Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSE50-f1-7

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: 1.0155
• F1: 0.6923

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	0.5249	0.7097
No log	2.0	68	0.4985	0.6897
No log	3.0	102	0.4999	0.6667
No log	4.0	136	0.5604	0.64
No log	5.0	170	0.9042	0.6667
No log	6.0	204	1.1122	0.6087
No log	7.0	238	0.8853	0.5833
No log	8.0	272	1.0365	0.6087
No log	9.0	306	1.1672	0.6000
No log	10.0	340	1.0155	0.6923

Framework versions

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