HW4_model – AI Model by eliyashev | AlphaNeural AI

You can deploy this model and start earning money today!

eliyashev/
HW4_model

like

0

text-classification

generated_from_trainer

distilbert/distilbert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

HW4_model

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

Loss: 0.0261
Accuracy: 0.9924
F1: 0.6776
Precision: 0.8150
Recall: 0.5798

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: 64
eval_batch_size: 64
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
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.1407	1.0	513	0.0376	0.9894	0.4377	0.8320	0.2970
0.0336	2.0	1026	0.0292	0.9921	0.6597	0.8128	0.5551
0.0285	3.0	1539	0.0273	0.9922	0.6700	0.8134	0.5696
0.0267	4.0	2052	0.0264	0.9923	0.6741	0.8144	0.5750
0.0256	5.0	2565	0.0261	0.9924	0.6776	0.8150	0.5798

Framework versions

Transformers 4.50.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1