Text Classification
setfit
Safetensors
sentence-transformers
xlm-roberta
generated_from_setfit_trainer
text-embeddings-inference
Instructions to use Methni/STEMO-SetFit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- setfit
How to use Methni/STEMO-SetFit with setfit:
from setfit import SetFitModel model = SetFitModel.from_pretrained("Methni/STEMO-SetFit") - sentence-transformers
How to use Methni/STEMO-SetFit with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Methni/STEMO-SetFit") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +10 -0
- README.md +672 -0
- config.json +29 -0
- config_sentence_transformers.json +14 -0
- config_setfit.json +11 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +61 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 768,
|
| 3 |
+
"pooling_mode_cls_token": false,
|
| 4 |
+
"pooling_mode_mean_tokens": true,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,672 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- setfit
|
| 4 |
+
- sentence-transformers
|
| 5 |
+
- text-classification
|
| 6 |
+
- generated_from_setfit_trainer
|
| 7 |
+
widget:
|
| 8 |
+
- text: Really @chirjathya බිය නොවන්න. මා අනුගමනය කරන්න.
|
| 9 |
+
- text: සිහිනයක් පමනකැයි සිතන්නද බිය වුනුපතිනියක වී සැරසිලාහද බැඳි කුමරු ගෙට යන්නට
|
| 10 |
+
මහ හුගක් ආශාවල්ඇතිය ලඟ සියල් සොඳුරු පැතුමන්කඩාවැටුනත් දෙපා මුලඅහිංසකාවියේ මහ දෙය|K|
|
| 11 |
+
pic.twitter.com/1w1nwGWXQC
|
| 12 |
+
- text: அய்யா உங்களை விட அவரை நன்கு அறிந்தவர் இருக்கமுடியாது. அவர்களின் மறைவு உங்களுக்கு
|
| 13 |
+
பெரிய மனவேதனை தரும் அவர்களின் என்பதில் ஐயம் இல்லை.
|
| 14 |
+
- text: '@Helayaa_max @gihan_ddde_alwis හිත හදාාාගන්නෙමීදුක දරාගන්නෙමී:face_with_tears_of_joy::face_with_tears_of_joy::face_with_tears_of_joy:'
|
| 15 |
+
- text: බලන්න මේ චුටි පැටියා ට අධික විදිය (සංවේදී කිසිම කෝපය මේක බලන්න එපා ගහන කෙනක්
|
| 16 |
+
තියන අයත් බලන්න
|
| 17 |
+
metrics:
|
| 18 |
+
- accuracy
|
| 19 |
+
pipeline_tag: text-classification
|
| 20 |
+
library_name: setfit
|
| 21 |
+
inference: true
|
| 22 |
+
base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
# SetFit with sentence-transformers/paraphrase-multilingual-mpnet-base-v2
|
| 26 |
+
|
| 27 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-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.
|
| 28 |
+
|
| 29 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
| 30 |
+
|
| 31 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
| 32 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
| 33 |
+
|
| 34 |
+
## Model Details
|
| 35 |
+
|
| 36 |
+
### Model Description
|
| 37 |
+
- **Model Type:** SetFit
|
| 38 |
+
- **Sentence Transformer body:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2)
|
| 39 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
| 40 |
+
- **Maximum Sequence Length:** 128 tokens
|
| 41 |
+
- **Number of Classes:** 6 classes
|
| 42 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 43 |
+
<!-- - **Language:** Unknown -->
|
| 44 |
+
<!-- - **License:** Unknown -->
|
| 45 |
+
|
| 46 |
+
### Model Sources
|
| 47 |
+
|
| 48 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
| 49 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
| 50 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 51 |
+
|
| 52 |
+
### Model Labels
|
| 53 |
+
| Label | Examples |
|
| 54 |
+
|:---------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 55 |
+
| Happy | <ul><li>'Thanks For Tune In .අද ඇත්තටම සතුටු දවසක් :France: :grinning_face_with_big_eyes:.විකාශනයේ නිමාව! බායි …'</li><li>'@nwty_ck @imasha_fernando කොහොම හරි කමක් නෑ. සෙට් වෙන විදියකට ආතල් එකේ ඉන්නයි ඕන. හෙට මැරුනත් දුක නැති විදියකට.:smiling_face_with_smiling_eyes::smiling_face_with_smiling_eyes::smiling_face_with_smiling_eyes::smiling_face_with_smiling_eyes:'</li><li>'@Soulchild_Rishi සතුටු වෙන්න ඔනෙනෙ එහෙම හරි නාන්න වෙන එක ගැන..'</li></ul> |
|
| 56 |
+
| Anger | <ul><li>'හදිසි\u200d කෝපය මරු කැදවයි..ඊයේ (09) රාත්\u200dරී කතරගම, කඳසුරිගම ප්\u200dරදේශයේ පුද්ගලයෙකු බිරිඳට තියුණු ආයුධයකින් පහරදී...'</li><li>'@dinu_nilmini @itzJambole ඔහොම ද මෙච්චර කරපු අක්කාට සලකන්නේ දුක හිතුණා ජම්බෝලස් ඒකට නම් :loudly_crying_face::loudly_crying_face::loudly_crying_face::loudly_crying_face::loudly_crying_face:'</li><li>'ඉක්මන් කෝපය...'</li></ul> |
