vladjr's picture
Training in progress epoch 7
accd66b
metadata
license: apache-2.0
base_model: google/mt5-small
tags:
  - generated_from_keras_callback
model-index:
  - name: vladjr/mt5-small-finetuned-amazon-en-es
    results: []

vladjr/mt5-small-finetuned-amazon-en-es

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: 4.0679
  • Validation Loss: 3.3550
  • 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': 9672, '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
10.2003 4.2605 0
5.9025 3.7260 1
5.1086 3.5749 2
4.7038 3.4795 3
4.4331 3.4260 4
4.2478 3.3841 5
4.1313 3.3603 6
4.0679 3.3550 7

Framework versions

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