Hugging Face's logo

Tomiwajin
/
setfit_email_classifier

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Model card Files
xet
Community
Tomiwajin commited on
Commit
6ddcdae
·
verified ·
1 Parent(s): aeb6599

Upload 14 files

Browse files

fine-tuned with better dataset

Files changed (5) hide show
  1. README.md +259 -128
  2. config_setfit.json +5 -5
  3. model.safetensors +1 -1
  4. model_head.pkl +1 -1
  5. model_info.json +8 -8
README.md CHANGED
@@ -1,172 +1,303 @@
1
  ---
2
- license: mit
3
- language:
4
- - en
5
- base_model:
6
- - sentence-transformers/all-MiniLM-L6-v2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  pipeline_tag: text-classification
 
 
 
8
  ---
9
- # SetFit Email Job Status Classifier
10
 
11
- A fine-tuned SetFit model for classifying job application emails into different categories. This model can automatically categorize job-related emails to help track application status and organize your job search process.
12
 
13
- ## Model Description
14
 
15
- This model is based on [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) and fine-tuned using SetFit (Sentence Transformer Fine-tuning) for email classification tasks.
16
 
17
- **Base Model:** `sentence-transformers/all-MiniLM-L6-v2`
18
- **Framework:** SetFit
19
- **Task:** Multi-class text classification
20
- **Language:** English
21
 
22
- ## Model Performance
23
 
24
- - **Overall Accuracy:** 90%
25
- - **Training Samples:** 235
26
- - **Test Samples:** 59
27
- - **Classes:** 7
 
 
 
 
 
28
 
29
- ## Intended Use
30
 
31
- ### Primary Use Cases
 
 
32
 
33
- - **Job Search Management:** Automatically categorize job-related emails
34
- - **Email Organization:** Sort incoming emails by job application status
35
- - **Application Tracking:** Monitor progress of job applications
36
- - **Workflow Automation:** Integrate into email filtering systems
 
 
 
 
 
 
37
 
38
- ### Supported Categories
39
 
40
- 1. **Applied** - Confirmation emails after submitting applications
41
- 2. **Interview** - Interview invitations and scheduling emails
42
- 3. **Next-Step** - Follow-up emails about next steps in the process
43
- 4. **Not Job Related** - Non-job related emails
44
- 5. **Not Job Status Update** - Job-related but not status updates
45
- 6. **Offer** - Job offers and offer-related communications
46
- 7. **Rejected** - Rejection notifications
47
 
48
- ## How to Use
49
-
50
- ### Installation
51
 
52
  ```bash
53
  pip install setfit
54
  ```
55
 
56
- ### Quick Start
57
 
58
  ```python
59
  from setfit import SetFitModel
60
 
61
- # Load the model
62
- model = SetFitModel.from_pretrained("your-username/setfit-email-classifier")
63
-
64
- # Classify emails
65
- emails = [
66
- "Thank you for your application. We will review it and get back to you.",
67
- "We would like to schedule an interview with you for next Tuesday.",
68
- "Unfortunately, we have decided to move forward with other candidates.",
69
- "Congratulations! We would like to offer you the position."
70
- ]
71
-
72
- predictions = model(emails)
73
- print(predictions)
74
- # Output: ['applied', 'interview', 'rejected', 'offer']
75
  ```
76
 
77
- ### Batch Processing
 
78
 
79
- ```python
80
- import pandas as pd
81
 
82
- # Process multiple emails
83
- df = pd.DataFrame({
84
- 'subject': ['Application Confirmation', 'Interview Invitation', 'Unfortunately...'],
85
- 'body': ['Thank you for applying...', 'We would like to schedule...', 'We regret to inform...']
86
- })
87
 
88
- # Combine subject and body
89
- df['email_text'] = df['subject'] + ' ' + df['body']
90
 
91
- # Get predictions
92
- predictions = model(df['email_text'].tolist())
93
- df['classification'] = predictions
94
 
95
- print(df[['subject', 'classification']])
96
- ```
97
 
