CoolFace
Modelpublic

caspro/mt5-base_Nepali_News_Summarization_QLoRA_4bit

sourceHugging Faceapache-2.0updated 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. -->

mt5-baseNepaliNewsSummarizationQLoRA_4bit

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: nan
  • —Rouge-1 R: 0.0
  • —Rouge-1 P: 0.0
  • —Rouge-1 F: 0.0
  • —Rouge-2 R: 0.0
  • —Rouge-2 P: 0.0
  • —Rouge-2 F: 0.0
  • —Rouge-l R: 0.0
  • —Rouge-l P: 0.0
  • —Rouge-l F: 0.0
  • —Gen Len: 0.0

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: 5
  • —evalbatchsize: 5
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 3

Training results

Training LossEpochStepValidation LossRouge-1 RRouge-1 PRouge-1 FRouge-2 RRouge-2 PRouge-2 FRouge-l RRouge-l PRouge-l FGen Len
0.01.010191nan0.00.00.00.00.00.00.00.00.00.0
0.02.020382nan0.00.00.00.00.00.00.00.00.00.0
0.03.030573nan0.00.00.00.00.00.00.00.00.00.0

Framework versions

  • —PEFT 0.12.0
  • —Transformers 4.41.2
  • —Pytorch 2.1.2
  • —Datasets 2.19.2
  • —Tokenizers 0.19.1