Hugging Face's logo

badokorach
/
mobilebert-uncased-finetuned-agic-060124

Question Answering
Transformers
TensorFlow
mobilebert
generated_from_keras_callback
Inference Endpoints
Model card Files Community
mobilebert-uncased-finetuned-agic-060124 / README.md
badokorach's picture
badokorach
Training in progress epoch 18
b292f60
preview code
|
raw
history blame
2.45 kB
metadata
license: mit
base_model: badokorach/mobilebert-uncased-finetuned-agic-181223
tags:
  - generated_from_keras_callback
model-index:
  - name: badokorach/mobilebert-uncased-finetuned-agic-060124
    results: []

badokorach/mobilebert-uncased-finetuned-agic-060124

This model is a fine-tuned version of badokorach/mobilebert-uncased-finetuned-agic-181223 on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.3066
  • Validation Loss: 0.0
  • Epoch: 18

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': 2320, '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
0.8096 0.0 0
1.0508 0.0 1
0.5189 0.0 2
0.4869 0.0 3
0.4681 0.0 4
0.4300 0.0 5
0.4224 0.0 6
0.4163 0.0 7
0.3690 0.0 8
0.3680 0.0 9
0.3594 0.0 10
0.3456 0.0 11
0.3273 0.0 12
0.3345 0.0 13
0.3335 0.0 14
0.3056 0.0 15
0.3232 0.0 16
0.3027 0.0 17
0.3066 0.0 18

Framework versions

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