---
base_model: BAAI/bge-large-en-v1.5
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: Get me var Product_Profitability.
- text: What’s the best way to merge the Orders and Employees tables to identify the
top-performing departments?
- text: Please show min Total Company Revenue.
- text: Get me avg Intangible Assets.
- text: Can I join the Customers and Orders tables to find out which customers have
the highest lifetime value?
inference: true
model-index:
- name: SetFit with BAAI/bge-large-en-v1.5
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.5726495726495726
name: Accuracy
---
# SetFit with BAAI/bge-large-en-v1.5
This is a [SetFit](https://github.com/huggingface/setfit) model 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
### 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 |
|:-------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Generalreply | - 'How was your day today?'
- 'Oh, I have a lot of hobbies actually! But if I had to pick one, I would say that my favorite is probably reading. I love getting lost in a good book and discovering new worlds and characters. How about you?'
- 'Honestly, I hope to achieve a lot in the next 5 years. I want to continue growing in my career and learn new skills. I also aspire to travel more and experience different cultures. Overall, my goal is to be happy and fulfilled in both my personal and professional life. How about you? What are your hopes for the next 5 years?'
|
| Lookup_1 | - 'i want to get trend analysis and group by product'
- 'Show me data_asset_001_pcc details.'
- 'Analyze Product-wise EBIT Margin Trend.'
|
| Tablejoin | - 'Join data_asset_001_kpm with data_asset_kpi_is.'
- 'Can I merge cash flow and key performance metrics tables?'
- 'Join product category comparison and trend analysis tables.'
|
| Rejection | - "I'm not interested in filtering this collection."
- "I don't want to create any new data outputs."
- "I don't want to perform any filtering."
|
| Aggregation | - 'Can I have avg Cost_Broadband?'
- 'Please show min % YoY Change.'
- 'Get me avg Earning_per_Cost.'
|
| Viewtables | - 'What tables are included in the starhub_data_asset database that relate to customer complaints?'
- 'I need to see a list of tables that contain information about network outages.'
- 'What are the available tables in the starhub_data_asset database that are relevant to financial reporting?'
|
| Lookup | - 'Filter by orders placed by customer ID 102 and get me the order dates.'
- 'Show me the orders placed on January 1st, 2024.'
- "Get me the phone number of the customer with the first name 'Alice'."
|
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.5726 |
## 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-9-1-epoch")
# Run inference
preds = model("Get me avg Intangible Assets.")
```
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:-------|:----|
| Word count | 2 | 8.7792 | 62 |
| Label | Training Sample Count |
|:-------------|:----------------------|
| Tablejoin | 126 |
| Rejection | 72 |
| Aggregation | 221 |
| Lookup | 62 |
| Generalreply | 60 |
| Viewtables | 73 |
| Lookup_1 | 224 |
### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- 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 |
