<!-- 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. -->
tst-translation-output
This model is a fine-tuned version of mbart-cc25 on an custom dataset. It achieves the following results on the evaluation set:
- Loss: 3.2088
- Bleu: 9.6216
- Gen Len: 14.1419
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1500
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.434 | 8.57 | 10000 | 2.4226 | 8.1446 | 14.2034 |
| 0.0807 | 17.15 | 20000 | 2.9133 | 8.8515 | 14.1031 |
| 0.0234 | 25.72 | 30000 | 3.0851 | 9.026 | 14.2444 |
| 0.0066 | 34.29 | 40000 | 3.1791 | 9.5933 | 14.1908 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0
