leavoigt commited on
Commit
bdd9b5c
1 Parent(s): 668dcf2

Add SetFit model

Browse files
Files changed (3) hide show
  1. README.md +55 -57
  2. model_head.pkl +1 -1
  3. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,37 +15,35 @@ metrics:
15
  - F1-Score
16
  - accuracy
17
  widget:
18
- - text: Violence from intimate partners and male family members can escalate during
19
- emergencies. This tends to increase as the crisis worsens, and men have lost their
20
- jobs and status particularly in communities with traditional gender roles, and
21
- where family violence is normalised
22
- - text: Expand livelihood protection policies that assist vulnerable, low-income individuals
23
- to recover from damages associated with extreme weather events; provide support
24
- and protection for internally displaced persons, persons displaced across borders
25
- and host communities;. By 2026, draw up disaster recovery plans for all 22 municipalities
26
- with resource inventories, first response measures and actions (including on logistics)
27
- concerning humanitarian post-disaster needs.
28
- - text: recurrent droughts, (decrease in amount of rainfall from 550 to 400mm in the
29
- highlands), changes in seasonality that had resulted frequent crop failure, massive
30
- death of livestock, genetic erosion, extinction of endemic species, degradation
31
- of habitats and disequilibria in the ecosystem structure and function. The impact
32
- of climate change is manifested in recurrent droughts, desertification, sea level
33
- rise and increase in sea water temperature, depletion of ground water, widespread
34
- land degradation, and emergence of climate sensitive diseases.
35
- - text: They live in geographical regions and ecosystems that are the most vulnerable
36
- to climate change. These include polar regions, humid tropical forests, high mountains,
37
- small islands, coastal regions, and arid and semi-arid lands, among others. The
38
- impacts of climate change in such regions have strong implications for the ecosystem-based
39
- livelihoods on which many indigenous peoples depend. Moreover, in some regions
40
- such as the Pacific, the very existence of many indigenous territories is under
41
- threat from rising sea levels that not only pose a grave threat to indigenous
42
- peoples’ livelihoods but also to their cultures and ways of life.
43
- - text: Overcoming Poverty. Colombia, as a developing country, faces major socioeconomic
44
- challenges. According to the official figures of DANE, by 2014, the percentage
45
- of people in multidimensional poverty situation was 21.9% (this figure rises to
46
- 44.1% if we take into account only the rural population). For the same year, 28.5%
47
- of the population was found in a situation of monetary poverty (41.4% of the population
48
- in the case of the villages and rural centers scattered).
49
  pipeline_tag: text-classification
50
  inference: false
51
  base_model: sentence-transformers/all-mpnet-base-v2
@@ -61,28 +59,28 @@ model-index:
61
  split: test
62
  metrics:
63
  - type: Precision_micro
64
- value: 0.7972027972027972
65
  name: Precision_Micro
66
  - type: Precision_weighted
67
- value: 0.8053038510784989
68
  name: Precision_Weighted
69
  - type: Precision_samples
70
- value: 0.7972027972027972
71
  name: Precision_Samples
72
  - type: Recall_micro
73
- value: 0.7972027972027972
74
  name: Recall_Micro
75
  - type: Recall_weighted
76
- value: 0.7972027972027972
77
  name: Recall_Weighted
78
  - type: Recall_samples
79
- value: 0.7972027972027972
80
  name: Recall_Samples
81
  - type: F1-Score
82
- value: 0.7972027972027972
83
  name: F1-Score
84
  - type: accuracy
85
- value: 0.7972027972027972
86
  name: Accuracy
87
  ---
88
 
@@ -118,7 +116,7 @@ The model has been trained using an efficient few-shot learning technique that i
118
  ### Metrics
119
  | Label | Precision_Micro | Precision_Weighted | Precision_Samples | Recall_Micro | Recall_Weighted | Recall_Samples | F1-Score | Accuracy |
120
  |:--------|:----------------|:-------------------|:------------------|:-------------|:----------------|:---------------|:---------|:---------|
121
- | **all** | 0.7972 | 0.8053 | 0.7972 | 0.7972 | 0.7972 | 0.7972 | 0.7972 | 0.7972 |
122
 