98
- ### Confidence Scores
 
99
 
100
- ```python
101
- # Get prediction probabilities
102
- email_text = "We would like to schedule a phone interview with you."
103
- embeddings = model.model_body.encode([email_text])
104
- probabilities = model.model_head.predict_proba(embeddings)[0]
105
- classes = model.model_head.classes_
106
-
107
- # Display results
108
- prediction = model([email_text])[0]
109
- print(f"Prediction: {prediction}")
110
-
111
- for class_name, prob in zip(classes, probabilities):
112
- print(f"{class_name}: {prob:.3f}")
113
- ```
114
-
115
- ## Training Data
116
-
117
- The model was trained on a dataset of 294 job-related emails with the following distribution:
118
-
119
- - **Not Job Related:** 53 samples
120
- - **Rejected:** 47 samples
121
- - **Interview:** 47 samples
122
- - **Not Job Status Update:** 46 samples
123
- - **Applied:** 43 samples
124
- - **Next-Step:** 30 samples
125
- - **Offer:** 28 samples
126
 
127
  ## Training Details
128
 
129
- **Training Framework:** SetFit
130
- **Training Time:** ~1 hour
131
- **Hardware:** Local training (CPU/GPU)
132
- **Optimization:** Contrastive learning + classification head fine-tuning
133
-
134
- ### Training Parameters
135
-
136
- - **Base Model:** sentence-transformers/all-MiniLM-L6-v2
137
- - **Train/Test Split:** 80/20
138
- - **Stratified Split:** Yes (maintains class distribution)
139
- - **Random State:** 42 (reproducible results)
140
-
141
- ## Limitations
142
-
143
- - **Domain Specific:** Trained specifically on job application emails
144
- - **English Only:** Optimized for English language emails
145
- - **Class Imbalance:** Some categories have fewer training examples
146
- - **Context Length:** Best performance on email-length texts (not very long documents)
147
- - **Temporal Drift:** Performance may degrade on very recent email formats/styles
148
-
149
- ## Bias and Fairness
150
-
151
- - The model may reflect biases present in the training data
152
- - Performance may vary across different industries, company sizes, or communication styles
153
- - Regular evaluation recommended when deployed in production
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
154
 
155
  ## Citation
156
 
157
- If you use this model, please cite:
158
-
159
  ```bibtex
160
- @misc{setfit-email-classifier-2025,
161
- title={SetFit Email Job Status Classifier},
162
- author={Oluwatomiwa Jinadu},
163
- year={2025},
164
- howpublished={\\url{https://huggingface.co/Tomiwajin/setfit_email_classifier}},
 
 
 
 
165
  }
166
  ```
167
 
168
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
169
 
170
- **Model Card Authors:** Oluwatomiwa Jinadu
171
- **Model Card Date:** September 2025
172
- **Model Version:** 1.0
 
1
  ---
2
+ tags:
3
+ - setfit
4
+ - sentence-transformers
5
+ - text-classification
6
+ - generated_from_setfit_trainer
7
+ widget:
8
+ - text: 'Monorepos, Verified Templates, Replica Metrics It''s Friday and you know
9
+ what that means! Here''s a summary of the stuff we shipped this week Time! It''s
10
+ Friday and you know what that means! Here''s a summary of the stuff we shipped
11
+ this week: First-Class Support for Monorepos Verified Templates Replica Metrics
12
+ to Priority Boarding Fixes and Improv'
13
+ - text: 'Thanks for your time Thank you for applying to the Backend Developer position
14
+ at YinzCam, Inc..
15
+
16
+ Unfortunately, YinzCam, Inc. has moved to the next step in their hiring process,
17
+ and your application was not selected at this time.'
18
+ - text: "Humanoid Alert! Your Data Packet Caught Our Eye at 1X Technologies! Hi Tomiwa,\n\
19
+ \nThank you for sending your application data stream our way at 1X Technologies!\n\
20
+ \nYour resume just ran through our systems, and let's just say, your skill matrix\
21
+ \ looks incredibly promising. We were genuinely intrigued by your experience and\
22
+ \ see some serious potential \n\nfor you to help us b"
23
+ - text: 'Indeed Application: Software Developer We''ll help you get started pplication
24
+ submitted Software Developer TherapyNotes.com - United States 30 reviews The following
25
+ items were sent to TherapyNotes.com. Good luck! • Application • Resume
26
+ Next steps • The employer or job advertiser may reach out to you about your
27
+ application.'
28
+ - text: 'Jobs! I have a job that I think lines up well with your resume. It''s new,
29
+ so they don''t have many candidates yet. Check out the description and hit "View
30
+ Details" if you like what you see.
31
+
32
+
33
+ Entry Level Software Engineer - Revature - Jersey City, NJ
34
+
35
+ Revature is looking to hire Entry Level Software Engineer'
36
+ metrics:
37
+ - accuracy
38
  pipeline_tag: text-classification
39
+ library_name: setfit
40
+ inference: true
41
+ base_model: sentence-transformers/all-MiniLM-L6-v2
42
  ---
 
