Super squash history after split_eval_matrix removal

.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": 1024,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
+    "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 +1,256 @@
+---
+license: mit
+base_model: BAAI/bge-m3
+language:
+- de
+- en
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- retrieval
+- semantic-search
+- ifc
+- lca
+
+---
+
+# Hygroskopisch/bge-m3-ifc-kbob-finetuned
+
+Sentence-Transformers model finetuned from BAAI/bge-m3 for IFC-based construction material retrieval in KBOB/LCA workflows.
+
+## Model Summary
+
+- Model ID: Hygroskopisch/bge-m3-ifc-kbob-finetuned
+- Release: v3 (2026-04-16)
+- Base model: BAAI/bge-m3
+- Embedding dimension: 1024
+- Max sequence length: 128
+- Similarity: cosine
+
+The model is optimized for queries generated from IFC element metadata and maps them to KBOB-like material labels for downstream environmental impact workflows.
+
+## Intended Use
+
+- IFC-to-material retrieval in building and infrastructure datasets.
+- Candidate generation before manual validation in LCA pipelines.
+- Semantic search over construction material catalogs with domain-specific wording.
+
+## Out-of-Scope Use
+
+- Legal, compliance, or procurement decisions without human review.
+- Safety-critical engineering sign-off.
+- Use as a standalone source of truth for environmental declarations.
+
+## Responsible Use
+
+- Keep a human-in-the-loop for final material assignment.
+- Validate results against project context, standards, and local regulations.
+- Contact: sbert-lca@pm.me
+
+## Training Data
+
+The v3 run used project-internal data artifacts and generated pair files.
+
+- Query source file: Training/query_generation/generated_queries/generated_queries.txt
+- Expected mapping file: Training/query_generation/generated_queries/mapping_generated_queries.txt
+- Pair file used for training: Training/outputs/phase12/random_preselected_pairs_generated_queries-mapping_generated_querie-bge-m3-e2-b32-lr2e-05-d0p1-s42-d1-f8c0ccef.jsonl
+- Hard-negative strategy: fallback mode with random_preselected selection, up to 2 hard negatives per record
+
+Train/dev counts from run metadata:
+
+- Total pairs: 16386
+- Train pairs: 14748
+- Dev pairs: 1638
+
+## Evaluation Data
+
+Evaluation artifacts for this release:
+
+- eval/normal_queries/summary_eval-bge-m3-ifc-kbob-finetuned_model-1d06a0d7_queries-b9bc9eb9_no-reranker-7521044b.csv
+- eval/normal_queries/details_eval-bge-m3-ifc-kbob-finetuned_model-1d06a0d7_queries-b9bc9eb9_no-reranker-7521044b.csv
+
+Evaluation query count: 389
+
+## Evaluation Results
+
+The following results mirror the full evaluation summary in the main project README for the v3 model.
+
+### Core metrics by query set
+
+| Queries | Cases | Hit@1 | Hit@10 | Hit@20 | Hit@30 | Hit@50 | MRR@10 | MAP@10 | nDCG@10 | Recall@10 |
+| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| Normal | 389 | 97.43% | 99.49% | 99.74% | 99.74% | 100.00% | 0.984 | 0.932 | 0.954 | 0.960 |
+| Typos | 389 | 88.43% | 94.86% | 98.20% | 98.97% | 99.49% | 0.909 | 0.844 | 0.876 | 0.890 |
+| Missing Attribute | 389 | 75.32% | 92.80% | 96.40% | 98.20% | 98.71% | 0.803 | 0.750 | 0.794 | 0.860 |
+| Missing + Typos | 389 | 68.12% | 88.17% | 94.34% | 96.92% | 98.46% | 0.739 | 0.682 | 0.731 | 0.805 |
+
+95% confidence intervals (bootstrap from summary files):
+
+| Queries | Hit@1 95% CI | Hit@10 95% CI | MRR@10 95% CI | nDCG@10 95% CI |
+| --- | --- | --- | --- | --- |
+| Normal | [95.37%, 98.97%] | [98.71%, 100.00%] | [0.971, 0.994] | [0.939, 0.968] |
+| Typos | [84.83%, 91.77%] | [92.80%, 96.66%] | [0.881, 0.935] | [0.847, 0.902] |
+| Missing Attribute | [70.69%, 79.18%] | [89.97%, 94.99%] | [0.766, 0.835] | [0.759, 0.824] |
+| Missing + Typos | [63.36%, 72.49%] | [84.95%, 91.14%] | [0.695, 0.778] | [0.690, 0.767] |
+
+### Query set definitions
+
+The four query files test robustness under controlled perturbations.
+
+| Queries | Transformation | Hard invariants |
+| --- | --- | --- |
+| Normal | Unchanged query (reference run) | No perturbation |
+| Missing file | Removes one allowed token from `PredefinedType`, `Material`, `StrengthClass`, or `insitu/precast` (`Ortbeton/Fertigteil`) | `IfcEntity` is never removed |
