TheophileCA's picture
Upload TFRobertaForMaskedLM
2574123 verified
|
raw
history blame
No virus
1.52 kB
metadata
license: apache-2.0
base_model: TheophileCA/distilroberta_trainedOnCACatalogue
tags:
  - generated_from_keras_callback
model-index:
  - name: distilroberta_trainedOnCACatalogue
    results: []

distilroberta_trainedOnCACatalogue

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

  • Train Loss: 1.8254
  • Validation Loss: 1.7345
  • 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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Validation Loss Epoch
2.2309 1.9275 0
1.9894 1.7416 1
1.8254 1.7345 2

Framework versions

  • Transformers 4.34.0
  • TensorFlow 2.12.1
  • Datasets 2.14.5
  • Tokenizers 0.14.1