ablation-pymethods2test-seqmean-arm0-tis-15-8B/training_logs/20260609_214045_metrics_job_653588.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_InvalidChatHistory	batch_errors/total_InvalidChatHistory	batch_errors/avg_ContextLengthExceededError	batch_errors/total_ContextLengthExceededError	batch_errors/avg_AgentTimeoutError	batch_errors/total_AgentTimeoutError	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
2	0.0	0	64	512	3	0.4219	0	0.2188	3685.4219	3527.8649	4019.75	16769	1	2307.0638	1257847.0	2.0	0.9993	0.0	0.0	0.0007	0.6797	-0.0006	0.0628	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0381	0.0	0.0	1.0	0.0	0.0162	1.0002	1.312	0.0	0.9678	0.0118	0.7544	0.6797	8.3562	50.2278	634.6806	26.0	857.9676	223.287	0.0717	3.4039	26.6535	126.6473	153.6151	4895.4874	32.7345	126.8502	4705.7335	0.0	0.0	0	61	54	432	360	23	69	1.2592592592592593	68	0.2222222222222222	12	0.1111111111111111	6	0.05555555555555555	3.0
3	0.0	0	64	512	1	0.9219	0	0.9219	3966.3945	3777.5464	4071.4377	31765	1	4125.9274	1408431.0	14.0	0.9555	0.0	0.0	0.0445	0.3574	0.0054	0.0859	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0428	0.0	0.0	1.0	0.0	0.0312	4798878720.0	5626906804224.0	0.0	0.8313	0.0134	0.4688	0.3574	13.8742	50.7912	624.6771	27.2	857.9676	233.2905	0.0654	5.9309	30.7554	183.7737	214.8289	884.5667	32.4223	184.0075	631.377	0.0	0.0	0	62	56	448	392	17	55	0.7857142857142857	44	0.08928571428571429	5	0.14285714285714285	8	0.017857142857142856	1.0	8.4412	17.7924
4	0.0	0	64	512	2	1.6094	0	0.9688	4484.8535	4127.1455	4739.6756	31775	1	4685.7602	1592891.0	27.0	0.914	0.0	0.0	0.086	0.416	0.0051	0.0481	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0438	0.0	0.0	1.0	0.0	0.014	1.49631712790315e+18	1.8779827487400106e+21	0.0	0.8914	0.0146	0.4531	0.416	14.0978	50.9457	622.3339	27.5	857.9676	235.6337	0.0902	5.9053	35.778	202.1171	238.2046	1021.0078	34.2374	202.3359	742.6567	0.0	0.0	0	63	65	520	475	16	39	0.4461538461538462	29	0.07692307692307693	5	0.07692307692307693	5	0.09230769230769231	6.0
5	0.0	0	64	512	3	1.9219	0	0.8438	4086.5547	3298.7422	4704.1777	31791	1	3910.7476	1452474.0	19.0	0.9538	0.0	0.0	0.0462	0.4395	0.0004	0.0928	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0441	-0.0	0.0	1.0	0.0	0.0169	680327517306880.0	8.199202519226778e+17	0.0	0.9173	0.0141	0.5938	0.4395	14.9725	51.1755	619.0883	27.8	857.9676	238.8793	0.0605	5.8121	35.1041	187.1695	222.5884	1993.5726	35.8302	187.4233	1729.3387	0.0	0.0	0	64	60	480	427	15	53	0.75	45	0.15	9	0.05	3			0.0083	8.9351
6	0.0	0	64	512	4	1.9531	0	0.8594	4482.5859	4188.5991	4726.175	31715	1	4433.6859	1614330.0	23.0	0.916	0.0	0.0	0.084	0.4531	0.0098	0.1061	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.045	0.0	0.0	1.0	0.0	0.0159	8.676132800661553e+23	8.132848488751659e+26	0.0	0.8934	0.0148	0.5781	0.4531	15.4079	51.6347	616.659	28.1	857.9676	241.3086	0.0896	5.6735	34.9766	204.9392	240.2083	1228.4685	32.6219	205.1416	949.9589	0.0	0.0	0	65	63	504	428	24	63	0.8253968253968254	52	0.12698412698412698	8	0.047619047619047616	3	0.20634920634920634	13.0			6.8083
