CoolFace
Modelpublic

chchen/MentaLLaMA-chat-7B-PsyCourse-doc-info-fold9

sourceHugging Facemitupdated 1y agoView on Hugging Face
0likes15downloads
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. -->

MentaLLaMA-chat-7B-PsyCourse-doc-info-fold9

This model is a fine-tuned version of klyang/MentaLLaMA-chat-7B-hf on the course-doc-info-train-fold9 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0834

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: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —gradientaccumulationsteps: 16
  • —totaltrainbatch_size: 16
  • —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_ratio: 0.1
  • —num_epochs: 5.0

Training results

Training LossEpochStepValidation Loss
0.36040.3951100.3692
1.09780.7901200.2423
0.15191.1852300.1737
0.13841.5802400.1437
0.10761.9753500.1253
0.10852.3704600.1120
0.08842.7654700.1006
0.10713.1605800.0919
0.07613.5556900.0892
0.06613.95061000.0851
0.05324.34571100.0835
0.06534.74071200.0834

Framework versions

  • —PEFT 0.12.0
  • —Transformers 4.46.1
  • —Pytorch 2.5.1+cu124
  • —Datasets 3.1.0
  • —Tokenizers 0.20.3