nazhan's picture
Add SetFit model
1951715 verified
metadata
base_model: BAAI/bge-large-en-v1.5
datasets:
  - nazhan/brahmaputra-full-datasets-iter-8-2nd-fixed
library_name: setfit
metrics:
  - accuracy
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      Can you filter by the 'Fashion' category and show me the products
      available?
  - text: Get forecast by service type.
  - text: How many orders were placed in each quarter?
  - text: What are the details of customers with no phone number listed?
  - text: I don't want to filter the database currently.
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-8-2nd-fixed
          type: nazhan/brahmaputra-full-datasets-iter-8-2nd-fixed
          split: test
        metrics:
          - type: accuracy
            value: 0.9739130434782609
            name: Accuracy

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

This is a SetFit model trained on the nazhan/brahmaputra-full-datasets-iter-8-2nd-fixed dataset that can be used for Text Classification. This SetFit model uses BAAI/bge-large-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
Aggregation
  • 'How many unique customers made purchases last year?'
  • 'Determine the minimum order amount for each customer.'
  • 'Get me sum of total_revenue.'
Tablejoin
  • 'Show me a join of cash flow and variance.'
  • 'Join data_asset_001_forecast with data_asset_kpi_bs tables.'
  • 'Join data_asset_kpi_ma_product with data_asset_001_variance.'
Lookup_1
  • 'Show me asset impairment by year.'
  • 'Get me data_asset_001_pcc group by category.'
  • 'Show me data_asset_001_variance group by category.'
Viewtables
  • 'What are the table names within the starhub_data_asset database that enable data analysis of customer feedback?'
  • 'How can I access the table directory for starhub_data_asset database to view all the available tables?'
  • 'Please show me the tables that contain data related to customer transactions present in the starhub_data_asset database.'
Generalreply
  • "Oh my favorite food? That's a tough one. I love so many different kinds of food, but if I had to choose one it would probably be pizza. What about you? What's your favorite food?"
  • "Hmm, let me think... I'm actually pretty good at playing guitar! I've been playing for a few years now and it's always been one of my favorite hobbies. How about you, do you play any instruments or have any interesting hobbies?"
  • 'What is your favorite color?'
Lookup
  • "Get me all the customers who haven't placed any orders."
  • 'Get me the list of customers who have a phone number listed.'
