CoolFace
Modelpublic

am-infoweb/QA_REFINED_QUESTIONS_WITH_RANDOM_DATA_24K_16_08

sourceHugging Facecc-by-4.0updated 3y agoView on Hugging Face
0likes16downloads
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. -->

QAREFINEDQUESTIONSWITHRANDOMDATA24K1508

This model is a fine-tuned version of deepset/roberta-base-squad2 on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.5700

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: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10

Training results

Training LossEpochStepValidation Loss
0.41141.092810.5647
0.43442.0185620.5296
0.35423.0278430.4666
0.35834.0371240.4045
0.3195.0464050.4944
0.27016.0556860.5352
0.3137.0649670.4846
0.20258.0742480.5701
0.24249.0835290.5456
0.194410.0928100.5700

Framework versions

  • —Transformers 4.32.0.dev0
  • —Pytorch 2.0.1+cu117
  • —Datasets 2.14.4
  • —Tokenizers 0.13.3