Add SetFit model
Browse files- README.md +12 -10
- config_setfit.json +2 -2
- model.safetensors +1 -1
- model_head.pkl +1 -1
README.md
CHANGED
@@ -62,10 +62,10 @@ 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 |
|
@@ -124,12 +124,12 @@ preds = model("The product is out of stock")
|
|
124 |
### Training Set Metrics
|
125 |
| Training set | Min | Median | Max |
|
126 |
|:-------------|:----|:-------|:----|
|
127 |
-
| Word count | 4 |
|
128 |
|
129 |
| Label | Training Sample Count |
|
130 |
|:------|:----------------------|
|
131 |
-
| 0 |
|
132 |
-
| 1 |
|
133 |
|
134 |
### Training Hyperparameters
|
135 |
- batch_size: (16, 16)
|
@@ -150,9 +150,11 @@ preds = model("The product is out of stock")
|
|
150 |
- load_best_model_at_end: False
|
151 |
|
152 |
### Training Results
|
153 |
-
| Epoch
|
154 |
-
|
155 |
-
| 0.
|
|
|
|
|
156 |
|
157 |
### Framework Versions
|
158 |
- Python: 3.11.8
|
|
|
62 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
63 |
|
64 |
### Model Labels
|
65 |
+
| Label | Examples |
|
66 |
+
|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
67 |
+
| 0 | <ul><li>'I need to speak to a real person, not a dumb machine.'</li><li>'Stop with the automated nonsense and connect me to a human!'</li><li>'Your automated system is beyond frustrating, let me talk to someone!'</li></ul> |
|
68 |
+
| 1 | <ul><li>'I love your new product!'</li><li>'The delivery was very quick!'</li><li>'I would recommend this company to a friend'</li></ul> |
|
69 |
|
70 |
## Evaluation
|
71 |
|
|
|
124 |
### Training Set Metrics
|
125 |
| Training set | Min | Median | Max |
|
126 |
|:-------------|:----|:-------|:----|
|
127 |
+
| Word count | 4 | 10.0 | 14 |
|
128 |
|
129 |
| Label | Training Sample Count |
|
130 |
|:------|:----------------------|
|
131 |
+
| 0 | 46 |
|
132 |
+
| 1 | 6 |
|
133 |
|
134 |
### Training Hyperparameters
|
135 |
- batch_size: (16, 16)
|
|
|
150 |
- load_best_model_at_end: False
|
151 |
|
152 |
### Training Results
|
153 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
154 |
+
|:------:|:----:|:-------------:|:---------------:|
|
155 |
+
| 0.0077 | 1 | 0.1479 | - |
|
156 |
+
| 0.3846 | 50 | 0.0008 | - |
|
157 |
+
| 0.7692 | 100 | 0.0005 | - |
|
158 |
|
159 |
### Framework Versions
|
160 |
- Python: 3.11.8
|
config_setfit.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
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:
|
3 |
size 265462608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12036439de3b12ed53c9df4c6012291dc214f27d9e9813e4f1607f62826a704a
|
3 |
size 265462608
|
model_head.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7013
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcc435cc39a180f5ee67295ca54a394ec08fb6c3d76b57543a2e615ba98b0cda
|
3 |
size 7013
|