<!-- 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-4-ep_10-seq_128_bs-64
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4108
- Bleu: 5.8803
- Meteor: 0.1857
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: 64
- eval_batch_size: 64
- 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 | 101 | 2.8898 | 2.8643 | 0.1158 |
No log | 2.0 | 202 | 2.7574 | 3.5561 | 0.1355 |
No log | 3.0 | 303 | 2.6672 | 4.1558 | 0.1509 |
No log | 4.0 | 404 | 2.5927 | 4.5156 | 0.1593 |
2.9931 | 5.0 | 505 | 2.5319 | 4.9528 | 0.1673 |
2.9931 | 6.0 | 606 | 2.4832 | 5.2665 | 0.1728 |
2.9931 | 7.0 | 707 | 2.4505 | 5.4822 | 0.1778 |
2.9931 | 8.0 | 808 | 2.4290 | 5.7456 | 0.1829 |
2.9931 | 9.0 | 909 | 2.4147 | 5.8499 | 0.185 |
2.6176 | 10.0 | 1010 | 2.4108 | 5.8803 | 0.1857 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2