Hugging Face's logo

soniarocca31
/
prova_modello

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
soniarocca31 commited on
Commit
1384786
·
1 Parent(s): 64ea1c3

End of training

Browse files
Files changed (6) hide show
  1. README.md +12 -33
  2. config.json +3 -3
  3. model.safetensors +1 -1
  4. runs/Dec13_14-56-53_a046f3ebcea3/events.out.tfevents.1702479418.a046f3ebcea3.739.0 +3 -0
  5. runs/Dec13_15-22-16_a046f3ebcea3/events.out.tfevents.1702480937.a046f3ebcea3.739.1 +3 -0
  6. training_args.bin +2 -2
README.md CHANGED
@@ -24,13 +24,13 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.9879112133882781
28
  - name: Recall
29
  type: recall
30
- value: 0.9819168919464998
31
  - name: F1
32
  type: f1
33
- value: 0.984681052785158
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,10 +40,10 @@ should probably proofread and complete it, then remove this comment. -->
40
 
41
  This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the swiss_law_area_prediction dataset.
42
  It achieves the following results on the evaluation set:
43
- - Loss: 0.0961
44
- - Precision: 0.9879
45
- - Recall: 0.9819
46
- - F1: 0.9847
47
 
48
  ## Model description
49
 
@@ -74,32 +74,11 @@ The following hyperparameters were used during training:
74
 
75
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
76
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
77
- | 0.1371 | 0.08 | 100 | 0.4143 | 0.9470 | 0.9603 | 0.9530 |
78
- | 0.0066 | 0.15 | 200 | 0.1658 | 0.9727 | 0.9776 | 0.9751 |
79
- | 0.0299 | 0.23 | 300 | 0.2387 | 0.9649 | 0.9584 | 0.9611 |
80
- | 0.0759 | 0.31 | 400 | 0.1448 | 0.9700 | 0.9722 | 0.9708 |
81
- | 0.0007 | 0.38 | 500 | 0.1411 | 0.9710 | 0.9706 | 0.9706 |
82
- | 0.02 | 0.46 | 600 | 0.1305 | 0.9667 | 0.9708 | 0.9683 |
83
- | 0.1232 | 0.53 | 700 | 0.0746 | 0.9844 | 0.9817 | 0.9830 |
84
- | 0.012 | 0.61 | 800 | 0.1557 | 0.9688 | 0.9780 | 0.9731 |
85
- | 0.115 | 0.69 | 900 | 0.0647 | 0.9826 | 0.9824 | 0.9825 |
86
- | 0.0001 | 0.76 | 1000 | 0.1090 | 0.9812 | 0.9786 | 0.9797 |
87
- | 0.0002 | 0.84 | 1100 | 0.0849 | 0.9809 | 0.9808 | 0.9808 |
88
- | 0.0017 | 0.92 | 1200 | 0.1556 | 0.9760 | 0.9696 | 0.9721 |
89
- | 0.012 | 0.99 | 1300 | 0.0904 | 0.9855 | 0.9832 | 0.9843 |
90
- | 0.0001 | 1.07 | 1400 | 0.0963 | 0.9866 | 0.9825 | 0.9845 |
91
- | 0.0113 | 1.15 | 1500 | 0.0663 | 0.9847 | 0.9826 | 0.9835 |
92
- | 0.0005 | 1.22 | 1600 | 0.0645 | 0.9862 | 0.9834 | 0.9847 |
93
- | 0.0 | 1.3 | 1700 | 0.1229 | 0.9867 | 0.9757 | 0.9808 |
94
- | 0.0 | 1.37 | 1800 | 0.0715 | 0.9892 | 0.9845 | 0.9868 |
95
- | 0.0 | 1.45 | 1900 | 0.0795 | 0.9889 | 0.9837 | 0.9862 |
96
- | 0.0 | 1.53 | 2000 | 0.1029 | 0.9870 | 0.9791 | 0.9827 |
97
- | 0.0 | 1.6 | 2100 | 0.0967 | 0.9893 | 0.9832 | 0.9861 |
98
- | 0.1249 | 1.68 | 2200 | 0.0980 | 0.9873 | 0.9808 | 0.9838 |
99
- | 0.0 | 1.76 | 2300 | 0.0967 | 0.9880 | 0.9813 | 0.9844 |
100
- | 0.0728 | 1.83 | 2400 | 0.1013 | 0.9864 | 0.9806 | 0.9833 |
101
- | 0.1324 | 1.91 | 2500 | 0.0926 | 0.9877 | 0.9821 | 0.9847 |
102
- | 0.0649 | 1.98 | 2600 | 0.0961 | 0.9879 | 0.9819 | 0.9847 |
103
 
104
 
105
  ### Framework versions
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.9875458681646828
28
  - name: Recall
29
  type: recall
30
+ value: 0.9851501871487068
31
  - name: F1
32
  type: f1
33
+ value: 0.9862914035976681
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
40
 
41
  This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the swiss_law_area_prediction dataset.
42
  It achieves the following results on the evaluation set:
43
+ - Loss: 0.0821
44
+ - Precision: 0.9875
45
+ - Recall: 0.9852
46
+ - F1: 0.9863
47
 
48
  ## Model description
49
 
 
74
 
75
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
76
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
77
+ | 0.089 | 0.38 | 500 | 0.1169 | 0.9765 | 0.9777 | 0.9770 |
78
+ | 0.0011 | 0.76 | 1000 | 0.0962 | 0.9855 | 0.9802 | 0.9826 |
79
+ | 0.0001 | 1.15 | 1500 | 0.0993 | 0.9834 | 0.9801 | 0.9817 |
80
+ | 0.0002 | 1.53 | 2000 | 0.1114 | 0.9868 | 0.9782 | 0.9822 |
81
+ | 0.2093 | 1.91 | 2500 | 0.0821 | 0.9875 | 0.9852 | 0.9863 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
 
83
 
84
  ### Framework versions
config.json CHANGED
@@ -9,9 +9,9 @@
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
11
  "id2label": {
12
- "0": "LABEL_0",
13
- "1": "LABEL_1",
14
- "2": "LABEL_2"
15
  },
16
  "initializer_range": 0.02,
17
  "label2id": {
 
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
11
  "id2label": {
12
+ "0": "Civil",
13
+ "1": "Criminal",
14
+ "2": "Public"
15
  },
16
  "initializer_range": 0.02,
17
  "label2id": {
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e3ff50a2570ae137553914eb12cf3e0370c67e539405dd5290032b01ec448f5
3
  size 541320452
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7228013c0c6a87a7ee4148c4c7d077ef3337c01a78f16457437f05734ff3ae25
3
  size 541320452
runs/Dec13_14-56-53_a046f3ebcea3/events.out.tfevents.1702479418.a046f3ebcea3.739.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d63fdfc5375f99eedd04a8c1b502c5c929acfaccd8326f2bc861cf5801a571
3
+ size 47487
runs/Dec13_15-22-16_a046f3ebcea3/events.out.tfevents.1702480937.a046f3ebcea3.739.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2eda1802a2bedcd5143e96a5752c8e260a0a76e9a7ec1c284c208a04c32962
3
+ size 48063
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:924989d5b7362fb07455e770bf4ffd4c16becb13ffae3f630cd7dc5a74b4962d
3
- size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973cc57d66c29d3329af6eedb54f2ff070b0befca5dbf028e7650df7b9673ebc
3
+ size 4728