ablation-pymethods2test-shaped-45-8B/training_logs/20260612_220132_metrics_job_628826.csv

1	async/discard_rate	async/discarded_count	async/effective_batch_groups	async/effective_batch_samples	async/staleness_max	async/staleness_mean	async/staleness_min	async/staleness_ratio	generate/avg_num_tokens	generate/avg_tokens_non_zero_rewards	generate/avg_tokens_zero_rewards	generate/max_num_tokens	generate/min_num_tokens	generate/std_num_tokens	loss/avg_final_rewards	loss/avg_raw_advantages	loss/avg_raw_advantages_abs	policy/final_loss	policy/log_ratio_abs_max	policy/log_ratio_abs_mean	policy/log_ratio_abs_p99	policy/log_ratio_abs_pos00	policy/log_ratio_abs_pos10	policy/log_ratio_abs_pos20	policy/log_ratio_abs_pos30	policy/log_ratio_abs_pos40	policy/log_ratio_abs_pos50	policy/log_ratio_abs_pos60	policy/log_ratio_abs_pos70	policy/log_ratio_abs_pos80	policy/log_ratio_abs_pos90	policy/n_tokens_dp_gt_10pct	policy/n_tokens_dp_gt_1pct	policy/n_tokens_dp_gt_50pct	policy/policy_entropy	policy/policy_loss	policy/policy_lr	policy/policy_update_steps	policy/ppo_clip_ratio	policy/raw_grad_norm	reward/avg_pass_at_8	reward/avg_raw_reward	system/process_rss_gb	system/process_vms_gb	system/ram_available_gb	system/ram_percent	system/ram_total_gb	system/ram_used_gb	timing/compute_advantages_and_returns	timing/convert_to_training_input	timing/fwd_logprobs_values_reward	timing/policy_train	timing/run_training	timing/step	timing/sync_weights	timing/train_critic_and_policy	timing/wait_for_generation_buffer	trainer/epoch	trainer/global_step	batch_errors/total_batches	batch_errors/total_instances	batch_errors/total_successful	batch_errors/total_failed	batch_errors/total_masked	batch_errors/avg_VerifierTimeoutError	batch_errors/total_VerifierTimeoutError	batch_errors/avg_ContextLengthExceededError	batch_errors/total_ContextLengthExceededError	batch_errors/avg_InvalidChatHistory	batch_errors/total_InvalidChatHistory	timing/cleanup_old_checkpoints	timing/save_checkpoints	batch_errors/avg_AgentTimeoutError	batch_errors/total_AgentTimeoutError	batch_errors/avg_DaytonaError	batch_errors/total_DaytonaError	timing/save_hf_model	batch_errors/avg_AgentSetupTimeoutError	batch_errors/total_AgentSetupTimeoutError	batch_errors/avg_DaytonaAuthenticationError	batch_errors/total_DaytonaAuthenticationError
2	0.0	0	64	512	3	0.3125	0	0.1562	3212.9512	3060.2589	3599.4207	25987	1	2338.6713	0.7168	0.006	0.1066	-0.0002	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0976	-0.0106	0.0	1.0	0.0	0.0154	0.8136	0.7168	10.7443	50.2974	572.7775	33.2	857.9676	285.1901	0.2346	3.8459	30.3294	122.9738	153.7887	2578.924	24.1815	123.2241	2397.1075	0	63	65	520	503	10	16	0.015384615384615385	1.0	0.07692307692307693	5	0.16923076923076924	11
3	0.0	0	64	512	1	0.7969	0	0.7969	4535.9375	4288.981	4934.0918	31787	1	3261.3111	0.6172	0.0105	0.0579	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1193	-0.0	0.0	1.0	0.0	0.0124	0.6562	0.6172	12.7589	50.5271	567.3896	33.9	857.9676	290.5779	0.0738	5.7156	29.8831	163.5481	193.777	2364.0615	23.8467	163.8194	2140.7174	0	64	57	456	350	33	106	0.03508771929824561	2.0	0.14035087719298245	8	1.8070175438596492	103	13.7898	21.7901	0.17543859649122806	10.0	0.017543859649122806	1.0
