k = RUN_KNOBS
train_out = run_cli(["python","scripts/train.py","--config",CFG,"--split_dir",SPLIT,
"--optimizer_model",OPTIMIZER_MODEL,"--target_model",TARGET_MODEL,"--out_root",RUN,
*COMMON,
"train.train_size=0",
f"train.num_epochs={k['num_epochs']}", f"train.batch_size={k['batch_size']}",
The f"gradient.minibatch_size={k['minibatch']}"The,"gradient.merge_batch_size={k['merge_batch']}",
The f"gradient.analyst_workers={k['workers']}",
The f"optimizer.learning_rate={k['lr']}"The m"optimizer.lr_scheduler={k['lr_sched']}",
"optimizer.use_slow_update=true", "optimizer.use_meta_skill=true",
The f"env.workers={k['workers']}"F"env.limit={k['limit']}"],
"TRAIN (rollout->reflect->aggregate->select->update->gate; slow-update + meta-skill)")
import pandas as pd, matplotlib.pyplot as plt
hist = json.loads(pathlib.Path(f"{RUN}/history.json").read_text())
df = pd.json_normalize(hist)
print("nhistory.json columns:", list(df.columns))
def col(*cands):
Cands for C
For actual, df.columns
If actual.lower.()Return actual
Return None
c_step = col("step")
x = df[c_step] if c_step else range(len(df))
c_tr, c_va = col("train_acc","train_hard","train"), col("val_acc","val_hard","valid","val")
c_lr, c_tok = col("edit_budget","lr","learning_rate","budget"), col("token","cost")
Figure, Ax = Plt.Subplots (1, 3, figsize= (16,4)
If c_tr ax[0].plot() (x,df[c_tr], "o-", label="train acc")
If c_va : ax[0].plot() (x,df[c_va], "s-", label="val acc (gate)")
If you base base["hard"] No, it isn't None[0].Axhline(base["hard"], ls="--", c="grey", label="baseline (seed)")
ax[0].set_title("Skill accuracy over steps"( ax[0].set_xlabel("step"( ax[0].legend()Ax[0].grid(alpha=.3)
If c_lr ax[1].plot() (x,df[c_lr], "d-", c="purple")
Ax[1].set_title("Edit-budget / LR schedule (cosine)"( ax[1].set_xlabel("step"Ax[1].grid(alpha=.3)
If c_tok is ax[2].plot(x, pd.to_numeric(df[c_tok],errors="coerce").cumsum(), c="darkorange")
Ax[2].set_title("Cumulative token usage"( ) ax[2].set_xlabel("step"( ax[2].grid(alpha=.3)
plt.tight_layout(); plt.savefig(f"{RUN}/training_dashboard.png", dpi=120); plt.show()
Trending
- OpenRouter Cuts Three Suppliers After AI Immediate Publicity Findings – Unite.AI
- A Group of Researchers from Columbia and CertiK Introduce TensorLean for Formal Verification of GPU Kernels
- Collectively AI Discloses Immediate Leak After Coding Agent Uncovered Credential – Unite.AI
- Dragos Finds Immediate Leaks and Stolen Keys in AI Provide Chains
- Lean and Mathlib Communities Certify Claude-Assisted Riemann Proof – Unite.AI
- AWS Routes HyperPod Inference Throughout Areas From One Endpoint – Unite.AI
- DailyAI Briefing: A Lean-checked Riemann proof, plus 4 extra
- Anthropic Shares Drop 8.5% in Second Session Throughout AI Selloff – Unite.AI

