Aleksandar commited on
Commit
7a3247d
1 Parent(s): 396270b
Files changed (4) hide show
  1. README.md +27 -40
  2. config.json +2 -8
  3. pytorch_model.bin +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -2,24 +2,26 @@
2
  tags:
3
  - generated_from_trainer
4
  datasets:
5
- - setimes
6
  metrics:
7
  - precision
8
  - recall
9
  - f1
10
  - accuracy
11
- language:
12
- - sr
13
  model_index:
14
  - name: distilbert-srb-ner
15
  results:
16
  - task:
17
  name: Token Classification
18
  type: token-classification
 
 
 
 
19
  metric:
20
  name: Accuracy
21
  type: accuracy
22
- value: 0.966779551685212
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,40 +29,25 @@ should probably proofread and complete it, then remove this comment. -->
27
 
28
  # distilbert-srb-ner
29
 
30
- This model was finetuned from Aleksandar/distilbert-srb-cased-oscar on the setimes.SR dataset.
31
-
32
  It achieves the following results on the evaluation set:
33
- - Loss: 0.1531
34
- - Precision: 0.8296
35
- - Recall: 0.8593
36
- - F1: 0.8442
37
- - Accuracy: 0.9668
38
 
39
  ## Model description
40
 
41
- Finetuned model of Aleksandar/distilbert-srb-cased-oscar on settimes.SR dataset
42
 
43
  ## Intended uses & limitations
44
 
45
- | Tag (IOB) | Numerical representation | Meaning (Beginning = B., Inside = I.) |
46
- |-------------|--------------------------|------------------------------------------|
47
- | O | 0 | Other |
48
- | B-per | 1 | B.Person |
49
- | I-per | 2 | I. Person |
50
- | B-org | 3 | B. organization |
51
- | I-org | 4 | I. organization |
52
- | B-loc | 5 | B. location |
53
- | I-loc | 6 | I. location |
54
- | B-misc | 7 | B. Miscellaneous |
55
- | I-misc | 8 | I. Miscellaneous |
56
- | B-deriv-per | 9 | B. Derived Person |
57
-
58
- MIT license
59
 
60
  ## Training and evaluation data
61
 
62
- Training was performed with seqeval as the evaluation metric.
63
- 0.15% of dataset (setimes.SR) was used as validation dataset.
64
 
65
  ## Training procedure
66
 
@@ -77,18 +64,18 @@ The following hyperparameters were used during training:
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | No log | 1.0 | 207 | 0.2235 | 0.7038 | 0.7314 | 0.7174 | 0.9381 |
83
- | No log | 2.0 | 414 | 0.1538 | 0.7565 | 0.7937 | 0.7746 | 0.9548 |
84
- | 0.2327 | 3.0 | 621 | 0.1467 | 0.7863 | 0.8171 | 0.8014 | 0.9594 |
85
- | 0.2327 | 4.0 | 828 | 0.1398 | 0.8009 | 0.8526 | 0.8260 | 0.9630 |
86
- | 0.0771 | 5.0 | 1035 | 0.1319 | 0.8021 | 0.8376 | 0.8195 | 0.9637 |
87
- | 0.0771 | 6.0 | 1242 | 0.1482 | 0.8098 | 0.8513 | 0.8300 | 0.9652 |
88
- | 0.0771 | 7.0 | 1449 | 0.1454 | 0.8234 | 0.8510 | 0.8370 | 0.9667 |
89
- | 0.0339 | 8.0 | 1656 | 0.1503 | 0.8310 | 0.8547 | 0.8427 | 0.9663 |
90
- | 0.0339 | 9.0 | 1863 | 0.1525 | 0.8279 | 0.8587 | 0.8430 | 0.9661 |
91
- | 0.0169 | 10.0 | 2070 | 0.1531 | 0.8296 | 0.8593 | 0.8442 | 0.9668 |
92
 
93
 
94
  ### Framework versions
 
2
  tags:
3
  - generated_from_trainer
4
  datasets:
5
+ - wikiann
6
  metrics:
7
  - precision
8
  - recall
9
  - f1
10
  - accuracy
 
 
11
  model_index:
12
  - name: distilbert-srb-ner
13
  results:
14
  - task:
15
  name: Token Classification
16
  type: token-classification
17
+ dataset:
18
+ name: wikiann
19
+ type: wikiann
20
+ args: sr
21
  metric:
22
  name: Accuracy
23
  type: accuracy
24
+ value: 0.9570619691726958
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  # distilbert-srb-ner
31
 
32
+ This model was trained from scratch on the wikiann dataset.
 