|:-------:|:---------:|:-------------:|:---------------:|
| 0.0000 | 1 | 0.2059 | - |
| 0.0014 | 50 | 0.1956 | - |
| 0.0028 | 100 | 0.207 | - |
| 0.0042 | 150 | 0.1783 | - |
| 0.0056 | 200 | 0.1517 | - |
| 0.0070 | 250 | 0.1795 | - |
| 0.0084 | 300 | 0.1227 | - |
| 0.0098 | 350 | 0.063 | - |
| 0.0112 | 400 | 0.0451 | - |
| 0.0126 | 450 | 0.0408 | - |
| 0.0140 | 500 | 0.0576 | - |
| 0.0155 | 550 | 0.0178 | - |
| 0.0169 | 600 | 0.0244 | - |
| 0.0183 | 650 | 0.0072 | - |
| 0.0197 | 700 | 0.0223 | - |
| 0.0211 | 750 | 0.0046 | - |
| 0.0225 | 800 | 0.003 | - |
| 0.0239 | 850 | 0.004 | - |
| 0.0253 | 900 | 0.0042 | - |
| 0.0267 | 950 | 0.0047 | - |
| 0.0281 | 1000 | 0.0045 | - |
| 0.0295 | 1050 | 0.0032 | - |
| 0.0309 | 1100 | 0.0021 | - |
| 0.0323 | 1150 | 0.0028 | - |
| 0.0337 | 1200 | 0.0022 | - |
| 0.0351 | 1250 | 0.0024 | - |
| 0.0365 | 1300 | 0.0019 | - |
| 0.0379 | 1350 | 0.002 | - |
| 0.0393 | 1400 | 0.0015 | - |
| 0.0407 | 1450 | 0.0016 | - |
| 0.0421 | 1500 | 0.0014 | - |
| 0.0436 | 1550 | 0.0013 | - |
| 0.0450 | 1600 | 0.0016 | - |
| 0.0464 | 1650 | 0.0011 | - |
| 0.0478 | 1700 | 0.0012 | - |
| 0.0492 | 1750 | 0.0011 | - |
| 0.0506 | 1800 | 0.0015 | - |
| 0.0520 | 1850 | 0.0016 | - |
| 0.0534 | 1900 | 0.0012 | - |
| 0.0548 | 1950 | 0.0008 | - |
| 0.0562 | 2000 | 0.0011 | - |
| 0.0576 | 2050 | 0.001 | - |
| 0.0590 | 2100 | 0.001 | - |
| 0.0604 | 2150 | 0.0008 | - |
| 0.0618 | 2200 | 0.0009 | - |
| 0.0632 | 2250 | 0.0007 | - |
| 0.0646 | 2300 | 0.0008 | - |
| 0.0660 | 2350 | 0.0006 | - |
| 0.0674 | 2400 | 0.0007 | - |
| 0.0688 | 2450 | 0.0008 | - |
| 0.0702 | 2500 | 0.0006 | - |
| 0.0717 | 2550 | 0.0007 | - |
| 0.0731 | 2600 | 0.0006 | - |
| 0.0745 | 2650 | 0.0007 | - |
| 0.0759 | 2700 | 0.0005 | - |
| 0.0773 | 2750 | 0.0006 | - |
| 0.0787 | 2800 | 0.0007 | - |
| 0.0801 | 2850 | 0.0007 | - |
| 0.0815 | 2900 | 0.0005 | - |
| 0.0829 | 2950 | 0.0008 | - |
| 0.0843 | 3000 | 0.0005 | - |
| 0.0857 | 3050 | 0.0007 | - |
| 0.0871 | 3100 | 0.0006 | - |
| 0.0885 | 3150 | 0.0005 | - |
| 0.0899 | 3200 | 0.0007 | - |
| 0.0913 | 3250 | 0.0005 | - |
| 0.0927 | 3300 | 0.0004 | - |
| 0.0941 | 3350 | 0.0005 | - |
| 0.0955 | 3400 | 0.0003 | - |
| 0.0969 | 3450 | 0.0004 | - |
| 0.0983 | 3500 | 0.0004 | - |
| 0.0998 | 3550 | 0.0004 | - |
| 0.1012 | 3600 | 0.0004 | - |
| 0.1026 | 3650 | 0.0004 | - |
| 0.1040 | 3700 | 0.0004 | - |
| 0.1054 | 3750 | 0.0004 | - |
| 0.1068 | 3800 | 0.0003 | - |
| 0.1082 | 3850 | 0.0003 | - |
| 0.1096 | 3900 | 0.0005 | - |
| 0.1110 | 3950 | 0.0005 | - |
| 0.1124 | 4000 | 0.0005 | - |
| 0.1138 | 4050 | 0.0003 | - |
| 0.1152 | 4100 | 0.0006 | - |
| 0.1166 | 4150 | 0.0004 | - |
| 0.1180 | 4200 | 0.0003 | - |
| 0.1194 | 4250 | 0.0004 | - |
| 0.1208 | 4300 | 0.0003 | - |
| 0.1222 | 4350 | 0.0004 | - |
| 0.1236 | 4400 | 0.0003 | - |
| 0.1250 | 4450 | 0.0003 | - |
| 0.1264 | 4500 | 0.0004 | - |
| 0.1279 | 4550 | 0.0003 | - |
| 0.1293 | 4600 | 0.0005 | - |
| 0.1307 | 4650 | 0.0004 | - |
| 0.1321 | 4700 | 0.0003 | - |
| 0.1335 | 4750 | 0.0004 | - |
| 0.1349 | 4800 | 0.0003 | - |
| 0.1363 | 4850 | 0.0003 | - |
| 0.1377 | 4900 | 0.0003 | - |
| 0.1391 | 4950 | 0.0003 | - |
| 0.1405 | 5000 | 0.0003 | - |
| 0.1419 | 5050 | 0.0003 | - |
| 0.1433 | 5100 | 0.0004 | - |
