<!-- 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. -->
opus-mt-ko-en-finetuned-ko-to-en
This model is a fine-tuned version of Helsinki-NLP/opus-mt-ko-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2159
- Bleu: 43.3502
- Gen Len: 3.5474
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-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 0.96 | 20 | 1.3139 | 37.8375 | 3.5612 |
| No log | 1.96 | 40 | 1.2849 | 40.9049 | 3.5566 |
| No log | 2.96 | 60 | 1.2653 | 40.3399 | 3.565 |
| No log | 3.96 | 80 | 1.2516 | 42.7497 | 3.5563 |
| No log | 4.96 | 100 | 1.2395 | 42.5064 | 3.5478 |
| No log | 5.96 | 120 | 1.2311 | 43.2749 | 3.5477 |
| No log | 6.96 | 140 | 1.2232 | 42.0691 | 3.5472 |
| No log | 7.96 | 160 | 1.2193 | 43.5797 | 3.5525 |
| No log | 8.96 | 180 | 1.2169 | 43.2313 | 3.547 |
| No log | 9.96 | 200 | 1.2159 | 43.3502 | 3.5474 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
