visobert-sentiment-neu-esc – AI Model by bie-nhd | AlphaNeural AI

You can deploy this model and start earning money today!

bie-nhd/
visobert-sentiment-neu-esc

like

0

text-classification

generated_from_trainer

uitnlp/visobert

text-embeddings-inference

endpoints_compatible

Views

No views yet

visobert-sentiment-neu-esc

This model is a fine-tuned version of uitnlp/visobert on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4683
Accuracy: 0.8290
F1 Weighted: 0.8250
F1 Macro: 0.7526
Precision: 0.8283
Recall: 0.8290

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: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Weighted	F1 Macro	Precision	Recall
0.4471	1.0	721	0.4617	0.8209	0.8182	0.7380	0.8176	0.8209
0.3817	2.0	1442	0.4683	0.8290	0.8250	0.7526	0.8283	0.8290
0.2134	3.0	2163	0.5516	0.8278	0.8241	0.7526	0.8231	0.8278
0.1048	4.0	2884	0.8084	0.8230	0.8181	0.7453	0.8168	0.8230
0.0488	5.0	3605	0.8976	0.8188	0.8163	0.7437	0.8156	0.8188

Framework versions

Transformers 4.57.6
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.2