metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: t5-base-finetuned-arxiv2
results: []
t5-base-finetuned-arxiv2
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.1012
- Validation Loss: 2.0674
- 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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': 1.0, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 24894, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: mixed_float16
Training results
Train Loss | Validation Loss | Epoch |
---|---|---|
2.3695 | 2.1248 | 0 |
2.1762 | 2.0810 | 1 |
2.1012 | 2.0674 | 2 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.9.0
- Tokenizers 0.13.2