distilbert-base-uncased

xshubhamx/distilbert-base-uncased

distilbert-base-uncased is a text classification model from xshubhamx. Use it when you need a label for a piece of text. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

8% of all-time downloads

All-time downloads

216

Public

Parameters

67M

15 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt7.5 GB · 65%

At a glance

Task: Text Classification
Library: transformers
Model type: distilbert
Access: Public
Created: Apr 11, 2024
Updated: Apr 13, 2024
SHA: 504ac2aa

Try a prompt

Model card

From the Hugging Face model README

distilbert-base-uncased

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.7370
Accuracy: 0.8071
Precision: 0.8073
Recall: 0.8071
Precision Macro: 0.7532
Recall Macro: 0.7485
Macro Fpr: 0.0174
Weighted Fpr: 0.0168
Weighted Specificity: 0.9739
Macro Specificity: 0.9854
Weighted Sensitivity: 0.8071
Macro Sensitivity: 0.7485
F1 Micro: 0.8071
F1 Macro: 0.7471
F1 Weighted: 0.8062

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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	Precision Macro	Recall Macro	Macro Fpr	Weighted Fpr	Weighted Specificity	Macro Specificity	Weighted Sensitivity	Macro Sensitivity	F1 Micro	F1 Macro	F1 Weighted
1.2542	1.0	643	0.7791	0.7692	0.7497	0.7692	0.5867	0.5990	0.0220	0.0210	0.9667	0.9824	0.7692	0.5990	0.7692	0.5787	0.7526
0.694	2.0	1286	0.7609	0.7823	0.8036	0.7823	0.7590	0.7111	0.0198	0.0195	0.9740	0.9838	0.7823	0.7111	0.7823	0.7012	0.7834
0.5369	3.0	1929	0.8125	0.7971	0.7885	0.7971	0.7027	0.7031	0.0186	0.0179	0.9723	0.9846	0.7971	0.7031	0.7971	0.6990	0.7891
0.2844	4.0	2572	1.0480	0.7823	0.7986	0.7823	0.7151	0.7178	0.0199	0.0195	0.9733	0.9837	0.7823	0.7178	0.7823	0.7080	0.7846
0.1931	5.0	3215	1.0895	0.7971	0.8023	0.7971	0.7557	0.7253	0.0183	0.0179	0.9740	0.9847	0.7971	0.7253	0.7971	0.7329	0.7966
0.1154	6.0	3858	1.4085	0.7792	0.7905	0.7792	0.7382	0.7224	0.0202	0.0198	0.9727	0.9835	0.7792	0.7224	0.7792	0.7231	0.7805
0.0634	7.0	4501	1.3117	0.8102	0.8116	0.8102	0.7444	0.7383	0.0170	0.0165	0.9755	0.9857	0.8102	0.7383	0.8102	0.7391	0.8096
0.0338	8.0	5144	1.4611	0.7955	0.8068	0.7955	0.7378	0.7481	0.0184	0.0180	0.9767	0.9848	0.7955	0.7481	0.7955	0.7373	0.7993
0.0432	9.0	5787	1.5679	0.7971	0.8013	0.7971	0.7543	0.7434	0.0186	0.0179	0.9733	0.9847	0.7971	0.7434	0.7971	0.7423	0.7956
0.0194	10.0	6430	1.6639	0.8033	0.8045	0.8033	0.7636	0.7482	0.0179	0.0172	0.9727	0.9851	0.8033	0.7482	0.8033	0.7516	0.8014
0.014	11.0	7073	1.6361	0.8110	0.8106	0.8110	0.7620	0.7667	0.0170	0.0164	0.9746	0.9857	0.8110	0.7667	0.8110	0.7593	0.8098
0.0079	12.0	7716	1.7016	0.8141	0.8123	0.8141	0.7804	0.7482	0.0168	0.0160	0.9725	0.9858	0.8141	0.7482	0.8141	0.7593	0.8117
0.0057	13.0	8359	1.7229	0.8110	0.8110	0.8110	0.7785	0.7477	0.0170	0.0164	0.9737	0.9856	0.8110	0.7477	0.8110	0.7537	0.8092
0.0037	14.0	9002	1.7630	0.8048	0.8060	0.8048	0.7571	0.7510	0.0178	0.0170	0.9729	0.9852	0.8048	0.7510	0.8048	0.7499	0.8038
0.0011	15.0	9645	1.7370	0.8071	0.8073	0.8071	0.7532	0.7485	0.0174	0.0168	0.9739	0.9854	0.8071	0.7485	0.8071	0.7471	0.8062

Framework versions

Transformers 4.38.2
Pytorch 2.1.2
Datasets 2.1.0
Tokenizers 0.15.2

Task: Text Classification
Library: transformers
Type: distilbert
Created: Apr 11, 2024
Updated: Apr 13, 2024