Commit
•
fda9330
1
Parent(s):
72e5c66
update model card README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Matthews Correlation
|
23 |
type: matthews_correlation
|
24 |
-
value: 0.
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss:
|
35 |
-
- Matthews Correlation: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -51,19 +51,38 @@ More information needed
|
|
51 |
### Training hyperparameters
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
-
- learning_rate:
|
55 |
- train_batch_size: 16
|
56 |
- eval_batch_size: 16
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
-
- num_epochs:
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
-
| Training Loss | Epoch | Step
|
65 |
-
|
66 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
|
69 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Matthews Correlation
|
23 |
type: matthews_correlation
|
24 |
+
value: 0.5779953180551635
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 1.4260
|
35 |
+
- Matthews Correlation: 0.5780
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
51 |
### Training hyperparameters
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 7.530341440816975e-06
|
55 |
- train_batch_size: 16
|
56 |
- eval_batch_size: 16
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 20
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|
65 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------------------:|
|
66 |
+
| 0.5137 | 1.0 | 535 | 0.4936 | 0.4808 |
|
67 |
+
| 0.362 | 2.0 | 1070 | 0.4270 | 0.5781 |
|
68 |
+
| 0.2679 | 3.0 | 1605 | 0.6409 | 0.5148 |
|
69 |
+
| 0.2046 | 4.0 | 2140 | 0.5658 | 0.5892 |
|
70 |
+
| 0.1736 | 5.0 | 2675 | 0.7711 | 0.5624 |
|
71 |
+
| 0.1378 | 6.0 | 3210 | 0.8053 | 0.5956 |
|
72 |
+
| 0.1137 | 7.0 | 3745 | 0.9714 | 0.5523 |
|
73 |
+
| 0.0903 | 8.0 | 4280 | 0.9119 | 0.5735 |
|
74 |
+
| 0.0839 | 9.0 | 4815 | 1.0448 | 0.5839 |
|
75 |
+
| 0.0629 | 10.0 | 5350 | 1.2056 | 0.5521 |
|
76 |
+
| 0.0577 | 11.0 | 5885 | 1.1880 | 0.5889 |
|
77 |
+
| 0.0505 | 12.0 | 6420 | 1.1722 | 0.5836 |
|
78 |
+
| 0.0519 | 13.0 | 6955 | 1.2863 | 0.5884 |
|
79 |
+
| 0.0369 | 14.0 | 7490 | 1.2971 | 0.5608 |
|
80 |
+
| 0.032 | 15.0 | 8025 | 1.3024 | 0.5785 |
|
81 |
+
| 0.0244 | 16.0 | 8560 | 1.3904 | 0.5737 |
|
82 |
+
| 0.0166 | 17.0 | 9095 | 1.4044 | 0.5778 |
|
83 |
+
| 0.0185 | 18.0 | 9630 | 1.4234 | 0.5650 |
|
84 |
+
| 0.0168 | 19.0 | 10165 | 1.4384 | 0.5727 |
|
85 |
+
| 0.0224 | 20.0 | 10700 | 1.4260 | 0.5780 |
|
86 |
|
87 |
|
88 |
### Framework versions
|