ablation-pymethods2test-seqmean-arm0-30-8B/training_logs/20260612_220124_metrics_job_630130.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_AgentTimeoutError	batch_errors/total_AgentTimeoutError	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_AgentSetupTimeoutError	batch_errors/total_AgentSetupTimeoutError	batch_errors/avg_DaytonaAuthenticationError	batch_errors/total_DaytonaAuthenticationError	timing/cleanup_old_checkpoints	timing/save_checkpoints	timing/save_hf_model	batch_errors/avg_DaytonaError	batch_errors/total_DaytonaError
2	0.0	0	64	512	4	0.3438	0	0.1406	2745.916	4536.7524	2283.9066	31842	1	3652.8031	0.2051	0.0705	0.1449	-0.0007	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0683	-0.0442	0.0	1.0	0.0	0.0137	0.3898	0.2051	12.7084	50.5586	566.71	33.9	857.9675	291.2575	0.1351	4.4486	104.946	152.1059	257.396	10105.4336	18.2174	152.3142	9825.3711	0	57	63	504	281	58	154	1.8253968253968254	115	0.19047619047619047	12.0	0.42857142857142855	27	0.8095238095238095	51.0	0.25396825396825395	16.0	0.031746031746031744	2.0
3	0.0	0	64	512	1	0.9844	0	0.9844	2990.8008	4339.4828	2595.7323	31794	1	4262.9787	0.2266	0.0705	0.1484	-0.0008	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0829	-0.0481	0.0	1.0	0.0	0.0181	0.5	0.2266	12.7156	50.6524	565.6756	34.1	857.9675	292.2919	0.0685	4.3634	31.3815	172.8736	204.58	3407.9472	17.5583	173.1294	3181.4385	0	58	59	472	191	58	157	2.3389830508474576	138	0.22033898305084745	13.0	0.3050847457627119	18	1.9491525423728813	115.0	0.2711864406779661	16.0			113.7448	123.1255
4	0.0	0	64	512	2	1.4531	0	0.9219	1842.3164	3830.7287	1172.5901	31730	1	3083.3057	0.252	0.1959	0.2355	-0.0015	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0529	-0.0935	0.0	1.0	0.0	0.0296	0.5	0.252	12.8444	50.7361	566.7198	33.9	857.9675	291.2477	0.0904	4.2018	17.8872	126.8601	145.0002	3636.1329	18.2801	127.022	3468.6454	0	59	59	472	191	58	160	2.559322033898305	151	0.23728813559322035	14.0	0.3728813559322034	22	1.8305084745762712	108.0	0.3728813559322034	22.0
5	0.0	0	64	512	3	1.5469	0	0.9531	1687.9023	3823.3853	1110.3151	19335	1	2744.5105	0.2129	0.1122	0.1362	-0.0008	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0511	-0.0532	0.0	1.0	0.0	0.0138	0.4531	0.2129	12.8585	50.7328	566.4686	34.0	857.9675	291.4989	0.0597	2.7178	15.1498	108.5325	123.9181	3855.0493	17.9434	108.7081	3710.4636	0	60	63	504	312	48	79	0.7936507936507936	50	0.14285714285714285	9.0	0.31746031746031744	20	1.746031746031746	110.0	0.047619047619047616	3.0			0.0099	8.8255	275.4291
6	0.0	0	64	512	3	1.4844	0	0.875	2705.2773	3926.8809	1668.8989	31646	1	3012.6819	0.459	0.1462	0.1798	-0.0015	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0697	-0.0959	0.0	1.0	0.0	0.0179	0.7188	0.459	13.0881	50.9166	566.6464	34.0	857.9675	291.3212	0.0697	4.435	19.2157	123.2323	142.7038	1882.4268	20.2012	123.418	1715.083	0	61	62	496	397	29	58	0.3387096774193548	21	0.1935483870967742	12.0	0.4032258064516129	25	0.6290322580645161	39.0	0.03225806451612903	2.0						0.016129032258064516	1.0
7	0.0	0	64	512	3	1.5625	0	0.875	4372.2871	4678.6603	4051.208	31765	1	4031.5953	0.5117	0.0301	0.1117	-0.0003	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1006	-0.022	0.0	1.0	0.0	0.0107	0.6094	0.5117	13.2397	51.094	568.5527	33.7	857.9675	289.4149	0.0919	4.5973	32.0721	189.1022	221.4727	1318.3369	21.5119	189.3083	1070.747	0	62	62	496	467	17	21	0.03225806451612903	2	0.11290322580645161	7.0	0.24193548387096775	15	0.11290322580645161	7.0	0.016129032258064516	1.0			0.0085	8.9973		0.016129032258064516	1.0
