laion/ablation-pymethods2test-seqmean-arm0-tis-15-8B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: laion/ablation-pymethods2test-seqmean-arm0-tis-15-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-09 05:27:18 +08:00
commit 9f22667c70
40 changed files with 298738 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
training_logs/20260609_214045_metrics_job_653586.csv Normal file
View File

@@ -0,0 +1,21 @@
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/save_hf_model,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_AgentTimeoutError,batch_errors/total_AgentTimeoutError,batch_errors/avg_ContextLengthExceededError,batch_errors/total_ContextLengthExceededError,batch_errors/avg_VerifierTimeoutError,batch_errors/total_VerifierTimeoutError,timing/cleanup_old_checkpoints,timing/save_checkpoints,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError,batch_errors/avg_DaytonaAuthenticationError,batch_errors/total_DaytonaAuthenticationError,batch_errors/avg_DaytonaError,batch_errors/total_DaytonaError
0.0,0,64,512,4,0.4375,0,0.1875,4367.6348,4450.258,4236.6061,20102,1,3081.0821,1530592.0,25.0,0.9745,0.0,0.0,0.0255,0.6133,-0.0018,0.082,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0643,-0.0,0.0,1.0,0.0,0.0116,1005131.5625,1241936512.0,0.0,0.9556,0.021,0.65,0.6133,9.9297,50.2901,562.6478,34.4,857.9675,295.3198,0.0524,3.9222,32.4786,156.8412,189.5694,6.8707,4387.0719,37.9376,157.0373,4155.6423,0.0,0.0,0,15,54,432,390,20,41,0.7962962962962963,43,0.037037037037037035,2.0,0.09259259259259259,5.0,0.018518518518518517,1.0,,,,,,,,
0.0,0,64,512,1,0.9531,0,0.9531,5236.6426,4392.4831,5489.4619,31722,1,5068.1073,1953529.0,45.0,0.8724,0.0,0.0,0.1276,0.2305,0.008,0.0679,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0736,-0.0004,0.0,1.0,0.0,0.012,2.912904544507658e+18,4.067950672816252e+21,0.0,0.908,0.0255,0.3438,0.2305,13.9738,50.8674,555.7899,35.2,857.9675,302.1776,0.0685,6.0938,36.9697,235.7047,272.9919,,940.3521,34.9952,235.9529,626.262,0.0,0.0,0,16,58,464,422,13,41,0.5517241379310345,32,0.1896551724137931,11.0,0.017241379310344827,1.0,0.017241379310344827,1.0,10.4479,18.917,,,,,,
0.0,0,64,512,2,1.6562,0,0.9531,4441.8926,4303.1646,4561.4509,31764,1,4231.7973,1624165.0,28.0,0.9089,0.0,0.0,0.0911,0.4629,-0.0268,0.1262,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0631,-0.0001,0.0,1.0,0.0,0.014,80980987609088.0,9.804779835568947e+16,0.0,0.919,0.0208,0.6094,0.4629,14.1574,51.0022,555.1819,35.3,857.9675,302.7856,0.8639,6.2006,35.3247,195.5062,231.9566,,866.8196,41.0458,195.7672,587.611,0.0,0.0,0,17,63,504,479,13,24,0.2857142857142857,18,0.047619047619047616,3.0,0.047619047619047616,3.0,0.015873015873015872,1.0,,,,,,,,
0.0,0,64,512,3,1.9844,0,0.8438,4984.2539,4197.7163,5522.4112,31647,1,4678.7713,1808744.0,41.0,0.8809,0.0,0.0,0.1191,0.4062,-0.0087,0.1018,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0679,-0.0,0.0,1.0,0.0,0.0172,7.39416158020567e+16,9.942431530797027e+19,0.0,0.9589,0.0221,0.5312,0.4062,14.2903,51.1974,554.0929,35.4,857.9675,303.8746,0.0899,6.4232,37.3252,220.9561,258.6391,,2168.7359,37.6553,221.2235,1866.0111,0.0,0.0,0,18,63,504,457,21,46,0.6190476190476191,39,0.047619047619047616,3.0,0.06349206349206349,4.0,0.015873015873015872,1.0,0.0074,8.3881,,,,,,
