Add SetFit model

README.md

@@ -10,15 +10,24 @@ tags:
 - text-classification
 - generated_from_setfit_trainer
 widget:
-- text: and importance of the climate crisis requires everyone to play their part.
-- text: The Group has unused tax losses carried forward of 512m, primarily UK capital
-    losses, on which no deferred tax is recognised.
 - text: If an acquirer of shares is not prepared to provide this declaration, the
     Board may refuse to register him as a shareholder with the right to vote.
 - text: The Company will also make every effort to improve the effectiveness of its
     sustainability reporting.
 - text: The Company maintains sufficient liquidity and has a variety of contingent
     liquidity resources to manage liquidity across a range of economic scenarios.
+- text: If we are unable to continue as a going concern, we may have to liquidate
+    our assets and may receive less than the value at which those assets are carried
+    on our audited financial statements, and it is likely that investors will lose
+    all or a part of their investment.
+- text: In addition, factors such as failing to meet the expectations of or provide
+    quality medical care for our participants, adverse cyber or data security events,
+    adverse publicity or litigation involving or surrounding us, one of our centers
+    or our management, such as news articles and market rumors with respect to audits,
+    litigation and other processes described in these risk factors, have diminished
+    and may in the future diminish our reputation or that of our management and have
+    harmed and may in the future harm our brand, making it substantially more difficult
+    for us to attract new participants.
 inference: true
 model-index:
 - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
@@ -32,7 +41,7 @@ model-index:
       split: test
     metrics:
     - type: accuracy
-      value: 0.7657430730478589
+      value: 0.8261964735516373
       name: Accuracy
 ---
 
@@ -64,17 +73,17 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
 ### Model Labels
-| Label | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-|:------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| 0.0   | <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>'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></ul> |
-| 1.0   | <ul><li>'In addition, we have a majority standard for the election of directors on our board.'</li><li>'We generally find that it is more effective to take a collaborative approach in identifying and addressing proposed regulatory changes related to our assets and operations.'</li><li>'Regulations of the Supervisory Board The tasks, responsibilities and internal procedural matters for the Supervisory Board are addressed in the Regulations of the Supervisory Board and are available on our corporate website.'</li></ul>                              |
+| Label | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 0.0   | <ul><li>'Our goal is for every employee to feel a strong sense of belonging and psychological safety.'</li><li>'Revenue from products labeled andor marketed to promote health and nutrition attributes is approximately 10.3 billion.'</li><li>'Assess climate change scenarios of key material risks.'</li></ul>                                                                                                                                                                                                                                                                                                                   |
+| 1.0   | <ul><li>'We assessed accounting estimates for bias and evaluated whether the circumstances producing the bias, if any, represent a risk of material misstatement due to fraud.'</li><li>'Board to review and make recommendations to shareholders concerning the composition of the Board of Directors, with particular focus on issues of independence.'</li><li>'Our group audit mainly focused on significant group entities in terms of size and financial interest or where significant risks or complex activities were present, leading to full scope audits performed for including 2 nonconsolidated components.'</li></ul> |
 
 ## Evaluation
 
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.7657   |
+| **all** | 0.8262   |
 
 ## Uses
 
@@ -92,9 +101,9 @@ Then you can load this model and run inference.
 from setfit import SetFitModel
 
