|
--- |
|
library_name: setfit |
|
tags: |
|
- setfit |
|
- sentence-transformers |
|
- text-classification |
|
- generated_from_setfit_trainer |
|
base_model: sentence-transformers/paraphrase-mpnet-base-v2 |
|
metrics: |
|
- accuracy |
|
widget: |
|
- text: i'm busy with a project can we talk later |
|
- text: are you situated in india by any chance |
|
- text: '35' |
|
- text: at the tone please record your message |
|
- text: i told you not to keep going |
|
pipeline_tag: text-classification |
|
inference: true |
|
--- |
|
|
|
# SetFit with sentence-transformers/paraphrase-mpnet-base-v2 |
|
|
|
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) 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:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) |
|
- **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:** 29 classes |
|
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) --> |
|
<!-- - **Language:** Unknown --> |
|
<!-- - **License:** Unknown --> |
|
|
|
### 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 | |
|
|:---------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
|
| decline | <ul><li>'no i am not registered with medicare for part a or part b'</li><li>"no i'm not in"</li><li>"thank you very much but i don't think i will need that"</li></ul> | |
|
| provide_age | <ul><li>'my age is 36'</li><li>"i'm 62 years old"</li><li>'49'</li></ul> | |
|
| complain_calls | <ul><li>'stop disrupting my life with these calls'</li><li>'your constant calls are causing me distress'</li><li>'same as i was last time you called'</li></ul> | |
|
| already | <ul><li>'i already charged it should be good to go'</li><li>'already took care of it no worries'</li><li>'got the app installed already'</li></ul> | |
|
| Not_Interested | <ul><li>"oh but i'm not interested"</li><li>"no i don't want to talk i don't want to talk"</li><li>"i'm not interested in making any decisions right now"</li></ul> | |
|
| DNC | <ul><li>'i asked you to stop calling me'</li><li>"i've had enough no more calls"</li><li>'would you take me off your list please'</li></ul> | |
|
| where_get_number | <ul><li>"i never provided my number to you what's going on"</li><li>'who is responsible for sharing my number with you'</li><li>"what's the source of my contact details in your database"</li></ul> | |
|
| language_barrier | <ul><li>"speak espanol i'm lost"</li><li>"sorry i'm not speaking english"</li><li>'no english'</li></ul> | |
|
| answering_machine | <ul><li>'this is the voicemail system record your message after the beep'</li><li>'this is the voicemail speak your message after the beep'</li><li>'you have reached a law source number that is no longer in service please check the number you have dialed'</li></ul> | |
|
| BUSY | <ul><li>"i'm engaged in a conference call can we talk later"</li><li>"right now i'm not able to talk right now bye"</li><li>"i don't have time"</li></ul> | |
|
| where_are_you_calling_from | <ul><li>'is the philippines where your organization is based'</li><li>'where can i find your headquarters'</li><li>"can you confirm if you're in canada"</li></ul> | |
|
| scam | <ul><li>"that's none of your business"</li><li>"i don't think i'm going to say it"</li><li>'scammers are clever what measures do you have to counteract them'</li></ul> | |
|
| affirmation | <ul><li>'yeah you are'</li><li>"for sure that's correct"</li><li>'i have secured both medicare part a and part b coverage'</li></ul> | |
|
| transfer_request | <ul><li>'i want to discuss this with someone higher up'</li><li>'transfer my call to your superior please'</li><li>'i require assistance from your manager immediately'</li></ul> | |
|