43
 
44
+ # SetFit with sentence-transformers/all-MiniLM-L6-v2
45
 
46
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
47
 
48
+ The model has been trained using an efficient few-shot learning technique that involves:
49
 
50
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
51
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
 
 
52
 
53
+ ## Model Details
54
 
55
+ ### Model Description
56
+ - **Model Type:** SetFit
57
+ - **Sentence Transformer body:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)
58
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
59
+ - **Maximum Sequence Length:** 256 tokens
60
+ - **Number of Classes:** 7 classes
61
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
62
+ <!-- - **Language:** Unknown -->
63
+ <!-- - **License:** Unknown -->
64
 
65
+ ### Model Sources
66
 
67
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
68
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
69
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
70
 
71
+ ### Model Labels
72
+ | Label | Examples |
73
+ |:----------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
74
+ | next-phase | <ul><li>"Next step: Assessment 📋 for the Product Manager role at StartupXYZ Hi Thomas, Thank you again for your interest in the Product Manager position at StartupXYZ. As part of our hiring process, the next step is to complete an assessment that will help us better understand your skills and suitability for the role. Here's what to expect: • Assessment details: Product str"</li><li>"Next Steps - Front-End Engineer Hey Oluwatomiwa,\nWe're excited to invite you to the next phase of the Front-End Engineer role.\nBefore moving forward, please ensure your location is on the list of accepted locations.\nImportant Notice\n\nIf you currently have or previously had credentials with Outlier or a related platform, please do"</li><li>'Coding Assessment - Backend Developer Position Dear Kevin, We appreciate your interest in the Backend Developer role at CloudSync Technologies. As the next step in our selection process, we invite you to complete our technical coding assessment. This assessment has been carefully designed to evaluate your programming skills and problem-solving a'</li></ul> |
75
+ | interview | <ul><li>"Interview for DevOps Engineer at ServerMax Hi Daniel, Thanks again for taking the time to chat with me on the phone! I'm very happy to move you to the next stage of our hiring process — a 45-minute video interview. This interview will include me and my colleague Tom Rodriguez, our Infrastructure Lead. If you'd like to learn a little about hi"</li><li>"Video interview for Social Media Manager at BuzzMarketing Hi Taylor, Thank you for your application for the Social Media Manager position with BuzzMarketing. We're excited to learn more about you and your qualifications! We would like to invite you to a video interview with Christina Park, our Digital Marketing Director. This will be a chance for us to dis"</li><li>'Final round interview for Marketing Director at BrandBoost Hi Michelle, Congratulations on making it to the final round of interviews for the Marketing Director position! We would like to invite you to a final in-person interview with our executive team including CEO Jonathan Miller and CMO Patricia Davis. This will be a chance for us to discuss your strate'</li></ul> |
76
+ | not-job-status-update | <ul><li>"Jobs! Hi Seth,\n\nI found a job you may be interested in: 100% REMOTE - Senior Fullstack Engineer\n\nIf you'd like to apply, let me know in a quick response with your updated resume. Full job details below.\n\nf you are a Senior Software Engineer with Python and React experience, please read on!\n\nWe headquarter"</li><li>'Oluwatomiwa, you have new application updates this week Check out the status of your applications on LinkedIn Check out the status of your applications on LinkedIn Here are the latest updates from the past week Junior Software Engineer Fortune 500 &middot; Plano, TX (On-site) No longer accepting applications Software Quality Assurance Engineer ChronicCar'</li><li>'Junior Software Engineer role at AmeriNat: you would be a great fit! Hey! Check out the latest industry content about career advice, salary negotiations, and interview tips, among other topics. Explore now! Jobs for you Jobs for you We’re on a mission to connect you with a dream job. To help us refine this list, search for more jobs AmeriNat 4.1 ★ Junior Softwar'</li></ul> |
