Push model using huggingface_hub.
Browse files- README.md +91 -78
- model.safetensors +1 -1
- model_head.pkl +1 -1
README.md
CHANGED
@@ -10,13 +10,19 @@ tags:
|
|
10 |
- text-classification
|
11 |
- generated_from_setfit_trainer
|
12 |
widget:
|
13 |
-
- text:
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
- text:
|
18 |
-
|
19 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
inference: true
|
21 |
model-index:
|
22 |
- name: SetFit with akhooli/sbert_ar_nli_500k_ubc_norm
|
@@ -30,7 +36,7 @@ model-index:
|
|
30 |
split: test
|
31 |
metrics:
|
32 |
- type: accuracy
|
33 |
-
value: 0.
|
34 |
name: Accuracy
|
35 |
---
|
36 |
|
@@ -62,17 +68,17 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
62 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
63 |
|
64 |
### Model Labels
|
65 |
-
| Label | Examples
|
66 |
-
|
67 |
-
|
|
68 |
-
|
|
69 |
|
70 |
## Evaluation
|
71 |
|
72 |
### Metrics
|
73 |
| Label | Accuracy |
|
74 |
|:--------|:---------|
|
75 |
-
| **all** | 0.
|
76 |
|
77 |
## Uses
|
78 |
|
@@ -92,7 +98,14 @@ from setfit import SetFitModel
|
|
92 |
# Download from the 🤗 Hub
|
93 |
model = SetFitModel.from_pretrained("akhooli/setfit_ar_ubc_hs")
|
94 |
# Run inference
|
95 |
-
preds = model("
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
```
|
97 |
|
98 |
<!--
|
@@ -124,12 +137,12 @@ preds = model("كول هوا و سد نيعك")
|
|
124 |
### Training Set Metrics
|
125 |
| Training set | Min | Median | Max |
|
126 |
|:-------------|:----|:--------|:----|
|
127 |
-
| Word count | 1 |
|
128 |
|
129 |
| Label | Training Sample Count |
|
130 |
|:---------|:----------------------|
|
131 |
-
| negative |
|
132 |
-
| positive |
|
133 |
|
134 |
### Training Hyperparameters
|
135 |
- batch_size: (32, 32)
|
@@ -146,73 +159,73 @@ preds = model("كول هوا و سد نيعك")
|
|
146 |
- warmup_proportion: 0.1
|
147 |
- l2_weight: 0.01
|
148 |
- seed: 42
|
149 |
-
- run_name:
|
150 |
- eval_max_steps: -1
|
151 |
- load_best_model_at_end: False
|
152 |
|
153 |
### Training Results
|
154 |
| Epoch | Step | Training Loss | Validation Loss |
|
155 |
|:------:|:----:|:-------------:|:---------------:|
|
156 |
-
| 0.0003 | 1 | 0.
|
157 |
-
| 0.0333 | 100 | 0.
|
158 |
-
| 0.0667 | 200 | 0.
|
159 |
-
| 0.1 | 300 | 0.
|
160 |
-
| 0.1333 | 400 | 0.
|
161 |
-
| 0.1667 | 500 | 0.
|
162 |
-
| 0.2 | 600 | 0.
|
163 |
-
| 0.2333 | 700 | 0.
|
164 |
-
| 0.2667 | 800 | 0.
|
165 |
-
| 0.3 | 900 | 0.
|
166 |
-
| 0.3333 | 1000 | 0.
|
167 |
-
| 0.3667 | 1100 | 0.
|
168 |
-
| 0.4 | 1200 | 0.
|
169 |
-
| 0.4333 | 1300 | 0.
|
170 |
-
| 0.4667 | 1400 | 0.
|
171 |
-
| 0.5 | 1500 | 0.
|
172 |
-
| 0.5333 | 1600 | 0.
|
173 |
-
| 0.5667 | 1700 | 0.
|
174 |
-
| 0.6 | 1800 | 0.
|
175 |
-
| 0.6333 | 1900 | 0.
|
176 |
-
| 0.6667 | 2000 | 0.
|
177 |
-
| 0.7 | 2100 | 0.
|
178 |
-
| 0.7333 | 2200 | 0.
