---
base_model: BAAI/bge-large-en-v1.5
datasets:
- nazhan/brahmaputra-full-datasets-iter-8
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: I'm not interested in filtering the results.
- text: Please don't filter the data at this point.
- text: How's your day going?
- text: What’s the best way to merge the Products and Orders tables to identify products
with the highest sales growth?
- text: When is your birthday?
inference: true
model-index:
- name: SetFit with BAAI/bge-large-en-v1.5
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: nazhan/brahmaputra-full-datasets-iter-8
type: nazhan/brahmaputra-full-datasets-iter-8
split: test
metrics:
- type: accuracy
value: 1.0
name: Accuracy
---
# SetFit with BAAI/bge-large-en-v1.5
This is a [SetFit](https://github.com/huggingface/setfit) model trained on the [nazhan/brahmaputra-full-datasets-iter-8](https://huggingface.co/datasets/nazhan/brahmaputra-full-datasets-iter-8) dataset that can be used for Text Classification. This SetFit model uses [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 7 classes
- **Training Dataset:** [nazhan/brahmaputra-full-datasets-iter-8](https://huggingface.co/datasets/nazhan/brahmaputra-full-datasets-iter-8)
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:-------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Lookup_1 | - 'Analyze product category revenue impact.'
- 'Show me monthly EBIT by product.'
- 'Visualize M&A deal size distribution.'
|
| Tablejoin | - 'Could you link the Orders and Employees tables to find out which departments are processing the most orders?'
- 'Is it possible to combine the Employees and Orders tables to see which employees are assigned to specific order types?'
- 'Join data_asset_kpi_cf with data_asset_001_kpm tables.'
|
| Lookup | - "Show me the details of employees with the last name 'Smith'."
- "Filter by customers with the first name 'Emily' and show me their email addresses."
- "Show me the products with 'Tablet' in the name and filter by price above 200."
|
| Rejection | - "Let's not worry about generating additional data."
- "I'd prefer not to apply any filters."
- "I don't want to sort or filter right now."
|
| Viewtables | - 'What is the inventory of tables held in the starhub_data_asset database?'
- 'What tables are available in the starhub_data_asset database for performing basic data explorations?'
- 'What is the complete list of all the tables stored in the starhub_data_asset database that require a join operation for data analysis?'
|
| Generalreply | - "Oh, I enjoy spending my free time doing a few different things! Sometimes I like to read, other times I might go for a walk or watch a movie. It really just depends on what I'm in the mood for. What about you, how do you like to spend your free time?"
