metadata
license: cc-by-nc-4.0
base_model: facebook/nllb-200-distilled-600M
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: fb-nllb-2d6m-Bilibili_MIX_1350K-en-th-70k-clean-punct
results: []
fb-nllb-2d6m-Bilibili_MIX_1350K-en-th-70k-clean-punct
This model is a fine-tuned version of facebook/nllb-200-distilled-600M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2449
- Bleu: 41.9443
- Gen Len: 31.5709
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.129 | 1.0 | 144 | 1.2976 | 40.8925 | 31.6055 |
| 1.1063 | 2.0 | 288 | 1.2713 | 40.2012 | 31.346 |
| 0.9238 | 3.0 | 432 | 1.2449 | 41.9443 | 31.5709 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2