<!-- 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. -->
nmt-mpst-id-en-lr_0.0001-ep_10-seq_128_bs-32
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2914
- Bleu: 0.0708
- Meteor: 0.2054
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Meteor |
|---|---|---|---|---|---|
| No log | 1.0 | 202 | 2.8210 | 0.0313 | 0.1235 |
| No log | 2.0 | 404 | 2.6712 | 0.0398 | 0.1478 |
| 3.0646 | 3.0 | 606 | 2.5543 | 0.0483 | 0.1661 |
| 3.0646 | 4.0 | 808 | 2.4735 | 0.0537 | 0.1751 |
| 2.6866 | 5.0 | 1010 | 2.4120 | 0.0591 | 0.1855 |
| 2.6866 | 6.0 | 1212 | 2.3663 | 0.0618 | 0.1906 |
| 2.6866 | 7.0 | 1414 | 2.3324 | 0.0667 | 0.1993 |
| 2.5034 | 8.0 | 1616 | 2.3098 | 0.0684 | 0.2023 |
| 2.5034 | 9.0 | 1818 | 2.2969 | 0.0696 | 0.2042 |
| 2.4271 | 10.0 | 2020 | 2.2914 | 0.0708 | 0.2054 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2
