bert-large-cased-finetuned-low20-cased-DA-20 – AI Model by jojoUla | AlphaNeural AI

You can deploy this model and start earning money today!

jojoUla/
bert-large-cased-finetuned-low20-cased-DA-20

like

0

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

bert-large-cased-finetuned-low20-cased-DA-20 (not in use)

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: 1.3667

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: 64
eval_batch_size: 64
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
2.477	1.0	1	3.0843
3.5516	2.0	2	4.2279
3.6173	3.0	3	4.2543
3.1873	4.0	4	2.8752
3.9494	5.0	5	1.7727
2.628	6.0	6	2.2849
1.7451	7.0	7	2.2338
2.6641	8.0	8	1.4185
3.0739	9.0	9	4.0617
2.1557	10.0	10	3.4256
1.6353	11.0	11	3.0232
2.6313	12.0	12	4.2908
1.9466	13.0	13	3.0047
1.8104	14.0	14	2.9170
2.0315	15.0	15	3.5850
2.6848	16.0	16	4.4435
2.0859	17.0	17	3.9439
1.6852	18.0	18	0.9313
1.6071	19.0	19	3.6927
1.697	20.0	20	3.7250

Framework versions

Transformers 4.26.0
Pytorch 1.13.1+cu116
Datasets 2.9.0
Tokenizers 0.13.2