ablation-pymethods2test-seqnorm-15-8B/training_logs/20260608_210110_metrics_job_639473.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_InvalidChatHistory	batch_errors/total_InvalidChatHistory	batch_errors/avg_AgentSetupTimeoutError	batch_errors/total_AgentSetupTimeoutError	batch_errors/avg_AgentTimeoutError	batch_errors/total_AgentTimeoutError	batch_errors/avg_ContextLengthExceededError	batch_errors/total_ContextLengthExceededError	batch_errors/avg_VerifierTimeoutError	batch_errors/total_VerifierTimeoutError	timing/cleanup_old_checkpoints	timing/save_checkpoints	timing/save_hf_model	batch_errors/avg_DaytonaError	batch_errors/total_DaytonaError	batch_errors/avg_DaytonaAuthenticationError	batch_errors/total_DaytonaAuthenticationError
2	0.0	0	64	512	0	0.0	0	0.0	2574.8984	3414.6373	2066.8433	14422	1	2612.5608	0.377	0.1212	0.1534	-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	0.0885	-0.0	0.0	1.0	0.0	0.0	0.5625	0.377	7.261	50.0898	573.4373	33.2	857.9675	284.5302	0.0455	2.2784	38.4903	117.0694	155.8179	9181.4558	19.7276	117.2818	9003.6315	0	49	60	480	400	37	48	0.21666666666666667	13	0.18333333333333332	11.0	0.38333333333333336	23.0	0.26666666666666666	16	0.4666666666666667	28.0
3	0.0	0	64	512	1	1.0	1	1.0	3732.3652	3769.9299	3715.7521	31808	1	4078.5665	0.3066	0.024	0.0998	-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	0.117	-0.0	0.0	1.0	0.0	0.0	0.4531	0.3066	12.5825	50.4959	566.5182	34.0	857.9675	291.4493	0.0686	4.4722	26.4647	178.2315	205.0064	611.3836	22.5264	178.4728	379.3765	0	50	61	488	454	16	7	0.06557377049180328	4	0.03278688524590164	2.0	0.01639344262295082	1.0	0.01639344262295082	1	0.4098360655737705	25.0	73.2928	82.7069	20.5797	0.01639344262295082	1.0
4	0.0	0	64	512	2	1.5312	0	0.875	4180.8438	3657.6311	4591.0279	17255	1	3125.6494	0.4395	0.0131	0.0883	-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	0.1311	-0.0	0.0	1.0	0.0	0.0	0.5312	0.4395	12.5143	50.4529	565.7725	34.1	857.9675	292.1951	0.0393	2.8336	28.712	150.3515	179.3291	1837.5348	23.3846	150.5774	1631.9841	0	51	63	504	477	13	26	0.2222222222222222	14			0.015873015873015872	1.0	0.14285714285714285	9	0.015873015873015872	1.0				0.031746031746031744	2.0
5	0.0	0	64	512	3	1.6719	0	0.8906	4772.627	4960.8151	4609.1642	31652	1	3769.5395	0.4648	0.014	0.0786	-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	0.1376	-0.0	0.0	1.0	0.0	0.0	0.5781	0.4648	12.8545	50.8127	566.1333	34.0	857.9675	291.8342	0.0654	5.1247	31.4543	178.3831	210.1787	1732.7267	22.7374	178.6587	1494.6839	0	52	61	488	431	19	52	0.639344262295082	39			0.11475409836065574	7.0	0.13114754098360656	8	0.06557377049180328	4.0	0.0085	8.3109		0.06557377049180328	4.0	0.01639344262295082	1.0
