ablation-pymethods2test-seqnorm-15-8B/training_logs/20260608_210110_metrics_job_639471.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_ContextLengthExceededError	batch_errors/total_ContextLengthExceededError	batch_errors/avg_InvalidChatHistory	batch_errors/total_InvalidChatHistory	batch_errors/avg_VerifierTimeoutError	batch_errors/total_VerifierTimeoutError	batch_errors/avg_AgentTimeoutError	batch_errors/total_AgentTimeoutError	batch_errors/avg_AgentSetupTimeoutError	batch_errors/total_AgentSetupTimeoutError	timing/cleanup_old_checkpoints	timing/save_checkpoints	timing/save_hf_model	batch_errors/avg_DaytonaAuthenticationError	batch_errors/total_DaytonaAuthenticationError	batch_errors/avg_DaytonaError	batch_errors/total_DaytonaError
2	0.0	0	64	512	4	0.5312	0	0.2344	5278.6973	5088.7018	5517.2379	25239	1	3818.4836	0.5566	-0.004	0.1129	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1241	0.0	0.0	1.0	0.0	0.0	0.6481	0.5566	10.4951	50.4392	584.3245	31.9	857.9675	273.643	0.1302	3.8894	37.1114	202.1707	239.6029	4371.2665	22.4624	202.3605	4105.3115	0	29	52	416	374	16	39	0.11538461538461539	6	0.7884615384615384	41	0.019230769230769232	1.0	0.019230769230769232	1.0	0.038461538461538464	2.0
3	0.0	0	64	512	1	0.9844	0	0.9844	4944.7676	5091.439	4875.6466	31704	1	4244.5182	0.3203	0.008	0.0845	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1335	-0.0	0.0	1.0	0.0	0.0	0.4219	0.3203	12.8603	50.865	578.3782	32.6	857.9675	279.5893	0.0666	4.6428	32.9006	192.3422	225.5807	695.9013	22.4198	192.613	443.2517	0	30	57	456	414	19	35	0.08771929824561403	5	0.7017543859649122	40	0.12280701754385964	7.0	0.05263157894736842	3.0			10.7945	19.7607	6.6515
4	0.0	0	64	512	2	1.7188	0	0.9844	4114.9512	3919.9412	4244.1136	31730	1	4194.079	0.3984	0.0198	0.0875	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.125	-0.0	0.0	1.0	0.0	0.0	0.5312	0.3984	13.8393	50.8987	577.0171	32.7	857.9675	280.9504	0.0636	4.4873	29.5848	193.0235	222.9079	1107.8622	24.0469	193.259	856.417	0	31	64	512	493	10	15	0.03125	2	0.203125	13	0.046875	3.0			0.015625	1.0
5	0.0	0	64	512	3	1.7656	0	0.8594	5001.7891	4406.6449	5429.1745	31817	1	4145.4506	0.418	-0.0054	0.0829	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.14	0.0	0.0	1.0	0.0	0.0	0.5	0.418	14.1603	51.2707	576.1389	32.8	857.9675	281.8287	0.0622	4.6552	38.8123	204.3063	243.3941	2021.8598	23.3742	204.5192	1750.4335	0	32	61	488	437	20	46	0.08196721311475409	5	0.639344262295082	39	0.06557377049180328	4.0	0.04918032786885246	3.0	0.01639344262295082	1.0	0.0081	7.8836
6	0.0	0	64	512	4	2.0312	0	0.9375	4818.6543	4762.1027	4841.2131	31726	1	5036.9689	0.2852	0.0145	0.1036	-0.0	0.0	0.0	0.0	0.0	0.0	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	0.4062	0.2852	14.1077	51.196	575.3264	32.9	857.9675	282.6411	0.0656	4.6631	33.8051	229.0206	263.108	1289.5434	22.5459	229.237	999.2225	0	33	61	488	465	10	21	0.11475409836065574	7	0.22950819672131148	14			0.03278688524590164	2.0	0.03278688524590164	2.0
7	0.0	0	64	512	4	1.75	0	0.9375	4567.793	4373.0586	4762.5273	31639	1	3628.674	0.5	0.0075	0.1492	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1348	-0.0	0.0	1.0	0.0	0.0	0.6406	0.5	14.1472	51.2188	573.8872	33.1	857.9675	284.0803	0.0665	4.5609	28.5178	173.7767	202.5827	1301.8005	22.2062	173.9981	1072.4469	0	34	59	472	441	17	23	0.13559322033898305	8	0.2542372881355932	15	0.13559322033898305	8.0					0.0083	8.411
