nazhan's picture
Add SetFit model
53aea9d verified
metadata
base_model: BAAI/bge-small-en-v1.5
library_name: setfit
metrics:
  - accuracy
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      What tables are included in the starhub_data_asset database that relate to
      customer complaints?
  - text: What are the tables that I can access in the starhub_data_asset database?
  - text: Can I have avg Cost_Efficiency
  - text: Analyze product category revenue impact.
  - text: Retrieve data_asset_kpi_ma_product details.
inference: true
model-index:
  - name: SetFit with BAAI/bge-small-en-v1.5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.9914529914529915
            name: Accuracy

SetFit with BAAI/bge-small-en-v1.5

This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-small-en-v1.5 as the Sentence Transformer embedding model. A LogisticRegression 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 with contrastive learning.
  2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

Model Sources

Model Labels

Label Examples
Generalreply
  • 'Can you recommend a good movie to watch?'
  • "Oh, that's a tough one! There are so many good memories to choose from. But if I had to pick just one, I think it would be spending summers at my grandparent's house. We would play board games, make homemade ice cream, and have big family dinners. It was always so much fun!"
  • 'Oh, I love reading books! My favorite genre is definitely fantasy. How about you? What kind of books do you like to read?'
Lookup_1
  • 'Get me data_asset_kpi_cf cash flow.'
  • 'Display data_asset_001_pcc for electronics category.'
  • 'Calculate Gross Profit Margin Trends.'
Lookup
  • "What are the products in the 'Clothing' category?"
  • "Get me the phone numbers of customers with the last name 'Johnson'."
  • "Can you filter by employees who have the last name 'Brown'?"
Aggregation
  • 'Get me max Accumulated Amortisation and Impairment.'
  • 'Can I have mode of Revenue'
  • 'Show me count company_name'
Tablejoin
  • 'Could you merge the Orders and Employees tables to identify which employees have processed high-value orders?'
  • 'Could you connect the Products and Orders tables to analyze sales data by product category?'
  • 'How can I connect the Customers and Orders tables to find customers who made purchases during a specific promotion?'
Viewtables
  • 'What are the tables in the starhub_data_asset database that a user can join to perform a sales analysis?'
  • 'What tables can be found in the asset-tracking section of the starhub_data_asset database?'
  • 'What tables exist in the starhub_data_asset database?'
Rejection
  • "Let's avoid creating any new data sets."
  • "I'd prefer to avoid generating data fields."
  • "I'm not interested in filtering this collection."

Evaluation

Metrics

Label Accuracy
all 0.9915

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("nazhan/bge-small-en-v1.5-brahmaputra-iter-10")
# Run inference
preds = model("Can I have avg Cost_Efficiency")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 1 8.6563 62
Label Training Sample Count
Tablejoin 129
Rejection 77
Aggregation 282
Lookup 60
Generalreply 63
Viewtables 74
Lookup_1 150

