CoolFace
Modelpublic

fresst/mbart-large-50-b16-e16-lr2e-05-126k-jupyter

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes3downloads
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. -->

mbart-large-50-b16-e16-lr2e-05-126k-jupyter

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.1198
  • —Bleu: 84.233
  • —Gen Len Ratio: 1.0012

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: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 16

Training results

Training LossEpochStepBleuGen Len RatioValidation Loss
0.15321.77691400084.2331.00120.1198
0.04853.55382800072.10080.88480.1352
0.01965.33064200064.29910.80810.1477
0.00837.10755600056.85080.74440.1608
0.00318.88447000063.66760.79820.1675
0.001710.66138400072.88350.88610.1744
0.000812.43819800072.24470.88510.1819
0.000514.215011200069.41060.85490.1856
0.000315.991912600067.00960.83010.1877

Framework versions

  • —Transformers 4.49.0
  • —Pytorch 2.6.0+cu124
  • —Datasets 3.4.1
  • —Tokenizers 0.21.1