<!-- 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-finetuned-ko-to-en5
This model is a fine-tuned version of inhee/m2m100_418M-finetuned-ko-to-en4 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2863
- Bleu: 87.4185
- Gen Len: 9.7107
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: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
No log | 1.0 | 105 | 0.3571 | 78.7464 | 9.5775 |
No log | 2.0 | 210 | 0.3410 | 81.9462 | 9.6505 |
No log | 3.0 | 315 | 0.3102 | 84.746 | 9.6732 |
No log | 4.0 | 420 | 0.2929 | 86.5137 | 9.6997 |
0.2431 | 5.0 | 525 | 0.2863 | 87.4185 | 9.7107 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1