vnktrmnb's picture
Training in progress epoch 2
7a4da41
metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
  - generated_from_keras_callback
model-index:
  - name: vnktrmnb/bert-base-multilingual-cased-FT-TyDiQA_PPQ
    results: []

vnktrmnb/bert-base-multilingual-cased-FT-TyDiQA_PPQ

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

  • Train Loss: 0.1315
  • Train End Logits Accuracy: 0.9554
  • Train Start Logits Accuracy: 0.9654
  • Validation Loss: 0.6059
  • Validation End Logits Accuracy: 0.8518
  • Validation Start Logits Accuracy: 0.9021
  • Epoch: 2

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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2676, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
  • training_precision: float32

Training results

Train Loss Train End Logits Accuracy Train Start Logits Accuracy Validation Loss Validation End Logits Accuracy Validation Start Logits Accuracy Epoch
0.4322 0.8625 0.8874 0.5311 0.8621 0.9008 0
0.2279 0.9238 0.9391 0.5657 0.8402 0.9046 1
0.1315 0.9554 0.9654 0.6059 0.8518 0.9021 2

Framework versions

  • Transformers 4.31.0
  • TensorFlow 2.12.0
  • Datasets 2.14.4
  • Tokenizers 0.13.3