CoolFace
Modelpublic

silmi224/led-risalah-v5

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes8downloads
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-risalah-v5

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: 1.5242
  • —Rouge1 Precision: 0.676
  • —Rouge1 Recall: 0.1721
  • —Rouge1 Fmeasure: 0.2728

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

Training results

Training LossEpochStepValidation LossRouge1 PrecisionRouge1 RecallRouge1 Fmeasure
No log1.0701.64790.61780.16180.2556
1.85122.01401.57440.65610.1740.2745
1.42963.02101.55950.66170.17040.2702
1.42964.02801.54020.6850.17190.274
1.19765.03501.52420.6760.17210.2728
1.06386.04201.53830.68860.1820.2873
1.06387.04901.56520.66360.17570.2771
0.96578.05601.57970.67880.1720.2733
0.92159.06301.59600.66440.17150.2715
0.84910.07001.59430.65810.16930.2681

Framework versions

  • —Transformers 4.35.2
  • —Pytorch 2.1.1+cu121
  • —Datasets 2.14.5
  • —Tokenizers 0.15.1