7	0.0	0	64	512	5	1.9219	0	0.9062	4357.2324	4060.3786	4557.0752	31769	1	4668.8661	1580861.0	37.0	0.8957	0.0	0.0	0.1043	0.4023	0.0064	0.0877	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.045	-0.0002	0.0	1.0	0.0	0.0172	1.054274388152946e+23	1.2798084482887822e+26	0.0	0.8563	0.015	0.5312	0.4023	15.6097	51.7144	614.0408	28.4	857.9676	243.9268	0.0622	6.0018	33.4297	213.4844	247.2341	1499.3639	32.0364	213.7417	1214.0885	0.0	0.0	0	66	61	488	438	15	44	0.6065573770491803	37	0.09836065573770492	6	0.01639344262295082	1	0.09836065573770492	6.0	0.008	9.2733
8	0.0	0	64	512	4	1.7344	0	0.8906	4419.9375	3553.4759	4918.4862	31735	1	4351.8887	1540086.0	31.0	0.9326	0.0	0.0	0.0674	0.3652	-0.0012	0.0879	-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	0.0436	-0.0053	0.0	1.0	0.0	0.0166	7106447872.0	7634057953280.0	0.0	0.9049	0.0147	0.4844	0.3652	15.652	51.8026	611.4824	28.7	857.9676	246.4852	0.0622	6.0487	33.6584	200.2845	234.3115	1811.2337	34.6927	200.5905	1536.1294	0.0	0.0	0	67	58	464	396	26	66	0.8275862068965517	48	0.25862068965517243	15	0.05172413793103448	3	0.034482758620689655	2.0				0.05172413793103448	3.0
9	0.0	0	64	512	4	1.5156	0	0.8906	4066.9102	4048.2335	4078.5905	31837	1	4387.0666	1427586.0	25.0	0.9098	0.0	0.0	0.0902	0.3848	-0.0114	0.0895	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0438	-0.0	0.0	1.0	0.0	0.0141	3215390490492928.0	3.841650471617954e+18	0.0	0.8661	0.015	0.4688	0.3848	16.0492	52.3116	609.3674	29.0	857.9676	248.6002	0.0897	6.1724	31.0609	203.1937	234.6137	1248.5725	32.0514	203.4626	975.7293	0.0	0.0	0	68	63	504	455	13	46	0.6190476190476191	39	0.07936507936507936	5	0.031746031746031744	2	0.047619047619047616	3.0	0.0086	8.9362
10	0.0	0	64	512	8	2.0156	0	0.9375	4388.7012	3827.7276	5121.5045	31658	1	3792.0489	1553676.0	18.0	0.9743	0.0	0.0	0.0257	0.5664	-0.0064	0.0802	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0449	0.0	0.0	1.0	0.0	0.0138	942792901656576.0	1.1535304966096814e+18	0.0	0.9097	0.0145	0.6406	0.5664	16.1733	52.4356	607.0387	29.2	857.9676	250.9289	0.1701	5.7865	33.4522	177.4228	211.3543	1399.7571	37.3866	177.7316	1145.224	0.0	0.0	0	69	62	496	433	24	58	0.5967741935483871	37	0.2903225806451613	18	0.03225806451612903	2	0.08064516129032258	5.0				0.04838709677419355	3.0
11	0.0	0	64	512	3	1.5938	0	0.9219	4478.5273	4706.2548	4322.7138	31693	1	4388.6691	1567154.0	14.0	0.9596	0.0	0.0	0.0404	0.4062	0.0146	0.0753	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.045	-0.0017	0.0	1.0	0.0	0.0203	37698882502656.0	3.898363573436416e+16	0.0	0.8784	0.0142	0.5	0.4062	16.1904	52.4454	604.8707	29.5	857.9676	253.0969	0.0912	5.8848	33.2322	191.6949	225.2911	1712.3059	39.3967	191.9673	1441.7301	0.0	0.0	0	70	63	504	441	22	60	0.6349206349206349	40	0.14285714285714285	9	0.19047619047619047	12	0.047619047619047616	3.0	0.009	9.5302	6.3806
