Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSE50-f1-6

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: 0.5965
• F1: 0.6154

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	0.7538	0.5652
No log	2.0	68	0.6708	0.0
No log	3.0	102	0.6652	0.0
No log	4.0	136	0.6904	0.6190
No log	5.0	170	0.5285	0.7143
No log	6.0	204	0.5537	0.7429
No log	7.0	238	0.6288	0.5263
No log	8.0	272	0.5419	0.6957
No log	9.0	306	0.5619	0.6875
No log	10.0	340	0.5965	0.6154

Framework versions

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