Hugging Face's logo

badokorach
/
afriqa_afroxlmr_squad_v2-luganda_311223

Question Answering
Transformers
TensorFlow
xlm-roberta
generated_from_keras_callback
Inference Endpoints
Model card Files Community
afriqa_afroxlmr_squad_v2-luganda_311223 / README.md
badokorach's picture
badokorach
Training in progress epoch 22
c8bded5
preview code
|
raw
history blame
2.59 kB
metadata
license: mit
base_model: badokorach/afriqa_afroxlmr_squad_v2-luganda
tags:
  - generated_from_keras_callback
model-index:
  - name: badokorach/afriqa_afroxlmr_squad_v2-luganda_311223
    results: []

badokorach/afriqa_afroxlmr_squad_v2-luganda_311223

This model is a fine-tuned version of badokorach/afriqa_afroxlmr_squad_v2-luganda on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.6746
  • Validation Loss: 0.0
  • Epoch: 22

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:

  • optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 14760, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}
  • training_precision: mixed_float16

Training results

Train Loss Validation Loss Epoch
3.4699 0.0 0
3.3401 0.0 1
3.1487 0.0 2
2.9589 0.0 3
2.7472 0.0 4
2.5135 0.0 5
2.3000 0.0 6
2.0904 0.0 7
1.9314 0.0 8
1.7617 0.0 9
1.6075 0.0 10
1.4573 0.0 11
1.3275 0.0 12
1.2261 0.0 13
1.1378 0.0 14
1.0358 0.0 15
0.9618 0.0 16
0.9082 0.0 17
0.8762 0.0 18
0.8012 0.0 19
0.7568 0.0 20
0.7120 0.0 21
0.6746 0.0 22

Framework versions

  • Transformers 4.35.2
  • TensorFlow 2.15.0
  • Datasets 2.16.1
  • Tokenizers 0.15.0