CoolFace
Modelpublic

philschmid/MiniLMv2-L12-H384-distilled-finetuned-clinc

sourceHugging Faceupdated 4y agoView on Hugging Face
0likes64downloads
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. -->

MiniLMv2-L12-H384-distilled-finetuned-clinc

This model is a fine-tuned version of nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large on the clinc_oos dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.3058
  • —Accuracy: 0.9529

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: 64
  • —evalbatchsize: 64
  • —seed: 33
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
1.99081.02391.68160.3910
1.52122.04781.23650.7697
1.1293.07170.92090.8706
0.84624.09560.69780.9152
0.64975.011950.54990.9342
0.51246.014340.44470.9445
0.41967.016730.37970.9455
0.35878.019120.33580.95
0.32289.021510.31330.9513
0.305210.023900.30580.9529

Framework versions

  • —Transformers 4.17.0
  • —Pytorch 1.10.2+cu113
  • —Datasets 1.18.4
  • —Tokenizers 0.11.6