初始化项目，由ModelHub XC社区提供模型

Model: 81melody/algerianME5
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": true,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,360 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- Algerian AI
+- Algerian
+- algeria
+- darja
+- darija
+- algerian darija
+- algerian dialect
+- rag 
+- ar
+- multilingual-e5
+- generated_from_trainer
+- loss:MultipleNegativesRankingLoss
+base_model: intfloat/multilingual-e5-base
+widget:
+- source_sentence: 'query: Renault Kangoo 2019'
+  sentences:
+  - >-
+    passage: سيارة Renault Kangoo 2019 Confort · مازوت · يدوية · 1.5 DCI 90ch ·
+    المسافة: 199,000 كم · السعر: 420 مليون دج · سيسبونسيو 10/10
+
+    موتور 10/10
+
+    سبيغة 0
+
+    كلشي معاود فيها جديد
+  - >-
+    passage: سيارة Dfsq Dfsq 2013 · بنزين · يدوية · 1.1 · المسافة: 280 كم ·
+    السعر: 140 مليون دج · باتنة · مفيهش معاود
+
+    موتور محطوط جديد
+  - >-
+    passage: بيع فيلا تيبازة بوسماعيل · فيلا · السعر: 8 مليون دج · تيبازة ·
+    agence immobilier LABID agrée par l'état met en vente trés bel villa r+2 de
+    sup 250 m² deux facade dans un résidence clôturé et gardée jour et nuit
+    libre de suite l'villa avec toute commanditée :
+
+    - rdc : deux garage pour 7 véhicule + studio + jardain
+
+    - 1ére étage : salon de chambre + cuisine + salle de bain + sanitaire
+
+    - 2éme étage : salon +3 chambre + sanitaire + Hammam
+
+    - 3éme étage : grand salon + deux terrasse
+
+    - chauffage centrale
+
+    - climatisation
+
+    - caméra de surveillance
+
+    - bâché d'eau
+
+    - acte et livret foncier
+
+    - les prix : 8 milliards nég lég
+
+    - pour plus d'informations consultéz agence labid au :
+
+    -
+- source_sentence: 'query: location terrain Oran'
+  sentences:
+  - >-
+    passage: كراء عمارة وهران وهران · ارض · 90 م² · السعر: 6 مليون دج · وهران ·
+    location plusieurs appartements dans un immeuble de 5 étages et avec
+    ascenseur
+
+    les appartements sont neuf jamais habité
+
+    merci de nous contacter pour savoir plus de détails .
+  - >-
+    passage: سيارة Kia Seltos 2025 LUXuRY · بنزين · اوتوماتيك · 1.5 · السعر: 545
+    مليون دج · الوادي
+  - >-
+    passage: سيارة Peugeot 308 2015 Active · مازوت · يدوية · 1.6 e HDI 112ch ·
+    المسافة: 375,000 كم · وهران · Je vente 308 jdida machya 375000
+- source_sentence: 'query: villa Alger avec jardin'
+  sentences:
+  - >-
+    passage: بيع شقة 3 غرف الجزائر العاشور · شقة · 3 غرف · السعر: 3 مليون دج ·
+    الجزائر ·vente une appartement a el3achour Hawch chawech De 96m F3 en 3 em
+    etg avec la scenseur tout comoditie chauffage central climatisation cuisine
+    équipée boxe pour stationnement les caméras de surveillance avec act et
+    livret foncièr
+  - >-
+    passage: كراء شقة دوبلكس 4 غرف الجزائر العاشور · شقة · 4 غرف · مطبخ مجهز ·
+    تدفئة مركزية · تكييف · تيراس · مفروش · جناح غرفة النوم · السعر: 29 مليون دج
+    · الجزائر · El Achour Location d’un Duplex F4 meublé de haut standing
+    superficie 213 m²
+
+
+
+    Le Duplex se compose :
+
+
+    Niveau 1: une entrée, un joli séjour avec une salle à manger, une cuisine
+    équipée haute gamme, sanitaire + hammame, terrasse.
+
+
+    Niveau 2 : 3 chambres dont une master bed room, une salle de bain avec
+    jacuzzi, espace bureau, 2 balcons.
+
+
+    Équipements : climatisation, chauffage central, double vitrage, stores
+    électriques, visiophone, 1 place de parking.
+
+
+    Commodités de la résidence : ascenseur, parking, gardiennage 24h/24, aire de
+    jeux pour enfants, espaces verts pour vos moments de détente.
