masked-lm-tpu / README.md
luiscunhacsc's picture
Training in progress epoch 9
e731401
metadata
license: mit
tags:
  - generated_from_keras_callback
model-index:
  - name: luiscunhacsc/masked-lm-tpu
    results: []

luiscunhacsc/masked-lm-tpu

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

  • Train Loss: 9.8209
  • Train Accuracy: 0.0113
  • Validation Loss: 9.6999
  • Validation Accuracy: 0.0188
  • Epoch: 9

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': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0001, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 22325, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1175, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}
  • training_precision: float32

Training results

Train Loss Train Accuracy Validation Loss Validation Accuracy Epoch
10.2855 0.0000 10.2842 0.0 0
10.2729 0.0000 10.2651 0.0000 1
10.2599 0.0 10.2357 0.0000 2
10.2335 0.0 10.1943 0.0000 3
10.1915 0.0000 10.1447 0.0000 4
10.1449 0.0000 10.0705 0.0000 5
10.0750 0.0000 9.9926 0.0001 6
10.0099 0.0002 9.9074 0.0023 7
9.9197 0.0025 9.7964 0.0146 8
9.8209 0.0113 9.6999 0.0188 9

Framework versions

  • Transformers 4.29.2
  • TensorFlow 2.12.0
  • Tokenizers 0.13.3