+| Typos file | 1 to 2 typos per line, max 1 typo per token/word | `IfcEntity` remains correct |
+| Combined file | First remove one allowed token, then inject 1 to 2 typos into remaining allowed tokens (max 1 typo per token) | `IfcEntity` remains correct |
+
+Summary of generated perturbation files:
+
+| File | Changed lines | Typo distribution |
+| --- | ---: | --- |
+| Missing | 388 | - |
+| Typos | 388 | 1 typo: 193, 2 typos: 195 |
+| Missing + Typos | 388 | 1 typo: 309, 2 typos: 61 |
+
+### Detailed interpretation
+
+Readability note: metrics are computed on 389 evaluation cases; the perturbation table above reports changed lines in the generated query files.
+
+Degradation versus Normal Queries:
+
+| Queries | Delta Hit@1 | Delta Hit@10 | Delta MRR@10 | Delta nDCG@10 |
+| --- | ---: | ---: | ---: | ---: |
+| Typos | -9.00% | -4.63% | -0.075 | -0.078 |
+| Missing Attribute | -22.11% | -6.69% | -0.181 | -0.160 |
+| Missing + Typos | -29.31% | -11.32% | -0.245 | -0.223 |
+
+Conclusion: token removal hurts more than pure typo noise; the combined perturbation is strongest, as expected.
+
+Typos vs. Missing (direct comparison):
+- Hit@1: Missing is 13.11 percentage points below Typos (75.32% vs 88.43%).
+- Hit@10: Missing is 2.06 percentage points below Typos (92.80% vs 94.86%).
+- MRR@10: Missing is 0.106 below Typos (0.803 vs 0.909).
+- nDCG@10: Missing is 0.082 below Typos (0.794 vs 0.876).
+
+Conclusion: missing semantic slots move correct results further down the ranking than typos.
+
+Top-1 vs Top-10 recovery potential:
+- Normal: Hit@10 - Hit@1 = 2.06%.
+- Typos: Hit@10 - Hit@1 = 6.43%.
+- Missing Attribute: Hit@10 - Hit@1 = 17.48%.
+- Missing + Typos: Hit@10 - Hit@1 = 20.05%.
+
+Conclusion: under perturbation, the correct material often remains in top-10 but drops from rank 1 more frequently.
+
+Statistical separability (Hit@1 CIs):
+- Normal vs Typos: no overlap; interval gap 3.60% (95.37% vs 91.77%).
+- Typos vs Missing: no overlap; interval gap 5.65% (84.83% vs 79.18%).
+- Missing vs Missing + Typos: overlap 1.80% (70.69% to 72.49%).
+
+Conclusion: the first two degradation steps are clearly separated; the final step is smaller but still negative.
+
+Practical implications:
+- High automation precision depends strongly on stable `Material`, `StrengthClass`, and `CastingMethod` slots.
+- For noisy IFC text, UI workflows should prioritize top-10 candidates and avoid relying on top-1 alone.
+- Main improvement lever is robust semantic token extraction/preservation, more than additional typo tolerance.
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = [
+  "IfcPile BORED Stahlbeton C40/50 500 INSITU",
+  "Tiefgründung Ortbetonbohrpfahl 700",
+]
+
+model = SentenceTransformer("Hygroskopisch/bge-m3-ifc-kbob-finetuned")
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+Load a fixed released revision:
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer(
+  "Hygroskopisch/bge-m3-ifc-kbob-finetuned",
+  revision="v3",
+)
+```
+
+## Training
+
+Core training configuration (v3):
+
+- Epochs: 2
+- Batch size: 32
+- Learning rate: 2e-05
+- Warmup ratio: 0.1
+- FP16: true
+- Seed: 42
+- Device: cuda
+- Prefix mode: no_prefix
+
+DataLoader length: 7418
+
+Loss:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+fit() parameters:
+```
+{
+    "epochs": 2,
+    "evaluation_steps": 0,
+    "evaluator": "__main__.CombinedHit5Mrr10Evaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 1484,
+    "weight_decay": 0.01
+}
+```
+
+
+## Release Notes
+
+### v3 (2026-04-16)
+
+- Replaced previous published checkpoint with the new finetuned weights from the latest IFC/KBOB training run.
+- Updated training data pipeline artifacts and documented exact source file names used for this release.
+- Published baseline retrieval metrics on 389 evaluation queries (no cross-encoder reranker).
+- Behavior change: retrieval rankings can differ from previous versions; if you require reproducibility, pin revision v3.
+- Responsible-use contact added: sbert-lca@pm.me.
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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()
+)
+```
+
+## Citing & Authors
+
+If you use this model in a report or publication, cite the project repository and this Hugging Face model page.