+  - >-
+    passage: كراء شقة 5 غرف البليدة البليدة · شقة · 5 غرف · السعر: 5 مليون دج ·
+    البليدة · 203m plus ascenseur
+- source_sentence: 'query: Cuxi Cuxi 2025'
+  sentences:
+  - >-
+    passage: سيارة Volkswagen Golf 7 2016 Trendline + · مازوت · يدوية · 2.0 TDI
+    110ch · المسافة: 280,000 كم
+  - >-
+    passage: سيارة Opel Corsa 2001 Corsa · مازوت · يدوية · 1.7 D 60ch · المسافة:
+    350,000 كم · السعر: 65 مليون دج · موتور نعاود يدور شهرة السبيغة فيها سوباسمو
+  - >-
+    passage: سيارة Cuxi Cuxi 2025 · بنزين · اوتوماتيك · Yamaha 110 · المسافة:
+    9,250 كم · السعر: 28 مليون دج · قسنطينة · Cuxi 2025 jdida état 10/10
+- source_sentence: 'query: Rani nhawes 3la tonobil Hyundai i10'
+  sentences:
+  - 'passage: بيع شقة غرفتين 3 غرف 4 غرف وهران بئر الجير · شقة · 3 غرف · وهران'
+  - >-
+    passage: سيارة Kia Cerato 2008 · مازوت · يدوية · المسافة: 230,000 كم ·
+    السعر: 135 مليون دج · سوق اهراس · Problem də terage
+  - >-
+    passage: سيارة Hyundai i10 2014 GLS · بنزين · يدوية · 1.1 · المسافة: 300,000
+    كم · عين تموشنت · Fiha bantoura
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+license: mit
+language:
+- ar
+- fr
+---
+
+# AlgerianME5
+
+**algerianME5** is a specialized **Sentence-Transformer** model designed to map Algerian search queries to a 768-dimensional dense vector space, It is specifically fine-tuned to understand the nuances and the vocabulary of the Algerian car and real estate markets, where listings often mix Arabic, French, and darja in both Arabic and Latin script
+
+Note: For more details about the methodology, data synthesis, and evaluation, [please visit the full Medium Story](https://medium.com/@ayoubhimeur/building-a-semantic-search-engine-for-algerian-marketplaces-cc04a0008346)
+
+## Key Features : 
+-**Domain Specific**: Optimized for real estate and automotive algerian vocabulary “sbigha,” “f3,” “livret foncier”
+
+-**Cross lingual Retrieval**: Maps informal latin queries "tonobil mliha" to formal Arabic or French listing descriptions
+
+-**Robust Embeddings**: Based on the powerful intfloat/multilingual-e5-base architecture
+
+## Use cases : 
+
+-**Semantic Search** : Find relevant listings even if keywords dont match exactly (use it as a second layer)
+
+-**Textual Similarity**:Compare two listings to find duplicates or similar items
+
+-**Clustering**	Group listings by sub-market or vehicle/property type
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) <!-- at revision 835193815a3936a24a0ee7dc9e3d48c1fbb19c55 -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'})
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+
+model = SentenceTransformer("81melody/algerianME5")
+sentences = [
+    'query: Rani nhawes 3la tonobil Hyundai i10',
+    'passage: سيارة Hyundai i10 2014 GLS · بنزين · يدوية · 1.1 · المسافة: 300,000 كم · عين تموشنت · Fiha bantoura',
+    'passage: سيارة Kia Cerato 2008 · مازوت · يدوية · المسافة: 230,000 كم · السعر: 135 مليون دج · سوق اهراس · Problem də terage',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+```
+**OR**
+
+```python
+from sentence_transformers import SentenceTransformer , util
+model = SentenceTransformer("81melody/algerianME5")
+listings = [
+    # REAL ESTATE
+    "بيع شقة 4 غرف الجزائر شراقة · شقة · 4 غرف · السعر: 4 مليون دج · Appartement Composé De 1 Suite Parentale... Résidence sécurisée",
+    "كراء شقة 4 غرف وهران وهران · شقة · 4 غرف · Location appartement par jour pour familles",
+    "بيع ارض تلمسان مغنية · ارض · الجزائر · بلان فالسانك مليح",
+    "كراء محل الجزائر الابيار · محل تجاري · 105 م² · Local avec Deux rideaux",
+    
+    # CARS
+    "سيارة MG Zs Ev 2024 Comfort · بنزين · يدوية · 1.5 VTi-Tech 106ch · المسافة: 67,000 كم · Très beau SUV comme neuf",
+    "سيارة Hyundai Grand i10 2018 Restylée DZ · بنزين · يدوية · 1.2 ess 87ch · السعر: 265 مليون دج · صبيغة فيها لال و لامان",
+    "سيارة Renault Clio 4 2018 GT Line + · مازوت · يدوية · 1.5 DCI 85ch · السعر: 330 مليون دج"
+]
+queries = [
+    "شقة 4 غرف الجزائر",              
+    "dar lel bi3 fi Alger centre",    
+    "ard lel bi3 telemcan"   ,           
+    "chhal souma MG Zs Ev",          
+    "Grand I10 2018 Restylée DZ",     
+    "tonobil mliha fiha sbigha shwia" 
+]
+  q_prefix = "query: "
+  p_prefix = "passage: "
+
+  encoded_listings = model.encode(
+      [f"{p_prefix}{l}" for l in listings], 
+      convert_to_tensor=True,
+      show_progress_bar=False
+  )
+  for query in queries:
+      print(f"\nQuery: '{query}'")
+      
+      
+      query_emb = model.encode(f"{q_prefix}{query}", convert_to_tensor=True)
+      hits = util.semantic_search(query_emb, encoded_listings, top_k=3)[0]
+
+
+      for i, hit in enumerate(hits):
+          score = hit['score']
+          doc_id = hit['corpus_id']
+          display_text = listings[doc_id][:100] + "..." if len(listings[doc_id]) > 100 else listings[doc_id]
+          print(f"[Score: {score:.3f}] {display_text}")
