CoolFace
Modelpublic

GabSo/santacoder-finetuned-robot4

sourceHugging Facebigcode-openrail-mupdated 3y agoView on Hugging Face
0likes26downloads
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. -->

santacoder-finetuned-robot4

This model is a fine-tuned version of bigcode/santacoder on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.5116

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: 5e-05
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 4
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 1
  • —training_steps: 20

Training results

Training LossEpochStepValidation Loss
No log0.0511.5720
No log0.122.6819
No log0.1531.3777
No log0.241.7661
No log0.2551.0597
No log0.361.1801
No log0.3570.8989
No log0.480.9572
No log0.4590.7408
1.480.5100.7517
1.480.55110.6493
1.480.6120.6206
1.480.65130.5872
1.480.7140.5644
1.480.75150.5415
1.480.8160.5298
1.480.85170.5186
1.480.9180.5128
1.480.95190.5120
0.53071.0200.5116

Framework versions

  • —Transformers 4.35.0
  • —Pytorch 2.1.0+cu118
  • —Datasets 2.14.6
  • —Tokenizers 0.14.1