725_model_v3 / README.md
jamiehudson's picture
Push model using huggingface_hub.
a3c2c1a verified
metadata
library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
widget:
  - text: >-
      brand's product, powered by product, is making waves by potentially
      surpassing brand's product in ai performance. lets not forget massive
      developments in ai from brand, brand, brand and 5 new tools here's what
      you need to know:
  - text: >-
      well... brand launches product tomorrow so it's going to be much more
      exciting than 2x! product ca: 0x09e5e172df245529b22686b77e959d3f2937feb0
  - text: >-
      brand's product is product's newest and greatest competitor yet: here's
      how you can use it within product dlvr.it/szs9nh
  - text: >-
      bad actors exploit product to write malicious codes product, ever since
      its launch in november last year, has been making lots of noise. with
      creators experimenting with it and getting varied results, the product
      became an acceptable product tool that couldlnkd.in/drbvpbdt
  - text: >-
      testing out product. i find it incredibly useful. one way to monetize it
      is simply to put paid links related to the search
pipeline_tag: text-classification
inference: true
base_model: BAAI/bge-base-en-v1.5
model-index:
  - name: SetFit with BAAI/bge-base-en-v1.5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.86
            name: Accuracy
          - type: f1
            value:
              - 0.2857142857142857
              - 0.5945945945945945
              - 0.9195402298850575
            name: F1
          - type: precision
            value:
              - 1
              - 0.9166666666666666
              - 0.8547008547008547
            name: Precision
          - type: recall
            value:
              - 0.16666666666666666
              - 0.44
              - 0.9950248756218906
            name: Recall

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

This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-base-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
neither
  • 'ai becomes so much easier to spot when you realize it can replicate, but never understand. its why product usually gives its answers in lists. its a standardized format meant to hide its ignorance to prose.'
  • "hakeem jeffries' tweets are getting so productian it's not even funny and boring any more. he may have brand cranking these out."
  • 'have you tried this with product? i did this with music and got amazing results'
peak