123
  ## Uses
124
 
@@ -138,7 +136,7 @@ from setfit import SetFitModel
138
  # Download from the 🤗 Hub
139
  model = SetFitModel.from_pretrained("leavoigt/vulnerability_target")
140
  # Run inference
141
- preds = model("Violence from intimate partners and male family members can escalate during emergencies. This tends to increase as the crisis worsens, and men have lost their jobs and status particularly in communities with traditional gender roles, and where family violence is normalised")
142
  ```
143
 
144
  <!--
@@ -170,7 +168,7 @@ preds = model("Violence from intimate partners and male family members can escal
170
  ### Training Set Metrics
171
  | Training set | Min | Median | Max |
172
  |:-------------|:----|:--------|:----|
173
- | Word count | 15 | 71.9518 | 238 |
174
 
175
  ### Training Hyperparameters
176
  - batch_size: (16, 16)
@@ -193,23 +191,23 @@ preds = model("Violence from intimate partners and male family members can escal
193
  ### Training Results
194
  | Epoch | Step | Training Loss | Validation Loss |
195
  |:------:|:----:|:-------------:|:---------------:|
196
- | 0.0012 | 1 | 0.2559 | - |
197
- | 0.0602 | 50 | 0.2509 | - |
198
- | 0.1205 | 100 | 0.2595 | - |
199
- | 0.1807 | 150 | 0.0868 | - |
200
- | 0.2410 | 200 | 0.0302 | - |
201
- | 0.3012 | 250 | 0.0024 | - |
202
- | 0.3614 | 300 | 0.0225 | - |
203
- | 0.4217 | 350 | 0.0007 | - |
204
- | 0.4819 | 400 | 0.0004 | - |
205
- | 0.5422 | 450 | 0.0003 | - |
206
  | 0.6024 | 500 | 0.0002 | - |
207
- | 0.6627 | 550 | 0.0005 | - |
208
- | 0.7229 | 600 | 0.0319 | - |
209
- | 0.7831 | 650 | 0.0001 | - |
210
- | 0.8434 | 700 | 0.0104 | - |
211
  | 0.9036 | 750 | 0.0003 | - |
212
- | 0.9639 | 800 | 0.0009 | - |
213
 
214
  ### Framework Versions
215
  - Python: 3.10.12
 
15
  - F1-Score
16
  - accuracy
17
  widget:
18
+ - text: Amended proposal for a Regulation of the European Parliament and of the Council
19
+ on establishing the framework for achieving climate neutrality and amending Regulation
20
+ (EU) 2018/1999 (European Climate Law). COM(2020) 563 (currently undergoing the
21
+ EU internal legislative process)↩︎. Council conclusions of 7 March 2011 on European
22
+ Pact for Gender Equality (2011-2020)↩︎. Council conclusions of 9 April 2019, Towards
23
+ an ever more sustainable Union by 2030↩︎. Council conclusions of 15 May 2017 on
24
+ Indigenous Peoples↩︎. Regulation (EU) 2018/1999↩︎.
25
+ - text: 'Development of 15,000 ha of shallows and irrigated areas and their exploitation
26
+ for the intensive rice cultivation system. Agriculture, water. 705. 28. Development
27
+ of research on health and climate change: total of three activities. Health. 690.
28
+ 29. Audit of plans to develop all classified or protected forests for updating
29
+ purposes. Forests-land use. 685. 30. Strengthening of capabilities to forecast
30
+ and respond to phenomena associated with climate change: creation of an MT health
31
+ care monitoring centre. Health. 680. 31. Participative development of sustainable
32
+ land.'
33
+ - text: The Ministry of Health notes that any adaptation work should prioritise vulnerable
34
+ populations. It also considers that more work is needed in health system planning,
35
+ to accommodate a potential increase in migrants and refugees
36
+ - text: 'The overall outcome is to ensure that projects and programmes are gender
37
+ responsive: meaning that it aims to go beyond gender sensitivity to actively promote
38
+ gender equality and women’s empowerment. The country is committed to achieving
39
+ SDG 5: Gender equality by promoting low carbon development where men and women
40
+ contributions to climate change mitigation and adaptation are recognized and valued,
41
+ existing gender inequalities are reduced and opportunities for effective empowerment
42
+ for women are promoted.'
43
+ - text: Cities depend heavily on other cities and regions to provide them with indispensable
44
+ services such as food, water and energy and the infrastructure to deliver them.
45
+ Ecosystem services from surrounding regions provide fresh air, store or drain
46
+ flood water as well as drinking water
 
 
47
  pipeline_tag: text-classification
48
  inference: false
49
  base_model: sentence-transformers/all-mpnet-base-v2
 
59
  split: test
60
  metrics:
61
  - type: Precision_micro
62
+ value: 0.7692307692307693
63
  name: Precision_Micro
64
  - type: Precision_weighted
65
+ value: 0.7748199704721445
66
  name: Precision_Weighted
67
  - type: Precision_samples
68
+ value: 0.7692307692307693
69
  name: Precision_Samples
70
  - type: Recall_micro
71
+ value: 0.7692307692307693
72
  name: Recall_Micro
73
  - type: Recall_weighted
74
+ value: 0.7692307692307693
75
  name: Recall_Weighted
76
  - type: Recall_samples
77
+ value: 0.7692307692307693
78
  name: Recall_Samples
79
  - type: F1-Score
80
+ value: 0.7692307692307693
81
  name: F1-Score
82
  - type: accuracy
83
+ value: 0.7692307692307693
84
  name: Accuracy
85
  ---
86
 
 
116
  ### Metrics
117
  | Label | Precision_Micro | Precision_Weighted | Precision_Samples | Recall_Micro | Recall_Weighted | Recall_Samples | F1-Score | Accuracy |
118
  |:--------|:----------------|:-------------------|:------------------|:-------------|:----------------|:---------------|:---------|:---------|
119
+ | **all** | 0.7692 | 0.7748 | 0.7692 | 0.7692 | 0.7692 | 0.7692 | 0.7692 | 0.7692 |
120
 
121
  ## Uses
122
 
 
136
  # Download from the 🤗 Hub
137
  model = SetFitModel.from_pretrained("leavoigt/vulnerability_target")
138
  # Run inference
139
+ preds = model("The Ministry of Health notes that any adaptation work should prioritise vulnerable populations. It also considers that more work is needed in health system planning, to accommodate a potential increase in migrants and refugees")
140
  ```
141
 