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 0.2038 -
0.0014 50 0.2019 -
0.0029 100 0.1983 -
0.0043 150 0.206 -
0.0057 200 0.2268 -
0.0071 250 0.2025 -
0.0086 300 0.2041 -
0.0100 350 0.1426 -
0.0114 400 0.1513 -
0.0129 450 0.1215 -
0.0143 500 0.1426 -
0.0157 550 0.0859 -
0.0172 600 0.0486 -
0.0186 650 0.0378 -
0.0200 700 0.0519 -
0.0214 750 0.0717 -
0.0229 800 0.1161 -
0.0243 850 0.0771 -
0.0257 900 0.074 -
0.0272 950 0.0567 -
0.0286 1000 0.0223 -
0.0300 1050 0.0266 -
0.0315 1100 0.0261 -
0.0329 1150 0.0333 -
0.0343 1200 0.0107 -
0.0357 1250 0.0123 -
0.0372 1300 0.0193 -
0.0386 1350 0.0039 -
0.0400 1400 0.0079 -
0.0415 1450 0.0035 -
0.0429 1500 0.003 -
0.0443 1550 0.0041 -
0.0457 1600 0.0038 -
0.0472 1650 0.002 -
0.0486 1700 0.0028 -
0.0500 1750 0.0056 -
0.0515 1800 0.0035 -
0.0529 1850 0.0027 -
0.0543 1900 0.0028 -
0.0558 1950 0.0028 -
0.0572 2000 0.0019 -
0.0586 2050 0.0046 -
0.0600 2100 0.0017 -
0.0615 2150 0.0016 -
0.0629 2200 0.0022 -
0.0643 2250 0.002 -
0.0658 2300 0.0029 -
0.0672 2350 0.0032 -
0.0686 2400 0.0018 -
0.0701 2450 0.0015 -
0.0715 2500 0.0015 -
0.0729 2550 0.0016 -
0.0743 2600 0.0012 -
0.0758 2650 0.0014 -
0.0772 2700 0.0015 -
0.0786 2750 0.0018 -
0.0801 2800 0.0012 -
0.0815 2850 0.0009 -
0.0829 2900 0.001 -
0.0843 2950 0.0011 -
0.0858 3000 0.0011 -
0.0872 3050 0.001 -
0.0886 3100 0.0012 -
0.0901 3150 0.0006 -
0.0915 3200 0.0013 -
0.0929 3250 0.0007 -
0.0944 3300 0.0007 -
0.0958 3350 0.0009 -
0.0972 3400 0.0008 -
0.0986 3450 0.0005 -
0.1001 3500 0.001 -
0.1015 3550 0.001 -
0.1029 3600 0.0008 -
0.1044 3650 0.0007 -
0.1058 3700 0.0006 -
0.1072 3750 0.0009 -
0.1086 3800 0.0012 -
0.1101 3850 0.0007 -
0.1115 3900 0.0008 -
0.1129 3950 0.0009 -
0.1144 4000 0.0007 -
0.1158 4050 0.0007 -
0.1172 4100 0.0007 -
0.1187 4150 0.0006 -
0.1201 4200 0.0006 -
0.1215 4250 0.0011 -
0.1229 4300 0.0012 -
0.1244 4350 0.0007 -
0.1258 4400 0.0007 -
0.1272 4450 0.0006 -
0.1287 4500 0.0005 -
0.1301 4550 0.0008 -
0.1315 4600 0.0006 -
0.1330 4650 0.0007 -
0.1344 4700 0.0006 -
0.1358 4750 0.0005 -
0.1372 4800 0.0006 -
0.1387 4850 0.0008 -
0.1401 4900 0.0008 -
0.1415 4950 0.0004 -
0.1430 5000 0.0005 -
0.1444 5050 0.0005 -
0.1458 5100 0.0007 -
0.1472 5150 0.0006 -
0.1487 5200 0.0006 -
0.1501 5250 0.0004 -
0.1515 5300 0.0005 -
0.1530 5350 0.0007 -
0.1544 5400 0.0007 -
0.1558 5450 0.0005 -
0.1573 5500 0.0007 -
0.1587 5550 0.0004 -
0.1601 5600 0.0004 -
0.1615 5650 0.0006 -
0.1630 5700 0.0005 -
0.1644 5750 0.0006 -
0.1658 5800 0.0004 -
0.1673 5850 0.0005 -
0.1687 5900 0.0007 -
0.1701 5950 0.0005 -
0.1716 6000 0.0005 -
0.1730 6050 0.0003 -
0.1744 6100 0.0003 -