  • 'thats rad man. i have adhd and dyslexia and some other cognitive disabilities and honestly brand is a lifesaver.'
  • "product is like having a coding partner that understands my style, enhancing my productivity significantly. i've even changed the way i code. my code and process is more modular so it's easier to use the output from product in my code base!"
  • 'product is an incredible tool for explaining concepts in i prompted it to describe how k-means clustering could be applied to an engagement survey. it generated sample data, explained the concept and how the insights could be applied.'
pit
  • 'many similar posts popping up on my timeline frustrated with chatproduct not performing to previous levels defeats the purpose of having an ai assitant available 24/7 if it never wants to do any of the tasks you ask of it'
  • "the stuff brand gives is entirely too scripted and impractical, which is what i'm trying to avoid:/"
  • 'so disappointed theyve programmed product to think starvation mode is real'

Evaluation

Metrics

Label Accuracy F1 Precision Recall
all 0.86 [0.2857142857142857, 0.5945945945945945, 0.9195402298850575] [1.0, 0.9166666666666666, 0.8547008547008547] [0.16666666666666666, 0.44, 0.9950248756218906]

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("jamiehudson/725_model_v3")
# Run inference
preds = model("brand's product is product's newest and greatest competitor yet: here's how you can use it within product dlvr.it/szs9nh")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 3 27.8534 91
Label Training Sample Count
pit 26
peak 51
neither 1137

Training Hyperparameters

  • batch_size: (32, 32)
  • 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: False

Training Results

Epoch Step Training Loss Validation Loss
0.0012 1 0.2612 -
0.0621 50 0.2009 -
0.1242 100 0.0339 -
0.1863 150 0.0062 -
0.2484 200 0.0039 -
0.3106 250 0.0017 -
0.3727 300 0.003 -
0.4348 350 0.0015 -
0.4969 400 0.002 -
0.5590 450 0.0022 -
0.6211 500 0.0013 -
0.6832 550 0.0013 -
0.7453 600 0.0014 -
0.8075 650 0.0014 -
0.8696 700 0.0012 -
0.9317 750 0.0014 -
0.9938 800 0.0016 -
0.0000 1 0.0897 -
0.0012 50 0.1107 -
0.0025 100 0.065 -
0.0037 150 0.1892 -
0.0049 200 0.0774 -
0.0062 250 0.0391 -
0.0074 300 0.117 -
0.0086 350 0.0954 -
0.0099 400 0.0292 -
0.0111 450 0.0327 -
0.0123 500 0.0041 -
0.0136 550 0.0018 -
0.0148 600 0.03 -
0.0160 650 0.0015 -
0.0173 700 0.0036 -
0.0185 750 0.0182 -
0.0197 800 0.0017 -
0.0210 850 0.0012 -
0.0222 900 0.0014 -
0.0234 950 0.0011 -
0.0247 1000 0.0014 -
0.0259 1050 0.0301 -
0.0271 1100 0.001 -
0.0284 1150 0.0011 -
0.0296 1200 0.0009 -