- 'What is your favorite color?'
- "that's not good."
|
| Aggregation | - 'What’s the total number of products sold in the Electronics category?'
- 'Determine the total number of orders placed during promotional periods.'
- 'What’s the total sales amount recorded in the Orders table?'
|
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 1.0 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("nazhan/bge-large-en-v1.5-brahmaputra-iter-8-2-epoch")
# Run inference
preds = model("How's your day going?")
```
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 3 | 11.0696 | 62 |
| Label | Training Sample Count |
|:-------------|:----------------------|
| Tablejoin | 112 |
| Rejection | 67 |
| Aggregation | 71 |
| Lookup | 56 |
| Generalreply | 69 |
| Viewtables | 73 |
| Lookup_1 | 69 |
### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (2, 2)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: True
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:-------:|:---------:|:-------------:|:---------------:|
| 0.0001 | 1 | 0.1865 | - |
| 0.0035 | 50 | 0.1599 | - |
| 0.0070 | 100 | 0.1933 | - |
| 0.0106 | 150 | 0.1595 | - |
| 0.0141 | 200 | 0.0899 | - |
| 0.0176 | 250 | 0.1334 | - |
| 0.0211 | 300 | 0.0722 | - |
| 0.0246 | 350 | 0.0411 | - |
| 0.0282 | 400 | 0.0171 | - |
| 0.0317 | 450 | 0.0293 | - |
| 0.0352 | 500 | 0.0218 | - |
| 0.0387 | 550 | 0.0057 | - |
| 0.0422 | 600 | 0.0065 | - |
| 0.0458 | 650 | 0.0047 | - |
| 0.0493 | 700 | 0.0045 | - |
| 0.0528 | 750 | 0.0048 | - |
| 0.0563 | 800 | 0.0032 | - |
| 0.0599 | 850 | 0.0038 | - |
| 0.0634 | 900 | 0.0033 | - |
| 0.0669 | 950 | 0.0027 | - |
| 0.0704 | 1000 | 0.0025 | - |
| 0.0739 | 1050 | 0.0024 | - |
| 0.0775 | 1100 | 0.0021 | - |
| 0.0810 | 1150 | 0.0025 | - |
| 0.0845 | 1200 | 0.0016 | - |
| 0.0880 | 1250 | 0.0019 | - |
| 0.0915 | 1300 | 0.0017 | - |
| 0.0951 | 1350 | 0.0016 | - |
| 0.0986 | 1400 | 0.0025 | - |
| 0.1021 | 1450 | 0.0016 | - |
| 0.1056 | 1500 | 0.0015 | - |
| 0.1091 | 1550 | 0.0012 | - |
| 0.1127 | 1600 | 0.001 | - |
| 0.1162 | 1650 | 0.0012 | - |
| 0.1197 | 1700 | 0.0012 | - |
| 0.1232 | 1750 | 0.0013 | - |
| 0.1267 | 1800 | 0.0012 | - |
| 0.1303 | 1850 | 0.0009 | - |
| 0.1338 | 1900 | 0.0011 | - |
| 0.1373 | 1950 | 0.001 | - |
| 0.1408 | 2000 | 0.0009 | - |
| 0.1443 | 2050 | 0.0009 | - |
| 0.1479 | 2100 | 0.0008 | - |
| 0.1514 | 2150 | 0.0007 | - |
| 0.1549 | 2200 | 0.0008 | - |
| 0.1584 | 2250 | 0.0008 | - |
| 0.1619 | 2300 | 0.0008 | - |
| 0.1655 | 2350 | 0.0007 | - |
| 0.1690 | 2400 | 0.0008 | - |
| 0.1725 | 2450 | 0.0006 | - |
| 0.1760 | 2500 | 0.0005 | - |
| 0.1796 | 2550 | 0.0006 | - |
| 0.1831 | 2600 | 0.0005 | - |
| 0.1866 | 2650 | 0.0006 | - |
