ayameRushia
commited on
Commit
•
0b25a99
1
Parent(s):
97cddff
update model card README.md
Browse files
README.md
CHANGED
@@ -6,6 +6,9 @@ datasets:
|
|
6 |
- indonlu
|
7 |
metrics:
|
8 |
- accuracy
|
|
|
|
|
|
|
9 |
model-index:
|
10 |
- name: indobert-base-uncased-finetuned-indonlu-smsa
|
11 |
results:
|
@@ -19,7 +22,16 @@ model-index:
|
|
19 |
metrics:
|
20 |
- name: Accuracy
|
21 |
type: accuracy
|
22 |
-
value: 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
---
|
24 |
|
25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -29,8 +41,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
29 |
|
30 |
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the indonlu dataset.
|
31 |
It achieves the following results on the evaluation set:
|
32 |
-
- Loss: 0.
|
33 |
-
- Accuracy: 0.
|
|
|
|
|
|
|
34 |
|
35 |
## Model description
|
36 |
|
@@ -55,23 +70,23 @@ The following hyperparameters were used during training:
|
|
55 |
- seed: 42
|
56 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
- lr_scheduler_type: linear
|
58 |
-
- lr_scheduler_warmup_steps:
|
59 |
- num_epochs: 10
|
60 |
|
61 |
### Training results
|
62 |
|
63 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
64 |
-
|
65 |
-
| No log | 1.0 | 344 | 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
6 |
- indonlu
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
+
- f1
|
10 |
+
- precision
|
11 |
+
- recall
|
12 |
model-index:
|
13 |
- name: indobert-base-uncased-finetuned-indonlu-smsa
|
14 |
results:
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.9301587301587302
|
26 |
+
- name: F1
|
27 |
+
type: f1
|
28 |
+
value: 0.9066105299178986
|
29 |
+
- name: Precision
|
30 |
+
type: precision
|
31 |
+
value: 0.8992078788375845
|
32 |
+
- name: Recall
|
33 |
+
type: recall
|
34 |
+
value: 0.9147307323234121
|
35 |
---
|
36 |
|
37 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
41 |
|
42 |
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the indonlu dataset.
|
43 |
It achieves the following results on the evaluation set:
|
44 |
+
- Loss: 0.2277
|
45 |
+
- Accuracy: 0.9302
|
46 |
+
- F1: 0.9066
|
47 |
+
- Precision: 0.8992
|
48 |
+
- Recall: 0.9147
|
49 |
|
50 |
## Model description
|
51 |
|
|
|
70 |
- seed: 42
|
71 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
72 |
- lr_scheduler_type: linear
|
73 |
+
- lr_scheduler_warmup_steps: 1500
|
74 |
- num_epochs: 10
|
75 |
|
76 |
### Training results
|
77 |
|
78 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
79 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
80 |
+
| No log | 1.0 | 344 | 0.3831 | 0.8476 | 0.7715 | 0.7817 | 0.7627 |
|
81 |
+
| 0.4167 | 2.0 | 688 | 0.2809 | 0.8905 | 0.8406 | 0.8699 | 0.8185 |
|
82 |
+
| 0.2624 | 3.0 | 1032 | 0.2254 | 0.9230 | 0.8842 | 0.9004 | 0.8714 |
|
83 |
+
| 0.2624 | 4.0 | 1376 | 0.2378 | 0.9238 | 0.8797 | 0.9180 | 0.8594 |
|
84 |
+
| 0.1865 | 5.0 | 1720 | 0.2277 | 0.9302 | 0.9066 | 0.8992 | 0.9147 |
|
85 |
+
| 0.1217 | 6.0 | 2064 | 0.2444 | 0.9262 | 0.8981 | 0.9013 | 0.8957 |
|
86 |
+
| 0.1217 | 7.0 | 2408 | 0.2985 | 0.9286 | 0.8999 | 0.9035 | 0.8971 |
|
87 |
+
| 0.0847 | 8.0 | 2752 | 0.3397 | 0.9278 | 0.8969 | 0.9090 | 0.8871 |
|
88 |
+
| 0.0551 | 9.0 | 3096 | 0.3542 | 0.9270 | 0.8961 | 0.9010 | 0.8924 |
|
89 |
+
| 0.0551 | 10.0 | 3440 | 0.3862 | 0.9222 | 0.8895 | 0.8970 | 0.8846 |
|
90 |
|
91 |
|
92 |
### Framework versions
|