| 0.1447 | 5150 | 0.0003 | - |
| 0.1461 | 5200 | 0.0004 | - |
| 0.1475 | 5250 | 0.0004 | - |
| 0.1489 | 5300 | 0.0003 | - |
| 0.1503 | 5350 | 0.0003 | - |
| 0.1517 | 5400 | 0.0003 | - |
| 0.1531 | 5450 | 0.0003 | - |
| 0.1545 | 5500 | 0.0002 | - |
| 0.1560 | 5550 | 0.0003 | - |
| 0.1574 | 5600 | 0.0003 | - |
| 0.1588 | 5650 | 0.0003 | - |
| 0.1602 | 5700 | 0.0002 | - |
| 0.1616 | 5750 | 0.0002 | - |
| 0.1630 | 5800 | 0.0003 | - |
| 0.1644 | 5850 | 0.0002 | - |
| 0.1658 | 5900 | 0.0003 | - |
| 0.1672 | 5950 | 0.0002 | - |
| 0.1686 | 6000 | 0.0002 | - |
| 0.1700 | 6050 | 0.0002 | - |
| 0.1714 | 6100 | 0.0002 | - |
| 0.1728 | 6150 | 0.0003 | - |
| 0.1742 | 6200 | 0.0003 | - |
| 0.1756 | 6250 | 0.0003 | - |
| 0.1770 | 6300 | 0.0003 | - |
| 0.1784 | 6350 | 0.0002 | - |
| 0.1798 | 6400 | 0.0003 | - |
| 0.1812 | 6450 | 0.0002 | - |
| 0.1826 | 6500 | 0.0003 | - |
| 0.1841 | 6550 | 0.0002 | - |
| 0.1855 | 6600 | 0.0002 | - |
| 0.1869 | 6650 | 0.0002 | - |
| 0.1883 | 6700 | 0.0002 | - |
| 0.1897 | 6750 | 0.0003 | - |
| 0.1911 | 6800 | 0.0003 | - |
| 0.1925 | 6850 | 0.0002 | - |
| 0.1939 | 6900 | 0.0002 | - |
| 0.1953 | 6950 | 0.0002 | - |
| 0.1967 | 7000 | 0.0002 | - |
| 0.1981 | 7050 | 0.0001 | - |
| 0.1995 | 7100 | 0.0002 | - |
| 0.2009 | 7150 | 0.0002 | - |
| 0.2023 | 7200 | 0.0002 | - |
| 0.2037 | 7250 | 0.0002 | - |
| 0.2051 | 7300 | 0.0002 | - |
| 0.2065 | 7350 | 0.0001 | - |
| 0.2079 | 7400 | 0.0002 | - |
| 0.2093 | 7450 | 0.0024 | - |
| 0.2107 | 7500 | 0.0718 | - |
| 0.2122 | 7550 | 0.1 | - |
| 0.2136 | 7600 | 0.1876 | - |
| 0.2150 | 7650 | 0.1006 | - |
| 0.2164 | 7700 | 0.163 | - |
| 0.2178 | 7750 | 0.1008 | - |
| 0.2192 | 7800 | 0.1073 | - |
| 0.2206 | 7850 | 0.2059 | - |
| 0.2220 | 7900 | 0.112 | - |
| 0.2234 | 7950 | 0.1103 | - |
| 0.2248 | 8000 | 0.1921 | - |
| 0.2262 | 8050 | 0.0641 | - |
| 0.2276 | 8100 | 0.0992 | - |
| 0.2290 | 8150 | 0.2486 | - |
| 0.2304 | 8200 | 0.1716 | - |
| 0.2318 | 8250 | 0.142 | - |
| 0.2332 | 8300 | 0.1431 | - |
| 0.2346 | 8350 | 0.1774 | - |
| 0.2360 | 8400 | 0.1537 | - |
| 0.2374 | 8450 | 0.1902 | - |
| 0.2388 | 8500 | 0.1015 | - |
| 0.2402 | 8550 | 0.1401 | - |
| 0.2417 | 8600 | 0.2599 | - |
| 0.2431 | 8650 | 0.261 | - |
| 0.2445 | 8700 | 0.1861 | - |
| 0.2459 | 8750 | 0.1743 | - |
| 0.2473 | 8800 | 0.1705 | - |
| 0.2487 | 8850 | 0.1752 | - |
| 0.2501 | 8900 | 0.0914 | - |
| 0.2515 | 8950 | 0.1651 | - |
| 0.2529 | 9000 | 0.1165 | - |
| 0.2543 | 9050 | 0.2675 | - |
| 0.2557 | 9100 | 0.0953 | - |
| 0.2571 | 9150 | 0.0713 | - |
| 0.2585 | 9200 | 0.1782 | - |
| 0.2599 | 9250 | 0.1995 | - |
| 0.2613 | 9300 | 0.2393 | - |
| 0.2627 | 9350 | 0.1734 | - |
| 0.2641 | 9400 | 0.2222 | - |
| 0.2655 | 9450 | 0.3005 | - |
| 0.2669 | 9500 | 0.2252 | - |
| 0.2683 | 9550 | 0.2498 | - |
| 0.2698 | 9600 | 0.3293 | - |
| 0.2712 | 9650 | 0.2422 | - |
| 0.2726 | 9700 | 0.1943 | - |
| 0.2740 | 9750 | 0.2497 | - |
| 0.2754 | 9800 | 0.2538 | - |
| 0.2768 | 9850 | 0.2114 | - |
| 0.2782 | 9900 | 0.1719 | - |
| 0.2796 | 9950 | 0.2453 | - |
| 0.2810 | 10000 | 0.2571 | - |
| 0.2824 | 10050 | 0.2267 | - |
| 0.2838 | 10100 | 0.2274 | - |
| 0.2852 | 10150 | 0.2441 | - |
| 0.2866 | 10200 | 0.2536 | - |
| 0.2880 | 10250 | 0.236 | - |
| 0.2894 | 10300 | 0.204 | - |
| 0.2908 | 10350 | 0.2636 | - |