| 0.1901 | 2700 | 0.0005 | - |
| 0.1936 | 2750 | 0.0007 | - |
| 0.1972 | 2800 | 0.0006 | - |
| 0.2007 | 2850 | 0.0005 | - |
| 0.2042 | 2900 | 0.0006 | - |
| 0.2077 | 2950 | 0.0007 | - |
| 0.2112 | 3000 | 0.0006 | - |
| 0.2148 | 3050 | 0.0005 | - |
| 0.2183 | 3100 | 0.0005 | - |
| 0.2218 | 3150 | 0.0005 | - |
| 0.2253 | 3200 | 0.0006 | - |
| 0.2288 | 3250 | 0.0005 | - |
| 0.2324 | 3300 | 0.0006 | - |
| 0.2359 | 3350 | 0.0004 | - |
| 0.2394 | 3400 | 0.0005 | - |
| 0.2429 | 3450 | 0.0005 | - |
| 0.2464 | 3500 | 0.0004 | - |
| 0.2500 | 3550 | 0.0006 | - |
| 0.2535 | 3600 | 0.0004 | - |
| 0.2570 | 3650 | 0.0004 | - |
| 0.2605 | 3700 | 0.0004 | - |
| 0.2640 | 3750 | 0.0004 | - |
| 0.2676 | 3800 | 0.0003 | - |
| 0.2711 | 3850 | 0.0004 | - |
| 0.2746 | 3900 | 0.0005 | - |
| 0.2781 | 3950 | 0.0004 | - |
| 0.2817 | 4000 | 0.0004 | - |
| 0.2852 | 4050 | 0.0003 | - |
| 0.2887 | 4100 | 0.0004 | - |
| 0.2922 | 4150 | 0.0004 | - |
| 0.2957 | 4200 | 0.0004 | - |
| 0.2993 | 4250 | 0.0005 | - |
| 0.3028 | 4300 | 0.0004 | - |
| 0.3063 | 4350 | 0.0004 | - |
| 0.3098 | 4400 | 0.0003 | - |
| 0.3133 | 4450 | 0.0004 | - |
| 0.3169 | 4500 | 0.0004 | - |
| 0.3204 | 4550 | 0.0003 | - |
| 0.3239 | 4600 | 0.0003 | - |
| 0.3274 | 4650 | 0.0004 | - |
| 0.3309 | 4700 | 0.0003 | - |
| 0.3345 | 4750 | 0.0003 | - |
| 0.3380 | 4800 | 0.0003 | - |
| 0.3415 | 4850 | 0.0003 | - |
| 0.3450 | 4900 | 0.0004 | - |
| 0.3485 | 4950 | 0.0003 | - |
| 0.3521 | 5000 | 0.0003 | - |
| 0.3556 | 5050 | 0.0003 | - |
| 0.3591 | 5100 | 0.0003 | - |
| 0.3626 | 5150 | 0.0004 | - |
| 0.3661 | 5200 | 0.0002 | - |
| 0.3697 | 5250 | 0.0004 | - |
| 0.3732 | 5300 | 0.0003 | - |
| 0.3767 | 5350 | 0.0003 | - |
| 0.3802 | 5400 | 0.0002 | - |
| 0.3837 | 5450 | 0.0003 | - |
| 0.3873 | 5500 | 0.0003 | - |
| 0.3908 | 5550 | 0.0003 | - |
| 0.3943 | 5600 | 0.0002 | - |
| 0.3978 | 5650 | 0.0003 | - |
| 0.4014 | 5700 | 0.0003 | - |
| 0.4049 | 5750 | 0.0002 | - |
| 0.4084 | 5800 | 0.0003 | - |
| 0.4119 | 5850 | 0.0003 | - |
| 0.4154 | 5900 | 0.0003 | - |
| 0.4190 | 5950 | 0.0002 | - |
| 0.4225 | 6000 | 0.0002 | - |
| 0.4260 | 6050 | 0.0002 | - |
| 0.4295 | 6100 | 0.0003 | - |
| 0.4330 | 6150 | 0.0003 | - |
| 0.4366 | 6200 | 0.0002 | - |
| 0.4401 | 6250 | 0.0003 | - |
| 0.4436 | 6300 | 0.0003 | - |
| 0.4471 | 6350 | 0.0002 | - |
| 0.4506 | 6400 | 0.0002 | - |
| 0.4542 | 6450 | 0.0002 | - |
| 0.4577 | 6500 | 0.0002 | - |
| 0.4612 | 6550 | 0.0002 | - |
| 0.4647 | 6600 | 0.0002 | - |
| 0.4682 | 6650 | 0.0002 | - |
| 0.4718 | 6700 | 0.0002 | - |
| 0.4753 | 6750 | 0.0003 | - |
| 0.4788 | 6800 | 0.0003 | - |
| 0.4823 | 6850 | 0.0002 | - |
| 0.4858 | 6900 | 0.0003 | - |
| 0.4894 | 6950 | 0.0002 | - |
| 0.4929 | 7000 | 0.0003 | - |
| 0.4964 | 7050 | 0.0002 | - |
