CoolFace
Modelpublic

lcaragiov/business-news-generator-v4

sourceHugging Faceapache-2.0updated 11mo agoView on Hugging Face
0likes22downloads
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-v4

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: 2.4468

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: 32
  • —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
1.7210.10661002.5413
1.70990.21322002.5191
1.74190.31983002.5133
1.71120.42644002.4781
1.71170.53305002.4521
1.74920.63976002.4189
1.6910.74637002.3948
1.66310.85298002.3661
1.66420.95959002.3370
1.24171.066110002.4726
0.99861.172711002.4814
0.97571.279312002.4765
0.97431.385913002.4615
0.98191.492514002.4594
0.97391.599115002.4506
0.94611.705816002.4477
0.96711.812417002.4458
0.92751.919018002.4468

Framework versions

  • —Transformers 4.57.1
  • —Pytorch 2.8.0+cu126
  • —Datasets 4.0.0
  • —Tokenizers 0.22.1