vishalp23 commited on
Commit
5f49a75
·
verified ·
1 Parent(s): f30dde3

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +26 -26
README.md CHANGED
@@ -19,7 +19,7 @@ dataset_name: New
19
 
20
  <!-- Provide a longer summary of what this model is. -->
21
 
22
- Auto Fine-tuned acuvity/model_integration_test for text-classification task. The run id is v0.0.2
23
 
24
  - **Developed by:** Auto-Finetune Bot
25
  - **Funded by [optional]:** Auto-Finetune Bot
@@ -103,7 +103,7 @@ classifier("Hello, my dog is cute")
103
 
104
  <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
105
 
106
- (New | v0.0.2) [https://huggingface.co/datasets/acuvity/New]
107
 
108
  ### Training Procedure
109
 
@@ -134,7 +134,7 @@ No modifications done on the dataset.
134
 
135
  <!-- This should link to a Dataset Card if possible. -->
136
 
137
- (New | v0.0.2) [https://huggingface.co/datasets/acuvity/New]
138
 
139
  #### Factors
140
 
@@ -153,36 +153,36 @@ No modifications done on the dataset.
153
 
154
  # Auto Finetune Report for Prompt Injection
155
  ## Model URL: acuvity/model_integration_test
156
- ## Model Commit: v0.0.2
157
 
158
  ## Quick Summary
159
 
160
- Accuracy: 0.014995313964386137
161
- Regression: 0.030901660532351393
162
- Improvement: 0.14807888125828456
163
 
164
  ## Results Summary
165
 
166
- ### Prompt Injection | v0.0.2 Results
167
 
168
  | | accuracy | f1 | precision | recall |
169
  |:---------|-----------:|----------:|------------:|---------:|
170
- | New | 0.996251 | 0.995984 | 1 | 0.992 |
171
- | Baseline | 0.998 | 0.997988 | 1 | 0.995984 |
172
- | Feedback | 0.833333 | 0 | 0 | 0 |
173
- | QA | 0.980398 | 0 | 0 | 0 |
174
- | PINT | 0.0804789 | 0.0972902 | 0.0523726 | 0.683486 |
175
- | Sanity | 0.652174 | 0.789474 | 0.652174 | 1 |
176
  ----------------------------------------------------
177
- ### Prompt Injection | v0.0.1 Results
178
- | | accuracy | f1 | precision | recall |
179
- |:---------|-----------:|---------:|------------:|---------:|
180
- | New | 0.981256 | 0.980159 | 0.995968 | 0.964844 |
181
- | Baseline | 0.993 | 0.992965 | 0.995968 | 0.98998 |
182
- | Feedback | 0 | 0 | 0 | 0 |
183
- | QA | 0.973455 | 0 | 0 | 0 |
184
- | PINT | 0.122049 | 0.175515 | 0.0987698 | 0.787115 |
185
- | Sanity | 0.76087 | 0.864198 | 0.76087 | 1 |
186
 
187
 
188
 
@@ -233,9 +233,9 @@ Quadro P4000
233
 
234
  | | 0 |
235
  |:---------------------|:------------|
236
- | python_version | 3.10.12 |
237
- | pytorch_version | 2.1.2+cu121 |
238
- | transformers_version | 4.49.0 |
239
  | datasets_version | 3.2.0 |
240
 
241
  ## Citation [optional]
 
19
 
20
  <!-- Provide a longer summary of what this model is. -->
21
 
22
+ Auto Fine-tuned acuvity/model_integration_test for text-classification task. The run id is v0.0.4
23
 
24
  - **Developed by:** Auto-Finetune Bot
25
  - **Funded by [optional]:** Auto-Finetune Bot
 
103
 
104
  <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
105
 
106
+ (New | v0.0.4) [https://huggingface.co/datasets/acuvity/New]
107
 
108
  ### Training Procedure
109
 
 
134
 
135
  <!-- This should link to a Dataset Card if possible. -->
136
 
137
+ (New | v0.0.4) [https://huggingface.co/datasets/acuvity/New]
138
 
139
  #### Factors
140
 
 
153
 
154
  # Auto Finetune Report for Prompt Injection
155
  ## Model URL: acuvity/model_integration_test
156
+ ## Model Commit: v0.0.4
157
 
158
  ## Quick Summary
159
 
160
+ Accuracy: 0.0008237232289950436
161
+ Regression: 0.0006873789967815756
162
+ Improvement: 0.0009149276196107874
163
 
164
  ## Results Summary
165
 
166
+ ### Prompt Injection | v0.0.4 Results
167
 
168
  | | accuracy | f1 | precision | recall |
169
  |:---------|-----------:|----------:|------------:|---------:|
170
+ | New | 0.999176 | 0.998993 | 1 | 0.997988 |
171
+ | Baseline | 0.999126 | 0.998993 | 1 | 0.997988 |
172
+ | Feedback | 1 | 0 | 0 | 0 |
173
+ | QA | 0.982216 | 0 | 0 | 0 |
174
+ | PINT | 0.0701696 | 0.0790514 | 0.0421793 | 0.628272 |
175
+ | Sanity | 0.630435 | 0.773333 | 0.630435 | 1 |
176
  ----------------------------------------------------
177
+ ### Prompt Injection | v0.0.3 Results
178
+ | | accuracy | f1 | precision | recall |
179
+ |:---------|-----------:|----------:|------------:|---------:|
180
+ | New | 0.998353 | 0.997988 | 1 | 0.995984 |
181
+ | Baseline | 0.998252 | 0.997988 | 1 | 0.995984 |
182
+ | Feedback | 1 | 0 | 0 | 0 |
183
+ | QA | 0.98164 | 0 | 0 | 0 |
184
+ | PINT | 0.0705022 | 0.0808944 | 0.0432337 | 0.627551 |
185
+ | Sanity | 0.630435 | 0.773333 | 0.630435 | 1 |
186
 
187
 
188
 
 
233
 
234
  | | 0 |
235
  |:---------------------|:------------|
236
+ | python_version | 3.10.16 |
237
+ | pytorch_version | 2.5.1+cu124 |
238
+ | transformers_version | 4.47.1 |
239
  | datasets_version | 3.2.0 |
240
 
241
  ## Citation [optional]