0.0,0,64,512,4,1.9062,0,0.8906,4700.6758,3937.2571,5231.5298,31734,1,4306.1606,1743000.0,35.0,0.9022,0.0,0.0,0.0978,0.4102,-0.02,0.1351,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0714,0.0,0.0,1.0,0.0,0.0168,6328167232962560.0,7.310935387570962e+18,0.0,0.9156,0.0245,0.5156,0.4102,14.5789,51.2928,552.8044,35.6,857.9675,305.1631,0.0891,6.021,34.5214,198.7713,233.6051,,1196.6914,32.8597,198.9941,924.198,0.0,0.0,0,19,62,496,459,12,35,0.5483870967741935,34,,,0.03225806451612903,2.0,0.03225806451612903,2.0,,,,,,,,
0.0,0,64,512,4,1.6562,0,0.8281,4695.9609,4342.2462,4913.5457,31736,1,4065.4442,1681502.0,28.0,0.9544,0.0,0.0,0.0456,0.3809,0.0048,0.0503,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0696,-0.0005,0.0,1.0,0.0,0.0122,1080837378408448.0,1.4011869695511101e+18,0.0,0.9341,0.022,0.4531,0.3809,14.7026,51.4866,551.9064,35.7,857.9675,306.0612,0.0871,6.1017,31.5548,187.9218,219.7869,5.8852,1351.9719,33.9437,188.1445,1092.1314,0.0,0.0,0,20,56,448,403,15,42,0.6964285714285714,39,0.07142857142857142,4.0,,,0.10714285714285714,6.0,0.0088,8.1422,,,,,,
0.0,0,64,512,4,1.9844,0,0.8906,4777.4453,4620.9898,4874.4873,31826,1,4055.0244,1707389.0,27.0,0.9601,0.0,0.0,0.0399,0.3828,0.0103,0.1078,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0684,-0.0062,0.0,1.0,0.0,0.0144,20477047209984.0,2.673594378433331e+16,0.0,0.9125,0.0217,0.5,0.3828,14.9075,51.7109,624.8141,27.2,857.9675,233.1534,0.0882,7.6651,35.0631,196.5691,231.9387,,1653.9283,32.7526,196.7865,1381.5656,0.0,0.0,0,21,56,448,403,15,44,0.9642857142857143,54,,,0.03571428571428571,2.0,0.017857142857142856,1.0,,,,,,,,
0.0,0,64,512,3,1.6406,0,0.8438,4256.166,4364.5684,4192.2019,19194,1,3380.6239,1525708.0,35.0,0.9617,0.0,0.0,0.0383,0.3711,0.0204,0.1066,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0682,-0.0021,0.0,1.0,0.0,0.0156,9.329387085443891e+16,1.1523618092078439e+20,0.0,0.8961,0.0225,0.5156,0.3711,14.5482,51.4926,619.0483,27.8,857.9675,238.9193,0.047,3.8528,29.6378,159.7489,189.6301,,1708.2028,35.8861,159.9448,1478.8283,0.0,0.0,0,22,61,488,396,27,75,0.639344262295082,39,0.6229508196721312,38.0,0.04918032786885246,3.0,0.36065573770491804,22.0,0.0083,8.0671,0.03278688524590164,2.0,0.01639344262295082,1.0,,
0.0,0,64,512,3,1.2656,0,0.7969,3544.1543,3840.6749,3276.2937,28297,1,3722.3558,1252311.0,10.0,0.991,0.0,0.0,0.009,0.4746,0.0158,0.0979,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0518,-0.0098,0.0,1.0,0.0,0.0149,7758122496.0,8681794568192.0,0.0,0.8013,0.0161,0.5781,0.4746,15.0082,51.8909,612.8306,28.6,857.9675,245.137,0.0827,5.0234,30.5594,167.256,198.1548,,2873.6125,18.8351,167.5122,2651.5938,0.0,0.0,0,23,63,504,245,58,161,0.6825396825396826,43,1.9841269841269842,125.0,0.015873015873015872,1.0,1.0952380952380953,69.0,,,0.4603174603174603,29.0,,,,
