End of training

README.md

@@ -1,70 +1,65 @@
 ---
-language:
-- en
-- fr
-- es
-- de
-- it
-- pt
-- zh
-- ar
-- ru
+library_name: transformers
+license: apache-2.0
+base_model: distilbert-base-multilingual-cased
 tags:
-- text-classification
-- intent-classification
-- enterprise-ai
-- voice-ai
-- multilingual
-- distilbert
-license: mit
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: intent-classifier
+  results: []
 ---
 
-# ConceptNet Intent Classifier
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-Fine-tuned `distilbert-base-multilingual-cased` on the ConceptNet 4-layer enterprise voice intent taxonomy.
+# intent-classifier
 
-## Independent Evaluation — August 2026
+This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0071
+- Accuracy: 1.0
 
-Independently tested by the Hugging Face community (John6666):
-- Neural model: **99.315%** on reconstructed public test split
-- Grouped lexical-family holdout: **99.78%**
-- Conclusion: "The obvious train/test leakage explanation did not survive that check"
+## Model description
 
-## Accuracy
-- Fast-path classifier: **83%** · <5ms latency  
-- Neural model: **98.6%** (99.3% independently verified)
-- L3 Predictive precision: **100%**
-- Dataset: 757 examples across 9 languages (updated with L3 paraphrase diversity)
+More information needed
 
-## Cascade Performance
-| Threshold | Fast coverage | Fast accuracy | Final accuracy |
-|-----------|--------------|---------------|----------------|
-| 0.50 | 69.2% | 95.0% | 95.9% |
-| 0.55 | 60.3% | 98.9% | 98.6% |
-| 0.65 | 43.2% | 100% | 99.3% |
+## Intended uses & limitations
 
-## Layer Precedence (mixed semantics)
-When a command contains signals from multiple layers: **L4 > L3 > L2 > L1**
+More information needed
 
-## The 4 Layers
-- **L1 Basic** — "Do X" — immediate execution
-- **L2 Context-Aware** — "Do X when Y" — conditional
-- **L3 Predictive** — "Do X before/ahead of/prior to Y" — proactive
-- **L4 Autonomous** — "Do X always" — persistent agent
+## Training and evaluation data
 
-## Languages
-English · French · Spanish · German · Italian · Portuguese · Chinese · Arabic · Russian
+More information needed
 
-## Usage
-```python
-from transformers import pipeline
-classifier = pipeline("text-classification", model="conceptnetUk/intent-classifier")
-classifier("Send the report when the contract is signed")
-```
+## Training procedure
 
-## Links
-- Sandbox: https://conceptnet.co.uk/sandbox/
-- GitHub: https://github.com/wushu75/ConceptNet
-- Website: https://conceptnet.co.uk
+### Training hyperparameters
 
-*© 2026 ConceptNet Ltd · Patents pending*
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 38   | 0.2696          | 0.9342   |
+| No log        | 2.0   | 76   | 0.0652          | 0.9868   |
+| No log        | 3.0   | 114  | 0.0401          | 0.9934   |
+| No log        | 4.0   | 152  | 0.0075          | 1.0      |
+| No log        | 5.0   | 190  | 0.0071          | 1.0      |
+
+
+### Framework versions
+
+- Transformers 5.15.1
+- Pytorch 2.11.0+cpu
+- Datasets 4.0.0
+- Tokenizers 0.22.2

config.json

@@ -35,7 +35,7 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "tie_word_embeddings": true,
-  "transformers_version": "5.15.0",
+  "transformers_version": "5.15.1",
   "use_cache": false,
   "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4934ed4bfeb0c9e04a857e53a6df65403c823fb89c76469db2caf273836eaebf
+oid sha256:6ab5f4ca713f098792b03b17ccba6a42bb3a3ec2f7f9624950b4576bd8452e30
 size 541323528

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e7fc8cad10b25f6f55e0d0b510aeb70b111eb30216129eb606911e9ab0f802
-size 5201
+oid sha256:575a3ea3b4b2ff0e735dd4863828c480058f475a19882863e1013b9506a012ec
+size 5265