0.0308 1250 0.0011 -
0.0321 1300 0.0012 -
0.0333 1350 0.001 -
0.0345 1400 0.0008 -
0.0358 1450 0.005 -
0.0370 1500 0.0008 -
0.0382 1550 0.0044 -
0.0395 1600 0.0008 -
0.0407 1650 0.0007 -
0.0419 1700 0.0014 -
0.0432 1750 0.0006 -
0.0444 1800 0.001 -
0.0456 1850 0.0007 -
0.0469 1900 0.0006 -
0.0481 1950 0.0006 -
0.0493 2000 0.0005 -
0.0506 2050 0.0006 -
0.0518 2100 0.0041 -
0.0530 2150 0.0006 -
0.0543 2200 0.0006 -
0.0555 2250 0.0007 -
0.0567 2300 0.0006 -
0.0580 2350 0.0005 -
0.0592 2400 0.0007 -
0.0604 2450 0.0005 -
0.0617 2500 0.0004 -
0.0629 2550 0.0005 -
0.0641 2600 0.0004 -
0.0654 2650 0.0007 -
0.0666 2700 0.0004 -
0.0678 2750 0.0005 -
0.0691 2800 0.0004 -
0.0703 2850 0.0004 -
0.0715 2900 0.0004 -
0.0728 2950 0.0005 -
0.0740 3000 0.0004 -
0.0752 3050 0.0004 -
0.0765 3100 0.0003 -
0.0777 3150 0.0003 -
0.0789 3200 0.0003 -
0.0802 3250 0.0003 -
0.0814 3300 0.0004 -
0.0826 3350 0.0003 -
0.0839 3400 0.0003 -
0.0851 3450 0.0007 -
0.0863 3500 0.0003 -
0.0876 3550 0.0003 -
0.0888 3600 0.0004 -
0.0900 3650 0.0003 -
0.0913 3700 0.0003 -
0.0925 3750 0.0004 -
0.0937 3800 0.0004 -
0.0950 3850 0.0232 -
0.0962 3900 0.0004 -
0.0974 3950 0.0165 -
0.0987 4000 0.0003 -
0.0999 4050 0.0229 -
0.1011 4100 0.0004 -
0.1024 4150 0.0003 -
0.1036 4200 0.0004 -
0.1048 4250 0.0002 -
0.1061 4300 0.0002 -
0.1073 4350 0.0002 -
0.1085 4400 0.0003 -
0.1098 4450 0.0002 -
0.1110 4500 0.0002 -
0.1122 4550 0.0003 -
0.1135 4600 0.0002 -
0.1147 4650 0.0002 -
0.1159 4700 0.0002 -
0.1172 4750 0.0002 -
0.1184 4800 0.0002 -
0.1196 4850 0.0002 -
0.1209 4900 0.0002 -
0.1221 4950 0.0002 -
0.1233 5000 0.0002 -
0.1246 5050 0.0002 -
0.1258 5100 0.0002 -
0.1270 5150 0.0003 -
0.1283 5200 0.0001 -
0.1295 5250 0.0002 -
0.1307 5300 0.0002 -
0.1320 5350 0.0002 -
0.1332 5400 0.0001 -
0.1344 5450 0.0002 -
0.1357 5500 0.0002 -
0.1369 5550 0.0002 -
0.1381 5600 0.0001 -
0.1394 5650 0.0001 -
0.1406 5700 0.0001 -
0.1418 5750 0.0001 -
0.1431 5800 0.0001 -
0.1443 5850 0.0001 -
0.1455 5900 0.0001 -
0.1468 5950 0.0002 -
0.1480 6000 0.0001 -
0.1492 6050 0.0002 -
0.1505 6100 0.0002 -
0.1517 6150 0.0004 -
0.1529 6200 0.0003 -
0.1542 6250 0.0001 -
0.1554 6300 0.0003 -
0.1566 6350 0.0001 -
0.1579 6400 0.0001 -
0.1591 6450 0.0002 -
0.1603 6500 0.0001 -
0.1616 6550 0.0001 -
0.1628 6600 0.0001 -
0.1640 6650 0.0001 -
0.1653 6700 0.0002 -
0.1665 6750 0.0001 -
0.1677 6800 0.0001 -
0.1690 6850 0.0001 -
0.1702 6900 0.0001 -
0.1714 6950 0.0001 -
0.1727 7000 0.0001 -
0.1739 7050 0.0001 -
0.1751 7100 0.0001 -
0.1764 7150 0.0001 -
0.1776 7200 0.0001 -
0.1788 7250 0.0001 -
0.1801 7300 0.0001 -
0.1813 7350 0.0001 -
