Hugging Face's logo

Aleksandar
/
distilbert-srb-ner-setimes

Token Classification
Transformers
PyTorch
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
Aleksandar commited on
Commit
1ece13f
•
1 Parent(s): 748982e

add model

Browse files
Files changed (4) hide show
  1. README.md +13 -18
  2. config.json +10 -10
  3. pytorch_model.bin +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ model_index:
17
  metric:
18
  name: Accuracy
19
  type: accuracy
20
- value: 0.9660941783583293
21
  ---
22
 
23
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,11 +27,11 @@ should probably proofread and complete it, then remove this comment. -->
27
 
28
  This model was trained from scratch on the None dataset.
29
  It achieves the following results on the evaluation set:
30
- - Loss: 0.1522
31
- - Precision: 0.8280
32
- - Recall: 0.8607
33
- - F1: 0.8440
34
- - Accuracy: 0.9661
35
 
36
  ## Model description
37
 
@@ -51,27 +51,22 @@ More information needed
51
 
52
  The following hyperparameters were used during training:
53
  - learning_rate: 2e-05
54
- - train_batch_size: 16
55
  - eval_batch_size: 8
56
  - seed: 42
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
- - num_epochs: 10
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
64
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
65
- | No log | 1.0 | 207 | 0.2240 | 0.6996 | 0.7200 | 0.7097 | 0.9375 |
66
- | No log | 2.0 | 414 | 0.1538 | 0.7501 | 0.7930 | 0.7710 | 0.9546 |
67
- | 0.2348 | 3.0 | 621 | 0.1459 | 0.7756 | 0.8115 | 0.7931 | 0.9576 |
68
- | 0.2348 | 4.0 | 828 | 0.1465 | 0.7918 | 0.8456 | 0.8178 | 0.9611 |
69
- | 0.0782 | 5.0 | 1035 | 0.1310 | 0.7981 | 0.8352 | 0.8162 | 0.9636 |
70
- | 0.0782 | 6.0 | 1242 | 0.1466 | 0.8103 | 0.8510 | 0.8301 | 0.9646 |
71
- | 0.0782 | 7.0 | 1449 | 0.1441 | 0.8222 | 0.8503 | 0.8360 | 0.9655 |
72
- | 0.0343 | 8.0 | 1656 | 0.1493 | 0.8265 | 0.8600 | 0.8429 | 0.9666 |
73
- | 0.0343 | 9.0 | 1863 | 0.1524 | 0.8236 | 0.8570 | 0.8400 | 0.9656 |
74
- | 0.0169 | 10.0 | 2070 | 0.1522 | 0.8280 | 0.8607 | 0.8440 | 0.9661 |
75
 
76
 
77
  ### Framework versions
 
17
  metric:
18
  name: Accuracy
19
  type: accuracy
20
+ value: 0.9558538945331398
21
  ---
22
 
23
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
27
 
28
  This model was trained from scratch on the None dataset.
29
  It achieves the following results on the evaluation set:
30
+ - Loss: 0.1509
31
+ - Precision: 0.7589
32
+ - Recall: 0.7883
33
+ - F1: 0.7733
34
+ - Accuracy: 0.9559
35
 
36
  ## Model description
37
 
 
51
 
52
  The following hyperparameters were used during training:
53
  - learning_rate: 2e-05
54
+ - train_batch_size: 32
55
  - eval_batch_size: 8
56
  - seed: 42
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
+ - num_epochs: 5
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
64
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
65
+ | No log | 1.0 | 104 | 0.2391 | 0.6625 | 0.6778 | 0.6701 | 0.9334 |
66
+ | No log | 2.0 | 208 | 0.1869 | 0.7314 | 0.7425 | 0.7369 | 0.9455 |
67
+ | No log | 3.0 | 312 | 0.1640 | 0.7513 | 0.7729 | 0.7620 | 0.9514 |
68
+ | No log | 4.0 | 416 | 0.1541 | 0.7606 | 0.7853 | 0.7728 | 0.9548 |
69
+ | 0.2087 | 5.0 | 520 | 0.1509 | 0.7589 | 0.7883 | 0.7733 | 0.9559 |
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
config.json CHANGED
@@ -9,16 +9,16 @@
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
11
  "id2label": {
12
- "0": "LABEL_0",
13
- "1": "LABEL_1",
14
- "2": "LABEL_2",
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": {
 
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
11
  "id2label": {
12
+ "0": "O",
13
+ "1": "B-per",
14
+ "2": "I-per",
15
+ "3": "B-org",
16
+ "4": "I-org",
17
+ "5": "B-loc",
18
+ "6": "I-loc",
19
+ "7": "B-misc",
20
+ "8": "I-misc",
21
+ "9": "B-deriv-per"
22
  },
23
  "initializer_range": 0.02,
24
  "label2id": {
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e743efaaa3003240e4e06bb7af40efa05482920c9e09104a9fb3178220b0126f
3
  size 326147573
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac6f7eb8668faa4e931380cb493de0990d3b135fcb1228579e40edc9e339181e
3
  size 326147573
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f536dd40afb0defadb2b81bdbc8a9bd7dece9987a1d8b6b7ee3bbfcbfdfd3ef
3
  size 2735
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0ead48b115175ea32a86cffeced55641202d6018c09c8ae5d58bc684047d6b7
3
  size 2735