| 0.4999 | 7100 | 0.0002 | - |
| 0.5035 | 7150 | 0.0002 | - |
| 0.5070 | 7200 | 0.0003 | - |
| 0.5105 | 7250 | 0.0002 | - |
| 0.5140 | 7300 | 0.0003 | - |
| 0.5175 | 7350 | 0.0004 | - |
| 0.5211 | 7400 | 0.0002 | - |
| 0.5246 | 7450 | 0.0002 | - |
| 0.5281 | 7500 | 0.0002 | - |
| 0.5316 | 7550 | 0.0002 | - |
| 0.5351 | 7600 | 0.0002 | - |
| 0.5387 | 7650 | 0.0002 | - |
| 0.5422 | 7700 | 0.0002 | - |
| 0.5457 | 7750 | 0.0002 | - |
| 0.5492 | 7800 | 0.0003 | - |
| 0.5527 | 7850 | 0.0002 | - |
| 0.5563 | 7900 | 0.0002 | - |
| 0.5598 | 7950 | 0.0002 | - |
| 0.5633 | 8000 | 0.0002 | - |
| 0.5668 | 8050 | 0.0002 | - |
| 0.5703 | 8100 | 0.0002 | - |
| 0.5739 | 8150 | 0.0002 | - |
| 0.5774 | 8200 | 0.0003 | - |
| 0.5809 | 8250 | 0.0002 | - |
| 0.5844 | 8300 | 0.0002 | - |
| 0.5879 | 8350 | 0.0002 | - |
| 0.5915 | 8400 | 0.0002 | - |
| 0.5950 | 8450 | 0.0001 | - |
| 0.5985 | 8500 | 0.0001 | - |
| 0.6020 | 8550 | 0.0001 | - |
| 0.6055 | 8600 | 0.0001 | - |
| 0.6091 | 8650 | 0.0002 | - |
| 0.6126 | 8700 | 0.0002 | - |
| 0.6161 | 8750 | 0.0002 | - |
| 0.6196 | 8800 | 0.0002 | - |
| 0.6232 | 8850 | 0.0002 | - |
| 0.6267 | 8900 | 0.0001 | - |
| 0.6302 | 8950 | 0.0001 | - |
| 0.6337 | 9000 | 0.0002 | - |
| 0.6372 | 9050 | 0.0002 | - |
| 0.6408 | 9100 | 0.0002 | - |
| 0.6443 | 9150 | 0.0001 | - |
| 0.6478 | 9200 | 0.0002 | - |
| 0.6513 | 9250 | 0.0003 | - |
| 0.6548 | 9300 | 0.0002 | - |
| 0.6584 | 9350 | 0.0003 | - |
| 0.6619 | 9400 | 0.0001 | - |
| 0.6654 | 9450 | 0.0001 | - |
| 0.6689 | 9500 | 0.0001 | - |
| 0.6724 | 9550 | 0.0001 | - |
| 0.6760 | 9600 | 0.0001 | - |
| 0.6795 | 9650 | 0.0002 | - |
| 0.6830 | 9700 | 0.0002 | - |
| 0.6865 | 9750 | 0.0002 | - |
| 0.6900 | 9800 | 0.0001 | - |
| 0.6936 | 9850 | 0.0001 | - |
| 0.6971 | 9900 | 0.0002 | - |
| 0.7006 | 9950 | 0.0001 | - |
| 0.7041 | 10000 | 0.0001 | - |
| 0.7076 | 10050 | 0.0001 | - |
| 0.7112 | 10100 | 0.0002 | - |
| 0.7147 | 10150 | 0.0001 | - |
| 0.7182 | 10200 | 0.0002 | - |
| 0.7217 | 10250 | 0.0002 | - |
| 0.7252 | 10300 | 0.0001 | - |
| 0.7288 | 10350 | 0.0001 | - |
| 0.7323 | 10400 | 0.0001 | - |
| 0.7358 | 10450 | 0.0001 | - |
| 0.7393 | 10500 | 0.0002 | - |
| 0.7429 | 10550 | 0.0001 | - |
| 0.7464 | 10600 | 0.0002 | - |
| 0.7499 | 10650 | 0.0001 | - |
| 0.7534 | 10700 | 0.0001 | - |
| 0.7569 | 10750 | 0.0002 | - |
| 0.7605 | 10800 | 0.0002 | - |
| 0.7640 | 10850 | 0.0001 | - |
| 0.7675 | 10900 | 0.0001 | - |
| 0.7710 | 10950 | 0.0001 | - |
| 0.7745 | 11000 | 0.0001 | - |
| 0.7781 | 11050 | 0.0001 | - |
| 0.7816 | 11100 | 0.0001 | - |
| 0.7851 | 11150 | 0.0001 | - |
| 0.7886 | 11200 | 0.0001 | - |
| 0.7921 | 11250 | 0.0001 | - |
| 0.7957 | 11300 | 0.0001 | - |
| 0.7992 | 11350 | 0.0001 | - |
| 0.8027 | 11400 | 0.0002 | - |
| 0.8062 | 11450 | 0.0001 | - |