|
| 57 |
+
| Sadness | <ul><li>'@IamHisAnchor සමාව දෙන්න..එපා තියාගන්න:worried_face: දුක..'</li><li>'@otaradel you just looked at the picture and didnt read the caption සියලු සතුන්ට වේදනාව, දුක හා මරණ බිය දැනෙයි.සියලු සතුන්ට කරුණාවන්ත වෙමු.#LiveKind #BeKind #AllLivesMatter'</li><li>'බෑ මෙහෙම විඳගන්න තනියෙන් දුක හිර කරන්මට හරිම පාළුයි මගෙ රත්තරං:shushing_face::face_with_crossed-out_eyes::astonished_face::astonished_face::astonished_face::man_gesturing_OK:'</li></ul> |
|
| 58 |
+
| Fear | <ul><li>'‘වියත් මග’ කිසියම් රැස්වීමක් ෂැංග්\u200dරිලා හෝටලයේ තිබුණා ය කියා ලංකාවට ඒකාධිපතියකු ආවොත් මාර ආතල් එකක් ලැබේ ය කියා සිතන අය උෂාර් වී සිටින අතර, ගෝඨාභය රාජපක්ෂ ජනාධිපති වුණොත් ලංකාව මිනී කනත්තක් වේ යයි සිතෙන අයට අධික බිය ඇති වී ගුද මාර්ගය හීන් වී ඇත.'</li><li>'අදත් රෑ වෙනකං යාළුවො ඇවිත් කතා කරල යාවි. හෙටත් අනිද්දත්. හත්දවසෙ දානෙ ඉවරවෙනකං. සුදු කොඩි දාපු ඩීපි වෙනස් වේවි. ඉන්පස්සෙ උඹේ දුක බලන්න කවුරුත් නැතිවේවි.'</li><li>'කශ්ශපගෙ බය සීගිරිය උනා..අට වෙනි පුදුමය එයම උනා.. බයෙන් බයෙන් thrill ගත් රට මේකද.. #sajje'</li></ul> |
|
| 59 |
+
| Surprise | <ul><li>'වෙන එකෙක්ට මෙහෙම උනානම් දුකක් නෑ Charith Thambavita ..:face_with_tears_of_joy: පවුල් පිටින් දඩ අලි වෙච්ච උබටම මේක උනු එකයි මට දුක.. අවුලක් නෑ අවුරුද්දකට සැරයක් ජාත්\u200dයන්තරේ ජයගන්න එක උබේ හැකියාවනේ.. ට්\u200dරිප් එක ඉවර කරලා ඉක්මනට වරෙන් සහෝදරයා... …'</li><li>'ඔබ පුදුමය පත් වන දෙයක් සිතුවාද ? කැනඩාවේ හිටපු ආරක්ෂක අමාත්\u200dය Paul Hellyer විසින් හෙළි කර තිබෙනවා “ වසර දහස් ගණන්...'</li><li>'ලොව 8 වෙනි පුදුමය නැවත සොයාගනියි, එය අතුරුදහන් වුනේ වසර 131 පෙරයි - 8th ... via @YouTube'</li></ul> |
|
| 60 |
+
| Disgust | <ul><li>'@NightWingzzz අප්\u200dරසන්නයි නේ!'</li><li>'@nirowa74 :grinning_face::grinning_face::grinning_face:ඒ විතරක් නෙමේ අයියෙ ඔය සේරමත් කරලා සිංහලයයි බෞද්ධාගමත් මේ රටෙන් තුරන් කරපු දවසට ඔය හිටං තවත් සතුටු වෙයි'</li><li>'@යහපාලන ආණ්ඩුවේ @officialunp වුර්තිය සමිති යොදා අප්\u200dරසන්න වීගෙන ආණ්ඩු විරෝධය වෙනස් කිරීමේ පහත් ක්\u200dරියාවලියක කුමන්ත��\u200dරණකාරී වැඩපිළිවෙලක් නොවේද මේ. තමන්ගේම ජාතික සේවක සංගමයට පොලිසිය යොදා පහර දීම විහිළුවක් නොවේද? … #SriLanka #SriLankan @Neetwit @sajithpremadasa pic.twitter.com/6PPPLk5t4s'</li></ul> |
|
| 61 |
+
|
| 62 |
+
## Uses
|
| 63 |
+
|
| 64 |
+
### Direct Use for Inference
|
| 65 |
+
|
| 66 |
+
First install the SetFit library:
|
| 67 |
+
|
| 68 |
+
```bash
|
| 69 |
+
pip install setfit
|
| 70 |
+
```
|
| 71 |
+
|
| 72 |
+
Then you can load this model and run inference.
|
| 73 |
+
|
| 74 |
+
```python
|
| 75 |
+
from setfit import SetFitModel
|
| 76 |
+
|
| 77 |
+
# Download from the 🤗 Hub
|
| 78 |
+
model = SetFitModel.from_pretrained("setfit_model_id")
|
| 79 |
+
# Run inference
|
| 80 |
+
preds = model("Really @chirjathya බිය නොවන්න. මා අනුගමනය කරන්න.")
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
<!--
|
| 84 |
+
### Downstream Use
|
| 85 |
+
|
| 86 |
+
*List how someone could finetune this model on their own dataset.*
|
| 87 |
+
-->
|
| 88 |
+
|
| 89 |
+
<!--
|
| 90 |
+
### Out-of-Scope Use
|
| 91 |
+
|
| 92 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 93 |
+
-->
|
| 94 |
+
|
| 95 |
+
<!--
|
| 96 |
+
## Bias, Risks and Limitations
|
| 97 |
+
|
| 98 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 99 |
+
-->
|
| 100 |
+
|
| 101 |
+
<!--
|
| 102 |
+
### Recommendations
|
| 103 |
+
|
| 104 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 105 |
+
-->
|
| 106 |
+
|
| 107 |
+
## Training Details
|
| 108 |
+
|
| 109 |
+
### Training Set Metrics
|
| 110 |
+
| Training set | Min | Median | Max |
|
| 111 |
+
|:-------------|:----|:--------|:----|
|
| 112 |
+
| Word count | 1 | 16.2605 | 53 |
|
| 113 |
+
|
| 114 |
+
| Label | Training Sample Count |
|
| 115 |
+
|:---------|:----------------------|
|
| 116 |
+
| Happy | 1610 |
|
| 117 |
+
| Anger | 1610 |
|
| 118 |
+
| Sadness | 1610 |
|
| 119 |
+
| Fear | 1610 |
|
| 120 |
+
| Surprise | 1610 |
|
| 121 |
+
| Disgust | 1610 |
|
| 122 |
+
|
| 123 |
+
