metadata
license: apache-2.0
base_model: google-t5/t5-base
tags:
- generated_from_keras_callback
model-index:
- name: jemmyJohnes/t5-base-finetuned-en-to-ro
results: []
jemmyJohnes/t5-base-finetuned-en-to-ro
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: 0.4646
- Validation Loss: 1.3576
- Train Bleu: 27.4347
- Train Gen Len: 42.2766
- Epoch: 5
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 Bleu | Train Gen Len | Epoch |
---|---|---|---|---|
0.6844 | 1.3261 | 26.5988 | 42.1146 | 0 |
0.5396 | 1.3241 | 26.8846 | 42.0145 | 1 |
0.5118 | 1.3326 | 27.2074 | 42.2061 | 2 |
0.4936 | 1.3441 | 27.4083 | 42.1591 | 3 |
0.4777 | 1.3560 | 27.4022 | 42.3367 | 4 |
0.4646 | 1.3576 | 27.4347 | 42.2766 | 5 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.15.0
- Datasets 2.20.0
- Tokenizers 0.19.1