  • 'Can you filter by customers who registered without an email address?'
Rejection
  • "I'm not keen on producing any new data sets."
  • "Please don't generate any new data."
  • "I don't want to create any new data outputs."

Evaluation

Metrics

Label Accuracy
all 0.9739

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-large-en-v1.5-brahmaputra-iter-8-2nd-1-epoch")
# Run inference
preds = model("Get forecast by service type.")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 2 8.8252 62
Label Training Sample Count
Tablejoin 129
Rejection 74
Aggregation 210
Lookup 60
Generalreply 59
Viewtables 75
Lookup_1 217

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 0.1706 -
0.0014 50 0.1976 -
0.0029 100 0.2045 -
0.0043 150 0.1846 -
0.0058 200 0.1608 -
0.0072 250 0.105 -
0.0087 300 0.1618 -
0.0101 350 0.1282 -
0.0116 400 0.0382 -
0.0130 450 0.0328 -
0.0145 500 0.0483 -
0.0159 550 0.0245 -
0.0174 600 0.0093 -
0.0188 650 0.0084 -
0.0203 700 0.0042 -
0.0217 750 0.0044 -
0.0231 800 0.0035 -
0.0246 850 0.0065 -
0.0260 900 0.0036 -
0.0275 950 0.0039 -
0.0289 1000 0.0037 -
0.0304 1050 0.005 -
0.0318 1100 0.0024 -
0.0333 1150 0.0023 -
0.0347 1200 0.0023 -
0.0362 1250 0.0019 -
0.0376 1300 0.0015 -
0.0391 1350 0.0023 -
0.0405 1400 0.0011 -
0.0420 1450 0.0017 -
0.0434 1500 0.0015 -
0.0448 1550 0.0014 -
0.0463 1600 0.0014 -
0.0477 1650 0.0013 -
0.0492 1700 0.0013 -
0.0506 1750 0.001 -
0.0521 1800 0.0013 -
0.0535 1850 0.0013 -
0.0550 1900 0.0011 -
0.0564 1950 0.0012 -
0.0579 2000 0.001 -
0.0593 2050 0.0012 -
0.0608 2100 0.0008 -
0.0622 2150 0.0008 -
0.0637 2200 0.001 -
0.0651 2250 0.0007 -
0.0665 2300 0.0006 -
0.0680 2350 0.0007 -
0.0694 2400 0.0008 -
0.0709 2450 0.0008 -
0.0723 2500 0.0006 -
0.0738 2550 0.0006 -
0.0752 2600 0.0007 -
0.0767 2650 0.0008 -
0.0781 2700 0.0005 -
0.0796 2750 0.0008 -
0.0810 2800 0.0006 -
0.0825 2850 0.0007 -
0.0839 2900 0.0007 -
0.0854 2950 0.0005 -
0.0868 3000 0.0007 -
0.0882 3050 0.0005 -
0.0897 3100 0.0005 -
0.0911 3150 0.0007 -
0.0926 3200 0.0005 -
0.0940 3250 0.0005 -
0.0955 3300 0.0007 -
0.0969 3350 0.0004 -
0.0984 3400 0.0005 -
0.0998 3450 0.0004 -
0.1013 3500 0.0007 -
0.1027 3550 0.0004 -
0.1042 3600 0.0004 -
0.1056 3650 0.0006 -
0.1071 3700 0.0005 -
0.1085 3750 0.0004 -
0.1100 3800 0.0005 -
0.1114 3850 0.0004 -
0.1128 3900 0.0004 -
0.1143 3950 0.0003 -
0.1157 4000 0.0004 -
0.1172 4050 0.0004 -
0.1186 4100 0.0004 -
0.1201 4150 0.0004 -
0.1215 4200 0.0004 -
0.1230 4250 0.0004 -
0.1244 4300 0.0003 -
0.1259 4350 0.0004 -
0.1273 4400 0.0003 -
0.1288 4450 0.0003 -
0.1302 4500 0.0003 -
0.1317 4550 0.0002 -
0.1331 4600 0.0003 -
0.1345 4650 0.0004 -
0.1360 4700 0.0003 -