12	0.0	0	64	512	4	1.6094	0	0.8594	3870.6582	3993.4078	3804.6757	31660	1	3994.7037	1414538.0	14.0	0.939	0.0	0.0	0.061	0.3496	-0.014	0.1576	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0445	-0.0001	0.0	1.0	0.0	0.0232	6.827100124823203e+21	8.119763290842973e+24	0.0	0.8805	0.014	0.5	0.3496	16.2904	52.5068	603.2638	29.7	857.9676	254.7038	0.064	5.8584	27.7403	178.662	206.7592	1436.6431	32.111	178.9542	1191.9108	0.0	0.0	0	71	63	504	457	19	47	0.6507936507936508	41	0.06349206349206349	4	0.031746031746031744	2
13	0.0	0	64	512	3	1.6094	0	0.875	4486.5332	3847.2383	5028.8953	31774	1	4668.9327	1632410.0	30.0	0.8736	0.0	0.0	0.1264	0.459	0.004	0.0411	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0437	0.0	0.0	1.0	0.0	0.0117	2.0079791588560077e+17	2.5626006126882246e+20	0.0	0.9135	0.0143	0.5	0.459	16.2309	52.5107	603.6477	29.6	857.9676	254.3199	0.063	5.8585	33.7104	209.3972	243.4676	1574.2016	33.0528	209.6937	1291.8188	0.0	0.0	0	72	60	480	436	12	43	0.55	33	0.11666666666666667	7	0.08333333333333333	5	0.016666666666666666	1.0	0.0102	9.398		0.016666666666666666	1.0
14	0.0	0	64	512	3	1.625	0	0.9219	4030.5508	3747.5877	4257.7183	31764	1	3919.6801	1430904.0	31.0	0.9122	0.0	0.0	0.0878	0.4453	-0.0008	0.0867	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0396	-0.0001	0.0	1.0	0.0	0.0184	436822212608.0	400335680045056.0	0.0	0.9088	0.0133	0.5469	0.4453	16.4671	52.6346	602.5194	29.8	857.9676	255.4482	0.0953	5.9026	29.5781	177.2825	207.2711	1411.7807	48.8291	177.5971	1149.7701	0.0	0.0	0	73	64	512	477	18	30	0.375	24	0.046875	3	0.046875	3	0.078125	5.0
15	0.0	0	64	512	6	1.9062	0	0.9375	4928.0742	5089.388	4838.3465	31829	1	4458.2535	1709041.0	22.0	0.9236	0.0	0.0	0.0764	0.3574	0.028	0.1375	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0459	0.0	0.0	1.0	0.0	0.0152	30543561359360.0	3.860194628573594e+16	0.0	0.941	0.0148	0.4844	0.3574	16.4362	52.6385	601.1992	29.9	857.9676	256.7684	0.0942	6.2333	36.9222	215.6981	253.0054	1584.8429	35.8218	215.9884	1289.7748	0.0	0.0	0	74	60	480	413	18	57	0.9833333333333333	59	0.08333333333333333	5	0.016666666666666666	1	0.16666666666666666	10.0	0.0087	9.1809
16	0.0	0	64	512	4	2.0469	1	1.0	4001.4727	3601.346	4281.9601	31741	1	3888.6649	1397275.0	23.0	0.9487	0.0	0.0	0.0513	0.4121	0.0048	0.063	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0436	-0.0026	0.0	1.0	0.0	0.0135	8.207850865374003e+16	9.702147778100068e+19	0.0	0.8586	0.0144	0.5312	0.4121	16.4568	52.7637	599.1791	30.2	857.9676	258.7885	0.0656	5.9013	30.0436	169.248	199.6035	1374.3084	36.1758	169.4935	1132.5895	0.0	0.0	0	75	63	504	422	22	64	0.8253968253968254	52	0.09523809523809523	6	0.1111111111111111	7	0.2857142857142857	18.0			6.5286
