| tags: | |
| - generated_from_trainer | |
| metrics: | |
| - rouge | |
| model-index: | |
| - name: t5-russian-spell | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # t5-russian-spell | |
| This model is a fine-tuned version of [sberbank-ai/ruT5-base](https://huggingface.co/sberbank-ai/ruT5-base) on the None dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.4066 | |
| - Rouge1: 44.2214 | |
| - Rouge2: 21.688 | |
| - Rougel: 44.2793 | |
| - Rougelsum: 44.0781 | |
| - Gen Len: 60.87 | |
| ## 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: 8 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - num_epochs: 1 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | | |
| |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| | |
| | 0.2958 | 0.2 | 2500 | 0.4393 | 43.9635 | 21.3982 | 43.9784 | 43.8423 | 61.338 | | |
| | 0.2427 | 0.4 | 5000 | 0.4460 | 44.609 | 22.1448 | 44.6314 | 44.4817 | 61.028 | | |
| | 0.5326 | 0.6 | 7500 | 0.4100 | 44.7071 | 21.9365 | 44.7491 | 44.5944 | 60.844 | | |
| | 0.5262 | 0.8 | 10000 | 0.4066 | 44.2214 | 21.688 | 44.2793 | 44.0781 | 60.87 | | |
| ### Framework versions | |
| - Transformers 4.17.0 | |
| - Pytorch 1.10.0+cu111 | |
| - Datasets 2.0.0 | |
| - Tokenizers 0.11.6 | |