0.1825 7400 0.0001 -
0.1838 7450 0.0001 -
0.1850 7500 0.0001 -
0.1862 7550 0.0001 -
0.1875 7600 0.0 -
0.1887 7650 0.0001 -
0.1899 7700 0.0001 -
0.1912 7750 0.0001 -
0.1924 7800 0.0001 -
0.1936 7850 0.0 -
0.1949 7900 0.0001 -
0.1961 7950 0.0 -
0.1973 8000 0.0001 -
0.1986 8050 0.0 -
0.1998 8100 0.0 -
0.2010 8150 0.0 -
0.2023 8200 0.0 -
0.2035 8250 0.0 -
0.2047 8300 0.0 -
0.2060 8350 0.0 -
0.2072 8400 0.0001 -
0.2084 8450 0.0 -
0.2097 8500 0.0002 -
0.2109 8550 0.0 -
0.2121 8600 0.0 -
0.2134 8650 0.0 -
0.2146 8700 0.0 -
0.2158 8750 0.0001 -
0.2171 8800 0.0002 -
0.2183 8850 0.0 -
0.2195 8900 0.0001 -
0.2208 8950 0.0 -
0.2220 9000 0.0 -
0.2232 9050 0.0 -
0.2245 9100 0.0 -
0.2257 9150 0.0 -
0.2269 9200 0.0 -
0.2282 9250 0.0 -
0.2294 9300 0.0 -
0.2306 9350 0.0 -
0.2319 9400 0.0 -
0.2331 9450 0.0 -
0.2343 9500 0.0 -
0.2356 9550 0.0 -
0.2368 9600 0.0 -
0.2380 9650 0.0 -
0.2393 9700 0.0 -
0.2405 9750 0.0 -
0.2417 9800 0.0 -
0.2430 9850 0.0 -
0.2442 9900 0.0 -
0.2454 9950 0.0 -
0.2467 10000 0.0 -
0.2479 10050 0.0 -
0.2491 10100 0.0 -
0.2504 10150 0.0 -
0.2516 10200 0.0 -
0.2528 10250 0.0 -
0.2541 10300 0.0001 -
0.2553 10350 0.0001 -
0.2565 10400 0.0 -
0.2578 10450 0.0 -
0.2590 10500 0.0 -
0.2602 10550 0.0 -
0.2615 10600 0.0 -
0.2627 10650 0.0 -
0.2639 10700 0.0 -
0.2652 10750 0.0 -
0.2664 10800 0.0 -
0.2676 10850 0.0 -
0.2689 10900 0.0 -
0.2701 10950 0.0 -
0.2713 11000 0.0 -
0.2726 11050 0.0 -
0.2738 11100 0.0 -
0.2750 11150 0.0 -
0.2763 11200 0.0 -
0.2775 11250 0.0 -
0.2787 11300 0.0 -
0.2800 11350 0.0 -
0.2812 11400 0.0 -
0.2824 11450 0.0 -
0.2837 11500 0.0 -
0.2849 11550 0.0 -
0.2861 11600 0.0 -
0.2874 11650 0.0001 -
0.2886 11700 0.0301 -
0.2898 11750 0.0 -
0.2911 11800 0.0 -
0.2923 11850 0.0 -
0.2935 11900 0.0 -
0.2948 11950 0.0 -
0.2960 12000 0.0 -
0.2972 12050 0.0 -
0.2985 12100 0.0 -
0.2997 12150 0.0 -
0.3009 12200 0.0001 -
0.3022 12250 0.0 -
0.3034 12300 0.0 -
0.3046 12350 0.0 -
0.3059 12400 0.0 -
0.3071 12450 0.0 -
0.3083 12500 0.0 -
0.3096 12550 0.0 -
0.3108 12600 0.0 -
0.3120 12650 0.0 -
0.3133 12700 0.0 -
0.3145 12750 0.0 -
0.3157 12800 0.0 -
0.3170 12850 0.0 -
0.3182 12900 0.0 -
0.3194 12950 0.0 -
0.3207 13000 0.0 -
0.3219 13050 0.0001 -
0.3231 13100 0.0 -
0.3244 13150 0.0 -
0.3256 13200 0.0 -
0.3268 13250 0.0 -
0.3281 13300 0.0 -
0.3293 13350 0.0 -
0.3305 13400 0.0 -
0.3318 13450 0.0 -
0.3330 13500 0.0 -
0.3342 13550 0.0 -
0.3355 13600 0.0 -
0.3367 13650 0.0 -
0.3379 13700 0.0 -
0.3392 13750 0.0 -
0.3404 13800 0.0 -
0.3416 13850 0.0 -
0.3429 13900 0.0 -
0.3441 13950 0.0 -
0.3453 14000 0.0 -
0.3466 14050 0.0 -
0.3478 14100 0.0 -