17	0.0	0	64	512	4	2.4219	2	1.0	4137.8809	3989.7778	4218.1777	31802	1	4719.6405	1531507.0	24.0	0.8609	0.0	0.0	0.1391	0.3516	0.0177	0.1025	-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	0.0403	-0.0055	0.0	1.0	0.0	0.0169	3.817858620540846e+17	4.6935484414353107e+20	0.0	0.8424	0.0134	0.4531	0.3516	16.7703	53.0803	597.8522	30.3	857.9676	260.1154	0.0901	7.0109	36.2508	203.9976	240.5622	1688.1237	39.0785	204.2208	1401.4078	0.0	0.0	0	76	62	496	434	20	62	0.8548387096774194	53	0.16129032258064516	10	0.016129032258064516	1			0.0106	9.297
18	0.0	0	64	512	4	3.1875	3	1.0	4233.2773	3857.1	4420.2661	31765	1	4184.3433	1522291.0	17.0	0.9239	0.0	0.0	0.0761	0.332	0.0005	0.0567	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0415	-0.0	0.0	1.0	0.0	0.0102	2.0191042252585673e+22	2.49119404899192e+25	0.0	0.8799	0.0145	0.4219	0.332	16.9553	53.3296	595.7158	30.6	857.9676	262.2518	0.0855	5.9291	31.0768	185.4559	216.9091	1561.9809	30.9184	185.7463	1308.1743	0.0	0.0	0	77	62	496	395	33	95	0.9193548387096774	57	0.5806451612903226	36	0.04838709677419355	3	0.0967741935483871	6.0
19	0.0	0	64	512	5	4.4219	4	1.0	4333.3574	4615.6172	4239.2708	31662	1	4448.1268	1530711.0	16.0	0.9692	0.0	0.0	0.0308	0.25	0.0094	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	0.0453	0.0	0.0	1.0	0.0	0.0122	1.5951538773913764e+21	1.973554746569748e+24	0.0	0.8063	0.0155	0.3594	0.25	17.0168	53.3903	595.507	30.6	857.9676	262.4606	0.0912	5.6163	32.4987	196.5511	229.4039	1882.9354	24.8707	196.8133	1622.983	0.0	0.0	0	78	96	768	690	25	71	0.53125	51	0.1875	18	0.020833333333333332	2	0.07291666666666667	7.0	0.0105	9.6184
20	0.0	0	64	512	0	0.0	0	0.0	3256.0234	2826.6427	4613.9837	13362	1	1838.6673	1104019.0	5.0	0.996	0.0	0.0	0.004	0.7598	-0.0018	0.0763	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0334	-0.0011	0.0	1.0	0.0	0.0149	8603.9307	9039291.0	0.0	1.0023	0.0111	0.8125	0.7598	16.4131	52.7717	596.1255	30.5	857.9676	261.842	0.0432	2.9452	20.7324	109.5379	130.5083	2969.965	32.266	109.7322	2804.1924	0.0	0.0	1	79	61	488	428	22	60	0.819672131147541	50	0.19672131147540983	12	0.03278688524590164	2						0.03278688524590164	2.0
21	0.0	0	64	512	1	0.7188	0	0.7188	4464.1445	4825.3981	4220.9477	31774	1	4860.2721	1603625.0	28.0	0.9096	0.0	0.0	0.0904	0.4023	0.0085	0.1165	-0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0434	-0.0001	0.0	1.0	0.0	0.0207	2.0403219462220677e+19	2.583743478900106e+22	0.0	0.8802	0.0142	0.5312	0.4023	17.2875	53.606	593.67	30.8	857.9676	264.2975	0.092	5.9528	32.0153	208.4403	240.7613	2243.0022	39.1203	208.6536	1957.1655	0.0	0.0	1	80	57	456	397	21	54	0.8070175438596491	46	0.08771929824561403	5	0.05263157894736842	3	0.08771929824561403	5.0	0.0085	10.2197	6.298