CoolFace
Modelpublic

archit11/worldmodel2

sourceHugging Facemitupdated 2y agoView on Hugging Face
0likes10downloads
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. -->

acha

This model is a fine-tuned version of nisten/Biggie-SmoLlm-0.15B-Base on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 2.8727

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: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 16
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 5
  • —training_steps: 800

Training results

Training LossEpochStepValidation Loss
3.70940.0920503.5122
3.54640.18411003.2981
3.42920.27611503.1894
3.35760.36822003.0917
3.350.46022503.0353
3.33340.55223002.9864
3.30960.64433502.9512
3.27730.73634002.9281
3.23430.82834502.9118
3.22650.92045002.9015
3.02571.01245502.8853
2.90921.10456002.8748
2.91091.19656502.8732
2.94371.28857002.8728
2.8941.38067502.8727
2.92861.47268002.8727

Framework versions

  • —Transformers 4.44.2
  • —Pytorch 2.4.0
  • —Datasets 3.0.0
  • —Tokenizers 0.19.1