0.3490 14150 0.0 -
0.3503 14200 0.0 -
0.3515 14250 0.0 -
0.3527 14300 0.0 -
0.3540 14350 0.0 -
0.3552 14400 0.0001 -
0.3564 14450 0.0 -
0.3577 14500 0.0 -
0.3589 14550 0.0 -
0.3601 14600 0.0 -
0.3614 14650 0.0 -
0.3626 14700 0.0 -
0.3638 14750 0.0 -
0.3651 14800 0.0 -
0.3663 14850 0.0 -
0.3675 14900 0.0 -
0.3688 14950 0.0 -
0.3700 15000 0.0 -
0.3712 15050 0.0 -
0.3725 15100 0.0 -
0.3737 15150 0.0 -
0.3749 15200 0.0 -
0.3762 15250 0.0 -
0.3774 15300 0.0 -
0.3786 15350 0.0 -
0.3799 15400 0.0 -
0.3811 15450 0.0 -
0.3823 15500 0.0 -
0.3836 15550 0.0 -
0.3848 15600 0.0 -
0.3860 15650 0.0 -
0.3873 15700 0.0 -
0.3885 15750 0.0 -
0.3897 15800 0.0001 -
0.3910 15850 0.0 -
0.3922 15900 0.0 -
0.3934 15950 0.0 -
0.3947 16000 0.0 -
0.3959 16050 0.0 -
0.3971 16100 0.0 -
0.3984 16150 0.0 -
0.3996 16200 0.0 -
0.4008 16250 0.0 -
0.4021 16300 0.0 -
0.4033 16350 0.0 -
0.4045 16400 0.0 -
0.4058 16450 0.0001 -
0.4070 16500 0.0 -
0.4082 16550 0.0 -
0.4095 16600 0.0 -
0.4107 16650 0.0 -
0.4119 16700 0.0 -
0.4132 16750 0.0 -
0.4144 16800 0.0001 -
0.4156 16850 0.0 -
0.4169 16900 0.0 -
0.4181 16950 0.0 -
0.4193 17000 0.0 -
0.4206 17050 0.0 -
0.4218 17100 0.0 -
0.4230 17150 0.0 -
0.4243 17200 0.0 -
0.4255 17250 0.0 -
0.4267 17300 0.0 -
0.4280 17350 0.0 -
0.4292 17400 0.0 -
0.4304 17450 0.0 -
0.4317 17500 0.0 -
0.4329 17550 0.0 -
0.4341 17600 0.0 -
0.4354 17650 0.0 -
0.4366 17700 0.0 -
0.4378 17750 0.0 -
0.4391 17800 0.0 -
0.4403 17850 0.0 -
0.4415 17900 0.0 -
0.4428 17950 0.0 -
0.4440 18000 0.0 -
0.4452 18050 0.0 -
0.4465 18100 0.0 -
0.4477 18150 0.0 -
0.4489 18200 0.0 -
0.4502 18250 0.0 -
0.4514 18300 0.0 -
0.4526 18350 0.0 -
0.4539 18400 0.0 -
0.4551 18450 0.0001 -
0.4563 18500 0.0 -
0.4576 18550 0.0 -
0.4588 18600 0.0 -
0.4600 18650 0.0 -
0.4613 18700 0.0 -
0.4625 18750 0.0 -
0.4637 18800 0.0 -
0.4650 18850 0.0 -
0.4662 18900 0.0 -
0.4674 18950 0.0 -
0.4687 19000 0.0 -
0.4699 19050 0.0 -
0.4711 19100 0.0 -
0.4724 19150 0.0 -
0.4736 19200 0.0 -
0.4748 19250 0.0 -
0.4761 19300 0.0 -
0.4773 19350 0.0 -
0.4785 19400 0.0 -
0.4798 19450 0.0 -
0.4810 19500 0.0 -
0.4822 19550 0.0 -
0.4835 19600 0.0 -
0.4847 19650 0.0 -
0.4859 19700 0.0 -
0.4872 19750 0.0 -
0.4884 19800 0.0 -
0.4896 19850 0.0 -
0.4909 19900 0.0 -
0.4921 19950 0.0 -
0.4933 20000 0.0 -
0.4946 20050 0.0 -
0.4958 20100 0.0 -
0.4970 20150 0.0 -
0.4983 20200 0.0 -
0.4995 20250 0.0 -
0.5007 20300 0.0 -
0.5020 20350 0.0 -
0.5032 20400 0.0001 -
0.5044 20450 0.0 -
0.5057 20500 0.0 -
0.5069 20550 0.0 -
0.5081 20600 0.0 -
0.5094 20650 0.0 -
0.5106 20700 0.0 -
0.5118 20750 0.0 -
0.5131 20800 0.0 -
0.5143 20850 0.0 -