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.2532
35
+ - Precision: 0.8859
36
+ - Recall: 0.9066
37
+ - F1: 0.8962
38
+ - Accuracy: 0.9571
39
 
40
  ## Model description
41
 
42
+ More information needed
43
 
44
  ## Intended uses & limitations
45
 
46
+ More information needed
 
 
 
 
 
 
 
 
 
 
 
 
 
47
 
48
  ## Training and evaluation data
49
 
50
+ More information needed
 
51
 
52
  ## Training procedure
53
 
 
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
68
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
69
+ | 0.2615 | 1.0 | 1250 | 0.2126 | 0.8268 | 0.8327 | 0.8297 | 0.9319 |
70
+ | 0.1568 | 2.0 | 2500 | 0.1775 | 0.8695 | 0.8699 | 0.8697 | 0.9472 |
71
+ | 0.1017 | 3.0 | 3750 | 0.1718 | 0.8649 | 0.8857 | 0.8752 | 0.9504 |
72
+ | 0.066 | 4.0 | 5000 | 0.1906 | 0.8734 | 0.8930 | 0.8831 | 0.9530 |
73
+ | 0.0413 | 5.0 | 6250 | 0.2076 | 0.8805 | 0.8992 | 0.8897 | 0.9549 |
74
+ | 0.03 | 6.0 | 7500 | 0.2257 | 0.8758 | 0.9045 | 0.8899 | 0.9554 |
75
+ | 0.0213 | 7.0 | 8750 | 0.2286 | 0.8864 | 0.9015 | 0.8939 | 0.9556 |
76
+ | 0.0157 | 8.0 | 10000 | 0.2454 | 0.8874 | 0.9021 | 0.8947 | 0.9566 |
77
+ | 0.01 | 9.0 | 11250 | 0.2486 | 0.8878 | 0.9043 | 0.8960 | 0.9573 |
78
+ | 0.0076 | 10.0 | 12500 | 0.2532 | 0.8859 | 0.9066 | 0.8962 | 0.9571 |
79
 
80
 
81
  ### Framework versions
config.json CHANGED
@@ -15,10 +15,7 @@
15
  "3": "LABEL_3",
16
  "4": "LABEL_4",
17
  "5": "LABEL_5",
18
- "6": "LABEL_6",
19
- "7": "LABEL_7",
20
- "8": "LABEL_8",
21
- "9": "LABEL_9"
22
  },
23
  "initializer_range": 0.02,
24
  "label2id": {
@@ -28,10 +25,7 @@
28
  "LABEL_3": 3,
29
  "LABEL_4": 4,
30
  "LABEL_5": 5,
31
- "LABEL_6": 6,
32
- "LABEL_7": 7,
33
- "LABEL_8": 8,
34
- "LABEL_9": 9
35
  },
36
  "max_position_embeddings": 512,
37
  "model_type": "distilbert",
 
15
  "3": "LABEL_3",
16
  "4": "LABEL_4",
17
  "5": "LABEL_5",
18
+ "6": "LABEL_6"
 
 
 
19
  },
20
  "initializer_range": 0.02,
21
  "label2id": {
 
25
  "LABEL_3": 3,
26
  "LABEL_4": 4,
27
  "LABEL_5": 5,
28
+ "LABEL_6": 6
 
 
 
29
  },
30
  "max_position_embeddings": 512,
31
  "model_type": "distilbert",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:267fd56b0d6ca6ed95da5412797b485185702f3d8bd75999489004dd7a2f03e2
3
- size 326147573
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec278e2e6a712f0e95da93b29462d1a5264e4ece5970fd9a42654c335808a512
3
+ size 326138357
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f82a22e0f04c36406249ccb577e1cb6c4688cb6856034ad08f6e349f5857562e
3
  size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0287ce65dbcec4df2dfdbdd416dd8bf259fb567921a3e005e33e8a703ae04a
3
  size 2671