bert2bert-abs-final-lr-5e-05-encmaxlen-512-decmaxlen-256
This model is a fine-tuned version of on the id_liputan6 dataset. It achieves the following results on the evaluation set:
- Loss: 2.876
- R1 Precision: 0.2907
- R1 Recall: 0.3519
- R1 Fmeasure: 0.3149
- R2 Precision: 0.1166
- R2 Recall: 0.1408
- R2 Fmeasure: 0.1261
- Rl Precision: 0.2301
- Rl Recall: 0.2787
- Rl Fmeasure: 0.2493
Model description
Encoder Decoder Model using IndoBERT (indobert-base-uncased) as Encoder and Decoder
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
- Max length generation: 80
- Min length generation: 10
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: 8
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 14