142
  <!--
 
168
  ### Training Set Metrics
169
  | Training set | Min | Median | Max |
170
  |:-------------|:----|:--------|:----|
171
+ | Word count | 15 | 72.4819 | 238 |
172
 
173
  ### Training Hyperparameters
174
  - batch_size: (16, 16)
 
191
  ### Training Results
192
  | Epoch | Step | Training Loss | Validation Loss |
193
  |:------:|:----:|:-------------:|:---------------:|
194
+ | 0.0012 | 1 | 0.2938 | - |
195
+ | 0.0602 | 50 | 0.2188 | - |
196
+ | 0.1205 | 100 | 0.1733 | - |
197
+ | 0.1807 | 150 | 0.1578 | - |
198
+ | 0.2410 | 200 | 0.02 | - |
199
+ | 0.3012 | 250 | 0.0028 | - |
200
+ | 0.3614 | 300 | 0.0004 | - |
201
+ | 0.4217 | 350 | 0.0011 | - |
202
+ | 0.4819 | 400 | 0.0008 | - |
203
+ | 0.5422 | 450 | 0.0005 | - |
204
  | 0.6024 | 500 | 0.0002 | - |
205
+ | 0.6627 | 550 | 0.0002 | - |
206
+ | 0.7229 | 600 | 0.0004 | - |
207
+ | 0.7831 | 650 | 0.0332 | - |
208
+ | 0.8434 | 700 | 0.0003 | - |
209
  | 0.9036 | 750 | 0.0003 | - |
210
+ | 0.9639 | 800 | 0.0004 | - |
211
 
212
  ### Framework Versions
213
  - Python: 3.10.12
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21a68d4e0e07be270d3269ec0649d0450f5c2f5aacb912bb4381821794f08f6c
3
  size 13956
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50c1c8ee41837d2379a3431c1409a50a06470ea8c55aaefdf0b1eaa898a57cb
3
  size 13956
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c76b3427c76aa76bb48187a1b4a7f125229943b9887e4c2bae30dbed7753011e
3
  size 438016938
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc684736afdcca8e895c8635f3fe38976632dbfbe0f4ac1768927805f93f234c
3
  size 438016938