mdebertatask2 – AI Model by MohammadKarami | AlphaNeural AI

You can deploy this model and start earning money today!

MohammadKarami/
mdebertatask2

like

0

text-classification

generated_from_trainer

microsoft/mdeberta-v3-base

autotrain_compatible

endpoints_compatible

Views

No views yet

Model

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: 1.5484
F1: 0.7866

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 8
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.8731	1.0	1469	0.9043	0.6580
0.5627	2.0	2938	0.7961	0.7249
0.3709	3.0	4407	0.7498	0.7616
0.2306	4.0	5876	1.0133	0.7449
0.1605	5.0	7345	0.9206	0.7930
0.0903	6.0	8814	1.1841	0.7797
0.0506	7.0	10283	1.4182	0.7864
0.027	8.0	11752	1.5484	0.7866

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1