metadata
license: apache-2.0
tags:
- 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: 10.8752
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: 3.1491
- Rouge1: 10.8752
- Rouge2: 3.8695
- Rougel: 10.6991
- Rougelsum: 10.6616
- Gen Len: 5.6085
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: 2e-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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 9.1733 | 1.0 | 2202 | 3.4863 | 6.3629 | 1.4637 | 6.2501 | 6.2752 | 3.3302 |
| 4.4547 | 2.0 | 4404 | 3.2809 | 9.1283 | 2.992 | 8.9851 | 9.0487 | 4.7642 |
| 4.0581 | 3.0 | 6606 | 3.2108 | 10.5207 | 3.7411 | 10.2595 | 10.234 | 5.3208 |
| 3.8821 | 4.0 | 8808 | 3.1701 | 10.8636 | 4.0944 | 10.6462 | 10.6468 | 5.2453 |
| 3.7857 | 5.0 | 11010 | 3.1600 | 10.9456 | 4.5187 | 10.784 | 10.7542 | 5.691 |
| 3.7273 | 6.0 | 13212 | 3.1491 | 10.8752 | 3.8695 | 10.6991 | 10.6616 | 5.6085 |
Framework versions
- Transformers 4.10.3
- Pytorch 1.9.1+cu102
- Datasets 1.12.1
- Tokenizers 0.10.3