Hugging Face's logo

spaly99
/
my-setfit-model-dataset-PG-OCR-2

Text Classification
setfit
Safetensors
sentence-transformers
mpnet
generated_from_setfit_trainer
Eval Results
Model card Files Community
spaly99 commited on
Commit
7aee559
•
1 Parent(s): 5bd93f6

Add SetFit model

Browse files
Files changed (4) hide show
  1. README.md +59 -27
  2. config_setfit.json +2 -2
  3. model.safetensors +1 -1
  4. model_head.pkl +1 -1
README.md CHANGED
@@ -11,11 +11,11 @@ metrics:
11
  - recall
12
  - f1
13
  widget:
14
- - text: 'mar | : { ‘ : Ui * | z : gg ‘ey bal _ . '' '
15
- - text: www.statista.fr
16
- - text: French Polynesia
17
- - text: 'SHOP DRESS SHIRTS > '
18
- - text: '’ \ Rather Go Naked a Wé FE '
19
  pipeline_tag: text-classification
20
  inference: true
21
  base_model: sentence-transformers/paraphrase-mpnet-base-v2
@@ -31,16 +31,16 @@ model-index:
31
  split: test
32
  metrics:
33
  - type: accuracy
34
- value: 0.9
35
  name: Accuracy
36
  - type: precision
37
- value: 0.8823529411764706
38
  name: Precision
39
  - type: recall
40
- value: 0.8823529411764706
41
  name: Recall
42
  - type: f1
43
- value: 0.8823529411764706
44
  name: F1
45
  ---
46
 
@@ -72,17 +72,17 @@ The model has been trained using an efficient few-shot learning technique that i
72
  - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
73
 
74
  ### Model Labels
75
- | Label | Examples |
76
- |:------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------|
77
- | True | <ul><li>'WHEN DID HE STOP TREATING YOU LIKE A PRINGESS? '</li><li>'Samsung” 65" Class Curved 4K Ultra HD '</li><li>'Finger Lickin’ Mini Fillet Burge: '</li></ul> |
78
- | False | <ul><li>'speedtest.net'</li><li>'Dane z przeglądania i interakcji'</li><li>'Announcements'</li></ul> |
79
 
80
  ## Evaluation
81
 
82
  ### Metrics
83
  | Label | Accuracy | Precision | Recall | F1 |
84
  |:--------|:---------|:----------|:-------|:-------|
85
- | **all** | 0.9 | 0.8824 | 0.8824 | 0.8824 |
86
 
87
  ## Uses
88
 
@@ -102,7 +102,7 @@ from setfit import SetFitModel
102
  # Download from the 🤗 Hub
103
  model = SetFitModel.from_pretrained("setfit_model_id")
104
  # Run inference
105
- preds = model("www.statista.fr")
106
  ```
107
 
108
  <!--
@@ -134,12 +134,12 @@ preds = model("www.statista.fr")
134
  ### Training Set Metrics
135
  | Training set | Min | Median | Max |
136
  |:-------------|:----|:-------|:----|
137
- | Word count | 1 | 8.6188 | 267 |
138
 
139
  | Label | Training Sample Count |
140
  |:------|:----------------------|
141
- | False | 77 |
142
- | True | 83 |
143
 
144
  ### Training Hyperparameters
145
  - batch_size: (16, 2)
@@ -163,15 +163,47 @@ preds = model("www.statista.fr")
163
  ### Training Results
164
  | Epoch | Step | Training Loss | Validation Loss |
165
  |:------:|:----:|:-------------:|:---------------:|
166
- | 0.0025 | 1 | 0.3647 | - |
167
- | 0.125 | 50 | 0.2765 | - |
168
- | 0.25 | 100 | 0.0519 | - |
169
- | 0.375 | 150 | 0.0045 | - |
170
- | 0.5 | 200 | 0.055 | - |
171
- | 0.625 | 250 | 0.0033 | - |
172
- | 0.75 | 300 | 0.1017 | - |
173
- | 0.875 | 350 | 0.02 | - |
174
- | 1.0 | 400 | 0.0015 | - |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
175
 
176
  ### Framework Versions
177
  - Python: 3.11.0
 
11
  - recall
12
  - f1
13
  widget:
14
+ - text: 'VALID THRU 02/10/2015 '
15
+ - text: Les chaines Universal+
16
+ - text: "\tminute = second * 60,"
17
+ - text: ': Session'
18
+ - text: Phil Klay
19
  pipeline_tag: text-classification
20
  inference: true
21
  base_model: sentence-transformers/paraphrase-mpnet-base-v2
 
31
  split: test
32
  metrics:
33
  - type: accuracy
34
+ value: 0.87
35
  name: Accuracy
36
  - type: precision
37
+ value: 0.8452380952380952
38
  name: Precision
39
  - type: recall
40
+ value: 0.8452380952380952
41
  name: Recall
42
  - type: f1
43
+ value: 0.8452380952380952
44
  name: F1
45
  ---
46
 
 
72
  - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
73
 
74
  ### Model Labels
75
+ | Label | Examples |
76
+ |:------|:-----------------------------------------------------------------------------------------------------------------------------------------------------|
77
+ | True | <ul><li>'ace} UNIV FEATURING CHAMILLIONAIRE ©) '</li><li>'ee — Pra yon t “pink you are S© Mer '</li><li>'ae PTAA Be hs B corms of Rermee '</li></ul> |
78
+ | False | <ul><li>'mmmmmmmmmmlli'</li><li>'Manage Cookie Preferences'</li><li>'Supply Partners'</li></ul> |
79
 
80
  ## Evaluation
81
 
82
  ### Metrics
83
  | Label | Accuracy | Precision | Recall | F1 |
84
  |:--------|:---------|:----------|:-------|:-------|
85
+ | **all** | 0.87 | 0.8452 | 0.8452 | 0.8452 |
86
 
87
  ## Uses
88
 
 
102
  # Download from the 🤗 Hub
103
  model = SetFitModel.from_pretrained("setfit_model_id")
104
  # Run inference
105
+ preds = model(": Session")
106
  ```
107
 
