update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- glue
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
model-index:
|
10 |
+
- name: hBERTv1_new_pretrain_w_init_48_mrpc
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: glue
|
17 |
+
type: glue
|
18 |
+
config: mrpc
|
19 |
+
split: validation
|
20 |
+
args: mrpc
|
21 |
+
metrics:
|
22 |
+
- name: Accuracy
|
23 |
+
type: accuracy
|
24 |
+
value: 0.678921568627451
|
25 |
+
- name: F1
|
26 |
+
type: f1
|
27 |
+
value: 0.7827529021558872
|
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 |
+
# hBERTv1_new_pretrain_w_init_48_mrpc
|
34 |
+
|
35 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48) on the glue dataset.
|
36 |
+
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.7737
|
38 |
+
- Accuracy: 0.6789
|
39 |
+
- F1: 0.7828
|
40 |
+
- Combined Score: 0.7308
|
41 |
+
|
42 |
+
## Model description
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Intended uses & limitations
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training and evaluation data
|
51 |
+
|
52 |
+
More information needed
|
53 |
+
|
54 |
+
## Training procedure
|
55 |
+
|
56 |
+
### Training hyperparameters
|
57 |
+
|
58 |
+
The following hyperparameters were used during training:
|
59 |
+
- learning_rate: 4e-05
|
60 |
+
- train_batch_size: 128
|
61 |
+
- eval_batch_size: 128
|
62 |
+
- seed: 10
|
63 |
+
- distributed_type: multi-GPU
|
64 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
+
- lr_scheduler_type: linear
|
66 |
+
- num_epochs: 50
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
|
72 |
+
| 0.6607 | 1.0 | 29 | 0.6262 | 0.6838 | 0.8122 | 0.7480 |
|
73 |
+
| 0.6421 | 2.0 | 58 | 0.6368 | 0.6838 | 0.8122 | 0.7480 |
|
74 |
+
| 0.6411 | 3.0 | 87 | 0.6258 | 0.6838 | 0.8122 | 0.7480 |
|
75 |
+
| 0.6406 | 4.0 | 116 | 0.6422 | 0.6838 | 0.8122 | 0.7480 |
|
76 |
+
| 0.6364 | 5.0 | 145 | 0.6263 | 0.6838 | 0.8122 | 0.7480 |
|
77 |
+
| 0.6322 | 6.0 | 174 | 0.6253 | 0.6838 | 0.8122 | 0.7480 |
|
78 |
+
| 0.6398 | 7.0 | 203 | 0.6289 | 0.6838 | 0.8122 | 0.7480 |
|
79 |
+
| 0.6363 | 8.0 | 232 | 0.6267 | 0.6838 | 0.8122 | 0.7480 |
|
80 |
+
| 0.6374 | 9.0 | 261 | 0.6375 | 0.6838 | 0.8122 | 0.7480 |
|
81 |
+
| 0.6374 | 10.0 | 290 | 0.6248 | 0.6838 | 0.8122 | 0.7480 |
|
82 |
+
| 0.638 | 11.0 | 319 | 0.6262 | 0.6838 | 0.8122 | 0.7480 |
|
83 |
+
| 0.6353 | 12.0 | 348 | 0.6236 | 0.6838 | 0.8122 | 0.7480 |
|
84 |
+
| 0.6338 | 13.0 | 377 | 0.6263 | 0.6838 | 0.8122 | 0.7480 |
|
85 |
+
| 0.637 | 14.0 | 406 | 0.6250 | 0.6838 | 0.8122 | 0.7480 |
|
86 |
+
| 0.6375 | 15.0 | 435 | 0.6229 | 0.6838 | 0.8122 | 0.7480 |
|
87 |
+
| 0.7037 | 16.0 | 464 | 0.6438 | 0.6838 | 0.8122 | 0.7480 |
|
88 |
+
| 0.6198 | 17.0 | 493 | 0.6242 | 0.6961 | 0.8038 | 0.7499 |
|
89 |
+
| 0.5847 | 18.0 | 522 | 0.6260 | 0.6740 | 0.7742 | 0.7241 |
|
90 |
+
| 0.4983 | 19.0 | 551 | 0.7174 | 0.7034 | 0.8158 | 0.7596 |
|
91 |
+
| 0.4245 | 20.0 | 580 | 0.7737 | 0.6789 | 0.7828 | 0.7308 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- Transformers 4.29.2
|
97 |
+
- Pytorch 1.14.0a0+410ce96
|
98 |
+
- Datasets 2.12.0
|
99 |
+
- Tokenizers 0.13.3
|