| 0.2922 | 10400 | 0.2562 | - |
| 0.2936 | 10450 | 0.2437 | - |
| 0.2950 | 10500 | 0.2395 | - |
| 0.2964 | 10550 | 0.2616 | - |
| 0.2979 | 10600 | 0.272 | - |
| 0.2993 | 10650 | 0.2637 | - |
| 0.3007 | 10700 | 0.2503 | - |
| 0.3021 | 10750 | 0.2401 | - |
| 0.3035 | 10800 | 0.2485 | - |
| 0.3049 | 10850 | 0.2521 | - |
| 0.3063 | 10900 | 0.256 | - |
| 0.3077 | 10950 | 0.2363 | - |
| 0.3091 | 11000 | 0.2482 | - |
| 0.3105 | 11050 | 0.2533 | - |
| 0.3119 | 11100 | 0.2598 | - |
| 0.3133 | 11150 | 0.2572 | - |
| 0.3147 | 11200 | 0.2631 | - |
| 0.3161 | 11250 | 0.2399 | - |
| 0.3175 | 11300 | 0.2509 | - |
| 0.3189 | 11350 | 0.2447 | - |
| 0.3203 | 11400 | 0.2395 | - |
| 0.3217 | 11450 | 0.2439 | - |
| 0.3231 | 11500 | 0.2497 | - |
| 0.3245 | 11550 | 0.2377 | - |
| 0.3260 | 11600 | 0.2452 | - |
| 0.3274 | 11650 | 0.2361 | - |
| 0.3288 | 11700 | 0.2431 | - |
| 0.3302 | 11750 | 0.2462 | - |
| 0.3316 | 11800 | 0.2438 | - |
| 0.3330 | 11850 | 0.2498 | - |
| 0.3344 | 11900 | 0.262 | - |
| 0.3358 | 11950 | 0.2451 | - |
| 0.3372 | 12000 | 0.251 | - |
| 0.3386 | 12050 | 0.2605 | - |
| 0.3400 | 12100 | 0.2477 | - |
| 0.3414 | 12150 | 0.2417 | - |
| 0.3428 | 12200 | 0.2566 | - |
| 0.3442 | 12250 | 0.2373 | - |
| 0.3456 | 12300 | 0.2444 | - |
| 0.3470 | 12350 | 0.2589 | - |
| 0.3484 | 12400 | 0.2491 | - |
| 0.3498 | 12450 | 0.2438 | - |
| 0.3512 | 12500 | 0.2519 | - |
| 0.3526 | 12550 | 0.2406 | - |
| 0.3541 | 12600 | 0.2472 | - |
| 0.3555 | 12650 | 0.2447 | - |
| 0.3569 | 12700 | 0.2677 | - |
| 0.3583 | 12750 | 0.2486 | - |
| 0.3597 | 12800 | 0.2585 | - |
| 0.3611 | 12850 | 0.2539 | - |
| 0.3625 | 12900 | 0.2556 | - |
| 0.3639 | 12950 | 0.2653 | - |
| 0.3653 | 13000 | 0.2583 | - |
| 0.3667 | 13050 | 0.2308 | - |
| 0.3681 | 13100 | 0.2586 | - |
| 0.3695 | 13150 | 0.2384 | - |
| 0.3709 | 13200 | 0.2645 | - |
| 0.3723 | 13250 | 0.2394 | - |
| 0.3737 | 13300 | 0.2575 | - |
| 0.3751 | 13350 | 0.2418 | - |
| 0.3765 | 13400 | 0.2414 | - |
| 0.3779 | 13450 | 0.2516 | - |
| 0.3793 | 13500 | 0.2571 | - |
| 0.3807 | 13550 | 0.2352 | - |
| 0.3822 | 13600 | 0.2584 | - |
| 0.3836 | 13650 | 0.2561 | - |
| 0.3850 | 13700 | 0.2672 | - |
| 0.3864 | 13750 | 0.2574 | - |
| 0.3878 | 13800 | 0.2398 | - |
| 0.3892 | 13850 | 0.2359 | - |
| 0.3906 | 13900 | 0.2397 | - |
| 0.3920 | 13950 | 0.2582 | - |
| 0.3934 | 14000 | 0.2468 | - |
| 0.3948 | 14050 | 0.2702 | - |
| 0.3962 | 14100 | 0.2547 | - |
| 0.3976 | 14150 | 0.2382 | - |
| 0.3990 | 14200 | 0.255 | - |
| 0.4004 | 14250 | 0.2382 | - |
| 0.4018 | 14300 | 0.2516 | - |
| 0.4032 | 14350 | 0.236 | - |
| 0.4046 | 14400 | 0.2499 | - |
| 0.4060 | 14450 | 0.2606 | - |
| 0.4074 | 14500 | 0.2514 | - |
| 0.4088 | 14550 | 0.2442 | - |
| 0.4103 | 14600 | 0.2516 | - |
| 0.4117 | 14650 | 0.2439 | - |
| 0.4131 | 14700 | 0.2547 | - |
| 0.4145 | 14750 | 0.2522 | - |
| 0.4159 | 14800 | 0.2421 | - |
| 0.4173 | 14850 | 0.2461 | - |
| 0.4187 | 14900 | 0.2663 | - |
| 0.4201 | 14950 | 0.259 | - |
| 0.4215 | 15000 | 0.2526 | - |
| 0.4229 | 15050 | 0.2527 | - |
| 0.4243 | 15100 | 0.2547 | - |
| 0.4257 | 15150 | 0.2696 | - |
| 0.4271 | 15200 | 0.2399 | - |
| 0.4285 | 15250 | 0.2557 | - |
| 0.4299 | 15300 | 0.2581 | - |
| 0.4313 | 15350 | 0.2402 | - |
| 0.4327 | 15400 | 0.2658 | - |
