Hugging Face's logo

stulcrad
/
fine_tuned_BERT_cs_wikann

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
stulcrad commited on
Commit
325fd4f
•
1 Parent(s): 1456bd5

End of training

Browse files
Files changed (3) hide show
  1. README.md +17 -25
  2. model.safetensors +1 -1
  3. runs/Dec13_00-09-53_n26/events.out.tfevents.1702422595.n26.74777.0 +2 -2
README.md CHANGED
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the wikiann dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1618
21
- - Overall Accuracy: 0.9672
22
- - Overall F1: 0.9184
23
- - Overall Precision: 0.9155
24
- - Overall Recall: 0.9213
25
 
26
  ## Model description
27
 
@@ -40,9 +40,9 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 5e-05
44
- - train_batch_size: 8
45
- - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
@@ -50,23 +50,15 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Overall Accuracy | Overall F1 | Overall Precision | Overall Recall |
54
- |:-------------:|:-----:|:----:|:---------------:|:----------------:|:----------:|:-----------------:|:--------------:|
55
- | 0.3538 | 0.2 | 500 | 0.2330 | 0.9392 | 0.8365 | 0.8271 | 0.8461 |
56
- | 0.2331 | 0.4 | 1000 | 0.2291 | 0.9429 | 0.8536 | 0.8442 | 0.8633 |
57
- | 0.2093 | 0.6 | 1500 | 0.1936 | 0.9515 | 0.8720 | 0.8777 | 0.8663 |
58
- | 0.1976 | 0.8 | 2000 | 0.1728 | 0.9512 | 0.8673 | 0.8634 | 0.8714 |
59
- | 0.1911 | 1.0 | 2500 | 0.1811 | 0.9586 | 0.8911 | 0.8797 | 0.9027 |
60
- | 0.1245 | 1.2 | 3000 | 0.1771 | 0.9604 | 0.8977 | 0.8933 | 0.9022 |
61
- | 0.1219 | 1.4 | 3500 | 0.1731 | 0.9595 | 0.8965 | 0.8893 | 0.9039 |
62
- | 0.1102 | 1.6 | 4000 | 0.1721 | 0.9625 | 0.9060 | 0.9041 | 0.9078 |
63
- | 0.1203 | 1.8 | 4500 | 0.1538 | 0.9625 | 0.9038 | 0.9095 | 0.8981 |
64
- | 0.1105 | 2.0 | 5000 | 0.1562 | 0.9656 | 0.9120 | 0.9065 | 0.9177 |
65
- | 0.0601 | 2.2 | 5500 | 0.1700 | 0.9648 | 0.9113 | 0.9006 | 0.9222 |
66
- | 0.0579 | 2.4 | 6000 | 0.1569 | 0.9659 | 0.9140 | 0.9105 | 0.9176 |
67
- | 0.0571 | 2.6 | 6500 | 0.1595 | 0.9673 | 0.9168 | 0.9154 | 0.9183 |
68
- | 0.0504 | 2.8 | 7000 | 0.1664 | 0.9670 | 0.9174 | 0.9120 | 0.9228 |
69
- | 0.0588 | 3.0 | 7500 | 0.1618 | 0.9672 | 0.9184 | 0.9155 | 0.9213 |
70
 
71
 
72
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the wikiann dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1428
21
+ - Overall Precision: 0.9090
22
+ - Overall Recall: 0.9274
23
+ - Overall F1: 0.9181
24
+ - Overall Accuracy: 0.9673
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 2e-05
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 16
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|
55
+ | 0.3011 | 0.4 | 500 | 0.1781 | 0.8588 | 0.8721 | 0.8654 | 0.9501 |
56
+ | 0.1717 | 0.8 | 1000 | 0.1524 | 0.8733 | 0.9033 | 0.8880 | 0.9565 |
57
+ | 0.1307 | 1.2 | 1500 | 0.1443 | 0.9058 | 0.9051 | 0.9054 | 0.9639 |
58
+ | 0.0968 | 1.6 | 2000 | 0.1392 | 0.9075 | 0.9107 | 0.9091 | 0.9651 |
59
+ | 0.0974 | 2.0 | 2500 | 0.1352 | 0.9030 | 0.9201 | 0.9115 | 0.9647 |
60
+ | 0.0603 | 2.4 | 3000 | 0.1410 | 0.9091 | 0.9217 | 0.9154 | 0.9667 |
61
+ | 0.054 | 2.8 | 3500 | 0.1428 | 0.9090 | 0.9274 | 0.9181 | 0.9673 |
 
 
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22ef0bc59ef9a3abcec993c0bbb6da0af77b2e1b764f2265f163c1398ba96be9
3
  size 709096284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a96cd56f2f8342b2e54665696bb3db5926ca535340925dc1918da415309162b7
3
  size 709096284
runs/Dec13_00-09-53_n26/events.out.tfevents.1702422595.n26.74777.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f018df7f33b92e60c688cd3b27b5369b87a5fe521d88fb2d40cfdf754712010
3
- size 9344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad3fbbcff242c3dc13c9d395e65460e878d0d087a850783aef61bdbfc2e4292
3
+ size 9698