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: 0.8401
- Bleu: 12.2867
- Gen Len: 17.8712
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: 0.0004
- train_batch_size: 14
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 140
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.1469 | 1.0 | 11019 | 1.0554 | 10.1262 | 17.8974 |
| 1.0112 | 2.0 | 22038 | 0.9529 | 10.9674 | 17.8698 |
| 0.937 | 3.0 | 33057 | 0.8913 | 11.6301 | 17.8687 |
| 0.8809 | 4.0 | 44076 | 0.8545 | 11.9517 | 17.8833 |
| 0.8501 | 5.0 | 55095 | 0.8401 | 12.2867 | 17.8712 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0