Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSE50-f1-v11

This model is a fine-tuned version of IDEA-CCNL/Erlangshen-Longformer-110M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.3920
• F1: 0.7097

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	2.6021	0.625
No log	2.0	68	1.9084	0.7500
No log	3.0	102	2.1467	0.5833
No log	4.0	136	3.2366	0.6286
No log	5.0	170	3.7965	0.5789
No log	6.0	204	2.5093	0.6667
No log	7.0	238	3.5738	0.5946
No log	8.0	272	2.6489	0.6667
No log	9.0	306	2.4766	0.6207
No log	10.0	340	2.3920	0.7097

Framework versions

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