metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- summarization
- generated_from_trainer
datasets:
- xlsum
metrics:
- rouge
model-index:
- name: mt5-small-xlsum
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: xlsum
type: xlsum
config: ukrainian
split: train
args: ukrainian
metrics:
- name: Rouge1
type: rouge
value: 1.1945
mt5-small-xlsum
This model is a fine-tuned version of google/mt5-small on the xlsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.8395
- Rouge1: 1.1945
- Rouge2: 0.1467
- Rougel: 1.1902
- Rougelsum: 1.196
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 |
|---|---|---|---|---|---|---|---|
| 11.9992 | 1.0 | 125 | 4.0495 | 0.3829 | 0.0 | 0.3905 | 0.3905 |
| 5.8176 | 2.0 | 250 | 3.3431 | 0.491 | 0.0667 | 0.4988 | 0.4821 |
| 4.9907 | 3.0 | 375 | 3.1548 | 0.6481 | 0.08 | 0.6766 | 0.6655 |
| 4.6486 | 4.0 | 500 | 3.0347 | 1.0105 | 0.1467 | 1.0398 | 1.0274 |
| 4.4541 | 5.0 | 625 | 2.9414 | 0.9581 | 0.1467 | 0.951 | 0.9643 |
| 4.3195 | 6.0 | 750 | 2.8837 | 1.1129 | 0.1467 | 1.1245 | 1.1193 |
| 4.2618 | 7.0 | 875 | 2.8473 | 1.1019 | 0.1467 | 1.1048 | 1.1224 |
| 4.2228 | 8.0 | 1000 | 2.8395 | 1.1945 | 0.1467 | 1.1902 | 1.196 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1