| abusive | <ul><li>'what the fuck you calling me for'</li><li>'and you rather the fucking guy you fucked up'</li><li>'crikey'</li></ul> | |
|
| calling_about | <ul><li>'why are you getting in touch with me'</li><li>"what's the main subject of discussion in this call"</li><li>"what's the rationale behind this call"</li></ul> | |
|
| GreetBack | <ul><li>"what's crackin' how you been"</li><li>"i'm doing good how are you doing"</li><li>"hi i'm fine how's your day been so far"</li></ul> | |
|
| say_again | <ul><li>'can you please say that again'</li><li>'sorry i need you to repeat that'</li><li>'what was that can you repeat it'</li></ul> | |
|
| sorry_greeting | <ul><li>"to be honest i'm feeling a bit down"</li><li>"i'm not really in a great mood"</li><li>"i'm not feeling very joyful right now"</li></ul> | |
|
| not_decision_maker | <ul><li>'decisions like this require a different approach'</li><li>"decisions of this nature aren't mine to make"</li><li>'decisions in this regard are not mine to make'</li></ul> | |
|
| hold_a_sec | <ul><li>'please stay on the line while i check'</li><li>'i need to consult with my colleague hold on'</li><li>"i'll be right back don't disconnect"</li></ul> | |
|
| interested | <ul><li>'your topic has piqued my curiosity do continue'</li><li>'go'</li><li>"i'm all ears talk"</li></ul> | |
|
| greetings | <ul><li>"i'm doing great thank you"</li><li>"hi there hope you're having a splendid day"</li><li>'rest well and recharge good night'</li></ul> | |
|
| who_are_you | <ul><li>'start by telling me who you are'</li><li>'can you tell me your given name'</li><li>"what's your name and position"</li></ul> | |
|
| can_you_email | <ul><li>'can you send an email with the instructions'</li><li>'can you email me the contract terms'</li><li>'is email the preferred way to receive updates'</li></ul> | |
|
| DNQ | <ul><li>"i'm not the right fit for this"</li><li>"i'm not the right person for this"</li><li>"it's not the right fit for me"</li></ul> | |
|
| are_you_bot | <ul><li>'is this interaction with an automated system'</li><li>'is this interaction with a human or a bot'</li><li>'is this interaction with a robot or human'</li></ul> | |
|
| other | <ul><li>'i love exploring the different neighborhoods of our city each has its own charm'</li><li>'no i have to buy a car'</li><li>'i was just reading an article about the latest technological innovations'</li></ul> | |
|
| weather | <ul><li>"how's the climate today"</li><li>'tell me what the weather is like'</li><li>"how's the weather in the morning"</li></ul> | |
|
|
|
## 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("m-aliabbas1/medicare_idrak_ab") |
|
# Run inference |
|
preds = model("35") |
|
``` |
|
|
|
<!-- |
|
### Downstream Use |
|
|
|
*List how someone could finetune this model on their own dataset.* |
|
--> |
|
|
|
<!-- |
|
### Out-of-Scope Use |
|
|
|
*List how the model may foreseeably be misused and address what users ought not to do with the model.* |
|
--> |
|
|
|
<!-- |
|
## Bias, Risks and Limitations |
|
|
|
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
|
--> |
|
|
|
<!-- |
|
### Recommendations |
|
|
|
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
|
--> |
|
|
|
## Training Details |
|
|
|
### Training Set Metrics |
|
| Training set | Min | Median | Max | |
|
|:-------------|:----|:-------|:----| |
|
| Word count | 1 | 7.3794 | 109 | |
|
|
|
| Label | Training Sample Count | |
|
|:---------------------------|:----------------------| |
|
| BUSY | 528 | |
|
| DNC | 585 | |
|
| DNQ | 96 | |
|
| GreetBack | 224 | |
|
| Not_Interested | 497 | |
|
| abusive | 145 | |
|
| affirmation | 306 | |
|
| already | 70 | |
|
| answering_machine | 316 | |
