CoolFace
Modelpublic

hosseinmhmdkhani/google-mt5-base-lora-finetuned-persian-news

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes13downloads
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. -->

google-mt5-base-lora-finetuned-persian-news

This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.9099
  • —Rouge1 Precision: 59.4386
  • —Rouge1 Recall: 60.3359
  • —Rouge1 F1: 58.6755
  • —Rouge2 Precision: 42.2757
  • —Rouge2 Recall: 43.1573
  • —Rouge2 F1: 41.7994
  • —Rougel Precision: 51.4347
  • —Rougel Recall: 52.3226
  • —Rougel F1: 50.8172

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: 0.0005
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —gradientaccumulationsteps: 8
  • —totaltrainbatch_size: 32
  • —optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 0.1
  • —num_epochs: 4

Training results

Training LossEpochStepValidation LossRouge1 F1Rouge1 PrecisionRouge1 RecallRouge2 F1Rouge2 PrecisionRouge2 RecallRougel F1Rougel PrecisionRougel Recall
11.20261.03020.967654.50561.750951.824238.984944.321737.061947.226753.5644.907
9.75892.06040.955558.062758.272760.52541.37941.461243.312850.217750.36852.4143
9.32703.09060.914458.5861.099358.660741.504643.616641.671250.586652.894950.7062
9.27824.012080.909959.438660.335958.675542.275743.157341.799451.434752.322650.8172

Framework versions

  • —PEFT 0.20.0
  • —Transformers 5.14.1
  • —Pytorch 2.11.0+cu128
  • —Datasets 4.0.0
  • —Tokenizers 0.22.2