Hugging Face's logo

Thenghuy
/
cropwiz_qa_model_2

Question Answering
Transformers
TensorBoard
Safetensors
electra
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
cropwiz_qa_model_2 / README.md
Thenghuy's picture
Thenghuy
End of training
8d2f977 verified
preview code
|
raw
history blame
2.31 kB
metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: cropwiz_qa_model_2
    results: []

cropwiz_qa_model_2

This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.1802

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: 0.0002
  • train_batch_size: 6
  • eval_batch_size: 6
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 19 2.8276
No log 2.0 38 2.6534
No log 3.0 57 3.0085
No log 4.0 76 3.1586
No log 5.0 95 3.3162
No log 6.0 114 3.4105
No log 7.0 133 3.6466
No log 8.0 152 3.6437
No log 9.0 171 4.3458
No log 10.0 190 4.2937
No log 11.0 209 4.5459
No log 12.0 228 4.1286
No log 13.0 247 4.3959
No log 14.0 266 3.9187
No log 15.0 285 3.8182
No log 16.0 304 4.3889
No log 17.0 323 4.2887
No log 18.0 342 4.1675
No log 19.0 361 4.1868
No log 20.0 380 4.1802

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1