Commit
•
c51a712
1
Parent(s):
b0a47bd
update model card README.md
Browse files
README.md
CHANGED
@@ -35,7 +35,7 @@ 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: 1.0
|
40 |
- Roc Auc: 1.0
|
41 |
- Accuracy: 1.0
|
@@ -57,33 +57,38 @@ 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
|
64 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
- lr_scheduler_type: linear
|
66 |
-
- num_epochs:
|
67 |
|
68 |
### Training results
|
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 |
|
88 |
|
89 |
### Framework versions
|
|
|
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: 0.2201
|
39 |
- F1: 1.0
|
40 |
- Roc Auc: 1.0
|
41 |
- Accuracy: 1.0
|
|
|
57 |
### Training hyperparameters
|
58 |
|
59 |
The following hyperparameters were used during training:
|
60 |
+
- learning_rate: 1.3e-05
|
61 |
- train_batch_size: 8
|
62 |
- eval_batch_size: 8
|
63 |
- seed: 42
|
64 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
- lr_scheduler_type: linear
|
66 |
+
- num_epochs: 20
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
|
72 |
+
| 0.6747 | 1.0 | 13 | 0.5868 | 0.5 | 0.6649 | 0.1818 |
|
73 |
+
| 0.5843 | 2.0 | 26 | 0.5321 | 0.4828 | 0.6575 | 0.0 |
|
74 |
+
| 0.5445 | 3.0 | 39 | 0.5029 | 0.6 | 0.7162 | 0.2727 |
|
75 |
+
| 0.4713 | 4.0 | 52 | 0.4667 | 0.6207 | 0.725 | 0.2727 |
|
76 |
+
| 0.4304 | 5.0 | 65 | 0.4321 | 0.6667 | 0.7575 | 0.4545 |
|
77 |
+
| 0.3983 | 6.0 | 78 | 0.3909 | 0.7500 | 0.8 | 0.4545 |
|
78 |
+
| 0.3433 | 7.0 | 91 | 0.3571 | 0.7879 | 0.825 | 0.5455 |
|
79 |
+
| 0.3186 | 8.0 | 104 | 0.3319 | 0.8235 | 0.85 | 0.6364 |
|
80 |
+
| 0.2967 | 9.0 | 117 | 0.3049 | 0.8571 | 0.875 | 0.6364 |
|
81 |
+
| 0.2739 | 10.0 | 130 | 0.2857 | 0.8571 | 0.875 | 0.6364 |
|
82 |
+
| 0.2535 | 11.0 | 143 | 0.2686 | 0.9474 | 0.95 | 0.8182 |
|
83 |
+
| 0.234 | 12.0 | 156 | 0.2501 | 0.9474 | 0.95 | 0.8182 |
|
84 |
+
| 0.2338 | 13.0 | 169 | 0.2358 | 0.9474 | 0.95 | 0.8182 |
|
85 |
+
| 0.2049 | 14.0 | 182 | 0.2201 | 1.0 | 1.0 | 1.0 |
|
86 |
+
| 0.1942 | 15.0 | 195 | 0.2098 | 1.0 | 1.0 | 1.0 |
|
87 |
+
| 0.1957 | 16.0 | 208 | 0.2063 | 1.0 | 1.0 | 1.0 |
|
88 |
+
| 0.1892 | 17.0 | 221 | 0.1969 | 1.0 | 1.0 | 1.0 |
|
89 |
+
| 0.1836 | 18.0 | 234 | 0.1919 | 1.0 | 1.0 | 1.0 |
|
90 |
+
| 0.1767 | 19.0 | 247 | 0.1909 | 1.0 | 1.0 | 1.0 |
|
91 |
+
| 0.1702 | 20.0 | 260 | 0.1901 | 1.0 | 1.0 | 1.0 |
|
92 |
|
93 |
|
94 |
### Framework versions
|