khadija69's picture
Training in progress epoch 4
e178f8d
|
raw
history blame
2.36 kB
metadata
license: mit
base_model: khadija69/xlmRobertaLarge_BIES_stem_1K_3
tags:
  - generated_from_keras_callback
model-index:
  - name: khadija69/xlmRobertaLarge_BIES_stem_1K_4
    results: []

khadija69/xlmRobertaLarge_BIES_stem_1K_4

This model is a fine-tuned version of khadija69/xlmRobertaLarge_BIES_stem_1K_3 on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.3388
  • Train Accuracy: 0.6085
  • Validation Loss: 0.7071
  • Validation Accuracy: 0.5640
  • Epoch: 4

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': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1300, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 500, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Train Accuracy Validation Loss Validation Accuracy Epoch
0.6674 0.5493 0.6292 0.5491 0
0.6193 0.5540 0.6428 0.5514 1
0.5089 0.5762 0.6467 0.5601 2
0.4181 0.5927 0.6735 0.5610 3
0.3388 0.6085 0.7071 0.5640 4

Framework versions

  • Transformers 4.42.3
  • TensorFlow 2.15.0
  • Datasets 2.20.0
  • Tokenizers 0.19.1