| 0.8097 | 11500 | 0.0001 | - |
| 0.8133 | 11550 | 0.0001 | - |
| 0.8168 | 11600 | 0.0001 | - |
| 0.8203 | 11650 | 0.0001 | - |
| 0.8238 | 11700 | 0.0001 | - |
| 0.8273 | 11750 | 0.0001 | - |
| 0.8309 | 11800 | 0.0001 | - |
| 0.8344 | 11850 | 0.0001 | - |
| 0.8379 | 11900 | 0.0001 | - |
| 0.8414 | 11950 | 0.0001 | - |
| 0.8450 | 12000 | 0.0001 | - |
| 0.8485 | 12050 | 0.0001 | - |
| 0.8520 | 12100 | 0.0001 | - |
| 0.8555 | 12150 | 0.0001 | - |
| 0.8590 | 12200 | 0.0001 | - |
| 0.8626 | 12250 | 0.0002 | - |
| 0.8661 | 12300 | 0.0002 | - |
| 0.8696 | 12350 | 0.0002 | - |
| 0.8731 | 12400 | 0.0002 | - |
| 0.8766 | 12450 | 0.0001 | - |
| 0.8802 | 12500 | 0.0001 | - |
| 0.8837 | 12550 | 0.0001 | - |
| 0.8872 | 12600 | 0.0001 | - |
| 0.8907 | 12650 | 0.0002 | - |
| 0.8942 | 12700 | 0.0001 | - |
| 0.8978 | 12750 | 0.0001 | - |
| 0.9013 | 12800 | 0.0001 | - |
| 0.9048 | 12850 | 0.0001 | - |
| 0.9083 | 12900 | 0.0001 | - |
| 0.9118 | 12950 | 0.0001 | - |
| 0.9154 | 13000 | 0.0001 | - |
| 0.9189 | 13050 | 0.0001 | - |
| 0.9224 | 13100 | 0.0001 | - |
| 0.9259 | 13150 | 0.0001 | - |
| 0.9294 | 13200 | 0.0001 | - |
| 0.9330 | 13250 | 0.0001 | - |
| 0.9365 | 13300 | 0.0001 | - |
| 0.9400 | 13350 | 0.0001 | - |
| 0.9435 | 13400 | 0.0001 | - |
| 0.9470 | 13450 | 0.0001 | - |
| 0.9506 | 13500 | 0.0001 | - |
| 0.9541 | 13550 | 0.0001 | - |
| 0.9576 | 13600 | 0.0001 | - |
| 0.9611 | 13650 | 0.0001 | - |
| 0.9647 | 13700 | 0.0001 | - |
| 0.9682 | 13750 | 0.0001 | - |
| 0.9717 | 13800 | 0.0001 | - |
| 0.9752 | 13850 | 0.0001 | - |
| 0.9787 | 13900 | 0.0001 | - |
| 0.9823 | 13950 | 0.0001 | - |
| 0.9858 | 14000 | 0.0001 | - |
| 0.9893 | 14050 | 0.0001 | - |
| 0.9928 | 14100 | 0.0001 | - |
| 0.9963 | 14150 | 0.0002 | - |
| 0.9999 | 14200 | 0.0001 | - |
| 1.0 | 14202 | - | 0.0082 |
| 1.0034 | 14250 | 0.0001 | - |
| 1.0069 | 14300 | 0.0001 | - |
| 1.0104 | 14350 | 0.0001 | - |
| 1.0139 | 14400 | 0.0001 | - |
| 1.0175 | 14450 | 0.0001 | - |
| 1.0210 | 14500 | 0.0001 | - |
| 1.0245 | 14550 | 0.0001 | - |
| 1.0280 | 14600 | 0.0001 | - |
| 1.0315 | 14650 | 0.0001 | - |
| 1.0351 | 14700 | 0.0001 | - |
| 1.0386 | 14750 | 0.0001 | - |
| 1.0421 | 14800 | 0.0001 | - |
| 1.0456 | 14850 | 0.0001 | - |
| 1.0491 | 14900 | 0.0001 | - |
| 1.0527 | 14950 | 0.0001 | - |
| 1.0562 | 15000 | 0.0001 | - |
| 1.0597 | 15050 | 0.0001 | - |
| 1.0632 | 15100 | 0.0001 | - |
| 1.0668 | 15150 | 0.0001 | - |
| 1.0703 | 15200 | 0.0001 | - |
| 1.0738 | 15250 | 0.0001 | - |
| 1.0773 | 15300 | 0.0001 | - |
| 1.0808 | 15350 | 0.0001 | - |
| 1.0844 | 15400 | 0.0001 | - |
| 1.0879 | 15450 | 0.0001 | - |
| 1.0914 | 15500 | 0.0001 | - |
| 1.0949 | 15550 | 0.0001 | - |
| 1.0984 | 15600 | 0.0001 | - |
| 1.1020 | 15650 | 0.0001 | - |