0.1758 6150 0.0005 -
0.1773 6200 0.0007 -
0.1787 6250 0.0004 -
0.1801 6300 0.0006 -
0.1816 6350 0.0004 -
0.1830 6400 0.0003 -
0.1844 6450 0.0005 -
0.1858 6500 0.0004 -
0.1873 6550 0.0006 -
0.1887 6600 0.0005 -
0.1901 6650 0.0005 -
0.1916 6700 0.0003 -
0.1930 6750 0.0004 -
0.1944 6800 0.0004 -
0.1959 6850 0.0004 -
0.1973 6900 0.0003 -
0.1987 6950 0.0004 -
0.2001 7000 0.0004 -
0.2016 7050 0.0003 -
0.2030 7100 0.0003 -
0.2044 7150 0.0005 -
0.2059 7200 0.0004 -
0.2073 7250 0.0003 -
0.2087 7300 0.0002 -
0.2102 7350 0.0003 -
0.2116 7400 0.0004 -
0.2130 7450 0.0006 -
0.2144 7500 0.0003 -
0.2159 7550 0.0002 -
0.2173 7600 0.0004 -
0.2187 7650 0.0003 -
0.2202 7700 0.0005 -
0.2216 7750 0.0004 -
0.2230 7800 0.0004 -
0.2244 7850 0.0004 -
0.2259 7900 0.0003 -
0.2273 7950 0.0005 -
0.2287 8000 0.0003 -
0.2302 8050 0.0003 -
0.2316 8100 0.0003 -
0.2330 8150 0.0002 -
0.2345 8200 0.0002 -
0.2359 8250 0.0004 -
0.2373 8300 0.0004 -
0.2387 8350 0.0004 -
0.2402 8400 0.0003 -
0.2416 8450 0.0002 -
0.2430 8500 0.0002 -
0.2445 8550 0.0003 -
0.2459 8600 0.0004 -
0.2473 8650 0.0004 -
0.2487 8700 0.0003 -
0.2502 8750 0.0002 -
0.2516 8800 0.0003 -
0.2530 8850 0.0003 -
0.2545 8900 0.0004 -
0.2559 8950 0.0003 -
0.2573 9000 0.0002 -
0.2588 9050 0.0003 -
0.2602 9100 0.0003 -
0.2616 9150 0.0003 -
0.2630 9200 0.0003 -
0.2645 9250 0.0002 -
0.2659 9300 0.0002 -
0.2673 9350 0.0003 -
0.2688 9400 0.0552 -
0.2702 9450 0.0003 -
0.2716 9500 0.0003 -
0.2731 9550 0.0004 -
0.2745 9600 0.0004 -
0.2759 9650 0.0005 -
0.2773 9700 0.0003 -
0.2788 9750 0.0003 -
0.2802 9800 0.0003 -
0.2816 9850 0.0003 -
0.2831 9900 0.0004 -
0.2845 9950 0.0003 -
0.2859 10000 0.0003 -
0.2873 10050 0.0004 -
0.2888 10100 0.0005 -
0.2902 10150 0.0003 -
0.2916 10200 0.0004 -
0.2931 10250 0.0002 -
0.2945 10300 0.0005 -
0.2959 10350 0.0003 -
0.2974 10400 0.0003 -
0.2988 10450 0.0002 -
0.3002 10500 0.0003 -
0.3016 10550 0.0004 -
0.3031 10600 0.0003 -
0.3045 10650 0.0003 -
0.3059 10700 0.0004 -
0.3074 10750 0.0003 -
0.3088 10800 0.0003 -
0.3102 10850 0.0003 -
0.3117 10900 0.0002 -
0.3131 10950 0.0005 -
0.3145 11000 0.0003 -
0.3159 11050 0.0002 -
0.3174 11100 0.0003 -
0.3188 11150 0.0004 -
0.3202 11200 0.0004 -
0.3217 11250 0.0002 -
0.3231 11300 0.0003 -
0.3245 11350 0.0003 -
0.3259 11400 0.0003 -
0.3274 11450 0.0004 -
0.3288 11500 0.0004 -
0.3302 11550 0.0003 -
0.3317 11600 0.0003 -
0.3331 11650 0.0002 -
0.3345 11700 0.0004 -
0.3360 11750 0.0002 -
0.3374 11800 0.0003 -
0.3388 11850 0.0002 -
0.3402 11900 0.0003 -
0.3417 11950 0.0002 -
0.3431 12000 0.0004 -
0.3445 12050 0.0003 -
0.3460 12100 0.0004 -
0.3474 12150 0.0005 -
