Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSE50-f1-9

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: 1.4656
• F1: 0.4800

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	1.2272	0.375
No log	2.0	68	0.8381	0.4444
No log	3.0	102	0.7255	0.3333
No log	4.0	136	0.9033	0.5600
No log	5.0	170	1.5124	0.4211
No log	6.0	204	1.3618	0.5455
No log	7.0	238	1.3947	0.5385
No log	8.0	272	1.4106	0.5385
No log	9.0	306	1.4768	0.5385
No log	10.0	340	1.4656	0.4800

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1