8	0.0	0	64	512	3	1.9688	0	0.8906	5203.1992	4785.8119	5475.1742	31726	1	4610.7692	0.3945	0.0015	0.1334	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1392	-0.0	0.0	1.0	0.0	0.0	0.5781	0.3945	14.2407	51.2979	572.6302	33.3	857.9675	285.3373	0.0655	4.7104	36.7892	210.5074	247.6007	1785.0733	22.4758	210.7457	1510.2823	0	35	61	488	460	13	27	0.11475409836065574	7	0.32786885245901637	20					0.01639344262295082	1.0			7.3123
9	0.0	0	64	512	4	1.9219	0	0.9219	5044.2012	5116.1058	4961.4202	31779	1	4480.1027	0.5352	-0.0054	0.0842	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.135	0.0	0.0	1.0	0.0	0.0	0.625	0.5352	14.2407	51.3575	572.3281	33.3	857.9675	285.6394	0.0627	4.8504	36.6108	213.1635	250.063	1218.0837	21.7718	213.3891	941.3942	0	36	60	480	441	17	39	0.18333333333333332	11	0.43333333333333335	26			0.03333333333333333	2.0			0.0077	8.4733
10	0.0	0	64	512	3	1.75	0	0.8906	4737.1152	4212.0859	5262.1445	30999	1	4007.6604	0.5	0.0051	0.1255	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1275	-0.0	0.0	1.0	0.0	0.0	0.625	0.5	14.3788	51.4694	571.8417	33.3	857.9675	286.1258	0.0673	4.553	31.2988	186.6306	218.2242	1048.2685	23.4353	186.8577	802.0521	0	37	64	512	479	17	31	0.15625	10	0.296875	19	0.015625	1.0	0.03125	2.0	0.015625	1.0
11	0.0	0	64	512	4	2.0781	0	0.9062	5100.459	5243.36	5008.8558	31758	1	4289.2275	0.3906	0.0276	0.1256	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1362	-0.0	0.0	1.0	0.0	0.0	0.5312	0.3906	14.4257	51.5521	570.7955	33.5	857.9675	287.172	0.0653	4.7056	32.7387	201.981	235.0431	1731.9565	21.626	202.2386	1470.5772	0	38	59	472	444	14	24	0.06779661016949153	4	0.3898305084745763	23	0.05084745762711865	3.0	0.03389830508474576	2.0	0.01694915254237288	1.0	0.0086	9.2793
12	0.0	0	64	512	4	1.7031	0	0.9531	5043.1562	4965.0356	5119.4672	31823	1	4607.3975	0.4941	0.0074	0.126	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1292	-0.0	0.0	1.0	0.0	0.0	0.625	0.4941	14.4556	51.6204	570.5818	33.5	857.9675	287.3857	0.0686	4.688	40.8057	219.6135	260.7417	1244.3571	27.5955	219.867	951.3271	0	39	61	488	452	14	36	0.08196721311475409	5	0.45901639344262296	28			0.04918032786885246	3.0
13	0.0	0	64	512	4	1.875	0	0.9219	4419.4766	4218.5217	4583.3759	31827	1	4168.3604	0.4492	0.0001	0.0823	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1279	0.0	0.0	1.0	0.0	0.0	0.5625	0.4492	14.7014	51.8757	569.6165	33.6	857.9675	288.3511	0.0662	4.5612	30.5522	192.2327	223.0663	1248.4529	24.1425	192.4475	996.6791	0	40	61	488	466	11	17	0.08196721311475409	5	0.18032786885245902	11	0.08196721311475409	5.0	0.01639344262295082	1.0			0.0084	8.4746	6.1621
14	0.0	0	64	512	4	1.8281	0	0.875	4378.8047	4390.5302	4370.3165	20422	1	3374.562	0.4199	0.0026	0.1097	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1403	-0.0	0.0	1.0	0.0	0.0	0.5469	0.4199	14.6059	51.8282	569.7355	33.6	857.9675	288.2321	0.0477	3.2238	29.9727	163.6158	193.973	1448.2179	23.0063	163.9523	1228.0101	0	41	63	504	473	17	31	0.15873015873015872	10	0.3333333333333333	21
15	0.0	0	64	512	4	1.9688	0	0.8906	5440.5508	5273.5025	5545.0222	31794	1	4314.333	0.3848	-0.0019	0.0687	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1387	0.0	0.0	1.0	0.0	0.0	0.4688	0.3848	14.9666	52.2508	569.2278	33.7	857.9675	288.7397	0.065	4.781	34.9912	208.4372	243.726	1518.1162	21.834	208.6693	1247.7718	0	42	60	480	440	14	32	0.16666666666666666	10	0.35	21	0.13333333333333333	8.0	0.016666666666666666	1.0			0.0078	8.9859