0.3488 12200 0.0004 -
0.3503 12250 0.0004 -
0.3517 12300 0.0002 -
0.3531 12350 0.0002 -
0.3545 12400 0.0004 -
0.3560 12450 0.0002 -
0.3574 12500 0.0002 -
0.3588 12550 0.0003 -
0.3603 12600 0.0005 -
0.3617 12650 0.0003 -
0.3631 12700 0.0003 -
0.3645 12750 0.0002 -
0.3660 12800 0.0003 -
0.3674 12850 0.0002 -
0.3688 12900 0.0002 -
0.3703 12950 0.0001 -
0.3717 13000 0.0002 -
0.3731 13050 0.0003 -
0.3746 13100 0.0003 -
0.3760 13150 0.0002 -
0.3774 13200 0.0004 -
0.3788 13250 0.0003 -
0.3803 13300 0.0002 -
0.3817 13350 0.0003 -
0.3831 13400 0.0003 -
0.3846 13450 0.0003 -
0.3860 13500 0.0002 -
0.3874 13550 0.0002 -
0.3888 13600 0.0003 -
0.3903 13650 0.0003 -
0.3917 13700 0.0002 -
0.3931 13750 0.0002 -
0.3946 13800 0.0002 -
0.3960 13850 0.0004 -
0.3974 13900 0.0003 -
0.3989 13950 0.0002 -
0.4003 14000 0.0003 -
0.4017 14050 0.0001 -
0.4031 14100 0.0002 -
0.4046 14150 0.0001 -
0.4060 14200 0.0002 -
0.4074 14250 0.0002 -
0.4089 14300 0.0002 -
0.4103 14350 0.0003 -
0.4117 14400 0.0003 -
0.4132 14450 0.0002 -
0.4146 14500 0.0003 -
0.4160 14550 0.0003 -
0.4174 14600 0.0002 -
0.4189 14650 0.0002 -
0.4203 14700 0.0003 -
0.4217 14750 0.0003 -
0.4232 14800 0.0002 -
0.4246 14850 0.0003 -
0.4260 14900 0.0003 -
0.4274 14950 0.0003 -
0.4289 15000 0.0002 -
0.4303 15050 0.0002 -
0.4317 15100 0.0002 -
0.4332 15150 0.0004 -
0.4346 15200 0.0003 -
0.4360 15250 0.0001 -
0.4375 15300 0.0002 -
0.4389 15350 0.0001 -
0.4403 15400 0.0002 -
0.4417 15450 0.0001 -
0.4432 15500 0.0002 -
0.4446 15550 0.0002 -
0.4460 15600 0.0002 -
0.4475 15650 0.0002 -
0.4489 15700 0.0003 -
0.4503 15750 0.0002 -
0.4518 15800 0.0002 -
0.4532 15850 0.0003 -
0.4546 15900 0.0003 -
0.4560 15950 0.0002 -
0.4575 16000 0.0002 -
0.4589 16050 0.0002 -
0.4603 16100 0.0003 -
0.4618 16150 0.0002 -
0.4632 16200 0.0003 -
0.4646 16250 0.0002 -
0.4660 16300 0.0002 -
0.4675 16350 0.0002 -
0.4689 16400 0.0002 -
0.4703 16450 0.0002 -
0.4718 16500 0.0002 -
0.4732 16550 0.0002 -
0.4746 16600 0.0003 -
0.4761 16650 0.0002 -
0.4775 16700 0.0002 -
0.4789 16750 0.0002 -
0.4803 16800 0.0002 -
0.4818 16850 0.0001 -
0.4832 16900 0.0003 -
0.4846 16950 0.0002 -
0.4861 17000 0.0002 -
0.4875 17050 0.0002 -
0.4889 17100 0.0002 -
0.4904 17150 0.0002 -
0.4918 17200 0.0002 -
0.4932 17250 0.0002 -
0.4946 17300 0.0002 -
0.4961 17350 0.0002 -
0.4975 17400 0.0002 -
0.4989 17450 0.0001 -
0.5004 17500 0.0001 -
0.5018 17550 0.0002 -
0.5032 17600 0.0002 -
0.5046 17650 0.0002 -
0.5061 17700 0.0002 -
0.5075 17750 0.0002 -
0.5089 17800 0.0002 -
0.5104 17850 0.0002 -
0.5118 17900 0.0002 -
0.5132 17950 0.0003 -
0.5147 18000 0.0002 -
