chinese-pert-base-wallstreetcn-morning-news-market-overview-SSEC-f1-v9

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

• Loss: 2.8284
• F1: 0.4

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	2.4013	0.5
No log	2.0	68	2.7811	0.4444
No log	3.0	102	2.3900	0.5333
No log	4.0	136	2.5631	0.3810
No log	5.0	170	2.1066	0.5926
No log	6.0	204	2.6985	0.3636
No log	7.0	238	2.8111	0.4615
No log	8.0	272	2.9921	0.4
No log	9.0	306	2.8214	0.4
No log	10.0	340	2.8284	0.4

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3