4	0.0	0	64	512	2	1.5625	0	0.9844	3972.8203	4672.6544	3719.6888	31688	1	4306.1245	0.2656	0.0172	0.0813	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1093	0.0	0.0	1.0	0.0	0.0106	0.4062	0.2656	12.8392	50.6329	566.724	33.9	857.9676	291.2436	0.0933	4.7412	30.4057	181.6246	212.4095	710.5469	22.8651	181.9099	470.525	0	65	58	464	417	13	34	0.22413793103448276	13.0	0.06896551724137931	4	0.6206896551724138	36			0.017241379310344827	1.0			6.9862
5	0.0	0	64	512	3	1.7188	0	0.8906	4121.877	4062.4562	4190.2857	31735	1	3737.8543	0.5352	0.0191	0.1223	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1086	-0.0016	0.0	1.0	0.0	0.0189	0.6875	0.5352	12.9229	50.747	566.2948	34.0	857.9676	291.6728	0.082	4.6144	30.3875	177.256	208.0248	1419.1444	21.1494	177.5549	1185.3513	0	66	64	512	446	20	62	0.0625	4.0	0.09375	6	0.828125	53	0.0296	7.9612	0.03125	2.0	0.015625	1.0
6	0.0	0	64	512	4	1.7656	0	0.75	4548.4258	5085.392	4267.1577	31721	1	4466.4205	0.3438	0.0189	0.08	-0.0001	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.111	-0.0039	0.0	1.0	0.0	0.0106	0.4219	0.3438	13.1517	50.9762	565.8719	34.0	857.9676	292.0957	0.1053	4.6859	37.4981	207.9956	245.8996	2122.2256	28.164	208.2957	1843.4698	0	67	62	496	406	25	88	0.03225806451612903	2.0	0.06451612903225806	4	1.2580645161290323	78			0.11290322580645161	7.0
7	0.0	0	64	512	5	1.6875	0	0.9531	3900.3008	4422.9592	3576.1203	31728	1	3986.5011	0.3828	-0.0061	0.119	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1031	-0.0	0.0	1.0	0.0	0.0157	0.5	0.3828	13.1199	50.9385	564.5773	34.2	857.9676	293.3903	0.0729	4.6002	30.5859	176.2726	207.1868	1248.7385	22.7304	176.5273	1014.2161	0	68	64	512	456	17	53	0.046875	3.0	0.046875	3	0.734375	47	0.0101	8.9855	0.046875	3.0
8	0.0	0	64	512	3	1.6562	0	0.8906	3996.1523	3658.4788	4284.8877	31658	1	3365.4959	0.4609	0.0031	0.0935	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1101	-0.0	0.0	1.0	0.0	0.0154	0.5469	0.4609	13.989	51.1971	563.4398	34.3	857.9676	294.5278	0.0907	4.7091	25.5046	155.0343	180.9023	1332.3415	27.9054	155.3066	1118.8162	0	69	61	488	429	18	59			0.09836065573770492	6	0.9344262295081968	57			0.01639344262295082	1.0
9	0.0	0	64	512	3	1.5625	0	0.8594	3865.9531	3843.2096	3884.3569	31729	1	3913.163	0.4473	-0.0107	0.0938	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.103	0.0	0.0	1.0	0.0	0.0162	0.5469	0.4473	14.0488	51.2578	563.1133	34.4	857.9676	294.8543	0.0701	4.7381	27.9634	163.6438	191.9411	1573.6054	24.5297	163.9072	1352.3918	0	70	59	472	407	16	61	0.06779661016949153	4.0	0.03389830508474576	2	1.0677966101694916	63	0.0091	8.8785	0.03389830508474576	2.0			6.6827
10	0.0	0	64	512	4	1.5469	0	0.9375	4000.8145	4048.4398	3958.4613	19932	1	3429.9239	0.4707	-0.0016	0.1175	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1043	-0.0	0.0	1.0	0.0	0.0159	0.625	0.4707	13.827	51.1002	562.6223	34.4	857.9676	295.3453	0.0691	3.1795	25.4564	156.8136	182.6179	1325.101	24.226	157.0917	1115.0701	0	71	63	504	424	21	77	0.047619047619047616	3.0	0.031746031746031744	2	1.1746031746031746	74			0.015873015873015872	1.0
11	0.0	0	64	512	4	1.625	0	0.9062	3909.4648	3903.1875	3913.2312	21731	1	3487.2979	0.375	0.0049	0.1063	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1072	0.0	0.0	1.0	0.0	0.0127	0.4688	0.375	13.9503	51.2075	561.9954	34.5	857.9676	295.9722	0.0666	3.4426	27.267	163.5783	191.2401	1530.8972	24.8288	163.9058	1311.3809	0	72	61	488	392	26	96			0.03278688524590164	2	1.540983606557377	94	0.0082	8.5919
