update model card README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- en
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
@@ -15,7 +13,7 @@ model-index:
|
|
15 |
name: Text Classification
|
16 |
type: text-classification
|
17 |
dataset:
|
18 |
-
name:
|
19 |
type: glue
|
20 |
config: qqp
|
21 |
split: validation
|
@@ -23,10 +21,10 @@ model-index:
|
|
23 |
metrics:
|
24 |
- name: Accuracy
|
25 |
type: accuracy
|
26 |
-
value: 0.
|
27 |
- name: F1
|
28 |
type: f1
|
29 |
-
value: 0.
|
30 |
---
|
31 |
|
32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -34,12 +32,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
34 |
|
35 |
# hBERTv1_no_pretrain_qqp
|
36 |
|
37 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on the
|
38 |
It achieves the following results on the evaluation set:
|
39 |
-
- Loss: 0.
|
40 |
-
- Accuracy: 0.
|
41 |
-
- F1: 0.
|
42 |
-
- Combined Score: 0.
|
43 |
|
44 |
## Model description
|
45 |
|
@@ -58,31 +56,32 @@ More information needed
|
|
58 |
### Training hyperparameters
|
59 |
|
60 |
The following hyperparameters were used during training:
|
61 |
-
- learning_rate:
|
62 |
-
- train_batch_size:
|
63 |
-
- eval_batch_size:
|
64 |
- seed: 10
|
65 |
- distributed_type: multi-GPU
|
66 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
67 |
- lr_scheduler_type: linear
|
68 |
- num_epochs: 50
|
69 |
-
- mixed_precision_training: Native AMP
|
70 |
|
71 |
### Training results
|
72 |
|
73 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1
|
74 |
-
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
|
|
|
|
81 |
|
82 |
|
83 |
### Framework versions
|
84 |
|
85 |
-
- Transformers 4.
|
86 |
- Pytorch 1.14.0a0+410ce96
|
87 |
- Datasets 2.12.0
|
88 |
- Tokenizers 0.13.3
|
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
|
|
13 |
name: Text Classification
|
14 |
type: text-classification
|
15 |
dataset:
|
16 |
+
name: glue
|
17 |
type: glue
|
18 |
config: qqp
|
19 |
split: validation
|
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
+
value: 0.8193173386099432
|
25 |
- name: F1
|
26 |
type: f1
|
27 |
+
value: 0.7510988449350915
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
# hBERTv1_no_pretrain_qqp
|
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: 0.5245
|
38 |
+
- Accuracy: 0.8193
|
39 |
+
- F1: 0.7511
|
40 |
+
- Combined Score: 0.7852
|
41 |
|
42 |
## Model description
|
43 |
|
|
|
56 |
### Training hyperparameters
|
57 |
|
58 |
The following hyperparameters were used during training:
|
59 |
+
- learning_rate: 4e-05
|
60 |
+
- train_batch_size: 96
|
61 |
+
- eval_batch_size: 96
|
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 |
+
| 0.5334 | 1.0 | 3791 | 0.4826 | 0.7676 | 0.6650 | 0.7163 |
|
73 |
+
| 0.4491 | 2.0 | 7582 | 0.4493 | 0.7909 | 0.6926 | 0.7417 |
|
74 |
+
| 0.3866 | 3.0 | 11373 | 0.4402 | 0.7954 | 0.7269 | 0.7612 |
|
75 |
+
| 0.3657 | 4.0 | 15164 | 0.4990 | 0.7775 | 0.7211 | 0.7493 |
|
76 |
+
| 0.3708 | 5.0 | 18955 | 0.4744 | 0.8077 | 0.7273 | 0.7675 |
|
77 |
+
| 0.2948 | 6.0 | 22746 | 0.4693 | 0.8143 | 0.7379 | 0.7761 |
|
78 |
+
| 0.2546 | 7.0 | 26537 | 0.4507 | 0.8120 | 0.7578 | 0.7849 |
|
79 |
+
| 0.2225 | 8.0 | 30328 | 0.5245 | 0.8193 | 0.7511 | 0.7852 |
|
80 |
|
81 |
|
82 |
### Framework versions
|
83 |
|
84 |
+
- Transformers 4.30.2
|
85 |
- Pytorch 1.14.0a0+410ce96
|
86 |
- Datasets 2.12.0
|
87 |
- Tokenizers 0.13.3
|