mengzi-bert-base-fin-wallstreetcn-morning-news-market-overview-open-SSEC-f1-v1

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

• Loss: 1.0486
• F1: 0.4706

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	F1
No log	1.0	38	0.6755	0.0
No log	2.0	76	0.6067	0.2857
No log	3.0	114	0.6956	0.4211
No log	4.0	152	0.5666	0.5714
No log	5.0	190	0.6870	0.4444
No log	6.0	228	0.8044	0.4706
No log	7.0	266	0.9209	0.4706
No log	8.0	304	0.9736	0.4706
No log	9.0	342	1.0042	0.4706
No log	10.0	380	1.0486	0.4706

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.3
• Tokenizers 0.13.3