metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: t5-small-finetuned-NL2ModelioMQ
results: []
t5-small-finetuned-NL2ModelioMQ
This model is a fine-tuned version of t5-small on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Rouge2 Precision: 0.9789
- Rouge2 Recall: 0.6056
- Rouge2 Fmeasure: 0.7296
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:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| 0.0095 | 1.0 | 4449 | 0.0005 | 0.9702 | 0.6012 | 0.7238 |
| 0.0015 | 2.0 | 8898 | 0.0000 | 0.9789 | 0.6056 | 0.7296 |
| 0.0006 | 3.0 | 13347 | 0.0000 | 0.9789 | 0.6056 | 0.7296 |
| 0.0004 | 4.0 | 17796 | 0.0000 | 0.9789 | 0.6056 | 0.7296 |
| 0.0003 | 5.0 | 22245 | 0.0000 | 0.9789 | 0.6056 | 0.7296 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2