bert-base-chinese-wallstreetcn-morning-news-market-overview-SSE50-f1-v10

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: 4.0984
• F1: 0.5000

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	34	3.8089	0.4444
No log	2.0	68	4.1142	0.4545
No log	3.0	102	3.6047	0.4762
No log	4.0	136	3.4138	0.5833
No log	5.0	170	3.5034	0.5833
No log	6.0	204	3.4997	0.6087
No log	7.0	238	4.0061	0.5000
No log	8.0	272	4.0838	0.5000
No log	9.0	306	4.0919	0.5000
No log	10.0	340	4.0984	0.5000

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1