12	0.0	0	64	512	3	1.4531	0	0.8438	3892.7324	4250.0823	3598.968	31727	1	4215.9467	0.4512	-0.0032	0.054	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0979	0.0	0.0	1.0	0.0	0.016	0.5312	0.4512	14.2002	51.4395	562.7875	34.4	857.9676	295.1801	0.0663	4.6386	28.847	179.0119	208.2091	1586.4309	22.6523	179.2954	1350.9267	0	73	62	496	444	20	51	0.03225806451612903	2.0	0.04838709677419355	3	0.7741935483870968	48			0.0967741935483871	6.0
13	0.0	0	64	512	4	1.625	0	0.8281	4627.0781	4912.5607	4422.0671	31779	1	4396.9421	0.418	-0.0113	0.1153	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1037	0.0	0.0	1.0	0.0	0.0163	0.5469	0.418	14.2074	51.4462	562.0214	34.5	857.9676	295.9462	0.0676	4.8121	34.6294	197.6062	232.6055	1485.3391	22.7112	197.9081	1225.2061	0	74	61	488	400	21	69	0.36065573770491804	22.0	0.01639344262295082	1	1.0819672131147542	66	0.0101	8.716	0.01639344262295082	1.0
14	0.0	0	64	512	3	1.8594	1	1.0	3627.1289	3950.0	3361.7082	24803	1	3212.1194	0.4512	0.0103	0.0629	-0.0001	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1013	-0.0061	0.0	1.0	0.0	0.0148	0.5156	0.4512	14.2832	51.4595	562.0718	34.5	857.9676	295.8958	0.0741	3.8123	25.7174	144.2323	170.2738	1332.0754	26.5799	144.4819	1131.3878	0	75	60	480	401	23	79			0.06666666666666667	4	1.35	81			0.05	3.0			7.0029
15	0.0	0	64	512	3	2.3438	2	1.0	3952.7734	4178.1104	3855.8408	31737	1	3643.2581	0.3008	-0.0053	0.1026	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0974	0.0	0.0	1.0	0.0	0.0257	0.4062	0.3008	14.4194	51.6903	561.2421	34.6	857.9676	296.7255	0.082	4.6294	28.9629	162.0516	191.402	1875.4162	24.6133	162.3568	1654.7496	0	76	61	488	410	21	77	0.01639344262295082	1.0	0.03278688524590164	2	1.4098360655737705	86	0.0086	8.2613	0.01639344262295082	1.0
16	0.0	0	64	512	3	3.0	3	1.0	3720.1211	3738.1695	3710.5851	31683	1	3286.5665	0.3457	0.0014	0.0701	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1044	-0.0	0.0	1.0	0.0	0.0163	0.4219	0.3457	14.4559	51.6895	560.5397	34.7	857.9676	297.4279	0.0904	4.6185	24.9949	150.9842	176.3639	1368.0435	24.1864	151.2781	1162.8469	0	77	63	504	382	33	113	0.14285714285714285	9.0	0.14285714285714285	9	1.619047619047619	102			0.031746031746031744	2.0
17	0.0	0	64	512	4	4.0	4	1.0	3750.1133	3737.0709	3755.0701	31752	1	3546.4326	0.2754	0.0005	0.0538	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0972	-0.0	0.0	1.0	0.0	0.0103	0.3594	0.2754	14.777	52.0029	559.1461	34.8	857.9676	298.8215	0.0904	4.5998	26.0086	154.5381	180.9664	1663.0565	20.6241	154.8668	1456.8378	0	78	96	768	677	28	87	0.041666666666666664	4.0	0.23958333333333334	23	0.7083333333333334	68	0.0084	8.9896	0.03125	3.0
18	0.0	0	64	512	0	0.0	0	0.0	3445.207	3148.4329	4447.1368	16283	1246	2094.0951	0.7715	-0.0007	0.0106	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0922	0.0	0.0	1.0	0.0	0.008	0.7812	0.7715	14.3432	51.7614	559.8598	34.7	857.9676	298.1078	0.0389	2.652	23.5649	113.9723	137.7901	3065.3214	22.3426	114.1859	2902.5137	1	79	69	552	295	54	198	0.43478260869565216	30.0	0.08695652173913043	6	0.34782608695652173	24			2.4347826086956523	168.0				0.5072463768115942	35.0
19	0.0	0	64	512	1	0.7812	0	0.7812	2892.1074	4823.0845	2151.0297	31540	1	3993.9597	0.2773	0.0169	0.1069	-0.0001	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0661	-0.0053	0.0	1.0	0.0	0.0132	0.4375	0.2773	14.7557	52.215	560.3083	34.7	857.9676	297.6592	0.0847	4.3929	23.704	158.7652	182.8215	3331.0036	18.6838	159.0324	3125.1035	1	80	16	128	86	14	21	0.8125	13.0	0.0625	1	0.3125	5	0.0078	29.8329	0.9375	15.0			7.9827	0.4375	7.0	0.0625	1.0