Hugging Face's logo

santyzenith
/
uda_rules_qa

Question Answering
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
uda_rules_qa / README.md
santyzenith's picture
santyzenith
End of training
61517cd verified
preview code
|
raw history blame contribute delete
No virus
2.17 kB
metadata
base_model: MMG/bert-base-spanish-wwm-cased-finetuned-spa-squad2-es-finetuned-sqac
tags:
  - generated_from_trainer
model-index:
  - name: uda_rules_qa
    results: []

uda_rules_qa

This model is a fine-tuned version of MMG/bert-base-spanish-wwm-cased-finetuned-spa-squad2-es-finetuned-sqac on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5263

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: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.2609 1.0 22 1.0845
0.5942 2.0 44 0.8048
0.2471 3.0 66 0.5481
0.108 4.0 88 0.5052
0.0665 5.0 110 0.5149
0.0612 6.0 132 0.6101
0.0265 7.0 154 0.7251
0.0457 8.0 176 0.5007
0.0108 9.0 198 0.4987
0.0037 10.0 220 0.5012
0.0013 11.0 242 0.5184
0.0053 12.0 264 0.5087
0.0002 13.0 286 0.5167
0.0003 14.0 308 0.5225
0.0004 15.0 330 0.5263

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0