|
| are_you_bot | 205 | |
|
| calling_about | 147 | |
|
| can_you_email | 116 | |
|
| complain_calls | 65 | |
|
| decline | 455 | |
|
| greetings | 82 | |
|
| hold_a_sec | 79 | |
|
| interested | 94 | |
|
| language_barrier | 163 | |
|
| not_decision_maker | 83 | |
|
| other | 56 | |
|
| provide_age | 355 | |
|
| say_again | 83 | |
|
| scam | 110 | |
|
| sorry_greeting | 102 | |
|
| transfer_request | 73 | |
|
| weather | 129 | |
|
| where_are_you_calling_from | 250 | |
|
| where_get_number | 127 | |
|
| who_are_you | 221 | |
|
|
|
### Training Hyperparameters |
|
- batch_size: (16, 16) |
|
- num_epochs: (1, 1) |
|
- max_steps: -1 |
|
- sampling_strategy: oversampling |
|
- num_iterations: 40 |
|
- body_learning_rate: (2e-05, 2e-05) |
|
- head_learning_rate: 2e-05 |
|
- 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 | |
|
|:------:|:-----:|:-------------:|:---------------:| |
|
| 0.0000 | 1 | 0.2366 | - | |
|
| 0.0017 | 50 | 0.1785 | - | |
|
| 0.0035 | 100 | 0.1604 | - | |
|
| 0.0052 | 150 | 0.1877 | - | |
|
| 0.0069 | 200 | 0.1209 | - | |
|
| 0.0087 | 250 | 0.161 | - | |
|
| 0.0104 | 300 | 0.1261 | - | |
|
| 0.0121 | 350 | 0.153 | - | |
|
| 0.0139 | 400 | 0.1333 | - | |
|
| 0.0156 | 450 | 0.0675 | - | |
|
| 0.0174 | 500 | 0.0623 | - | |
|
| 0.0191 | 550 | 0.1324 | - | |
|
| 0.0208 | 600 | 0.0481 | - | |
|
| 0.0226 | 650 | 0.0894 | - | |
|
| 0.0243 | 700 | 0.0484 | - | |
|
| 0.0260 | 750 | 0.0683 | - | |
|
| 0.0278 | 800 | 0.1025 | - | |
|
| 0.0295 | 850 | 0.028 | - | |
|
| 0.0312 | 900 | 0.0218 | - | |
|
| 0.0330 | 950 | 0.0078 | - | |
|
| 0.0347 | 1000 | 0.0682 | - | |
|
| 0.0364 | 1050 | 0.0094 | - | |
|
| 0.0382 | 1100 | 0.0836 | - | |
|
| 0.0399 | 1150 | 0.0858 | - | |
|
| 0.0417 | 1200 | 0.0115 | - | |
|
| 0.0434 | 1250 | 0.0738 | - | |
|
| 0.0451 | 1300 | 0.009 | - | |
|
| 0.0469 | 1350 | 0.044 | - | |
|
| 0.0486 | 1400 | 0.059 | - | |
|
| 0.0503 | 1450 | 0.0271 | - | |
|
| 0.0521 | 1500 | 0.1249 | - | |
|
| 0.0538 | 1550 | 0.0032 | - | |
|
| 0.0555 | 1600 | 0.0897 | - | |
|
| 0.0573 | 1650 | 0.0758 | - | |
|
| 0.0590 | 1700 | 0.0573 | - | |
|
| 0.0607 | 1750 | 0.0063 | - | |
|
| 0.0625 | 1800 | 0.011 | - | |
|
| 0.0642 | 1850 | 0.005 | - | |
|
| 0.0659 | 1900 | 0.0545 | - | |
|
| 0.0677 | 1950 | 0.0216 | - | |
|
| 0.0694 | 2000 | 0.0059 | - | |
|
| 0.0712 | 2050 | 0.0043 | - | |
|
| 0.0729 | 2100 | 0.0109 | - | |
|
| 0.0746 | 2150 | 0.0049 | - | |
|
| 0.0764 | 2200 | 0.012 | - | |
|
| 0.0781 | 2250 | 0.0012 | - | |
|
| 0.0798 | 2300 | 0.0284 | - | |
|
| 0.0816 | 2350 | 0.0089 | - | |
|
| 0.0833 | 2400 | 0.0023 | - | |
|
| 0.0850 | 2450 | 0.0234 | - | |
|
| 0.0868 | 2500 | 0.0463 | - | |
|
| 0.0885 | 2550 | 0.0647 | - | |
|
| 0.0902 | 2600 | 0.0578 | - | |
|
| 0.0920 | 2650 | 0.0119 | - | |
|
| 0.0937 | 2700 | 0.0562 | - | |
|
| 0.0955 | 2750 | 0.0009 | - | |
|
| 0.0972 | 2800 | 0.0573 | - | |
|
| 0.0989 | 2850 | 0.0042 | - | |
|
| 0.1007 | 2900 | 0.0028 | - | |
|
| 0.1024 | 2950 | 0.0048 | - | |
|
| 0.1041 | 3000 | 0.1124 | - | |
|
| 0.1059 | 3050 | 0.0022 | - | |
|
| 0.1076 | 3100 | 0.0033 | - | |
|
| 0.1093 | 3150 | 0.0029 | - | |
|
| 0.1111 | 3200 | 0.0281 | - | |
|
| 0.1128 | 3250 | 0.0474 | - | |
|
| 0.1145 | 3300 | 0.0059 | - | |
|
| 0.1163 | 3350 | 0.0198 | - | |
|
| 0.1180 | 3400 | 0.128 | - | |
|
| 0.1198 | 3450 | 0.0092 | - | |
|
| 0.1215 | 3500 | 0.0023 | - | |
|
| 0.1232 | 3550 | 0.044 | - | |
|
| 0.1250 | 3600 | 0.0333 | - | |
|
| 0.1267 | 3650 | 0.0014 | - | |
|
| 0.1284 | 3700 | 0.0019 | - | |
|
| 0.1302 | 3750 | 0.0514 | - | |
|
| 0.1319 | 3800 | 0.0004 | - | |
|
| 0.1336 | 3850 | 0.0022 | - | |
|
| 0.1354 | 3900 | 0.0012 | - | |
|
| 0.1371 | 3950 | 0.0598 | - | |
