N_distilbert_sst5_padding60model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
N_distilbert_sst5_padding60model

like

0

text-classification

generated_from_trainer

distilbert/distilbert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

N_distilbert_sst5_padding60model

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.8121
Accuracy: 0.5077

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.4634	1.0	534	1.2850	0.4163
1.1378	2.0	1068	1.1331	0.4941
0.9377	3.0	1602	1.2002	0.4900
0.7621	4.0	2136	1.2642	0.5113
0.6022	5.0	2670	1.4911	0.4869
0.4592	6.0	3204	1.6732	0.4810
0.3597	7.0	3738	1.8616	0.4869
0.2659	8.0	4272	2.0609	0.4846
0.2268	9.0	4806	2.3938	0.4774
0.1879	10.0	5340	2.4559	0.4846
0.1601	11.0	5874	2.9729	0.4851
0.1232	12.0	6408	3.0635	0.4891
0.1247	13.0	6942	3.3278	0.5009
0.0986	14.0	7476	3.4084	0.4955
0.065	15.0	8010	3.5277	0.4919
0.0544	16.0	8544	3.5801	0.4910
0.0506	17.0	9078	3.7815	0.4910
0.036	18.0	9612	3.8462	0.4941
0.0333	19.0	10146	3.7974	0.5009
0.0343	20.0	10680	3.8121	0.5077

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3