0.0,0,64,512,4,1.6875,0,0.9375,2838.584,5697.4839,2204.031,21845,1,4033.9811,998412.0,19.0,0.9595,0.0,0.0,0.0405,0.1816,0.0534,0.1319,-0.0005,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0375,-0.031,0.0,1.0,0.0,0.0176,796371091193856.0,7.9573848653457e+17,0.0,0.4832,0.012,0.375,0.1816,14.9013,51.7034,610.9744,28.8,857.9675,246.9931,0.0656,3.9288,26.3368,163.6413,190.2636,,4553.1826,19.7707,163.8606,4339.2146,0.0,0.0,0,24,63,504,198,59,150,0.31746031746031744,20,2.015873015873016,127.0,0.031746031746031744,2.0,2.1904761904761907,138.0,0.0083,30.3375,0.30158730158730157,19.0,0.015873015873015872,1.0,0.015873015873015872,1.0
0.0,0,64,512,3,1.5469,0,0.9375,1484.3555,3727.4578,1050.3753,15945,1,2355.9005,540011.0,7.0,0.9765,0.0,0.0,0.0235,0.1621,0.0976,0.1584,-0.0006,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0251,-0.0401,0.0,1.0,0.0,0.0162,175853157744640.0,1.2922646919590707e+17,0.0,0.4014,0.0083,0.3906,0.1621,14.7827,51.591,611.105,28.8,857.9675,246.8625,0.0412,2.8411,14.0718,97.9816,112.2645,6.1145,2911.5013,20.8742,98.1511,2775.5178,0.0,0.0,0,25,60,480,239,50,62,0.16666666666666666,10,0.7833333333333333,47.0,0.06666666666666667,4.0,2.7,162.0,,,0.35,21.0,0.016666666666666666,1.0,0.016666666666666666,1.0
0.0,0,64,512,3,1.4688,0,0.9062,1762.2266,3276.9356,775.2226,14084,1,2254.5374,611382.0,7.0,0.9867,0.0,0.0,0.0133,0.3945,0.2088,0.2489,-0.0017,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.028,-0.1098,0.0,1.0,0.0,0.0301,78101203648512.0,6.106804833275085e+16,0.0,0.5056,0.0092,0.6875,0.3945,15.0391,51.8378,607.4099,29.2,857.9675,250.5576,0.0393,2.7152,16.2956,95.0195,111.5402,,2183.5461,21.0421,95.2048,2048.2464,0.0,0.0,0,26,50,400,287,35,28,0.26,13,0.38,19.0,0.1,5.0,2.2,110.0,0.0076,18.4531,0.2,10.0,,,,
0.0,0,64,512,3,1.7344,0,0.9844,3225.4141,4233.3925,2501.5638,31725,1,3531.9698,1097953.0,6.0,0.9706,0.0,0.0,0.0294,0.418,0.0857,0.1298,-0.001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0417,-0.064,0.0,1.0,0.0,0.0185,1.7051105289310222e+21,1.7866703500134324e+24,0.0,0.7126,0.0141,0.5938,0.418,15.2845,52.0295,607.246,29.2,857.9675,250.7216,0.0933,6.0684,24.9326,145.5165,170.7634,,1456.934,22.7893,145.7369,1257.3089,0.0,0.0,0,27,63,504,327,51,68,0.3968253968253968,25,0.5396825396825397,34.0,0.12698412698412698,8.0,0.9523809523809523,60.0,,,0.7301587301587301,46.0,,,0.015873015873015872,1.0
0.0,0,64,512,4,2.0312,0,0.9062,3251.666,4554.6894,2653.9829,21699,1,3609.6329,1139572.0,15.0,0.9862,0.0,0.0,0.0138,0.3145,0.1116,0.1947,-0.0011,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0421,-0.0686,0.0,1.0,0.0,0.0196,3.3728,2506.6016,0.0,0.6563,0.0144,0.5312,0.3145,15.0491,51.7938,605.1166,29.5,857.9675,252.8509,0.0646,4.1197,22.7726,156.63,179.688,,3692.4206,19.6838,156.8504,3488.9217,0.0,0.0,0,28,62,496,313,47,111,0.3870967741935484,24,1.3548387096774193,84.0,0.0967741935483871,6.0,0.967741935483871,60.0,0.0078,10.6979,0.24193548387096775,15.0,,,0.03225806451612903,2.0
