Hugging Face's logo

GIZ
/
SECTOR-multilabel-climatebert_f

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ppsingh commited on
Commit
a25d05d
•
1 Parent(s): beff054

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +61 -19
README.md CHANGED
@@ -10,13 +10,13 @@ datasets:
10
  - GIZ/policy_classification
11
 
12
  co2_eq_emissions:
13
- emissions: 23.3572576873636
14
  source: codecarbon
15
  training_type: fine-tuning
16
  on_cloud: true
17
  cpu_model: Intel(R) Xeon(R) CPU @ 2.00GHz
18
  ram_total_size: 12.6747894287109
19
- hours_used: 0.529
20
  hardware_used: 1 x Tesla T4
21
  ---
22
 
@@ -52,21 +52,49 @@ More information needed
52
 
53
  ## Training and evaluation data
54
 
55
- - Training Dataset: 10031
56
  | Class | Positive Count of Class|
57
  |:-------------|:--------|
58
- | Action | 5416 |
59
- | Plans | 2140 |
60
- | Policy | 1396|
61
- | Target | 2911 |
62
-
63
- - Validation Dataset: 932
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
  | Class | Positive Count of Class|
65
  |:-------------|:--------|
66
- | Action | 513 |
67
- | Plans | 198 |
68
- | Policy | 122 |
69
- | Target | 256 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
  ## Training procedure
72
 
@@ -96,15 +124,29 @@ The following hyperparameters were used during training:
96
 
97
  |label | precision |recall |f1-score| support|
98
  |:-------------:|:---------:|:-----:|:------:|:------:|
99
- |Action |0.828 |0.807 |0.817 | 513.0 |
100
- |Plans |0.560 |0.707 |0.625 | 198.0 |
101
- |Policy |0.727 |0.786 |0.756 | 122.0 |
102
- |Target |0.741 |0.886 |0.808 | 256.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
103
 
104
  ### Environmental Impact
105
  Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
106
- - **Carbon Emitted**: 0.02335 kg of CO2
107
- - **Hours Used**: 0.529 hours
108
 
109
  ### Training Hardware
110
  - **On Cloud**: yes
 
10
  - GIZ/policy_classification
11
 
12
  co2_eq_emissions:
13
+ emissions: 28.6797414394632
14
  source: codecarbon
15
  training_type: fine-tuning
16
  on_cloud: true
17
  cpu_model: Intel(R) Xeon(R) CPU @ 2.00GHz
18
  ram_total_size: 12.6747894287109
19
+ hours_used: 0.706
20
  hardware_used: 1 x Tesla T4
21
  ---
22
 
 
52
 
53
  ## Training and evaluation data
54
 
55
+ - Training Dataset: 10123
56
  | Class | Positive Count of Class|
57
  |:-------------|:--------|
58
+ | Agriculture | 2235 |
59
+ | Buildings | 169 |
60
+ | Coastal Zone | 698|
61
+ | Cross-Cutting Area | 1853 |
62
+ | Disaster Risk Management (DRM) | 814 |
63
+ | Economy-wide | 873 |
64
+ | Education | 180|
65
+ | Energy | 2847 |
66
+ | Environment | 905 |
67
+ | Health | 662|
68
+ | Industries | 419 |
69
+ | LULUCF/Forestry | 1861|
70
+ | Social Development | 507 |
71
+ | Tourism | 192 |
72
+ | Transport | 1173|
73
+ | Urban | 558 |
74
+ | Waste | 714|
75
+ | Water | 1207 |
76
+
77
+ - Validation Dataset: 936
78
  | Class | Positive Count of Class|
79
  |:-------------|:--------|
80
+ | Agriculture | 200 |
81
+ | Buildings | 18 |
82
+ | Coastal Zone | 71|
83
+ | Cross-Cutting Area | 180 |
84
+ | Disaster Risk Management (DRM) | 85 |
85
+ | Economy-wide | 85 |
86
+ | Education | 23|
87
+ | Energy | 254 |
88
+ | Environment | 91 |
89
+ | Health | 68|
90
+ | Industries | 41 |
91
+ | LULUCF/Forestry | 193|
92
+ | Social Development | 56 |
93
+ | Tourism | 28 |
94
+ | Transport | 107|
95
+ | Urban | 51 |
96
+ | Waste | 59|
97
+ | Water | 106 |
98
 
99
  ## Training procedure
100
 
 
124
 
125
  |label | precision |recall |f1-score| support|
126
  |:-------------:|:---------:|:-----:|:------:|:------:|
127
+ | Agriculture | 0.720 | 0.850|0.780|200|
128
+ | Buildings | 0.636 |0.777|0.700|18|
129
+ | Coastal Zone | 0.562|0.760|0.646|71|
130
+ | Cross-Cutting Area | 0.569 |0.777|0.657|180|
131
+ | Disaster Risk Management (DRM) | 0.567 |0.694|0.624|85|
132
+ | Economy-wide | 0.461 |0.635| 0.534|85|
133
+ | Education | 0.608|0.608|0.608|23|
134
+ | Energy | 0.816 |0.838|0.827|254|
135
+ | Environment | 0.561 |0.703|0.624|91|
136
+ | Health | 0.708|0.750|0.728|68|
137
+ | Industries | 0.660 |0.902|0.762|41|
138
+ | LULUCF/Forestry | 0.676|0.844|0.751|193|
139
+ | Social Development | 0.593 | 0.678|0.633|56|
140
+ | Tourism | 0.551 |0.571|0.561|28|
141
+ | Transport | 0.700|0.766|0.732|107|
142
+ | Urban | 0.414 |0.568|0.479|51|
143
+ | Waste | 0.658|0.881|0.753|59|
144
+ | Water | 0.602 |0.773|0.677|106|
145
 
146
  ### Environmental Impact
147
  Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
148
+ - **Carbon Emitted**: 0.02867 kg of CO2
149
+ - **Hours Used**: 0.706 hours
150
 
151
  ### Training Hardware
152
  - **On Cloud**: yes