| 1.1055 | 15700 | 0.0001 | - |
| 1.1090 | 15750 | 0.0001 | - |
| 1.1125 | 15800 | 0.0001 | - |
| 1.1160 | 15850 | 0.0001 | - |
| 1.1196 | 15900 | 0.0001 | - |
| 1.1231 | 15950 | 0.0001 | - |
| 1.1266 | 16000 | 0.0001 | - |
| 1.1301 | 16050 | 0.0001 | - |
| 1.1336 | 16100 | 0.0001 | - |
| 1.1372 | 16150 | 0.0001 | - |
| 1.1407 | 16200 | 0.0001 | - |
| 1.1442 | 16250 | 0.0001 | - |
| 1.1477 | 16300 | 0.0001 | - |
| 1.1512 | 16350 | 0.0001 | - |
| 1.1548 | 16400 | 0.0001 | - |
| 1.1583 | 16450 | 0.0001 | - |
| 1.1618 | 16500 | 0.0001 | - |
| 1.1653 | 16550 | 0.0001 | - |
| 1.1688 | 16600 | 0.0001 | - |
| 1.1724 | 16650 | 0.0001 | - |
| 1.1759 | 16700 | 0.0001 | - |
| 1.1794 | 16750 | 0.0001 | - |
| 1.1829 | 16800 | 0.0001 | - |
| 1.1865 | 16850 | 0.0001 | - |
| 1.1900 | 16900 | 0.0001 | - |
| 1.1935 | 16950 | 0.0001 | - |
| 1.1970 | 17000 | 0.0001 | - |
| 1.2005 | 17050 | 0.0001 | - |
| 1.2041 | 17100 | 0.0001 | - |
| 1.2076 | 17150 | 0.0001 | - |
| 1.2111 | 17200 | 0.0001 | - |
| 1.2146 | 17250 | 0.0001 | - |
| 1.2181 | 17300 | 0.0001 | - |
| 1.2217 | 17350 | 0.0001 | - |
| 1.2252 | 17400 | 0.0001 | - |
| 1.2287 | 17450 | 0.0001 | - |
| 1.2322 | 17500 | 0.0001 | - |
| 1.2357 | 17550 | 0.0001 | - |
| 1.2393 | 17600 | 0.0001 | - |
| 1.2428 | 17650 | 0.0001 | - |
| 1.2463 | 17700 | 0.0001 | - |
| 1.2498 | 17750 | 0.0001 | - |
| 1.2533 | 17800 | 0.0001 | - |
| 1.2569 | 17850 | 0.0001 | - |
| 1.2604 | 17900 | 0.0001 | - |
| 1.2639 | 17950 | 0.0001 | - |
| 1.2674 | 18000 | 0.0001 | - |
| 1.2709 | 18050 | 0.0001 | - |
| 1.2745 | 18100 | 0.0001 | - |
| 1.2780 | 18150 | 0.0001 | - |
| 1.2815 | 18200 | 0.0001 | - |
| 1.2850 | 18250 | 0.0001 | - |
| 1.2886 | 18300 | 0.0001 | - |
| 1.2921 | 18350 | 0.0001 | - |
| 1.2956 | 18400 | 0.0001 | - |
| 1.2991 | 18450 | 0.0001 | - |
| 1.3026 | 18500 | 0.0001 | - |
| 1.3062 | 18550 | 0.0001 | - |
| 1.3097 | 18600 | 0.0001 | - |
| 1.3132 | 18650 | 0.0001 | - |
| 1.3167 | 18700 | 0.0001 | - |
| 1.3202 | 18750 | 0.0001 | - |
| 1.3238 | 18800 | 0.0001 | - |
| 1.3273 | 18850 | 0.0001 | - |
| 1.3308 | 18900 | 0.0001 | - |
| 1.3343 | 18950 | 0.0001 | - |
| 1.3378 | 19000 | 0.0001 | - |
| 1.3414 | 19050 | 0.0001 | - |
| 1.3449 | 19100 | 0.0001 | - |
| 1.3484 | 19150 | 0.0001 | - |
| 1.3519 | 19200 | 0.0001 | - |
| 1.3554 | 19250 | 0.0001 | - |
| 1.3590 | 19300 | 0.0001 | - |
| 1.3625 | 19350 | 0.0001 | - |
| 1.3660 | 19400 | 0.0001 | - |
| 1.3695 | 19450 | 0.0001 | - |
| 1.3730 | 19500 | 0.0001 | - |
| 1.3766 | 19550 | 0.0001 | - |
| 1.3801 | 19600 | 0.0001 | - |
| 1.3836 | 19650 | 0.0001 | - |
| 1.3871 | 19700 | 0.0001 | - |
| 1.3906 | 19750 | 0.0001 | - |
| 1.3942 | 19800 | 0.0001 | - |
| 1.3977 | 19850 | 0.0001 | - |
| 1.4012 | 19900 | 0.0001 | - |
| 1.4047 | 19950 | 0.0001 | - |