77
+ | not-job-related | <ul><li>'Welcome to Idealist! Four actions you can take right now to get started Hi Oluwatomiwa, My name is Ami, and I‚Äôm the founder and executive director of Idealist. We started Idealist in the summer of 1995‚Äîon one old computer and with no full-time staff‚Äîto help connect people around the world with opportunities to do'</li><li>'New arrivals are here SHEIN Shop at SHEIN for the latest trends! Shop at SHEIN for the latest trends! Unsubscribe | View in Browser Pick your unique look SHOP NEW ARRIVALS > FIND US ON APP'</li><li>'\uf8ffüö®Here‚Äôs the Zoom Link & exclusive offers! \uf8ffüö®Here‚Äôs the Zoom Link & exclusive offers! Your seat at the Agentic AI Conference is reserved - plus unlock exclusive training offers up to 40% off! Hi Oluwatomiwa, We‚Äôre thrilled to have you join us for the second edition of the Future of Data and AI: Agentic AI Conference! \uf8ffüîó Link to Join'</li></ul> |
78
+ | applied | <ul><li>'Thank you for applying! Dear Name,\n\nThank you for your interest in a career at Delta Dental of Iowa. We have received your application for Software Development Intern.\nIn the event that we wish to arrange a personal interview, we will contact you. Again, thank you for your interest in employment at Delta Dental of Iowa.'</li><li>'Thank You For Applying! Dear Name,\nThank you for applying! Your application will be taken into careful consideration and you will hear back from us after we review your application.\n\n\nBest Regards,\n\nBracco Human Resources Team'</li><li>'Thank you for applying to Passes Name,\n\nThanks for applying to Passes. Your application has been received and we will review it right away.\n\nIf your application seems like a good fit for the position we will contact you soon.\n\nRegards,\nPasses\n\n** Please note: Do not reply to this email. This email is sent from an unattended mailbox'</li></ul> |
79
+ | offer | <ul><li>"Congratulations - You're Our New Management Consultant! Dear Diana Brown, Congratulations! StrategyConsult Partners is excited to call you our new Management Consultant. We'll focus on wrapping up a few more formalities, including the successful completion of your background check and client reference verification, and aim to get you settled into your ne"</li><li>'Full-Time Employment Offer Dear Brandon Taylor, ArchitectureMax is offering to extend your current employment status from contractor to full-time employee, as of June 1st, 2024. If you choose to accept our offer, please review the terms and conditions of your new employment contract below: Position: You will be working as a S'</li><li>'Employment Offer - Product Manager Position Michael Chen 456 Innovation Drive, San Francisco, CA 94105 Re: Employment Offer Dear Michael: On behalf of ProductMax, Inc. (the "Company"), it is my pleasure to offer you employment with the Company in the role set forth below. The purpose of this letter is to summarize the initial terms of your em'</li></ul> |
80
+ | rejected | <ul><li>'Thanks for your time Thank you for your interest in the Software Engineer position at Lantana Consulting Group in Vermont, United States. Unfortunately, we will not be moving forward with your application, but we appreciate your time and interest in Lantana Consulting Group.\n\nRegards,\n\nLantana Consulting Group'</li><li>"Thanks for your time Hello Name,\n\nThank you very much for your interest in our Software Engineer - React/Redux opening. We've had a chance to discuss your background and qualifications with the hiring manager and unfortunately, we have decided to pursue other candidates who appear to match our requirements more closely"</li><li>"Thanks for your interest in Supernova Technology, Name Hi Name,\nThank you for your interest in Supernova Technology. After reviewing your background and experience, we’ve decided not to move forward with your application at this time.\n\nWe truly appreciate the time and effort you put into the process, and we hope you don't mind if we reach out in the fut"</li></ul> |
81
 
82
+ ## Uses
83
 
84
+ ### Direct Use for Inference
 
 
 
 
 
 
85
 
86
+ First install the SetFit library:
 
