metadata
license: cc-by-sa-4.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-base-japanese-tobyoki-pairwise-wo_space
results: []
bart-base-japanese-tobyoki-pairwise-wo_space
This model is a fine-tuned version of ku-nlp/bart-base-japanese on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0850
- Rouge1: 15.3454
- Rouge2: 2.9489
- Rougel: 10.7691
- Rougelsum: 12.7028
- Gen Len: 66.075
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.1701 | 1.0 | 717 | 1.9507 | 12.6467 | 2.901 | 10.0035 | 11.1471 | 47.7375 |
| 1.4042 | 2.0 | 1434 | 1.9519 | 11.9515 | 3.096 | 10.2259 | 10.8478 | 21.1375 |
| 0.8952 | 3.0 | 2151 | 2.0323 | 15.5721 | 3.5875 | 10.6382 | 12.9346 | 76.35 |
| 0.7489 | 4.0 | 2868 | 2.0724 | 15.5769 | 3.3042 | 11.0176 | 12.8107 | 63.7625 |
| 0.5941 | 5.0 | 3585 | 2.0850 | 15.3454 | 2.9489 | 10.7691 | 12.7028 | 66.075 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3