0.1374 4750 0.0003 -
0.1389 4800 0.0002 -
0.1403 4850 0.0003 -
0.1418 4900 0.0003 -
0.1432 4950 0.0003 -
0.1447 5000 0.0002 -
0.1461 5050 0.0002 -
0.1476 5100 0.0003 -
0.1490 5150 0.0002 -
0.1505 5200 0.0004 -
0.1519 5250 0.0003 -
0.1534 5300 0.0003 -
0.1548 5350 0.0002 -
0.1562 5400 0.0003 -
0.1577 5450 0.0002 -
0.1591 5500 0.0002 -
0.1606 5550 0.0002 -
0.1620 5600 0.0002 -
0.1635 5650 0.0002 -
0.1649 5700 0.0003 -
0.1664 5750 0.0002 -
0.1678 5800 0.0003 -
0.1693 5850 0.0003 -
0.1707 5900 0.0002 -
0.1722 5950 0.0007 -
0.1736 6000 0.0003 -
0.1751 6050 0.0002 -
0.1765 6100 0.0002 -
0.1779 6150 0.0003 -
0.1794 6200 0.0002 -
0.1808 6250 0.0002 -
0.1823 6300 0.0002 -
0.1837 6350 0.0003 -
0.1852 6400 0.0002 -
0.1866 6450 0.0003 -
0.1881 6500 0.0002 -
0.1895 6550 0.0003 -
0.1910 6600 0.0002 -
0.1924 6650 0.0003 -
0.1939 6700 0.0002 -
0.1953 6750 0.0002 -
0.1968 6800 0.0002 -
0.1982 6850 0.0003 -
0.1996 6900 0.0003 -
0.2011 6950 0.0002 -
0.2025 7000 0.0002 -
0.2040 7050 0.0001 -
0.2054 7100 0.0002 -
0.2069 7150 0.0002 -
0.2083 7200 0.0002 -
0.2098 7250 0.0002 -
0.2112 7300 0.0002 -
0.2127 7350 0.0002 -
0.2141 7400 0.0002 -
0.2156 7450 0.0004 -
0.2170 7500 0.0002 -
0.2185 7550 0.0002 -
0.2199 7600 0.0003 -
0.2213 7650 0.0002 -
0.2228 7700 0.0003 -
0.2242 7750 0.0002 -
0.2257 7800 0.0001 -
0.2271 7850 0.0001 -
0.2286 7900 0.0002 -
0.2300 7950 0.0002 -
0.2315 8000 0.0001 -
0.2329 8050 0.0002 -
0.2344 8100 0.0002 -
0.2358 8150 0.0002 -
0.2373 8200 0.0002 -
0.2387 8250 0.0002 -
0.2402 8300 0.0001 -
0.2416 8350 0.0005 -
0.2430 8400 0.002 -
0.2445 8450 0.0037 -
0.2459 8500 0.0516 -
0.2474 8550 0.0028 -
0.2488 8600 0.0013 -
0.2503 8650 0.0017 -
0.2517 8700 0.0012 -
0.2532 8750 0.0513 -
0.2546 8800 0.001 -
0.2561 8850 0.035 -
0.2575 8900 0.0005 -
0.2590 8950 0.0076 -
0.2604 9000 0.0113 -
0.2619 9050 0.0006 -
0.2633 9100 0.0006 -
0.2647 9150 0.0018 -
0.2662 9200 0.0025 -
0.2676 9250 0.0011 -
0.2691 9300 0.001 -
0.2705 9350 0.0011 -
0.2720 9400 0.0004 -
0.2734 9450 0.0012 -
0.2749 9500 0.0011 -
0.2763 9550 0.0009 -
0.2778 9600 0.0003 -
0.2792 9650 0.0005 -
0.2807 9700 0.0006 -
0.2821 9750 0.0004 -
0.2836 9800 0.0004 -
0.2850 9850 0.0009 -
0.2865 9900 0.0014 -
0.2879 9950 0.0007 -
0.2893 10000 0.0014 -
0.2908 10050 0.0007 -
0.2922 10100 0.0003 -
0.2937 10150 0.0015 -
0.2951 10200 0.0003 -
0.2966 10250 0.0006 -
0.2980 10300 0.0003 -
0.2995 10350 0.0003 -
0.3009 10400 0.0004 -
0.3024 10450 0.0003 -
0.3038 10500 0.0008 -
0.3053 10550 0.0002 -
0.3067 10600 0.0005 -
0.3082 10650 0.0004 -
0.3096 10700 0.0006 -
0.3110 10750 0.0002 -
0.3125 10800 0.0008 -
0.3139 10850 0.0005 -