|
| 0.1388 | 4000 | 0.0013 | - | |
|
| 0.1406 | 4050 | 0.0597 | - | |
|
| 0.1423 | 4100 | 0.0004 | - | |
|
| 0.1440 | 4150 | 0.0038 | - | |
|
| 0.1458 | 4200 | 0.0523 | - | |
|
| 0.1475 | 4250 | 0.0481 | - | |
|
| 0.1493 | 4300 | 0.1062 | - | |
|
| 0.1510 | 4350 | 0.0033 | - | |
|
| 0.1527 | 4400 | 0.0007 | - | |
|
| 0.1545 | 4450 | 0.0002 | - | |
|
| 0.1562 | 4500 | 0.0009 | - | |
|
| 0.1579 | 4550 | 0.0021 | - | |
|
| 0.1597 | 4600 | 0.0013 | - | |
|
| 0.1614 | 4650 | 0.0012 | - | |
|
| 0.1631 | 4700 | 0.0012 | - | |
|
| 0.1649 | 4750 | 0.0016 | - | |
|
| 0.1666 | 4800 | 0.0002 | - | |
|
| 0.1683 | 4850 | 0.0005 | - | |
|
| 0.1701 | 4900 | 0.0039 | - | |
|
| 0.1718 | 4950 | 0.0013 | - | |
|
| 0.1736 | 5000 | 0.0022 | - | |
|
| 0.1753 | 5050 | 0.0006 | - | |
|
| 0.1770 | 5100 | 0.002 | - | |
|
| 0.1788 | 5150 | 0.0004 | - | |
|
| 0.1805 | 5200 | 0.0009 | - | |
|
| 0.1822 | 5250 | 0.0004 | - | |
|
| 0.1840 | 5300 | 0.0006 | - | |
|
| 0.1857 | 5350 | 0.0107 | - | |
|
| 0.1874 | 5400 | 0.0002 | - | |
|
| 0.1892 | 5450 | 0.0006 | - | |
|
| 0.1909 | 5500 | 0.0017 | - | |
|
| 0.1926 | 5550 | 0.0049 | - | |
|
| 0.1944 | 5600 | 0.0006 | - | |
|
| 0.1961 | 5650 | 0.0138 | - | |
|
| 0.1978 | 5700 | 0.011 | - | |
|
| 0.1996 | 5750 | 0.0042 | - | |
|
| 0.2013 | 5800 | 0.0017 | - | |
|
| 0.2031 | 5850 | 0.0011 | - | |
|
| 0.2048 | 5900 | 0.0103 | - | |
|
| 0.2065 | 5950 | 0.0008 | - | |
|
| 0.2083 | 6000 | 0.0615 | - | |
|
| 0.2100 | 6050 | 0.0539 | - | |
|
| 0.2117 | 6100 | 0.0016 | - | |
|
| 0.2135 | 6150 | 0.0005 | - | |
|
| 0.2152 | 6200 | 0.0004 | - | |
|
| 0.2169 | 6250 | 0.0296 | - | |
|
| 0.2187 | 6300 | 0.0003 | - | |
|
| 0.2204 | 6350 | 0.0023 | - | |
|
| 0.2221 | 6400 | 0.0306 | - | |
|
| 0.2239 | 6450 | 0.0496 | - | |
|
| 0.2256 | 6500 | 0.0433 | - | |
|
| 0.2274 | 6550 | 0.0005 | - | |
|
| 0.2291 | 6600 | 0.0109 | - | |
|
| 0.2308 | 6650 | 0.0354 | - | |
|
| 0.2326 | 6700 | 0.0007 | - | |
|
| 0.2343 | 6750 | 0.0003 | - | |
|
| 0.2360 | 6800 | 0.0006 | - | |
|
| 0.2378 | 6850 | 0.0002 | - | |
|
| 0.2395 | 6900 | 0.0014 | - | |
|
| 0.2412 | 6950 | 0.0005 | - | |
|
| 0.2430 | 7000 | 0.0002 | - | |
|
| 0.2447 | 7050 | 0.0394 | - | |
|
| 0.2464 | 7100 | 0.0006 | - | |
|
| 0.2482 | 7150 | 0.0005 | - | |
|
| 0.2499 | 7200 | 0.0002 | - | |
|
| 0.2516 | 7250 | 0.0017 | - | |
|
| 0.2534 | 7300 | 0.0004 | - | |
|
| 0.2551 | 7350 | 0.0018 | - | |
|
| 0.2569 | 7400 | 0.0184 | - | |
|
| 0.2586 | 7450 | 0.0003 | - | |
|
| 0.2603 | 7500 | 0.0515 | - | |
|
| 0.2621 | 7550 | 0.0003 | - | |
|
| 0.2638 | 7600 | 0.0013 | - | |
|
| 0.2655 | 7650 | 0.0609 | - | |
|
| 0.2673 | 7700 | 0.0017 | - | |
|
| 0.2690 | 7750 | 0.0003 | - | |
|
| 0.2707 | 7800 | 0.0011 | - | |
|
| 0.2725 | 7850 | 0.0016 | - | |
|
| 0.2742 | 7900 | 0.003 | - | |
|
| 0.2759 | 7950 | 0.1212 | - | |
|
| 0.2777 | 8000 | 0.0001 | - | |
|
| 0.2794 | 8050 | 0.0004 | - | |
|
| 0.2812 | 8100 | 0.0003 | - | |
|
| 0.2829 | 8150 | 0.0608 | - | |
|
| 0.2846 | 8200 | 0.0002 | - | |
|
| 0.2864 | 8250 | 0.0003 | - | |
|
| 0.2881 | 8300 | 0.0022 | - | |
|
| 0.2898 | 8350 | 0.0052 | - | |
|
| 0.2916 | 8400 | 0.0003 | - | |
|
| 0.2933 | 8450 | 0.0001 | - | |
|
| 0.2950 | 8500 | 0.0007 | - | |
|
| 0.2968 | 8550 | 0.0336 | - | |
|
| 0.2985 | 8600 | 0.0071 | - | |
|
| 0.3002 | 8650 | 0.0002 | - | |
|
| 0.3020 | 8700 | 0.0002 | - | |
|
| 0.3037 | 8750 | 0.0107 | - | |
|
| 0.3054 | 8800 | 0.0006 | - | |
|
| 0.3072 | 8850 | 0.002 | - | |
|
| 0.3089 | 8900 | 0.001 | - | |
|
| 0.3107 | 8950 | 0.0002 | - | |
|
| 0.3124 | 9000 | 0.0002 | - | |
|
| 0.3141 | 9050 | 0.0021 | - | |
|
| 0.3159 | 9100 | 0.0545 | - | |
|
| 0.3176 | 9150 | 0.0007 | - | |
|
| 0.3193 | 9200 | 0.0152 | - | |
