metadata
base_model: ai-forever/ruT5-base
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: t5-rebuilder
results: []
t5-rebuilder
This model is a fine-tuned version of ai-forever/ruT5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1184
- Bleu: 94.1519
- Chrf: 97.4152
- Gen Len: 13.3872
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: 0.0003
- 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Gen Len |
|---|---|---|---|---|---|---|
| 0.2957 | 1.0 | 3832 | 0.1915 | 87.926 | 94.6246 | 13.3604 |
| 0.1356 | 2.0 | 7664 | 0.1307 | 92.8051 | 96.7011 | 13.3754 |
| 0.0626 | 3.0 | 11496 | 0.1184 | 94.1519 | 97.4152 | 13.3872 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2