0.3154 10900 0.0004 -
0.3168 10950 0.0002 -
0.3183 11000 0.0002 -
0.3197 11050 0.0002 -
0.3212 11100 0.0006 -
0.3226 11150 0.0003 -
0.3241 11200 0.0002 -
0.3255 11250 0.0002 -
0.3270 11300 0.0003 -
0.3284 11350 0.0001 -
0.3299 11400 0.0002 -
0.3313 11450 0.0004 -
0.3327 11500 0.0006 -
0.3342 11550 0.0003 -
0.3356 11600 0.0003 -
0.3371 11650 0.0002 -
0.3385 11700 0.0002 -
0.3400 11750 0.0005 -
0.3414 11800 0.0003 -
0.3429 11850 0.0004 -
0.3443 11900 0.0004 -
0.3458 11950 0.0002 -
0.3472 12000 0.0004 -
0.3487 12050 0.0002 -
0.3501 12100 0.0002 -
0.3516 12150 0.0002 -
0.3530 12200 0.0002 -
0.3544 12250 0.0002 -
0.3559 12300 0.0002 -
0.3573 12350 0.0003 -
0.3588 12400 0.0002 -
0.3602 12450 0.0002 -
0.3617 12500 0.0002 -
0.3631 12550 0.0005 -
0.3646 12600 0.0003 -
0.3660 12650 0.0003 -
0.3675 12700 0.0002 -
0.3689 12750 0.0004 -
0.3704 12800 0.0003 -
0.3718 12850 0.0003 -
0.3733 12900 0.0001 -
0.3747 12950 0.0002 -
0.3761 13000 0.0001 -
0.3776 13050 0.0002 -
0.3790 13100 0.0001 -
0.3805 13150 0.0001 -
0.3819 13200 0.0002 -
0.3834 13250 0.0003 -
0.3848 13300 0.0001 -
0.3863 13350 0.0003 -
0.3877 13400 0.0002 -
0.3892 13450 0.0001 -
0.3906 13500 0.0003 -
0.3921 13550 0.0002 -
0.3935 13600 0.0002 -
0.3950 13650 0.0001 -
0.3964 13700 0.0004 -
0.3978 13750 0.0002 -
0.3993 13800 0.0002 -
0.4007 13850 0.0003 -
0.4022 13900 0.0002 -
0.4036 13950 0.0003 -
0.4051 14000 0.0003 -
0.4065 14050 0.0003 -
0.4080 14100 0.0002 -
0.4094 14150 0.0002 -
0.4109 14200 0.0002 -
0.4123 14250 0.0002 -
0.4138 14300 0.0002 -
0.4152 14350 0.0002 -
0.4167 14400 0.0002 -
0.4181 14450 0.0003 -
0.4195 14500 0.0002 -
0.4210 14550 0.0002 -
0.4224 14600 0.0001 -
0.4239 14650 0.0003 -
0.4253 14700 0.0002 -
0.4268 14750 0.0002 -
0.4282 14800 0.0002 -
0.4297 14850 0.0002 -
0.4311 14900 0.0002 -
0.4326 14950 0.0003 -
0.4340 15000 0.0002 -
0.4355 15050 0.0002 -
0.4369 15100 0.0002 -
0.4384 15150 0.0002 -
0.4398 15200 0.0002 -
0.4412 15250 0.0001 -
0.4427 15300 0.0002 -
0.4441 15350 0.0003 -
0.4456 15400 0.0003 -
0.4470 15450 0.0003 -
0.4485 15500 0.0002 -
0.4499 15550 0.0001 -
0.4514 15600 0.0001 -
0.4528 15650 0.0001 -
0.4543 15700 0.0001 -
0.4557 15750 0.0002 -
0.4572 15800 0.0001 -
0.4586 15850 0.0002 -
0.4601 15900 0.0003 -
0.4615 15950 0.0002 -
0.4629 16000 0.0002 -
0.4644 16050 0.0002 -
0.4658 16100 0.0001 -
0.4673 16150 0.0001 -
0.4687 16200 0.0001 -
0.4702 16250 0.0002 -
0.4716 16300 0.0003 -
0.4731 16350 0.0001 -
0.4745 16400 0.0001 -
0.4760 16450 0.0001 -
0.4774 16500 0.0002 -
0.4789 16550 0.0006 -
0.4803 16600 0.0002 -
0.4818 16650 0.0001 -
0.4832 16700 0.0002 -
0.4847 16750 0.0001 -
0.4861 16800 0.0003 -
