<!-- 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-3-ep_20-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: 1.6391
- Bleu: 18.9112
- Meteor: 0.3583
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: 0.001
- 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 | 1.8793 | 13.9958 | 0.2988 |
| No log | 2.0 | 404 | 1.7154 | 15.2332 | 0.3136 |
| 1.6109 | 3.0 | 606 | 1.6615 | 16.4394 | 0.3279 |
| 1.6109 | 4.0 | 808 | 1.6292 | 17.1368 | 0.3375 |
| 1.2855 | 5.0 | 1010 | 1.6205 | 17.7174 | 0.3451 |
| 1.2855 | 6.0 | 1212 | 1.6246 | 17.9786 | 0.3478 |
| 1.2855 | 7.0 | 1414 | 1.6178 | 18.3294 | 0.3515 |
| 1.0144 | 8.0 | 1616 | 1.6195 | 18.6155 | 0.3556 |
| 1.0144 | 9.0 | 1818 | 1.6320 | 18.7035 | 0.3565 |
| 0.8814 | 10.0 | 2020 | 1.6391 | 18.9112 | 0.3583 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2
