bert-base-uncased-issues-128 – AI Model by kiki2013 | AlphaNeural AI

You can deploy this model and start earning money today!

kiki2013/
bert-base-uncased-issues-128

like

0

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

bert-base-uncased-issues-128

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.1415

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: 5e-05
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss
1.6963	1.0	291	1.5992
1.5292	2.0	582	1.4419
1.4256	3.0	873	1.4078
1.3472	4.0	1164	1.2984
1.3002	5.0	1455	1.2909
1.2514	6.0	1746	1.3003
1.2022	7.0	2037	1.2514
1.1681	8.0	2328	1.2121
1.1532	9.0	2619	1.2843
1.1214	10.0	2910	1.2365
1.1247	11.0	3201	1.1365
1.1033	12.0	3492	1.2102
1.0748	13.0	3783	1.2221
1.0698	14.0	4074	1.1152
1.0534	15.0	4365	1.1890
1.065	16.0	4656	1.1415

Framework versions

Transformers 4.27.4
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.2