<!-- 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. -->
m2m100_418M-finetuned-ko-to-en4
This model is a fine-tuned version of facebook/m2m100_418M on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4598
- Bleu: 85.3745
- Gen Len: 9.7522
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 256
- total_train_batch_size: 1024
- 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 | 1.0 | 105 | 1.8667 | 24.5072 | 9.523 |
| No log | 2.0 | 210 | 0.8581 | 57.9973 | 9.2779 |
| No log | 3.0 | 315 | 0.6587 | 69.4588 | 9.7399 |
| No log | 4.0 | 420 | 0.5762 | 74.5636 | 9.6775 |
| 1.4539 | 5.0 | 525 | 0.5254 | 78.8897 | 9.6946 |
| 1.4539 | 6.0 | 630 | 0.4952 | 81.0054 | 9.7073 |
| 1.4539 | 7.0 | 735 | 0.4773 | 83.0792 | 9.7233 |
| 1.4539 | 8.0 | 840 | 0.4669 | 84.4309 | 9.7429 |
| 1.4539 | 9.0 | 945 | 0.4616 | 85.0965 | 9.749 |
| 0.144 | 10.0 | 1050 | 0.4598 | 85.3745 | 9.7522 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
