update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- glue
|
6 |
+
metrics:
|
7 |
+
- spearmanr
|
8 |
+
model-index:
|
9 |
+
- name: hBERTv1_stsb
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Text Classification
|
13 |
+
type: text-classification
|
14 |
+
dataset:
|
15 |
+
name: glue
|
16 |
+
type: glue
|
17 |
+
config: stsb
|
18 |
+
split: validation
|
19 |
+
args: stsb
|
20 |
+
metrics:
|
21 |
+
- name: Spearmanr
|
22 |
+
type: spearmanr
|
23 |
+
value: 0.6941784502109372
|
24 |
+
---
|
25 |
+
|
26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
27 |
+
should probably proofread and complete it, then remove this comment. -->
|
28 |
+
|
29 |
+
# hBERTv1_stsb
|
30 |
+
|
31 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the glue dataset.
|
32 |
+
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 1.2614
|
34 |
+
- Pearson: 0.6982
|
35 |
+
- Spearmanr: 0.6942
|
36 |
+
- Combined Score: 0.6962
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 256
|
57 |
+
- eval_batch_size: 256
|
58 |
+
- seed: 10
|
59 |
+
- distributed_type: multi-GPU
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- num_epochs: 50
|
63 |
+
- mixed_precision_training: Native AMP
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|
68 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
|
69 |
+
| 4.0796 | 1.0 | 23 | 2.3017 | 0.0761 | 0.0547 | 0.0654 |
|
70 |
+
| 2.0746 | 2.0 | 46 | 2.6181 | 0.0850 | 0.0772 | 0.0811 |
|
71 |
+
| 1.9142 | 3.0 | 69 | 2.2963 | 0.1878 | 0.1852 | 0.1865 |
|
72 |
+
| 1.6883 | 4.0 | 92 | 2.1866 | 0.4740 | 0.4777 | 0.4759 |
|
73 |
+
| 1.1166 | 5.0 | 115 | 1.9367 | 0.6319 | 0.6450 | 0.6384 |
|
74 |
+
| 0.7598 | 6.0 | 138 | 1.4188 | 0.6801 | 0.6888 | 0.6845 |
|
75 |
+
| 0.5453 | 7.0 | 161 | 1.2720 | 0.6988 | 0.7001 | 0.6994 |
|
76 |
+
| 0.3705 | 8.0 | 184 | 1.1154 | 0.7159 | 0.7156 | 0.7157 |
|
77 |
+
| 0.2976 | 9.0 | 207 | 1.6889 | 0.6754 | 0.6807 | 0.6780 |
|
78 |
+
| 0.2272 | 10.0 | 230 | 1.3627 | 0.6929 | 0.6899 | 0.6914 |
|
79 |
+
| 0.1966 | 11.0 | 253 | 1.1278 | 0.7195 | 0.7167 | 0.7181 |
|
80 |
+
| 0.1708 | 12.0 | 276 | 1.3476 | 0.7171 | 0.7165 | 0.7168 |
|
81 |
+
| 0.1529 | 13.0 | 299 | 1.2614 | 0.6982 | 0.6942 | 0.6962 |
|
82 |
+
|
83 |
+
|
84 |
+
### Framework versions
|
85 |
+
|
86 |
+
- Transformers 4.26.1
|
87 |
+
- Pytorch 1.14.0a0+410ce96
|
88 |
+
- Datasets 2.10.1
|
89 |
+
- Tokenizers 0.13.2
|