metadata
base_model: Alfahluzi/bert2bert-model99-last
tags:
- generated_from_trainer
datasets:
- id_liputan6
model-index:
- name: bert2bert-model99-last-Xtreme-Train
results: []
bert2bert-model99-last-Xtreme-Train
This model is a fine-tuned version of Alfahluzi/bert2bert-model99-last on the id_liputan6 dataset. It achieves the following results on the evaluation set:
- Loss: 2.8449
- R1 Precision: 0.3481
- R1 Recall: 0.3462
- R1 Fmeasure: 0.3448
- R2 Precision: 0.1475
- R2 Recall: 0.1463
- R2 Fmeasure: 0.1458
- Rl Precision: 0.2761
- Rl Recall: 0.2748
- Rl Fmeasure: 0.2736
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2.5931 | 1.0 | 495 | 2.3625 | 0.359 | 0.3516 | 0.3528 | 0.159 | 0.155 | 0.1557 | 0.2876 | 0.2819 | 0.2826 |
| 1.8329 | 2.0 | 990 | 2.4301 | 0.3577 | 0.3489 | 0.3508 | 0.1563 | 0.1517 | 0.1528 | 0.286 | 0.2793 | 0.2806 |
| 1.3237 | 3.0 | 1485 | 2.6019 | 0.3483 | 0.3445 | 0.344 | 0.149 | 0.1468 | 0.1468 | 0.2784 | 0.2755 | 0.275 |
| 0.976 | 4.0 | 1980 | 2.7468 | 0.3509 | 0.3481 | 0.3471 | 0.1501 | 0.1483 | 0.1481 | 0.2784 | 0.2765 | 0.2755 |
| 0.7665 | 5.0 | 2475 | 2.8449 | 0.3481 | 0.3462 | 0.3448 | 0.1475 | 0.1463 | 0.1458 | 0.2761 | 0.2748 | 0.2736 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2