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: 0.9002
- Bleu: 79.5906
- Em: 0.08
- Rm: 0.9565
- Gen Len: 48.48
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: 8
- 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: 10.0
Training results
| Training Loss | Epoch | Step | Bleu | Em | Gen Len | Validation Loss | Rm |
|---|---|---|---|---|---|---|---|
| 7.2445 | 0.83 | 2000 | 1.523 | 0.0 | 204.48 | 7.5619 | nan |
| 3.4458 | 1.66 | 4000 | 16.0372 | 0.0 | 76.36 | 3.4202 | nan |
| 2.2571 | 2.49 | 6000 | 34.5826 | 0.0 | 48.98 | 2.1971 | 0.8125 |
| 1.5696 | 3.32 | 8000 | 53.8822 | 0.0 | 48.7 | 1.6802 | 1.0 |
| 1.1359 | 4.15 | 10000 | 64.5591 | 0.02 | 45.2 | 1.3464 | 0.973 |
| 0.9994 | 4.98 | 12000 | 68.0869 | 0.02 | 47.76 | 1.0576 | 0.8889 |
| 0.7275 | 5.81 | 14000 | 74.1032 | 0.02 | 46.52 | 0.9522 | 0.9556 |
| 0.5868 | 6.64 | 16000 | 0.9307 | 71.6124 | 0.02 | 0.9556 | 47.52 |
| 0.4499 | 7.47 | 18000 | 0.8866 | 77.237 | 0.06 | 0.9574 | 46.0 |
| 0.3515 | 8.3 | 20000 | 0.9070 | 77.5798 | 0.08 | 0.9574 | 47.5 |
| 0.292 | 9.13 | 22000 | 0.8905 | 78.649 | 0.06 | 0.9574 | 47.96 |
| 0.2658 | 9.96 | 24000 | 0.9002 | 79.5906 | 0.08 | 0.9565 | 48.48 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3