nguyenkhoa2407
commited on
Commit
•
6dcfb75
1
Parent(s):
09574a8
update model card README.md
Browse files
README.md
CHANGED
@@ -22,10 +22,10 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: F1
|
24 |
type: f1
|
25 |
-
value:
|
26 |
- name: Accuracy
|
27 |
type: accuracy
|
28 |
-
value:
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -35,10 +35,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
35 |
|
36 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the filter_v2 dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
-
- Loss: 0.
|
39 |
-
- F1:
|
40 |
-
- Roc Auc:
|
41 |
-
- Accuracy:
|
42 |
|
43 |
## Model description
|
44 |
|
@@ -57,7 +57,7 @@ More information needed
|
|
57 |
### Training hyperparameters
|
58 |
|
59 |
The following hyperparameters were used during training:
|
60 |
-
- learning_rate: 1.
|
61 |
- train_batch_size: 8
|
62 |
- eval_batch_size: 8
|
63 |
- seed: 42
|
@@ -69,26 +69,26 @@ The following hyperparameters were used during training:
|
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
|
93 |
|
94 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: F1
|
24 |
type: f1
|
25 |
+
value: 0.9666666666666667
|
26 |
- name: Accuracy
|
27 |
type: accuracy
|
28 |
+
value: 0.9375
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
35 |
|
36 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the filter_v2 dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.2721
|
39 |
+
- F1: 0.9667
|
40 |
+
- Roc Auc: 0.9772
|
41 |
+
- Accuracy: 0.9375
|
42 |
|
43 |
## Model description
|
44 |
|
|
|
57 |
### Training hyperparameters
|
58 |
|
59 |
The following hyperparameters were used during training:
|
60 |
+
- learning_rate: 1.5e-05
|
61 |
- train_batch_size: 8
|
62 |
- eval_batch_size: 8
|
63 |
- seed: 42
|
|
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
|
72 |
+
| 0.7591 | 1.0 | 14 | 0.6660 | 0.3137 | 0.5541 | 0.0 |
|
73 |
+
| 0.6506 | 2.0 | 28 | 0.5575 | 0.4706 | 0.6451 | 0.0625 |
|
74 |
+
| 0.5006 | 3.0 | 42 | 0.5010 | 0.5385 | 0.6846 | 0.0625 |
|
75 |
+
| 0.4416 | 4.0 | 56 | 0.4536 | 0.6538 | 0.7528 | 0.125 |
|
76 |
+
| 0.3815 | 5.0 | 70 | 0.4127 | 0.8070 | 0.8589 | 0.5 |
|
77 |
+
| 0.3468 | 6.0 | 84 | 0.3748 | 0.8621 | 0.8984 | 0.5625 |
|
78 |
+
| 0.3316 | 7.0 | 98 | 0.3487 | 0.8621 | 0.8984 | 0.5625 |
|
79 |
+
| 0.2834 | 8.0 | 112 | 0.3191 | 0.9 | 0.9317 | 0.6875 |
|
80 |
+
| 0.2565 | 9.0 | 126 | 0.2970 | 0.9492 | 0.9606 | 0.875 |
|
81 |
+
| 0.2241 | 10.0 | 140 | 0.2721 | 0.9667 | 0.9772 | 0.9375 |
|
82 |
+
| 0.214 | 11.0 | 154 | 0.2563 | 0.9492 | 0.9606 | 0.875 |
|
83 |
+
| 0.2041 | 12.0 | 168 | 0.2499 | 0.9492 | 0.9606 | 0.875 |
|
84 |
+
| 0.1831 | 13.0 | 182 | 0.2353 | 0.9492 | 0.9606 | 0.875 |
|
85 |
+
| 0.1852 | 14.0 | 196 | 0.2285 | 0.9492 | 0.9606 | 0.875 |
|
86 |
+
| 0.1636 | 15.0 | 210 | 0.2178 | 0.9667 | 0.9772 | 0.9375 |
|
87 |
+
| 0.1581 | 16.0 | 224 | 0.2110 | 0.9667 | 0.9772 | 0.9375 |
|
88 |
+
| 0.1473 | 17.0 | 238 | 0.2057 | 0.9492 | 0.9606 | 0.875 |
|
89 |
+
| 0.1479 | 18.0 | 252 | 0.2025 | 0.9667 | 0.9772 | 0.9375 |
|
90 |
+
| 0.141 | 19.0 | 266 | 0.2038 | 0.9667 | 0.9772 | 0.9375 |
|
91 |
+
| 0.1424 | 20.0 | 280 | 0.2032 | 0.9667 | 0.9772 | 0.9375 |
|
92 |
|
93 |
|
94 |
### Framework versions
|