mt5-base-mt5-full / README.md
vladjr's picture
Training in progress epoch 7
f36ddd4
metadata
license: apache-2.0
base_model: google/mt5-base
tags:
  - generated_from_keras_callback
model-index:
  - name: vladjr/mt5-base-mt5-full
    results: []

vladjr/mt5-base-mt5-full

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

  • Train Loss: 1.1101
  • Validation Loss: 0.9831
  • 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 9280, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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
6.7607 1.6963 0
2.6675 1.4045 1
1.8063 1.2591 2
1.5864 1.0469 3
1.2627 1.0222 4
1.1802 1.0123 5
1.1343 0.9810 6
1.1101 0.9831 7

Framework versions

  • Transformers 4.34.1
  • TensorFlow 2.13.0
  • Datasets 2.14.5
  • Tokenizers 0.14.1