<!-- 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-16
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1098
- Bleu: 0.0918
- Meteor: 0.2374
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: 16
- eval_batch_size: 16
- 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 | 404 | 2.7230 | 0.0372 | 0.1397 |
| 3.1248 | 2.0 | 808 | 2.5087 | 0.0495 | 0.1692 |
| 2.7527 | 3.0 | 1212 | 2.3751 | 0.062 | 0.1916 |
| 2.5311 | 4.0 | 1616 | 2.2955 | 0.0703 | 0.2068 |
| 2.4088 | 5.0 | 2020 | 2.2217 | 0.0785 | 0.2173 |
| 2.4088 | 6.0 | 2424 | 2.1797 | 0.0822 | 0.2223 |
| 2.297 | 7.0 | 2828 | 2.1409 | 0.0859 | 0.2283 |
| 2.2287 | 8.0 | 3232 | 2.1239 | 0.0891 | 0.2326 |
| 2.1918 | 9.0 | 3636 | 2.1117 | 0.0907 | 0.2357 |
| 2.1626 | 10.0 | 4040 | 2.1098 | 0.0918 | 0.2374 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2