| 1.4083 | 20000 | 0.0001 | - |
| 1.4118 | 20050 | 0.0001 | - |
| 1.4153 | 20100 | 0.0001 | - |
| 1.4188 | 20150 | 0.0001 | - |
| 1.4223 | 20200 | 0.0001 | - |
| 1.4259 | 20250 | 0.0001 | - |
| 1.4294 | 20300 | 0.0001 | - |
| 1.4329 | 20350 | 0.0001 | - |
| 1.4364 | 20400 | 0.0 | - |
| 1.4399 | 20450 | 0.0001 | - |
| 1.4435 | 20500 | 0.0001 | - |
| 1.4470 | 20550 | 0.0001 | - |
| 1.4505 | 20600 | 0.0001 | - |
| 1.4540 | 20650 | 0.0001 | - |
| 1.4575 | 20700 | 0.0001 | - |
| 1.4611 | 20750 | 0.0001 | - |
| 1.4646 | 20800 | 0.0001 | - |
| 1.4681 | 20850 | 0.0 | - |
| 1.4716 | 20900 | 0.0001 | - |
| 1.4751 | 20950 | 0.0001 | - |
| 1.4787 | 21000 | 0.0 | - |
| 1.4822 | 21050 | 0.0001 | - |
| 1.4857 | 21100 | 0.0001 | - |
| 1.4892 | 21150 | 0.0001 | - |
| 1.4927 | 21200 | 0.0001 | - |
| 1.4963 | 21250 | 0.0001 | - |
| 1.4998 | 21300 | 0.0001 | - |
| 1.5033 | 21350 | 0.0 | - |
| 1.5068 | 21400 | 0.0001 | - |
| 1.5104 | 21450 | 0.0001 | - |
| 1.5139 | 21500 | 0.0001 | - |
| 1.5174 | 21550 | 0.0 | - |
| 1.5209 | 21600 | 0.0001 | - |
| 1.5244 | 21650 | 0.0001 | - |
| 1.5280 | 21700 | 0.0001 | - |
| 1.5315 | 21750 | 0.0001 | - |
| 1.5350 | 21800 | 0.0001 | - |
| 1.5385 | 21850 | 0.0001 | - |
| 1.5420 | 21900 | 0.0 | - |
| 1.5456 | 21950 | 0.0001 | - |
| 1.5491 | 22000 | 0.0001 | - |
| 1.5526 | 22050 | 0.0001 | - |
| 1.5561 | 22100 | 0.0001 | - |
| 1.5596 | 22150 | 0.0001 | - |
| 1.5632 | 22200 | 0.0001 | - |
| 1.5667 | 22250 | 0.0 | - |
| 1.5702 | 22300 | 0.0 | - |
| 1.5737 | 22350 | 0.0001 | - |
| 1.5772 | 22400 | 0.0001 | - |
| 1.5808 | 22450 | 0.0001 | - |
| 1.5843 | 22500 | 0.0001 | - |
| 1.5878 | 22550 | 0.0001 | - |
| 1.5913 | 22600 | 0.0001 | - |
| 1.5948 | 22650 | 0.0001 | - |
| 1.5984 | 22700 | 0.0 | - |
| 1.6019 | 22750 | 0.0001 | - |
| 1.6054 | 22800 | 0.0001 | - |
| 1.6089 | 22850 | 0.0001 | - |
| 1.6124 | 22900 | 0.0001 | - |
| 1.6160 | 22950 | 0.0001 | - |
| 1.6195 | 23000 | 0.0001 | - |
| 1.6230 | 23050 | 0.0001 | - |
| 1.6265 | 23100 | 0.0001 | - |
| 1.6301 | 23150 | 0.0 | - |
| 1.6336 | 23200 | 0.0001 | - |
| 1.6371 | 23250 | 0.0001 | - |
| 1.6406 | 23300 | 0.0 | - |
| 1.6441 | 23350 | 0.0001 | - |
| 1.6477 | 23400 | 0.0 | - |
| 1.6512 | 23450 | 0.0001 | - |
| 1.6547 | 23500 | 0.0 | - |
| 1.6582 | 23550 | 0.0001 | - |
| 1.6617 | 23600 | 0.0001 | - |
| 1.6653 | 23650 | 0.0 | - |
| 1.6688 | 23700 | 0.0 | - |
| 1.6723 | 23750 | 0.0001 | - |
| 1.6758 | 23800 | 0.0001 | - |
| 1.6793 | 23850 | 0.0 | - |
| 1.6829 | 23900 | 0.0001 | - |
| 1.6864 | 23950 | 0.0 | - |
| 1.6899 | 24000 | 0.0 | - |
| 1.6934 | 24050 | 0.0 | - |
| 1.6969 | 24100 | 0.0001 | - |
| 1.7005 | 24150 | 0.0001 | - |
| 1.7040 | 24200 | 0.0001 | - |
| 1.7075 | 24250 | 0.0001 | - |
| 1.7110 | 24300 | 0.0001 | - |
