Safick-HF's picture
End of training
dcda0df verified
|
raw
history blame
1.82 kB
metadata
license: mit
base_model: deepset/gelectra-large-germanquad
tags:
  - generated_from_trainer
model-index:
  - name: Finetuned_Question_Answering_Model
    results: []

Finetuned_Question_Answering_Model

This model is a fine-tuned version of deepset/gelectra-large-germanquad on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0316

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: 5
  • eval_batch_size: 10
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
0.0762 1.0 3 0.3330
0.5877 2.0 6 0.2301
0.0194 3.0 9 0.1833
0.1341 4.0 12 0.0951
0.002 5.0 15 0.0650
0.1363 6.0 18 0.0458
0.0263 7.0 21 0.0385
0.0032 8.0 24 0.0349
0.0036 9.0 27 0.0328
0.0031 10.0 30 0.0316

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2