deanna-emery's picture
Upload TFT5ForConditionalGeneration
61d8b3c
metadata
tags:
  - generated_from_keras_callback
model-index:
  - name: ASL_t5_word_epoch15_1204
    results: []

ASL_t5_word_epoch15_1204

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.6353
  • Train Top 1: 0.8837
  • Train Top 5: 0.9260
  • Validation Loss: 0.7085
  • Validation Top 1: 0.8757
  • Validation Top 5: 0.9198
  • Train Bleu: 0.0
  • Train Gen Len: 2.0
  • 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': 'Adafactor', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-04, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': True}
  • training_precision: float32

Training results

Train Loss Train Top 1 Train Top 5 Validation Loss Validation Top 1 Validation Top 5 Train Bleu Train Gen Len Epoch
0.7484 0.8717 0.9143 0.6913 0.8819 0.9227 0.0 2.0 0
0.6793 0.8787 0.9218 0.6967 0.8807 0.9220 0.0 2.0 1
0.6353 0.8837 0.9260 0.7085 0.8757 0.9198 0.0 2.0 2

Framework versions

  • Transformers 4.34.1
  • TensorFlow 2.13.0
  • Datasets 2.15.0
  • Tokenizers 0.14.1