.0	19	2.4138
1.8369	20.0	20	2.2895

Framework versions

Transformers 4.26.0
Pytorch 1.13.1+cu116
Datasets 2.9.0
Tokenizers 0.13.2