### Training Hyperparameters
|
| 124 |
+
- batch_size: (16, 16)
|
| 125 |
+
- num_epochs: (1, 1)
|
| 126 |
+
- max_steps: -1
|
| 127 |
+
- sampling_strategy: oversampling
|
| 128 |
+
- num_iterations: 20
|
| 129 |
+
- body_learning_rate: (1e-05, 1e-05)
|
| 130 |
+
- head_learning_rate: 0.01
|
| 131 |
+
- loss: CosineSimilarityLoss
|
| 132 |
+
- distance_metric: cosine_distance
|
| 133 |
+
- margin: 0.25
|
| 134 |
+
- end_to_end: False
|
| 135 |
+
- use_amp: False
|
| 136 |
+
- warmup_proportion: 0.1
|
| 137 |
+
- l2_weight: 0.01
|
| 138 |
+
- seed: 42
|
| 139 |
+
- evaluation_strategy: epoch
|
| 140 |
+
- eval_max_steps: -1
|
| 141 |
+
- load_best_model_at_end: True
|
| 142 |
+
|
| 143 |
+
### Training Results
|
| 144 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
| 145 |
+
|:------:|:-----:|:-------------:|:---------------:|
|
| 146 |
+
| 0.0000 | 1 | 0.2776 | - |
|
| 147 |
+
| 0.0021 | 50 | 0.2549 | - |
|
| 148 |
+
| 0.0041 | 100 | 0.2624 | - |
|
| 149 |
+
| 0.0062 | 150 | 0.2501 | - |
|
| 150 |
+
| 0.0083 | 200 | 0.2594 | - |
|
| 151 |
+
| 0.0104 | 250 | 0.2484 | - |
|
| 152 |
+
| 0.0124 | 300 | 0.259 | - |
|
| 153 |
+
| 0.0145 | 350 | 0.2403 | - |
|
| 154 |
+
| 0.0166 | 400 | 0.2257 | - |
|
| 155 |
+
| 0.0186 | 450 | 0.2218 | - |
|
| 156 |
+
| 0.0207 | 500 | 0.2148 | - |
|
| 157 |
+
| 0.0228 | 550 | 0.2021 | - |
|
| 158 |
+
| 0.0248 | 600 | 0.1823 | - |
|
| 159 |
+
| 0.0269 | 650 | 0.1759 | - |
|
| 160 |
+
| 0.0290 | 700 | 0.1682 | - |
|
| 161 |
+
| 0.0311 | 750 | 0.1668 | - |
|
| 162 |
+
| 0.0331 | 800 | 0.1527 | - |
|
| 163 |
+
| 0.0352 | 850 | 0.1353 | - |
|
| 164 |
+
| 0.0373 | 900 | 0.1293 | - |
|
| 165 |
+
| 0.0393 | 950 | 0.1169 | - |
|
| 166 |
+
| 0.0414 | 1000 | 0.1125 | - |
|
| 167 |
+
| 0.0435 | 1050 | 0.1137 | - |
|
| 168 |
+
| 0.0455 | 1100 | 0.1081 | - |
|
| 169 |
+
| 0.0476 | 1150 | 0.0986 | - |
|
| 170 |
+
| 0.0497 | 1200 | 0.089 | - |
|
| 171 |
+
| 0.0518 | 1250 | 0.0808 | - |
|
| 172 |
+
| 0.0538 | 1300 | 0.0735 | - |
|
| 173 |
+
| 0.0559 | 1350 | 0.0753 | - |
|
| 174 |
+
| 0.0580 | 1400 | 0.0751 | - |
|
| 175 |
+
| 0.0600 | 1450 | 0.064 | - |
|
| 176 |
+
| 0.0621 | 1500 | 0.0674 | - |
|
| 177 |
+
| 0.0642 | 1550 | 0.0521 | - |
|
| 178 |
+
| 0.0663 | 1600 | 0.0438 | - |
|
| 179 |
+
| 0.0683 | 1650 | 0.0406 | - |
|
| 180 |
+
| 0.0704 | 1700 | 0.0347 | - |
|
| 181 |
+
| 0.0725 | 1750 | 0.028 | - |
|
| 182 |
+
| 0.0745 | 1800 | 0.0251 | - |
|
| 183 |
+
| 0.0766 | 1850 | 0.0376 | - |
|
| 184 |
+
| 0.0787 | 1900 | 0.0265 | - |
|
| 185 |
+
| 0.0807 | 1950 | 0.0294 | - |
|
| 186 |
+
| 0.0828 | 2000 | 0.0203 | - |
|
| 187 |
+
| 0.0849 | 2050 | 0.021 | - |
|
| 188 |
+
| 0.0870 | 2100 | 0.018 | - |
|
| 189 |
+
| 0.0890 | 2150 | 0.0171 | - |
|
| 190 |
+
| 0.0911 | 2200 | 0.01 | - |
|
| 191 |
+
| 0.0932 | 2250 | 0.0108 | - |
|
| 192 |
+
| 0.0952 | 2300 | 0.0092 | - |
|
| 193 |
+
| 0.0973 | 2350 | 0.0079 | - |
|
| 194 |
+
| 0.0994 | 2400 | 0.0107 | - |
|
| 195 |
+
| 0.1014 | 2450 | 0.016 | - |
|
| 196 |
+
| 0.1035 | 2500 | 0.01 | - |
|
| 197 |
+
| 0.1056 | 2550 | 0.0041 | - |
|
| 198 |
+
| 0.1077 | 2600 | 0.0071 | - |
|
| 199 |
+
| 0.1097 | 2650 | 0.0103 | - |
|
| 200 |
+
| 0.1118 | 2700 | 0.0067 | - |
|
| 201 |
+
| 0.1139 | 2750 | 0.0062 | - |
|
| 202 |
+
| 0.1159 | 2800 | 0.0071 | - |
|
| 203 |
+
| 0.1180 | 2850 | 0.0064 | - |
|
| 204 |
+
| 0.1201 | 2900 | 0.0089 | - |
|
| 205 |
+
| 0.1222 | 2950 | 0.0065 | - |
|
| 206 |
+
| 0.1242 | 3000 | 0.0031 | - |
|
| 207 |
+
| 0.1263 | 3050 | 0.0038 | - |
|
| 208 |
+
| 0.1284 | 3100 | 0.005 | - |
|
| 209 |
+
| 0.1304 | 3150 | 0.0038 | - |
|
| 210 |
+
| 0.1325 | 3200 | 0.0077 | - |
|
| 211 |
+
| 0.1346 | 3250 | 0.0022 | - |
|
| 212 |
+
| 0.1366 | 3300 | 0.0022 | - |
|
| 213 |
+
| 0.1387 | 3350 | 0.0008 | - |
|
| 214 |
+
| 0.1408 | 3400 | 0.0047 | - |
|
| 215 |
+
| 0.1429 | 3450 | 0.0024 | - |
|
| 216 |
+
| 0.1449 | 3500 | 0.0062 | - |
|
| 217 |
+
| 0.1470 | 3550 | 0.0038 | - |
|
| 218 |
+
| 0.1491 | 3600 | 0.0016 | - |
|
| 219 |
+
| 0.1511 | 3650 | 0.0011 | - |
|
| 220 |
+
| 0.1532 | 3700 | 0.0026 | - |
|
| 221 |
+
| 0.1553 | 3750 | 0.0005 | - |
