distilbert-base-uncased-final2-mnli

charlemagne/distilbert-base-uncased-final2-mnli

distilbert-base-uncased-final2-mnli is a text classification model from charlemagne. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

434

Public

Repo size

6.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin268 MB · 100%

At a glance

Task: Text Classification
Library: transformers
License: apache-2.0
Model type: distilbert
Access: Public
Created: Jan 11, 2023
Updated: Jan 11, 2023
SHA: aac4dc36

Try a prompt

Model card

From the Hugging Face model README

distilbert-base-uncased-final2-mnli

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: 0.1172
Accuracy: 0.9714

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	75	0.5516	0.8627
No log	2.0	150	0.2118	0.9553
No log	3.0	225	0.1482	0.9671
No log	4.0	300	0.1172	0.9714
No log	5.0	375	0.1240	0.9705

Framework versions

Transformers 4.17.0
Pytorch 1.8.0+cu111
Datasets 2.1.0
Tokenizers 0.11.6

Task: Text Classification
Library: transformers
Type: distilbert
License: apache-2.0
Created: Jan 11, 2023
Updated: Jan 11, 2023