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: stsb
|
20 |
split: validation
|
@@ -22,7 +20,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Spearmanr
|
24 |
type: spearmanr
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -30,12 +28,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
# hBERTv1_new_pretrain_w_init__stsb
|
32 |
|
33 |
-
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init) on the
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 2.
|
36 |
-
- Pearson: 0.
|
37 |
-
- Spearmanr: 0.
|
38 |
-
- Combined Score: 0.
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -54,7 +52,7 @@ More information needed
|
|
54 |
### Training hyperparameters
|
55 |
|
56 |
The following hyperparameters were used during training:
|
57 |
-
- learning_rate:
|
58 |
- train_batch_size: 128
|
59 |
- eval_batch_size: 128
|
60 |
- seed: 10
|
@@ -67,14 +65,12 @@ The following hyperparameters were used during training:
|
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
|
70 |
-
|
|
71 |
-
| 2.
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
| 2.1933 | 7.0 | 315 | 2.3738 | 0.0495 | 0.0497 | 0.0496 |
|
77 |
-
| 2.2067 | 8.0 | 360 | 2.2834 | 0.0372 | -0.0148 | 0.0112 |
|
78 |
|
79 |
|
80 |
### 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: stsb
|
18 |
split: validation
|
|
|
20 |
metrics:
|
21 |
- name: Spearmanr
|
22 |
type: spearmanr
|
23 |
+
value: 0.4406348486823185
|
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_w_init__stsb
|
30 |
|
31 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init) on the glue dataset.
|
32 |
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 2.8004
|
34 |
+
- Pearson: 0.4571
|
35 |
+
- Spearmanr: 0.4406
|
36 |
+
- Combined Score: 0.4489
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 4e-05
|
56 |
- train_batch_size: 128
|
57 |
- eval_batch_size: 128
|
58 |
- seed: 10
|
|
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
|
68 |
+
| 2.5056 | 1.0 | 45 | 2.2584 | 0.0949 | 0.0892 | 0.0920 |
|
69 |
+
| 2.1254 | 2.0 | 90 | 2.6871 | 0.1250 | 0.1231 | 0.1241 |
|
70 |
+
| 1.9839 | 3.0 | 135 | 2.2709 | 0.1790 | 0.1840 | 0.1815 |
|
71 |
+
| 1.6299 | 4.0 | 180 | 2.5115 | 0.2691 | 0.2797 | 0.2744 |
|
72 |
+
| 1.3155 | 5.0 | 225 | 2.4555 | 0.3453 | 0.3437 | 0.3445 |
|
73 |
+
| 0.9686 | 6.0 | 270 | 2.8004 | 0.4571 | 0.4406 | 0.4489 |
|
|
|
|
|
74 |
|
75 |
|
76 |
### Framework versions
|