 
87
 
88
  ```bash
89
  pip install setfit
90
  ```
91
 
92
+ Then you can load this model and run inference.
93
 
94
  ```python
95
  from setfit import SetFitModel
96
 
97
+ # Download from the 🤗 Hub
98
+ model = SetFitModel.from_pretrained("setfit_model_id")
99
+ # Run inference
100
+ preds = model("Thanks for your time Thank you for applying to the Backend Developer position at YinzCam, Inc..
101
+ Unfortunately, YinzCam, Inc. has moved to the next step in their hiring process, and your application was not selected at this time.")
 
 
 
 
 
 
 
 
 
102
  ```
103
 
104
+ <!--
105
+ ### Downstream Use
106
 
107
+ *List how someone could finetune this model on their own dataset.*
108
+ -->
109
 
110
+ <!--
111
+ ### Out-of-Scope Use
 
 
 
112
 
113
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
114
+ -->
115
 
116
+ <!--
117
+ ## Bias, Risks and Limitations
 
118
 
119
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
120
+ -->
121
 
122
+ <!--
123
+ ### Recommendations
124
 
125
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
126
+ -->
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
127
 
128
  ## Training Details
129
 
130
+ ### Training Set Metrics
131
+ | Training set | Min | Median | Max |
132
+ |:-------------|:----|:--------|:----|
133
+ | Word count | 14 | 55.2121 | 288 |
134
+
135
+ | Label | Training Sample Count |
136
+ |:----------------------|:----------------------|
137
+ | applied | 40 |
138
+ | interview | 45 |
139
+ | next-phase | 35 |
140
+ | not-job-related | 55 |
141
+ | not-job-status-update | 41 |
142
+ | offer | 36 |
143
+ | rejected | 45 |
144
+
145
+ ### Training Hyperparameters
146
+ - batch_size: (16, 2)
147
+ - num_epochs: (1, 16)
148
+ - max_steps: -1
149
+ - sampling_strategy: oversampling
150
+ - body_learning_rate: (2e-05, 1e-05)
151
+ - head_learning_rate: 0.01
152
+ - loss: CosineSimilarityLoss
153
+ - distance_metric: cosine_distance
154
+ - margin: 0.25
155
+ - end_to_end: False
156
+ - use_amp: False
157
+ - warmup_proportion: 0.1
158
+ - l2_weight: 0.01
159
+ - seed: 42
160
+ - eval_max_steps: -1
161
+ - load_best_model_at_end: False
162
+
163
+ ### Training Results
164
+ | Epoch | Step | Training Loss | Validation Loss |
165
+ |:------:|:----:|:-------------:|:---------------:|
166
+ | 0.0002 | 1 | 0.3397 | - |
167
+ | 0.0106 | 50 | 0.2699 | - |
168
+ | 0.0212 | 100 | 0.2293 | - |
169
+ | 0.0319 | 150 | 0.1907 | - |
170
+ | 0.0425 | 200 | 0.1685 | - |
171
+ | 0.0531 | 250 | 0.1174 | - |
172
+ | 0.0637 | 300 | 0.078 | - |
173
+ | 0.0743 | 350 | 0.0524 | - |
174
+ | 0.0849 | 400 | 0.0319 | - |
175
+ | 0.0956 | 450 | 0.0113 | - |
176
+ | 0.1062 | 500 | 0.0073 | - |
177
+ | 0.1168 | 550 | 0.0051 | - |
178
+ | 0.1274 | 600 | 0.0038 | - |
179
+ | 0.1380 | 650 | 0.0029 | - |
180
+ | 0.1487 | 700 | 0.0023 | - |
181
+ | 0.1593 | 750 | 0.0021 | - |
182
+ | 0.1699 | 800 | 0.0017 | - |
183
+ | 0.1805 | 850 | 0.0017 | - |
184
+ | 0.1911 | 900 | 0.0015 | - |
185
+ | 0.2017 | 950 | 0.0012 | - |
