Upload v0.1
Browse files- README.md +46 -78
- model.safetensors +1 -1
- model_head.pkl +0 -0
README.md
CHANGED
|
@@ -5,35 +5,17 @@ tags:
|
|
| 5 |
- text-classification
|
| 6 |
- generated_from_setfit_trainer
|
| 7 |
widget:
|
| 8 |
-
- text:
|
| 9 |
-
- text: what
|
| 10 |
-
- text:
|
| 11 |
-
- text:
|
| 12 |
-
- text:
|
| 13 |
metrics:
|
| 14 |
- accuracy
|
| 15 |
-
- f1
|
| 16 |
pipeline_tag: text-classification
|
| 17 |
library_name: setfit
|
| 18 |
inference: true
|
| 19 |
base_model: BAAI/bge-small-en-v1.5
|
| 20 |
-
model-index:
|
| 21 |
-
- name: SetFit with BAAI/bge-small-en-v1.5
|
| 22 |
-
results:
|
| 23 |
-
- task:
|
| 24 |
-
type: text-classification
|
| 25 |
-
name: Text Classification
|
| 26 |
-
dataset:
|
| 27 |
-
name: Unknown
|
| 28 |
-
type: unknown
|
| 29 |
-
split: test
|
| 30 |
-
metrics:
|
| 31 |
-
- type: accuracy
|
| 32 |
-
value: 0.9864864864864865
|
| 33 |
-
name: Accuracy
|
| 34 |
-
- type: f1
|
| 35 |
-
value: 0.9861111111111112
|
| 36 |
-
name: F1
|
| 37 |
---
|
| 38 |
|
| 39 |
# SetFit with BAAI/bge-small-en-v1.5
|
|
@@ -69,13 +51,6 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
| 69 |
| 1 | <ul><li>'how far is palms casino from the airport in las vegas'</li><li>'anarkali bazar lahore'</li><li>'what county is alma nebraska in?'</li></ul> |
|
| 70 |
| 0 | <ul><li>'what is symptom of bipolar disorder'</li><li>'early symptoms of shingles outbreak'</li><li>'bnsf total employees'</li></ul> |
|
| 71 |
|
| 72 |
-
## Evaluation
|
| 73 |
-
|
| 74 |
-
### Metrics
|
| 75 |
-
| Label | Accuracy | F1 |
|
| 76 |
-
|:--------|:---------|:-------|
|
| 77 |
-
| **all** | 0.9865 | 0.9861 |
|
| 78 |
-
|
| 79 |
## Uses
|
| 80 |
|
| 81 |
### Direct Use for Inference
|
|
@@ -94,7 +69,7 @@ from setfit import SetFitModel
|
|
| 94 |
# Download from the 🤗 Hub
|
| 95 |
model = SetFitModel.from_pretrained("setfit_model_id")
|
| 96 |
# Run inference
|
| 97 |
-
preds = model("
|
| 98 |
```
|
| 99 |
|
| 100 |
<!--
|
|
@@ -126,12 +101,12 @@ preds = model("how old is jacob sar")
|
|
| 126 |
### Training Set Metrics
|
| 127 |
| Training set | Min | Median | Max |
|
| 128 |
|:-------------|:----|:-------|:----|
|
| 129 |
-
| Word count | 2 | 6.
|
| 130 |
|
| 131 |
| Label | Training Sample Count |
|
| 132 |
|:------|:----------------------|
|
| 133 |
-
| 0 |
|
| 134 |
-
| 1 |
|
| 135 |
|
| 136 |
### Training Hyperparameters
|
| 137 |
- batch_size: (64, 64)
|
|
@@ -149,52 +124,45 @@ preds = model("how old is jacob sar")
|
|
| 149 |
- l2_weight: 0.01
|
| 150 |
- seed: 42
|
| 151 |
- eval_max_steps: -1
|
| 152 |
-
- load_best_model_at_end:
|
| 153 |
|
| 154 |
### Training Results
|
| 155 |
-
| Epoch | Step
|
| 156 |
-
|
| 157 |
-
| 0.0001 | 1
|
| 158 |
-
| 0.