0.4875 16850 0.0001 -
0.4890 16900 0.0002 -
0.4904 16950 0.0002 -
0.4919 17000 0.0001 -
0.4933 17050 0.0002 -
0.4948 17100 0.0001 -
0.4962 17150 0.0002 -
0.4977 17200 0.0002 -
0.4991 17250 0.0001 -
0.5006 17300 0.0002 -
0.5020 17350 0.0002 -
0.5035 17400 0.0001 -
0.5049 17450 0.0002 -
0.5064 17500 0.0003 -
0.5078 17550 0.0001 -
0.5092 17600 0.0002 -
0.5107 17650 0.0001 -
0.5121 17700 0.0002 -
0.5136 17750 0.0002 -
0.5150 17800 0.0003 -
0.5165 17850 0.0002 -
0.5179 17900 0.0002 -
0.5194 17950 0.0001 -
0.5208 18000 0.0002 -
0.5223 18050 0.0001 -
0.5237 18100 0.0001 -
0.5252 18150 0.0001 -
0.5266 18200 0.0003 -
0.5281 18250 0.0001 -
0.5295 18300 0.0001 -
0.5309 18350 0.0001 -
0.5324 18400 0.0001 -
0.5338 18450 0.0002 -
0.5353 18500 0.0008 -
0.5367 18550 0.0002 -
0.5382 18600 0.0001 -
0.5396 18650 0.0002 -
0.5411 18700 0.0002 -
0.5425 18750 0.0001 -
0.5440 18800 0.0001 -
0.5454 18850 0.0001 -
0.5469 18900 0.0002 -
0.5483 18950 0.0001 -
0.5498 19000 0.0001 -
0.5512 19050 0.0001 -
0.5526 19100 0.0002 -
0.5541 19150 0.0001 -
0.5555 19200 0.0001 -
0.5570 19250 0.0002 -
0.5584 19300 0.0001 -
0.5599 19350 0.0002 -
0.5613 19400 0.0001 -
0.5628 19450 0.0002 -
0.5642 19500 0.0001 -
0.5657 19550 0.0002 -
0.5671 19600 0.0002 -
0.5686 19650 0.0002 -
0.5700 19700 0.0001 -
0.5715 19750 0.0001 -
0.5729 19800 0.0003 -
0.5743 19850 0.0001 -
0.5758 19900 0.0001 -
0.5772 19950 0.0001 -
0.5787 20000 0.0001 -
0.5801 20050 0.0001 -
0.5816 20100 0.0001 -
0.5830 20150 0.0001 -
0.5845 20200 0.0001 -
0.5859 20250 0.0001 -
0.5874 20300 0.0002 -
0.5888 20350 0.0002 -
0.5903 20400 0.0001 -
0.5917 20450 0.0002 -
0.5932 20500 0.0001 -
0.5946 20550 0.0001 -
0.5960 20600 0.0001 -
0.5975 20650 0.0002 -
0.5989 20700 0.0002 -
0.6004 20750 0.0001 -
0.6018 20800 0.0001 -
0.6033 20850 0.0002 -
0.6047 20900 0.0001 -
0.6062 20950 0.0002 -
0.6076 21000 0.0001 -
0.6091 21050 0.0001 -
0.6105 21100 0.0001 -
0.6120 21150 0.0002 -
0.6134 21200 0.0001 -
0.6149 21250 0.0001 -
0.6163 21300 0.0001 -
0.6177 21350 0.0001 -
0.6192 21400 0.0002 -
0.6206 21450 0.0001 -
0.6221 21500 0.0002 -
0.6235 21550 0.0003 -
0.6250 21600 0.0001 -
0.6264 21650 0.0001 -
0.6279 21700 0.0001 -
0.6293 21750 0.0001 -
0.6308 21800 0.0002 -
0.6322 21850 0.0001 -
0.6337 21900 0.0001 -
0.6351 21950 0.0001 -
0.6366 22000 0.0002 -
0.6380 22050 0.0001 -
0.6394 22100 0.0001 -
0.6409 22150 0.0002 -
0.6423 22200 0.0002 -
0.6438 22250 0.0003 -
0.6452 22300 0.0001 -
0.6467 22350 0.0001 -
0.6481 22400 0.0001 -
0.6496 22450 0.0002 -
0.6510 22500 0.0001 -
0.6525 22550 0.0001 -
0.6539 22600 0.0001 -
0.6554 22650 0.0001 -
0.6568 22700 0.0002 -
0.6583 22750 0.0001 -
