CoolFace
Modelpublic

silmi224/led-risalah_data_v11

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes11downloads
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. -->

led-risalahdatav11

This model is a fine-tuned version of silmi224/finetune-led-35000 on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.6843
  • —Rouge1 Precision: 0.7035
  • —Rouge1 Recall: 0.1205
  • —Rouge1 Fmeasure: 0.2038

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
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 4
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 8
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossRouge1 PrecisionRouge1 RecallRouge1 Fmeasure
2.60710.9714171.89380.60210.10740.1803
1.7452.0351.76610.70950.11740.1994
1.57172.9714521.72510.67040.11760.1968
1.49214.0701.67720.70140.11750.1986
1.39324.9714871.67450.70080.11870.2011
1.30026.01051.68690.69130.11960.2012
1.27846.97141221.68570.71140.12460.2097
1.17797.77141361.68430.70350.12050.2038

Framework versions

  • —Transformers 4.41.2
  • —Pytorch 2.1.2
  • —Datasets 2.19.2
  • —Tokenizers 0.19.1