|
| 159 |
-
| 0.
|
| 160 |
-
| 0.
|
| 161 |
-
| 0.
|
| 162 |
-
| 0.
|
| 163 |
-
| 0.
|
| 164 |
-
| 0.
|
| 165 |
-
| 0.
|
| 166 |
-
| 0.
|
| 167 |
-
| 0.
|
| 168 |
-
| 0.
|
| 169 |
-
| 0.
|
| 170 |
-
| 0.
|
| 171 |
-
| 0.
|
| 172 |
-
| 0.
|
| 173 |
-
| 0.
|
| 174 |
-
| 0.
|
| 175 |
-
| 0.
|
| 176 |
-
| 0.
|
| 177 |
-
| 0.
|
| 178 |
-
| 0.
|
| 179 |
-
| 0.
|
| 180 |
-
| 0.
|
| 181 |
-
| 0.
|
| 182 |
-
| 0.
|
| 183 |
-
| 0.
|
| 184 |
-
| 0.
|
| 185 |
-
| 0.
|
| 186 |
-
| 0.
|
| 187 |
-
| 0.
|
| 188 |
-
| 0.
|
| 189 |
-
| 0.
|
| 190 |
-
| 0.
|
| 191 |
-
| 0.1567 | 1700 | 0.0006 | - |
|
| 192 |
-
| 0.1613 | 1750 | 0.0009 | - |
|
| 193 |
-
| 0.1659 | 1800 | 0.0007 | - |
|
| 194 |
-
| 0.1705 | 1850 | 0.0006 | - |
|
| 195 |
-
| 0.1751 | 1900 | 0.0006 | - |
|
| 196 |
-
| 0.1798 | 1950 | 0.0006 | - |
|
| 197 |
-
| 0.1844 | 2000 | 0.0005 | 0.0663 |
|
| 198 |
|
| 199 |
### Framework Versions
|
| 200 |
- Python: 3.11.5
|
|
|
|
| 5 |
- text-classification
|
| 6 |
- generated_from_setfit_trainer
|
| 7 |
widget:
|
| 8 |
+
- text: hotel in geneva airport
|
| 9 |
+
- text: what payroll deduction is mpp
|
| 10 |
+
- text: weather in erlanger ky
|
| 11 |
+
- text: what is the coordinates of point p
|
| 12 |
+
- text: what's the weather in roseburg
|
| 13 |
metrics:
|
| 14 |
- accuracy
|
|
|
|
| 15 |
pipeline_tag: text-classification
|
| 16 |
library_name: setfit
|
| 17 |
inference: true
|
| 18 |
base_model: BAAI/bge-small-en-v1.5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
---
|
| 20 |
|
| 21 |
# SetFit with BAAI/bge-small-en-v1.5
|
|
|
|
| 51 |
| 1 | <ul><li>'how far is palms casino from the airport in las vegas'</li><li>'anarkali bazar lahore'</li><li>'what county is alma nebraska in?'</li></ul> |
|
| 52 |
| 0 | <ul><li>'what is symptom of bipolar disorder'</li><li>'early symptoms of shingles outbreak'</li><li>'bnsf total employees'</li></ul> |
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
## Uses
|
| 55 |
|
| 56 |
### Direct Use for Inference
|
|
|
|
| 69 |
# Download from the 🤗 Hub
|
| 70 |
model = SetFitModel.from_pretrained("setfit_model_id")
|
| 71 |
# Run inference
|
| 72 |
+
preds = model("weather in erlanger ky")
|
| 73 |
```
|
| 74 |
|
| 75 |
<!--
|
|
|
|
| 101 |
### Training Set Metrics
|
| 102 |
| Training set | Min | Median | Max |
|
| 103 |
|:-------------|:----|:-------|:----|
|
| 104 |
+
| Word count | 2 | 6.3028 | 21 |
|
| 105 |
|
| 106 |
