<!-- 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-large-cc25 reduced embedding layer on an custom dataset. It achieves the following results on the evaluation set:
- Loss: 5.5358
- Bleu: 19.1915
- Gen Len: 17.7756
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: 1000
- num_epochs: 35
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.1497 | 5.23 | 5000 | 3.8817 | 16.4877 | 18.2485 |
| 0.2561 | 10.46 | 10000 | 4.6013 | 17.9256 | 17.8049 |
| 0.0915 | 15.69 | 15000 | 4.9996 | 17.8722 | 18.1405 |
| 0.0436 | 20.92 | 20000 | 5.2561 | 19.0141 | 17.4316 |
| 0.0202 | 26.14 | 25000 | 5.4249 | 18.4325 | 18.2234 |
| 0.0087 | 31.37 | 30000 | 5.5129 | 18.9301 | 17.8334 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
