CoolFace
Modelpublic

hw2942/Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-market-overview-open-000001SH-v1

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes21downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-market-overview-open-000001SH-v1

This model is a fine-tuned version of IDEA-CCNL/Erlangshen-Longformer-110M on the dataset of Wallstreetcn Morning News Market Overview with overnight index (000001.SH) movement labels. It achieves the following results on the best evaluation set:

  • —Loss: 0.7186
  • —Accuracy: 0.6552

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
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10

Training results

Training LossEpochStepValidation LossAccuracy
No log1.0380.67790.5862
No log2.0760.67710.5862
No log3.01140.67520.5862
No log4.01520.71860.6552
No log5.01900.72960.5862
No log6.02280.79480.5862
No log7.02660.96980.6207
No log8.03041.02750.5862
No log9.03421.04340.6207
No log10.03801.06030.5862

Framework versions

  • —Transformers 4.31.0
  • —Pytorch 2.0.1+cu118
  • —Datasets 2.14.2
  • —Tokenizers 0.13.3