<!-- 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_1e-05-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: 2.8391
- Bleu: 0.0308
- Meteor: 0.1222
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: 1e-05
- 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 | 3.1172 | 0.0194 | 0.0879 |
| 3.6071 | 2.0 | 808 | 2.9990 | 0.0251 | 0.1066 |
| 3.2935 | 3.0 | 1212 | 2.9471 | 0.027 | 0.1118 |
| 3.1963 | 4.0 | 1616 | 2.9105 | 0.0281 | 0.1145 |
| 3.1602 | 5.0 | 2020 | 2.8873 | 0.0286 | 0.1168 |
| 3.1602 | 6.0 | 2424 | 2.8686 | 0.0293 | 0.1187 |
| 3.1194 | 7.0 | 2828 | 2.8547 | 0.0301 | 0.1204 |
| 3.0906 | 8.0 | 3232 | 2.8464 | 0.0306 | 0.1214 |
| 3.0866 | 9.0 | 3636 | 2.8408 | 0.0307 | 0.1221 |
| 3.0672 | 10.0 | 4040 | 2.8391 | 0.0308 | 0.1222 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2
