You can deploy this model and start earning money today!

hw2942/
Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-close-000001.SH-v1

Name: Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-close-000001.SH-v1
Availability: InStock

generated_from_trainer

apache-2.0

autotrain_compatible

endpoints_compatible

Views

No views yet

Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-close-000001.SH-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: 0.6933
Accuracy: 0.5

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	32	0.7041	0.5
No log	2.0	64	0.7197	0.5
No log	3.0	96	0.6980	0.5
No log	4.0	128	0.6933	0.5
No log	5.0	160	0.6945	0.5
No log	6.0	192	0.7116	0.5
No log	7.0	224	0.6933	0.5
No log	8.0	256	0.6958	0.5
No log	9.0	288	0.6944	0.5
No log	10.0	320	0.6933	0.5

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

hw2942/Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-close-000001.SH-v1

Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-close-000001.SH-v1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hw2942/
Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-close-000001.SH-v1