CoolFace
Modelpublic

genki10/Version_Test_ASAP_FineTuningBERT_AugV14_k5_task1_organization_k5_k5_fold0

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes2downloads
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. -->

VersionTestASAPFineTuningBERTAugV14k5task1organizationk5k5fold0

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.5425
  • —Qwk: 0.6029
  • —Mse: 0.5425
  • —Rmse: 0.7366

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: 64
  • —evalbatchsize: 64
  • —seed: 42
  • —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 100

Training results

Training LossEpochStepValidation LossQwkMseRmse
No log1.047.59820.07.59822.7565
No log2.085.89580.02255.89582.4281
No log3.0124.18700.00394.18702.0462
No log4.0162.64380.02.64381.6260
No log5.0201.53150.03161.53151.2375
No log6.0240.97270.01060.97280.9863
No log7.0280.76120.13210.76120.8725
No log8.0320.74210.11840.74210.8615
No log9.0360.66930.22070.66930.8181
No log10.0400.46540.46620.46540.6822
No log11.0440.48200.51800.48200.6942
No log12.0480.46000.54480.46000.6782
No log13.0520.48280.55560.48280.6948
No log14.0560.53190.58320.53190.7293
No log15.0600.47120.62410.47120.6864
No log16.0640.49280.63480.49280.7020
No log17.0680.48880.57420.48880.6991
No log18.0720.48550.61060.48550.6968
No log19.0760.48710.62510.48710.6979
No log20.0800.51170.61210.51170.7153
No log21.0840.52050.60960.52050.7214
No log22.0880.70070.55660.70070.8371
No log23.0920.53560.54500.53560.7318
No log24.0960.63530.54850.63530.7971
No log25.01000.50410.58330.50410.7100
No log26.01040.51990.62290.51990.7211
No log27.01080.54200.61050.54200.7362
No log28.01120.51620.61500.51620.7185
No log29.01160.52590.59470.52590.7252
No log30.01200.54340.60760.54340.7372
No log31.01240.65010.56120.65010.8063
No log32.01280.53750.56840.53750.7332
No log33.01320.50590.60320.50590.7112
No log34.01360.56620.57390.56620.7525
No log35.01400.52290.60390.52290.7231
No log36.01440.54250.60290.54250.7366

Framework versions

  • —Transformers 4.47.0
  • —Pytorch 2.5.1+cu121
  • —Datasets 3.2.0
  • —Tokenizers 0.21.0