|
| 0.3211 | 9250 | 0.0003 | - | |
|
| 0.3228 | 9300 | 0.0005 | - | |
|
| 0.3245 | 9350 | 0.053 | - | |
|
| 0.3263 | 9400 | 0.0031 | - | |
|
| 0.3280 | 9450 | 0.0002 | - | |
|
| 0.3297 | 9500 | 0.0002 | - | |
|
| 0.3315 | 9550 | 0.0002 | - | |
|
| 0.3332 | 9600 | 0.0009 | - | |
|
| 0.3350 | 9650 | 0.0023 | - | |
|
| 0.3367 | 9700 | 0.0011 | - | |
|
| 0.3384 | 9750 | 0.0003 | - | |
|
| 0.3402 | 9800 | 0.0003 | - | |
|
| 0.3419 | 9850 | 0.0005 | - | |
|
| 0.3436 | 9900 | 0.0004 | - | |
|
| 0.3454 | 9950 | 0.0028 | - | |
|
| 0.3471 | 10000 | 0.0016 | - | |
|
| 0.3488 | 10050 | 0.0008 | - | |
|
| 0.3506 | 10100 | 0.001 | - | |
|
| 0.3523 | 10150 | 0.0005 | - | |
|
| 0.3540 | 10200 | 0.0002 | - | |
|
| 0.3558 | 10250 | 0.0002 | - | |
|
| 0.3575 | 10300 | 0.0003 | - | |
|
| 0.3593 | 10350 | 0.0003 | - | |
|
| 0.3610 | 10400 | 0.0009 | - | |
|
| 0.3627 | 10450 | 0.0001 | - | |
|
| 0.3645 | 10500 | 0.0001 | - | |
|
| 0.3662 | 10550 | 0.0002 | - | |
|
| 0.3679 | 10600 | 0.0003 | - | |
|
| 0.3697 | 10650 | 0.0002 | - | |
|
| 0.3714 | 10700 | 0.0006 | - | |
|
| 0.3731 | 10750 | 0.0042 | - | |
|
| 0.3749 | 10800 | 0.0005 | - | |
|
| 0.3766 | 10850 | 0.0009 | - | |
|
| 0.3783 | 10900 | 0.0604 | - | |
|
| 0.3801 | 10950 | 0.0002 | - | |
|
| 0.3818 | 11000 | 0.0013 | - | |
|
| 0.3835 | 11050 | 0.0001 | - | |
|
| 0.3853 | 11100 | 0.0005 | - | |
|
| 0.3870 | 11150 | 0.0007 | - | |
|
| 0.3888 | 11200 | 0.0002 | - | |
|
| 0.3905 | 11250 | 0.0001 | - | |
|
| 0.3922 | 11300 | 0.0006 | - | |
|
| 0.3940 | 11350 | 0.0593 | - | |
|
| 0.3957 | 11400 | 0.0007 | - | |
|
| 0.3974 | 11450 | 0.0001 | - | |
|
| 0.3992 | 11500 | 0.0003 | - | |
|
| 0.4009 | 11550 | 0.0647 | - | |
|
| 0.4026 | 11600 | 0.0001 | - | |
|
| 0.4044 | 11650 | 0.0001 | - | |
|
| 0.4061 | 11700 | 0.0001 | - | |
|
| 0.4078 | 11750 | 0.0003 | - | |
|
| 0.4096 | 11800 | 0.0002 | - | |
|
| 0.4113 | 11850 | 0.0128 | - | |
|
| 0.4131 | 11900 | 0.0015 | - | |
|
| 0.4148 | 11950 | 0.0002 | - | |
|
| 0.4165 | 12000 | 0.0004 | - | |
|
| 0.4183 | 12050 | 0.0003 | - | |
|
| 0.4200 | 12100 | 0.0001 | - | |
|
| 0.4217 | 12150 | 0.0003 | - | |
|
| 0.4235 | 12200 | 0.0006 | - | |
|
| 0.4252 | 12250 | 0.0205 | - | |
|
| 0.4269 | 12300 | 0.0004 | - | |
|
| 0.4287 | 12350 | 0.0002 | - | |
|
| 0.4304 | 12400 | 0.0001 | - | |
|
| 0.4321 | 12450 | 0.0002 | - | |
|
| 0.4339 | 12500 | 0.0025 | - | |
|
| 0.4356 | 12550 | 0.0002 | - | |
|
| 0.4373 | 12600 | 0.0002 | - | |
|
| 0.4391 | 12650 | 0.0102 | - | |
|
| 0.4408 | 12700 | 0.0001 | - | |
|
| 0.4426 | 12750 | 0.0002 | - | |
|
| 0.4443 | 12800 | 0.0003 | - | |
|
| 0.4460 | 12850 | 0.0002 | - | |
|
| 0.4478 | 12900 | 0.0003 | - | |
|
| 0.4495 | 12950 | 0.0003 | - | |
|
| 0.4512 | 13000 | 0.0007 | - | |
|
| 0.4530 | 13050 | 0.0001 | - | |
|
| 0.4547 | 13100 | 0.0002 | - | |
|
| 0.4564 | 13150 | 0.0002 | - | |
|
| 0.4582 | 13200 | 0.0004 | - | |
|
| 0.4599 | 13250 | 0.0002 | - | |
|
| 0.4616 | 13300 | 0.0001 | - | |
|
| 0.4634 | 13350 | 0.0001 | - | |
|
| 0.4651 | 13400 | 0.0001 | - | |
|
| 0.4669 | 13450 | 0.0002 | - | |
|
| 0.4686 | 13500 | 0.0007 | - | |
|
| 0.4703 | 13550 | 0.0023 | - | |
|
| 0.4721 | 13600 | 0.0004 | - | |
|
| 0.4738 | 13650 | 0.0001 | - | |
|
| 0.4755 | 13700 | 0.0002 | - | |
|
| 0.4773 | 13750 | 0.0001 | - | |
|
| 0.4790 | 13800 | 0.0001 | - | |
|
| 0.4807 | 13850 | 0.0002 | - | |
|
| 0.4825 | 13900 | 0.0003 | - | |
|
| 0.4842 | 13950 | 0.027 | - | |
|
| 0.4859 | 14000 | 0.0002 | - | |
|
| 0.4877 | 14050 | 0.0001 | - | |
|
| 0.4894 | 14100 | 0.0002 | - | |
|
| 0.4911 | 14150 | 0.0003 | - | |
|
| 0.4929 | 14200 | 0.0001 | - | |
|
| 0.4946 | 14250 | 0.0001 | - | |
|
| 0.4964 | 14300 | 0.0002 | - | |
|