| 0.4341 | 15450 | 0.2491 | - |
| 0.4355 | 15500 | 0.2434 | - |
| 0.4369 | 15550 | 0.2511 | - |
| 0.4384 | 15600 | 0.2448 | - |
| 0.4398 | 15650 | 0.262 | - |
| 0.4412 | 15700 | 0.2549 | - |
| 0.4426 | 15750 | 0.2546 | - |
| 0.4440 | 15800 | 0.2444 | - |
| 0.4454 | 15850 | 0.2551 | - |
| 0.4468 | 15900 | 0.247 | - |
| 0.4482 | 15950 | 0.253 | - |
| 0.4496 | 16000 | 0.2615 | - |
| 0.4510 | 16050 | 0.2514 | - |
| 0.4524 | 16100 | 0.2587 | - |
| 0.4538 | 16150 | 0.2591 | - |
| 0.4552 | 16200 | 0.249 | - |
| 0.4566 | 16250 | 0.2459 | - |
| 0.4580 | 16300 | 0.2582 | - |
| 0.4594 | 16350 | 0.243 | - |
| 0.4608 | 16400 | 0.2493 | - |
| 0.4622 | 16450 | 0.2306 | - |
| 0.4636 | 16500 | 0.2561 | - |
| 0.4650 | 16550 | 0.2363 | - |
| 0.4664 | 16600 | 0.2412 | - |
| 0.4679 | 16650 | 0.2454 | - |
| 0.4693 | 16700 | 0.2575 | - |
| 0.4707 | 16750 | 0.2369 | - |
| 0.4721 | 16800 | 0.245 | - |
| 0.4735 | 16850 | 0.2591 | - |
| 0.4749 | 16900 | 0.2582 | - |
| 0.4763 | 16950 | 0.2629 | - |
| 0.4777 | 17000 | 0.2393 | - |
| 0.4791 | 17050 | 0.2563 | - |
| 0.4805 | 17100 | 0.2511 | - |
| 0.4819 | 17150 | 0.2538 | - |
| 0.4833 | 17200 | 0.2464 | - |
| 0.4847 | 17250 | 0.2511 | - |
| 0.4861 | 17300 | 0.244 | - |
| 0.4875 | 17350 | 0.2688 | - |
| 0.4889 | 17400 | 0.2729 | - |
| 0.4903 | 17450 | 0.2523 | - |
| 0.4917 | 17500 | 0.2507 | - |
| 0.4931 | 17550 | 0.2527 | - |
| 0.4945 | 17600 | 0.2478 | - |
| 0.4960 | 17650 | 0.26 | - |
| 0.4974 | 17700 | 0.2526 | - |
| 0.4988 | 17750 | 0.2549 | - |
| 0.5002 | 17800 | 0.2496 | - |
| 0.5016 | 17850 | 0.2537 | - |
| 0.5030 | 17900 | 0.2644 | - |
| 0.5044 | 17950 | 0.2633 | - |
| 0.5058 | 18000 | 0.2515 | - |
| 0.5072 | 18050 | 0.2551 | - |
| 0.5086 | 18100 | 0.2427 | - |
| 0.5100 | 18150 | 0.2615 | - |
| 0.5114 | 18200 | 0.2455 | - |
| 0.5128 | 18250 | 0.2615 | - |
| 0.5142 | 18300 | 0.2558 | - |
| 0.5156 | 18350 | 0.2483 | - |
| 0.5170 | 18400 | 0.2618 | - |
| 0.5184 | 18450 | 0.2404 | - |
| 0.5198 | 18500 | 0.2562 | - |
| 0.5212 | 18550 | 0.259 | - |
| 0.5226 | 18600 | 0.246 | - |
| 0.5241 | 18650 | 0.2529 | - |
| 0.5255 | 18700 | 0.2526 | - |
| 0.5269 | 18750 | 0.2381 | - |
| 0.5283 | 18800 | 0.2648 | - |
| 0.5297 | 18850 | 0.2628 | - |
| 0.5311 | 18900 | 0.2528 | - |
| 0.5325 | 18950 | 0.2447 | - |
| 0.5339 | 19000 | 0.2467 | - |
| 0.5353 | 19050 | 0.2487 | - |
| 0.5367 | 19100 | 0.2494 | - |
| 0.5381 | 19150 | 0.2441 | - |
| 0.5395 | 19200 | 0.2507 | - |
| 0.5409 | 19250 | 0.2494 | - |
| 0.5423 | 19300 | 0.2501 | - |
| 0.5437 | 19350 | 0.2586 | - |
| 0.5451 | 19400 | 0.2677 | - |
| 0.5465 | 19450 | 0.2558 | - |
| 0.5479 | 19500 | 0.2444 | - |
| 0.5493 | 19550 | 0.251 | - |
| 0.5507 | 19600 | 0.2545 | - |
| 0.5522 | 19650 | 0.2464 | - |
| 0.5536 | 19700 | 0.2565 | - |
| 0.5550 | 19750 | 0.2674 | - |
| 0.5564 | 19800 | 0.2483 | - |
| 0.5578 | 19850 | 0.241 | - |
| 0.5592 | 19900 | 0.2504 | - |
| 0.5606 | 19950 | 0.2655 | - |
| 0.5620 | 20000 | 0.2484 | - |
| 0.5634 | 20050 | 0.254 | - |
| 0.5648 | 20100 | 0.2482 | - |
| 0.5662 | 20150 | 0.2644 | - |
| 0.5676 | 20200 | 0.2694 | - |
| 0.5690 | 20250 | 0.258 | - |
| 0.5704 | 20300 | 0.2587 | - |
| 0.5718 | 20350 | 0.2571 | - |
| 0.5732 | 20400 | 0.2464 | - |
| 0.5746 | 20450 | 0.2531 | - |
| 0.5760 | 20500 | 0.2504 | - |