| 1.7145 | 24350 | 0.0001 | - |
| 1.7181 | 24400 | 0.0001 | - |
| 1.7216 | 24450 | 0.0 | - |
| 1.7251 | 24500 | 0.0001 | - |
| 1.7286 | 24550 | 0.0 | - |
| 1.7322 | 24600 | 0.0001 | - |
| 1.7357 | 24650 | 0.0001 | - |
| 1.7392 | 24700 | 0.0 | - |
| 1.7427 | 24750 | 0.0001 | - |
| 1.7462 | 24800 | 0.0001 | - |
| 1.7498 | 24850 | 0.0001 | - |
| 1.7533 | 24900 | 0.0 | - |
| 1.7568 | 24950 | 0.0 | - |
| 1.7603 | 25000 | 0.0001 | - |
| 1.7638 | 25050 | 0.0001 | - |
| 1.7674 | 25100 | 0.0001 | - |
| 1.7709 | 25150 | 0.0001 | - |
| 1.7744 | 25200 | 0.0 | - |
| 1.7779 | 25250 | 0.0001 | - |
| 1.7814 | 25300 | 0.0 | - |
| 1.7850 | 25350 | 0.0 | - |
| 1.7885 | 25400 | 0.0 | - |
| 1.7920 | 25450 | 0.0 | - |
| 1.7955 | 25500 | 0.0 | - |
| 1.7990 | 25550 | 0.0 | - |
| 1.8026 | 25600 | 0.0001 | - |
| 1.8061 | 25650 | 0.0 | - |
| 1.8096 | 25700 | 0.0001 | - |
| 1.8131 | 25750 | 0.0001 | - |
| 1.8166 | 25800 | 0.0 | - |
| 1.8202 | 25850 | 0.0 | - |
| 1.8237 | 25900 | 0.0 | - |
| 1.8272 | 25950 | 0.0 | - |
| 1.8307 | 26000 | 0.0001 | - |
| 1.8342 | 26050 | 0.0 | - |
| 1.8378 | 26100 | 0.0 | - |
| 1.8413 | 26150 | 0.0 | - |
| 1.8448 | 26200 | 0.0 | - |
| 1.8483 | 26250 | 0.0 | - |
| 1.8519 | 26300 | 0.0 | - |
| 1.8554 | 26350 | 0.0001 | - |
| 1.8589 | 26400 | 0.0 | - |
| 1.8624 | 26450 | 0.0 | - |
| 1.8659 | 26500 | 0.0 | - |
| 1.8695 | 26550 | 0.0 | - |
| 1.8730 | 26600 | 0.0 | - |
| 1.8765 | 26650 | 0.0 | - |
| 1.8800 | 26700 | 0.0 | - |
| 1.8835 | 26750 | 0.0001 | - |
| 1.8871 | 26800 | 0.0 | - |
| 1.8906 | 26850 | 0.0 | - |
| 1.8941 | 26900 | 0.0 | - |
| 1.8976 | 26950 | 0.0 | - |
| 1.9011 | 27000 | 0.0001 | - |
| 1.9047 | 27050 | 0.0 | - |
| 1.9082 | 27100 | 0.0 | - |
| 1.9117 | 27150 | 0.0 | - |
| 1.9152 | 27200 | 0.0001 | - |
| 1.9187 | 27250 | 0.0 | - |
| 1.9223 | 27300 | 0.0001 | - |
| 1.9258 | 27350 | 0.0 | - |
| 1.9293 | 27400 | 0.0 | - |
| 1.9328 | 27450 | 0.0 | - |
| 1.9363 | 27500 | 0.0 | - |
| 1.9399 | 27550 | 0.0 | - |
| 1.9434 | 27600 | 0.0 | - |
| 1.9469 | 27650 | 0.0 | - |
| 1.9504 | 27700 | 0.0 | - |
| 1.9540 | 27750 | 0.0001 | - |
| 1.9575 | 27800 | 0.0 | - |
| 1.9610 | 27850 | 0.0 | - |
| 1.9645 | 27900 | 0.0 | - |
| 1.9680 | 27950 | 0.0001 | - |
| 1.9716 | 28000 | 0.0 | - |
| 1.9751 | 28050 | 0.0 | - |
| 1.9786 | 28100 | 0.0001 | - |
| 1.9821 | 28150 | 0.0 | - |
| 1.9856 | 28200 | 0.0 | - |
| 1.9892 | 28250 | 0.0 | - |
| 1.9927 | 28300 | 0.0 | - |
| 1.9962 | 28350 | 0.0 | - |
| 1.9997 | 28400 | 0.0001 | - |
| **2.0** | **28404** | **-** | **0.0076** |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.11.9
- SetFit: 1.1.0.dev0
- Sentence Transformers: 3.0.1
- Transformers: 4.44.2
- PyTorch: 2.4.0+cu121
- Datasets: 2.21.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```