CoolFace
Modelpublic

deepakshirkem/image-description_to_emotion

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
1likes17downloads
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. -->

image-descriptiontoemotion

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-360M on the arrow dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.1650

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: 2e-05
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 16
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_ratio: 0.1
  • —num_epochs: 4
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.59790.3361500.5039
0.32620.67231000.2783
0.25991.00841500.2305
0.22111.34452000.2071
0.20041.68072500.1969
0.20942.01683000.1840
0.17882.35293500.1797
0.17092.68914000.1739
0.16043.02524500.1693
0.1413.36135000.1671
0.14793.69755500.1650

Framework versions

  • —Transformers 4.44.2
  • —Pytorch 2.4.1+cu121
  • —Datasets 3.2.0
  • —Tokenizers 0.19.1