metadata
base_model: kravchenko/uk-mt5-base
tags:
- summarization
- generated_from_trainer
datasets:
- xlsum
metrics:
- rouge
model-index:
- name: uk-mt5-base-xlsum-4000
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: xlsum
type: xlsum
config: ukrainian
split: validation
args: ukrainian
metrics:
- name: Rouge1
type: rouge
value: 4.2038
uk-mt5-base-xlsum-4000
This model is a fine-tuned version of kravchenko/uk-mt5-base on the xlsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.7909
- Rouge1: 4.2038
- Rouge2: 0.6736
- Rougel: 4.1229
- Rougelsum: 4.1353
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: 6
- eval_batch_size: 6
- 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 |
|---|---|---|---|---|---|---|---|
| 2.871 | 1.0 | 7201 | 1.9992 | 3.157 | 0.5155 | 3.1283 | 3.1298 |
| 2.3902 | 2.0 | 14402 | 1.9162 | 3.6231 | 0.595 | 3.5878 | 3.6125 |
| 2.2273 | 3.0 | 21603 | 1.8681 | 3.8688 | 0.5949 | 3.8101 | 3.8106 |
| 2.1219 | 4.0 | 28804 | 1.8264 | 3.7935 | 0.58 | 3.741 | 3.7647 |
| 2.0448 | 5.0 | 36005 | 1.8062 | 3.9388 | 0.7156 | 3.8877 | 3.9098 |
| 1.9898 | 6.0 | 43206 | 1.8077 | 4.3916 | 0.8113 | 4.3133 | 4.327 |
| 1.9483 | 7.0 | 50407 | 1.7935 | 4.2474 | 0.7119 | 4.1732 | 4.197 |
| 1.9209 | 8.0 | 57608 | 1.7909 | 4.2038 | 0.6736 | 4.1229 | 4.1353 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1