bert_ds_sst3_5e-5_5_42

yongxin2020/bert_ds_sst3_5e-5_5_42

bert_ds_sst3_5e-5_5_42 is a token classification model from yongxin2020. Use it when you need labels on individual words, such as names. It is set up for transformers.

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

Downloads · 30 days

50% of all-time downloads

All-time downloads

Public

Repo size

871 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin436 MB · 100%

At a glance

Task: Token Classification
Library: transformers
Model type: bert
Access: Public
Created: Mar 21, 2024
Updated: Nov 4, 2024
SHA: 1a151211

Try a prompt

Model card

From the Hugging Face model README

bert_ds_sst3_5e-5_5_42

This model is a fine-tuned version of /data/yongxin/DiaSumDA/token_classification/ACIInew/annotate_dialogsum_2e-5_5_42/ on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0689
Precision: 0.8816
Recall: 0.8785
F1: 0.8800
Accuracy: 0.9792

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: 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: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1293	1.0	534	0.0749	0.8752	0.8190	0.8462	0.9739
0.049	2.0	1068	0.0689	0.8816	0.8785	0.8800	0.9792
0.0227	3.0	1602	0.0792	0.8896	0.8880	0.8888	0.9805
0.0106	4.0	2136	0.1008	0.8878	0.8935	0.8906	0.9809
0.005	5.0	2670	0.1055	0.8951	0.8923	0.8937	0.9814

Framework versions

Transformers 4.27.0.dev0
Pytorch 1.9.0+cu102
Datasets 2.8.0
Tokenizers 0.13.2

Task: Token Classification
Library: transformers
Type: bert
Created: Mar 21, 2024
Updated: Nov 4, 2024