+```
+
+## Training Details
+
+### Training Dataset
+
+* Size: 100,000 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                        | sentence_1                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                             |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 11.07 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 82.2 tokens</li><li>max: 256 tokens</li></ul> |
+* Samples:
+  | sentence_0                              | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+  |:----------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>query: بيع محل وهران بئر</code>   | <code>passage: بيع محل وهران بئر الجير · محل تجاري · 750 م² · السعر: 20 مليار دج · وهران · On vous propose en vente un local de 750 m² (550 m² en rez-de-chaussée et 200 m² sous pente) , avec deux rideaux électriques , pour le prix de : 20 Milliards fixe .<br><br>Pour plus de détails veuillez nous contacter</code>                                                                                                                                                                                                       |
+  | <code>query: شقة الجزائر برج</code>     | <code>passage: بيع شقة الجزائر برج الكيفان · شقة · 1 غرف · 64 م² · وثائق: دفتر عقاري · عقد موثق · الجزائر · 🔔OPPORTUNITÉ EN OR 🔔<br>– T2 à vendre +paiement par tranche dans 24mois<br><br>❄️À seulement quelques pas de la piscine, dans une site sécurisée et bien située, ce T2 en semi-finis une valeur sûre pour tout investisseur avisé.<br><br>Pourquoi ce bien est exceptionnel ?<br>✅️Localisation stratégique, très demandée<br>✅️Retour sur investissement rapide<br>✅️Prêt à être exploité dès l’achat !<br>✅️Un petit prix pour un grand potentiel.<br>✅️Les bonnes affaires ne durent jamais longtemps…<br>Saisissez cette opportunité maintenant !</code> |
+  | <code>query: GX3 PRO 2025 X3 Pro</code> | <code>passage: سيارة Geely GX3 PRO 2025 X3 pro livane · بنزين · اوتوماتيك · 1.5 · المسافة: جديدة · بجاية · Vent une livane x3pro neuf carte grise Safia</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false,
+      "directions": [
+          "query_to_doc"
+      ],
+      "partition_mode": "joint",
+      "hardness_mode": null,
+      "hardness_strength": 0.0
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `fp16`: True
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss |
+|:------:|:-----:|:-------------:|
+|   ...  |  ...  |     ...       | 
+| 2.32   | 14500 | 0.2827        |
+| 2.4    | 15000 | 0.3062        |
+| 2.48   | 15500 | 0.3045        |
+| 2.56   | 16000 | 0.2841        |
+
+
+### Framework Versions
+- Python: 3.12.13
+- Sentence Transformers: 5.3.0
+- Transformers: 5.0.0
+- PyTorch: 2.10.0+cu128
+- Accelerate: 1.13.0
+- Datasets: 4.0.0
+- Tokenizers: 0.22.2
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{oord2019representationlearningcontrastivepredictive,
+      title={Representation Learning with Contrastive Predictive Coding},
+      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
+      year={2019},
+      eprint={1807.03748},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/1807.03748},
+}
+```
+### Contact 
+Iam interested in any further related work, contact me at mohamed.himeur@student.unamur.be 

config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "5.0.0",
+    "pytorch": "2.10.0+cu128"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b342b6314310b1fdd89c60c05e81b0212c743f54d30430d2968fe9f4667afb3
+size 1112197064

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913a5368a7577d2be0e6c0babf983ef3b480fcd6823e79a547c9a24735c8a300
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492bc78bd83b826eedbe67547210706d1c9a2b14604e5b97f861b508daf02d5c
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216aaa27aba2a207d4db80b37b87abe496b983a01e4691c445bcc1f4502f7dbf
+size 1465

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 256,
+    "do_lower_case": false
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c16d8a2bff758ba6e009849c31b8ffc8ba92bfc907e0bcee96a09f1818fe2da
+size 16766387

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.56,
+  "eval_steps": 0,
+  "global_step": 16000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 9.120098114013672,
+      "learning_rate": 5.2906666666666675e-06,
+      "loss": 0.772038330078125,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 16.881511688232422,
+      "learning_rate": 1.0624e-05,
+      "loss": 0.37112783813476563,
+      "step": 1000
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 9.139080047607422,
+      "learning_rate": 1.5957333333333334e-05,
+      "loss": 0.36207400512695315,
+      "step": 1500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.8323566913604736,
+      "learning_rate": 1.9856592592592595e-05,
+      "loss": 0.34735809326171874,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.640134811401367,
