CoolFace
Modelpublic

SurajSphinx/shipping_qa_model_30_04_24

sourceHugging Facecc-by-4.0updated 2y agoView on Hugging Face
0likes6downloads
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. -->

shippingqamodel3004_24

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: 3.8070

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: 1e-05
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 30

Training results

Training LossEpochStepValidation Loss
No log1.0285.7792
No log2.0565.4899
No log3.0845.3744
No log4.01125.2672
No log5.01405.0586
No log6.01684.8332
No log7.01964.7809
No log8.02244.7767
No log9.02524.6233
No log10.02804.5430
No log11.03084.4714
No log12.03364.3689
No log13.03644.3410
No log14.03924.2705
No log15.04204.2760
No log16.04484.1572
No log17.04764.1465
4.574318.05044.0708
4.574319.05324.0196
4.574320.05604.0183
4.574321.05883.9759
4.574322.06163.9140
4.574323.06443.9308
4.574324.06723.8611
4.574325.07003.8159
4.574326.07283.8126
4.574327.07563.8272
4.574328.07843.8185
4.574329.08123.8074
4.574330.08403.8070

Framework versions

  • —Transformers 4.41.0.dev0
  • —Pytorch 2.2.2+cu118
  • —Datasets 2.18.0
  • —Tokenizers 0.19.1