| 0.4981 | 14350 | 0.0001 | - | |
|
| 0.4998 | 14400 | 0.0002 | - | |
|
| 0.5016 | 14450 | 0.0004 | - | |
|
| 0.5033 | 14500 | 0.0001 | - | |
|
| 0.5050 | 14550 | 0.0085 | - | |
|
| 0.5068 | 14600 | 0.0008 | - | |
|
| 0.5085 | 14650 | 0.0001 | - | |
|
| 0.5102 | 14700 | 0.0001 | - | |
|
| 0.5120 | 14750 | 0.0001 | - | |
|
| 0.5137 | 14800 | 0.044 | - | |
|
| 0.5154 | 14850 | 0.0001 | - | |
|
| 0.5172 | 14900 | 0.0001 | - | |
|
| 0.5189 | 14950 | 0.0001 | - | |
|
| 0.5207 | 15000 | 0.0002 | - | |
|
| 0.5224 | 15050 | 0.0001 | - | |
|
| 0.5241 | 15100 | 0.0001 | - | |
|
| 0.5259 | 15150 | 0.0003 | - | |
|
| 0.5276 | 15200 | 0.003 | - | |
|
| 0.5293 | 15250 | 0.0027 | - | |
|
| 0.5311 | 15300 | 0.0001 | - | |
|
| 0.5328 | 15350 | 0.0003 | - | |
|
| 0.5345 | 15400 | 0.0003 | - | |
|
| 0.5363 | 15450 | 0.0002 | - | |
|
| 0.5380 | 15500 | 0.0004 | - | |
|
| 0.5397 | 15550 | 0.0002 | - | |
|
| 0.5415 | 15600 | 0.0001 | - | |
|
| 0.5432 | 15650 | 0.0001 | - | |
|
| 0.5449 | 15700 | 0.0002 | - | |
|
| 0.5467 | 15750 | 0.0108 | - | |
|
| 0.5484 | 15800 | 0.0001 | - | |
|
| 0.5502 | 15850 | 0.0002 | - | |
|
| 0.5519 | 15900 | 0.0001 | - | |
|
| 0.5536 | 15950 | 0.0014 | - | |
|
| 0.5554 | 16000 | 0.0001 | - | |
|
| 0.5571 | 16050 | 0.0003 | - | |
|
| 0.5588 | 16100 | 0.0008 | - | |
|
| 0.5606 | 16150 | 0.0333 | - | |
|
| 0.5623 | 16200 | 0.0018 | - | |
|
| 0.5640 | 16250 | 0.0002 | - | |
|
| 0.5658 | 16300 | 0.0002 | - | |
|
| 0.5675 | 16350 | 0.0001 | - | |
|
| 0.5692 | 16400 | 0.0001 | - | |
|
| 0.5710 | 16450 | 0.0003 | - | |
|
| 0.5727 | 16500 | 0.0001 | - | |
|
| 0.5745 | 16550 | 0.0073 | - | |
|
| 0.5762 | 16600 | 0.0012 | - | |
|
| 0.5779 | 16650 | 0.0002 | - | |
|
| 0.5797 | 16700 | 0.0001 | - | |
|
| 0.5814 | 16750 | 0.0022 | - | |
|
| 0.5831 | 16800 | 0.0003 | - | |
|
| 0.5849 | 16850 | 0.0002 | - | |
|
| 0.5866 | 16900 | 0.0001 | - | |
|
| 0.5883 | 16950 | 0.0019 | - | |
|
| 0.5901 | 17000 | 0.0003 | - | |
|
| 0.5918 | 17050 | 0.0001 | - | |
|
| 0.5935 | 17100 | 0.0003 | - | |
|
| 0.5953 | 17150 | 0.0001 | - | |
|
| 0.5970 | 17200 | 0.0001 | - | |
|
| 0.5988 | 17250 | 0.0167 | - | |
|
| 0.6005 | 17300 | 0.0002 | - | |
|
| 0.6022 | 17350 | 0.0001 | - | |
|
| 0.6040 | 17400 | 0.0001 | - | |
|
| 0.6057 | 17450 | 0.0242 | - | |
|
| 0.6074 | 17500 | 0.0015 | - | |
|
| 0.6092 | 17550 | 0.0009 | - | |
|
| 0.6109 | 17600 | 0.0001 | - | |
|
| 0.6126 | 17650 | 0.0001 | - | |
|
| 0.6144 | 17700 | 0.0001 | - | |
|
| 0.6161 | 17750 | 0.0001 | - | |
|
| 0.6178 | 17800 | 0.0001 | - | |
|
| 0.6196 | 17850 | 0.0113 | - | |
|
| 0.6213 | 17900 | 0.0001 | - | |
|
| 0.6230 | 17950 | 0.0005 | - | |
|
| 0.6248 | 18000 | 0.0017 | - | |
|
| 0.6265 | 18050 | 0.0001 | - | |
|
| 0.6283 | 18100 | 0.0001 | - | |
|
| 0.6300 | 18150 | 0.0003 | - | |
|
| 0.6317 | 18200 | 0.0001 | - | |
|
| 0.6335 | 18250 | 0.0004 | - | |
|
| 0.6352 | 18300 | 0.0001 | - | |
|
| 0.6369 | 18350 | 0.0001 | - | |
|
| 0.6387 | 18400 | 0.0021 | - | |
|
| 0.6404 | 18450 | 0.0001 | - | |
|
| 0.6421 | 18500 | 0.0002 | - | |
|
| 0.6439 | 18550 | 0.0006 | - | |
|
| 0.6456 | 18600 | 0.0001 | - | |
|
| 0.6473 | 18650 | 0.0001 | - | |
|
| 0.6491 | 18700 | 0.0003 | - | |
|
| 0.6508 | 18750 | 0.0001 | - | |
|
| 0.6526 | 18800 | 0.0001 | - | |
|
| 0.6543 | 18850 | 0.0002 | - | |
|
| 0.6560 | 18900 | 0.001 | - | |
|
| 0.6578 | 18950 | 0.0002 | - | |
|
| 0.6595 | 19000 | 0.0047 | - | |
|
| 0.6612 | 19050 | 0.0001 | - | |
|
| 0.6630 | 19100 | 0.0001 | - | |
|
| 0.6647 | 19150 | 0.0002 | - | |
|
| 0.6664 | 19200 | 0.0001 | - | |
|
| 0.6682 | 19250 | 0.0001 | - | |
|
| 0.6699 | 19300 | 0.0064 | - | |
|
| 0.6716 | 19350 | 0.0001 | - | |
|
| 0.6734 | 19400 | 0.0001 | - | |
|
| 0.6751 | 19450 | 0.0001 | - | |
