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_AgentEnvironmentTimeoutError,batch_errors/total_AgentEnvironmentTimeoutError,batch_errors/avg_DaytonaAuthenticationError,batch_errors/total_DaytonaAuthenticationError,batch_errors/avg_VerifierRuntimeError,batch_errors/total_VerifierRuntimeError,batch_errors/avg_DaytonaNotFoundError,batch_errors/total_DaytonaNotFoundError,timing/cleanup_old_checkpoints,timing/save_checkpoints,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError,batch_errors/avg_VerifierTimeoutError,batch_errors/total_VerifierTimeoutError,batch_errors/avg_DaytonaError,batch_errors/total_DaytonaError,batch_errors/avg_ContextLengthExceededError,batch_errors/total_ContextLengthExceededError,timing/save_hf_model,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError
0.0,0,64,512,1,0.0156,0,0.0156,513.5391,2625.2,1.0,26236,1,1588.8893,0.1953,0.1608,0.1609,-0.0005,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0083,-0.0291,0.0,1.0,0.0,0.0178,0.4444,0.1953,12.0642,78.6154,606.7097,29.3,857.9687,251.259,0.1923,3.5931,15.4184,73.4268,89.2021,8145.718,17.602,73.591,8035.3206,0,37,64,512,40,63,367,5.734375,367,1.46875,94,0.15625,10,0.015625,1.0,,,,,,,,,,,,,
0.0,0,64,512,1,0.9844,0,0.9844,256.4102,3270.25,1.0,8312,1,1017.874,0.0781,0.3646,0.3647,-0.0003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0034,-0.0217,0.0,1.0,0.0,0.0125,0.2344,0.0781,12.0077,78.1334,605.2178,29.5,857.9687,252.7509,0.0239,1.3387,7.0582,59.3834,66.5873,3328.8664,18.4202,59.5048,3242.5172,0,38,64,512,86,64,312,4.828125,309,1.0,64,0.5625,36,0.09375,6.0,11.4426,19.0624,0.078125,5.0,0.046875,3.0,0.015625,1.0,0.03125,2.0,,,
0.0,0,64,512,2,0.7656,0,0.5312,408.6738,2428.0814,1.0,8101,1,1031.8913,0.168,0.3035,0.3037,-0.0008,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0079,-0.0498,0.0,1.0,0.0,0.0244,0.4375,0.168,13.3047,91.9354,606.3735,29.3,857.9687,251.5952,0.0241,1.2992,6.9572,60.9637,68.0737,6397.0696,17.4018,61.092,6310.2938,0,39,68,544,61,67,381,5.573529411764706,379,1.1764705882352942,80,0.25,17,,,,,0.014705882352941176,1.0,0.058823529411764705,4.0,0.014705882352941176,1.0,0.014705882352941176,1.0,,,
0.0,0,64,512,3,1.2344,0,0.9688,383.9883,3215.5902,1.0,9054,1,1172.8826,0.1191,0.181,0.1811,-0.0004,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0055,-0.0256,0.0,1.0,0.0,0.0197,0.3281,0.1191,14.0406,92.0868,605.7397,29.4,857.9687,252.229,0.0354,1.6468,7.3746,62.4563,69.9967,5420.0066,17.7311,62.5862,5330.6236,0,40,64,512,64,64,399,6.234375,399,0.546875,35,0.203125,13,0.015625,1.0,0.0079,8.9118,,,,,,,,,6.6659,,
0.0,0,64,512,4,1.0781,0,0.8281,315.2949,2596.4677,1.0,6019,1,911.6647,0.1211,0.075,0.0751,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.006,-0.0107,0.0,1.0,0.0,0.01,0.2812,0.1211,14.3649,92.0377,605.8729,29.4,857.9687,252.0958,0.0196,1.2515,6.8124,57.2361,64.2337,2226.1873,17.7717,57.4013,2142.928,0,41,60,480,76,57,352,5.866666666666666,352,0.55,33,0.3,18,0.016666666666666666,1.0,,,,,,,,,,,,,
0.0,0,64,512,2,1.1562,0,0.8594,350.4609,2294.8974,1.0,6096,1,918.4495,0.1523,0.156,0.1561,-0.0003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.007,-0.0193,0.0,1.0,0.0,0.0108,0.3281,0.1523,16.0237,92.0465,604.1669,29.6,857.9687,253.8018,0.0281,1.007,6.8732,58.1443,65.1695,4730.9187,18.9548,58.2679,4645.7861,0,42,65,520,117,60,320,4.923076923076923,320,0.7846153846153846,51,0.4461538461538462,29,0.03076923076923077,2.0,0.0079,7.5503,0.015384615384615385,1.0,,,,,,,,,
0.0,0,64,512,3,1.1562,0,0.8594,506.7285,2214.1026,1.0,9784,1,1181.084,0.2285,0.1962,0.1963,-0.0006,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0097,-0.0374,0.0,1.0,0.0,0.02,0.4688,0.2285,16.5446,92.2373,608.1587,29.1,857.9687,249.81,0.0281,1.6023,8.6365,65.3044,74.2194,3828.8954,19.3517,65.5544,3733.7211,0,43,63,504,57,63,380,6.0,378,0.7619047619047619,48,0.2857142857142857,18,0.015873015873015872,1.0,,,,,,,,,0.031746031746031744,2.0,,,
0.0,0,64,512,3,1.2812,0,0.875,384.8477,3448.8947,1.0,11922,1,1321.23,0.1113,0.1286,0.1287,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0052,-0.0139,0.0,1.0,0.0,0.0125,0.2656,0.1113,16.9448,92.2662,606.6965,29.3,857.9687,251.2722,0.0323,1.7789,8.0712,63.9146,72.1439,4075.9496,19.0722,64.0401,3982.9522,0,44,67,536,61,66,393,5.82089552238806,390,0.7761194029850746,52,0.43283582089552236,29,0.014925373134328358,1.0,0.0083,7.3633,,,,,0.014925373134328358,1.0,,,,0.029850746268656716,2.0
0.0,0,64,512,3,1.0625,0,0.7344,289.7832,2550.2586,1.0,9971,1,1016.4986,0.1133,0.148,0.1481,-0.0003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0047,-0.0191,0.0,1.0,0.0,0.0151,0.2344,0.1133,17.2552,92.2487,605.9093,29.4,857.9687,252.0594,0.0283,2.2306,6.986,57.0132,64.3289,4079.3376,19.0583,57.3142,3993.7175,0,45,18,144,27,18,97,5.333333333333333,96,0.6111111111111112,11,0.5,9,,,,,,,,,,,,,5.9741,0.05555555555555555,1.0