0.6597 22800 0.0001 -
0.6611 22850 0.0001 -
0.6626 22900 0.0001 -
0.6640 22950 0.0001 -
0.6655 23000 0.0001 -
0.6669 23050 0.0002 -
0.6684 23100 0.0001 -
0.6698 23150 0.0001 -
0.6713 23200 0.0001 -
0.6727 23250 0.0001 -
0.6742 23300 0.0002 -
0.6756 23350 0.0002 -
0.6771 23400 0.0001 -
0.6785 23450 0.0001 -
0.6800 23500 0.0001 -
0.6814 23550 0.0001 -
0.6829 23600 0.0002 -
0.6843 23650 0.0001 -
0.6857 23700 0.0001 -
0.6872 23750 0.0001 -
0.6886 23800 0.0001 -
0.6901 23850 0.0002 -
0.6915 23900 0.0001 -
0.6930 23950 0.0001 -
0.6944 24000 0.0002 -
0.6959 24050 0.0001 -
0.6973 24100 0.0001 -
0.6988 24150 0.0001 -
0.7002 24200 0.0001 -
0.7017 24250 0.0001 -
0.7031 24300 0.0001 -
0.7046 24350 0.0001 -
0.7060 24400 0.0001 -
0.7074 24450 0.0002 -
0.7089 24500 0.0001 -
0.7103 24550 0.0002 -
0.7118 24600 0.0001 -
0.7132 24650 0.0001 -
0.7147 24700 0.0001 -
0.7161 24750 0.0001 -
0.7176 24800 0.0001 -
0.7190 24850 0.0001 -
0.7205 24900 0.0001 -
0.7219 24950 0.0001 -
0.7234 25000 0.0001 -
0.7248 25050 0.0002 -
0.7263 25100 0.0001 -
0.7277 25150 0.0001 -
0.7291 25200 0.0001 -
0.7306 25250 0.0001 -
0.7320 25300 0.0001 -
0.7335 25350 0.0001 -
0.7349 25400 0.0 -
0.7364 25450 0.0001 -
0.7378 25500 0.0001 -
0.7393 25550 0.0001 -
0.7407 25600 0.0001 -
0.7422 25650 0.0001 -
0.7436 25700 0.0001 -
0.7451 25750 0.0001 -
0.7465 25800 0.0 -
0.7480 25850 0.0001 -
0.7494 25900 0.0001 -
0.7508 25950 0.0001 -
0.7523 26000 0.0001 -
0.7537 26050 0.0001 -
0.7552 26100 0.0001 -
0.7566 26150 0.0001 -
0.7581 26200 0.0001 -
0.7595 26250 0.0001 -
0.7610 26300 0.0001 -
0.7624 26350 0.0001 -
0.7639 26400 0.0002 -
0.7653 26450 0.0001 -
0.7668 26500 0.0001 -
0.7682 26550 0.0001 -
0.7697 26600 0.0001 -
0.7711 26650 0.0002 -
0.7725 26700 0.0001 -
0.7740 26750 0.0001 -
0.7754 26800 0.0001 -
0.7769 26850 0.0001 -
0.7783 26900 0.0001 -
0.7798 26950 0.0001 -
0.7812 27000 0.0001 -
0.7827 27050 0.0001 -
0.7841 27100 0.0001 -
0.7856 27150 0.0001 -
0.7870 27200 0.0001 -
0.7885 27250 0.0001 -
0.7899 27300 0.0001 -
0.7914 27350 0.0001 -
0.7928 27400 0.0001 -
0.7942 27450 0.0001 -
0.7957 27500 0.0001 -
0.7971 27550 0.0001 -
0.7986 27600 0.0001 -
0.8000 27650 0.0001 -
0.8015 27700 0.0001 -
0.8029 27750 0.0001 -
0.8044 27800 0.0 -
0.8058 27850 0.0001 -
0.8073 27900 0.0001 -
0.8087 27950 0.0001 -
0.8102 28000 0.0001 -
0.8116 28050 0.0 -
0.8131 28100 0.0 -
0.8145 28150 0.0001 -
0.8159 28200 0.0001 -
0.8174 28250 0.0001 -
0.8188 28300 0.0001 -
0.8203 28350 0.0001 -
0.8217 28400 0.0001 -
0.8232 28450 0.0001 -
0.8246 28500 0.0001 -
0.8261 28550 0.0001 -
0.8275 28600 0.0001 -
0.8290 28650 0.0001 -
0.8304 28700 0.0001 -
0.8319 28750 0.0001 -
