metadata
license: apache-2.0
tags:
- summarization
- generated_from_trainer
datasets:
- null
metrics:
- rouge
model-index:
- name: mt5-small-finetuned-amazon-en-es
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
metrics:
- name: Rouge1
type: rouge
value: 12.4927
mt5-small-finetuned-amazon-en-es
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: 2.9894
- Rouge1: 12.4927
- Rouge2: 4.847
- Rougel: 12.4387
- Rougelsum: 12.4383
- Gen Len: 6.1675
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: 4e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 6.5619 | 1.0 | 2202 | 3.2749 | 9.2423 | 3.2813 | 9.2013 | 9.1698 | 5.0354 |
| 3.8525 | 2.0 | 4404 | 3.1296 | 11.1883 | 4.047 | 11.1545 | 11.1885 | 6.4033 |
| 3.5419 | 3.0 | 6606 | 3.0478 | 11.4905 | 4.4465 | 11.3538 | 11.3805 | 6.6462 |
| 3.4045 | 4.0 | 8808 | 3.0174 | 11.5798 | 4.4426 | 11.5372 | 11.571 | 6.6816 |
| 3.3091 | 5.0 | 11010 | 3.0080 | 12.0207 | 4.5622 | 11.9232 | 11.9476 | 6.4976 |
| 3.2457 | 6.0 | 13212 | 2.9981 | 12.2459 | 4.6924 | 12.2306 | 12.2375 | 6.1533 |
| 3.2179 | 7.0 | 15414 | 2.9943 | 12.3927 | 4.6072 | 12.2888 | 12.2848 | 6.3561 |
| 3.1898 | 8.0 | 17616 | 2.9894 | 12.4927 | 4.847 | 12.4387 | 12.4383 | 6.1675 |
Framework versions
- Transformers 4.10.3
- Pytorch 1.9.1+cu111
- Datasets 1.12.1
- Tokenizers 0.10.3