saattrupdan
commited on
Commit
•
4e03af4
1
Parent(s):
88a1b98
update model card README.md
Browse files
README.md
CHANGED
@@ -1,27 +1,33 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
model-index:
|
6 |
- name: contract-ner-model-da
|
7 |
-
results:
|
8 |
-
- task:
|
9 |
-
type: token-classification
|
10 |
-
name: Token Classification
|
11 |
-
widget:
|
12 |
-
- "Medarbejderen ansættes til 35.000,00 kr. om måneden og arbejdsstedet er Supergaden 21, 2000 Frederiksberg."
|
13 |
-
inference:
|
14 |
-
parameters:
|
15 |
-
aggregation_strategy: "first"
|
16 |
---
|
17 |
|
|
|
|
|
|
|
18 |
# contract-ner-model-da
|
19 |
|
20 |
-
This model is a fine-tuned version of [
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 0.
|
23 |
-
- Micro F1: 0.
|
24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
|
26 |
## Training procedure
|
27 |
|
@@ -36,33 +42,56 @@ The following hyperparameters were used during training:
|
|
36 |
- total_train_batch_size: 32
|
37 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
- lr_scheduler_type: linear
|
39 |
-
- lr_scheduler_warmup_steps:
|
40 |
-
- num_epochs:
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
-
| Training Loss | Epoch
|
45 |
-
|
46 |
-
|
|
47 |
-
| 0.
|
48 |
-
| 0.
|
49 |
-
| 0.
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.0004 |
|
61 |
-
| 0.0003 |
|
62 |
-
| 0.0003 |
|
63 |
-
| 0.0003 |
|
64 |
-
| 0.
|
65 |
-
| 0.0002 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
|
68 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: cc-by-4.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
model-index:
|
6 |
- name: contract-ner-model-da
|
7 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
# contract-ner-model-da
|
14 |
|
15 |
+
This model is a fine-tuned version of [NbAiLab/nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.0213
|
18 |
+
- Micro F1: 0.9217
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
|
32 |
## Training procedure
|
33 |
|
|
|
42 |
- total_train_batch_size: 32
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 201
|
46 |
+
- num_epochs: 500
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Micro F1 |
|
51 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
52 |
+
| 0.2722 | 4.44 | 200 | 0.0318 | 0.6422 |
|
53 |
+
| 0.0182 | 8.88 | 400 | 0.0176 | 0.8321 |
|
54 |
+
| 0.0081 | 13.33 | 600 | 0.0202 | 0.8530 |
|
55 |
+
| 0.0045 | 17.77 | 800 | 0.0168 | 0.8839 |
|
56 |
+
| 0.0029 | 22.22 | 1000 | 0.0230 | 0.8758 |
|
57 |
+
| 0.0016 | 26.66 | 1200 | 0.0234 | 0.8690 |
|
58 |
+
| 0.0013 | 31.11 | 1400 | 0.0219 | 0.8853 |
|
59 |
+
| 0.0012 | 35.55 | 1600 | 0.0248 | 0.8831 |
|
60 |
+
| 0.0008 | 39.99 | 1800 | 0.0223 | 0.8979 |
|
61 |
+
| 0.0006 | 44.44 | 2000 | 0.0257 | 0.8752 |
|
62 |
+
| 0.0004 | 48.88 | 2200 | 0.0191 | 0.9018 |
|
63 |
+
| 0.0004 | 53.33 | 2400 | 0.0244 | 0.9029 |
|
64 |
+
| 0.0004 | 57.77 | 2600 | 0.0227 | 0.8986 |
|
65 |
+
| 0.0007 | 62.22 | 2800 | 0.0242 | 0.9004 |
|
66 |
+
| 0.0004 | 66.66 | 3000 | 0.0218 | 0.8937 |
|
67 |
+
| 0.0003 | 71.11 | 3200 | 0.0214 | 0.9039 |
|
68 |
+
| 0.0003 | 75.55 | 3400 | 0.0251 | 0.8958 |
|
69 |
+
| 0.0003 | 79.99 | 3600 | 0.0210 | 0.8943 |
|
70 |
+
| 0.0004 | 84.44 | 3800 | 0.0227 | 0.8995 |
|
71 |
+
| 0.0002 | 88.88 | 4000 | 0.0226 | 0.9116 |
|
72 |
+
| 0.0002 | 93.33 | 4200 | 0.0209 | 0.9121 |
|
73 |
+
| 0.0001 | 97.77 | 4400 | 0.0225 | 0.9105 |
|
74 |
+
| 0.0003 | 102.22 | 4600 | 0.0278 | 0.9039 |
|
75 |
+
| 0.0003 | 106.66 | 4800 | 0.0223 | 0.9009 |
|
76 |
+
| 0.0002 | 111.11 | 5000 | 0.0274 | 0.9123 |
|
77 |
+
| 0.0003 | 115.55 | 5200 | 0.0236 | 0.9123 |
|
78 |
+
| 0.0001 | 119.99 | 5400 | 0.0235 | 0.9059 |
|
79 |
+
| 0.0001 | 124.44 | 5600 | 0.0220 | 0.9165 |
|
80 |
+
| 0.0002 | 128.88 | 5800 | 0.0265 | 0.9021 |
|
81 |
+
| 0.0001 | 133.33 | 6000 | 0.0225 | 0.9029 |
|
82 |
+
| 0.0002 | 137.77 | 6200 | 0.0249 | 0.9166 |
|
83 |
+
| 0.0004 | 142.22 | 6400 | 0.0192 | 0.9128 |
|
84 |
+
| 0.0002 | 146.66 | 6600 | 0.0181 | 0.9313 |
|
85 |
+
| 0.0001 | 151.11 | 6800 | 0.0191 | 0.9269 |
|
86 |
+
| 0.0001 | 155.55 | 7000 | 0.0224 | 0.9154 |
|
87 |
+
| 0.0002 | 159.99 | 7200 | 0.0192 | 0.9171 |
|
88 |
+
| 0.0002 | 164.44 | 7400 | 0.0202 | 0.9217 |
|
89 |
+
| 0.0001 | 168.88 | 7600 | 0.0185 | 0.9171 |
|
90 |
+
| 0.0001 | 173.33 | 7800 | 0.0207 | 0.9201 |
|
91 |
+
| 0.0001 | 177.77 | 8000 | 0.0226 | 0.9121 |
|
92 |
+
| 0.0001 | 182.22 | 8200 | 0.0208 | 0.9191 |
|
93 |
+
| 0.0002 | 186.66 | 8400 | 0.0248 | 0.9184 |
|
94 |
+
| 0.0002 | 191.11 | 8600 | 0.0213 | 0.9217 |
|
95 |
|
96 |
|
97 |
### Framework versions
|