|
179 |
-
| 0.7667 | 2300 | 0.
|
180 |
-
| 0.8 | 2400 | 0.
|
181 |
-
| 0.8333 | 2500 | 0.
|
182 |
-
| 0.8667 | 2600 | 0.
|
183 |
-
| 0.9 | 2700 | 0.
|
184 |
-
| 0.9333 | 2800 | 0.
|
185 |
-
| 0.9667 | 2900 | 0.
|
186 |
-
| 1.0 | 3000 | 0.
|
187 |
-
| 1.0333 | 3100 | 0.
|
188 |
-
| 1.0667 | 3200 | 0.
|
189 |
-
| 1.1 | 3300 | 0.
|
190 |
-
| 1.1333 | 3400 | 0.
|
191 |
-
| 1.1667 | 3500 | 0.
|
192 |
-
| 1.2 | 3600 | 0.
|
193 |
-
| 1.2333 | 3700 | 0.
|
194 |
-
| 1.2667 | 3800 | 0.
|
195 |
-
| 1.3 | 3900 | 0.
|
196 |
-
| 1.3333 | 4000 | 0.
|
197 |
-
| 1.3667 | 4100 | 0.
|
198 |
-
| 1.4 | 4200 | 0.
|
199 |
-
| 1.4333 | 4300 | 0.
|
200 |
-
| 1.4667 | 4400 | 0.
|
201 |
-
| 1.5 | 4500 | 0.
|
202 |
-
| 1.5333 | 4600 | 0.
|
203 |
-
| 1.5667 | 4700 | 0.
|
204 |
-
| 1.6 | 4800 | 0.
|
205 |
-
| 1.6333 | 4900 | 0.
|
206 |
-
| 1.6667 | 5000 | 0.
|
207 |
-
| 1.7 | 5100 | 0.
|
208 |
-
| 1.7333 | 5200 | 0.
|
209 |
-
| 1.7667 | 5300 | 0.
|
210 |
-
| 1.8 | 5400 | 0.
|
211 |
-
| 1.8333 | 5500 | 0.
|
212 |
-
| 1.8667 | 5600 | 0.
|
213 |
-
| 1.9 | 5700 | 0.
|
214 |
-
| 1.9333 | 5800 | 0.
|
215 |
-
| 1.9667 | 5900 | 0.
|
216 |
| 2.0 | 6000 | 0.0007 | - |
|
217 |
|
218 |
### Framework Versions
|
|
|
10 |
- text-classification
|
11 |
- generated_from_setfit_trainer
|
12 |
widget:
|
13 |
+
- text: 'بلد مخيف، صار القتل بحجه الشرف متل قتل بعوضة، واللي بيخوف اكتر من اللي واقف
|
14 |
+
مكتف ايديه ومش مساعد. وين كنآ، ووين وصلنآ، لمتى حنضل عايشين وساكتين!
|
15 |
+
|
16 |
+
'
|
17 |
+
- text: "من خلال المتابعة ..يتضح أن أكثر اللاعبين الذين يتم تسويقهم هم لاعبي امريكا\
|
18 |
+
\ الجنوبية وأقلهم الافارقة. \nمن خلال الواقع ..أكثر اللاعبين تهاونا ولعب على\
|
19 |
+
\ الواقف في آخر ٦ شهور من عقودهم هم لاعبي امريكا الجنوبية ."
|
20 |
+
- text: ' علم الحزب يا فهمانه ما حطوا لانه عم يحكي وطنيا ومشان ماحدا متلك يعترض. اذا
|
21 |
+
حطوا بتعترضي واذا ما حطوا كمان بتعترضي.'
