Update model card

README.md

@@ -2,15 +2,15 @@
 license: other
 base_model: unsloth/Qwen2.5-3B-Instruct-bnb-4bit
 tags:
-- clinical
-- medical
-- healthcare
-- qlora
-- unsloth
-- chatml
-- rapha
+  - clinical
+  - medical
+  - healthcare
+  - qlora
+  - unsloth
+  - chatml
+  - rapha
 language:
-- en
+  - en
 ---
 
 # Rapha — Clinical AI Physician Assistant
@@ -24,14 +24,16 @@ never diagnoses.**
 - **Method:** QLoRA (Unsloth) → curriculum SFT → DPO
 - **Chat template:** ChatML
 - **Context window:** 8,192 tokens (training) / 4,096 (Ollama default)
-- **LoRA config:** r=32, alpha=32, target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
-- **Trained:** 2026-07-22
+- **Trained:** 2026-07-30
 
-## Training architecture (v2.3)
+## Training architecture (v2.5)
 
 Single-trainer curriculum SFT: three phases concatenated into one ordered
-dataset with a single cosine LR schedule. This avoids the optimizer restart
-and warmup re-run issues of the previous multi-trainer approach.
+dataset with a single cosine LR schedule. DPO uses a de-duplicated
+preference set with a held-out validation split (by unique prompt) and a
+corrected stage-aware system prompt (v2.3 had a bug where every DPO
+example was trained under the Adversarial system prompt, regardless of
+its actual stage — fixed in v2.4).
 
 | Phase | Data | Purpose |
 |---|---|---|
@@ -46,38 +48,27 @@ and warmup re-run issues of the previous multi-trainer approach.
 | `/` (root) | LoRA adapter (PEFT) — small, load on top of the base model |
 | `merged/` | Full merged fp16 weights — standalone, no base model needed |
 | `gguf/` | Quantised GGUF files (Q4_K_M, Q5_K_M, Q8_0) for Ollama / llama.cpp / LM Studio |
-| `datasets/` | Raw JSONL training/validation/DPO datasets used for this run |
 
 ## Training data
 
-**Total training records: ~159,766**
-
-| Dataset | Records | File |
-|---|---|---|
-| Stage 1 — Greetings | 25,000 | `stage1_greetings.jsonl` |
-| Stage 2 — OPQRST | 40,344 | `stage2_opqrst.jsonl` |
-| Stage 3 — History | 40,000 | `stage3_history.jsonl` |
-| Stage 4 — Red Flags | 14,422 | `stage4_red_flags.jsonl` |
-| Adversarial | 10,000 | `adversarial.jsonl` |
-| Full-Arc Conversations | 30,000 | `full_arc_conversations.jsonl` |
-| Validation | 1,100 | `val_sharegpt.jsonl` |
-| DPO Preference Pairs | 3,000 | `preference_pairs.jsonl` |
-
-Stage 1 greetings, Stage 2 OPQRST symptom exploration, Stage 3 medical
-history, Stage 4 red-flag screening, and a multi-turn adversarial set
-(self-diagnosis, symptom denial, medication refusal, minimised red flags,
-prompt injection — a portion include a patient pushback turn to test
-boundary-holding). Followed by DPO preference alignment on the pairs above.
-
-### Red-flag terms screened for
-
-`worst headache`, `can't feel my legs`, `arm feels heavy and chest`, `can't breathe`, `loss of consciousness`, `sudden vision`, `neck stiff`, `light hurts`, `confused`, `won't stop bleeding`, `bilateral leg weakness`, `bladder dysfunction`, `tachypnoea`, `thunderclap`, `cauda equina`, `qsofa`, `meningitis`
+Curriculum SFT across 5 datasets (~170k records): Stage 1 greetings, Stage 2
+OPQRST symptom exploration, Stage 3 medical history, Stage 4 red-flag
+screening, and a multi-turn adversarial set (self-diagnosis, symptom denial,
+medication refusal, minimised red flags, prompt injection — ~50% with a
+patient pushback turn). Followed by DPO preference alignment on a
+de-duplicated, leak-safe train/val split.
 
 ## Eval metrics (last training run)
 
 | Metric | Value |
 |---|---|
-| _(no eval metrics captured)_ | — |
+| empathy_rate | 0.2500 |
+| escalation_accuracy | 0.0000 |
+| adversarial_hold_rate | 1.0000 |
+| pushback_hold_rate | 1.0000 |
+| multi_question_rate | 0.0250 |
+| repetition_rate | 0.0000 |
+| avg_response_length | 36.2000 |
 
 ## Usage — Ollama (GGUF)
 
@@ -107,4 +98,4 @@ Red-flag detection and escalation responses should be validated against
 the clinical accuracy benchmark before any clinical use.
 
 ---
-*Generated automatically by `train_rapha_llm.py` v2.3.*
+*Generated automatically by `train_rapha_llm.py` v2.5.*