Hugging Face's logo

ehsanhallo
/
setfit-paraphrase-multilingual-MiniLM-L12-v2-ig-fa

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Eval Results
Model card Files Community
ehsanhallo commited on
Commit
1cb1519
•
1 Parent(s): fccd4ae

Add SetFit model

Browse files
Files changed (4) hide show
  1. README.md +54 -45
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. model_head.pkl +1 -1
README.md CHANGED
@@ -29,7 +29,7 @@ model-index:
29
  split: test
30
  metrics:
31
  - type: accuracy
32
- value: 0.77
33
  name: Accuracy
34
  ---
35
 
@@ -72,7 +72,7 @@ The model has been trained using an efficient few-shot learning technique that i
72
  ### Metrics
73
  | Label | Accuracy |
74
  |:--------|:---------|
75
- | **all** | 0.77 |
76
 
77
  ## Uses
78
 
@@ -124,17 +124,17 @@ preds = model(" where`d you go!")
124
  ### Training Set Metrics
125
  | Training set | Min | Median | Max |
126
  |:-------------|:----|:-------|:----|
127
- | Word count | 1 | 7.0 | 75 |
128
 
129
  | Label | Training Sample Count |
130
  |:------|:----------------------|
131
- | 0 | 31 |
132
- | 1 | 131 |
133
- | 2 | 364 |
134
 
135
  ### Training Hyperparameters
136
  - batch_size: (32, 16)
137
- - num_epochs: (2, 4)
138
  - max_steps: -1
139
  - sampling_strategy: oversampling
140
  - body_learning_rate: (2e-05, 5e-06)
@@ -153,44 +153,53 @@ preds = model(" where`d you go!")
153
  ### Training Results
154
  | Epoch | Step | Training Loss | Validation Loss |
155
  |:----------:|:--------:|:-------------:|:---------------:|
156
- | 0.0002 | 1 | 0.1854 | - |
157
- | 0.0529 | 250 | 0.0626 | - |
158
- | 0.1058 | 500 | 0.0034 | 0.2484 |
159
- | 0.1588 | 750 | 0.0029 | - |
160
- | 0.2117 | 1000 | 0.001 | 0.1899 |
161
- | 0.2646 | 1250 | 0.0001 | - |
162
- | **0.3175** | **1500** | **0.0001** | **0.1849** |
163
- | 0.3704 | 1750 | 0.0001 | - |
164
- | 0.4234 | 2000 | 0.0001 | 0.1876 |
165
- | 0.4763 | 2250 | 0.0001 | - |
166
- | 0.5292 | 2500 | 0.0 | 0.1888 |
167
- | 0.5821 | 2750 | 0.0001 | - |
168
- | 0.6351 | 3000 | 0.0 | 0.1885 |
169
- | 0.6880 | 3250 | 0.0 | - |
170
- | 0.7409 | 3500 | 0.0 | 0.1915 |
171
- | 0.7938 | 3750 | 0.0 | - |
172
- | 0.8467 | 4000 | 0.0 | 0.1947 |
173
- | 0.8997 | 4250 | 0.0 | - |
174
- | 0.9526 | 4500 | 0.0 | 0.1986 |
175
- | 1.0055 | 4750 | 0.0 | - |
176
- | 1.0584 | 5000 | 0.0 | 0.207 |
177
- | 1.1113 | 5250 | 0.0 | - |
178
- | 1.1643 | 5500 | 0.0 | 0.2078 |
179
- | 1.2172 | 5750 | 0.0 | - |
180
- | 1.2701 | 6000 | 0.0 | 0.2096 |
181
- | 1.3230 | 6250 | 0.0 | - |
182
- | 1.3760 | 6500 | 0.0 | 0.2095 |
183
- | 1.4289 | 6750 | 0.0 | - |
184
- | 1.4818 | 7000 | 0.0 | 0.2103 |
185
- | 1.5347 | 7250 | 0.0 | - |
186
- | 1.5876 | 7500 | 0.0 | 0.2133 |
187
- | 1.6406 | 7750 | 0.0 | - |
188
- | 1.6935 | 8000 | 0.0 | 0.2154 |
189
- | 1.7464 | 8250 | 0.0 | - |
190
- | 1.7993 | 8500 | 0.0 | 0.2141 |
191
- | 1.8522 | 8750 | 0.0 | - |
192
- | 1.9052 | 9000 | 0.0 | 0.2141 |
193
- | 1.9581 | 9250 | 0.0 | - |
 
 
 
 
 
 
 
 
 
194
 
195
  * The bold row denotes the saved checkpoint.
196
  ### Framework Versions
 
29
  split: test
30
  metrics:
31
  - type: accuracy
32
+ value: 0.79
33
  name: Accuracy
34
  ---
35
 
 
72
  ### Metrics
73
  | Label | Accuracy |
74
  |:--------|:---------|
75
+ | **all** | 0.79 |
76
 
