Update model to version 4 (#4)

- Update model to version 4 (85a9e9d59203caa3e65336309f161f1c9496ae37)


Co-authored-by: Marlon Amunga <[email protected]>

README.md

@@ -1,97 +1,147 @@
 ---
 datasets:
-- ner_distillbert
-- openchs/synthetic-helpline-ner-v1
+- ner_dataset_2.jsonl
 language:
 - en
-library_name: pytorch
 license: apache-2.0
+model-index:
+- name: ner-distilbert-base-cased
+  results:
+  - dataset:
+      name: ner_dataset_2.jsonl
+      type: ner_dataset_2.jsonl
+    metrics:
+    - name: Eval Loss
+      type: eval_loss
+      value: 0.0216
+    - name: Eval Accuracy
+      type: eval_accuracy
+      value: 0.993
+    - name: Eval F1
+      type: eval_f1
+      value: 0.9929
+    - name: Eval Recall
+      type: eval_recall
+      value: 0.993
+    - name: Eval Precision
+      type: eval_precision
+      value: 0.9933
+    task:
+      name: Ner
+      type: token-classification
 tags:
 - ner
-- pytorch
+- sklearn
 - mlflow
-- helpline
-task: token-classification
-metrics:
-- accuracy
-base_model:
-- distilbert/distilbert-base-uncased
+- transformers
+- openchs
 ---
 
-# ner_distillbert
+# ner-distilbert-base-cased
 
-## Model Description
+This model performs ner trained using MLflow and deployed on Hugging Face.
 
-This is a Named Entity Recognition (NER) model based on DistilBERT, a distilled version of BERT that retains 97% of BERT's performance while being 60% smaller and faster. The model identifies and classifies named entities in text such as persons, organizations, locations, and other predefined categories.
+## Model Details
 
-**Model Details:**
-- **Model Name:** ner_distillbert
-- **Version:** 1
+- **Model Name:** ner-distilbert-base-cased
+- **Version:** 4
 - **Task:** Ner
-- **Framework:** pytorch
-- **Language(s):** en
+- **Languages:** en
+- **Framework:** sklearn
 - **License:** apache-2.0
 
-## Intended Uses
+## Intended Uses & Limitations
 
-This model is designed for ner tasks. Please evaluate on your specific use case before production deployment.
+### Intended Uses
+- Ner tasks
+- Research and development
+- Child helpline services support
 
-## Training Details
+### Limitations
+- Performance may vary on out-of-distribution data
+- Should be evaluated on your specific use case before production deployment
+- Designed for child helpline contexts, may need adaptation for other domains
 
-### Training Data
-- **Dataset:** ner_distillbert
-- **Dataset Size:** Not specified
+## Training Data
 
-### Training Configuration
+- **Dataset:** ner_dataset_2.jsonl
+- **Size:** Not specified
+- **Languages:** en
+
+## Training Configuration
+
+| Parameter | Value |
+|-----------|-------|
+| Author | Rogendo |
+| Batch Size | 4 |
+| Epochs | 10 |
+| Lr | 2e-05 |
+| Model Name | distilbert-base-cased |
+| Test Size | 0.1 |
+| Training Date | 2025-10-30T11:58:48.315647 |
+| Weight Decay | 0.01 |
+
+## Performance Metrics
+
+### Evaluation Results
+| Metric | Value |
+|--------|-------|
+| Epoch | 10.0000 |
+| Eval Accuracy | 0.9930 |
+| Eval F1 | 0.9929 |
+| Eval Loss | 0.0216 |
+| Eval Precision | 0.9933 |
+| Eval Recall | 0.9930 |
+| Eval Runtime | 0.1509 |
+| Eval Samples Per Second | 106.0170 |
+| Eval Steps Per Second | 13.2520 |
 
 ## Usage
 
 ### Installation
 ```bash
-pip install transformers torch  # For transformers models
-# OR
-pip install -r requirements.txt  # For other frameworks
+pip install transformers torch
 ```
 
