This model is a fine-tuned version of Langboat/mengzi-bert-base-fin on the dataset of Wallstreetcn Morning News Market Overview with overnight index (000001.SH) movement labels. It achieves the following results on the evaluation set:

Loss: 0.7016905546188354
Accuracy: 0.7586206896551724

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	Accuracy
No log	1.0	38	0.6799	0.5517
No log	2.0	76	0.6132	0.7241
No log	3.0	114	0.6453	0.6207
No log	4.0	152	0.7017	0.7586
No log	5.0	190	0.9160	0.7241
No log	6.0	228	1.0803	0.7586
No log	7.0	266	1.1766	0.7241
No log	8.0	304	1.1976	0.7586
No log	9.0	342	1.2610	0.7241
No log	10.0	380	1.2948	0.7241

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.14.2
Tokenizers 0.13.3

hw2942/mengzi-bert-base-fin-finetuning-wallstreetcn-morning-news-market-overview-open-000001SH-v1

mengzi-bert-base-fin-finetuning-wallstreetcn-morning-news-market-overview-open-000001SH-v1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hw2942/
mengzi-bert-base-fin-finetuning-wallstreetcn-morning-news-market-overview-open-000001SH-v1