Model save
Browse files- README.md +85 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gpl-3.0
|
| 3 |
+
base_model: ckiplab/bert-base-chinese
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: bert-base-chinese-finetuned-QA-b8
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# bert-base-chinese-finetuned-QA-b8
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [ckiplab/bert-base-chinese](https://huggingface.co/ckiplab/bert-base-chinese) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.3405
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 3e-05
|
| 38 |
+
- train_batch_size: 2
|
| 39 |
+
- eval_batch_size: 2
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 4
|
| 42 |
+
- total_train_batch_size: 8
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 4
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
+
| 1.9325 | 0.14 | 500 | 1.2076 |
|
| 52 |
+
| 1.1199 | 0.29 | 1000 | 1.0315 |
|
| 53 |
+
| 1.0118 | 0.43 | 1500 | 0.9836 |
|
| 54 |
+
| 0.9398 | 0.58 | 2000 | 0.9762 |
|
| 55 |
+
| 0.9526 | 0.72 | 2500 | 0.9374 |
|
| 56 |
+
| 0.9142 | 0.87 | 3000 | 0.8783 |
|
| 57 |
+
| 0.8265 | 1.01 | 3500 | 0.9919 |
|
| 58 |
+
| 0.6091 | 1.16 | 4000 | 0.9613 |
|
| 59 |
+
| 0.6303 | 1.3 | 4500 | 0.9769 |
|
| 60 |
+
| 0.6161 | 1.45 | 5000 | 0.9882 |
|
| 61 |
+
| 0.6109 | 1.59 | 5500 | 0.9160 |
|
| 62 |
+
| 0.5887 | 1.73 | 6000 | 0.9105 |
|
| 63 |
+
| 0.5811 | 1.88 | 6500 | 0.9812 |
|
| 64 |
+
| 0.5638 | 2.02 | 7000 | 1.0669 |
|
| 65 |
+
| 0.4174 | 2.17 | 7500 | 1.2101 |
|
| 66 |
+
| 0.3958 | 2.31 | 8000 | 1.2186 |
|
| 67 |
+
| 0.4032 | 2.46 | 8500 | 1.1691 |
|
| 68 |
+
| 0.4183 | 2.6 | 9000 | 1.0890 |
|
| 69 |
+
| 0.4247 | 2.75 | 9500 | 1.0721 |
|
| 70 |
+
| 0.3917 | 2.89 | 10000 | 1.1714 |
|
| 71 |
+
| 0.3738 | 3.04 | 10500 | 1.1794 |
|
| 72 |
+
| 0.29 | 3.18 | 11000 | 1.2494 |
|
| 73 |
+
| 0.326 | 3.32 | 11500 | 1.2822 |
|
| 74 |
+
| 0.3076 | 3.47 | 12000 | 1.3214 |
|
| 75 |
+
| 0.3071 | 3.61 | 12500 | 1.2968 |
|
| 76 |
+
| 0.2797 | 3.76 | 13000 | 1.3410 |
|
| 77 |
+
| 0.3192 | 3.9 | 13500 | 1.3405 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.34.0
|
| 83 |
+
- Pytorch 1.13.1+cu116
|
| 84 |
+
- Datasets 2.14.5
|
| 85 |
+
- Tokenizers 0.14.1
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 406782121
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d61ac230d5697aae314e263e921e0d905093e8efa634d755b31210083a51f57
|
| 3 |
size 406782121
|