0.0,0,64,512,4,1.6719,0,0.9375,2571.3672,3743.3082,2043.4958,15866,1,2671.8445,889053.0,7.0,0.9918,0.0,0.0,0.0082,0.3105,0.0625,0.1191,-0.0007,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.036,-0.0436,0.0,1.0,0.0,0.0144,2088775.625,1969496832.0,0.0,0.6323,0.0129,0.4375,0.3105,15.0667,51.8913,603.0693,29.7,857.9675,254.8982,0.0526,3.2231,19.9907,119.1558,139.374,,2121.552,24.1526,119.3302,1954.7975,0.0,0.0,0,29,62,496,399,34,26,0.3064516129032258,19,0.1935483870967742,12.0,0.04838709677419355,3.0,1.032258064516129,64.0,,,0.16129032258064516,10.0,,,,
0.0,0,64,512,4,1.5938,0,0.8594,3329.0859,3448.2411,3212.6911,31752,1,3171.8807,1207059.0,16.0,0.9547,0.0,0.0,0.0453,0.4941,0.0633,0.1659,-0.0008,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0435,-0.0529,0.0,1.0,0.0,0.0237,166590859444224.0,1.8302711074127872e+17,0.0,0.7955,0.0163,0.7031,0.4941,15.2241,52.0995,601.8652,29.8,857.9675,256.1023,0.0917,5.5872,23.2574,143.9244,167.4704,6.1638,1800.873,28.7964,144.1208,1599.0148,0.0,0.0,0,30,61,488,408,28,51,0.7049180327868853,43,0.01639344262295082,1.0,0.11475409836065574,7.0,0.4426229508196721,27.0,0.0073,8.1466,0.01639344262295082,1.0,0.01639344262295082,1.0,,
0.0,0,64,512,4,1.7188,0,0.875,4176.25,4287.3301,4101.4706,22905,1,3442.4973,1477397.0,13.0,0.9695,0.0,0.0,0.0305,0.4023,0.0198,0.0959,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0487,-0.0138,0.0,1.0,0.0,0.0177,17930.9121,21793098.0,0.0,0.8509,0.0185,0.5312,0.4023,14.9604,51.8221,601.6973,29.9,857.9675,256.2702,0.0519,4.5315,30.1351,156.4327,186.8623,,1635.6999,31.1503,156.6733,1413.1506,0.0,0.0,0,31,62,496,427,25,63,1.0483870967741935,65,0.016129032258064516,1.0,0.016129032258064516,1.0,0.0967741935483871,6.0,,,,,,,0.04838709677419355,3.0
0.0,0,64,512,5,1.7031,0,0.875,4112.8223,4007.204,4181.0836,31560,1,3957.1982,1471823.0,15.0,0.9631,0.0,0.0,0.0369,0.3926,0.0092,0.1152,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0462,-0.0013,0.0,1.0,0.0,0.0137,113758040.0,137789751296.0,0.0,0.8584,0.0187,0.5156,0.3926,15.251,52.1536,599.0416,30.2,857.9675,258.9259,0.0694,5.7857,28.8593,179.0917,208.2315,,1896.1165,35.5573,179.3023,1646.5384,0.0,0.0,0,32,62,496,454,17,33,0.3870967741935484,24,0.08064516129032258,5.0,0.016129032258064516,1.0,0.14516129032258066,9.0,0.0086,11.4834,,,,,0.06451612903225806,4.0
0.0,0,64,512,3,1.6719,0,0.8906,3989.2363,3479.5046,4367.2007,23645,1,3195.8215,1377193.0,19.0,0.9806,0.0,0.0,0.0194,0.4258,0.0032,0.0398,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0433,-0.0003,0.0,1.0,0.0,0.0155,214550183936.0,251782945046528.0,0.0,0.9224,0.0178,0.4844,0.4258,15.0996,52.0021,598.8062,30.2,857.9675,259.1614,0.0535,4.9425,28.9784,147.4112,176.6704,,1164.9656,31.3944,147.638,951.9529,0.0,0.0,0,33,64,512,443,16,69,1.046875,67,0.015625,1.0,,,,,,,,,,,0.015625,1.0
0.0,0,64,512,5,1.7812,0,0.875,3690.3398,3317.2692,3896.0939,20066,1,3147.0993,1351091.0,13.0,0.9855,0.0,0.0,0.0145,0.3555,-0.0158,0.1224,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0489,0.0,0.0,1.0,0.0,0.0231,4346809.0,4922826240.0,0.0,0.8724,0.0195,0.4844,0.3555,15.2644,52.2489,596.6576,30.5,857.9675,261.3099,0.0489,4.2274,24.6053,147.5165,172.3903,,1643.8279,30.4621,147.7346,1436.743,0.0,0.0,0,34,18,144,123,6,21,1.0555555555555556,19,,,0.05555555555555555,1.0,,,0.0074,8.954,,,,,0.05555555555555555,1.0