|
22 |
+
- text: "شيوعي \nعلماني \nمسيحي\nانصار سنه \nصوفي \nيمثلك التجمع \nلا يمثلك التجمع\
|
23 |
+
\ \nاهلا بكم جميعا فنحن نريد بناء وطن ❤"
|
24 |
+
- text: كنا نهرب بحصة الرياضيات والمحاسبة وبنرجع آخر الحصة بخمس دئايئ ولمن تسئلنا
|
25 |
+
المعلمة بنحكيلها كنا عند المديرة وبتسدئنا وضلينا
|
26 |
inference: true
|
27 |
model-index:
|
28 |
- name: SetFit with akhooli/sbert_ar_nli_500k_ubc_norm
|
|
|
36 |
split: test
|
37 |
metrics:
|
38 |
- type: accuracy
|
39 |
+
value: 0.8398268398268398
|
40 |
name: Accuracy
|
41 |
---
|
42 |
|
|
|
68 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
69 |
|
70 |
### Model Labels
|
71 |
+
| Label | Examples |
|
72 |
+
|:---------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
73 |
+
| positive | <ul><li>' سبحان الله الفلسطينيين شعب خاين في كل مكان \nلاحول ولا قوة إلا بالله'</li><li>'يا بيك عّم تخبرنا عن شي ما فينا تعملو نحن ماًعندنا نواب ولا وزراء بمثلونا بالدولة الا اذا زهقان وعبالك ليك'</li><li>'جوز كذابين منافقين...'</li></ul> |
|
74 |
+
| negative | <ul><li>'ربي لا تجعلني أسيء الظن بأحد ولا تجعل في قلبي شيئا على أحد ، اللهم أسألك قلباً نقياً صافيا'</li><li>'هشام حداد عامل فيها جون ستيوارت'</li><li>' بحياة اختك من وين بتجيبي اخبارك؟؟ من صغري وانا عبالي كون... LINK'</li></ul> |
|
75 |
|
76 |
## Evaluation
|
77 |
|
78 |
### Metrics
|
79 |
| Label | Accuracy |
|
80 |
|:--------|:---------|
|
81 |
+
| **all** | 0.8398 |
|
82 |
|
83 |
## Uses
|
84 |
|
|
|
98 |
# Download from the 🤗 Hub
|
99 |
model = SetFitModel.from_pretrained("akhooli/setfit_ar_ubc_hs")
|
100 |
# Run inference
|
101 |
+
preds = model("شيوعي
|
102 |
+
علماني
|
103 |
+
مسيحي
|
104 |
+
انصار سنه
|
105 |
+
صوفي
|
106 |
+
يمثلك التجمع
|
107 |
+
لا يمثلك التجمع
|
108 |
+
اهلا بكم جميعا فنحن نريد بناء وطن ❤")
|
109 |
```
|
110 |
|
111 |
<!--
|
|
|
137 |
### Training Set Metrics
|
138 |
| Training set | Min | Median | Max |
|
139 |
|:-------------|:----|:--------|:----|
|
140 |
+
| Word count | 1 | 18.8448 | 185 |
|
141 |
|
142 |
| Label | Training Sample Count |
|
143 |
|:---------|:----------------------|
|
144 |
+
| negative | 5200 |
|
145 |
+
| positive | 4943 |
|
146 |
|
147 |
### Training Hyperparameters
|
148 |
- batch_size: (32, 32)
|
|
|
159 |
- warmup_proportion: 0.1
|
160 |
- l2_weight: 0.01
|
161 |
- seed: 42
|
162 |
+
- run_name: setfit_hate_52k_ubc_6k
|
163 |
- eval_max_steps: -1
|
164 |
- load_best_model_at_end: False
|
165 |
|
166 |
### Training Results
|
167 |
| Epoch | Step | Training Loss | Validation Loss |
|
168 |
|:------:|:----:|:-------------:|:---------------:|
|
169 |
+
| 0.0003 | 1 | 0.297 | - |
|
170 |
+
| 0.0333 | 100 | 0.2741 | - |
|
171 |
+
| 0.0667 | 200 | 0.2178 | - |
|
172 |
+
| 0.1 | 300 | 0.1724 | - |
|
173 |