| Label | Training Sample Count |
|
| 107 |
|:------|:----------------------|
|
| 108 |
+
| 0 | 755 |
|
| 109 |
+
| 1 | 718 |
|
| 110 |
|
| 111 |
### Training Hyperparameters
|
| 112 |
- batch_size: (64, 64)
|
|
|
|
| 124 |
- l2_weight: 0.01
|
| 125 |
- seed: 42
|
| 126 |
- eval_max_steps: -1
|
| 127 |
+
- load_best_model_at_end: False
|
| 128 |
|
| 129 |
### Training Results
|
| 130 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
| 131 |
+
|:------:|:-----:|:-------------:|:---------------:|
|
| 132 |
+
| 0.0001 | 1 | 0.2507 | - |
|
| 133 |
+
| 0.0294 | 500 | 0.1803 | - |
|
| 134 |
+
| 0.0589 | 1000 | 0.0135 | - |
|
| 135 |
+
| 0.0883 | 1500 | 0.0021 | - |
|
| 136 |
+
| 0.1178 | 2000 | 0.001 | - |
|
| 137 |
+
| 0.1472 | 2500 | 0.0007 | - |
|
| 138 |
+
| 0.1766 | 3000 | 0.0005 | - |
|
| 139 |
+
| 0.2061 | 3500 | 0.0004 | - |
|
| 140 |
+
| 0.2355 | 4000 | 0.0004 | - |
|
| 141 |
+
| 0.2649 | 4500 | 0.0003 | - |
|
| 142 |
+
| 0.2944 | 5000 | 0.0003 | - |
|
| 143 |
+
| 0.3238 | 5500 | 0.0003 | - |
|
| 144 |
+
| 0.3533 | 6000 | 0.0003 | - |
|
| 145 |
+
| 0.3827 | 6500 | 0.0002 | - |
|
| 146 |
+
| 0.4121 | 7000 | 0.0003 | - |
|
| 147 |
+
| 0.4416 | 7500 | 0.0002 | - |
|
| 148 |
+
| 0.4710 | 8000 | 0.0002 | - |
|
| 149 |
+
| 0.5004 | 8500 | 0.0002 | - |
|
| 150 |
+
| 0.5299 | 9000 | 0.0002 | - |
|
| 151 |
+
| 0.5593 | 9500 | 0.0002 | - |
|
| 152 |
+
| 0.5888 | 10000 | 0.0002 | - |
|
| 153 |
+
| 0.6182 | 10500 | 0.0002 | - |
|
| 154 |
+
| 0.6476 | 11000 | 0.0001 | - |
|
| 155 |
+
| 0.6771 | 11500 | 0.0001 | - |
|
| 156 |
+
| 0.7065 | 12000 | 0.0001 | - |
|
| 157 |
+
| 0.7359 | 12500 | 0.0001 | - |
|
| 158 |
+
| 0.7654 | 13000 | 0.0001 | - |
|
| 159 |
+
| 0.7948 | 13500 | 0.0001 | - |
|
| 160 |
+
| 0.8243 | 14000 | 0.0001 | - |
|
| 161 |
+
| 0.8537 | 14500 | 0.0001 | - |
|
| 162 |
+
| 0.8831 | 15000 | 0.0001 | - |
|
| 163 |
+
| 0.9126 | 15500 | 0.0001 | - |
|
| 164 |
+
| 0.9420 | 16000 | 0.0001 | - |
|
| 165 |
+
| 0.9714 | 16500 | 0.0001 | - |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 166 |
|
| 167 |
### Framework Versions
|
| 168 |
- Python: 3.11.5
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 133462128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:487f5a8abf3dfc01c20f682fea8260245f8d65dc1c360034de899a102e8e271f
|
| 3 |
size 133462128
|
model_head.pkl
CHANGED
|
Binary files a/model_head.pkl and b/model_head.pkl differ
|
|
|