CoolFace
Modelpublic

lcaragiov/business-news-generator-v3

sourceHugging Faceapache-2.0updated 1y 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. -->

business-news-generator-v3

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 3.0796

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: 0.0004
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —num_epochs: 2

Training results

Training LossEpochStepValidation Loss
3.21060.161003.2888
2.98260.322003.2197
2.8920.483003.1724
2.74460.644003.1382
2.64920.85003.0762
2.62670.966003.0181
1.81071.127003.1238
1.50411.288003.1104
1.47731.449003.1164
1.4831.610003.0912
1.4371.7611003.0837
1.44151.9212003.0796

Framework versions

  • —Transformers 4.57.0
  • —Pytorch 2.8.0+cu126
  • —Datasets 4.0.0
  • —Tokenizers 0.22.1