186
+ | 0.2124 | 1000 | 0.0011 | - |
187
+ | 0.2230 | 1050 | 0.0011 | - |
188
+ | 0.2336 | 1100 | 0.001 | - |
189
+ | 0.2442 | 1150 | 0.001 | - |
190
+ | 0.2548 | 1200 | 0.0009 | - |
191
+ | 0.2654 | 1250 | 0.0008 | - |
192
+ | 0.2761 | 1300 | 0.0008 | - |
193
+ | 0.2867 | 1350 | 0.0007 | - |
194
+ | 0.2973 | 1400 | 0.0007 | - |
195
+ | 0.3079 | 1450 | 0.0006 | - |
196
+ | 0.3185 | 1500 | 0.0006 | - |
197
+ | 0.3292 | 1550 | 0.0006 | - |
198
+ | 0.3398 | 1600 | 0.0006 | - |
199
+ | 0.3504 | 1650 | 0.0006 | - |
200
+ | 0.3610 | 1700 | 0.0005 | - |
201
+ | 0.3716 | 1750 | 0.0005 | - |
202
+ | 0.3822 | 1800 | 0.0005 | - |
203
+ | 0.3929 | 1850 | 0.0005 | - |
204
+ | 0.4035 | 1900 | 0.0004 | - |
205
+ | 0.4141 | 1950 | 0.0004 | - |
206
+ | 0.4247 | 2000 | 0.0004 | - |
207
+ | 0.4353 | 2050 | 0.0004 | - |
208
+ | 0.4460 | 2100 | 0.0004 | - |
209
+ | 0.4566 | 2150 | 0.0004 | - |
210
+ | 0.4672 | 2200 | 0.0004 | - |
211
+ | 0.4778 | 2250 | 0.0004 | - |
212
+ | 0.4884 | 2300 | 0.0003 | - |
213
+ | 0.4990 | 2350 | 0.0003 | - |
214
+ | 0.5097 | 2400 | 0.0003 | - |
215
+ | 0.5203 | 2450 | 0.0003 | - |
216
+ | 0.5309 | 2500 | 0.0003 | - |
217
+ | 0.5415 | 2550 | 0.0003 | - |
218
+ | 0.5521 | 2600 | 0.0003 | - |
219
+ | 0.5628 | 2650 | 0.0003 | - |
220
+ | 0.5734 | 2700 | 0.0003 | - |
221
+ | 0.5840 | 2750 | 0.0002 | - |
222
+ | 0.5946 | 2800 | 0.0002 | - |
223
+ | 0.6052 | 2850 | 0.0003 | - |
224
+ | 0.6158 | 2900 | 0.0002 | - |
225
+ | 0.6265 | 2950 | 0.0002 | - |
226
+ | 0.6371 | 3000 | 0.0002 | - |
227
+ | 0.6477 | 3050 | 0.0002 | - |
228
+ | 0.6583 | 3100 | 0.0002 | - |
229
+ | 0.6689 | 3150 | 0.0002 | - |
230
+ | 0.6795 | 3200 | 0.0002 | - |
231
+ | 0.6902 | 3250 | 0.0002 | - |
232
+ | 0.7008 | 3300 | 0.0002 | - |
233
+ | 0.7114 | 3350 | 0.0002 | - |
234
+ | 0.7220 | 3400 | 0.0002 | - |
235
+ | 0.7326 | 3450 | 0.0002 | - |
236
+ | 0.7433 | 3500 | 0.0002 | - |
237
+ | 0.7539 | 3550 | 0.0002 | - |
238
+ | 0.7645 | 3600 | 0.0002 | - |
239
+ | 0.7751 | 3650 | 0.0002 | - |
240
+ | 0.7857 | 3700 | 0.0002 | - |
241
+ | 0.7963 | 3750 | 0.0002 | - |
242
+ | 0.8070 | 3800 | 0.0002 | - |
243
+ | 0.8176 | 3850 | 0.0002 | - |
244
+ | 0.8282 | 3900 | 0.0002 | - |
245
+ | 0.8388 | 3950 | 0.0002 | - |
246
+ | 0.8494 | 4000 | 0.0002 | - |
247
+ | 0.8601 | 4050 | 0.0002 | - |
248
+ | 0.8707 | 4100 | 0.0002 | - |
249
+ | 0.8813 | 4150 | 0.0002 | - |
250
+ | 0.8919 | 4200 | 0.0002 | - |
251
+ | 0.9025 | 4250 | 0.0002 | - |
252
+ | 0.9131 | 4300 | 0.0002 | - |
253
+ | 0.9238 | 4350 | 0.0002 | - |
254
+ | 0.9344 | 4400 | 0.0002 | - |
255
+ | 0.9450 | 4450 | 0.0001 | - |
256
+ | 0.9556 | 4500 | 0.0002 | - |
257
+ | 0.9662 | 4550 | 0.0001 | - |
258
+ | 0.9769 | 4600 | 0.0002 | - |
259
+ | 0.9875 | 4650 | 0.0001 | - |
260
+ | 0.9981 | 4700 | 0.0002 | - |
261
+
262
+ ### Framework Versions
263
+ - Python: 3.11.13
264
+ - SetFit: 1.1.3
265
+ - Sentence Transformers: 5.1.0
266
+ - Transformers: 4.56.1
267
+ - PyTorch: 2.2.2
268
+ - Datasets: 4.0.0
269
+ - Tokenizers: 0.22.0
270
 