0.5161 18050 0.0002 -
0.5175 18100 0.0002 -
0.5189 18150 0.0002 -
0.5204 18200 0.0002 -
0.5218 18250 0.0002 -
0.5232 18300 0.0002 -
0.5247 18350 0.0002 -
0.5261 18400 0.0002 -
0.5275 18450 0.0003 -
0.5289 18500 0.0001 -
0.5304 18550 0.0002 -
0.5318 18600 0.0001 -
0.5332 18650 0.0002 -
0.5347 18700 0.0002 -
0.5361 18750 0.0002 -
0.5375 18800 0.0002 -
0.5390 18850 0.0001 -
0.5404 18900 0.0001 -
0.5418 18950 0.0001 -
0.5432 19000 0.0002 -
0.5447 19050 0.0002 -
0.5461 19100 0.0002 -
0.5475 19150 0.0002 -
0.5490 19200 0.0002 -
0.5504 19250 0.0002 -
0.5518 19300 0.0001 -
0.5533 19350 0.0002 -
0.5547 19400 0.0002 -
0.5561 19450 0.0004 -
0.5575 19500 0.0002 -
0.5590 19550 0.0002 -
0.5604 19600 0.0003 -
0.5618 19650 0.0003 -
0.5633 19700 0.0002 -
0.5647 19750 0.0002 -
0.5661 19800 0.0001 -
0.5675 19850 0.0003 -
0.5690 19900 0.0002 -
0.5704 19950 0.0002 -
0.5718 20000 0.0001 -
0.5733 20050 0.0003 -
0.5747 20100 0.0001 -
0.5761 20150 0.0002 -
0.5776 20200 0.0003 -
0.5790 20250 0.0003 -
0.5804 20300 0.0002 -
0.5818 20350 0.0003 -
0.5833 20400 0.0002 -
0.5847 20450 0.0002 -
0.5861 20500 0.0002 -
0.5876 20550 0.0001 -
0.5890 20600 0.0002 -
0.5904 20650 0.0002 -
0.5919 20700 0.0002 -
0.5933 20750 0.0002 -
0.5947 20800 0.0001 -
0.5961 20850 0.0001 -
0.5976 20900 0.0001 -
0.5990 20950 0.0001 -
0.6004 21000 0.0002 -
0.6019 21050 0.0001 -
0.6033 21100 0.0002 -
0.6047 21150 0.0001 -
0.6061 21200 0.0002 -
0.6076 21250 0.0002 -
0.6090 21300 0.0001 -
0.6104 21350 0.0002 -
0.6119 21400 0.0001 -
0.6133 21450 0.0002 -
0.6147 21500 0.0001 -
0.6162 21550 0.0002 -
0.6176 21600 0.0001 -
0.6190 21650 0.0001 -
0.6204 21700 0.0001 -
0.6219 21750 0.0002 -
0.6233 21800 0.0001 -
0.6247 21850 0.0001 -
0.6262 21900 0.0001 -
0.6276 21950 0.0002 -
0.6290 22000 0.0002 -
0.6305 22050 0.0001 -
0.6319 22100 0.0002 -
0.6333 22150 0.0001 -
0.6347 22200 0.0001 -
0.6362 22250 0.0001 -
0.6376 22300 0.0002 -
0.6390 22350 0.0001 -
0.6405 22400 0.0003 -
0.6419 22450 0.0002 -
0.6433 22500 0.0002 -
0.6447 22550 0.0001 -
0.6462 22600 0.0002 -
0.6476 22650 0.0002 -
0.6490 22700 0.0002 -
0.6505 22750 0.0002 -
0.6519 22800 0.0001 -
0.6533 22850 0.0002 -
0.6548 22900 0.0002 -
0.6562 22950 0.0002 -
0.6576 23000 0.0002 -
0.6590 23050 0.0002 -
0.6605 23100 0.0002 -
0.6619 23150 0.0002 -
0.6633 23200 0.0002 -
0.6648 23250 0.0002 -
0.6662 23300 0.0002 -
0.6676 23350 0.0001 -
0.6690 23400 0.0002 -
0.6705 23450 0.0002 -
0.6719 23500 0.0001 -
0.6733 23550 0.0002 -
0.6748 23600 0.0001 -
0.6762 23650 0.0002 -
0.6776 23700 0.0002 -
0.6791 23750 0.0002 -
0.6805 23800 0.0001 -
0.6819 23850 0.0002 -
0.6833 23900 0.0003 -
