metadata
tags:
- generated_from_trainer
datasets:
- id_liputan6
model-index:
- name: bert2bert-abs-generationconfig-lr-5e-05-encmaxlen-512-decmaxlen-256
results: []
bert2bert-abs-generationconfig-lr-5e-05-encmaxlen-512-decmaxlen-256
This model was trained from scratch on the id_liputan6 dataset. It achieves the following results on the evaluation set:
- Loss: 2.4820
- R1 Precision: 0.0734
- R1 Recall: 0.5856
- R1 Fmeasure: 0.1301
- R2 Precision: 0.0268
- R2 Recall: 0.2229
- R2 Fmeasure: 0.0478
- Rl Precision: 0.0524
- Rl Recall: 0.4201
- Rl Fmeasure: 0.0929
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: 18
- eval_batch_size: 18
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | R1 Precision | R1 Recall | R1 Fmeasure | R2 Precision | R2 Recall | R2 Fmeasure | Rl Precision | Rl Recall | Rl Fmeasure |
---|---|---|---|---|---|---|---|---|---|---|---|---|
2.2905 | 1.0 | 10772 | 2.6334 | 0.0695 | 0.5865 | 0.124 | 0.0254 | 0.223 | 0.0454 | 0.0495 | 0.4196 | 0.0883 |
1.4553 | 2.0 | 21544 | 2.5229 | 0.0717 | 0.578 | 0.1273 | 0.0258 | 0.2165 | 0.046 | 0.0512 | 0.414 | 0.0908 |
1.2405 | 3.0 | 32316 | 2.4820 | 0.0734 | 0.5856 | 0.1301 | 0.0268 | 0.2229 | 0.0478 | 0.0524 | 0.4201 | 0.0929 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2