271
  ## Citation
272
 
273
+ ### BibTeX
 
274
  ```bibtex
275
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
276
+ doi = {10.48550/ARXIV.2209.11055},
277
+ url = {https://arxiv.org/abs/2209.11055},
278
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
279
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
280
+ title = {Efficient Few-Shot Learning Without Prompts},
281
+ publisher = {arXiv},
282
+ year = {2022},
283
+ copyright = {Creative Commons Attribution 4.0 International}
284
  }
285
  ```
286
 
287
+ <!--
288
+ ## Glossary
289
+
290
+ *Clearly define terms in order to be accessible across audiences.*
291
+ -->
292
+
293
+ <!--
294
+ ## Model Card Authors
295
+
296
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
297
+ -->
298
+
299
+ <!--
300
+ ## Model Card Contact
301
 
302
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
303
+ -->
 
config_setfit.json CHANGED
@@ -1,12 +1,12 @@
1
  {
 
2
  "labels": [
3
  "applied",
4
  "interview",
5
- "next-step",
6
- "not_job_related",
7
- "not_job_status_update",
8
  "offer",
9
  "rejected"
10
- ],
11
- "normalize_embeddings": false
12
  }
 
1
  {
2
+ "normalize_embeddings": false,
3
  "labels": [
4
  "applied",
5
  "interview",
6
+ "next-phase",
7
+ "not-job-related",
8
+ "not-job-status-update",
9
  "offer",
10
  "rejected"
11
+ ]
 
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deec023621bfb0a09323c23fcb6a2b2cd73367b983cd8ae61425e23d91084a0e
3
  size 90864192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173443ab9d8308ee7d1addda486e80e4fd2a2fa4120240c7998f0db6484d1735
3
  size 90864192
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4203f0bf3387d026cb71eb9b2e4fa5262c460b42e7052d57d10296112c7f1a5a
3
  size 22991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456e176ab13227682a341c825bc67297158c85cb2daa4f733541fe3bba0e0219
3
  size 22991
model_info.json CHANGED
@@ -1,17 +1,17 @@
1
  {
2
- "model_path": "setfit_email_classifier_20250909_135238",
3
- "timestamp": "20250909_135238",
4
  "base_model": "sentence-transformers/all-MiniLM-L6-v2",
5
- "training_date": "2025-09-09T13:52:39.181047",
6
  "model_type": "SetFit Email Classifier",
7
- "training_samples": 235,
8
- "test_samples": 59,
9
  "classes": [
10
  "applied",
11
  "interview",
12
- "next-step",
13
- "not_job_related",
14
- "not_job_status_update",
15
  "offer",
16
  "rejected"
17
  ]
 
1
  {
2
+ "model_path": "setfit_email_classifier_20250913_183201",
3
+ "timestamp": "20250913_183201",
4
  "base_model": "sentence-transformers/all-MiniLM-L6-v2",
5
+ "training_date": "2025-09-13T18:32:02.072415",
6
  "model_type": "SetFit Email Classifier",
7
+ "training_samples": 297,
8
+ "test_samples": 75,
9
  "classes": [
10
  "applied",
11
  "interview",
12
+ "next-phase",
13
+ "not-job-related",
14
+ "not-job-status-update",
15
  "offer",
16
  "rejected"
17
  ]