CoolFace
Modelpublic

hw2942/Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-open-SSEC-f1-v1

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes10downloads
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-wallstreetcn-morning-news-market-overview-open-SSEC-f1-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: 1.2093
  • —F1: 0.3636

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 LossF1
No log1.0380.68730.0
No log2.0760.69330.0
No log3.01140.74010.5854
No log4.01520.69130.0
No log5.01901.01420.4706
No log6.02280.89250.2353
No log7.02660.92580.1333
No log8.03041.02900.3636
No log9.03421.10180.4
No log10.03801.20930.3636

Framework versions

  • —Transformers 4.31.0
  • —Pytorch 2.0.1+cu118
  • —Datasets 2.14.3
  • —Tokenizers 0.13.3