mitra-mir commited on
Commit
33a241f
1 Parent(s): 6f72e57

Add SetFit model

Browse files
Files changed (3) hide show
  1. README.md +15 -25
  2. model.safetensors +1 -1
  3. model_head.pkl +1 -1
README.md CHANGED
@@ -32,7 +32,7 @@ model-index:
32
  split: test
33
  metrics:
34
  - type: accuracy
35
- value: 0.8337531486146096
36
  name: Accuracy
37
  ---
38
 
@@ -64,17 +64,17 @@ The model has been trained using an efficient few-shot learning technique that i
64
  - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
65
 
66
  ### Model Labels
67
- | Label | Examples |
68
- |:------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
69
- | 1.0 | <ul><li>'We believe that no company should prosper while violating the basic human rights of others whether through unlawful slavery, servitude, forced or compulsory labor, or otherwise exploitative means.'</li><li>'In addition to our onsite services, our ergonomics specialists provide ondemand virtual consulting to customers to help them assess their risks and offer effective solutions.'</li><li>'The Travelers Industrial Hygiene (IH) Laboratory, nationally accredited by the American Industrial Hygiene Association, provides specialized services to our commercial customers to help them understand occupational health exposures in order to minimize occupational diseases.'</li></ul> |
70
- | 0.0 | <ul><li>'The decreases in the current period were offset, in part, by increases in conference and training expenditures incurred.'</li><li>'Environmental Responsibility As a core part of our business, we continually monitor, assess and respond not only to the risks but also to the opportunities posed by changing climate conditions.'</li><li>'Revenue derived from sales outside the Americas region increased primarily due to an increase from system sales in EIMEA and Japan, and an increase from services in EIMEA, Asia Pacific, and China, mostly offset by a decrease from sales of systems in China, which was largely due to COVID19related restrictions that occurred during the first quarter of fiscal year 2023.'</li></ul> |
71
 
72
  ## Evaluation
73
 
74
  ### Metrics
75
  | Label | Accuracy |
76
  |:--------|:---------|
77
- | **all** | 0.8338 |
78
 
79
  ## Uses
80
 
@@ -92,7 +92,7 @@ Then you can load this model and run inference.
92
  from setfit import SetFitModel
93
 