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/save_hf_model 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_AgentTimeoutError batch_errors/total_AgentTimeoutError batch_errors/avg_ContextLengthExceededError batch_errors/total_ContextLengthExceededError batch_errors/avg_VerifierTimeoutError batch_errors/total_VerifierTimeoutError timing/cleanup_old_checkpoints timing/save_checkpoints batch_errors/avg_AgentSetupTimeoutError batch_errors/total_AgentSetupTimeoutError batch_errors/avg_DaytonaAuthenticationError batch_errors/total_DaytonaAuthenticationError batch_errors/avg_DaytonaError batch_errors/total_DaytonaError
2 0.0 0 64 512 4 0.4375 0 0.1875 4367.6348 4450.258 4236.6061 20102 1 3081.0821 1530592.0 25.0 0.9745 0.0 0.0 0.0255 0.6133 -0.0018 0.082 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0643 -0.0 0.0 1.0 0.0 0.0116 1005131.5625 1241936512.0 0.0 0.9556 0.021 0.65 0.6133 9.9297 50.2901 562.6478 34.4 857.9675 295.3198 0.0524 3.9222 32.4786 156.8412 189.5694 6.8707 4387.0719 37.9376 157.0373 4155.6423 0.0 0.0 0 15 54 432 390 20 41 0.7962962962962963 43 0.037037037037037035 2.0 0.09259259259259259 5.0 0.018518518518518517 1.0
3 0.0 0 64 512 1 0.9531 0 0.9531 5236.6426 4392.4831 5489.4619 31722 1 5068.1073 1953529.0 45.0 0.8724 0.0 0.0 0.1276 0.2305 0.008 0.0679 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0736 -0.0004 0.0 1.0 0.0 0.012 2.912904544507658e+18 4.067950672816252e+21 0.0 0.908 0.0255 0.3438 0.2305 13.9738 50.8674 555.7899 35.2 857.9675 302.1776 0.0685 6.0938 36.9697 235.7047 272.9919 940.3521 34.9952 235.9529 626.262 0.0 0.0 0 16 58 464 422 13 41 0.5517241379310345 32 0.1896551724137931 11.0 0.017241379310344827 1.0 0.017241379310344827 1.0 10.4479 18.917
4 0.0 0 64 512 2 1.6562 0 0.9531 4441.8926 4303.1646 4561.4509 31764 1 4231.7973 1624165.0 28.0 0.9089 0.0 0.0 0.0911 0.4629 -0.0268 0.1262 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0631 -0.0001 0.0 1.0 0.0 0.014 80980987609088.0 9.804779835568947e+16 0.0 0.919 0.0208 0.6094 0.4629 14.1574 51.0022 555.1819 35.3 857.9675 302.7856 0.8639 6.2006 35.3247 195.5062 231.9566 866.8196 41.0458 195.7672 587.611 0.0 0.0 0 17 63 504 479 13 24 0.2857142857142857 18 0.047619047619047616 3.0 0.047619047619047616 3.0 0.015873015873015872 1.0
5 0.0 0 64 512 3 1.9844 0 0.8438 4984.2539 4197.7163 5522.4112 31647 1 4678.7713 1808744.0 41.0 0.8809 0.0 0.0 0.1191 0.4062 -0.0087 0.1018 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0679 -0.0 0.0 1.0 0.0 0.0172 7.39416158020567e+16 9.942431530797027e+19 0.0 0.9589 0.0221 0.5312 0.4062 14.2903 51.1974 554.0929 35.4 857.9675 303.8746 0.0899 6.4232 37.3252 220.9561 258.6391 2168.7359 37.6553 221.2235 1866.0111 0.0 0.0 0 18 63 504 457 21 46 0.6190476190476191 39 0.047619047619047616 3.0 0.06349206349206349 4.0 0.015873015873015872 1.0 0.0074 8.3881