|
| 222 |
+
| 0.1573 | 3800 | 0.002 | - |
|
| 223 |
+
| 0.1594 | 3850 | 0.0007 | - |
|
| 224 |
+
| 0.1615 | 3900 | 0.0003 | - |
|
| 225 |
+
| 0.1636 | 3950 | 0.0038 | - |
|
| 226 |
+
| 0.1656 | 4000 | 0.0042 | - |
|
| 227 |
+
| 0.1677 | 4050 | 0.0028 | - |
|
| 228 |
+
| 0.1698 | 4100 | 0.0021 | - |
|
| 229 |
+
| 0.1718 | 4150 | 0.0005 | - |
|
| 230 |
+
| 0.1739 | 4200 | 0.0003 | - |
|
| 231 |
+
| 0.1760 | 4250 | 0.0032 | - |
|
| 232 |
+
| 0.1781 | 4300 | 0.0018 | - |
|
| 233 |
+
| 0.1801 | 4350 | 0.0012 | - |
|
| 234 |
+
| 0.1822 | 4400 | 0.0023 | - |
|
| 235 |
+
| 0.1843 | 4450 | 0.0013 | - |
|
| 236 |
+
| 0.1863 | 4500 | 0.0028 | - |
|
| 237 |
+
| 0.1884 | 4550 | 0.0025 | - |
|
| 238 |
+
| 0.1905 | 4600 | 0.0029 | - |
|
| 239 |
+
| 0.1925 | 4650 | 0.0052 | - |
|
| 240 |
+
| 0.1946 | 4700 | 0.0007 | - |
|
| 241 |
+
| 0.1967 | 4750 | 0.0059 | - |
|
| 242 |
+
| 0.1988 | 4800 | 0.002 | - |
|
| 243 |
+
| 0.2008 | 4850 | 0.0029 | - |
|
| 244 |
+
| 0.2029 | 4900 | 0.0028 | - |
|
| 245 |
+
| 0.2050 | 4950 | 0.0017 | - |
|
| 246 |
+
| 0.2070 | 5000 | 0.0025 | - |
|
| 247 |
+
| 0.2091 | 5050 | 0.0031 | - |
|
| 248 |
+
| 0.2112 | 5100 | 0.0026 | - |
|
| 249 |
+
| 0.2133 | 5150 | 0.0013 | - |
|
| 250 |
+
| 0.2153 | 5200 | 0.0012 | - |
|
| 251 |
+
| 0.2174 | 5250 | 0.0023 | - |
|
| 252 |
+
| 0.2195 | 5300 | 0.0001 | - |
|
| 253 |
+
| 0.2215 | 5350 | 0.0018 | - |
|
| 254 |
+
| 0.2236 | 5400 | 0.0013 | - |
|
| 255 |
+
| 0.2257 | 5450 | 0.0034 | - |
|
| 256 |
+
| 0.2277 | 5500 | 0.005 | - |
|
| 257 |
+
| 0.2298 | 5550 | 0.0012 | - |
|
| 258 |
+
| 0.2319 | 5600 | 0.0017 | - |
|
| 259 |
+
| 0.2340 | 5650 | 0.0019 | - |
|
| 260 |
+
| 0.2360 | 5700 | 0.0028 | - |
|
| 261 |
+
| 0.2381 | 5750 | 0.0013 | - |
|
| 262 |
+
| 0.2402 | 5800 | 0.0025 | - |
|
| 263 |
+
| 0.2422 | 5850 | 0.001 | - |
|
| 264 |
+
| 0.2443 | 5900 | 0.0019 | - |
|
| 265 |
+
| 0.2464 | 5950 | 0.0036 | - |
|
| 266 |
+
| 0.2484 | 6000 | 0.0004 | - |
|
| 267 |
+
| 0.2505 | 6050 | 0.0013 | - |
|
| 268 |
+
| 0.2526 | 6100 | 0.003 | - |
|
| 269 |
+
| 0.2547 | 6150 | 0.0016 | - |
|
| 270 |
+
| 0.2567 | 6200 | 0.0001 | - |
|
| 271 |
+
| 0.2588 | 6250 | 0.0021 | - |
|
| 272 |
+
| 0.2609 | 6300 | 0.0017 | - |
|
| 273 |
+
| 0.2629 | 6350 | 0.0033 | - |
|
| 274 |
+
| 0.2650 | 6400 | 0.0005 | - |
|
| 275 |
+
| 0.2671 | 6450 | 0.0025 | - |
|
| 276 |
+
| 0.2692 | 6500 | 0.0056 | - |
|
| 277 |
+
| 0.2712 | 6550 | 0.0039 | - |
|
| 278 |
+
| 0.2733 | 6600 | 0.0002 | - |
|
| 279 |
+
| 0.2754 | 6650 | 0.0025 | - |
|
| 280 |
+
| 0.2774 | 6700 | 0.0005 | - |
|
| 281 |
+
| 0.2795 | 6750 | 0.0002 | - |
|
| 282 |
+
| 0.2816 | 6800 | 0.0011 | - |
|
| 283 |
+
| 0.2836 | 6850 | 0.0007 | - |
|
| 284 |
+
| 0.2857 | 6900 | 0.0014 | - |
|
| 285 |
+
| 0.2878 | 6950 | 0.0021 | - |
|
| 286 |
+
| 0.2899 | 7000 | 0.0002 | - |
|
| 287 |
+
| 0.2919 | 7050 | 0.0039 | - |
|
| 288 |
+
| 0.2940 | 7100 | 0.0013 | - |
|
| 289 |
+
| 0.2961 | 7150 | 0.0001 | - |
|
| 290 |
+
| 0.2981 | 7200 | 0.0017 | - |
|
| 291 |
+
| 0.3002 | 7250 | 0.0036 | - |
|
| 292 |
+
| 0.3023 | 7300 | 0.0017 | - |
|
| 293 |
+
| 0.3043 | 7350 | 0.0025 | - |
|
| 294 |
+
| 0.3064 | 7400 | 0.0015 | - |
|
| 295 |
+
| 0.3085 | 7450 | 0.003 | - |
|
| 296 |
+
| 0.3106 | 7500 | 0.0015 | - |
|
| 297 |
+
| 0.3126 | 7550 | 0.0002 | - |
|
| 298 |
+
| 0.3147 | 7600 | 0.003 | - |
|
| 299 |
+
| 0.3168 | 7650 | 0.0003 | - |
|
| 300 |
+
| 0.3188 | 7700 | 0.0001 | - |
|
| 301 |
+
| 0.3209 | 7750 | 0.0005 | - |
|
| 302 |
+
| 0.3230 | 7800 | 0.0007 | - |
|
| 303 |
+
| 0.3251 | 7850 | 0.0014 | - |
|
| 304 |
+
| 0.3271 | 7900 | 0.0013 | - |
|
| 305 |
+
| 0.3292 | 7950 | 0.0 | - |
|
| 306 |
+
| 0.3313 | 8000 | 0.0013 | - |
|
| 307 |
+
| 0.3333 | 8050 | 0.0002 | - |
|
| 308 |
+
| 0.3354 | 8100 | 0.0 | - |
|
| 309 |
+
| 0.3375 | 8150 | 0.0 | - |
|
| 310 |
+
| 0.3395 | 8200 | 0.0 | - |
|
| 311 |
+
| 0.3416 | 8250 | 0.0012 | - |
|
| 312 |
+
| 0.3437 | 8300 | 0.0001 | - |
|
| 313 |
+
| 0.3458 | 8350 | 0.0002 | - |
|
| 314 |
+
| 0.3478 | 8400 | 0.0038 | - |
|
| 315 |
+
| 0.3499 | 8450 | 0.0013 | - |
|
| 316 |
+
