bedus-creation's picture
Training in progress epoch 39
3f91188
|
raw
history blame
2.94 kB
metadata
license: apache-2.0
base_model: t5-small
tags:
  - generated_from_keras_callback
model-index:
  - name: bedus-creation/t5-small-dataset-ii-eng-lim
    results: []

bedus-creation/t5-small-dataset-ii-eng-lim

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

  • Train Loss: 6.6551
  • Validation Loss: 6.6150
  • Epoch: 39

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': 2e-05, '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
8.3860 7.8693 0
7.8568 7.6558 1
7.6900 7.5352 2
7.5904 7.4631 3
7.5155 7.4041 4
7.4554 7.3553 5
7.4005 7.3036 6
7.3547 7.2561 7
7.3104 7.2076 8
7.2651 7.1736 9
7.2302 7.1315 10
7.1888 7.0968 11
7.1616 7.0651 12
7.1290 7.0307 13
7.1066 7.0053 14
7.0729 6.9707 15
7.0388 6.9448 16
7.0169 6.9307 17
6.9924 6.9024 18
6.9716 6.8793 19
6.9503 6.8574 20
6.9252 6.8467 21
6.9136 6.8283 22
6.8915 6.8110 23
6.8697 6.7949 24
6.8531 6.7795 25
6.8336 6.7697 26
6.8255 6.7512 27
6.8080 6.7408 28
6.7928 6.7286 29
6.7752 6.7145 30
6.7629 6.7035 31
6.7467 6.6857 32
6.7329 6.6796 33
6.7216 6.6668 34
6.7067 6.6644 35
6.6935 6.6473 36
6.6810 6.6427 37
6.6713 6.6261 38
6.6551 6.6150 39

Framework versions

  • Transformers 4.33.2
  • TensorFlow 2.13.0
  • Datasets 2.14.5
  • Tokenizers 0.13.3