0.6848 23950 0.0002 -
0.6862 24000 0.0002 -
0.6876 24050 0.0001 -
0.6891 24100 0.0002 -
0.6905 24150 0.0001 -
0.6919 24200 0.0003 -
0.6934 24250 0.0002 -
0.6948 24300 0.0001 -
0.6962 24350 0.0001 -
0.6976 24400 0.0001 -
0.6991 24450 0.0001 -
0.7005 24500 0.0001 -
0.7019 24550 0.0002 -
0.7034 24600 0.0001 -
0.7048 24650 0.0002 -
0.7062 24700 0.0001 -
0.7076 24750 0.0002 -
0.7091 24800 0.0002 -
0.7105 24850 0.0002 -
0.7119 24900 0.0002 -
0.7134 24950 0.0001 -
0.7148 25000 0.0002 -
0.7162 25050 0.0001 -
0.7177 25100 0.0002 -
0.7191 25150 0.0001 -
0.7205 25200 0.0001 -
0.7219 25250 0.0002 -
0.7234 25300 0.0002 -
0.7248 25350 0.0002 -
0.7262 25400 0.0001 -
0.7277 25450 0.0002 -
0.7291 25500 0.0002 -
0.7305 25550 0.0002 -
0.7320 25600 0.0001 -
0.7334 25650 0.0002 -
0.7348 25700 0.0002 -
0.7362 25750 0.0002 -
0.7377 25800 0.0002 -
0.7391 25850 0.0001 -
0.7405 25900 0.0002 -
0.7420 25950 0.0002 -
0.7434 26000 0.0001 -
0.7448 26050 0.0001 -
0.7462 26100 0.0001 -
0.7477 26150 0.0001 -
0.7491 26200 0.0001 -
0.7505 26250 0.0002 -
0.7520 26300 0.0001 -
0.7534 26350 0.0001 -
0.7548 26400 0.0001 -
0.7563 26450 0.0002 -
0.7577 26500 0.0001 -
0.7591 26550 0.0002 -
0.7605 26600 0.0003 -
0.7620 26650 0.0002 -
0.7634 26700 0.0002 -
0.7648 26750 0.0001 -
0.7663 26800 0.0001 -
0.7677 26850 0.0002 -
0.7691 26900 0.0002 -
0.7706 26950 0.0001 -
0.7720 27000 0.0001 -
0.7734 27050 0.0001 -
0.7748 27100 0.0001 -
0.7763 27150 0.0001 -
0.7777 27200 0.0002 -
0.7791 27250 0.0001 -
0.7806 27300 0.0001 -
0.7820 27350 0.0001 -
0.7834 27400 0.0002 -
0.7848 27450 0.0001 -
0.7863 27500 0.0001 -
0.7877 27550 0.0001 -
0.7891 27600 0.0001 -
0.7906 27650 0.0001 -
0.7920 27700 0.0001 -
0.7934 27750 0.0001 -
0.7949 27800 0.0001 -
0.7963 27850 0.0001 -
0.7977 27900 0.0001 -
0.7991 27950 0.0003 -
0.8006 28000 0.0001 -
0.8020 28050 0.0002 -
0.8034 28100 0.0001 -
0.8049 28150 0.0002 -
0.8063 28200 0.0 -
0.8077 28250 0.0001 -
0.8091 28300 0.0001 -
0.8106 28350 0.0001 -
0.8120 28400 0.0001 -
0.8134 28450 0.0002 -
0.8149 28500 0.0001 -
0.8163 28550 0.0001 -
0.8177 28600 0.0001 -
0.8192 28650 0.0001 -
0.8206 28700 0.0001 -
0.8220 28750 0.0002 -
0.8234 28800 0.0002 -
0.8249 28850 0.0002 -
0.8263 28900 0.0001 -
0.8277 28950 0.0002 -
0.8292 29000 0.0001 -
0.8306 29050 0.0002 -
0.8320 29100 0.0001 -
0.8335 29150 0.0001 -
0.8349 29200 0.0001 -
0.8363 29250 0.0001 -
0.8377 29300 0.0001 -
0.8392 29350 0.0001 -
0.8406 29400 0.0001 -
0.8420 29450 0.0002 -
0.8435 29500 0.0001 -
0.8449 29550 0.0001 -
0.8463 29600 0.0001 -
0.8477 29650 0.0001 -
0.8492 29700 0.0001 -
0.8506 29750 0.0002 -
0.8520 29800 0.0002 -