| 0.3520 | 8500 | 0.0014 | - |
|
| 317 |
+
| 0.3540 | 8550 | 0.0015 | - |
|
| 318 |
+
| 0.3561 | 8600 | 0.002 | - |
|
| 319 |
+
| 0.3582 | 8650 | 0.0001 | - |
|
| 320 |
+
| 0.3602 | 8700 | 0.0006 | - |
|
| 321 |
+
| 0.3623 | 8750 | 0.0031 | - |
|
| 322 |
+
| 0.3644 | 8800 | 0.0005 | - |
|
| 323 |
+
| 0.3665 | 8850 | 0.0004 | - |
|
| 324 |
+
| 0.3685 | 8900 | 0.0007 | - |
|
| 325 |
+
| 0.3706 | 8950 | 0.0024 | - |
|
| 326 |
+
| 0.3727 | 9000 | 0.0004 | - |
|
| 327 |
+
| 0.3747 | 9050 | 0.001 | - |
|
| 328 |
+
| 0.3768 | 9100 | 0.0001 | - |
|
| 329 |
+
| 0.3789 | 9150 | 0.0022 | - |
|
| 330 |
+
| 0.3810 | 9200 | 0.0013 | - |
|
| 331 |
+
| 0.3830 | 9250 | 0.0013 | - |
|
| 332 |
+
| 0.3851 | 9300 | 0.0031 | - |
|
| 333 |
+
| 0.3872 | 9350 | 0.0032 | - |
|
| 334 |
+
| 0.3892 | 9400 | 0.0005 | - |
|
| 335 |
+
| 0.3913 | 9450 | 0.0002 | - |
|
| 336 |
+
| 0.3934 | 9500 | 0.0 | - |
|
| 337 |
+
| 0.3954 | 9550 | 0.0004 | - |
|
| 338 |
+
| 0.3975 | 9600 | 0.0012 | - |
|
| 339 |
+
| 0.3996 | 9650 | 0.0011 | - |
|
| 340 |
+
| 0.4017 | 9700 | 0.0001 | - |
|
| 341 |
+
| 0.4037 | 9750 | 0.002 | - |
|
| 342 |
+
| 0.4058 | 9800 | 0.0015 | - |
|
| 343 |
+
| 0.4079 | 9850 | 0.0012 | - |
|
| 344 |
+
| 0.4099 | 9900 | 0.0018 | - |
|
| 345 |
+
| 0.4120 | 9950 | 0.0001 | - |
|
| 346 |
+
| 0.4141 | 10000 | 0.0002 | - |
|
| 347 |
+
| 0.4161 | 10050 | 0.0013 | - |
|
| 348 |
+
| 0.4182 | 10100 | 0.0017 | - |
|
| 349 |
+
| 0.4203 | 10150 | 0.001 | - |
|
| 350 |
+
| 0.4224 | 10200 | 0.0001 | - |
|
| 351 |
+
| 0.4244 | 10250 | 0.0001 | - |
|
| 352 |
+
| 0.4265 | 10300 | 0.0014 | - |
|
| 353 |
+
| 0.4286 | 10350 | 0.0001 | - |
|
| 354 |
+
| 0.4306 | 10400 | 0.001 | - |
|
| 355 |
+
| 0.4327 | 10450 | 0.0008 | - |
|
| 356 |
+
| 0.4348 | 10500 | 0.0004 | - |
|
| 357 |
+
| 0.4369 | 10550 | 0.0003 | - |
|
| 358 |
+
| 0.4389 | 10600 | 0.0012 | - |
|
| 359 |
+
| 0.4410 | 10650 | 0.0007 | - |
|
| 360 |
+
| 0.4431 | 10700 | 0.0 | - |
|
| 361 |
+
| 0.4451 | 10750 | 0.0 | - |
|
| 362 |
+
| 0.4472 | 10800 | 0.0004 | - |
|
| 363 |
+
| 0.4493 | 10850 | 0.0001 | - |
|
| 364 |
+
| 0.4513 | 10900 | 0.0 | - |
|
| 365 |
+
| 0.4534 | 10950 | 0.0004 | - |
|
| 366 |
+
| 0.4555 | 11000 | 0.0013 | - |
|
| 367 |
+
| 0.4576 | 11050 | 0.0 | - |
|
| 368 |
+
| 0.4596 | 11100 | 0.0016 | - |
|
| 369 |
+
| 0.4617 | 11150 | 0.0 | - |
|
| 370 |
+
| 0.4638 | 11200 | 0.0002 | - |
|
| 371 |
+
| 0.4658 | 11250 | 0.0011 | - |
|
| 372 |
+
| 0.4679 | 11300 | 0.0004 | - |
|
| 373 |
+
| 0.4700 | 11350 | 0.0009 | - |
|
| 374 |
+
| 0.4720 | 11400 | 0.0 | - |
|
| 375 |
+
| 0.4741 | 11450 | 0.0014 | - |
|
| 376 |
+
| 0.4762 | 11500 | 0.001 | - |
|
| 377 |
+
| 0.4783 | 11550 | 0.0028 | - |
|
| 378 |
+
| 0.4803 | 11600 | 0.0001 | - |
|
| 379 |
+
| 0.4824 | 11650 | 0.0009 | - |
|
| 380 |
+
| 0.4845 | 11700 | 0.0035 | - |
|
| 381 |
+
| 0.4865 | 11750 | 0.0002 | - |
|
| 382 |
+
| 0.4886 | 11800 | 0.0001 | - |
|
| 383 |
+
| 0.4907 | 11850 | 0.0 | - |
|
| 384 |
+
| 0.4928 | 11900 | 0.0001 | - |
|
| 385 |
+
| 0.4948 | 11950 | 0.0 | - |
|
| 386 |
+
| 0.4969 | 12000 | 0.0 | - |
|
| 387 |
+
| 0.4990 | 12050 | 0.0 | - |
|
| 388 |
+
| 0.5010 | 12100 | 0.0 | - |
|
| 389 |
+
| 0.5031 | 12150 | 0.0 | - |
|
| 390 |
+
| 0.5052 | 12200 | 0.0 | - |
|
| 391 |
+
| 0.5072 | 12250 | 0.0 | - |
|
| 392 |
+
| 0.5093 | 12300 | 0.0 | - |
|
| 393 |
+
| 0.5114 | 12350 | 0.0 | - |
|
| 394 |
+
| 0.5135 | 12400 | 0.0 | - |
|
| 395 |
+
| 0.5155 | 12450 | 0.0003 | - |
|
| 396 |
+
| 0.5176 | 12500 | 0.0008 | - |
|
| 397 |
+
| 0.5197 | 12550 | 0.0 | - |
|
| 398 |
+
| 0.5217 | 12600 | 0.0031 | - |
|
| 399 |
+
| 0.5238 | 12650 | 0.0001 | - |
|
| 400 |
+
| 0.5259 | 12700 | 0.0 | - |
|
| 401 |
+
| 0.5280 | 12750 | 0.0 | - |
|
| 402 |
+
| 0.5300 | 12800 | 0.0 | - |
|
| 403 |
+
| 0.5321 | 12850 | 0.0 | - |
|
| 404 |
+
| 0.5342 | 12900 | 0.0 | - |
|
| 405 |
+
| 0.5362 | 12950 | 0.0005 | - |
|
| 406 |
+
| 0.5383 | 13000 | 0.0 | - |
|
| 407 |
+
| 0.5404 | 13050 | 0.0 | - |
|
| 408 |
+
| 0.5424 | 13100 | 0.0 | - |
|
| 409 |
+
| 0.5445 | 13150 | 0.0 | - |
|
| 410 |
+
| 0.5466 | 13200 | 0.0 | - |
|
| 411 |
+
