CoolFace
Modelpublic

zeon8985army/IndonesiaLukasLargeV3-2

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes4downloads
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. -->

zeon8985army/IndonesiaLukasLargeV3-2

This model is a fine-tuned version of zeon8985army/IndonesiaLukasLargeV3-2 on the Mozilla & GoogleFleur dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.1613

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: 6e-05
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 12
  • —training_steps: 552
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.23960.0785230.2246
0.21990.1570460.2234
0.19630.2355690.2176
0.2060.3140920.2117
0.17550.39251150.1899
0.17130.47101380.2041
0.21260.54951610.1806
0.17780.62801840.1787
0.16460.70652070.1767
0.16740.78502300.1746
0.15450.86352530.1725
0.17420.94202760.1708
0.14341.02052990.1687
0.151.09903220.1679
0.13741.17753450.1671
0.1361.25603680.1650
0.14071.33453910.1642
0.1531.41304140.1629
0.15051.49154370.1632
0.15431.57004600.1624
0.13941.64854830.1616
0.12551.72705060.1617
0.13421.80555290.1613
0.14591.88405520.1613

Framework versions

  • —PEFT 0.9.0
  • —Transformers 4.44.2
  • —Pytorch 2.4.1+cu121
  • —Datasets 3.0.1
  • —Tokenizers 0.19.1