Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-vix-sz50-v1

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: 0.7690
• Accuracy: 0.5577

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: 5e-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	19	0.7136	0.5
No log	2.0	38	0.7423	0.5
No log	3.0	57	0.8728	0.5
No log	4.0	76	0.6878	0.5
No log	5.0	95	0.7361	0.5385
No log	6.0	114	0.7651	0.5577
No log	7.0	133	0.8437	0.6346
No log	8.0	152	0.8604	0.5577
No log	9.0	171	0.7503	0.6154
No log	10.0	190	0.7690	0.5577

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3