ukr-roberta-base-finetuned-sarc-synth – AI Model by Snizhanna | AlphaNeural AI

You can deploy this model and start earning money today!

Snizhanna/
ukr-roberta-base-finetuned-sarc-synth

like

0

text-classification

generated_from_trainer

youscan/ukr-roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

ukr-roberta-base-finetuned-sarc-synth

This model is a fine-tuned version of youscan/ukr-roberta-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7871
Accuracy: 0.7463
Precision: 0.7862
Recall: 0.6766
F1: 0.7273
Roc Auc: 0.7463

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: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
0.4042	1.0	857	0.5958	0.7305	0.7805	0.6413	0.7041	0.7305
0.3268	2.0	1714	0.5455	0.7426	0.8321	0.6078	0.7025	0.7426
0.2641	3.0	2571	0.7019	0.7528	0.7742	0.7138	0.7427	0.7528
0.1992	4.0	3428	0.7871	0.7463	0.7862	0.6766	0.7273	0.7463

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2