bic-fil-t5b / README.md
iManay's picture
Upload tokenizer
124d54a verified
metadata
license: apache-2.0
tags:
  - generated_from_keras_callback
base_model: google-t5/t5-base
model-index:
  - name: bic-fil-t5b
    results: []

bic-fil-t5b

This model is a fine-tuned version of google-t5/t5-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.4037
  • Validation Loss: 1.3410
  • Epoch: 9

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': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Validation Loss Epoch
1.9850 1.4928 0
1.3620 1.2710 1
1.1209 1.1860 2
0.9608 1.1466 3
0.8282 1.1467 4
0.7189 1.1613 5
0.6254 1.2177 6
0.5432 1.2522 7
0.4676 1.2758 8
0.4037 1.3410 9

Framework versions

  • Transformers 4.37.2
  • TensorFlow 2.15.0
  • Datasets 2.17.0
  • Tokenizers 0.15.2