94
  # Download from the 🤗 Hub
95
- model = SetFitModel.from_pretrained("mitra-mir/setfit-model-ESG-environmental")
96
  # Run inference
97
  preds = model("and importance of the climate crisis requires everyone to play their part.")
98
  ```
@@ -126,12 +126,12 @@ preds = model("and importance of the climate crisis requires everyone to play th
126
  ### Training Set Metrics
127
  | Training set | Min | Median | Max |
128
  |:-------------|:----|:--------|:----|
129
- | Word count | 3 | 25.4020 | 72 |
130
 
131
  | Label | Training Sample Count |
132
  |:------|:----------------------|
133
- | 0.0 | 145 |
134
- | 1.0 | 54 |
135
 
136
  ### Training Hyperparameters
137
  - batch_size: (16, 16)
@@ -155,26 +155,16 @@ preds = model("and importance of the climate crisis requires everyone to play th
155
  ### Training Results
156
  | Epoch | Step | Training Loss | Validation Loss |
157
  |:------:|:----:|:-------------:|:---------------:|
158
- | 0.0020 | 1 | 0.4091 | - |
159
- | 0.1004 | 50 | 0.1992 | - |
160
- | 0.2008 | 100 | 0.0104 | - |
161
- | 0.3012 | 150 | 0.0006 | - |
162
- | 0.4016 | 200 | 0.0003 | - |
163
  | 0.5020 | 250 | 0.0002 | - |
164
  | 0.6024 | 300 | 0.0002 | - |
165
  | 0.7028 | 350 | 0.0001 | - |
166
  | 0.8032 | 400 | 0.0001 | - |
167
  | 0.9036 | 450 | 0.0001 | - |
168
- | 0.0020 | 1 | 0.25 | - |
169
- | 0.1004 | 50 | 0.349 | - |
170
- | 0.2008 | 100 | 0.047 | - |
171
- | 0.3012 | 150 | 0.0172 | - |
172
- | 0.4016 | 200 | 0.0023 | - |
173
- | 0.5020 | 250 | 0.0002 | - |
174
- | 0.6024 | 300 | 0.0002 | - |
175
- | 0.7028 | 350 | 0.0003 | - |
176
- | 0.8032 | 400 | 0.0001 | - |
177
- | 0.9036 | 450 | 0.0001 | - |
178
 
179
  ### Framework Versions
180
  - Python: 3.11.6
 
32
  split: test
33
  metrics:
34
  - type: accuracy
35
+ value: 0.7909319899244333
36
  name: Accuracy
37
  ---
38
 
 
64
  - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
65
 
66
  ### Model Labels
67
+ | Label | Examples |
68
+ |:------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
69
+ | 0.0 | <ul><li>'The concentration of our sales in our fourth fiscal quarter increases this impact as the revenue impact of most fourth fiscal quarter subscription sales will not be realized until the following fiscal year.'</li><li>'The deposit insurance fund of the FDIC insures deposit accounts in HomeTrust Bank up to 250,000 per separately insured deposit ownership right or category.'</li><li>'On 19 October 2020 the Company entered into a 25 million revolving credit facility agreement with State Street Bank International GmbH.'</li></ul> |
70
+ | 1.0 | <ul><li>'The IH Laboratory supports our field organization and offers our customers a wide array of sampling and analysis protocols based on Occupational Safety and Health Administration (OSHA) and National Institute for Occupational Safety and Health methodologies.'</li><li>'We partnered with the Fair Wage Network to increase our understanding of the different definitions of fair wages and to benchmark against their extensive fair and living wage database.'</li><li>'Strategy is to ensure all our employees worldwide earn at least a fair wage.'</li></ul> |
71
 
72
  ## Evaluation
73
 
74
  ### Metrics
75
  | Label | Accuracy |
76
  |:--------|:---------|
77
+ | **all** | 0.7909 |
78
 
79
  ## Uses
80
 
 
92
  from setfit import SetFitModel
93
 
94
  # Download from the 🤗 Hub
95
+ model = SetFitModel.from_pretrained("mitra-mir/setfit-model-ESG-social")
96
  # Run inference
97
  preds = model("and importance of the climate crisis requires everyone to play their part.")
98
  ```
 
126
  ### Training Set Metrics
127
  | Training set | Min | Median | Max |
128
  |:-------------|:----|:--------|:----|
129
+ | Word count | 4 | 24.5578 | 112 |
130
 
131
  | Label | Training Sample Count |
132
  |:------|:----------------------|
133
+ | 0.0 | 147 |
134
+ | 1.0 | 52 |
135
 
136
  ### Training Hyperparameters
137
  - batch_size: (16, 16)
 
155
  ### Training Results
156
  | Epoch | Step | Training Loss | Validation Loss |
157
  |:------:|:----:|:-------------:|:---------------:|
158
+ | 0.0020 | 1 | 0.4072 | - |
159
+ | 0.1004 | 50 | 0.2038 | - |
160
+ | 0.2008 | 100 | 0.0155 | - |
161
+ | 0.3012 | 150 | 0.0003 | - |
162
+ | 0.4016 | 200 | 0.0002 | - |
163
  | 0.5020 | 250 | 0.0002 | - |
164
  | 0.6024 | 300 | 0.0002 | - |
165
  | 0.7028 | 350 | 0.0001 | - |
166
  | 0.8032 | 400 | 0.0001 | - |
167
  | 0.9036 | 450 | 0.0001 | - |
 
 
 
 
 
 
 
 
 
 
168
 
169
  ### Framework Versions
170
  - Python: 3.11.6
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd3b1582e58bc53f59b52d8cad2f826ff9c3cdf036b3fe5dbf925f1d2c63b8be
3
  size 437967672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50da4ffd74a3288675a738297bf886452f4464cc3c09aa0f31dff93dac0c676e
3
  size 437967672
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe92f91d771b6ab8d8e49c0e15a1390fa36f80d478503309fe6bbff118bb3859
3
  size 6959
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7907f3692e3f72319578bb211d48e9bf90fbfe22333a29766170eed685fe548b
3
  size 6959