ablation-pymethods2test-seqmean-arm0-tis-15-8B/training_logs/20260609_214045_metrics_job_653585.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	generate/tis/aligned_tokens	generate/tis/alignment_fail_count	generate/tis/exact_match_fraction	generate/tis/lcs_fallback_fraction	generate/tis/lcs_fallback_messages	generate/tis/unaligned_fraction	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	policy/rollout_train_prob_diff_mean	policy/rollout_train_prob_diff_std	policy/tis/imp_ratio_capped_fraction	policy/tis/imp_ratio_mean	policy/tis/log_ratio_abs_mean	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	tis/batch_skipped_no_logprobs	tis/skipped_fraction	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_AgentTimeoutError	batch_errors/total_AgentTimeoutError	batch_errors/avg_AgentSetupTimeoutError	batch_errors/total_AgentSetupTimeoutError	batch_errors/avg_InvalidChatHistory	batch_errors/total_InvalidChatHistory	batch_errors/avg_ContextLengthExceededError	batch_errors/total_ContextLengthExceededError	batch_errors/avg_DaytonaAuthenticationError	batch_errors/total_DaytonaAuthenticationError	timing/cleanup_old_checkpoints	timing/save_checkpoints	batch_errors/avg_Timeout	batch_errors/total_Timeout	timing/save_hf_model	batch_errors/avg_DaytonaError	batch_errors/total_DaytonaError
2	0.0	0	64	512	0	0.0	0	0.0	1665.6621	3021.6782	967.5947	14153	1	2057.7122	573938.0	33.0	0.9487	0.0	0.0	0.0513	0.3398	0.2099	0.2501	-0.0019	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0656	-0.1214	0.0	1.0	0.0	0.0309	425844310016.0	310867954499584.0	0.0	0.5258	0.022	0.6406	0.3398	7.5378	49.9637	630.257	26.5	857.9676	227.7106	0.0376	2.4443	199.3619	89.3179	288.8421	11028.1246	18.1382	89.4422	10718.6996	0.0	0.0	0	1	121	968	497	114	216	1.9090909090909092	231	1.6528925619834711	200.0	0.2231404958677686	27.0	0.15702479338842976	19	0.09090909090909091	11.0	0.024793388429752067	3.0
3	0.0	0	64	512	1	1.0	1	1.0	2192.3809	5107.972	1422.0889	31541	1	3242.089	778056.0	90.0	0.8463	0.0	0.0	0.1537	0.209	0.14	0.236	-0.0009	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0639	-0.0569	0.0	1.0	0.0	0.0223	5135849414983680.0	3.8306663504564716e+18	0.0001	0.5252	0.0393	0.4844	0.209	13.664	50.6382	619.7108	27.8	857.9676	238.2568	0.0608	5.2456	18.5674	134.9773	153.7971	3675.2048	21.6594	135.1685	3494.5009	0.0	0.0	0	2	64	512	253	62	90	2.109375	135	1.25	80.0	0.5	32.0	0.109375	7	0.046875	3.0	0.03125	2.0	139.9582	149.9938
4	0.0	0	64	512	2	1.6094	0	0.9844	1974.7832	3706.1466	1467.6162	19867	1	2776.8866	687353.0	78.0	0.904	0.0	0.0	0.096	0.2266	0.1618	0.2338	-0.0013	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0563	-0.0823	0.0	1.0	0.0	0.0252	5712403677315072.0	4.576328473257181e+18	0.0	0.4977	0.0341	0.5156	0.2266	13.514	50.458	618.5668	27.9	857.9676	239.4008	0.0426	3.6209	18.1097	113.5752	131.9041	3304.1227	19.8368	113.7514	3148.7583	0.0	0.0	0	3	63	504	278	59	93	1.7619047619047619	111	1.3015873015873016	82.0	0.31746031746031744	20.0	0.14285714285714285	9	0.031746031746031744	2.0	0.015873015873015872	1.0			0.015873015873015872	1.0