| 0.5774 | 20550 | 0.2551 | - |
| 0.5788 | 20600 | 0.253 | - |
| 0.5803 | 20650 | 0.2374 | - |
| 0.5817 | 20700 | 0.2405 | - |
| 0.5831 | 20750 | 0.2435 | - |
| 0.5845 | 20800 | 0.2569 | - |
| 0.5859 | 20850 | 0.2533 | - |
| 0.5873 | 20900 | 0.2508 | - |
| 0.5887 | 20950 | 0.2508 | - |
| 0.5901 | 21000 | 0.2531 | - |
| 0.5915 | 21050 | 0.2381 | - |
| 0.5929 | 21100 | 0.2009 | - |
| 0.5943 | 21150 | 0.0899 | - |
| 0.5957 | 21200 | 0.3046 | - |
| 0.5971 | 21250 | 0.2006 | - |
| 0.5985 | 21300 | 0.2289 | - |
| 0.5999 | 21350 | 0.1581 | - |
| 0.6013 | 21400 | 0.1769 | - |
| 0.6027 | 21450 | 0.2377 | - |
| 0.6041 | 21500 | 0.1988 | - |
| 0.6055 | 21550 | 0.2543 | - |
| 0.6069 | 21600 | 0.2517 | - |
| 0.6084 | 21650 | 0.2191 | - |
| 0.6098 | 21700 | 0.2803 | - |
| 0.6112 | 21750 | 0.2984 | - |
| 0.6126 | 21800 | 0.1915 | - |
| 0.6140 | 21850 | 0.189 | - |
| 0.6154 | 21900 | 0.1302 | - |
| 0.6168 | 21950 | 0.203 | - |
| 0.6182 | 22000 | 0.2038 | - |
| 0.6196 | 22050 | 0.134 | - |
| 0.6210 | 22100 | 0.1904 | - |
| 0.6224 | 22150 | 0.1477 | - |
| 0.6238 | 22200 | 0.1338 | - |
| 0.6252 | 22250 | 0.0709 | - |
| 0.6266 | 22300 | 0.0902 | - |
| 0.6280 | 22350 | 0.2025 | - |
| 0.6294 | 22400 | 0.0991 | - |
| 0.6308 | 22450 | 0.1321 | - |
| 0.6322 | 22500 | 0.1356 | - |
| 0.6336 | 22550 | 0.1682 | - |
| 0.6350 | 22600 | 0.2064 | - |
| 0.6365 | 22650 | 0.2 | - |
| 0.6379 | 22700 | 0.2105 | - |
| 0.6393 | 22750 | 0.2074 | - |
| 0.6407 | 22800 | 0.1901 | - |
| 0.6421 | 22850 | 0.1914 | - |
| 0.6435 | 22900 | 0.1831 | - |
| 0.6449 | 22950 | 0.1423 | - |
| 0.6463 | 23000 | 0.2502 | - |
| 0.6477 | 23050 | 0.1655 | - |
| 0.6491 | 23100 | 0.1585 | - |
| 0.6505 | 23150 | 0.2122 | - |
| 0.6519 | 23200 | 0.217 | - |
| 0.6533 | 23250 | 0.1704 | - |
| 0.6547 | 23300 | 0.189 | - |
| 0.6561 | 23350 | 0.1333 | - |
| 0.6575 | 23400 | 0.1863 | - |
| 0.6589 | 23450 | 0.2089 | - |
| 0.6603 | 23500 | 0.1261 | - |
| 0.6617 | 23550 | 0.1655 | - |
| 0.6631 | 23600 | 0.1721 | - |
| 0.6645 | 23650 | 0.083 | - |
| 0.6660 | 23700 | 0.1166 | - |
| 0.6674 | 23750 | 0.146 | - |
| 0.6688 | 23800 | 0.0423 | - |
| 0.6702 | 23850 | 0.1781 | - |
| 0.6716 | 23900 | 0.121 | - |
| 0.6730 | 23950 | 0.1624 | - |
| 0.6744 | 24000 | 0.1483 | - |
| 0.6758 | 24050 | 0.1479 | - |
| 0.6772 | 24100 | 0.2285 | - |
| 0.6786 | 24150 | 0.2084 | - |
| 0.6800 | 24200 | 0.12 | - |
| 0.6814 | 24250 | 0.115 | - |
| 0.6828 | 24300 | 0.1331 | - |
| 0.6842 | 24350 | 0.0971 | - |
| 0.6856 | 24400 | 0.0846 | - |
| 0.6870 | 24450 | 0.2254 | - |
| 0.6884 | 24500 | 0.1348 | - |
| 0.6898 | 24550 | 0.0633 | - |
| 0.6912 | 24600 | 0.1207 | - |
| 0.6926 | 24650 | 0.2109 | - |
| 0.6941 | 24700 | 0.0768 | - |
| 0.6955 | 24750 | 0.108 | - |
| 0.6969 | 24800 | 0.0665 | - |
| 0.6983 | 24850 | 0.0601 | - |
| 0.6997 | 24900 | 0.1922 | - |
| 0.7011 | 24950 | 0.1517 | - |
| 0.7025 | 25000 | 0.1049 | - |
| 0.7039 | 25050 | 0.1122 | - |
| 0.7053 | 25100 | 0.0973 | - |
| 0.7067 | 25150 | 0.1547 | - |
| 0.7081 | 25200 | 0.115 | - |
| 0.7095 | 25250 | 0.1881 | - |
| 0.7109 | 25300 | 0.2144 | - |
| 0.7123 | 25350 | 0.0567 | - |
| 0.7137 | 25400 | 0.0917 | - |
| 0.7151 | 25450 | 0.1404 | - |
| 0.7165 | 25500 | 0.019 | - |
| 0.7179 | 25550 | 0.1382 | - |
