Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSEC-f1-v2

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: 1.7671
• F1: 0.4167

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	0.7509	0.5806
No log	2.0	68	0.7816	0.5882
No log	3.0	102	0.8974	0.3
No log	4.0	136	0.8480	0.5333
No log	5.0	170	0.9435	0.4615
No log	6.0	204	1.4527	0.1905
No log	7.0	238	1.4867	0.2105
No log	8.0	272	1.6098	0.3846
No log	9.0	306	1.7910	0.2857
No log	10.0	340	1.7671	0.4167

Framework versions

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