CoolFace
Modelpublic

titi7242229/roberta-base-bne-finetuned_personality_multi_4

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes24downloads
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. -->

roberta-base-bne-finetunedpersonalitymulti_4

This model is a fine-tuned version of BSC-TeMU/roberta-base-bne on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 4.1709
  • —Accuracy: 0.3470

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: 0.0001
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 20

Training results

Training LossEpochStepValidation LossAccuracy
2.17591.01252.18730.2548
1.86512.02502.22850.2680
1.86193.03752.17320.2951
1.72244.05002.06880.3925
1.64325.06252.10940.3735
1.35996.07502.17320.3631
1.06237.08752.47850.3579
1.05048.010002.45980.3844
0.76629.011252.80810.3573
0.916710.012502.93850.3452
0.639111.013752.99330.3320
0.389312.015003.10370.3579
0.67313.016253.43690.3631
0.349814.017503.63960.3383
0.389115.018753.83320.3556
0.081816.020003.94510.3401
0.143817.021253.92710.3458
0.063418.022504.15640.3481
0.012119.023754.14050.3499
0.007120.025004.17090.3470

Framework versions

  • —Transformers 4.19.4
  • —Pytorch 1.11.0+cu113
  • —Datasets 2.2.2
  • —Tokenizers 0.12.1