CoolFace
Modelpublic

AdnanRiaz107/CodePhi-3-mini-128k-instruct-APPS

sourceHugging Facemitupdated 2y agoView on Hugging Face
1likes5downloads
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. -->

CodePhi-3-mini-128k-instruct-APPS

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.6750

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-06
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —gradientaccumulationsteps: 16
  • —totaltrainbatch_size: 16
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 100
  • —training_steps: 1000

Training results

Training LossEpochStepValidation Loss
0.6760.11000.7508
0.61710.22000.7113
0.70580.33000.6950
0.62920.44000.6864
0.60690.55000.6804
0.63690.66000.6768
0.60880.77000.6755
0.55980.88000.6752
0.59870.99000.6750
0.5931.010000.6750

Framework versions

  • —PEFT 0.11.0
  • —Transformers 4.40.2
  • —Pytorch 2.3.0+cu121
  • —Datasets 2.19.1
  • —Tokenizers 0.19.1