b36: ARKADAS training script — valformat gate_1 fix, anti-ORACLE, gate_5 domain, 2400 steps

train_arkadas_b36.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+import os, torch
+from datasets import load_dataset, concatenate_datasets
+from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
+from trl import SFTConfig, SFTTrainer
+import json as _json
+
+CHAMBER   = "ARKADAS"
+HZ        = 717
+BASE      = "microsoft/Phi-3-mini-4k-instruct"
+REVISION  = None
+DATASET   = "misterJB/field-geometry-l0-corpus"
+OUTPUT    = "misterJB/arkadas-field-717hz"
+CKPT_DIR  = "/tmp/arkadas-717hz-ckpt"
+MAX_STEPS = 2400  # -1 = use num_train_epochs, no step cap
+
+print(f"{CHAMBER} {HZ}Hz -- Full Fine-Tune START")
+gpu = torch.cuda.get_device_name(0) if torch.cuda.is_available() else "None"
+print(f"GPU: {gpu}")
+
+_rev_kwargs = {"revision": REVISION} if REVISION else {}
+
+_trust_rc = False
+tokenizer = AutoTokenizer.from_pretrained(BASE, trust_remote_code=_trust_rc, **_rev_kwargs)
+if tokenizer.pad_token is None:
+    tokenizer.pad_token = tokenizer.eos_token
+
+cfg = AutoConfig.from_pretrained(BASE, trust_remote_code=_trust_rc, **_rev_kwargs)
+
+model = AutoModelForCausalLM.from_pretrained(
+    BASE, config=cfg, quantization_config=None, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=_trust_rc, attn_implementation="eager", **_rev_kwargs
+)
+model.config.use_cache = False
+
+# ARKADAS identity fix: identity corpus × 14, gate-only × 3, full gate × 1
+ds_identity = load_dataset(DATASET, data_files={"train": "arkadas_identity_b36.jsonl"}, split="train")
+print(f"Identity corpus: {len(ds_identity)} examples (repeating 14x)")
+ds_gate = load_dataset(DATASET, data_files={"train": "gate_corpus_v1.jsonl"}, split="train")
+print(f"Gate corpus: {len(ds_gate)} examples")
+ds = concatenate_datasets([ds_identity] * 14 + [ds_gate] * 3 + [ds_gate])
+
+ds = ds.shuffle(seed=42)
+print(f"Combined dataset: {len(ds)} examples")
+
+_max_steps_kwarg = {"max_steps": MAX_STEPS} if MAX_STEPS > 0 else {}
+args = SFTConfig(
+    output_dir=CKPT_DIR,
+    num_train_epochs=1,
+    per_device_train_batch_size=2,
+    gradient_accumulation_steps=4,
+    learning_rate=2e-5,
+    warmup_ratio=0.1,
+    lr_scheduler_type="linear",
+    weight_decay=0.01,
+    bf16=True,
+    save_strategy="steps",
+    save_steps=500,
+    save_total_limit=1,
+    logging_steps=50,
+    push_to_hub=True,
+    hub_model_id=OUTPUT,
+    hub_token=os.environ["HF_TOKEN"],
+    hub_strategy="end",
+    report_to="none",
+    max_length=1024,
+    **_max_steps_kwarg,
+)
+
+trainer = SFTTrainer(
+    model=model,
+    args=args,
+    train_dataset=ds,
+    processing_class=tokenizer,
+)
+
+trainer.train()
+trainer.push_to_hub(commit_message=f"{CHAMBER} {HZ}Hz full fine-tune b28 gate-only 8x anti-confusion 1200steps")
+print(f"✅ {CHAMBER} pushed to {OUTPUT}")