patrickfleith
commited on
Commit
•
30f0705
1
Parent(s):
853f4a5
Push model using huggingface_hub.
Browse files- README.md +37 -29
- config_setfit.json +3 -2
- model.safetensors +1 -1
- model_head.pkl +2 -2
README.md
CHANGED
@@ -10,16 +10,17 @@ tags:
|
|
10 |
- text-classification
|
11 |
- generated_from_setfit_trainer
|
12 |
widget:
|
13 |
-
- text:
|
14 |
-
|
15 |
-
- text:
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
|
|
23 |
inference: true
|
24 |
model-index:
|
25 |
- name: SetFit with BAAI/bge-small-en-v1.5
|
@@ -33,7 +34,7 @@ model-index:
|
|
33 |
split: test
|
34 |
metrics:
|
35 |
- type: accuracy
|
36 |
-
value: 0
|
37 |
name: Accuracy
|
38 |
---
|
39 |
|
@@ -53,7 +54,7 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
53 |
- **Sentence Transformer body:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5)
|
54 |
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
55 |
- **Maximum Sequence Length:** 512 tokens
|
56 |
-
- **Number of Classes:**
|
57 |
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
58 |
<!-- - **Language:** Unknown -->
|
59 |
<!-- - **License:** Unknown -->
|
@@ -65,17 +66,18 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
65 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
66 |
|
67 |
### Model Labels
|
68 |
-
| Label
|
69 |
-
|
70 |
-
|
|
71 |
-
|
|
|
|
72 |
|
73 |
## Evaluation
|
74 |
|
75 |
### Metrics
|
76 |
| Label | Accuracy |
|
77 |
|:--------|:---------|
|
78 |
-
| **all** | 0
|
79 |
|
80 |
## Uses
|
81 |
|
@@ -95,7 +97,7 @@ from setfit import SetFitModel
|
|
95 |
# Download from the 🤗 Hub
|
96 |
model = SetFitModel.from_pretrained("patrickfleith/setfit-bge-small-v1.5-sst2-8-shot")
|
97 |
# Run inference
|
98 |
-
preds = model("
|
99 |
```
|
100 |
|
101 |
<!--
|
@@ -125,14 +127,15 @@ preds = model("it 's refreshing to see a romance this smart .")
|
|
125 |
## Training Details
|
126 |
|
127 |
### Training Set Metrics
|
128 |
-
| Training set | Min | Median
|
129 |
-
|
130 |
-
| Word count |
|
131 |
|
132 |
-
| Label
|
133 |
-
|
134 |
-
|
|
135 |
-
|
|
|
|
136 |
|
137 |
### Training Hyperparameters
|
138 |
- batch_size: (32, 32)
|
@@ -152,10 +155,15 @@ preds = model("it 's refreshing to see a romance this smart .")
|
|
152 |
- load_best_model_at_end: False
|
153 |
|
154 |
### Training Results
|
155 |
-
| Epoch
|
156 |
-
|
157 |
-
| 0.
|
158 |
-
|
|
|
|
|
|
|
|
|
|
|
|
159 |
|
160 |
### Framework Versions
|
161 |
- Python: 3.10.12
|
|
|
10 |
- text-classification
|
11 |
- generated_from_setfit_trainer
|
12 |
widget:
|
13 |
+
- text: Autonomous diagnostic and recovery protocols are embedded within the power
|
14 |
+
management system to isolate and rectify faults, ensuring mission continuity.
|
15 |
+
- text: The satellite thermal control subsystem (TCS) is crucial for maintaining operational
|
16 |
+
temperatures of all onboard instruments and systems within their specified limits.
|
17 |
+
- text: How does the choice of oxidizer, such as liquid oxygen or nitrogen tetroxide,
|
18 |
+
affect the performance and handling requirements of a rocket engine?
|
19 |
+
- text: The energy conversion efficiency of solar cells is influenced by factors such
|
20 |
+
as temperature, radiation exposure, and the angle of incidence of sunlight, necessitating
|
21 |
+
adaptive control mechanisms.
|
22 |
+
- text: The thermal control subsystem must accommodate both internal heat generated
|
23 |
+
by electronic components and external thermal loads from the space environment.