0.5155 20900 0.0 -
0.5168 20950 0.0 -
0.5180 21000 0.0 -
0.5192 21050 0.0 -
0.5205 21100 0.0 -
0.5217 21150 0.0001 -
0.5229 21200 0.0 -
0.5242 21250 0.0 -
0.5254 21300 0.0 -
0.5266 21350 0.0 -
0.5279 21400 0.0 -
0.5291 21450 0.0001 -
0.5303 21500 0.0 -
0.5316 21550 0.0 -
0.5328 21600 0.0 -
0.5340 21650 0.0 -
0.5353 21700 0.0 -
0.5365 21750 0.0 -
0.5377 21800 0.0 -
0.5390 21850 0.0 -
0.5402 21900 0.0 -
0.5414 21950 0.0 -
0.5427 22000 0.0 -
0.5439 22050 0.0 -
0.5451 22100 0.0 -
0.5464 22150 0.0 -
0.5476 22200 0.0 -
0.5488 22250 0.0 -
0.5501 22300 0.0001 -
0.5513 22350 0.0 -
0.5525 22400 0.0 -
0.5538 22450 0.0 -
0.5550 22500 0.0 -
0.5562 22550 0.0 -
0.5575 22600 0.0 -
0.5587 22650 0.0 -
0.5599 22700 0.0 -
0.5612 22750 0.0 -
0.5624 22800 0.0 -
0.5636 22850 0.0 -
0.5649 22900 0.0 -
0.5661 22950 0.0 -
0.5673 23000 0.0 -
0.5686 23050 0.0 -
0.5698 23100 0.0 -
0.5710 23150 0.0 -
0.5723 23200 0.0 -
0.5735 23250 0.0 -
0.5747 23300 0.0 -
0.5760 23350 0.0 -
0.5772 23400 0.0 -
0.5784 23450 0.0 -
0.5797 23500 0.0 -
0.5809 23550 0.0 -
0.5821 23600 0.0 -
0.5834 23650 0.0 -
0.5846 23700 0.0 -
0.5858 23750 0.0 -
0.5871 23800 0.0001 -
0.5883 23850 0.0 -
0.5895 23900 0.0 -
0.5908 23950 0.0 -
0.5920 24000 0.0 -
0.5932 24050 0.0 -
0.5945 24100 0.0 -
0.5957 24150 0.0 -
0.5969 24200 0.0 -
0.5982 24250 0.0 -
0.5994 24300 0.0 -
0.6006 24350 0.0 -
0.6019 24400 0.0 -
0.6031 24450 0.0 -
0.6043 24500 0.0 -
0.6056 24550 0.0 -
0.6068 24600 0.0 -
0.6080 24650 0.0 -
0.6093 24700 0.0 -
0.6105 24750 0.0 -
0.6117 24800 0.0 -
0.6130 24850 0.0001 -
0.6142 24900 0.0 -
0.6154 24950 0.0 -
0.6167 25000 0.0001 -
0.6179 25050 0.0 -
0.6191 25100 0.0 -
0.6204 25150 0.0 -
0.6216 25200 0.0 -
0.6228 25250 0.0 -
0.6241 25300 0.0 -
0.6253 25350 0.0 -
0.6265 25400 0.0 -
0.6278 25450 0.0 -
0.6290 25500 0.0 -
0.6302 25550 0.0 -
0.6315 25600 0.0 -
0.6327 25650 0.0 -
0.6339 25700 0.0 -
0.6352 25750 0.0001 -
0.6364 25800 0.0 -
0.6376 25850 0.0 -
0.6389 25900 0.0 -
0.6401 25950 0.0 -
0.6413 26000 0.0 -
0.6426 26050 0.0 -
0.6438 26100 0.0 -
0.6450 26150 0.0 -
0.6463 26200 0.0 -
0.6475 26250 0.0 -
0.6487 26300 0.0 -
0.6500 26350 0.0 -
0.6512 26400 0.0 -
0.6524 26450 0.0 -
0.6537 26500 0.0 -
0.6549 26550 0.0 -
0.6561 26600 0.0 -
0.6574 26650 0.0 -
0.6586 26700 0.0 -
0.6598 26750 0.0 -
0.6611 26800 0.0 -
0.6623 26850 0.0 -
0.6635 26900 0.0 -
0.6648 26950 0.0 -
0.6660 27000 0.0 -
0.6672 27050 0.0 -
0.6685 27100 0.0 -
0.6697 27150 0.0 -
0.6709 27200 0.0 -
0.6722 27250 0.0 -
0.6734 27300 0.0 -
0.6746 27350 0.0 -
0.6759 27400 0.0 -
0.6771 27450 0.0 -
0.6783 27500 0.0 -
0.6796 27550 0.0 -
0.6808 27600 0.0 -
