ablation-pymethods2test-shaped-45-8B/training_logs/20260612_220132_metrics_job_628825.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_VerifierTimeoutError	batch_errors/total_VerifierTimeoutError	batch_errors/avg_AgentTimeoutError	batch_errors/total_AgentTimeoutError	batch_errors/avg_ContextLengthExceededError	batch_errors/total_ContextLengthExceededError	batch_errors/avg_AgentSetupTimeoutError	batch_errors/total_AgentSetupTimeoutError	batch_errors/avg_InvalidChatHistory	batch_errors/total_InvalidChatHistory	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	3	0.2969	0	0.1719	3199.9375	4071.6584	2412.4721	31710	1	3554.7524	0.4746	0.0478	0.1097	-0.0005	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0996	-0.0347	0.0	1.0	0.0	0.0153	0.5818	0.4746	13.3086	50.5092	577.3386	32.7	857.9676	280.629	0.1782	4.5854	148.1198	158.2811	306.8462	7430.9562	17.454	158.5474	7102.0703	0	53	58	464	190	55	222	0.5862068965517241	34	3.0172413793103448	175	0.20689655172413793	12.0	0.3103448275862069	18.0	0.9827586206896551	57	0.034482758620689655	2.0
3	0.0	0	64	512	1	0.9688	0	0.9688	1660.8398	3606.8852	1397.6275	31652	1	2991.8597	0.1191	0.0393	0.101	-0.0002	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0643	-0.0118	0.0	1.0	0.0	0.0186	0.3281	0.1191	13.4609	50.5854	574.7183	33.0	857.9676	283.2493	0.0612	4.3067	16.4321	118.6926	135.4282	2972.7191	20.1445	118.9344	2812.8332	0	54	62	496	315	49	114	1.0161290322580645	63	1.3064516129032258	81	0.08064516129032258	5.0	0.0967741935483871	6.0	0.5	31	0.03225806451612903	2.0	788.2552	873.9508
4	0.0	0	64	512	2	1.5469	0	0.9375	2503.9727	3359.2695	2089.9594	31797	1	3307.4746	0.3262	0.0434	0.1494	-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	0.0875	-0.0549	0.0	1.0	0.0	0.0247	0.5156	0.3262	13.528	50.6887	573.6981	33.1	857.9676	284.2695	0.063	4.3599	19.3328	134.4189	154.0455	4313.6759	19.4671	134.6493	4135.7999	0	55	58	464	256	52	154	0.8793103448275862	51	2.189655172413793	127	0.13793103448275862	8.0	0.1896551724137931	11.0	0.5689655172413793	33	0.034482758620689655	2.0			33.3153
5	0.0	0	64	512	3	1.8438	1	1.0	2267.8379	4011.6465	1849.8305	31745	1	3089.9207	0.1934	0.0603	0.1131	-0.0005	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0768	-0.0295	0.0	1.0	0.0	0.0179	0.3906	0.1934	13.7004	50.9664	572.3271	33.3	857.9676	285.6404	0.0634	4.297	21.1829	126.7079	148.1795	2256.5	17.5778	126.9328	2086.4407	0	56	61	488	278	55	145	0.9180327868852459	56	1.639344262295082	100	0.08196721311475409	5.0	0.06557377049180328	4.0	0.9508196721311475	58	0.08196721311475409	5.0	0.0095	8.3159
6	0.0	0	64	512	3	1.6094	0	0.8906	1934.0137	2928.8582	1555.9191	31764	1	2911.8707	0.2754	0.0544	0.2013	-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	0.0735	-0.0418	0.0	1.0	0.0	0.0236	0.5	0.2754	13.806	51.0526	572.7429	33.2	857.9676	285.2247	0.0639	4.2663	17.1322	112.7882	130.1891	4721.0139	17.7285	112.9927	4568.8267	0	57	59	472	262	55	148	0.847457627118644	50	1.9491525423728813	115	0.0847457627118644	5.0	0.2033898305084746	12.0	0.6949152542372882	41	0.1016949152542373	6.0
7	0.0	0	64	512	3	1.5	0	0.9531	1770.4238	3112.9733	1214.1188	13369	1	2129.9135	0.293	0.0852	0.1678	-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	0.0766	-0.0504	0.0	1.0	0.0	0.0195	0.5	0.293	13.4865	50.6928	572.7063	33.2	857.9676	285.2613	0.0393	2.0026	14.0199	90.7598	105.0123	4293.1955	17.9141	90.9527	4168.2627	0	58	62	496	220	57	226	0.6129032258064516	38	3.064516129032258	190	0.04838709677419355	3.0	0.0967741935483871	6.0	0.8548387096774194	53	0.04838709677419355	3.0	0.0091	59.1392
8	0.0	0	64	512	3	1.4844	0	0.9688	1476.5684	2851.2992	1023.0857	13510	1	2062.2765	0.248	0.0652	0.1257	-0.0005	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0625	-0.0312	0.0	1.0	0.0	0.0158	0.4375	0.248	13.4512	50.6169	572.2433	33.3	857.9676	285.7242	0.0481	1.9872	13.9888	89.1352	103.3565	3191.8712	17.9253	89.3191	3068.5999	0	59	58	464	286	48	148	0.39655172413793105	23	1.6551724137931034	96	0.08620689655172414	5.0	0.1724137931034483	10.0	0.896551724137931	52
9	0.0	0	64	512	3	1.4219	0	0.9062	2018.3379	3368.0636	1329.5398	31744	1	2826.9423	0.3379	0.0441	0.0801	-0.0002	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0699	-0.0159	0.0	1.0	0.0	0.0143	0.4688	0.3379	14.2374	51.4343	571.5837	33.4	857.9676	286.3839	0.0659	4.3226	19.4907	115.4257	135.2091	3331.9646	17.9623	115.652	3174.4695	0	60	66	528	241	59	239	0.6212121212121212	41	2.8484848484848486	188	0.045454545454545456	3.0	0.030303030303030304	2.0	0.6818181818181818	45	0.045454545454545456	3.0	0.0077	67.4361	6.5117
10	0.0	0	64	512	3	1.2812	0	0.8906	1605.3398	3133.4453	1047.072	31571	1	2588.0632	0.2676	0.0765	0.1111	-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	0.054	-0.0366	0.0	1.0	0.0	0.0135	0.4375	0.2676	14.2345	51.4315	571.2025	33.4	857.9676	286.7651	0.0614	4.1828	15.4202	105.8485	121.543	4540.5155	17.9319	106.0611	4396.8541	0	61	62	496	271	54	161	1.1129032258064515	69	2.0806451612903225	129	0.12903225806451613	8.0			0.41935483870967744	26						0.016129032258064516	1.0
11	0.0	0	64	512	3	1.4375	0	0.9531	1755.4785	2907.0659	1198.0435	17523	1	2107.3788	0.3262	0.0952	0.1792	-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	0.0681	-0.0567	0.0	1.0	0.0	0.0201	0.5781	0.3262	13.987	51.1837	570.8343	33.5	857.9676	287.1333	0.0622	2.5366	14.8746	96.4969	111.6174	3708.0328	17.9029	96.68	3575.969	0	62	17	136	85	15	36	0.7058823529411765	12	1.588235294117647	27			0.11764705882352941	2.0	1.0	17	0.058823529411764705	1.0	0.009	8.2472