folflo's picture
Training in progress epoch 7
3d90ebb
metadata
license: apache-2.0
base_model: google/mt5-small
tags:
  - generated_from_keras_callback
model-index:
  - name: folflo/mt5-small-finetuned-amazon-en-de
    results: []

folflo/mt5-small-finetuned-amazon-en-de

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: 4.1509
  • Validation Loss: 3.5514
  • 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': 10200, '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
9.7620 4.3962 0
5.8713 3.9145 1
5.1562 3.7814 2
4.7817 3.7021 3
4.5273 3.6399 4
4.3519 3.5826 5
4.2228 3.5654 6
4.1509 3.5514 7

Framework versions

  • Transformers 4.32.0
  • TensorFlow 2.12.0
  • Datasets 2.14.4
  • Tokenizers 0.13.3