metadata
license: cc-by-sa-4.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-base-japanese-tobyoki-pairwise
results: []
bart-base-japanese-tobyoki-pairwise
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: 2.3352
- Rouge1: 2.9535
- Rouge2: 0.589
- Rougel: 2.0958
- Rougelsum: 2.7622
- Gen Len: 15.7896
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: 3e-06
- 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 |
---|---|---|---|---|---|---|---|---|
1.9659 | 1.0 | 4332 | 2.3037 | 1.596 | 0.3213 | 1.1975 | 1.4562 | 8.4066 |
1.555 | 2.0 | 8664 | 2.2936 | 3.1408 | 0.6522 | 2.3125 | 2.982 | 12.3861 |
1.3883 | 3.0 | 12996 | 2.3163 | 2.6939 | 0.5669 | 1.9944 | 2.6112 | 11.1440 |
1.2592 | 4.0 | 17328 | 2.3362 | 2.3473 | 0.4205 | 1.6502 | 2.2055 | 12.8228 |
1.2024 | 5.0 | 21660 | 2.3352 | 2.9535 | 0.589 | 2.0958 | 2.7622 | 15.7896 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu117
- Datasets 2.17.1
- Tokenizers 0.13.3