77
  ## Uses
78
 
 
124
  ### Training Set Metrics
125
  | Training set | Min | Median | Max |
126
  |:-------------|:----|:-------|:----|
127
+ | Word count | 1 | 6.4184 | 75 |
128
 
129
  | Label | Training Sample Count |
130
  |:------|:----------------------|
131
+ | 0 | 69 |
132
+ | 1 | 238 |
133
+ | 2 | 551 |
134
 
135
  ### Training Hyperparameters
136
  - batch_size: (32, 16)
137
+ - num_epochs: (1, 2)
138
  - max_steps: -1
139
  - sampling_strategy: oversampling
140
  - body_learning_rate: (2e-05, 5e-06)
 
153
  ### Training Results
154
  | Epoch | Step | Training Loss | Validation Loss |
155
  |:----------:|:--------:|:-------------:|:---------------:|
156
+ | 0.0001 | 1 | 0.1767 | - |
157
+ | 0.0216 | 250 | 0.1513 | - |
158
+ | 0.0431 | 500 | 0.0629 | 0.2389 |
159
+ | 0.0647 | 750 | 0.0351 | - |
160
+ | 0.0862 | 1000 | 0.0015 | 0.1886 |
161
+ | 0.1078 | 1250 | 0.0003 | - |
162
+ | 0.1293 | 1500 | 0.0004 | 0.1813 |
163
+ | 0.1509 | 1750 | 0.0002 | - |
164
+ | **0.1724** | **2000** | **0.0002** | **0.1807** |
165
+ | 0.1940 | 2250 | 0.0001 | - |
166
+ | 0.2155 | 2500 | 0.0001 | 0.187 |
167
+ | 0.2371 | 2750 | 0.0001 | - |
168
+ | 0.2586 | 3000 | 0.0001 | 0.1903 |
169
+ | 0.2802 | 3250 | 0.0001 | - |
170
+ | 0.3018 | 3500 | 0.0 | 0.1864 |
171
+ | 0.3233 | 3750 | 0.0 | - |
172
+ | 0.3449 | 4000 | 0.0 | 0.193 |
173
+ | 0.3664 | 4250 | 0.0 | - |
174
+ | 0.3880 | 4500 | 0.0 | 0.1879 |
175
+ | 0.4095 | 4750 | 0.0 | - |
176
+ | 0.4311 | 5000 | 0.0 | 0.1887 |
177
+ | 0.4526 | 5250 | 0.0 | - |
178
+ | 0.4742 | 5500 | 0.0 | 0.187 |
179
+ | 0.4957 | 5750 | 0.0 | - |
180
+ | 0.5173 | 6000 | 0.0001 | 0.205 |
181
+ | 0.5388 | 6250 | 0.0 | - |
182
+ | 0.5604 | 6500 | 0.0 | 0.205 |
183
+ | 0.5819 | 6750 | 0.0 | - |
184
+ | 0.6035 | 7000 | 0.0 | 0.2018 |
185
+ | 0.6251 | 7250 | 0.0 | - |
186
+ | 0.6466 | 7500 | 0.0 | 0.2022 |
187
+ | 0.6682 | 7750 | 0.0 | - |
188
+ | 0.6897 | 8000 | 0.0 | 0.2063 |
189
+ | 0.7113 | 8250 | 0.0 | - |
190
+ | 0.7328 | 8500 | 0.0 | 0.2143 |
191
+ | 0.7544 | 8750 | 0.0 | - |
192
+ | 0.7759 | 9000 | 0.0 | 0.2206 |
193
+ | 0.7975 | 9250 | 0.0 | - |
194
+ | 0.8190 | 9500 | 0.0 | 0.2167 |
195
+ | 0.8406 | 9750 | 0.0 | - |
196
+ | 0.8621 | 10000 | 0.0 | 0.2176 |
197
+ | 0.8837 | 10250 | 0.0 | - |
198
+ | 0.9053 | 10500 | 0.0 | 0.217 |
199
+ | 0.9268 | 10750 | 0.0 | - |
200
+ | 0.9484 | 11000 | 0.0 | 0.2153 |
201
+ | 0.9699 | 11250 | 0.0 | - |
202
+ | 0.9915 | 11500 | 0.0 | 0.2137 |
203
 
204
  * The bold row denotes the saved checkpoint.
205
  ### Framework Versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/content/drive/MyDrive/sentiment/train_output/step_1500/",
3
  "architectures": [
4
  "BertModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "/content/drive/MyDrive/sentiment/train_output/step_2000/",
3
  "architectures": [
4
  "BertModel"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2427ed2a40bad5f431b7d4d1fb03e42470b0cc80973c78b6f95fc9f51c37c804
3
  size 470637416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6665a57ac0643bd06f1adbb5a7e6d9ed98eaadb3a4a6d735d74008e5e56c9fe5
3
  size 470637416
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fab1dbb593ba765d69bc7cc97e81932a089bcf4f98f972ba79f9227585bb1a5c
3
  size 10095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b663bdb6fe7fcd8230aacb1f9ab85c3bc06f4291f0b635d5823b6e2cabf7b514
3
  size 10095