all-distilroberta-v1-finetuned-DIT-10_epochs

veddm/all-distilroberta-v1-finetuned-DIT-10_epochs

all-distilroberta-v1-finetuned-DIT-10_epochs is a fill-mask model from veddm. Use it when you need the model to fill a missing word. 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

1% of all-time downloads

All-time downloads

969

Public

Repo size

3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin329 MB · 99%

At a glance

Task: Fill-Mask
Library: transformers
License: apache-2.0
Model type: roberta
Access: Public
Created: Apr 13, 2022
Updated: Apr 13, 2022
SHA: b00eaa8e

Try a prompt

Model card

From the Hugging Face model README

all-distilroberta-v1-finetuned-DIT-10_epochs

This model is a fine-tuned version of sentence-transformers/all-distilroberta-v1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0044

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	358	0.0196
0.3013	2.0	716	0.0092
0.0073	3.0	1074	0.0065
0.0073	4.0	1432	0.0054
0.0021	5.0	1790	0.0051
0.0007	6.0	2148	0.0047
0.0004	7.0	2506	0.0047
0.0004	8.0	2864	0.0046
0.0004	9.0	3222	0.0044
0.0003	10.0	3580	0.0044

Framework versions

Transformers 4.17.0
Pytorch 1.10.2+cpu
Datasets 2.0.0
Tokenizers 0.11.6

Task: Fill-Mask
Library: transformers
Type: roberta
License: apache-2.0
Created: Apr 13, 2022
Updated: Apr 13, 2022