| 0.5487 | 13250 | 0.0 | - |
|
| 412 |
+
| 0.5507 | 13300 | 0.0 | - |
|
| 413 |
+
| 0.5528 | 13350 | 0.0003 | - |
|
| 414 |
+
| 0.5549 | 13400 | 0.0002 | - |
|
| 415 |
+
| 0.5569 | 13450 | 0.0018 | - |
|
| 416 |
+
| 0.5590 | 13500 | 0.0 | - |
|
| 417 |
+
| 0.5611 | 13550 | 0.0 | - |
|
| 418 |
+
| 0.5631 | 13600 | 0.0011 | - |
|
| 419 |
+
| 0.5652 | 13650 | 0.0017 | - |
|
| 420 |
+
| 0.5673 | 13700 | 0.0001 | - |
|
| 421 |
+
| 0.5694 | 13750 | 0.0008 | - |
|
| 422 |
+
| 0.5714 | 13800 | 0.0001 | - |
|
| 423 |
+
| 0.5735 | 13850 | 0.0007 | - |
|
| 424 |
+
| 0.5756 | 13900 | 0.0 | - |
|
| 425 |
+
| 0.5776 | 13950 | 0.0001 | - |
|
| 426 |
+
| 0.5797 | 14000 | 0.0 | - |
|
| 427 |
+
| 0.5818 | 14050 | 0.0 | - |
|
| 428 |
+
| 0.5839 | 14100 | 0.0001 | - |
|
| 429 |
+
| 0.5859 | 14150 | 0.0005 | - |
|
| 430 |
+
| 0.5880 | 14200 | 0.0011 | - |
|
| 431 |
+
| 0.5901 | 14250 | 0.0 | - |
|
| 432 |
+
| 0.5921 | 14300 | 0.0 | - |
|
| 433 |
+
| 0.5942 | 14350 | 0.0 | - |
|
| 434 |
+
| 0.5963 | 14400 | 0.0 | - |
|
| 435 |
+
| 0.5983 | 14450 | 0.0 | - |
|
| 436 |
+
| 0.6004 | 14500 | 0.0 | - |
|
| 437 |
+
| 0.6025 | 14550 | 0.0 | - |
|
| 438 |
+
| 0.6046 | 14600 | 0.0 | - |
|
| 439 |
+
| 0.6066 | 14650 | 0.0 | - |
|
| 440 |
+
| 0.6087 | 14700 | 0.0 | - |
|
| 441 |
+
| 0.6108 | 14750 | 0.0 | - |
|
| 442 |
+
| 0.6128 | 14800 | 0.0008 | - |
|
| 443 |
+
| 0.6149 | 14850 | 0.0006 | - |
|
| 444 |
+
| 0.6170 | 14900 | 0.0003 | - |
|
| 445 |
+
| 0.6190 | 14950 | 0.0 | - |
|
| 446 |
+
| 0.6211 | 15000 | 0.0 | - |
|
| 447 |
+
| 0.6232 | 15050 | 0.0 | - |
|
| 448 |
+
| 0.6253 | 15100 | 0.0 | - |
|
| 449 |
+
| 0.6273 | 15150 | 0.0 | - |
|
| 450 |
+
| 0.6294 | 15200 | 0.0 | - |
|
| 451 |
+
| 0.6315 | 15250 | 0.0 | - |
|
| 452 |
+
| 0.6335 | 15300 | 0.0 | - |
|
| 453 |
+
| 0.6356 | 15350 | 0.0 | - |
|
| 454 |
+
| 0.6377 | 15400 | 0.0 | - |
|
| 455 |
+
| 0.6398 | 15450 | 0.0004 | - |
|
| 456 |
+
| 0.6418 | 15500 | 0.0 | - |
|
| 457 |
+
| 0.6439 | 15550 | 0.0004 | - |
|
| 458 |
+
| 0.6460 | 15600 | 0.0 | - |
|
| 459 |
+
| 0.6480 | 15650 | 0.0 | - |
|
| 460 |
+
| 0.6501 | 15700 | 0.0 | - |
|
| 461 |
+
| 0.6522 | 15750 | 0.0 | - |
|
| 462 |
+
| 0.6542 | 15800 | 0.0 | - |
|
| 463 |
+
| 0.6563 | 15850 | 0.0 | - |
|
| 464 |
+
| 0.6584 | 15900 | 0.0001 | - |
|
| 465 |
+
| 0.6605 | 15950 | 0.0 | - |
|
| 466 |
+
| 0.6625 | 16000 | 0.0 | - |
|
| 467 |
+
| 0.6646 | 16050 | 0.0 | - |
|
| 468 |
+
| 0.6667 | 16100 | 0.0 | - |
|
| 469 |
+
| 0.6687 | 16150 | 0.0 | - |
|
| 470 |
+
| 0.6708 | 16200 | 0.0 | - |
|
| 471 |
+
| 0.6729 | 16250 | 0.0 | - |
|
| 472 |
+
| 0.6749 | 16300 | 0.0 | - |
|
| 473 |
+
| 0.6770 | 16350 | 0.0 | - |
|
| 474 |
+
| 0.6791 | 16400 | 0.0 | - |
|
| 475 |
+
| 0.6812 | 16450 | 0.0 | - |
|
| 476 |
+
| 0.6832 | 16500 | 0.0 | - |
|
| 477 |
+
| 0.6853 | 16550 | 0.0 | - |
|
| 478 |
+
| 0.6874 | 16600 | 0.0 | - |
|
| 479 |
+
| 0.6894 | 16650 | 0.0 | - |
|
| 480 |
+
| 0.6915 | 16700 | 0.0 | - |
|
| 481 |
+
| 0.6936 | 16750 | 0.0 | - |
|
| 482 |
+
| 0.6957 | 16800 | 0.0 | - |
|
| 483 |
+
| 0.6977 | 16850 | 0.0 | - |
|
| 484 |
+
| 0.6998 | 16900 | 0.0 | - |
|
| 485 |
+
| 0.7019 | 16950 | 0.0 | - |
|
| 486 |
+
| 0.7039 | 17000 | 0.0 | - |
|
| 487 |
+
| 0.7060 | 17050 | 0.0 | - |
|
| 488 |
+
| 0.7081 | 17100 | 0.0 | - |
|
| 489 |
+
| 0.7101 | 17150 | 0.0 | - |
|
| 490 |
+
| 0.7122 | 17200 | 0.0 | - |
|
| 491 |
+
| 0.7143 | 17250 | 0.0 | - |
|
| 492 |
+
| 0.7164 | 17300 | 0.0 | - |
|
| 493 |
+
| 0.7184 | 17350 | 0.0 | - |
|
| 494 |
+
| 0.7205 | 17400 | 0.0 | - |
|
| 495 |
+
| 0.7226 | 17450 | 0.0 | - |
|
| 496 |
+
| 0.7246 | 17500 | 0.0 | - |
|
| 497 |
+
| 0.7267 | 17550 | 0.0 | - |
|
| 498 |
+
| 0.7288 | 17600 | 0.0 | - |
|
| 499 |
+
| 0.7308 | 17650 | 0.0 | - |
|
| 500 |
+
| 0.7329 | 17700 | 0.0 | - |
|
| 501 |
+
| 0.7350 | 17750 | 0.0 | - |
|
| 502 |
+
| 0.7371 | 17800 | 0.0 | - |
|
| 503 |
+
| 0.7391 | 17850 | 0.0 | - |
|
| 504 |
+
| 0.7412 | 17900 | 0.0 | - |
|
| 505 |
+
| 0.7433 | 17950 | 0.0 | - |
|
| 506 |
+
| 0.7453 | 18000 | 0.0 | - |
|
| 507 |
+
| 0.7474 | 18050 | 0.0 | - |
|
| 508 |
+
| 0.7495 | 18100 | 0.0006 | - |
