qa-to-fact
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: 2.1446
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.9154 | 0.24 | 120 | 2.9647 |
3.7476 | 0.48 | 240 | 2.6029 |
2.3029 | 0.72 | 360 | 2.4172 |
1.6739 | 0.96 | 480 | 2.2824 |
1.3045 | 1.2 | 600 | 2.3350 |
2.0404 | 1.43 | 720 | 2.2483 |
1.8331 | 1.67 | 840 | 2.3469 |
1.2038 | 1.91 | 960 | 2.3409 |
2.3061 | 2.15 | 1080 | 2.2659 |
1.9986 | 2.39 | 1200 | 2.1488 |
2.0164 | 2.63 | 1320 | 2.4446 |
1.9707 | 2.87 | 1440 | 2.1446 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.14.1
- Downloads last month
- 2