CoolFace
Modelpublic

TonyStarkD99/PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Epoch_1-FT-Unsloth_Mistral7B

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes13downloads
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. -->

PerspectrumInstruct-Baseline-R32-Alpha64Batch4-Epoch1-FT-UnslothMistral7B

This model is a fine-tuned version of unsloth/mistral-7b-instruct-v0.2-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.3841

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: 0.0002
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 3407
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 16
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 5
  • —num_epochs: 1

Training results

Training LossEpochStepValidation Loss
1.3560.1078301.0690
1.02150.2156600.9446
0.90240.3235900.8369
0.89710.43131200.7261
0.78580.53911500.6317
0.76080.64691800.5461
0.67720.75472100.4775
0.63750.86252400.4176
0.61580.97042700.3841

Framework versions

  • —PEFT 0.12.0
  • —Transformers 4.44.0
  • —Pytorch 2.3.0+cu118
  • —Datasets 2.20.0
  • —Tokenizers 0.19.1