hw2942/Longformer-110M-SSE50

Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSE50-3

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: 0.5713
• Accuracy: 0.7879

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	Accuracy
No log	1.0	34	0.7372	0.3939
No log	2.0	68	0.6541	0.6061
No log	3.0	102	0.5675	0.8182
No log	4.0	136	0.7171	0.4242
No log	5.0	170	0.5655	0.7879
No log	6.0	204	0.8401	0.5152
No log	7.0	238	1.1332	0.6364
No log	8.0	272	0.5260	0.7879
No log	9.0	306	0.7753	0.6970
No log	10.0	340	0.5713	0.7879

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.0