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/nas05/data01/kbob-ai-matcher/models/bge-m3",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.33.0",
+    "pytorch": "2.1.2+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

eval/normal_queries/evaluation_report_eval-bge-m3-ifc-kbob-finetuned_model-1d06a0d7_queries-b9bc9eb9_no-reranker-7521044b.md

@@ -0,0 +1,34 @@
+## Evaluation Report
+
+Generated: 2026-04-16 10:03:27
+
+### Inputs
+- Summary CSV: `summary_eval-bge-m3-ifc-kbob-finetuned_model-1d06a0d7_queries-b9bc9eb9_no-reranker-7521044b.csv`
+- Details CSV: `details_eval-bge-m3-ifc-kbob-finetuned_model-1d06a0d7_queries-b9bc9eb9_no-reranker-7521044b.csv`
+
+### Overview
+![Model overview](overview_eval-bge-m3-ifc-kbob-finetuned_model-1d06a0d7_queries-b9bc9eb9_no-reranker-7521044b.svg)
+
+### Leaderboard
+
+#### Baseline (Bi-Encoder)
+
+| Rank | Model | Hit@1 | Hit@10 | Hit@20 | Hit@30 | Hit@50 | MRR@10 | MAP@10 | nDCG@10 | Recall@10 | Avg expected score | Hit@1 95% CI | Hit@10 95% CI | MRR@10 95% CI | nDCG@10 95% CI | Top1 errors |
+|---:|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---|---|---|---|---:|
+| 1 | models\\Hygroskopisch\\bge-m3-ifc-kbob-finetuned | 97.43% | 99.49% | 99.74% | 99.74% | 100.00% | 0.984 | 0.932 | 0.954 | 0.960 | 0.911 | [0.954, 0.990] | [0.987, 1.000] | [0.971, 0.994] | [0.939, 0.968] | 10 |
+
+#### Reranked (Bi-Encoder + Cross-Encoder)
+
+| Rank | Model | Cross-Encoder | Hit@1 | Hit@10 | Hit@20 | Hit@30 | Hit@50 | MRR@10 | MAP@10 | nDCG@10 | Recall@10 | Avg expected score | Hit@1 95% CI | Hit@10 95% CI | MRR@10 95% CI | nDCG@10 95% CI | Top1 errors |
+|---:|---|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---|---|---|---|---:|
+
+Anzahl Queries: 389
+
+### Hardest Queries (Baseline)
+Queries mit den meisten Top1-Fehlern in der Baseline:
+
+- (1 Fehler) IfcCovering MEMBRANE Abdichtung
+- (1 Fehler) IfcPavement FLEXIBLE Polymermodifiziertes Bitumen
+- (1 Fehler) IfcPile BORED Beton C20/25 insitu
+- (1 Fehler) IfcPile BORED Stahlbeton C20/25 insitu
+- (1 Fehler) IfcPile COHESION Beton C20/25 insitu