6	0.0	0	64	512	4	2.0156	0	0.9531	4045.3574	4180.3436	3982.3123	31771	1	3952.5092	0.3184	0.0176	0.1401	-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	0.1307	-0.0	0.0	1.0	0.0	0.0	0.5	0.3184	13.2115	51.1639	565.3646	34.1	857.9675	292.603	0.0634	4.4954	29.8155	172.7807	202.884	1262.3478	25.742	173.0047	1029.2236	0	53	65	520	492	13	26	0.27692307692307694	18			0.046153846153846156	3.0	0.03076923076923077	2	0.03076923076923077	2.0				0.046153846153846156	3.0
7	0.0	0	64	512	3	1.7031	0	0.8906	5088.5273	4488.8068	5495.5508	31800	1	4521.5771	0.4043	0.0049	0.0916	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	0.1336	0.0	0.0	1.0	0.0	0.0	0.4844	0.4043	13.4076	51.4641	565.8401	34.0	857.9675	292.1274	0.0649	4.8001	35.4838	216.8179	252.5977	1903.4231	22.6662	217.0486	1623.3547	0	54	61	488	453	13	31	0.4262295081967213	26			0.01639344262295082	1.0	0.08196721311475409	5	0.06557377049180328	4.0	0.0084	7.7525
8	0.0	0	64	512	3	1.75	0	0.8906	4631.4766	5009.6139	4385.0774	31812	1	4169.8675	0.3945	0.0182	0.0826	-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	0.1331	-0.0	0.0	1.0	0.0	0.0	0.4844	0.3945	13.6974	51.6048	565.2818	34.1	857.9675	292.6857	0.0706	4.5962	31.4269	196.5331	228.3023	1296.0607	24.1405	196.8045	1039.0185	0	55	61	488	457	12	23	0.2786885245901639	17			0.03278688524590164	2.0	0.06557377049180328	4	0.13114754098360656	8.0			6.2341	0.03278688524590164	2.0
9	0.0	0	64	512	3	1.875	0	0.9219	5294.6016	4989.8677	5472.9133	31704	1	4638.6034	0.3691	-0.0048	0.1111	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	0.1325	0.0	0.0	1.0	0.0	0.0	0.4844	0.3691	13.7494	51.6116	565.5437	34.1	857.9675	292.4238	0.0867	4.6832	38.8346	224.59	263.8149	1565.5302	22.4001	224.8932	1274.6283	0	56	63	504	478	11	24	0.25396825396825395	16			0.031746031746031744	2.0	0.1111111111111111	7	0.031746031746031744	2.0	0.0081	7.9573
10	0.0	0	64	512	3	1.7188	0	0.9062	4950.9766	4560.3436	5262.1123	31843	1	4774.4938	0.4434	-0.0031	0.134	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	0.1306	0.0	0.0	1.0	0.0	0.0	0.5781	0.4434	13.8882	51.8104	564.4661	34.2	857.9675	293.5014	0.0892	4.6537	34.0791	223.8635	258.2931	1726.4682	23.134	224.1245	1440.3826	0	57	63	504	466	17	31	0.38095238095238093	24			0.047619047619047616	3.0	0.06349206349206349	4	0.1111111111111111	7.0
11	0.0	0	64	512	3	1.6094	0	0.9375	4331.5684	4241.4459	4400.5586	31744	1	3845.2618	0.4336	0.0047	0.1354	-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	0.1298	-0.0	0.0	1.0	0.0	0.0	0.5781	0.4336	14.0239	51.9366	564.886	34.2	857.9675	293.0815	0.0936	4.5707	30.7528	183.0933	214.1963	1407.8184	24.3511	183.3495	1164.6952	0	58	63	504	475	13	29	0.3333333333333333	21			0.031746031746031744	2.0	0.07936507936507936	5			0.0073	7.6926		0.015873015873015872	1.0
12	0.0	0	64	512	3	1.5156	0	0.7812	4725.0371	3898.9237	5431.4239	31792	1	4496.5728	0.4609	0.0244	0.0844	-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	0.1322	-0.0	0.0	1.0	0.0	0.0	0.5625	0.4609	14.0273	51.9401	563.9426	34.3	857.9675	294.025	0.0865	4.6121	34.988	210.5671	245.9236	1490.2312	26.3782	210.8487	1213.311	0	59	61	488	465	10	22	0.3114754098360656	19	0.01639344262295082	1.0	0.08196721311475409	5.0	0.01639344262295082	1	0.06557377049180328	4.0
