20240320102435_big_hinton – AI Model by adasgaleus | AlphaNeural AI

You can deploy this model and start earning money today!

adasgaleus/
20240320102435_big_hinton

like

0

token-classification

generated_from_trainer

google-bert/bert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

20240320102435_big_hinton

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

Loss: 0.0351
Precision: 0.9436
Recall: 0.9308
F1: 0.9372
Accuracy: 0.9859

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: 0.001
train_batch_size: 32
eval_batch_size: 32
seed: 69
gradient_accumulation_steps: 8
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 350
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0805	0.09	300	0.0626	0.9020	0.8843	0.8931	0.9758
0.0969	0.18	600	0.0770	0.8912	0.8486	0.8694	0.9704
0.0879	0.27	900	0.0682	0.8943	0.8733	0.8837	0.9735
0.0778	0.36	1200	0.0612	0.9013	0.8891	0.8952	0.9762
0.0703	0.44	1500	0.0564	0.9137	0.8909	0.9021	0.9779
0.0638	0.53	1800	0.0521	0.9244	0.8975	0.9107	0.9799
0.0579	0.62	2100	0.0480	0.9309	0.9029	0.9167	0.9812
0.0534	0.71	2400	0.0447	0.9323	0.9095	0.9208	0.9825
0.049	0.8	2700	0.0399	0.9329	0.9236	0.9282	0.9841
0.0451	0.89	3000	0.0373	0.9411	0.9226	0.9318	0.9849
0.0424	0.98	3300	0.0351	0.9436	0.9308	0.9372	0.9859

Framework versions

Transformers 4.38.2
Pytorch 2.2.0a0+6a974be
Datasets 2.18.0
Tokenizers 0.15.2