eval/normal_queries/summary_eval-bge-m3-ifc-kbob-finetuned_model-1d06a0d7_queries-b9bc9eb9_no-reranker-7521044b.csv

@@ -0,0 +1,2 @@
+model,pipeline_variant,cross_encoder_model,cases,hit@1,hit@10,hit@20,hit@30,hit@50,mrr,map@10,ndcg@10,recall@10,avg_expected_score,hit@1_ci_low,hit@1_ci_high,hit@10_ci_low,hit@10_ci_high,mrr@10_ci_low,mrr@10_ci_high,ndcg@10_ci_low,ndcg@10_ci_high
+models\\Hygroskopisch\\bge-m3-ifc-kbob-finetuned,baseline,-,389,0.974293,0.994859,0.997429,0.997429,1.000000,0.984147,0.932194,0.954325,0.959956,0.910825,0.953728,0.989717,0.987147,1.000000,0.971069,0.993573,0.939483,0.967920

eval/queries_missing+typos/evaluation_report_eval-bge-m3-ifc-kbob-finetuned-missing-queries_typos_model-1d06a0d7_queries_missing_typo-ba9d4d3a_no-reranker-7521044b.md

@@ -0,0 +1,34 @@
+## Evaluation Report
+
+Generated: 2026-04-16 11:14:26
+
+### Inputs
+- Summary CSV: `summary_eval-bge-m3-ifc-kbob-finetuned-missing-queries_typos_model-1d06a0d7_queries_missing_typo-ba9d4d3a_no-reranker-7521044b.csv`
+- Details CSV: `details_eval-bge-m3-ifc-kbob-finetuned-missing-queries_typos_model-1d06a0d7_queries_missing_typo-ba9d4d3a_no-reranker-7521044b.csv`
+
+### Overview
+![Model overview](overview_eval-bge-m3-ifc-kbob-finetuned-missing-queries_typos_model-1d06a0d7_queries_missing_typo-ba9d4d3a_no-reranker-7521044b.svg)
+
+### Leaderboard
+
+#### Baseline (Bi-Encoder)
+
+| Rank | Model | Hit@1 | Hit@10 | Hit@20 | Hit@30 | Hit@50 | MRR@10 | MAP@10 | nDCG@10 | Recall@10 | Avg expected score | Hit@1 95% CI | Hit@10 95% CI | MRR@10 95% CI | nDCG@10 95% CI | Top1 errors |
+|---:|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---|---|---|---|---:|
+| 1 | models\\Hygroskopisch\\bge-m3-ifc-kbob-finetuned | 68.12% | 88.17% | 94.34% | 96.92% | 98.46% | 0.739 | 0.682 | 0.731 | 0.805 | 0.837 | [0.634, 0.725] | [0.850, 0.911] | [0.695, 0.778] | [0.690, 0.767] | 124 |
+
+#### Reranked (Bi-Encoder + Cross-Encoder)
+
+| Rank | Model | Cross-Encoder | Hit@1 | Hit@10 | Hit@20 | Hit@30 | Hit@50 | MRR@10 | MAP@10 | nDCG@10 | Recall@10 | Avg expected score | Hit@1 95% CI | Hit@10 95% CI | MRR@10 95% CI | nDCG@10 95% CI | Top1 errors |
+|---:|---|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---|---|---|---|---:|
+
+Anzahl Queries: 389
+
+### Hardest Queries (Baseline)
+Queries mit den meisten Top1-Fehlern in der Baseline:
+
+- (2 Fehler) IfcTendonConduit COPULER
+- (2 Fehler) IfcBuildingElementPart Sathl
+- (2 Fehler) IfcBuildingElementProxy RIAL
+- (1 Fehler) IfcBearing CYLINDRIVAL
+- (1 Fehler) IfcBearing YCLINDRICAL

