metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- opus_infopankki
metrics:
- bleu
model-index:
- name: opus-mt-ar-en-finetuned-ar-to-en
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: opus_infopankki
type: opus_infopankki
args: ar-en
metrics:
- name: Bleu
type: bleu
value: 28.9919
opus-mt-ar-en-finetuned-ar-to-en
This model is a fine-tuned version of Helsinki-NLP/opus-mt-ar-en on the opus_infopankki dataset. It achieves the following results on the evaluation set:
- Loss: 1.6629
- Bleu: 28.9919
- Gen Len: 15.6512
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: 2e-06
- 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: 11
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 159 | 2.1441 | 22.0728 | 16.5805 |
| No log | 2.0 | 318 | 2.0141 | 23.888 | 16.3754 |
| No log | 3.0 | 477 | 1.9228 | 25.2541 | 15.835 |
| 2.2356 | 4.0 | 636 | 1.8523 | 26.299 | 15.7874 |
| 2.2356 | 5.0 | 795 | 1.7971 | 26.8646 | 16.0247 |
| 2.2356 | 6.0 | 954 | 1.7536 | 27.2391 | 16.013 |
| 1.9609 | 7.0 | 1113 | 1.7200 | 27.7471 | 16.0237 |
| 1.9609 | 8.0 | 1272 | 1.6945 | 28.4924 | 15.6563 |
| 1.9609 | 9.0 | 1431 | 1.6771 | 28.8024 | 15.6445 |
| 1.8388 | 10.0 | 1590 | 1.6665 | 29.0016 | 15.6429 |
| 1.8388 | 11.0 | 1749 | 1.6629 | 28.9919 | 15.6512 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.7.1+cu110
- Datasets 2.2.2
- Tokenizers 0.12.1