<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 3.0294
- Rouge1: 16.497
- Rouge2: 8.0618
- Rougel: 16.2979
- Rougelsum: 16.1465
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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 6.5928 | 1.0 | 1209 | 3.3005 | 14.7843 | 6.5518 | 14.2805 | 14.2951 |
| 3.9024 | 2.0 | 2418 | 3.1399 | 16.8202 | 8.6739 | 16.1194 | 16.0844 |
| 3.5806 | 3.0 | 3627 | 3.0869 | 18.1223 | 9.3051 | 17.7533 | 17.7254 |
| 3.4201 | 4.0 | 4836 | 3.0590 | 17.654 | 9.0154 | 17.1853 | 17.1769 |
| 3.3202 | 5.0 | 6045 | 3.0598 | 17.612 | 8.6707 | 17.4662 | 17.2963 |
| 3.2436 | 6.0 | 7254 | 3.0409 | 16.7938 | 8.3054 | 16.6141 | 16.4853 |
| 3.2079 | 7.0 | 8463 | 3.0332 | 16.7246 | 8.2362 | 16.5065 | 16.3611 |
| 3.1801 | 8.0 | 9672 | 3.0294 | 16.497 | 8.0618 | 16.2979 | 16.1465 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