| 0.7193 | 25600 | 0.0727 | - |
| 0.7207 | 25650 | 0.1125 | - |
| 0.7222 | 25700 | 0.1133 | - |
| 0.7236 | 25750 | 0.0987 | - |
| 0.7250 | 25800 | 0.1915 | - |
| 0.7264 | 25850 | 0.09 | - |
| 0.7278 | 25900 | 0.1462 | - |
| 0.7292 | 25950 | 0.0881 | - |
| 0.7306 | 26000 | 0.1026 | - |
| 0.7320 | 26050 | 0.1079 | - |
| 0.7334 | 26100 | 0.1639 | - |
| 0.7348 | 26150 | 0.1229 | - |
| 0.7362 | 26200 | 0.3261 | - |
| 0.7376 | 26250 | 0.1426 | - |
| 0.7390 | 26300 | 0.0773 | - |
| 0.7404 | 26350 | 0.1607 | - |
| 0.7418 | 26400 | 0.1354 | - |
| 0.7432 | 26450 | 0.1512 | - |
| 0.7446 | 26500 | 0.1875 | - |
| 0.7460 | 26550 | 0.1403 | - |
| 0.7474 | 26600 | 0.1287 | - |
| 0.7488 | 26650 | 0.1892 | - |
| 0.7503 | 26700 | 0.166 | - |
| 0.7517 | 26750 | 0.2385 | - |
| 0.7531 | 26800 | 0.1445 | - |
| 0.7545 | 26850 | 0.0969 | - |
| 0.7559 | 26900 | 0.0948 | - |
| 0.7573 | 26950 | 0.0589 | - |
| 0.7587 | 27000 | 0.2326 | - |
| 0.7601 | 27050 | 0.1438 | - |
| 0.7615 | 27100 | 0.1032 | - |
| 0.7629 | 27150 | 0.0784 | - |
| 0.7643 | 27200 | 0.1478 | - |
| 0.7657 | 27250 | 0.1872 | - |
| 0.7671 | 27300 | 0.0672 | - |
| 0.7685 | 27350 | 0.0725 | - |
| 0.7699 | 27400 | 0.0771 | - |
| 0.7713 | 27450 | 0.2575 | - |
| 0.7727 | 27500 | 0.133 | - |
| 0.7741 | 27550 | 0.1222 | - |
| 0.7755 | 27600 | 0.1207 | - |
| 0.7769 | 27650 | 0.0973 | - |
| 0.7784 | 27700 | 0.2186 | - |
| 0.7798 | 27750 | 0.1648 | - |
| 0.7812 | 27800 | 0.1128 | - |
| 0.7826 | 27850 | 0.1626 | - |
| 0.7840 | 27900 | 0.1768 | - |
| 0.7854 | 27950 | 0.1806 | - |
| 0.7868 | 28000 | 0.1197 | - |
| 0.7882 | 28050 | 0.0472 | - |
| 0.7896 | 28100 | 0.1463 | - |
| 0.7910 | 28150 | 0.1707 | - |
| 0.7924 | 28200 | 0.0924 | - |
| 0.7938 | 28250 | 0.1708 | - |
| 0.7952 | 28300 | 0.1101 | - |
| 0.7966 | 28350 | 0.0867 | - |
| 0.7980 | 28400 | 0.1606 | - |
| 0.7994 | 28450 | 0.2422 | - |
| 0.8008 | 28500 | 0.1289 | - |
| 0.8022 | 28550 | 0.0513 | - |
| 0.8036 | 28600 | 0.1468 | - |
| 0.8050 | 28650 | 0.1742 | - |
| 0.8065 | 28700 | 0.0813 | - |
| 0.8079 | 28750 | 0.0916 | - |
| 0.8093 | 28800 | 0.0826 | - |
| 0.8107 | 28850 | 0.1457 | - |
| 0.8121 | 28900 | 0.0952 | - |
| 0.8135 | 28950 | 0.1376 | - |
| 0.8149 | 29000 | 0.06 | - |
| 0.8163 | 29050 | 0.1221 | - |
| 0.8177 | 29100 | 0.0713 | - |
| 0.8191 | 29150 | 0.1219 | - |
| 0.8205 | 29200 | 0.1051 | - |
| 0.8219 | 29250 | 0.1503 | - |
| 0.8233 | 29300 | 0.1128 | - |
| 0.8247 | 29350 | 0.0946 | - |
| 0.8261 | 29400 | 0.2115 | - |
| 0.8275 | 29450 | 0.1058 | - |
| 0.8289 | 29500 | 0.1085 | - |
| 0.8303 | 29550 | 0.1632 | - |
| 0.8317 | 29600 | 0.1022 | - |
| 0.8331 | 29650 | 0.136 | - |
| 0.8346 | 29700 | 0.1231 | - |
| 0.8360 | 29750 | 0.0929 | - |
| 0.8374 | 29800 | 0.1299 | - |
| 0.8388 | 29850 | 0.0693 | - |
| 0.8402 | 29900 | 0.0738 | - |
| 0.8416 | 29950 | 0.0826 | - |
| 0.8430 | 30000 | 0.1831 | - |
| 0.8444 | 30050 | 0.0962 | - |
| 0.8458 | 30100 | 0.0869 | - |
| 0.8472 | 30150 | 0.1459 | - |
| 0.8486 | 30200 | 0.1468 | - |
| 0.8500 | 30250 | 0.2132 | - |
| 0.8514 | 30300 | 0.1472 | - |
| 0.8528 | 30350 | 0.1294 | - |
| 0.8542 | 30400 | 0.0822 | - |
| 0.8556 | 30450 | 0.144 | - |
| 0.8570 | 30500 | 0.1216 | - |
| 0.8584 | 30550 | 0.1381 | - |
| 0.8598 | 30600 | 0.1612 | - |
| 0.8612 | 30650 | 0.1665 | - |
