GISchat-weibo-100k-fine-tuned-bert

track-AJ/GISchat-weibo-100k-fine-tuned-bert

GISchat-weibo-100k-fine-tuned-bert is a machine learning model from track-AJ. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

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

Downloads · 30 days

22% of all-time downloads

All-time downloads

Public

Parameters

102M

7.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors409 MB · 100%

At a glance

Model type: bert
Access: Public
Created: Aug 23, 2024
Updated: Aug 23, 2024
SHA: 08033781

Base models

Model card

From the Hugging Face model README

GISchat-weibo-100k-fine-tuned-bert

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

Loss: 0.0512
Accuracy: 0.9867

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: 1e-05
train_batch_size: 8
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.08	100	0.6513	0.6347
0.6142	0.16	200	0.2181	0.962
0.6142	0.24	300	0.0776	0.9847
0.1151	0.32	400	0.0886	0.9827
0.1151	0.4	500	0.0646	0.985
0.0978	0.48	600	0.0605	0.9843
0.0978	0.56	700	0.0545	0.9863
0.089	0.64	800	0.0635	0.9857
0.089	0.72	900	0.0532	0.9863
0.0535	0.8	1000	0.0634	0.9863
0.0535	0.88	1100	0.0570	0.9867
0.0557	0.96	1200	0.0512	0.9867

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Type: bert
Created: Aug 23, 2024
Updated: Aug 23, 2024