deberta-auto-grading-final – AI Model by nguyennghia0902 | AlphaNeural AI

You can deploy this model and start earning money today!

nguyennghia0902/
deberta-auto-grading-final

like

0

text-classification

generated_from_trainer

microsoft/deberta-v3-base

text-embeddings-inference

endpoints_compatible

Views

No views yet

deberta-auto-grading-final

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4719
Accuracy: 0.8213
F1 Macro: 0.8028
F1 Incorrect: 0.8220
F1 Partial: 0.7115
F1 Correct: 0.8748

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: 64
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
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_steps: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Incorrect	F1 Partial	F1 Correct
1.6870	1.0	354	0.6365	0.7322	0.6947	0.7070	0.5561	0.8209
0.9941	2.0	708	0.4973	0.7624	0.7493	0.7361	0.6870	0.8247
0.7576	3.0	1062	0.5003	0.7827	0.7653	0.7550	0.6924	0.8486
0.6073	4.0	1416	0.5100	0.7900	0.7716	0.7520	0.7089	0.8539
0.5072	5.0	1770	0.5263	0.8038	0.7840	0.7658	0.7203	0.8661

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.8.3
Tokenizers 0.22.2