|
24 |
inference: true
|
25 |
model-index:
|
26 |
- name: SetFit with BAAI/bge-small-en-v1.5
|
|
|
34 |
split: test
|
35 |
metrics:
|
36 |
- type: accuracy
|
37 |
+
value: 1.0
|
38 |
name: Accuracy
|
39 |
---
|
40 |
|
|
|
54 |
- **Sentence Transformer body:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5)
|
55 |
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
56 |
- **Maximum Sequence Length:** 512 tokens
|
57 |
+
- **Number of Classes:** 3 classes
|
58 |
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
59 |
<!-- - **Language:** Unknown -->
|
60 |
<!-- - **License:** Unknown -->
|
|
|
66 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
67 |
|
68 |
### Model Labels
|
69 |
+
| Label | Examples |
|
70 |
+
|:----------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
71 |
+
| Power Subsystem | <ul><li>'The electrical generation capability of a satellite is primarily determined by the efficiency and surface area of its photovoltaic cells, which convert incident solar radiation into electrical energy.'</li><li>'Energy distribution within the satellite is managed by a network of bus bars and wiring harnesses, designed to minimize resistive losses and maintain voltage stability across all operational conditions.'</li><li>'Redundant power paths and autonomous fault detection mechanisms are implemented to ensure continuous electrical supply even in the event of subsystem failures or external anomalies.'</li></ul> |
|
72 |
+
| Thermal Control | <ul><li>'Discuss the significance of thermal isolation techniques in preventing heat transfer between satellite components.'</li><li>'The thermal emissivity of radiators and heat pipes is optimized to dissipate the excess heat generated by power electronics, maintaining thermal equilibrium within the satellite.'</li><li>'Deployable radiators can be utilized to increase the heat rejection capacity of a satellite, particularly during high-power operational phases.'</li></ul> |
|
73 |
+
| Propulsion | <ul><li>'The combustion efficiency of a rocket engine depends on factors like propellant mixture ratio, injector design, and combustion chamber pressure.'</li><li>'Liquid rocket engines utilize cryogenic fuels and oxidizers, such as liquid hydrogen and liquid oxygen, which require complex storage and handling systems to maintain their extremely low temperatures.'</li><li>'The nozzle design, including its shape and expansion ratio, significantly influences the exhaust velocity and overall thrust of a rocket engine.'</li></ul> |
|
74 |
|
75 |
## Evaluation
|
76 |
|
77 |
### Metrics
|
78 |
| Label | Accuracy |
|
79 |
|:--------|:---------|
|
80 |
+
| **all** | 1.0 |
|
81 |
|
82 |
## Uses
|
83 |
|
|
|
97 |
# Download from the 🤗 Hub
|
98 |
model = SetFitModel.from_pretrained("patrickfleith/setfit-bge-small-v1.5-sst2-8-shot")
|
99 |
# Run inference
|
100 |
+
preds = model("How does the choice of oxidizer, such as liquid oxygen or nitrogen tetroxide, affect the performance and handling requirements of a rocket engine?")
|
101 |
```
|
102 |
|
103 |
<!--
|
|
|
127 |
## Training Details
|
128 |
|
129 |
### Training Set Metrics
|
130 |
+
| Training set | Min | Median | Max |
|
131 |
+
|:-------------|:----|:--------|:----|
|
132 |
+
| Word count | 11 | 23.2632 | 30 |
|
133 |
|
134 |
+
| Label | Training Sample Count |
|
135 |
+
|:----------------|:----------------------|
|
136 |
+
| Propulsion | 13 |
|
137 |
+
| Thermal Control | 13 |
|
138 |
+
| Power Subsystem | 12 |
|
139 |
|
140 |
### Training Hyperparameters
|
141 |
- batch_size: (32, 32)
|
|
|
155 |
- load_best_model_at_end: False
|
156 |
|
157 |
### Training Results
|
158 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
159 |
+
|:------:|:----:|:-------------:|:---------------:|
|
160 |
+
| 0.0323 | 1 | 0.2123 | - |
|
161 |
+
| 1.6129 | 50 | 0.0264 | - |
|
162 |
+
| 3.2258 | 100 | 0.0039 | - |
|
163 |
+
| 4.8387 | 150 | 0.0034 | - |
|
164 |
+
| 6.4516 | 200 | 0.0024 | - |
|
165 |
+
| 8.0645 | 250 | 0.0021 | - |
|
166 |
+
| 9.6774 | 300 | 0.0021 | - |
|
167 |
|
168 |
### Framework Versions
|
169 |
- Python: 3.10.12
|
config_setfit.json
CHANGED
@@ -1,7 +1,8 @@
|
|
1 |
{
|
2 |
"normalize_embeddings": false,
|
3 |
"labels": [
|
4 |
-
"
|
5 |
-
"
|
|
|
6 |
]
|
7 |
}
|
|
|
1 |
{
|
2 |
"normalize_embeddings": false,
|
3 |
"labels": [
|
4 |
+
"Propulsion",
|
5 |
+
"Thermal Control",
|
6 |
+
"Power Subsystem"
|
7 |
]
|
8 |
}
|
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 sha256:0d4a900dba5ac0dc1af2c7ecb13b681dcfd55b62a90d896b1ca9fcd40030f5e9
|
3 |
size 133462128
|
model_head.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19647582e5ec77ad321060ae00148054c6e8d5e922bcb96e2e31f092d401af91
|
3 |
+
size 10255
|