16	0.0	0	64	512	4	1.5469	0	0.7969	4309.9902	4170.6036	4471.7257	31730	1	3959.7796	0.5371	0.017	0.0942	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1249	-0.0	0.0	1.0	0.0	0.0	0.625	0.5371	15.3689	52.4981	568.5267	33.7	857.9675	289.4408	0.0633	4.577	30.0185	183.5674	213.8767	1281.3491	21.6632	183.7946	1041.2281	0	43	63	504	468	14	27	0.06349206349206349	4	0.31746031746031744	20	0.15873015873015872	10.0	0.047619047619047616	3.0
17	0.0	0	64	512	4	1.7969	0	0.9219	4686.1582	4334.2927	4921.1173	31718	1	4093.6999	0.4004	0.0024	0.0855	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1345	-0.0	0.0	1.0	0.0	0.0	0.5	0.4004	15.3116	52.6276	568.5529	33.7	857.9675	289.4147	0.0649	4.5947	33.5947	192.7301	226.6108	1070.9411	23.6635	192.9508	816.0677	0	44	64	512	404	33	66	0.03125	2	0.203125	13	0.25	16.0	0.796875	51.0	0.40625	26.0	0.0082	8.7248
18	0.0	0	64	512	4	2.1875	0	0.9062	4488.0605	4766.2674	4327.9846	31776	1	4643.8272	0.3652	0.0198	0.102	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.115	-0.0	0.0	1.0	0.0	0.0	0.4688	0.3652	15.2923	52.5649	567.6223	33.8	857.9675	290.3453	0.0648	4.5433	38.2594	212.1464	250.6847	2427.0584	19.2772	212.3601	2152.5489	0	45	59	472	281	51	126	0.1016949152542373	6	0.0847457627118644	5	0.6949152542372882	41.0	2.2033898305084745	130.0	0.559322033898305	33.0			6.1293
19	0.0	0	64	512	4	2.1406	0	0.9844	2831.2832	4734.6768	1934.2816	19126	1	3422.9025	0.3203	0.0741	0.1736	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0819	-0.0	0.0	1.0	0.0	0.0	0.5156	0.3203	15.0547	52.2833	567.6797	33.8	857.9675	290.2878	0.0433	2.9003	21.3716	139.1872	160.9597	2780.6994	19.1556	139.5444	2597.6796	0	46	57	456	174	56	114	0.05263157894736842	3	0.17543859649122806	10	2.5789473684210527	147.0	1.9473684210526316	111.0	0.7192982456140351	41.0	0.0085	55.7189		0.03508771929824561	2.0
20	0.0	0	64	512	4	2.0	0	0.9531	1948.959	3929.527	1614.3425	20028	1	3361.197	0.1445	0.0796	0.2262	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.057	-0.0	0.0	1.0	0.0	0.0	0.4375	0.1445	14.9425	52.2209	567.6288	33.8	857.9675	290.3387	0.0488	2.7631	25.3613	134.4423	160.065	4012.6647	18.8904	134.6545	3830.9431	0	47	60	480	251	53	87	0.06666666666666667	4	0.18333333333333332	11	1.8666666666666667	112.0	1.3333333333333333	80.0	0.6166666666666667	37.0						0.016666666666666666	1.0
21	0.0	0	64	512	3	1.5469	0	0.875	1713.2109	3120.7785	1084.9746	12999	1	2205.1024	0.3086	0.1337	0.1884	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0686	-0.0	0.0	1.0	0.0	0.0	0.5312	0.3086	14.818	52.0276	568.1573	33.8	857.9675	289.8102	0.0314	1.9562	15.2563	98.0173	113.4611	3641.5565	17.9428	98.173	3508.1929	0	48	64	512	309	57	117	0.171875	11	0.296875	19	1.34375	86.0	1.359375	87.0	0.09375	6.0	0.0082	8.6866		0.015625	1.0
22	0.0	0	64	512	7	1.625	0	0.9531	2370.7871	3573.7063	1978.1244	31763	1	3467.8194	0.2461	0.0916	0.1688	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0845	-0.0	0.0	1.0	0.0	0.0	0.4531	0.2461	15.1041	52.3137	567.8245	33.8	857.9675	290.143	0.065	4.2255	18.8418	139.4689	158.5744	3585.1599	19.0904	139.6672	3403.2676	0	49	39	312	191	35	70	0.07692307692307693	3	0.41025641025641024	16	1.1794871794871795	46.0	1.3076923076923077	51.0	0.10256410256410256	4.0				0.02564102564102564	1.0