CoolFace
Modelpublic

Mikask/indobart-indonlg-jv-id

sourceHugging Facemitupdated 3y agoView on Hugging Face
0likes7downloads
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. -->

indobart-combined-jv-id

This model is a fine-tuned version of indobenchmark/indobart-v2 on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.6285
  • —Bleu: 16.9732
  • —Gen Len: 19.4429

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: 64
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10

Training results

Training LossEpochStepValidation LossBleuGen Len
No log1.0940.808411.186519.5232
No log2.01880.725913.122319.478
No log3.02820.690514.685919.4366
No log4.03760.668215.257819.4216
No log5.04700.653615.945919.4366
0.87346.05640.643916.318919.4115
0.87347.06580.636716.735319.4228
0.87348.07520.632716.957519.4529
0.87349.08460.630017.09319.4442
0.873410.09400.628516.973219.4429

Framework versions

  • —Transformers 4.33.1
  • —Pytorch 2.0.1+cu118
  • —Datasets 2.14.5
  • —Tokenizers 0.13.3