+
| 0.1333 | 400 | 0.1449 | - |
|
174 |
+
| 0.1667 | 500 | 0.1137 | - |
|
175 |
+
| 0.2 | 600 | 0.0902 | - |
|
176 |
+
| 0.2333 | 700 | 0.0708 | - |
|
177 |
+
| 0.2667 | 800 | 0.0535 | - |
|
178 |
+
| 0.3 | 900 | 0.0483 | - |
|
179 |
+
| 0.3333 | 1000 | 0.0386 | - |
|
180 |
+
| 0.3667 | 1100 | 0.0319 | - |
|
181 |
+
| 0.4 | 1200 | 0.0279 | - |
|
182 |
+
| 0.4333 | 1300 | 0.0201 | - |
|
183 |
+
| 0.4667 | 1400 | 0.0234 | - |
|
184 |
+
| 0.5 | 1500 | 0.0151 | - |
|
185 |
+
| 0.5333 | 1600 | 0.0151 | - |
|
186 |
+
| 0.5667 | 1700 | 0.0137 | - |
|
187 |
+
| 0.6 | 1800 | 0.0117 | - |
|
188 |
+
| 0.6333 | 1900 | 0.011 | - |
|
189 |
+
| 0.6667 | 2000 | 0.0097 | - |
|
190 |
+
| 0.7 | 2100 | 0.0077 | - |
|
191 |
+
| 0.7333 | 2200 | 0.0089 | - |
|
192 |
+
| 0.7667 | 2300 | 0.0069 | - |
|
193 |
+
| 0.8 | 2400 | 0.0064 | - |
|
194 |
+
| 0.8333 | 2500 | 0.0083 | - |
|
195 |
+
| 0.8667 | 2600 | 0.0061 | - |
|
196 |
+
| 0.9 | 2700 | 0.0063 | - |
|
197 |
+
| 0.9333 | 2800 | 0.0051 | - |
|
198 |
+
| 0.9667 | 2900 | 0.0047 | - |
|
199 |
+
| 1.0 | 3000 | 0.0044 | - |
|
200 |
+
| 1.0333 | 3100 | 0.0035 | - |
|
201 |
+
| 1.0667 | 3200 | 0.0034 | - |
|
202 |
+
| 1.1 | 3300 | 0.0035 | - |
|
203 |
+
| 1.1333 | 3400 | 0.0043 | - |
|
204 |
+
| 1.1667 | 3500 | 0.0035 | - |
|
205 |
+
| 1.2 | 3600 | 0.0024 | - |
|
206 |
+
| 1.2333 | 3700 | 0.003 | - |
|
207 |
+
| 1.2667 | 3800 | 0.002 | - |
|
208 |
+
| 1.3 | 3900 | 0.0029 | - |
|
209 |
+
| 1.3333 | 4000 | 0.003 | - |
|
210 |
+
| 1.3667 | 4100 | 0.002 | - |
|
211 |
+
| 1.4 | 4200 | 0.0022 | - |
|
212 |
+
| 1.4333 | 4300 | 0.0027 | - |
|
213 |
+
| 1.4667 | 4400 | 0.004 | - |
|
214 |
+
| 1.5 | 4500 | 0.001 | - |
|
215 |
+
| 1.5333 | 4600 | 0.0027 | - |
|
216 |
+
| 1.5667 | 4700 | 0.0027 | - |
|
217 |
+
| 1.6 | 4800 | 0.0014 | - |
|
218 |
+
| 1.6333 | 4900 | 0.0022 | - |
|
219 |
+
| 1.6667 | 5000 | 0.0027 | - |
|
220 |
+
| 1.7 | 5100 | 0.0018 | - |
|
221 |
+
| 1.7333 | 5200 | 0.0018 | - |
|
222 |
+
| 1.7667 | 5300 | 0.0012 | - |
|
223 |
+
| 1.8 | 5400 | 0.0014 | - |
|
224 |
+
| 1.8333 | 5500 | 0.0015 | - |
|
225 |
+
| 1.8667 | 5600 | 0.0009 | - |
|
226 |
+
| 1.9 | 5700 | 0.0012 | - |
|
227 |
+
| 1.9333 | 5800 | 0.0009 | - |
|
228 |
+
| 1.9667 | 5900 | 0.001 | - |
|
229 |
| 2.0 | 6000 | 0.0007 | - |
|
230 |
|
231 |
### Framework Versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 651387752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ca212885b354e2a93b81a2c1a092367e37c2f0bced3dfc5577867667b4e0dab
|
3 |
size 651387752
|
model_head.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7007
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80630f7e418ad330a84cd6bd6246c1621e96731309f6165206b70612ced30280
|
3 |
size 7007
|