Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSEC-f1-10

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: 4.3800
• F1: 0.4286

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	2.7192	0.5294
No log	2.0	68	4.2851	0.3871
No log	3.0	102	3.9929	0.4138
No log	4.0	136	4.1544	0.5455
No log	5.0	170	3.4351	0.3333
No log	6.0	204	4.3974	0.4667
No log	7.0	238	3.8372	0.2609
No log	8.0	272	4.5766	0.4667
No log	9.0	306	4.1520	0.4
No log	10.0	340	4.3800	0.4286

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3