Question_model

This model is a fine-tuned version of retrieva-jp/t5-base-medium on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4010
  • Rouge1: 0.0886
  • Rouge2: 0.024
  • Rougel: 0.0884
  • Rougelsum: 0.0884
  • Gen Len: 16.0081

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
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
1.7738 1.0 7858 1.4773 0.0797 0.0215 0.0793 0.0797 16.2695
1.6313 2.0 15716 1.4103 0.0832 0.0241 0.0832 0.083 16.0633
1.6204 3.0 23574 1.4010 0.0886 0.024 0.0884 0.0884 16.0081

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.19.1
Downloads last month
90
Safetensors
Model size
248M 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 kikaigakushuu/Question_model

Finetuned
(5)
this model