prateeksahu147's picture
Upload TFT5ForConditionalGeneration
dde85c5
|
raw
history blame
2.52 kB
metadata
license: apache-2.0
base_model: t5-small
tags:
  - generated_from_keras_callback
model-index:
  - name: keyword-masked-model
    results: []

keyword-masked-model

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: 0.9545
  • Validation Loss: 0.7767
  • Train Rouge1: 76.8067
  • Train Rouge2: 64.2138
  • Train Rougel: 76.1124
  • Train Rougelsum: 76.0843
  • 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': 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 Train Rouge1 Train Rouge2 Train Rougel Train Rougelsum Epoch
2.7609 2.0508 69.5404 56.1190 67.9736 67.9553 0
2.0227 1.5912 71.6288 58.5009 70.6498 70.7363 1
1.6780 1.3604 70.8191 58.1082 70.0231 69.8913 2
1.4974 1.2163 69.9943 57.3099 68.7338 68.7593 3
1.3525 1.1001 70.4850 57.7869 69.2259 69.2106 4
1.2480 1.0154 71.1204 58.1709 69.9356 69.9324 5
1.1556 0.9368 72.5520 59.4597 71.3193 71.4219 6
1.0820 0.8754 74.5839 61.6499 73.6577 73.6458 7
1.0117 0.8244 75.0935 62.3254 74.3574 74.2253 8
0.9545 0.7767 76.8067 64.2138 76.1124 76.0843 9

Framework versions

  • Transformers 4.31.0
  • TensorFlow 2.12.0
  • Datasets 2.13.1
  • Tokenizers 0.13.3