gpad-v1-full-taskA – AI Model by ranjankn | AlphaNeural AI

You can deploy this model and start earning money today!

ranjankn/
gpad-v1-full-taskA

like

0

generated_from_trainer

microsoft/codebert-base

endpoints_compatible

Views

No views yet

gpad-v1-full-taskA

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

Loss: 0.0772
Accuracy: 0.9890
F1 Macro: 0.9895
F1 Weighted: 0.9890
Precision Macro: 0.9912
Recall Macro: 0.9878

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: 16
eval_batch_size: 16
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_steps: 500
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted	Precision Macro	Recall Macro
0.1028	1.0	7813	0.1371	0.9817	0.9824	0.9817	0.9848	0.9801
0.0957	2.0	15626	0.0937	0.9862	0.9868	0.9862	0.9835	0.9901
0.0909	3.0	23439	0.0772	0.9890	0.9895	0.9890	0.9912	0.9878

Framework versions

Transformers 4.53.3
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.2