update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- glue
|
6 |
+
metrics:
|
7 |
+
- matthews_correlation
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: add_BERT_no_pretrain_cola
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: glue
|
17 |
+
type: glue
|
18 |
+
config: cola
|
19 |
+
split: validation
|
20 |
+
args: cola
|
21 |
+
metrics:
|
22 |
+
- name: Matthews Correlation
|
23 |
+
type: matthews_correlation
|
24 |
+
value: 0.0
|
25 |
+
- name: Accuracy
|
26 |
+
type: accuracy
|
27 |
+
value: 0.6912751793861389
|
28 |
+
---
|
29 |
+
|
30 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
31 |
+
should probably proofread and complete it, then remove this comment. -->
|
32 |
+
|
33 |
+
# add_BERT_no_pretrain_cola
|
34 |
+
|
35 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the glue dataset.
|
36 |
+
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.6277
|
38 |
+
- Matthews Correlation: 0.0
|
39 |
+
- Accuracy: 0.6913
|
40 |
+
|
41 |
+
## Model description
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Intended uses & limitations
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training and evaluation data
|
50 |
+
|
51 |
+
More information needed
|
52 |
+
|
53 |
+
## Training procedure
|
54 |
+
|
55 |
+
### Training hyperparameters
|
56 |
+
|
57 |
+
The following hyperparameters were used during training:
|
58 |
+
- learning_rate: 0.0005
|
59 |
+
- train_batch_size: 128
|
60 |
+
- eval_batch_size: 128
|
61 |
+
- seed: 10
|
62 |
+
- distributed_type: multi-GPU
|
63 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
+
- lr_scheduler_type: linear
|
65 |
+
- num_epochs: 50
|
66 |
+
- mixed_precision_training: Native AMP
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation | Accuracy |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|:--------:|
|
72 |
+
| 0.9141 | 1.0 | 67 | 0.6220 | 0.0 | 0.6913 |
|
73 |
+
| 0.6242 | 2.0 | 134 | 0.6458 | 0.0 | 0.6913 |
|
74 |
+
| 0.62 | 3.0 | 201 | 0.6181 | 0.0 | 0.6913 |
|
75 |
+
| 0.6121 | 4.0 | 268 | 0.6184 | 0.0 | 0.6913 |
|
76 |
+
| 0.6096 | 5.0 | 335 | 0.6188 | 0.0 | 0.6913 |
|
77 |
+
| 0.6098 | 6.0 | 402 | 0.6184 | 0.0 | 0.6913 |
|
78 |
+
| 0.6106 | 7.0 | 469 | 0.6185 | 0.0 | 0.6913 |
|
79 |
+
| 0.6117 | 8.0 | 536 | 0.6181 | 0.0 | 0.6913 |
|
80 |
+
| 0.6088 | 9.0 | 603 | 0.6262 | 0.0 | 0.6913 |
|
81 |
+
| 0.6086 | 10.0 | 670 | 0.6218 | 0.0 | 0.6913 |
|
82 |
+
| 0.6087 | 11.0 | 737 | 0.6184 | 0.0 | 0.6913 |
|
83 |
+
| 0.7274 | 12.0 | 804 | 0.6211 | 0.0 | 0.6913 |
|
84 |
+
| 1.183 | 13.0 | 871 | 0.6277 | 0.0 | 0.6913 |
|
85 |
+
|
86 |
+
|
87 |
+
### Framework versions
|
88 |
+
|
89 |
+
- Transformers 4.29.2
|
90 |
+
- Pytorch 1.14.0a0+410ce96
|
91 |
+
- Datasets 2.12.0
|
92 |
+
- Tokenizers 0.13.3
|