deberta-v3-base-orgs-v2 – AI Model by nbroad | AlphaNeural AI

You can deploy this model and start earning money today!

nbroad/
deberta-v3-base-orgs-v2

like

0

token-classification

generated_from_trainer

microsoft/deberta-v3-base

autotrain_compatible

endpoints_compatible

Views

No views yet

deberta-v3-base-orgs-v2

This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

Accuracy: 0.9632
F1: 0.7927
Loss: 0.1186
Precision: 0.8127
Recall: 0.7735

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: 0.0003
train_batch_size: 256
eval_batch_size: 256
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 20
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Accuracy	F1	Validation Loss	Precision	Recall
0.0706	0.7	600	0.9602	0.7690	0.1138	0.7590	0.7793
0.0526	1.4	1200	0.9617	0.7870	0.1113	0.7942	0.7799
0.0409	2.11	1800	0.9627	0.7875	0.1125	0.7911	0.7839
0.0376	2.81	2400	0.9632	0.7927	0.1186	0.8127	0.7735

Framework versions

Transformers 4.35.2
Pytorch 2.1.0a0+32f93b1
Datasets 2.15.0
Tokenizers 0.15.0