modernbert-fineweb-is

This model is a fine-tuned version of answerdotai/ModernBERT-base on the Icelandic portion of Fineweb-2.

Model description

More information needed

Intended uses & limitations

This model is intended to be a baseline for research purposes. It uses the original ModernBERT tokenizer trained on predominantly English data, which will obviously not be ideal.

Training and evaluation data

Trained on Fineweb-2.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 64
  • total_train_batch_size: 256
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 1

Training results

Framework versions

  • Transformers 4.49.0.dev0
  • Pytorch 2.5.1
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
27
Safetensors
Model size
150M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for jekunz/modernbert-fineweb-is

Finetuned
(202)
this model

Dataset used to train jekunz/modernbert-fineweb-is