metadata
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: BERT2BERT_pretrained_LC-QuAD_2.0
results: []
BERT2BERT_pretrained_LC-QuAD_2.0
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0571
- Bleu: 75.7356
- Em: 0.0432
- Gen Len: 47.2896
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2500
- num_epochs: 8.0
Training results
| Training Loss | Epoch | Step | Bleu | Em | Gen Len | Validation Loss |
|---|---|---|---|---|---|---|
| 6.6044 | 1.4 | 2000 | 3.8045 | 0.0 | 158.8473 | 6.1713 |
| 3.032 | 2.8 | 4000 | 27.701 | 0.0 | 33.9568 | 2.9045 |
| 1.5893 | 4.19 | 6000 | 57.7509 | 0.0033 | 44.132 | 1.7327 |
| 1.0512 | 5.59 | 8000 | 71.1272 | 0.0241 | 46.0672 | 1.2382 |
| 0.7515 | 6.99 | 10000 | 1.0571 | 75.7356 | 0.0432 | 47.2896 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3