|
| 0.6768 | 19500 | 0.0001 | - | |
|
| 0.6786 | 19550 | 0.0001 | - | |
|
| 0.6803 | 19600 | 0.0001 | - | |
|
| 0.6821 | 19650 | 0.0001 | - | |
|
| 0.6838 | 19700 | 0.0001 | - | |
|
| 0.6855 | 19750 | 0.0002 | - | |
|
| 0.6873 | 19800 | 0.0001 | - | |
|
| 0.6890 | 19850 | 0.0001 | - | |
|
| 0.6907 | 19900 | 0.0001 | - | |
|
| 0.6925 | 19950 | 0.0001 | - | |
|
| 0.6942 | 20000 | 0.0002 | - | |
|
| 0.6959 | 20050 | 0.0015 | - | |
|
| 0.6977 | 20100 | 0.0002 | - | |
|
| 0.6994 | 20150 | 0.0001 | - | |
|
| 0.7011 | 20200 | 0.0001 | - | |
|
| 0.7029 | 20250 | 0.0001 | - | |
|
| 0.7046 | 20300 | 0.0011 | - | |
|
| 0.7064 | 20350 | 0.0001 | - | |
|
| 0.7081 | 20400 | 0.0001 | - | |
|
| 0.7098 | 20450 | 0.0001 | - | |
|
| 0.7116 | 20500 | 0.0057 | - | |
|
| 0.7133 | 20550 | 0.0 | - | |
|
| 0.7150 | 20600 | 0.0001 | - | |
|
| 0.7168 | 20650 | 0.0001 | - | |
|
| 0.7185 | 20700 | 0.0001 | - | |
|
| 0.7202 | 20750 | 0.0001 | - | |
|
| 0.7220 | 20800 | 0.0001 | - | |
|
| 0.7237 | 20850 | 0.0001 | - | |
|
| 0.7254 | 20900 | 0.0002 | - | |
|
| 0.7272 | 20950 | 0.0001 | - | |
|
| 0.7289 | 21000 | 0.0001 | - | |
|
| 0.7306 | 21050 | 0.0 | - | |
|
| 0.7324 | 21100 | 0.0002 | - | |
|
| 0.7341 | 21150 | 0.0001 | - | |
|
| 0.7359 | 21200 | 0.0001 | - | |
|
| 0.7376 | 21250 | 0.0001 | - | |
|
| 0.7393 | 21300 | 0.0001 | - | |
|
| 0.7411 | 21350 | 0.0001 | - | |
|
| 0.7428 | 21400 | 0.0001 | - | |
|
| 0.7445 | 21450 | 0.0001 | - | |
|
| 0.7463 | 21500 | 0.0001 | - | |
|
| 0.7480 | 21550 | 0.005 | - | |
|
| 0.7497 | 21600 | 0.0001 | - | |
|
| 0.7515 | 21650 | 0.0001 | - | |
|
| 0.7532 | 21700 | 0.0001 | - | |
|
| 0.7549 | 21750 | 0.0002 | - | |
|
| 0.7567 | 21800 | 0.0001 | - | |
|
| 0.7584 | 21850 | 0.0013 | - | |
|
| 0.7602 | 21900 | 0.0001 | - | |
|
| 0.7619 | 21950 | 0.0002 | - | |
|
| 0.7636 | 22000 | 0.0 | - | |
|
| 0.7654 | 22050 | 0.0001 | - | |
|
| 0.7671 | 22100 | 0.0002 | - | |
|
| 0.7688 | 22150 | 0.0001 | - | |
|
| 0.7706 | 22200 | 0.0002 | - | |
|
| 0.7723 | 22250 | 0.0001 | - | |
|
| 0.7740 | 22300 | 0.0001 | - | |
|
| 0.7758 | 22350 | 0.0002 | - | |
|
| 0.7775 | 22400 | 0.0001 | - | |
|
| 0.7792 | 22450 | 0.0013 | - | |
|
| 0.7810 | 22500 | 0.0001 | - | |
|
| 0.7827 | 22550 | 0.0002 | - | |
|
| 0.7844 | 22600 | 0.0002 | - | |
|
| 0.7862 | 22650 | 0.0069 | - | |
|
| 0.7879 | 22700 | 0.0001 | - | |
|
| 0.7897 | 22750 | 0.0001 | - | |
|
| 0.7914 | 22800 | 0.0001 | - | |
|
| 0.7931 | 22850 | 0.0001 | - | |
|
| 0.7949 | 22900 | 0.0001 | - | |
|
| 0.7966 | 22950 | 0.0001 | - | |
|
| 0.7983 | 23000 | 0.0001 | - | |
|
| 0.8001 | 23050 | 0.0002 | - | |
|
| 0.8018 | 23100 | 0.0001 | - | |
|
| 0.8035 | 23150 | 0.0001 | - | |
|
| 0.8053 | 23200 | 0.0001 | - | |
|
| 0.8070 | 23250 | 0.0001 | - | |
|
| 0.8087 | 23300 | 0.0001 | - | |
|
| 0.8105 | 23350 | 0.0001 | - | |
|
| 0.8122 | 23400 | 0.0027 | - | |
|
| 0.8140 | 23450 | 0.0001 | - | |
|
| 0.8157 | 23500 | 0.0001 | - | |
|
| 0.8174 | 23550 | 0.0027 | - | |
|
| 0.8192 | 23600 | 0.0002 | - | |
|
| 0.8209 | 23650 | 0.0002 | - | |
|
| 0.8226 | 23700 | 0.0001 | - | |
|
| 0.8244 | 23750 | 0.0003 | - | |
|
| 0.8261 | 23800 | 0.0001 | - | |
|
| 0.8278 | 23850 | 0.0001 | - | |
|
| 0.8296 | 23900 | 0.0001 | - | |
|
| 0.8313 | 23950 | 0.0001 | - | |
|
| 0.8330 | 24000 | 0.0014 | - | |
|
| 0.8348 | 24050 | 0.0083 | - | |
|
| 0.8365 | 24100 | 0.0001 | - | |
|
| 0.8383 | 24150 | 0.0001 | - | |
|
| 0.8400 | 24200 | 0.0001 | - | |
|
| 0.8417 | 24250 | 0.0001 | - | |
|
| 0.8435 | 24300 | 0.0001 | - | |
|
| 0.8452 | 24350 | 0.0001 | - | |
|
| 0.8469 | 24400 | 0.0 | - | |
|
| 0.8487 | 24450 | 0.0001 | - | |
|
| 0.8504 | 24500 | 0.0001 | - | |
|
| 0.8521 | 24550 | 0.022 | - | |