0.6820 27650 0.0 -
0.6833 27700 0.0 -
0.6845 27750 0.0 -
0.6857 27800 0.0 -
0.6870 27850 0.0 -
0.6882 27900 0.0 -
0.6894 27950 0.0 -
0.6907 28000 0.0 -
0.6919 28050 0.0 -
0.6931 28100 0.0 -
0.6944 28150 0.0 -
0.6956 28200 0.0 -
0.6968 28250 0.0 -
0.6981 28300 0.0 -
0.6993 28350 0.0 -
0.7005 28400 0.0 -
0.7018 28450 0.0 -
0.7030 28500 0.0 -
0.7042 28550 0.0 -
0.7055 28600 0.0 -
0.7067 28650 0.0 -
0.7079 28700 0.0 -
0.7092 28750 0.0 -
0.7104 28800 0.0 -
0.7116 28850 0.0 -
0.7129 28900 0.0 -
0.7141 28950 0.0 -
0.7153 29000 0.0 -
0.7166 29050 0.0 -
0.7178 29100 0.0 -
0.7190 29150 0.0 -
0.7203 29200 0.0001 -
0.7215 29250 0.0 -
0.7227 29300 0.0 -
0.7240 29350 0.0 -
0.7252 29400 0.0 -
0.7264 29450 0.0 -
0.7277 29500 0.0 -
0.7289 29550 0.0 -
0.7301 29600 0.0 -
0.7314 29650 0.0 -
0.7326 29700 0.0 -
0.7338 29750 0.0 -
0.7351 29800 0.0 -
0.7363 29850 0.0 -
0.7375 29900 0.0 -
0.7388 29950 0.0 -
0.7400 30000 0.0 -
0.7412 30050 0.0 -
0.7425 30100 0.0 -
0.7437 30150 0.0 -
0.7449 30200 0.0 -
0.7462 30250 0.0 -
0.7474 30300 0.0 -
0.7486 30350 0.0 -
0.7499 30400 0.0 -
0.7511 30450 0.0 -
0.7523 30500 0.0 -
0.7536 30550 0.0 -
0.7548 30600 0.0 -
0.7560 30650 0.0 -
0.7573 30700 0.0001 -
0.7585 30750 0.0 -
0.7597 30800 0.0 -
0.7610 30850 0.0 -
0.7622 30900 0.0 -
0.7634 30950 0.0 -
0.7647 31000 0.0 -
0.7659 31050 0.0 -
0.7671 31100 0.0 -
0.7684 31150 0.0 -
0.7696 31200 0.0 -
0.7708 31250 0.0 -
0.7721 31300 0.0 -
0.7733 31350 0.0 -
0.7745 31400 0.0 -
0.7758 31450 0.0 -
0.7770 31500 0.0 -
0.7782 31550 0.0 -
0.7795 31600 0.0 -
0.7807 31650 0.0 -
0.7819 31700 0.0 -
0.7832 31750 0.0 -
0.7844 31800 0.0 -
0.7856 31850 0.0 -
0.7869 31900 0.0 -
0.7881 31950 0.0 -
0.7893 32000 0.0 -
0.7906 32050 0.0 -
0.7918 32100 0.0 -
0.7930 32150 0.0 -
0.7943 32200 0.0 -
0.7955 32250 0.0 -
0.7967 32300 0.0 -
0.7980 32350 0.0 -
0.7992 32400 0.0 -
0.8004 32450 0.0 -
0.8017 32500 0.0 -
0.8029 32550 0.0 -
0.8041 32600 0.0 -
0.8054 32650 0.0 -
0.8066 32700 0.0 -
0.8078 32750 0.0 -
0.8091 32800 0.0 -
0.8103 32850 0.0 -
0.8115 32900 0.0 -
0.8128 32950 0.0 -
0.8140 33000 0.0 -
0.8152 33050 0.0 -
0.8165 33100 0.0 -
0.8177 33150 0.0 -
0.8189 33200 0.0 -
0.8202 33250 0.0 -
0.8214 33300 0.0 -
0.8226 33350 0.0 -
0.8239 33400 0.0 -
0.8251 33450 0.0001 -
0.8263 33500 0.0 -
0.8276 33550 0.0 -
0.8288 33600 0.0 -
0.8300 33650 0.0 -
0.8313 33700 0.0 -
0.8325 33750 0.0 -
0.8337 33800 0.0 -
0.8350 33850 0.0 -
0.8362 33900 0.0 -
0.8374 33950 0.0 -
0.8387 34000 0.0 -
0.8399 34050 0.0 -
0.8411 34100 0.0 -
0.8424 34150 0.0 -
0.8436 34200 0.0 -
0.8448 34250 0.0 -
0.8461 34300 0.0 -
0.8473 34350 0.0 -