0.8535 29850 0.0001 -
0.8549 29900 0.0002 -
0.8563 29950 0.0002 -
0.8578 30000 0.0002 -
0.8592 30050 0.0001 -
0.8606 30100 0.0002 -
0.8620 30150 0.0002 -
0.8635 30200 0.0003 -
0.8649 30250 0.0001 -
0.8663 30300 0.0001 -
0.8678 30350 0.0001 -
0.8692 30400 0.0001 -
0.8706 30450 0.0002 -
0.8721 30500 0.0001 -
0.8735 30550 0.0001 -
0.8749 30600 0.0001 -
0.8763 30650 0.0002 -
0.8778 30700 0.0002 -
0.8792 30750 0.0001 -
0.8806 30800 0.0002 -
0.8821 30850 0.0002 -
0.8835 30900 0.0001 -
0.8849 30950 0.0002 -
0.8863 31000 0.0002 -
0.8878 31050 0.0002 -
0.8892 31100 0.0001 -
0.8906 31150 0.0001 -
0.8921 31200 0.0001 -
0.8935 31250 0.0001 -
0.8949 31300 0.0002 -
0.8964 31350 0.0002 -
0.8978 31400 0.0001 -
0.8992 31450 0.0001 -
0.9006 31500 0.0002 -
0.9021 31550 0.0002 -
0.9035 31600 0.0001 -
0.9049 31650 0.0002 -
0.9064 31700 0.0001 -
0.9078 31750 0.0001 -
0.9092 31800 0.0001 -
0.9107 31850 0.0002 -
0.9121 31900 0.0002 -
0.9135 31950 0.0001 -
0.9149 32000 0.0001 -
0.9164 32050 0.0001 -
0.9178 32100 0.0001 -
0.9192 32150 0.0001 -
0.9207 32200 0.0001 -
0.9221 32250 0.0001 -
0.9235 32300 0.0002 -
0.9249 32350 0.0001 -
0.9264 32400 0.0001 -
0.9278 32450 0.0002 -
0.9292 32500 0.0001 -
0.9307 32550 0.0001 -
0.9321 32600 0.0002 -
0.9335 32650 0.0001 -
0.9350 32700 0.0001 -
0.9364 32750 0.0001 -
0.9378 32800 0.0001 -
0.9392 32850 0.0001 -
0.9407 32900 0.0002 -
0.9421 32950 0.0002 -
0.9435 33000 0.0 -
0.9450 33050 0.0001 -
0.9464 33100 0.0001 -
0.9478 33150 0.0001 -
0.9492 33200 0.0001 -
0.9507 33250 0.0001 -
0.9521 33300 0.0001 -
0.9535 33350 0.0002 -
0.9550 33400 0.0001 -
0.9564 33450 0.0001 -
0.9578 33500 0.0002 -
0.9593 33550 0.0001 -
0.9607 33600 0.0001 -
0.9621 33650 0.0002 -
0.9635 33700 0.0002 -
0.9650 33750 0.0001 -
0.9664 33800 0.0001 -
0.9678 33850 0.0001 -
0.9693 33900 0.0001 -
0.9707 33950 0.0 -
0.9721 34000 0.0002 -
0.9736 34050 0.0001 -
0.9750 34100 0.0001 -
0.9764 34150 0.0001 -
0.9778 34200 0.0001 -
0.9793 34250 0.0002 -
0.9807 34300 0.0002 -
0.9821 34350 0.0001 -
0.9836 34400 0.0001 -
0.9850 34450 0.0001 -
0.9864 34500 0.0001 -
0.9878 34550 0.0001 -
0.9893 34600 0.0001 -
0.9907 34650 0.0001 -
0.9921 34700 0.0001 -
0.9936 34750 0.0001 -
0.9950 34800 0.0001 -
0.9964 34850 0.0001 -
0.9979 34900 0.0002 -
0.9993 34950 0.0002 -
1.0 34975 - 0.0221
  • The bold row denotes the saved checkpoint.

Framework Versions

  • Python: 3.11.9
  • SetFit: 1.0.3
  • Sentence Transformers: 2.7.0
  • Transformers: 4.42.4
  • PyTorch: 2.4.0+cu121
  • Datasets: 2.21.0
  • Tokenizers: 0.19.1

Citation

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}
}