update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: chinese-bert-wwm-chinese_bert_wwm3
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# chinese-bert-wwm-chinese_bert_wwm3
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [hfl/chinese-bert-wwm](https://huggingface.co/hfl/chinese-bert-wwm) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.0000
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 2e-05
|
| 37 |
+
- train_batch_size: 16
|
| 38 |
+
- eval_batch_size: 16
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 30.0
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| No log | 1.0 | 287 | 0.0094 |
|
| 49 |
+
| 0.6238 | 2.0 | 574 | 0.0008 |
|
| 50 |
+
| 0.6238 | 3.0 | 861 | 0.0003 |
|
| 51 |
+
| 0.0074 | 4.0 | 1148 | 0.0002 |
|
| 52 |
+
| 0.0074 | 5.0 | 1435 | 0.0002 |
|
| 53 |
+
| 0.003 | 6.0 | 1722 | 0.0001 |
|
| 54 |
+
| 0.0019 | 7.0 | 2009 | 0.0001 |
|
| 55 |
+
| 0.0019 | 8.0 | 2296 | 0.0001 |
|
| 56 |
+
| 0.0014 | 9.0 | 2583 | 0.0001 |
|
| 57 |
+
| 0.0014 | 10.0 | 2870 | 0.0000 |
|
| 58 |
+
| 0.0012 | 11.0 | 3157 | 0.0000 |
|
| 59 |
+
| 0.0012 | 12.0 | 3444 | 0.0000 |
|
| 60 |
+
| 0.0011 | 13.0 | 3731 | 0.0000 |
|
| 61 |
+
| 0.0008 | 14.0 | 4018 | 0.0000 |
|
| 62 |
+
| 0.0008 | 15.0 | 4305 | 0.0000 |
|
| 63 |
+
| 0.0006 | 16.0 | 4592 | 0.0000 |
|
| 64 |
+
| 0.0006 | 17.0 | 4879 | 0.0000 |
|
| 65 |
+
| 0.0006 | 18.0 | 5166 | 0.0000 |
|
| 66 |
+
| 0.0006 | 19.0 | 5453 | 0.0000 |
|
| 67 |
+
| 0.0005 | 20.0 | 5740 | 0.0000 |
|
| 68 |
+
| 0.0003 | 21.0 | 6027 | 0.0000 |
|
| 69 |
+
| 0.0003 | 22.0 | 6314 | 0.0000 |
|
| 70 |
+
| 0.0003 | 23.0 | 6601 | 0.0000 |
|
| 71 |
+
| 0.0003 | 24.0 | 6888 | 0.0000 |
|
| 72 |
+
| 0.0003 | 25.0 | 7175 | 0.0000 |
|
| 73 |
+
| 0.0003 | 26.0 | 7462 | 0.0000 |
|
| 74 |
+
| 0.0002 | 27.0 | 7749 | 0.0000 |
|
| 75 |
+
| 0.0002 | 28.0 | 8036 | 0.0000 |
|
| 76 |
+
| 0.0002 | 29.0 | 8323 | 0.0000 |
|
| 77 |
+
| 0.0002 | 30.0 | 8610 | 0.0000 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.11.3
|
| 83 |
+
- Pytorch 1.9.1
|
| 84 |
+
- Datasets 1.13.3
|
| 85 |
+
- Tokenizers 0.10.3
|