krm's picture
End of training
6608fa1
|
raw
history blame
1.78 kB
metadata
license: apache-2.0
tags:
  - generated_from_keras_callback
model-index:
  - name: krm/mt5-small-OrangeSum-Summarizer
    results: []

krm/mt5-small-OrangeSum-Summarizer

This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 3.7771
  • Validation Loss: 2.5727
  • Epoch: 7

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': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 5000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: mixed_float16

Training results

Train Loss Validation Loss Epoch
7.8346 3.2199 0
5.1020 2.8619 1
4.5632 2.7564 2
4.2564 2.6726 3
4.0501 2.6300 4
3.9185 2.5930 5
3.8209 2.5792 6
3.7771 2.5727 7

Framework versions

  • Transformers 4.22.2
  • TensorFlow 2.8.2
  • Datasets 2.5.2
  • Tokenizers 0.12.1