|
| 509 |
+
| 0.7516 | 18150 | 0.0 | - |
|
| 510 |
+
| 0.7536 | 18200 | 0.0003 | - |
|
| 511 |
+
| 0.7557 | 18250 | 0.0 | - |
|
| 512 |
+
| 0.7578 | 18300 | 0.0 | - |
|
| 513 |
+
| 0.7598 | 18350 | 0.0 | - |
|
| 514 |
+
| 0.7619 | 18400 | 0.0015 | - |
|
| 515 |
+
| 0.7640 | 18450 | 0.0 | - |
|
| 516 |
+
| 0.7660 | 18500 | 0.0002 | - |
|
| 517 |
+
| 0.7681 | 18550 | 0.0005 | - |
|
| 518 |
+
| 0.7702 | 18600 | 0.0 | - |
|
| 519 |
+
| 0.7723 | 18650 | 0.0 | - |
|
| 520 |
+
| 0.7743 | 18700 | 0.0001 | - |
|
| 521 |
+
| 0.7764 | 18750 | 0.0 | - |
|
| 522 |
+
| 0.7785 | 18800 | 0.0 | - |
|
| 523 |
+
| 0.7805 | 18850 | 0.0 | - |
|
| 524 |
+
| 0.7826 | 18900 | 0.0001 | - |
|
| 525 |
+
| 0.7847 | 18950 | 0.0 | - |
|
| 526 |
+
| 0.7867 | 19000 | 0.0 | - |
|
| 527 |
+
| 0.7888 | 19050 | 0.0 | - |
|
| 528 |
+
| 0.7909 | 19100 | 0.0001 | - |
|
| 529 |
+
| 0.7930 | 19150 | 0.0 | - |
|
| 530 |
+
| 0.7950 | 19200 | 0.0 | - |
|
| 531 |
+
| 0.7971 | 19250 | 0.0 | - |
|
| 532 |
+
| 0.7992 | 19300 | 0.0 | - |
|
| 533 |
+
| 0.8012 | 19350 | 0.0 | - |
|
| 534 |
+
| 0.8033 | 19400 | 0.0 | - |
|
| 535 |
+
| 0.8054 | 19450 | 0.0 | - |
|
| 536 |
+
| 0.8075 | 19500 | 0.0 | - |
|
| 537 |
+
| 0.8095 | 19550 | 0.0 | - |
|
| 538 |
+
| 0.8116 | 19600 | 0.0 | - |
|
| 539 |
+
| 0.8137 | 19650 | 0.0 | - |
|
| 540 |
+
| 0.8157 | 19700 | 0.0 | - |
|
| 541 |
+
| 0.8178 | 19750 | 0.0 | - |
|
| 542 |
+
| 0.8199 | 19800 | 0.0 | - |
|
| 543 |
+
| 0.8219 | 19850 | 0.0 | - |
|
| 544 |
+
| 0.8240 | 19900 | 0.0 | - |
|
| 545 |
+
| 0.8261 | 19950 | 0.0 | - |
|
| 546 |
+
| 0.8282 | 20000 | 0.0 | - |
|
| 547 |
+
| 0.8302 | 20050 | 0.0 | - |
|
| 548 |
+
| 0.8323 | 20100 | 0.0012 | - |
|
| 549 |
+
| 0.8344 | 20150 | 0.0001 | - |
|
| 550 |
+
| 0.8364 | 20200 | 0.0 | - |
|
| 551 |
+
| 0.8385 | 20250 | 0.0 | - |
|
| 552 |
+
| 0.8406 | 20300 | 0.0 | - |
|
| 553 |
+
| 0.8427 | 20350 | 0.0 | - |
|
| 554 |
+
| 0.8447 | 20400 | 0.0 | - |
|
| 555 |
+
| 0.8468 | 20450 | 0.0 | - |
|
| 556 |
+
| 0.8489 | 20500 | 0.0 | - |
|
| 557 |
+
| 0.8509 | 20550 | 0.0 | - |
|
| 558 |
+
| 0.8530 | 20600 | 0.0 | - |
|
| 559 |
+
| 0.8551 | 20650 | 0.0 | - |
|
| 560 |
+
| 0.8571 | 20700 | 0.0 | - |
|
| 561 |
+
| 0.8592 | 20750 | 0.0001 | - |
|
| 562 |
+
| 0.8613 | 20800 | 0.0 | - |
|
| 563 |
+
| 0.8634 | 20850 | 0.0 | - |
|
| 564 |
+
| 0.8654 | 20900 | 0.0 | - |
|
| 565 |
+
| 0.8675 | 20950 | 0.0 | - |
|
| 566 |
+
| 0.8696 | 21000 | 0.0 | - |
|
| 567 |
+
| 0.8716 | 21050 | 0.0 | - |
|
| 568 |
+
| 0.8737 | 21100 | 0.0 | - |
|
| 569 |
+
| 0.8758 | 21150 | 0.0 | - |
|
| 570 |
+
| 0.8778 | 21200 | 0.0 | - |
|
| 571 |
+
| 0.8799 | 21250 | 0.0 | - |
|
| 572 |
+
| 0.8820 | 21300 | 0.0 | - |
|
| 573 |
+
| 0.8841 | 21350 | 0.0 | - |
|
| 574 |
+
| 0.8861 | 21400 | 0.0 | - |
|
| 575 |
+
| 0.8882 | 21450 | 0.0 | - |
|
| 576 |
+
| 0.8903 | 21500 | 0.0 | - |
|
| 577 |
+
| 0.8923 | 21550 | 0.0002 | - |
|
| 578 |
+
| 0.8944 | 21600 | 0.0 | - |
|
| 579 |
+
| 0.8965 | 21650 | 0.0 | - |
|
| 580 |
+
| 0.8986 | 21700 | 0.0 | - |
|
| 581 |
+
| 0.9006 | 21750 | 0.0 | - |
|
| 582 |
+
| 0.9027 | 21800 | 0.0 | - |
|
| 583 |
+
| 0.9048 | 21850 | 0.0 | - |
|
| 584 |
+
| 0.9068 | 21900 | 0.0 | - |
|
| 585 |
+
| 0.9089 | 21950 | 0.0 | - |
|
| 586 |
+
| 0.9110 | 22000 | 0.0 | - |
|
| 587 |
+
| 0.9130 | 22050 | 0.0 | - |
|
| 588 |
+
| 0.9151 | 22100 | 0.0 | - |
|
| 589 |
+
| 0.9172 | 22150 | 0.0 | - |
|
| 590 |
+
| 0.9193 | 22200 | 0.0 | - |
|
| 591 |
+
| 0.9213 | 22250 | 0.0 | - |
|
| 592 |
+
| 0.9234 | 22300 | 0.0 | - |
|
| 593 |
+
| 0.9255 | 22350 | 0.0 | - |
|
| 594 |
+
| 0.9275 | 22400 | 0.0 | - |
|
| 595 |
+
| 0.9296 | 22450 | 0.0 | - |
|
| 596 |
+
| 0.9317 | 22500 | 0.0 | - |
|
| 597 |
+
| 0.9337 | 22550 | 0.0 | - |
|
| 598 |
+
| 0.9358 | 22600 | 0.0 | - |
|
| 599 |
+
| 0.9379 | 22650 | 0.0 | - |
|
| 600 |
+
| 0.9400 | 22700 | 0.0 | - |
|
| 601 |
+
| 0.9420 | 22750 | 0.0 | - |
|
| 602 |
+
| 0.9441 | 22800 | 0.0 | - |
|
| 603 |
+
| 0.9462 | 22850 | 0.0 | - |
|
| 604 |
+
| 0.9482 | 22900 | 0.0 | - |
|
| 605 |
+
| 0.9503 | 22950 | 0.0 | - |
|
| 606 |
+
| 0.9524 | 23000 | 0.0 | - |