| 0.8627 | 30700 | 0.2035 | - |
| 0.8641 | 30750 | 0.136 | - |
| 0.8655 | 30800 | 0.1685 | - |
| 0.8669 | 30850 | 0.1421 | - |
| 0.8683 | 30900 | 0.1169 | - |
| 0.8697 | 30950 | 0.1799 | - |
| 0.8711 | 31000 | 0.2185 | - |
| 0.8725 | 31050 | 0.1321 | - |
| 0.8739 | 31100 | 0.145 | - |
| 0.8753 | 31150 | 0.1848 | - |
| 0.8767 | 31200 | 0.2173 | - |
| 0.8781 | 31250 | 0.2036 | - |
| 0.8795 | 31300 | 0.2056 | - |
| 0.8809 | 31350 | 0.312 | - |
| 0.8823 | 31400 | 0.2119 | - |
| 0.8837 | 31450 | 0.1875 | - |
| 0.8851 | 31500 | 0.2216 | - |
| 0.8865 | 31550 | 0.2267 | - |
| 0.8879 | 31600 | 0.2709 | - |
| 0.8893 | 31650 | 0.1868 | - |
| 0.8907 | 31700 | 0.1752 | - |
| 0.8922 | 31750 | 0.2468 | - |
| 0.8936 | 31800 | 0.1632 | - |
| 0.8950 | 31850 | 0.2483 | - |
| 0.8964 | 31900 | 0.1597 | - |
| 0.8978 | 31950 | 0.1587 | - |
| 0.8992 | 32000 | 0.0897 | - |
| 0.9006 | 32050 | 0.0764 | - |
| 0.9020 | 32100 | 0.1798 | - |
| 0.9034 | 32150 | 0.1254 | - |
| 0.9048 | 32200 | 0.1905 | - |
| 0.9062 | 32250 | 0.0714 | - |
| 0.9076 | 32300 | 0.1377 | - |
| 0.9090 | 32350 | 0.0192 | - |
| 0.9104 | 32400 | 0.1208 | - |
| 0.9118 | 32450 | 0.239 | - |
| 0.9132 | 32500 | 0.0965 | - |
| 0.9146 | 32550 | 0.1189 | - |
| 0.9160 | 32600 | 0.0856 | - |
| 0.9174 | 32650 | 0.1041 | - |
| 0.9188 | 32700 | 0.1107 | - |
| 0.9203 | 32750 | 0.1499 | - |
| 0.9217 | 32800 | 0.0874 | - |
| 0.9231 | 32850 | 0.1255 | - |
| 0.9245 | 32900 | 0.1099 | - |
| 0.9259 | 32950 | 0.1806 | - |
| 0.9273 | 33000 | 0.0544 | - |
| 0.9287 | 33050 | 0.0504 | - |
| 0.9301 | 33100 | 0.2441 | - |
| 0.9315 | 33150 | 0.0266 | - |
| 0.9329 | 33200 | 0.0985 | - |
| 0.9343 | 33250 | 0.0923 | - |
| 0.9357 | 33300 | 0.1054 | - |
| 0.9371 | 33350 | 0.0625 | - |
| 0.9385 | 33400 | 0.0882 | - |
| 0.9399 | 33450 | 0.102 | - |
| 0.9413 | 33500 | 0.108 | - |
| 0.9427 | 33550 | 0.135 | - |
| 0.9441 | 33600 | 0.1016 | - |
| 0.9455 | 33650 | 0.2008 | - |
| 0.9469 | 33700 | 0.0591 | - |
| 0.9484 | 33750 | 0.1922 | - |
| 0.9498 | 33800 | 0.1045 | - |
| 0.9512 | 33850 | 0.102 | - |
| 0.9526 | 33900 | 0.0634 | - |
| 0.9540 | 33950 | 0.0668 | - |
| 0.9554 | 34000 | 0.1339 | - |
| 0.9568 | 34050 | 0.0599 | - |
| 0.9582 | 34100 | 0.0623 | - |
| 0.9596 | 34150 | 0.1133 | - |
| 0.9610 | 34200 | 0.1218 | - |
| 0.9624 | 34250 | 0.0618 | - |
| 0.9638 | 34300 | 0.1062 | - |
| 0.9652 | 34350 | 0.0909 | - |
| 0.9666 | 34400 | 0.0885 | - |
| 0.9680 | 34450 | 0.1461 | - |
| 0.9694 | 34500 | 0.0254 | - |
| 0.9708 | 34550 | 0.0697 | - |
| 0.9722 | 34600 | 0.016 | - |
| 0.9736 | 34650 | 0.1524 | - |
| 0.9750 | 34700 | 0.1468 | - |
| 0.9765 | 34750 | 0.1497 | - |
| 0.9779 | 34800 | 0.0785 | - |
| 0.9793 | 34850 | 0.0645 | - |
| 0.9807 | 34900 | 0.1357 | - |
| 0.9821 | 34950 | 0.1469 | - |
| 0.9835 | 35000 | 0.2356 | - |
| 0.9849 | 35050 | 0.018 | - |
| 0.9863 | 35100 | 0.1534 | - |
| 0.9877 | 35150 | 0.14 | - |
| 0.9891 | 35200 | 0.1001 | - |
| 0.9905 | 35250 | 0.0614 | - |
| 0.9919 | 35300 | 0.1407 | - |
| 0.9933 | 35350 | 0.1104 | - |
| 0.9947 | 35400 | 0.1477 | - |
| 0.9961 | 35450 | 0.1279 | - |
| 0.9975 | 35500 | 0.0957 | - |
| 0.9989 | 35550 | 0.0579 | - |
| **1.0** | **35588** | **-** | **0.1207** |
* 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}
}
```