<!-- 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-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: 2.9022
- Bleu: 0.0284
- Meteor: 0.1159
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: 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 | 3.2021 | 0.0126 | 0.0683 |
| No log | 2.0 | 404 | 3.0749 | 0.0219 | 0.0958 |
| 3.559 | 3.0 | 606 | 3.0147 | 0.0252 | 0.1059 |
| 3.559 | 4.0 | 808 | 2.9738 | 0.0262 | 0.1094 |
| 3.2602 | 5.0 | 1010 | 2.9476 | 0.027 | 0.1113 |
| 3.2602 | 6.0 | 1212 | 2.9309 | 0.0278 | 0.1138 |
| 3.2602 | 7.0 | 1414 | 2.9153 | 0.0278 | 0.1139 |
| 3.1839 | 8.0 | 1616 | 2.9083 | 0.0285 | 0.116 |
| 3.1839 | 9.0 | 1818 | 2.9041 | 0.0284 | 0.1158 |
| 3.1574 | 10.0 | 2020 | 2.9022 | 0.0284 | 0.1159 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2
