metadata
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: vlsp_lo-vi-mta
results: []
vlsp_lo-vi-mta
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5710
- Bleu: 44.3925
- Gen Len: 24.808
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
1.6268 | 1.0 | 6250 | 1.7723 | 38.2292 | 24.737 |
1.4286 | 2.0 | 12500 | 1.6487 | 41.6858 | 24.748 |
1.2249 | 3.0 | 18750 | 1.5879 | 43.4096 | 24.624 |
1.1483 | 4.0 | 25000 | 1.5710 | 44.3925 | 24.808 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3