-### Basic Usage
+### Named Entity Recognition Example
 ```python
-# Load and use the model
-from inference import Model  # See inference.py in the repository
+from transformers import pipeline
+
+ner = pipeline("ner", model="openchs/ner_distillbert_v1", aggregation_strategy="simple")
+text = "John Smith works at OpenCHS in Nairobi and can be reached at [email protected]"
+entities = ner(text)
 
-model = Model(openchs/ner_distillbert_v1)
-predictions = model.predict([President Biden met with Chancellor Merkel at the White House to discuss NATO policies.])
-print(predictions)
+for entity in entities:
+    print(f"{entity['entity_group']}: {entity['word']} (score: {entity['score']:.2f})")
 ```
 
-## Performance Metrics
-
-### Evaluation Results
-| Metric | Value |
-|--------|-------|
-| Epoch | 3.0000 |
-| Eval Accuracy | 0.9608 |
-| Eval F1 | 0.9433 |
-| Eval Loss | 0.1171 |
-| Eval Precision | 0.9324 |
-| Eval Recall | 0.9608 |
-| Eval Runtime | 0.1943 |
-| Eval Samples Per Second | 82.3410 |
-| Eval Steps Per Second | 10.2930 |
 
 ## MLflow Tracking
 
-- **Experiment:** N/A
-- **Run ID:** `N/A`
-- **Training Date:** N/A
+- **Experiment:** NER_Distilbert/marlon
+- **Run ID:** `10d2648a456a4f6ab74022a9e45c9f40`
+- **Training Date:** 2025-10-30 11:58:48
+- **Tracking URI:** http://192.168.10.6:5000
+
+## Training Metrics Visualization
+
+View detailed training metrics and TensorBoard logs in the [Training metrics](https://huggingface.co/openchs/ner_distillbert_v1/tensorboard) tab.
 