6 0.0 0 64 512 4 1.9062 0 0.8906 4700.6758 3937.2571 5231.5298 31734 1 4306.1606 1743000.0 35.0 0.9022 0.0 0.0 0.0978 0.4102 -0.02 0.1351 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0714 0.0 0.0 1.0 0.0 0.0168 6328167232962560.0 7.310935387570962e+18 0.0 0.9156 0.0245 0.5156 0.4102 14.5789 51.2928 552.8044 35.6 857.9675 305.1631 0.0891 6.021 34.5214 198.7713 233.6051 1196.6914 32.8597 198.9941 924.198 0.0 0.0 0 19 62 496 459 12 35 0.5483870967741935 34 0.03225806451612903 2.0 0.03225806451612903 2.0
7 0.0 0 64 512 4 1.6562 0 0.8281 4695.9609 4342.2462 4913.5457 31736 1 4065.4442 1681502.0 28.0 0.9544 0.0 0.0 0.0456 0.3809 0.0048 0.0503 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0696 -0.0005 0.0 1.0 0.0 0.0122 1080837378408448.0 1.4011869695511101e+18 0.0 0.9341 0.022 0.4531 0.3809 14.7026 51.4866 551.9064 35.7 857.9675 306.0612 0.0871 6.1017 31.5548 187.9218 219.7869 5.8852 1351.9719 33.9437 188.1445 1092.1314 0.0 0.0 0 20 56 448 403 15 42 0.6964285714285714 39 0.07142857142857142 4.0 0.10714285714285714 6.0 0.0088 8.1422
8 0.0 0 64 512 4 1.9844 0 0.8906 4777.4453 4620.9898 4874.4873 31826 1 4055.0244 1707389.0 27.0 0.9601 0.0 0.0 0.0399 0.3828 0.0103 0.1078 -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 0.0684 -0.0062 0.0 1.0 0.0 0.0144 20477047209984.0 2.673594378433331e+16 0.0 0.9125 0.0217 0.5 0.3828 14.9075 51.7109 624.8141 27.2 857.9675 233.1534 0.0882 7.6651 35.0631 196.5691 231.9387 1653.9283 32.7526 196.7865 1381.5656 0.0 0.0 0 21 56 448 403 15 44 0.9642857142857143 54 0.03571428571428571 2.0 0.017857142857142856 1.0
9 0.0 0 64 512 3 1.6406 0 0.8438 4256.166 4364.5684 4192.2019 19194 1 3380.6239 1525708.0 35.0 0.9617 0.0 0.0 0.0383 0.3711 0.0204 0.1066 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0682 -0.0021 0.0 1.0 0.0 0.0156 9.329387085443891e+16 1.1523618092078439e+20 0.0 0.8961 0.0225 0.5156 0.3711 14.5482 51.4926 619.0483 27.8 857.9675 238.9193 0.047 3.8528 29.6378 159.7489 189.6301 1708.2028 35.8861 159.9448 1478.8283 0.0 0.0 0 22 61 488 396 27 75 0.639344262295082 39 0.6229508196721312 38.0 0.04918032786885246 3.0 0.36065573770491804 22.0 0.0083 8.0671 0.03278688524590164 2.0 0.01639344262295082 1.0
10 0.0 0 64 512 3 1.2656 0 0.7969 3544.1543 3840.6749 3276.2937 28297 1 3722.3558 1252311.0 10.0 0.991 0.0 0.0 0.009 0.4746 0.0158 0.0979 -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 0.0518 -0.0098 0.0 1.0 0.0 0.0149 7758122496.0 8681794568192.0 0.0 0.8013 0.0161 0.5781 0.4746 15.0082 51.8909 612.8306 28.6 857.9675 245.137 0.0827 5.0234 30.5594 167.256 198.1548 2873.6125 18.8351 167.5122 2651.5938 0.0 0.0 0 23 63 504 245 58 161 0.6825396825396826 43 1.9841269841269842 125.0 0.015873015873015872 1.0 1.0952380952380953 69.0 0.4603174603174603 29.0
