CoolFace
Modelpublic

raondm/jazz_clm-model

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes9downloads
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. -->

jazz_clm-model

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.5660

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: 8
  • —evalbatchsize: 8
  • —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 log1.03650.6431
0.61042.07300.6238
0.58593.010950.6103
0.58594.014600.6046
0.57245.018250.5941
0.55746.021900.5930
0.54787.025550.5841
0.54788.029200.5821
0.53959.032850.5810
0.52710.036500.5755
0.523711.040150.5728
0.523712.043800.5691
0.514713.047450.5733
0.514114.051100.5680
0.514115.054750.5657
0.507616.058400.5719
0.500417.062050.5691
0.498518.065700.5687
0.498519.069350.5679
0.492620.073000.5689
0.491421.076650.5667
0.488522.080300.5631
0.488523.083950.5666
0.486224.087600.5668
0.482525.091250.5643
0.482526.094900.5652
0.482827.098550.5667
0.4828.0102200.5657
0.477529.0105850.5654
0.477530.0109500.5660

Framework versions

  • —Transformers 4.34.0
  • —Pytorch 2.1.0
  • —Datasets 2.14.5
  • —Tokenizers 0.14.1