13	0.0	0	64	512	4	1.5781	0	0.8125	4552.8398	4327.259	4769.7778	31726	1	3951.5205	0.4902	0.0058	0.1092	-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	0.1243	-0.0	0.0	1.0	0.0	0.0	0.625	0.4902	14.0216	51.9988	563.3038	34.3	857.9675	294.6637	0.1176	4.6409	34.6955	189.8302	224.9402	1325.7249	23.1612	190.1267	1072.9765	0	60	58	464	413	16	40	0.5689655172413793	33			0.08620689655172414	5.0	0.13793103448275862	8	0.1896551724137931	11.0	0.0086	7.7063	6.7543
14	0.0	0	64	512	4	1.6719	0	0.8438	4229.166	4585.0703	3873.2617	31580	1	3910.4259	0.5	0.0132	0.1619	-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	0.1226	-0.0	0.0	1.0	0.0	0.0	0.6562	0.5	14.0175	52.0583	562.8052	34.4	857.9675	295.1624	0.097	4.5178	31.3756	184.0054	215.7393	1404.1596	25.5141	184.2663	1158.3824	0	61	62	496	465	15	27	0.25806451612903225	16			0.06451612903225806	4.0	0.12903225806451613	8	0.06451612903225806	4.0
15	0.0	0	64	512	5	1.7656	0	0.8594	4619.9727	4131.9717	5074.8264	31689	1	4163.141	0.4824	-0.0109	0.0868	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	0.1226	0.0	0.0	1.0	0.0	0.0	0.5625	0.4824	14.4709	52.4935	562.3414	34.5	857.9675	295.6262	0.1201	4.6276	38.4473	199.087	237.8926	1122.7358	23.8958	199.3249	856.3148	0	62	61	488	476	11	10	0.09836065573770492	6	0.01639344262295082	1.0			0.08196721311475409	5	0.01639344262295082	1.0	0.0085	7.8196
16	0.0	0	64	512	4	2.3594	0	0.9688	5134.4629	4500.9897	5524.1388	31785	1	3916.1129	0.3809	0.0077	0.1039	-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	0.1386	-0.0	0.0	1.0	0.0	0.0	0.4844	0.3809	14.3535	52.3757	561.5363	34.6	857.9675	296.4312	0.1201	4.8417	33.4082	196.2872	230.1101	1242.3513	24.6441	196.5814	982.7475	0	63	62	496	467	16	25	0.3225806451612903	20			0.03225806451612903	2.0	0.06451612903225806	4	0.06451612903225806	4.0
17	0.0	0	64	512	4	2.1562	0	0.9062	5462.8105	5057.0452	5720.7891	31766	1	5070.3185	0.3887	0.0044	0.069	-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	0.1309	-0.0	0.0	1.0	0.0	0.0	0.4844	0.3887	14.3912	52.3806	561.2214	34.6	857.9675	296.7462	0.1168	4.7044	38.1819	238.6575	277.2112	1523.0599	23.148	238.912	1217.9877	0	64	61	488	456	15	24	0.2786885245901639	17			0.03278688524590164	2.0	0.08196721311475409	5	0.13114754098360656	8.0	0.0084	9.6022
18	0.0	0	64	512	4	1.7188	0	0.8438	5144.3984	4651.443	5569.2364	31772	1	5404.6743	0.4629	0.0039	0.0697	-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	0.1304	-0.0	0.0	1.0	0.0	0.0	0.5469	0.4629	14.7312	52.7578	560.1469	34.7	857.9675	297.8206	0.1115	4.7518	42.0515	251.3932	293.8211	1513.4404	21.9402	251.6576	1192.9212	0	65	59	472	430	17	35	0.423728813559322	25			0.05084745762711865	3.0	0.11864406779661017	7	0.11864406779661017	7.0			6.0896