eval/queries_missing+typos/summary_eval-bge-m3-ifc-kbob-finetuned-missing-queries_typos_model-1d06a0d7_queries_missing_typo-ba9d4d3a_no-reranker-7521044b.csv

@@ -0,0 +1,2 @@
+model,pipeline_variant,cross_encoder_model,cases,hit@1,hit@10,hit@20,hit@30,hit@50,mrr,map@10,ndcg@10,recall@10,avg_expected_score,hit@1_ci_low,hit@1_ci_high,hit@10_ci_low,hit@10_ci_high,mrr@10_ci_low,mrr@10_ci_high,ndcg@10_ci_low,ndcg@10_ci_high
+models\\Hygroskopisch\\bge-m3-ifc-kbob-finetuned,baseline,-,389,0.681234,0.881748,0.943445,0.969152,0.984576,0.739290,0.682471,0.730620,0.804584,0.836972,0.633612,0.724936,0.849550,0.911375,0.694833,0.777858,0.690443,0.766578

eval/queries_missing/evaluation_report_eval-bge-m3-ifc-kbob-finetuned-missing-queries_model-1d06a0d7_queries_missing-a91a834f_no-reranker-7521044b.md

@@ -0,0 +1,34 @@
+## Evaluation Report
+
+Generated: 2026-04-16 11:04:03
+
+### Inputs
+- Summary CSV: `summary_eval-bge-m3-ifc-kbob-finetuned-missing-queries_model-1d06a0d7_queries_missing-a91a834f_no-reranker-7521044b.csv`
+- Details CSV: `details_eval-bge-m3-ifc-kbob-finetuned-missing-queries_model-1d06a0d7_queries_missing-a91a834f_no-reranker-7521044b.csv`
+
+### Overview
+![Model overview](overview_eval-bge-m3-ifc-kbob-finetuned-missing-queries_model-1d06a0d7_queries_missing-a91a834f_no-reranker-7521044b.svg)
+
+### Leaderboard
+
+#### Baseline (Bi-Encoder)
+
+| Rank | Model | Hit@1 | Hit@10 | Hit@20 | Hit@30 | Hit@50 | MRR@10 | MAP@10 | nDCG@10 | Recall@10 | Avg expected score | Hit@1 95% CI | Hit@10 95% CI | MRR@10 95% CI | nDCG@10 95% CI | Top1 errors |
+|---:|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---|---|---|---|---:|
+| 1 | models\\Hygroskopisch\\bge-m3-ifc-kbob-finetuned | 75.32% | 92.80% | 96.40% | 98.20% | 98.71% | 0.803 | 0.750 | 0.794 | 0.860 | 0.867 | [0.707, 0.792] | [0.900, 0.950] | [0.766, 0.835] | [0.759, 0.824] | 96 |
+
+#### Reranked (Bi-Encoder + Cross-Encoder)
+
+| Rank | Model | Cross-Encoder | Hit@1 | Hit@10 | Hit@20 | Hit@30 | Hit@50 | MRR@10 | MAP@10 | nDCG@10 | Recall@10 | Avg expected score | Hit@1 95% CI | Hit@10 95% CI | MRR@10 95% CI | nDCG@10 95% CI | Top1 errors |
+|---:|---|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---|---|---|---|---:|
+
+Anzahl Queries: 389
+
+### Hardest Queries (Baseline)
+Queries mit den meisten Top1-Fehlern in der Baseline:
+
+- (6 Fehler) IfcBuildingElementPart TrackElement
+- (6 Fehler) IfcRailing HANDRAIL
+- (5 Fehler) IfcRailing GUARDRAIL
+- (4 Fehler) IfcBuildingElementProxy Stahl
+- (2 Fehler) IfcBearing CYLINDRICAL

eval/queries_missing/summary_eval-bge-m3-ifc-kbob-finetuned-missing-queries_model-1d06a0d7_queries_missing-a91a834f_no-reranker-7521044b.csv

