mdeberta-v3-base-finetuned-climate-stance-supportive-classification – AI Model by mljn | AlphaNeural AI

You can deploy this model and start earning money today!

mljn/
mdeberta-v3-base-finetuned-climate-stance-supportive-classification

like

0

text-classification

generated_from_trainer

microsoft/mdeberta-v3-base

autotrain_compatible

endpoints_compatible

Views

No views yet

mdeberta-v3-base-finetuned-climate-stance-supportive-classification

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

Loss: 0.7262
Accuracy: 0.8543
F1 Macro: 0.8380
Accuracy Balanced: 0.8333
F1 Micro: 0.8543
Precision Macro: 0.8438
Recall Macro: 0.8333
Precision Micro: 0.8543
Recall Micro: 0.8543

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: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 0.06
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Accuracy Balanced	F1 Micro	Precision Macro	Recall Macro	Precision Micro	Recall Micro
0.4964	0.9980	500	0.5222	0.8044	0.7516	0.7321	0.8044	0.8489	0.7321	0.8044	0.8044
0.3209	1.9960	1000	0.4717	0.8673	0.8510	0.8433	0.8673	0.8616	0.8433	0.8673	0.8673
0.2092	2.9940	1500	0.6248	0.8673	0.8535	0.8510	0.8673	0.8563	0.8510	0.8673	0.8673
0.1279	3.9920	2000	0.7262	0.8543	0.8380	0.8333	0.8543	0.8438	0.8333	0.8543	0.8543

Framework versions

Transformers 4.52.2
Pytorch 2.6.0+cu124
Datasets 2.14.4
Tokenizers 0.21.1