metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: chinese-bert-wwm-chinese_bert_wwm3
results: []
chinese-bert-wwm-chinese_bert_wwm3
This model is a fine-tuned version of hfl/chinese-bert-wwm on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 287 | 0.0094 |
| 0.6238 | 2.0 | 574 | 0.0008 |
| 0.6238 | 3.0 | 861 | 0.0003 |
| 0.0074 | 4.0 | 1148 | 0.0002 |
| 0.0074 | 5.0 | 1435 | 0.0002 |
| 0.003 | 6.0 | 1722 | 0.0001 |
| 0.0019 | 7.0 | 2009 | 0.0001 |
| 0.0019 | 8.0 | 2296 | 0.0001 |
| 0.0014 | 9.0 | 2583 | 0.0001 |
| 0.0014 | 10.0 | 2870 | 0.0000 |
| 0.0012 | 11.0 | 3157 | 0.0000 |
| 0.0012 | 12.0 | 3444 | 0.0000 |
| 0.0011 | 13.0 | 3731 | 0.0000 |
| 0.0008 | 14.0 | 4018 | 0.0000 |
| 0.0008 | 15.0 | 4305 | 0.0000 |
| 0.0006 | 16.0 | 4592 | 0.0000 |
| 0.0006 | 17.0 | 4879 | 0.0000 |
| 0.0006 | 18.0 | 5166 | 0.0000 |
| 0.0006 | 19.0 | 5453 | 0.0000 |
| 0.0005 | 20.0 | 5740 | 0.0000 |
| 0.0003 | 21.0 | 6027 | 0.0000 |
| 0.0003 | 22.0 | 6314 | 0.0000 |
| 0.0003 | 23.0 | 6601 | 0.0000 |
| 0.0003 | 24.0 | 6888 | 0.0000 |
| 0.0003 | 25.0 | 7175 | 0.0000 |
| 0.0003 | 26.0 | 7462 | 0.0000 |
| 0.0002 | 27.0 | 7749 | 0.0000 |
| 0.0002 | 28.0 | 8036 | 0.0000 |
| 0.0002 | 29.0 | 8323 | 0.0000 |
| 0.0002 | 30.0 | 8610 | 0.0000 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.9.1
- Datasets 1.13.3
- Tokenizers 0.10.3