|
| 607 |
+
| 0.9545 | 23050 | 0.0 | - |
|
| 608 |
+
| 0.9565 | 23100 | 0.0 | - |
|
| 609 |
+
| 0.9586 | 23150 | 0.0 | - |
|
| 610 |
+
| 0.9607 | 23200 | 0.0 | - |
|
| 611 |
+
| 0.9627 | 23250 | 0.0 | - |
|
| 612 |
+
| 0.9648 | 23300 | 0.0 | - |
|
| 613 |
+
| 0.9669 | 23350 | 0.0 | - |
|
| 614 |
+
| 0.9689 | 23400 | 0.0 | - |
|
| 615 |
+
| 0.9710 | 23450 | 0.0 | - |
|
| 616 |
+
| 0.9731 | 23500 | 0.0 | - |
|
| 617 |
+
| 0.9752 | 23550 | 0.0 | - |
|
| 618 |
+
| 0.9772 | 23600 | 0.0 | - |
|
| 619 |
+
| 0.9793 | 23650 | 0.0 | - |
|
| 620 |
+
| 0.9814 | 23700 | 0.0 | - |
|
| 621 |
+
| 0.9834 | 23750 | 0.0 | - |
|
| 622 |
+
| 0.9855 | 23800 | 0.0 | - |
|
| 623 |
+
| 0.9876 | 23850 | 0.0 | - |
|
| 624 |
+
| 0.9896 | 23900 | 0.0 | - |
|
| 625 |
+
| 0.9917 | 23950 | 0.0 | - |
|
| 626 |
+
| 0.9938 | 24000 | 0.0 | - |
|
| 627 |
+
| 0.9959 | 24050 | 0.0 | - |
|
| 628 |
+
| 0.9979 | 24100 | 0.0 | - |
|
| 629 |
+
| 1.0 | 24150 | 0.0 | 0.1957 |
|
| 630 |
+
|
| 631 |
+
### Framework Versions
|
| 632 |
+
- Python: 3.12.12
|
| 633 |
+
- SetFit: 1.1.3
|
| 634 |
+
- Sentence Transformers: 5.2.3
|
| 635 |
+
- Transformers: 4.44.2
|
| 636 |
+
- PyTorch: 2.10.0+cu128
|
| 637 |
+
- Datasets: 4.0.0
|
| 638 |
+
- Tokenizers: 0.19.1
|
| 639 |
+
|
| 640 |
+
## Citation
|
| 641 |
+
|
| 642 |
+
### BibTeX
|
| 643 |
+
```bibtex
|
| 644 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
| 645 |
+
doi = {10.48550/ARXIV.2209.11055},
|
| 646 |
+
url = {https://arxiv.org/abs/2209.11055},
|
| 647 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
| 648 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
| 649 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
| 650 |
+
publisher = {arXiv},
|
| 651 |
+
year = {2022},
|
| 652 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
| 653 |
+
}
|
| 654 |
+
```
|
| 655 |
+
|
| 656 |
+
<!--
|
| 657 |
+
## Glossary
|
| 658 |
+
|
| 659 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 660 |
+
-->
|
| 661 |
+
|
| 662 |
+
<!--
|
| 663 |
+
## Model Card Authors
|
| 664 |
+
|
| 665 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 666 |
+
-->
|
| 667 |
+
|
| 668 |
+
<!--
|
| 669 |
+
## Model Card Contact
|
| 670 |
+
|
| 671 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 672 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "xlm-roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.44.2",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 250002
|
| 29 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "5.2.3",
|
| 4 |
+
"transformers": "4.44.2",
|
| 5 |
+
"pytorch": "2.10.0+cu128"
|
| 6 |
+
},
|
| 7 |
+
"model_type": "SentenceTransformer",
|
| 8 |
+
"prompts": {
|
| 9 |
+
"query": "",
|
| 10 |
+
"document": ""
|
| 11 |
+
},
|
| 12 |
+
"default_prompt_name": null,
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
config_setfit.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"normalize_embeddings": false,
|
| 3 |
+
"labels": [
|
| 4 |
+
"Happy",
|
| 5 |
+
"Anger",
|
| 6 |
+
"Sadness",
|
| 7 |
+
"Fear",
|
| 8 |
+
"Surprise",
|
| 9 |
+
"Disgust"
|
| 10 |
+
]
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fb9a73145a2a33a91fee9255982e433af3dbd1b0bc828a7588a425cbee7ef9b
|
| 3 |
+
size 1112197096
|
model_head.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7ad9485ce32f685615748f9bb0fd34a9550c94637507fa0851152cfe92d13b5
|
| 3 |
+
size 37799
|
modules.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
}
|
| 14 |
+
]
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 128,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
|
| 3 |
+
size 17082987
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"max_length": 128,
|
| 50 |
+
"model_max_length": 128,
|
| 51 |
+
"pad_to_multiple_of": null,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"pad_token_type_id": 0,
|
| 54 |
+
"padding_side": "right",
|
| 55 |
+
"sep_token": "</s>",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 58 |
+
"truncation_side": "right",
|
| 59 |
+
"truncation_strategy": "longest_first",
|
| 60 |
+
"unk_token": "<unk>"
|
| 61 |
+
}
|