 # Download from the 🤗 Hub
-model = SetFitModel.from_pretrained("mitra-mir/setfit-model-ESG-environmental")
+model = SetFitModel.from_pretrained("mitra-mir/setfit-model-ESG-governance")
 # Run inference
-preds = model("and importance of the climate crisis requires everyone to play their part.")
+preds = model("The Company will also make every effort to improve the effectiveness of its sustainability reporting.")
 ```
 
 <!--
@@ -124,14 +133,14 @@ preds = model("and importance of the climate crisis requires everyone to play th
 ## Training Details
 
 ### Training Set Metrics
-| Training set | Min | Median  | Max |
-|:-------------|:----|:--------|:----|
-| Word count   | 3   | 25.4020 | 72  |
+| Training set | Min | Median | Max |
+|:-------------|:----|:-------|:----|
+| Word count   | 2   | 24.51  | 74  |
 
 | Label | Training Sample Count |
 |:------|:----------------------|
-| 0.0   | 148                   |
-| 1.0   | 51                    |
+| 0.0   | 146                   |
+| 1.0   | 54                    |
 
 ### Training Hyperparameters
 - batch_size: (16, 16)
@@ -153,38 +162,19 @@ preds = model("and importance of the climate crisis requires everyone to play th
 - load_best_model_at_end: False
 
 ### Training Results
-| Epoch  | Step | Training Loss | Validation Loss |
-|:------:|:----:|:-------------:|:---------------:|
-| 0.0020 | 1    | 0.4091        | -               |
-| 0.1004 | 50   | 0.1992        | -               |
-| 0.2008 | 100  | 0.0104        | -               |
-| 0.3012 | 150  | 0.0006        | -               |
-| 0.4016 | 200  | 0.0003        | -               |
-| 0.5020 | 250  | 0.0002        | -               |
-| 0.6024 | 300  | 0.0002        | -               |
-| 0.7028 | 350  | 0.0001        | -               |
-| 0.8032 | 400  | 0.0001        | -               |
-| 0.9036 | 450  | 0.0001        | -               |
-| 0.0020 | 1    | 0.25          | -               |
-| 0.1004 | 50   | 0.349         | -               |
-| 0.2008 | 100  | 0.047         | -               |
-| 0.3012 | 150  | 0.0172        | -               |
-| 0.4016 | 200  | 0.0023        | -               |
-| 0.5020 | 250  | 0.0002        | -               |
-| 0.6024 | 300  | 0.0002        | -               |
-| 0.7028 | 350  | 0.0003        | -               |
-| 0.8032 | 400  | 0.0001        | -               |
-| 0.9036 | 450  | 0.0001        | -               |
-| 0.0020 | 1    | 0.3684        | -               |
-| 0.1004 | 50   | 0.39          | -               |
-| 0.2008 | 100  | 0.1277        | -               |
-| 0.3012 | 150  | 0.0064        | -               |
-| 0.4016 | 200  | 0.0006        | -               |
-| 0.5020 | 250  | 0.0004        | -               |
-| 0.6024 | 300  | 0.0003        | -               |
-| 0.7028 | 350  | 0.0003        | -               |
-| 0.8032 | 400  | 0.0002        | -               |
-| 0.9036 | 450  | 0.0002        | -               |
+| Epoch | Step | Training Loss | Validation Loss |
+|:-----:|:----:|:-------------:|:---------------:|
+| 0.002 | 1    | 0.479         | -               |
+| 0.1   | 50   | 0.2577        | -               |
+| 0.2   | 100  | 0.0589        | -               |
+| 0.3   | 150  | 0.0008        | -               |
+| 0.4   | 200  | 0.0004        | -               |
+| 0.5   | 250  | 0.0003        | -               |
+| 0.6   | 300  | 0.0002        | -               |
+| 0.7   | 350  | 0.0002        | -               |
+| 0.8   | 400  | 0.0002        | -               |
+| 0.9   | 450  | 0.0002        | -               |
+| 1.0   | 500  | 0.0002        | -               |
 
 ### Framework Versions
 - Python: 3.11.6

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aedcd9b1b711338c94874e7f407a9d55500617f993c1e7ab5d4aacd6ba0944e8
+oid sha256:f7de3a947e784171b5e89eee0d557402a71ae451864dc00099eb4935827e91be
 size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88b7ee7c63cdc0f6333a7e1992528a279acc6b57dc6cf3299ff8ac00137bb68
+oid sha256:11bc6c4d67f44046c5198270a0d434d663b94d788be512f4e2c4edeac132a36c
 size 6959