5	0.0	0	64	512	3	1.7656	0	0.9375	1916.1016	3570.8227	1287.2183	26360	1	2567.8385	672216.0	119.0	0.8943	0.0	0.0	0.1057	0.2754	0.1458	0.2335	-0.0013	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0609	-0.081	0.0	1.0	0.0	0.0264	2.5092910058202726e+17	2.0297533524949546e+20	0.0	0.5539	0.0386	0.5312	0.2754	13.7533	50.7891	617.0518	28.1	857.9676	240.9158	0.0533	4.4556	16.0924	108.7123	125.0416	3238.4887	20.0299	108.8955	3088.9592	0.0	0.0	0	4	59	472	401	29	13	1.0	59	0.15254237288135594	9.0	0.0847457627118644	5.0	0.01694915254237288	1	0.06779661016949153	4.0			0.0083	12.9332
6	0.0	0	64	512	3	1.4531	0	0.9219	3224.291	3590.6844	2890.709	13914	1	2397.9485	1106110.0	103.0	0.9644	0.0	0.0	0.0356	0.4766	0.064	0.1543	-0.0006	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0788	-0.0412	0.0	1.0	0.0	0.017	2.1654929612682035e+18	2.119323756633866e+21	0.0	0.8649	0.0405	0.625	0.4766	13.7164	50.7537	614.8819	28.3	857.9676	243.0857	0.0323	2.8211	19.9051	118.6808	138.8115	1062.3118	23.3888	118.8737	897.2872	0.0	0.0	0	5	63	504	460	23	14	0.42857142857142855	27	0.06349206349206349	4.0	0.047619047619047616	3.0	0.09523809523809523	6	0.047619047619047616	3.0							16.893	0.015873015873015872	1.0
7	0.0	0	64	512	4	1.6406	0	0.8594	4239.8125	4633.2308	3790.4268	22031	1	3300.5798	1457215.0	112.0	0.9654	0.0	0.0	0.0346	0.5332	0.044	0.102	-0.0004	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0853	-0.025	0.0	1.0	0.0	0.0138	6.141298557442851e+18	5.070549340210866e+21	0.0	0.9245	0.0456	0.6562	0.5332	14.4743	51.5385	613.4079	28.5	857.9676	244.5597	0.0452	4.2242	25.388	159.3519	185.0213	1290.7407	28.6557	159.5877	1072.8381	0.0	0.0	0	6	58	464	445	11	12	0.1206896551724138	7					0.10344827586206896	6	0.034482758620689655	2.0			0.0083	10.3463				0.06896551724137931	4.0
8	0.0	0	64	512	4	1.8906	0	0.8906	4397.6465	4166.2911	4597.0327	25556	1	3231.8595	1555192.0	95.0	0.9507	0.0	0.0	0.0493	0.4629	0.0201	0.1187	-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	0.0913	-0.0045	0.0	1.0	0.0	0.0167	4.5730908733082645e+20	5.0551306138646176e+23	0.0	0.9745	0.0461	0.5781	0.4629	14.6233	51.6414	612.7198	28.6	857.9676	245.2477	0.0504	4.7036	26.7455	163.7089	190.7489	2018.6125	34.5773	163.9526	1788.5789	0.0	0.0	0	7	60	480	458	10	12	0.15	9			0.016666666666666666	1.0	0.16666666666666666	10	0.016666666666666666	1.0								0.016666666666666666	1.0
9	0.0	0	64	512	4	2.1406	0	0.9531	5137.9238	4980.2167	5241.5307	31761	1	4015.1526	1850673.0	87.0	0.9135	0.0	0.0	0.0865	0.3965	0.0072	0.0726	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0938	0.0003	0.0	1.0	0.0	0.0119	2.930747012383905e+21	3.2028701271085374e+24	0.0	0.9696	0.046	0.4688	0.3965	15.9055	52.3258	610.4556	28.8	857.9676	247.512	0.0614	6.5073	32.8918	190.3358	223.5354	1224.5185	28.8017	190.5818	965.6712	0.0	0.0	0	8	63	504	480	13	21	0.047619047619047616	3	0.07936507936507936	5.0			0.20634920634920634	13					0.0081	12.67				0.047619047619047616	3.0
