metadata
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mt5-base-en-ru
results: []
mt5-base-en-ru
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7278
- Bleu: 14.0945
- Gen Len: 17.862
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 160
- 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 |
|---|---|---|---|---|---|
| 0.6357 | 1.0 | 9641 | 0.7772 | 13.6966 | 17.8754 |
| 0.6615 | 2.0 | 19282 | 0.7505 | 13.8085 | 17.8701 |
| 0.6991 | 3.0 | 28923 | 0.7278 | 14.0945 | 17.862 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0