kumapo
/

llm-jp-modernbert-base-jsquad

Question Answering

Generated from Trainer

Model card Files Files and versions

output

This model is a fine-tuned version of llm-jp/llm-jp-modernbert-base on the sbintuitions/JSQuAD dataset.

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: 4e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1.0

Training results

Framework versions

Transformers 4.52.4
Pytorch 2.10.0.dev20251211+cu128
Datasets 4.4.1
Tokenizers 0.21.4

Downloads last month: 35

Safetensors

Model size

0.2B params

Tensor type

F32

·

Model tree for kumapo/llm-jp-modernbert-base-jsquad

Base model

llm-jp/llm-jp-modernbert-base

Finetuned

(2)

this model

Dataset used to train kumapo/llm-jp-modernbert-base-jsquad