bert2bert-Large / README.md
Alfahluzi's picture
Alfahluzi/bert2bert-extreme-dropout-0.5-lr-5e-05-batchsize-4-encmaxlen-2048-decmaxlen-512 train 5 epochs with 4 batch size
446165e verified
|
raw
history blame
2.62 kB
---
tags:
- generated_from_trainer
datasets:
- id_liputan6
model-index:
- name: bert2bert-extreme-dropout-0.5-lr-5e-05-batchsize-4-encmaxlen-2048-decmaxlen-512
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert2bert-extreme-dropout-0.5-lr-5e-05-batchsize-4-encmaxlen-2048-decmaxlen-512
This model was trained from scratch on the id_liputan6 dataset.
It achieves the following results on the evaluation set:
- Loss: 8.6177
- R1 Precision: 0.0188
- R1 Recall: 0.0105
- R1 Fmeasure: 0.0133
- R2 Precision: 0.0
- R2 Recall: 0.0
- R2 Fmeasure: 0.0
- Rl Precision: 0.0188
- Rl Recall: 0.0105
- Rl Fmeasure: 0.0133
## 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: 2
- eval_batch_size: 2
- 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 |
|:-------------:|:-----:|:------:|:---------------:|:------------:|:---------:|:-----------:|:------------:|:---------:|:-----------:|:------------:|:---------:|:-----------:|
| 7.0769 | 1.0 | 96942 | 7.5336 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 7.1014 | 2.0 | 193884 | 7.6800 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 7.0648 | 3.0 | 290826 | 8.1448 | 0.0188 | 0.0105 | 0.0133 | 0.0 | 0.0 | 0.0 | 0.0188 | 0.0105 | 0.0133 |
| 7.0594 | 4.0 | 387768 | 8.4518 | 0.0188 | 0.0105 | 0.0133 | 0.0 | 0.0 | 0.0 | 0.0188 | 0.0105 | 0.0133 |
| 7.0322 | 5.0 | 484710 | 8.6177 | 0.0188 | 0.0105 | 0.0133 | 0.0 | 0.0 | 0.0 | 0.0188 | 0.0105 | 0.0133 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2