metadata
license: apache-2.0
tags:
- multilingual model
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt5-small-finetuned-multilingual-xlsum
results: []
mt5-small-finetuned-multilingual-xlsum
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: 2.7979
- Rouge1: 9.2017
- Rouge2: 2.3976
- Rougel: 7.7055
- Rougelsum: 7.7347
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 4.4524 | 1.0 | 3375 | 2.9251 | 8.1565 | 1.9058 | 6.7949 | 6.8196 |
| 3.6707 | 2.0 | 6750 | 2.8524 | 8.7884 | 2.147 | 7.339 | 7.3678 |
| 3.5273 | 3.0 | 10125 | 2.8184 | 9.1157 | 2.3886 | 7.6228 | 7.6592 |
| 3.4452 | 4.0 | 13500 | 2.8028 | 9.2619 | 2.406 | 7.7607 | 7.7921 |
| 3.4074 | 5.0 | 16875 | 2.7979 | 9.2017 | 2.3976 | 7.7055 | 7.7347 |
Framework versions
- Transformers 4.19.1
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1