11 0.0 0 64 512 4 1.6875 0 0.9375 2838.584 5697.4839 2204.031 21845 1 4033.9811 998412.0 19.0 0.9595 0.0 0.0 0.0405 0.1816 0.0534 0.1319 -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 0.0375 -0.031 0.0 1.0 0.0 0.0176 796371091193856.0 7.9573848653457e+17 0.0 0.4832 0.012 0.375 0.1816 14.9013 51.7034 610.9744 28.8 857.9675 246.9931 0.0656 3.9288 26.3368 163.6413 190.2636 4553.1826 19.7707 163.8606 4339.2146 0.0 0.0 0 24 63 504 198 59 150 0.31746031746031744 20 2.015873015873016 127.0 0.031746031746031744 2.0 2.1904761904761907 138.0 0.0083 30.3375 0.30158730158730157 19.0 0.015873015873015872 1.0 0.015873015873015872 1.0
12 0.0 0 64 512 3 1.5469 0 0.9375 1484.3555 3727.4578 1050.3753 15945 1 2355.9005 540011.0 7.0 0.9765 0.0 0.0 0.0235 0.1621 0.0976 0.1584 -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 0.0251 -0.0401 0.0 1.0 0.0 0.0162 175853157744640.0 1.2922646919590707e+17 0.0 0.4014 0.0083 0.3906 0.1621 14.7827 51.591 611.105 28.8 857.9675 246.8625 0.0412 2.8411 14.0718 97.9816 112.2645 6.1145 2911.5013 20.8742 98.1511 2775.5178 0.0 0.0 0 25 60 480 239 50 62 0.16666666666666666 10 0.7833333333333333 47.0 0.06666666666666667 4.0 2.7 162.0 0.35 21.0 0.016666666666666666 1.0 0.016666666666666666 1.0
13 0.0 0 64 512 3 1.4688 0 0.9062 1762.2266 3276.9356 775.2226 14084 1 2254.5374 611382.0 7.0 0.9867 0.0 0.0 0.0133 0.3945 0.2088 0.2489 -0.0017 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.028 -0.1098 0.0 1.0 0.0 0.0301 78101203648512.0 6.106804833275085e+16 0.0 0.5056 0.0092 0.6875 0.3945 15.0391 51.8378 607.4099 29.2 857.9675 250.5576 0.0393 2.7152 16.2956 95.0195 111.5402 2183.5461 21.0421 95.2048 2048.2464 0.0 0.0 0 26 50 400 287 35 28 0.26 13 0.38 19.0 0.1 5.0 2.2 110.0 0.0076 18.4531 0.2 10.0
14 0.0 0 64 512 3 1.7344 0 0.9844 3225.4141 4233.3925 2501.5638 31725 1 3531.9698 1097953.0 6.0 0.9706 0.0 0.0 0.0294 0.418 0.0857 0.1298 -0.001 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0417 -0.064 0.0 1.0 0.0 0.0185 1.7051105289310222e+21 1.7866703500134324e+24 0.0 0.7126 0.0141 0.5938 0.418 15.2845 52.0295 607.246 29.2 857.9675 250.7216 0.0933 6.0684 24.9326 145.5165 170.7634 1456.934 22.7893 145.7369 1257.3089 0.0 0.0 0 27 63 504 327 51 68 0.3968253968253968 25 0.5396825396825397 34.0 0.12698412698412698 8.0 0.9523809523809523 60.0 0.7301587301587301 46.0 0.015873015873015872 1.0
15 0.0 0 64 512 4 2.0312 0 0.9062 3251.666 4554.6894 2653.9829 21699 1 3609.6329 1139572.0 15.0 0.9862 0.0 0.0 0.0138 0.3145 0.1116 0.1947 -0.0011 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0421 -0.0686 0.0 1.0 0.0 0.0196 3.3728 2506.6016 0.0 0.6563 0.0144 0.5312 0.3145 15.0491 51.7938 605.1166 29.5 857.9675 252.8509 0.0646 4.1197 22.7726 156.63 179.688 3692.4206 19.6838 156.8504 3488.9217 0.0 0.0 0 28 62 496 313 47 111 0.3870967741935484 24 1.3548387096774193 84.0 0.0967741935483871 6.0 0.967741935483871 60.0 0.0078 10.6979 0.24193548387096775 15.0 0.03225806451612903 2.0