|
| 0.8539 | 24600 | 0.0001 | - | |
|
| 0.8556 | 24650 | 0.0001 | - | |
|
| 0.8573 | 24700 | 0.0003 | - | |
|
| 0.8591 | 24750 | 0.0001 | - | |
|
| 0.8608 | 24800 | 0.0002 | - | |
|
| 0.8625 | 24850 | 0.0001 | - | |
|
| 0.8643 | 24900 | 0.0001 | - | |
|
| 0.8660 | 24950 | 0.0001 | - | |
|
| 0.8678 | 25000 | 0.0002 | - | |
|
| 0.8695 | 25050 | 0.0001 | - | |
|
| 0.8712 | 25100 | 0.0001 | - | |
|
| 0.8730 | 25150 | 0.0001 | - | |
|
| 0.8747 | 25200 | 0.0001 | - | |
|
| 0.8764 | 25250 | 0.0007 | - | |
|
| 0.8782 | 25300 | 0.0001 | - | |
|
| 0.8799 | 25350 | 0.0001 | - | |
|
| 0.8816 | 25400 | 0.0002 | - | |
|
| 0.8834 | 25450 | 0.0001 | - | |
|
| 0.8851 | 25500 | 0.0001 | - | |
|
| 0.8868 | 25550 | 0.0001 | - | |
|
| 0.8886 | 25600 | 0.0006 | - | |
|
| 0.8903 | 25650 | 0.0003 | - | |
|
| 0.8921 | 25700 | 0.0001 | - | |
|
| 0.8938 | 25750 | 0.0002 | - | |
|
| 0.8955 | 25800 | 0.0001 | - | |
|
| 0.8973 | 25850 | 0.0001 | - | |
|
| 0.8990 | 25900 | 0.0015 | - | |
|
| 0.9007 | 25950 | 0.0005 | - | |
|
| 0.9025 | 26000 | 0.0001 | - | |
|
| 0.9042 | 26050 | 0.0056 | - | |
|
| 0.9059 | 26100 | 0.0001 | - | |
|
| 0.9077 | 26150 | 0.0001 | - | |
|
| 0.9094 | 26200 | 0.0001 | - | |
|
| 0.9111 | 26250 | 0.0001 | - | |
|
| 0.9129 | 26300 | 0.0001 | - | |
|
| 0.9146 | 26350 | 0.0001 | - | |
|
| 0.9163 | 26400 | 0.0002 | - | |
|
| 0.9181 | 26450 | 0.0001 | - | |
|
| 0.9198 | 26500 | 0.0003 | - | |
|
| 0.9216 | 26550 | 0.0001 | - | |
|
| 0.9233 | 26600 | 0.0001 | - | |
|
| 0.9250 | 26650 | 0.0002 | - | |
|
| 0.9268 | 26700 | 0.0001 | - | |
|
| 0.9285 | 26750 | 0.0002 | - | |
|
| 0.9302 | 26800 | 0.0001 | - | |
|
| 0.9320 | 26850 | 0.0002 | - | |
|
| 0.9337 | 26900 | 0.0001 | - | |
|
| 0.9354 | 26950 | 0.0001 | - | |
|
| 0.9372 | 27000 | 0.0001 | - | |
|
| 0.9389 | 27050 | 0.0001 | - | |
|
| 0.9406 | 27100 | 0.0001 | - | |
|
| 0.9424 | 27150 | 0.0001 | - | |
|
| 0.9441 | 27200 | 0.0001 | - | |
|
| 0.9459 | 27250 | 0.0001 | - | |
|
| 0.9476 | 27300 | 0.0001 | - | |
|
| 0.9493 | 27350 | 0.0001 | - | |
|
| 0.9511 | 27400 | 0.0001 | - | |
|
| 0.9528 | 27450 | 0.0001 | - | |
|
| 0.9545 | 27500 | 0.0001 | - | |
|
| 0.9563 | 27550 | 0.0035 | - | |
|
| 0.9580 | 27600 | 0.0001 | - | |
|
| 0.9597 | 27650 | 0.0002 | - | |
|
| 0.9615 | 27700 | 0.0001 | - | |
|
| 0.9632 | 27750 | 0.0001 | - | |
|
| 0.9649 | 27800 | 0.0001 | - | |
|
| 0.9667 | 27850 | 0.0002 | - | |
|
| 0.9684 | 27900 | 0.0 | - | |
|
| 0.9701 | 27950 | 0.0001 | - | |
|
| 0.9719 | 28000 | 0.0001 | - | |
|
| 0.9736 | 28050 | 0.0001 | - | |
|
| 0.9754 | 28100 | 0.0001 | - | |
|
| 0.9771 | 28150 | 0.0001 | - | |
|
| 0.9788 | 28200 | 0.0001 | - | |
|
| 0.9806 | 28250 | 0.0001 | - | |
|
| 0.9823 | 28300 | 0.0001 | - | |
|
| 0.9840 | 28350 | 0.0001 | - | |
|
| 0.9858 | 28400 | 0.0001 | - | |
|
| 0.9875 | 28450 | 0.0001 | - | |
|
| 0.9892 | 28500 | 0.0001 | - | |
|
| 0.9910 | 28550 | 0.0001 | - | |
|
| 0.9927 | 28600 | 0.0001 | - | |
|
| 0.9944 | 28650 | 0.0025 | - | |
|
| 0.9962 | 28700 | 0.0001 | - | |
|
| 0.9979 | 28750 | 0.0001 | - | |
|
| 0.9997 | 28800 | 0.0 | - | |
|
|
|
### Framework Versions |
|
- Python: 3.10.12 |
|
- SetFit: 1.0.3 |
|
- Sentence Transformers: 3.0.1 |
|
- Transformers: 4.39.0 |
|
- PyTorch: 2.3.0+cu121 |
|
- Datasets: 2.19.2 |
|
- Tokenizers: 0.15.2 |
|
|
|
## 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} |
|
} |
|
``` |
|
|
|
<!-- |
|
## Glossary |
|
|
|
*Clearly define terms in order to be accessible across audiences.* |
|
--> |
|
|
|
<!-- |
|
## Model Card Authors |
|
|
|
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
|
--> |
|
|
|
<!-- |
|
## Model Card Contact |
|
|
|
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
|
--> |
