iva_mt_wslot-m2m100_418M-zh-en
This model is a fine-tuned version of facebook/m2m100_418M on the iva_mt_wslot dataset. It achieves the following results on the evaluation set:
- Loss: 0.0139
- Bleu: 67.9385
- Gen Len: 18.9988
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: 4
- eval_batch_size: 4
- seed: 42
- 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 |
|---|---|---|---|---|---|
| 0.016 | 1.0 | 2437 | 0.0138 | 62.077 | 18.6077 |
| 0.0114 | 2.0 | 4874 | 0.0126 | 64.3834 | 18.9019 |
| 0.0084 | 3.0 | 7311 | 0.0123 | 66.0012 | 18.9206 |
| 0.0067 | 4.0 | 9748 | 0.0123 | 66.7838 | 19.0018 |
| 0.005 | 5.0 | 12185 | 0.0124 | 66.9053 | 18.9527 |
| 0.0039 | 6.0 | 14622 | 0.0128 | 67.5252 | 18.9918 |
| 0.003 | 7.0 | 17059 | 0.0131 | 67.3664 | 18.9609 |
| 0.0025 | 8.0 | 19496 | 0.0135 | 67.792 | 19.0198 |
| 0.0019 | 9.0 | 21933 | 0.0137 | 67.7256 | 18.9591 |
| 0.0015 | 10.0 | 24370 | 0.0139 | 67.9385 | 18.9988 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Evaluation results
- Bleu on iva_mt_wslotvalidation set self-reported67.939