10	0.0	0	64	512	5	1.9219	0	0.9062	4859.3164	4603.0995	5038.9236	31797	1	4029.8322	1739932.0	52.0	0.8962	0.0	0.0	0.1038	0.4121	0.0093	0.1242	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0803	0.0001	0.0	1.0	0.0	0.0145	1.7394266914541902e+21	2.2925263334899206e+24	0.0	0.9646	0.0375	0.5469	0.4121	16.1924	52.5256	608.6286	29.1	857.9676	249.339	0.0627	5.7252	31.0932	188.5143	219.9568	1481.3095	32.107	188.8005	1223.5171	0.0	0.0	0	9	63	504	487	10	14	0.047619047619047616	3	0.015873015873015872	1.0			0.1746031746031746	11										0.031746031746031744	2.0
11	0.0	0	64	512	3	1.6562	0	0.8594	4206.2637	3770.6644	4770.7848	31696	1	3098.8536	1466169.0	27.0	0.9684	0.0	0.0	0.0316	0.5645	-0.0016	0.1212	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0758	-0.0009	0.0	1.0	0.0	0.0186	2.486790661662018e+22	3.009927560391077e+25	0.0	0.9792	0.0338	0.7031	0.5645	16.1496	52.6445	607.3474	29.2	857.9676	250.6202	0.062	5.807	27.2616	157.0913	184.6351	1344.8255	28.0337	157.3111	1126.3452	0.0	0.0	0	10	62	496	465	10	25	0.0967741935483871	6	0.04838709677419355	3.0			0.3387096774193548	21	0.016129032258064516	1.0			0.0079	11.2982			6.1509
12	0.0	0	64	512	4	1.8125	0	0.8594	4341.25	4421.7844	4281.534	31768	1	3837.6661	1544551.0	26.0	0.9519	0.0	0.0	0.0481	0.4258	0.0172	0.1082	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0768	-0.0016	0.0	1.0	0.0	0.0145	2.3760572720076554e+18	2.479232720767365e+21	0.0	0.9513	0.0343	0.5312	0.4258	16.1263	52.6095	605.798	29.4	857.9676	252.1696	0.0603	5.7445	30.3901	180.1222	210.8445	1608.5564	32.131	180.3938	1359.8319	0.0	0.0	0	11	63	504	482	8	13	0.14285714285714285	9	0.031746031746031744	2.0			0.1746031746031746	11
13	0.0	0	64	512	4	2.0156	0	0.9375	5171.2402	4363.3762	5697.6548	31752	1	3838.9164	1805076.0	21.0	0.972	0.0	0.0	0.028	0.3945	-0.0056	0.099	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0793	0.0001	0.0	1.0	0.0	0.0187	3.3199502774606234e+17	4.460413625381222e+20	0.0	0.9698	0.0322	0.5156	0.3945	16.5123	53.0591	604.8148	29.5	857.9676	253.1528	0.5752	5.7891	36.193	189.4182	226.4272	1418.9828	24.7579	189.6581	1162.0041	0.0	0.0	0	12	63	504	486	8	16	0.031746031746031744	2	0.1111111111111111	7.0			0.14285714285714285	9					0.0085	10.287
14	0.0	0	64	512	3	1.5781	0	0.8594	4488.6309	4142.0406	4878.3651	31794	1	3769.576	1574682.0	18.0	0.937	0.0	0.0	0.063	0.5293	0.0116	0.1159	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0641	0.0001	0.0	1.0	0.0	0.0191	1.1232591437954967e+20	1.4095364312304327e+23	0.0	0.9755	0.0277	0.6719	0.5293	16.3773	52.9352	603.7007	29.6	857.9676	254.2668	0.0652	5.8155	29.0791	176.4044	205.7881	1174.4667	23.8728	176.6434	938.9854	0.0	0.0	0	13	63	504	462	18	34	0.12698412698412698	8	0.12698412698412698	8.0			0.36507936507936506	23	0.047619047619047616	3.0
15	0.0	0	64	512	4	1.9688	0	0.9375	4663.1953	4560.4923	4726.3722	31674	1	3835.0487	1647855.0	26.0	0.9488	0.0	0.0	0.0512	0.3809	-0.0175	0.1338	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0707	0.0	0.0	1.0	0.0	0.0173	1.3211500909875513e+22	1.6953347554969734e+25	0.0	0.9296	0.0299	0.5	0.3809	16.7322	53.2489	601.7022	29.9	857.9676	256.2654	0.1012	5.8519	30.3985	178.5781	209.3207	1621.8309	26.8666	178.8196	1379.7871	0.0	0.0	0	14	64	512	491	8	20	0.015625	1	0.1875	12.0			0.109375	7	0.015625	1.0			0.0082	11.2278