@@ -0,0 +1,2 @@
+model,pipeline_variant,cross_encoder_model,cases,hit@1,hit@10,hit@20,hit@30,hit@50,mrr,map@10,ndcg@10,recall@10,avg_expected_score,hit@1_ci_low,hit@1_ci_high,hit@10_ci_low,hit@10_ci_high,mrr@10_ci_low,mrr@10_ci_high,ndcg@10_ci_low,ndcg@10_ci_high
+models\\Hygroskopisch\\bge-m3-ifc-kbob-finetuned,baseline,-,389,0.753213,0.928021,0.964010,0.982005,0.987147,0.803195,0.749533,0.793588,0.860224,0.867081,0.706941,0.791774,0.899743,0.949936,0.766433,0.835491,0.758573,0.823939

eval/queries_typos/evaluation_report_eval-bge-m3-ifc-kbob-finetuned-typos_model-1d06a0d7_queries_typos-ec28a584_no-reranker-7521044b.md

@@ -0,0 +1,34 @@
+## Evaluation Report
+
+Generated: 2026-04-16 11:08:54
+
+### Inputs
+- Summary CSV: `summary_eval-bge-m3-ifc-kbob-finetuned-typos_model-1d06a0d7_queries_typos-ec28a584_no-reranker-7521044b.csv`
+- Details CSV: `details_eval-bge-m3-ifc-kbob-finetuned-typos_model-1d06a0d7_queries_typos-ec28a584_no-reranker-7521044b.csv`
+
+### Overview
+![Model overview](overview_eval-bge-m3-ifc-kbob-finetuned-typos_model-1d06a0d7_queries_typos-ec28a584_no-reranker-7521044b.svg)
+
+### Leaderboard
+
+#### Baseline (Bi-Encoder)
+
+| Rank | Model | Hit@1 | Hit@10 | Hit@20 | Hit@30 | Hit@50 | MRR@10 | MAP@10 | nDCG@10 | Recall@10 | Avg expected score | Hit@1 95% CI | Hit@10 95% CI | MRR@10 95% CI | nDCG@10 95% CI | Top1 errors |
+|---:|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---|---|---|---|---:|
+| 1 | models\\Hygroskopisch\\bge-m3-ifc-kbob-finetuned | 88.43% | 94.86% | 98.20% | 98.97% | 99.49% | 0.909 | 0.844 | 0.876 | 0.890 | 0.880 | [0.848, 0.918] | [0.928, 0.967] | [0.881, 0.935] | [0.847, 0.902] | 45 |
+
+#### Reranked (Bi-Encoder + Cross-Encoder)
+
+| Rank | Model | Cross-Encoder | Hit@1 | Hit@10 | Hit@20 | Hit@30 | Hit@50 | MRR@10 | MAP@10 | nDCG@10 | Recall@10 | Avg expected score | Hit@1 95% CI | Hit@10 95% CI | MRR@10 95% CI | nDCG@10 95% CI | Top1 errors |
+|---:|---|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---|---|---|---|---:|
+
+Anzahl Queries: 389
+
+### Hardest Queries (Baseline)
+Queries mit den meisten Top1-Fehlern in der Baseline:
+
+- (1 Fehler) IfcCourse ARMOUR5 Gestedin
+- (1 Fehler) IfcCourse PAVEENT Asühalt
+- (1 Fehler) IfcCovering MESMBRANE Sbdichtung
+- (1 Fehler) IfcCovering WRYPPING Kunssttoff
+- (1 Fehler) IfcMember CHORD Hokz

eval/queries_typos/summary_eval-bge-m3-ifc-kbob-finetuned-typos_model-1d06a0d7_queries_typos-ec28a584_no-reranker-7521044b.csv