 ## Citation
 
 ```bibtex
-@misc{ner_distillbert_1,
-  title={ner_distillbert},
-  author={BITZ-AI TEAM},
+@misc{ner_distilbert_base_cased,
+  title={ner-distilbert-base-cased},
+  author={OpenCHS Team},
   year={2025},
   publisher={Hugging Face},
-  url={https://huggingface.co/marlonbino/ner_distillbert}
+  url={https://huggingface.co/openchs/ner_distillbert_v1}
 }
-```
+```
+
+## Contact
+
+[email protected]
+
+---
+*Model card auto-generated from MLflow*

config.json

@@ -6,31 +6,30 @@
   "attention_dropout": 0.1,
   "dim": 768,
   "dropout": 0.1,
+  "dtype": "float32",
   "hidden_dim": 3072,
   "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6",
-    "7": "LABEL_7",
-    "8": "LABEL_8",
-    "9": "LABEL_9"
+    "0": "CALLER",
+    "1": "PERPETRATOR",
+    "2": "GENDER",
+    "3": "VICTIM",
+    "4": "AGE",
+    "5": "LOCATION",
+    "6": "INCIDENT_TYPE",
+    "7": "O",
+    "8": "COUNSELOR"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5,
-    "LABEL_6": 6,
-    "LABEL_7": 7,
-    "LABEL_8": 8,
-    "LABEL_9": 9
+    "AGE": 4,
+    "CALLER": 0,
+    "COUNSELOR": 8,
+    "GENDER": 2,
+    "INCIDENT_TYPE": 6,
+    "LOCATION": 5,
+    "O": 7,
+    "PERPETRATOR": 1,
+    "VICTIM": 3
   },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
@@ -42,7 +41,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.53.2",
+  "transformers_version": "4.56.2",
   "vocab_size": 28996
 }

logs/run_20251030_124314/1761817394.2624462/events.out.tfevents.1761817394.bitz-B760M-DS3H.33391.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a127786ab6f865c09c1a92d3339be0030501ed6414c24279f0d0de50322d787
+size 1263

logs/run_20251030_124314/events.out.tfevents.1761817394.bitz-B760M-DS3H.33391.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b607437e29eae1a9efe5fae22777bee1d9b89b593ef5f96ddc179f31c3ae139
+size 615

metadata.json

@@ -1,46 +1,54 @@
 {
   "mlflow": {
     "run_info": {
-      "run_id": "c46339588b6f41d5b8ecde878813d1f9",
-      "experiment_id": "35",
-      "experiment_name": "NER_Distilbert",
-      "start_time": "2025-09-29 16:23:10",
-      "end_time": "2025-09-29 16:23:30",
+      "run_id": "10d2648a456a4f6ab74022a9e45c9f40",
+      "experiment_id": "118",
+      "experiment_name": "NER_Distilbert/marlon",
+      "start_time": "2025-10-30 11:58:48",
+      "end_time": "2025-10-30 11:59:21",
       "status": "FINISHED",
-      "artifact_uri": "/opt/chl_ai/mlflow-shared/artifacts/35/c46339588b6f41d5b8ecde878813d1f9/artifacts"
+      "artifact_uri": "/opt/chl_ai/mlflow-shared/artifacts/118/10d2648a456a4f6ab74022a9e45c9f40/artifacts"
     },
     "metrics": {
-      "eval_loss": 0.11714156717061996,
-      "eval_accuracy": 0.9608154296875,
-      "eval_f1": 0.9432683470010941,
-      "eval_recall": 0.9608154296875,
-      "eval_precision": 0.9324452434283989,
-      "eval_runtime": 0.1943,
-      "eval_samples_per_second": 82.341,
-      "eval_steps_per_second": 10.293,
-      "epoch": 3.0
+      "eval_loss": 0.021556653082370758,
+      "eval_accuracy": 0.9930419921875,
+      "eval_f1": 0.9928845565611383,
+      "eval_recall": 0.9930419921875,
+      "eval_precision": 0.9933225081085078,
+      "eval_runtime": 0.1509,
+      "eval_samples_per_second": 106.017,
+      "eval_steps_per_second": 13.252,
+      "epoch": 10.0
     },
     "params": {
       "model_name": "distilbert-base-cased",
-      "epochs": "3",
+      "epochs": "10",
       "lr": "2e-05",
-      "batch_size": "8",
+      "batch_size": "4",
       "weight_decay": "0.01",
-      "test_size": "0.1"
+      "test_size": "0.1",
+      "training_date": "2025-10-30T11:58:48.315647",
+      "author": "Rogendo"
     },
     "tags": {
       "mlflow.user": "marlon",
-      "mlflow.source.name": "trainer.py",
+      "mlflow.source.name": "run_trainer.py",
       "mlflow.source.type": "LOCAL",
-      "mlflow.source.git.commit": "e03704543c1c918f19e5d1b560a8755096229b82",
+      "mlflow.source.git.commit": "1d336ef46e41caf713898d4d91d142c43907a543",
       "mlflow.runName": "NER_Distilbert"
     }
   },
-  "user": {},
+  "user": {
+    "model_name": "distilbert-base-cased",
+    "dataset_name": "ner_dataset_2.jsonl",
+    "language": "en",
+    "task_type": "ner",
+    "framework": "sklearn"
+  },
   "export": {
-    "method": "unknown",
-    "timestamp": "2025-10-01T15:55:51.912552",
-    "version": "1",
-    "mode": "metrics_only"
+    "method": "transformers",
+    "timestamp": "2025-10-30T12:43:14.264498",
+    "version": "4",
+    "mode": "full_update"
   }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d45a23c83fc64bbf0f95dc9b2b1a5a5c37c24a708c11b9ebbba2c63a7ac491b
-size 260806744
+oid sha256:215db0321a1a85118a83e7da4dac593eb20c073d8bc4a71d24a2b31f68ee3e34
+size 260803668

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -46,11 +46,18 @@
   "do_lower_case": false,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }