metadata
license: apache-2.0
base_model: IlyaGusev/rut5_base_sum_gazeta
tags:
- summarization_4
- generated_from_trainer
metrics:
- rouge
model-index:
- name: rut5_base_sum_gazeta-finetuned_week_gpt
results: []
rut5_base_sum_gazeta-finetuned_week_gpt
This model is a fine-tuned version of IlyaGusev/rut5_base_sum_gazeta on Natet/gpt_week_yandex dataset. This model is suitable for summarizing Hubr articles.
It achieves the following results on the evaluation set:
- Loss: 1.2643
- Rouge1: 38.9266
- Rouge2: 18.0587
- Rougel: 38.1447
- Rougelsum: 38.1337
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: 5.6e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 1.7691 | 1.0 | 1110 | 1.4005 | 37.7689 | 17.7394 | 36.8468 | 36.8842 |
| 1.4892 | 2.0 | 2220 | 1.3477 | 35.9349 | 16.8403 | 35.1786 | 35.2055 |
| 1.3579 | 3.0 | 3330 | 1.3079 | 37.7579 | 17.6421 | 36.8439 | 36.8182 |
| 1.2708 | 4.0 | 4440 | 1.2675 | 37.867 | 17.3909 | 36.9706 | 36.987 |
| 1.2006 | 5.0 | 5550 | 1.2703 | 38.8218 | 17.9772 | 38.001 | 37.9811 |
| 1.1519 | 6.0 | 6660 | 1.2703 | 38.0351 | 17.5386 | 37.209 | 37.1815 |
| 1.1132 | 7.0 | 7770 | 1.2593 | 38.4673 | 17.8343 | 37.529 | 37.5268 |
| 1.0932 | 8.0 | 8880 | 1.2643 | 38.9266 | 18.0587 | 38.1447 | 38.1337 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3