metadata
base_model: ai-forever/ruT5-base
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: my_t5_small_test
results: []
my_t5_small_test
This model is a fine-tuned version of ai-forever/ruT5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2583
- Bleu: 5.4572
- Gen Len: 16.7742
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: 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 114 | 2.4430 | 4.6333 | 16.5434 |
| No log | 2.0 | 228 | 2.3997 | 5.0426 | 16.397 |
| No log | 3.0 | 342 | 2.3420 | 5.4095 | 16.4839 |
| No log | 4.0 | 456 | 2.3057 | 5.1802 | 16.5782 |
| 2.7713 | 5.0 | 570 | 2.2985 | 5.6607 | 16.5831 |
| 2.7713 | 6.0 | 684 | 2.2824 | 5.5811 | 16.5757 |
| 2.7713 | 7.0 | 798 | 2.2759 | 6.1988 | 16.7221 |
| 2.7713 | 8.0 | 912 | 2.2611 | 5.6654 | 16.7097 |
| 2.5304 | 9.0 | 1026 | 2.2586 | 5.839 | 16.8065 |
| 2.5304 | 10.0 | 1140 | 2.2583 | 5.4572 | 16.7742 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2