108
  <!--
 
134
  ### Training Set Metrics
135
  | Training set | Min | Median | Max |
136
  |:-------------|:----|:-------|:----|
137
+ | Word count | 1 | 8.4575 | 265 |
138
 
139
  | Label | Training Sample Count |
140
  |:------|:----------------------|
141
+ | False | 384 |
142
+ | True | 416 |
143
 
144
  ### Training Hyperparameters
145
  - batch_size: (16, 2)
 
163
  ### Training Results
164
  | Epoch | Step | Training Loss | Validation Loss |
165
  |:------:|:----:|:-------------:|:---------------:|
166
+ | 0.0005 | 1 | 0.4077 | - |
167
+ | 0.025 | 50 | 0.2689 | - |
168
+ | 0.05 | 100 | 0.2505 | - |
169
+ | 0.075 | 150 | 0.1787 | - |
170
+ | 0.1 | 200 | 0.1602 | - |
171
+ | 0.125 | 250 | 0.1381 | - |
172
+ | 0.15 | 300 | 0.1753 | - |
173
+ | 0.175 | 350 | 0.018 | - |
174
+ | 0.2 | 400 | 0.024 | - |
175
+ | 0.225 | 450 | 0.0863 | - |
176
+ | 0.25 | 500 | 0.0504 | - |
177
+ | 0.275 | 550 | 0.0204 | - |
178
+ | 0.3 | 600 | 0.0124 | - |
179
+ | 0.325 | 650 | 0.066 | - |
180
+ | 0.35 | 700 | 0.1305 | - |
181
+ | 0.375 | 750 | 0.0599 | - |
182
+ | 0.4 | 800 | 0.0323 | - |
183
+ | 0.425 | 850 | 0.0039 | - |
184
+ | 0.45 | 900 | 0.0131 | - |
185
+ | 0.475 | 950 | 0.004 | - |
186
+ | 0.5 | 1000 | 0.0016 | - |
187
+ | 0.525 | 1050 | 0.0139 | - |
188
+ | 0.55 | 1100 | 0.0189 | - |
189
+ | 0.575 | 1150 | 0.0533 | - |
190
+ | 0.6 | 1200 | 0.0645 | - |
191
+ | 0.625 | 1250 | 0.0005 | - |
192
+ | 0.65 | 1300 | 0.0111 | - |
193
+ | 0.675 | 1350 | 0.002 | - |
194
+ | 0.7 | 1400 | 0.0082 | - |
195
+ | 0.725 | 1450 | 0.0009 | - |
196
+ | 0.75 | 1500 | 0.0018 | - |
197
+ | 0.775 | 1550 | 0.0003 | - |
198
+ | 0.8 | 1600 | 0.0108 | - |
199
+ | 0.825 | 1650 | 0.0009 | - |
200
+ | 0.85 | 1700 | 0.0003 | - |
201
+ | 0.875 | 1750 | 0.0009 | - |
202
+ | 0.9 | 1800 | 0.0038 | - |
203
+ | 0.925 | 1850 | 0.0406 | - |
204
+ | 0.95 | 1900 | 0.0012 | - |
205
+ | 0.975 | 1950 | 0.0024 | - |
206
+ | 1.0 | 2000 | 0.0004 | - |
207
 
208
  ### Framework Versions
209
  - Python: 3.11.0
config_setfit.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "normalize_embeddings": false,
3
- "labels": null
4
  }
 
1
  {
2
+ "labels": null,
3
+ "normalize_embeddings": false
4
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80bb1496041fcd14467a4f837dbe4fc62bb21d514e269c7ae434a07928da9e16
3
  size 437967672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c31f161564e4e1ea97deff9feb676cf6791edacb4b7c6aea784e495b8f16759
3
  size 437967672
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd7626ba6a3a59755deeaf71686b94e09eceb7dea2b743835558d6e7e079bf05
3
  size 6991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21dcf58ef236683a980cbb3208e81d8da62cf3572f2c815f74b11368a2497d3
3
  size 6991