16 0.0 0 64 512 4 1.6719 0 0.9375 2571.3672 3743.3082 2043.4958 15866 1 2671.8445 889053.0 7.0 0.9918 0.0 0.0 0.0082 0.3105 0.0625 0.1191 -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 0.036 -0.0436 0.0 1.0 0.0 0.0144 2088775.625 1969496832.0 0.0 0.6323 0.0129 0.4375 0.3105 15.0667 51.8913 603.0693 29.7 857.9675 254.8982 0.0526 3.2231 19.9907 119.1558 139.374 2121.552 24.1526 119.3302 1954.7975 0.0 0.0 0 29 62 496 399 34 26 0.3064516129032258 19 0.1935483870967742 12.0 0.04838709677419355 3.0 1.032258064516129 64.0 0.16129032258064516 10.0
17 0.0 0 64 512 4 1.5938 0 0.8594 3329.0859 3448.2411 3212.6911 31752 1 3171.8807 1207059.0 16.0 0.9547 0.0 0.0 0.0453 0.4941 0.0633 0.1659 -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 0.0435 -0.0529 0.0 1.0 0.0 0.0237 166590859444224.0 1.8302711074127872e+17 0.0 0.7955 0.0163 0.7031 0.4941 15.2241 52.0995 601.8652 29.8 857.9675 256.1023 0.0917 5.5872 23.2574 143.9244 167.4704 6.1638 1800.873 28.7964 144.1208 1599.0148 0.0 0.0 0 30 61 488 408 28 51 0.7049180327868853 43 0.01639344262295082 1.0 0.11475409836065574 7.0 0.4426229508196721 27.0 0.0073 8.1466 0.01639344262295082 1.0 0.01639344262295082 1.0
18 0.0 0 64 512 4 1.7188 0 0.875 4176.25 4287.3301 4101.4706 22905 1 3442.4973 1477397.0 13.0 0.9695 0.0 0.0 0.0305 0.4023 0.0198 0.0959 -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 0.0487 -0.0138 0.0 1.0 0.0 0.0177 17930.9121 21793098.0 0.0 0.8509 0.0185 0.5312 0.4023 14.9604 51.8221 601.6973 29.9 857.9675 256.2702 0.0519 4.5315 30.1351 156.4327 186.8623 1635.6999 31.1503 156.6733 1413.1506 0.0 0.0 0 31 62 496 427 25 63 1.0483870967741935 65 0.016129032258064516 1.0 0.016129032258064516 1.0 0.0967741935483871 6.0 0.04838709677419355 3.0
19 0.0 0 64 512 5 1.7031 0 0.875 4112.8223 4007.204 4181.0836 31560 1 3957.1982 1471823.0 15.0 0.9631 0.0 0.0 0.0369 0.3926 0.0092 0.1152 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0462 -0.0013 0.0 1.0 0.0 0.0137 113758040.0 137789751296.0 0.0 0.8584 0.0187 0.5156 0.3926 15.251 52.1536 599.0416 30.2 857.9675 258.9259 0.0694 5.7857 28.8593 179.0917 208.2315 1896.1165 35.5573 179.3023 1646.5384 0.0 0.0 0 32 62 496 454 17 33 0.3870967741935484 24 0.08064516129032258 5.0 0.016129032258064516 1.0 0.14516129032258066 9.0 0.0086 11.4834 0.06451612903225806 4.0
20 0.0 0 64 512 3 1.6719 0 0.8906 3989.2363 3479.5046 4367.2007 23645 1 3195.8215 1377193.0 19.0 0.9806 0.0 0.0 0.0194 0.4258 0.0032 0.0398 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0433 -0.0003 0.0 1.0 0.0 0.0155 214550183936.0 251782945046528.0 0.0 0.9224 0.0178 0.4844 0.4258 15.0996 52.0021 598.8062 30.2 857.9675 259.1614 0.0535 4.9425 28.9784 147.4112 176.6704 1164.9656 31.3944 147.638 951.9529 0.0 0.0 0 33 64 512 443 16 69 1.046875 67 0.015625 1.0 0.015625 1.0
21 0.0 0 64 512 5 1.7812 0 0.875 3690.3398 3317.2692 3896.0939 20066 1 3147.0993 1351091.0 13.0 0.9855 0.0 0.0 0.0145 0.3555 -0.0158 0.1224 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0489 0.0 0.0 1.0 0.0 0.0231 4346809.0 4922826240.0 0.0 0.8724 0.0195 0.4844 0.3555 15.2644 52.2489 596.6576 30.5 857.9675 261.3099 0.0489 4.2274 24.6053 147.5165 172.3903 1643.8279 30.4621 147.7346 1436.743 0.0 0.0 0 34 18 144 123 6 21 1.0555555555555556 19 0.05555555555555555 1.0 0.0074 8.954 0.05555555555555555 1.0