@@ -0,0 +1,2 @@
+model,pipeline_variant,cross_encoder_model,cases,hit@1,hit@10,hit@20,hit@30,hit@50,mrr,map@10,ndcg@10,recall@10,avg_expected_score,hit@1_ci_low,hit@1_ci_high,hit@10_ci_low,hit@10_ci_high,mrr@10_ci_low,mrr@10_ci_high,ndcg@10_ci_low,ndcg@10_ci_high
+models\\Hygroskopisch\\bge-m3-ifc-kbob-finetuned,baseline,-,389,0.884319,0.948586,0.982005,0.989717,0.994859,0.909083,0.844199,0.875710,0.889752,0.880119,0.848329,0.917738,0.928021,0.966581,0.880868,0.934868,0.847480,0.901832

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf267a3d7f35ef54739d18b8ef5e682120e3b045467217b30f03d92a7cbf0f4a
+size 2271064456

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"
+  }
+]

run_metadata.json

@@ -0,0 +1,52 @@
+{
+  "run_id": "generated_queries-mapping_generated_querie-bge-m3-e2-b32-lr2e-05-d0p1-s42-d1-f8c0ccef",
+  "rule_hash": "88814a6f2add361886c1919c0904b93a7afd0152",
+  "train_file": "Training/outputs/phase12/random_preselected_pairs_generated_queries-mapping_generated_querie-bge-m3-e2-b32-lr2e-05-d0p1-s42-d1-f8c0ccef.jsonl",
+  "base_model": "BAAI/bge-m3",
+  "output_dir": "models/Hygroskopisch/new/model",
+  "prefix_mode": "no_prefix",
+  "source_of_prefix_setting": "dense_only_bge_m3_default",
+  "dense_only_bge_m3_default_applied": true,
+  "legacy_prefix_experiment_active": false,
+  "device": "cuda",
+  "epochs": 2,
+  "batch_size": 32,
+  "learning_rate": 2e-05,
+  "warmup_ratio": 0.1,
+  "max_length": 128,
+  "dev_ratio": 0.1,
+  "seed": 42,
+  "fp16": true,
+  "hard_negative_mode": "fallback",
+  "hard_negative_selection": "random_preselected",
+  "num_hard_negatives": 2,
+  "model_selection_metric": "hit5_mrr10",
+  "hard_negative_stats": {
+    "records_total": 14748,
+    "dropped_non_positive_weight": 0,
+    "records_after_mode": 14748,
+    "records_with_hard_negatives": 14748,
+    "examples_total": 29496,
+    "examples_per_record_avg": 2.0,
+    "dropped_no_hard_negatives": 0,
+    "fallback_negatives_used": 0,
+    "fallback_fill_count": 0,
+    "dropped_unusable": 0,
+    "use_hard_negatives": 1,
+    "num_hard_negatives_requested": 2,
+    "renormalized_weight_applied": 14748,
+    "preselected_used": 29496,
+    "preselected_used_count": 29496,
+    "preselected_missing_runtime_fallback": 0,
+    "preselected_conflicts_with_positives": 0
+  },
+  "sampler_mode": "UniquePositiveBatchSampler",
+  "sampler_query_positive_union_aware": true,
+  "train_queries_with_multiple_positives": 3226,
+  "save_each_epoch": false,
+  "steps_per_epoch": 7418,
+  "total_pairs": 16386,
+  "train_pairs": 14748,
+  "dev_pairs": 1638,
+  "epoch_checkpoints": []
+}

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2174406fd56fd8d5b49b5a7bc51c2a8a7986ceacaed6ad9f3ee57fbc799b84a
+size 17083074

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}