Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSEC-f1-8

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: 3.2742
• F1: 0.3077

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	1.8915	0.4167
No log	2.0	68	2.5660	0.4167
No log	3.0	102	2.8068	0.4516
No log	4.0	136	2.4483	0.4348
No log	5.0	170	2.7211	0.2353
No log	6.0	204	3.2545	0.3333
No log	7.0	238	2.9097	0.3636
No log	8.0	272	3.6446	0.4138
No log	9.0	306	3.0882	0.3810
No log	10.0	340	3.2742	0.3077

Framework versions

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