0.8333 28800 0.0001 -
0.8348 28850 0.0002 -
0.8362 28900 0.0001 -
0.8376 28950 0.0001 -
0.8391 29000 0.0001 -
0.8405 29050 0.0001 -
0.8420 29100 0.0001 -
0.8434 29150 0.0001 -
0.8449 29200 0.0 -
0.8463 29250 0.0001 -
0.8478 29300 0.0001 -
0.8492 29350 0.0001 -
0.8507 29400 0.0001 -
0.8521 29450 0.0001 -
0.8536 29500 0.0001 -
0.8550 29550 0.0001 -
0.8565 29600 0.0002 -
0.8579 29650 0.0 -
0.8594 29700 0.0001 -
0.8608 29750 0.0001 -
0.8622 29800 0.0001 -
0.8637 29850 0.0001 -
0.8651 29900 0.0 -
0.8666 29950 0.0001 -
0.8680 30000 0.0001 -
0.8695 30050 0.0001 -
0.8709 30100 0.0 -
0.8724 30150 0.0 -
0.8738 30200 0.0001 -
0.8753 30250 0.0001 -
0.8767 30300 0.0001 -
0.8782 30350 0.0001 -
0.8796 30400 0.0001 -
0.8811 30450 0.0001 -
0.8825 30500 0.0001 -
0.8839 30550 0.0001 -
0.8854 30600 0.0 -
0.8868 30650 0.0001 -
0.8883 30700 0.0001 -
0.8897 30750 0.0001 -
0.8912 30800 0.0001 -
0.8926 30850 0.0 -
0.8941 30900 0.0 -
0.8955 30950 0.0001 -
0.8970 31000 0.0001 -
0.8984 31050 0.0001 -
0.8999 31100 0.0001 -
0.9013 31150 0.0 -
0.9028 31200 0.0001 -
0.9042 31250 0.0001 -
0.9056 31300 0.0001 -
0.9071 31350 0.0001 -
0.9085 31400 0.0001 -
0.9100 31450 0.0002 -
0.9114 31500 0.0001 -
0.9129 31550 0.0001 -
0.9143 31600 0.0001 -
0.9158 31650 0.0001 -
0.9172 31700 0.0001 -
0.9187 31750 0.0001 -
0.9201 31800 0.0001 -
0.9216 31850 0.0001 -
0.9230 31900 0.0001 -
0.9245 31950 0.0001 -
0.9259 32000 0.0001 -
0.9273 32050 0.0 -
0.9288 32100 0.0002 -
0.9302 32150 0.0001 -
0.9317 32200 0.0001 -
0.9331 32250 0.0001 -
0.9346 32300 0.0002 -
0.9360 32350 0.0 -
0.9375 32400 0.0001 -
0.9389 32450 0.0001 -
0.9404 32500 0.0 -
0.9418 32550 0.0001 -
0.9433 32600 0.0001 -
0.9447 32650 0.0001 -
0.9462 32700 0.0001 -
0.9476 32750 0.0001 -
0.9490 32800 0.0001 -
0.9505 32850 0.0001 -
0.9519 32900 0.0 -
0.9534 32950 0.0001 -
0.9548 33000 0.0001 -
0.9563 33050 0.0001 -
0.9577 33100 0.0001 -
0.9592 33150 0.0001 -
0.9606 33200 0.0001 -
0.9621 33250 0.0001 -
0.9635 33300 0.0001 -
0.9650 33350 0.0 -
0.9664 33400 0.0001 -
0.9679 33450 0.0001 -
0.9693 33500 0.0 -
0.9707 33550 0.0001 -
0.9722 33600 0.0 -
0.9736 33650 0.0001 -
0.9751 33700 0.0001 -
0.9765 33750 0.0001 -
0.9780 33800 0.0 -
0.9794 33850 0.0001 -
0.9809 33900 0.0001 -
0.9823 33950 0.0001 -
0.9838 34000 0.0001 -
0.9852 34050 0.0 -
0.9867 34100 0.0001 -
0.9881 34150 0.0 -
0.9896 34200 0.0001 -
0.9910 34250 0.0 -
0.9924 34300 0.0001 -
0.9939 34350 0.0 -
0.9953 34400 0.0001 -
0.9968 34450 0.0 -
0.9982 34500 0.0 -
0.9997 34550 0.0001 -
1.0 34561 - 0.0036
  • 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

@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}
}