+      "learning_rate": 1.9265185185185186e-05,
+      "loss": 0.329142578125,
+      "step": 2500
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 7.571471214294434,
+      "learning_rate": 1.8672592592592594e-05,
+      "loss": 0.3232558288574219,
+      "step": 3000
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.5788984298706055,
+      "learning_rate": 1.8080000000000003e-05,
+      "loss": 0.33851583862304685,
+      "step": 3500
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.823075771331787,
+      "learning_rate": 1.748740740740741e-05,
+      "loss": 0.3265293884277344,
+      "step": 4000
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.9052886962890625,
+      "learning_rate": 1.6897185185185187e-05,
+      "loss": 0.3228313903808594,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.530646562576294,
+      "learning_rate": 1.6304592592592593e-05,
+      "loss": 0.3212389831542969,
+      "step": 5000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.003970146179199,
+      "learning_rate": 1.5712e-05,
+      "loss": 0.3108310546875,
+      "step": 5500
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.259843111038208,
+      "learning_rate": 1.511940740740741e-05,
+      "loss": 0.33287890625,
+      "step": 6000
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.1002967357635498,
+      "learning_rate": 1.4526814814814815e-05,
+      "loss": 0.3126535949707031,
+      "step": 6500
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 2.696305751800537,
+      "learning_rate": 1.3934222222222222e-05,
+      "loss": 0.3110744323730469,
+      "step": 7000
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.0759758949279785,
+      "learning_rate": 1.3341629629629631e-05,
+      "loss": 0.307027099609375,
+      "step": 7500
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.2770161628723145,
+      "learning_rate": 1.2749037037037038e-05,
+      "loss": 0.31455657958984373,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 2.4967329502105713,
+      "learning_rate": 1.2156444444444447e-05,
+      "loss": 0.31456546020507814,
+      "step": 8500
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 5.275321006774902,
+      "learning_rate": 1.1565037037037039e-05,
+      "loss": 0.3131004943847656,
+      "step": 9000
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.145164966583252,
+      "learning_rate": 1.0972444444444446e-05,
+      "loss": 0.30567279052734375,
+      "step": 9500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.0739190578460693,
+      "learning_rate": 1.0379851851851853e-05,
+      "loss": 0.28998117065429685,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 3.1562881469726562,
+      "learning_rate": 9.78725925925926e-06,
+      "loss": 0.29778146362304686,
+      "step": 10500
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 3.498109817504883,
+      "learning_rate": 9.194666666666667e-06,
+      "loss": 0.2988756103515625,
+      "step": 11000
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 3.3291115760803223,
+      "learning_rate": 8.602074074074076e-06,
+      "loss": 0.2985075988769531,
+      "step": 11500
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.631378173828125,
+      "learning_rate": 8.009481481481483e-06,
+      "loss": 0.2991393737792969,
+      "step": 12000
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3230953216552734,
+      "learning_rate": 7.416888888888889e-06,
+      "loss": 0.30236148071289065,
+      "step": 12500
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 2.339695930480957,
+      "learning_rate": 6.825481481481482e-06,
+      "loss": 0.295860595703125,
+      "step": 13000
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.0685478448867798,
+      "learning_rate": 6.234074074074075e-06,
+      "loss": 0.2980207824707031,
+      "step": 13500
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.947058379650116,
+      "learning_rate": 5.6414814814814825e-06,
+      "loss": 0.29257803344726563,
+      "step": 14000
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 2.2130205631256104,
+      "learning_rate": 5.0488888888888895e-06,
+      "loss": 0.2826576843261719,
+      "step": 14500
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 6.699328422546387,
+      "learning_rate": 4.4562962962962965e-06,
+      "loss": 0.30620053100585937,
+      "step": 15000
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.5939074158668518,
+      "learning_rate": 3.863703703703704e-06,
+      "loss": 0.3044532470703125,
+      "step": 15500
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.3366057872772217,
+      "learning_rate": 3.2711111111111117e-06,
+      "loss": 0.28407180786132813,
+      "step": 16000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 18750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546a615de05e8adf2749ffb2c7c65e652fb8eff7d18b9af7b4f23b45741d3fb4
+size 5521