8	0.0	0	64	512	4	1.8906	0	0.9688	5146.4805	4434.7366	5789.4312	31600	1	4146.9309	0.4746	0.0104	0.0669	-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	0.1238	-0.0056	0.0	1.0	0.0	0.0102	0.5469	0.4746	13.2111	51.0682	568.2429	33.8	857.9675	289.7247	0.0709	4.7406	35.0463	194.8197	230.1324	1359.0594	21.4195	195.0147	1102.761	0	63	63	504	448	20	51	0.07936507936507936	5	0.09523809523809523	6.0	0.746031746031746	47	0.07936507936507936	5.0
9	0.0	0	64	512	7	1.8906	0	0.875	5587.1855	5587.4615	5587.0158	31766	1	4900.2073	0.3809	0.0053	0.1109	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1128	0.0	0.0	1.0	0.0	0.0114	0.4844	0.3809	13.5775	51.5483	569.7428	33.6	857.9675	288.2247	0.1075	4.8015	38.5633	225.6816	264.5674	1636.5882	22.1274	225.8961	1345.0836	0	64	62	496	422	26	68	0.04838709677419355	3	0.04838709677419355	3.0	1.0	62	0.0967741935483871	6.0					0.0081	8.5496		0.06451612903225806	4.0
10	0.0	0	64	512	4	1.9531	0	0.9375	4798.2617	4883.6444	4723.5128	31812	1	4722.6084	0.4668	0.0183	0.1052	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1087	0.0	0.0	1.0	0.0	0.0168	0.6094	0.4668	13.718	51.5807	568.653	33.7	857.9675	289.3145	0.075	4.7303	35.8252	213.9135	250.0471	1536.8344	21.852	214.1464	1260.1995	0	65	61	488	434	20	44	0.06557377049180328	4	0.04918032786885246	3.0	0.7213114754098361	44	0.16393442622950818	10.0							5.9602
11	0.0	0	64	512	3	1.6875	0	0.9062	4990.3906	4683.8621	5191.767	31741	1	4339.1846	0.3965	0.0113	0.1192	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1176	-0.0005	0.0	1.0	0.0	0.0138	0.5781	0.3965	13.9927	51.9113	567.4896	33.9	857.9675	290.4779	0.0707	4.8411	34.6825	205.3311	240.3191	1507.0204	22.8738	205.5654	1238.9803	0	66	64	512	451	19	50	0.03125	2	0.046875	3.0	0.75	48	0.171875	11.0					0.0085	8.6432
12	0.0	0	64	512	3	1.5938	0	0.8906	4687.6602	4780.5265	4614.2762	31720	1	3991.8123	0.4414	0.0147	0.1094	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1043	-0.0031	0.0	1.0	0.0	0.0126	0.5625	0.4414	14.1397	52.1146	567.5696	33.8	857.9675	290.3979	0.0726	4.6609	30.5811	185.1371	216.0168	1571.263	21.9126	185.3626	1328.6676	0	67	58	464	422	16	42	0.034482758620689655	2	0.08620689655172414	5.0	0.6896551724137931	40
13	0.0	0	64	512	4	1.5469	0	0.8281	4902.5645	4448.6776	5228.5101	31770	1	4445.7836	0.418	-0.0081	0.0909	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1147	-0.0	0.0	1.0	0.0	0.0128	0.5312	0.418	14.1629	52.2518	569.6768	33.6	857.9675	288.2908	0.0962	4.7131	33.8447	209.0269	243.2635	1442.218	21.5536	209.322	1172.6792	0	68	64	512	471	16	37	0.046875	3	0.0625	4.0	0.46875	30	0.046875	3.0	0.015625	1.0			0.0082	8.6812
14	0.0	0	64	512	4	1.7344	0	0.875	4912.1777	4638.6631	5239.691	31749	1	4027.0232	0.5449	0.0247	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	0.1083	-0.002	0.0	1.0	0.0	0.0111	0.6562	0.5449	14.5627	52.6307	568.1539	33.8	857.9675	289.8137	0.0922	4.7384	33.01	189.5539	222.8763	1413.2169	23.2675	189.7737	1162.3272	0	69	62	496	442	18	54	0.03225806451612903	2			0.8387096774193549	52
15	0.0	0	64	512	3	1.9219	0	0.9062	4989.8223	4749.7429	5156.7649	31793	1	4613.5261	0.4102	-0.0096	0.0915	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1134	-0.0	0.0	1.0	0.0	0.0151	0.5312	0.4102	14.5696	52.6356	567.6034	33.8	857.9675	290.3641	0.0859	4.6794	34.9319	213.77	248.9891	1779.8183	22.218	213.9708	1503.9267	0	70	62	496	433	16	61	0.12903225806451613	8	0.03225806451612903	2.0	0.8387096774193549	52	0.03225806451612903	2.0					0.0081	8.4344	5.9241