metadata
license: apache-2.0
tags:
- simplification
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt5-small-clara-med
results: []
mt5-small-clara-med
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3080
- Rouge1: 30.493
- Rouge2: 15.6893
- Rougel: 26.8862
- Rougelsum: 26.912
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: 5.6e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 190 | 3.2218 | 18.2868 | 7.2715 | 16.1223 | 16.4758 |
| No log | 2.0 | 380 | 2.5984 | 22.723 | 11.054 | 20.6104 | 20.5809 |
| 7.1737 | 3.0 | 570 | 2.4510 | 29.0855 | 14.5467 | 25.516 | 25.5461 |
| 7.1737 | 4.0 | 760 | 2.3834 | 29.5966 | 14.9256 | 26.0424 | 26.0825 |
| 3.3012 | 5.0 | 950 | 2.3490 | 30.0213 | 15.2307 | 26.3306 | 26.3528 |
| 3.3012 | 6.0 | 1140 | 2.3250 | 30.1084 | 15.1684 | 26.4745 | 26.4574 |
| 3.3012 | 7.0 | 1330 | 2.3139 | 30.5785 | 15.7414 | 26.9835 | 27.0047 |
| 3.0426 | 8.0 | 1520 | 2.3080 | 30.493 | 15.6893 | 26.8862 | 26.912 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0
- Datasets 2.8.0
- Tokenizers 0.12.1