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:
|
@@ -14,7 +12,7 @@ model-index:
|
|
14 |
name: Text Classification
|
15 |
type: text-classification
|
16 |
dataset:
|
17 |
-
name:
|
18 |
type: glue
|
19 |
config: wnli
|
20 |
split: validation
|
@@ -22,7 +20,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -30,10 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
# hBERTv1_new_pretrain_wnli
|
32 |
|
33 |
-
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new) on the
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -52,7 +50,7 @@ More information needed
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
-
- learning_rate:
|
56 |
- train_batch_size: 128
|
57 |
- eval_batch_size: 128
|
58 |
- seed: 10
|
@@ -65,12 +63,18 @@ The following hyperparameters were used during training:
|
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
|
|
12 |
name: Text Classification
|
13 |
type: text-classification
|
14 |
dataset:
|
15 |
+
name: glue
|
16 |
type: glue
|
17 |
config: wnli
|
18 |
split: validation
|
|
|
20 |
metrics:
|
21 |
- name: Accuracy
|
22 |
type: accuracy
|
23 |
+
value: 0.4647887323943662
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
28 |
|
29 |
# hBERTv1_new_pretrain_wnli
|
30 |
|
31 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new) on the glue dataset.
|
32 |
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 0.6922
|
34 |
+
- Accuracy: 0.4648
|
35 |
|
36 |
## Model description
|
37 |
|
|
|
50 |
### Training hyperparameters
|
51 |
|
52 |
The following hyperparameters were used during training:
|
53 |
+
- learning_rate: 4e-05
|
54 |
- train_batch_size: 128
|
55 |
- eval_batch_size: 128
|
56 |
- seed: 10
|
|
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
+
| 0.8538 | 1.0 | 5 | 0.6975 | 0.4366 |
|
67 |
+
| 0.7194 | 2.0 | 10 | 0.6922 | 0.5634 |
|
68 |
+
| 0.7223 | 3.0 | 15 | 0.6893 | 0.5634 |
|
69 |
+
| 0.713 | 4.0 | 20 | 0.7205 | 0.4366 |
|
70 |
+
| 0.7081 | 5.0 | 25 | 0.6865 | 0.5634 |
|
71 |
+
| 0.7028 | 6.0 | 30 | 0.7048 | 0.4366 |
|
72 |
+
| 0.697 | 7.0 | 35 | 0.6852 | 0.5634 |
|
73 |
+
| 0.7002 | 8.0 | 40 | 0.6967 | 0.4366 |
|
74 |
+
| 0.7017 | 9.0 | 45 | 0.7156 | 0.4366 |
|
75 |
+
| 0.702 | 10.0 | 50 | 0.6885 | 0.5634 |
|
76 |
+
| 0.6945 | 11.0 | 55 | 0.6927 | 0.4930 |
|
77 |
+
| 0.7002 | 12.0 | 60 | 0.6922 | 0.4648 |
|
78 |
|
79 |
|
80 |
### Framework versions
|