0.8485 34400 0.0 -
0.8498 34450 0.0 -
0.8510 34500 0.0 -
0.8522 34550 0.0 -
0.8535 34600 0.0 -
0.8547 34650 0.0 -
0.8559 34700 0.0 -
0.8572 34750 0.0 -
0.8584 34800 0.0 -
0.8596 34850 0.0 -
0.8609 34900 0.0 -
0.8621 34950 0.0 -
0.8633 35000 0.0 -
0.8646 35050 0.0 -
0.8658 35100 0.0 -
0.8670 35150 0.0 -
0.8683 35200 0.0 -
0.8695 35250 0.0 -
0.8707 35300 0.0 -
0.8720 35350 0.0 -
0.8732 35400 0.0 -
0.8744 35450 0.0 -
0.8757 35500 0.0 -
0.8769 35550 0.0 -
0.8781 35600 0.0 -
0.8794 35650 0.0 -
0.8806 35700 0.0 -
0.8818 35750 0.0 -
0.8831 35800 0.0 -
0.8843 35850 0.0 -
0.8855 35900 0.0 -
0.8868 35950 0.0 -
0.8880 36000 0.0 -
0.8892 36050 0.0 -
0.8905 36100 0.0 -
0.8917 36150 0.0 -
0.8929 36200 0.0 -
0.8942 36250 0.0 -
0.8954 36300 0.0 -
0.8966 36350 0.0 -
0.8979 36400 0.0 -
0.8991 36450 0.0 -
0.9003 36500 0.0 -
0.9016 36550 0.0 -
0.9028 36600 0.0 -
0.9040 36650 0.0 -
0.9053 36700 0.0 -
0.9065 36750 0.0 -
0.9077 36800 0.0 -
0.9090 36850 0.0 -
0.9102 36900 0.0 -
0.9114 36950 0.0 -
0.9127 37000 0.0 -
0.9139 37050 0.0 -
0.9151 37100 0.0 -
0.9164 37150 0.0 -
0.9176 37200 0.0 -
0.9188 37250 0.0 -
0.9201 37300 0.0 -
0.9213 37350 0.0 -
0.9225 37400 0.0 -
0.9238 37450 0.0 -
0.9250 37500 0.0 -
0.9262 37550 0.0 -
0.9275 37600 0.0 -
0.9287 37650 0.0 -
0.9299 37700 0.0 -
0.9312 37750 0.0 -
0.9324 37800 0.0 -
0.9336 37850 0.0 -
0.9349 37900 0.0 -
0.9361 37950 0.0 -
0.9373 38000 0.0 -
0.9386 38050 0.0 -
0.9398 38100 0.0 -
0.9410 38150 0.0 -
0.9423 38200 0.0 -
0.9435 38250 0.0 -
0.9447 38300 0.0 -
0.9460 38350 0.0 -
0.9472 38400 0.0 -
0.9484 38450 0.0 -
0.9497 38500 0.0 -
0.9509 38550 0.0 -
0.9521 38600 0.0 -
0.9534 38650 0.0 -
0.9546 38700 0.0 -
0.9558 38750 0.0 -
0.9571 38800 0.0 -
0.9583 38850 0.0 -
0.9595 38900 0.0 -
0.9608 38950 0.0 -
0.9620 39000 0.0 -
0.9632 39050 0.0 -
0.9645 39100 0.0 -
0.9657 39150 0.0 -
0.9669 39200 0.0 -
0.9682 39250 0.0 -
0.9694 39300 0.0 -
0.9706 39350 0.0 -
0.9719 39400 0.0 -
0.9731 39450 0.0 -
0.9743 39500 0.0 -
0.9756 39550 0.0 -
0.9768 39600 0.0 -
0.9780 39650 0.0 -
0.9793 39700 0.0 -
0.9805 39750 0.0 -
0.9817 39800 0.0 -
0.9830 39850 0.0 -
0.9842 39900 0.0 -
0.9854 39950 0.0 -
0.9867 40000 0.0 -
0.9879 40050 0.0 -
0.9891 40100 0.0 -
0.9904 40150 0.0 -
0.9916 40200 0.0 -
0.9928 40250 0.0 -
0.9941 40300 0.0 -
0.9953 40350 0.0 -
0.9965 40400 0.0 -
0.9978 40450 0.0 -
0.9990 40500 0.0 -

Framework Versions

  • Python: 3.10.12
  • SetFit: 1.0.3
  • Sentence Transformers: 2.5.1
  • Transformers: 4.38.1
  • PyTorch: 2.1.0+cu121
  • Datasets: 2.18.0
  • Tokenizers: 0.15.2

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}
}