laion/ablation-pymethods2test-shaped-45-8B
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-shaped-45-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 17:31:01 +08:00
commit 68d3be9a84
35 changed files with 261550 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
training_logs/20260612_220132_metrics_job_628824.csv Normal file
View File

@@ -0,0 +1,28 @@
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_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,timing/save_hf_model,batch_errors/avg_DaytonaAuthenticationError,batch_errors/total_DaytonaAuthenticationError,batch_errors/avg_DaytonaNotFoundError,batch_errors/total_DaytonaNotFoundError,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError
0.0,0,64,512,4,0.875,0,0.3438,4767.7715,4795.1262,4728.7488,25222,1,3182.1526,0.5879,0.0092,0.1088,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1199,-0.0056,0.0,1.0,0.0,0.013,0.625,0.5879,10.536,50.3104,626.3275,27.0,857.9676,231.6401,0.2023,3.92,34.2457,174.2058,208.9411,4078.6541,22.8866,174.4925,3842.9061,0,27,53,424,388,18,33,0.6226415094339622,33,0.03773584905660377,2.0,0.16981132075471697,9.0,0.05660377358490566,3.0,,,,,,,,,
0.0,0,64,512,1,0.9219,0,0.9219,4983.4746,5436.399,4709.4483,31754,1,4133.7783,0.377,0.0227,0.1274,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1345,-0.0042,0.0,1.0,0.0,0.0185,0.5,0.377,13.5033,50.54,618.0227,28.0,857.9676,239.9449,0.0639,4.7884,32.7876,194.5012,227.5803,1263.0117,21.7204,194.7281,1008.9141,0,28,56,448,407,14,36,0.6964285714285714,39,0.03571428571428571,2.0,0.125,7.0,0.08928571428571429,5.0,12.171,20.1752,,,,,,,
0.0,0,64,512,2,1.625,0,0.9375,4671.3027,5053.6712,4385.5051,31822,1,4728.8661,0.4277,0.0211,0.0979,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1248,0.0,0.0,1.0,0.0,0.0199,0.5469,0.4277,13.6422,50.7001,613.7819,28.5,857.9676,244.1857,0.0632,4.7469,34.1954,213.2039,247.7078,1068.7568,23.7909,213.4484,792.5078,0,29,60,480,418,17,56,0.8,48,0.03333333333333333,2.0,0.1,6.0,0.1,6.0,,,,,,,,,
0.0,0,64,512,3,1.7969,0,0.8594,4280.7344,4076.9107,4439.2639,31798,1,3580.8473,0.4375,0.0025,0.0887,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1155,-0.0042,0.0,1.0,0.0,0.0155,0.5156,0.4375,13.777,50.8871,612.502,28.6,857.9676,245.4656,0.0913,4.6547,28.7012,169.1447,198.1744,1539.4904,20.8891,169.3814,1315.7664,0,30,61,488,437,18,51,0.7704918032786885,47,,,0.08196721311475409,5.0,,,0.009,8.6111,6.395,,,,,,
0.0,0,64,512,4,2.1406,0,0.9375,5000.9766,5222.5862,4817.3571,31737,1,4371.6949,0.4531,0.016,0.088,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1205,0.0,0.0,1.0,0.0,0.0168,0.5312,0.4531,14.216,51.3028,608.8709,29.0,857.9676,249.0967,0.0647,4.7976,32.6722,201.0971,234.1363,1535.0765,21.6286,201.399,1274.5101,0,31,62,496,382,30,106,1.5806451612903225,98,0.04838709677419355,3.0,0.0967741935483871,6.0,0.0967741935483871,6.0,,,,0.016129032258064516,1.0,0.016129032258064516,1.0,,
0.0,0,64,512,5,1.9688,0,0.9219,3795.5312,4476.6118,3456.9825,31804,1,4323.2735,0.332,0.0128,0.1017,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1108,-0.0064,0.0,1.0,0.0,0.0172,0.4844,0.332,14.2689,51.3345,607.3277,29.2,857.9676,250.6399,0.0644,4.6435,28.605,177.2897,206.2082,1701.0639,23.5775,177.5384,1466.6314,0,32,62,496,430,20,62,0.9354838709677419,58,,,0.08064516129032258,5.0,0.06451612903225806,4.0,0.0098,7.957,,,,,,,
0.0,0,64,512,5,1.8281,0,0.9062,4426.4102,4337.7767,4486.0784,31776,1,4189.8754,0.4023,0.02,0.084,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1229,0.0,0.0,1.0,0.0,0.0162,0.4844,0.4023,14.2714,51.3339,605.3755,29.4,857.9676,252.5921,0.0989,4.7055,30.6605,192.3827,223.4015,1469.9716,21.125,192.6417,1220.734,0,33,62,496,445,19,46,0.6129032258064516,38,0.016129032258064516,1.0,0.11290322580645161,7.0,0.06451612903225806,4.0,,,,,,,,0.016129032258064516,1.0
0.0,0,64,512,4,1.8594,0,0.8906,4549.4668,4319.729,4714.4463,31620,1,3895.5488,0.418,-0.0026,0.1007,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1269,-0.002,0.0,1.0,0.0,0.0154,0.4844,0.418,14.2645,51.3268,603.5889,29.6,857.9676,254.3787,0.0836,4.6898,28.9795,187.0802,216.4045,1363.6601,23.3237,187.3409,1119.2363,0,34,62,496,423,24,73,1.032258064516129,64,0.016129032258064516,1.0,0.12903225806451613,8.0,,,0.0095,8.3515,,,,,,,
0.0,0,64,512,6,1.9219,0,0.9219,3946.0859,4376.362,3619.3127,31808,1,3948.408,0.4316,0.0053,0.1214,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1186,0.0,0.0,1.0,0.0,0.0191,0.5781,0.4316,14.2697,51.332,602.1526,29.8,857.9676,255.815,0.0941,4.6209,31.141,176.3125,207.7997,1421.4447,22.28,176.5642,1186.7383,0,35,64,512,454,20,49,0.75,48,,,0.015625,1.0,0.125,8.0,,,5.9666,,,,,0.015625,1.0
0.0,0,64,512,4,1.9844,0,0.8438,4738.3516,4627.5896,4816.6233,31838,1,4336.9944,0.4141,0.0016,0.1087,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1313,-0.002,0.0,1.0,0.0,0.0214,0.5469,0.4141,14.2961,51.3983,600.9323,30.0,857.9676,257.0353,0.077,4.82,30.3179,188.5618,219.2099,1686.9542,23.188,188.8147,1439.7332,0,36,62,496,429,23,66,0.9838709677419355,61,0.016129032258064516,1.0,0.06451612903225806,4.0,0.016129032258064516,1.0,0.0087,8.22,,,,,,,
0.0,0,64,512,3,1.75,0,0.875,4288.6914,4517.4416,4100.6441,31765,1,3993.4464,0.4512,0.0038,0.1186,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1252,-0.0,0.0,1.0,0.0,0.0137,0.5469,0.4512,14.4357,51.5209,598.8259,30.2,857.9676,259.1417,0.0654,5.1265,29.5529,183.3451,213.2355,1634.9331,22.0702,183.617,1394.4971,0,37,63,504,462,16,41,0.49206349206349204,31,0.07936507936507936,5.0,0.07936507936507936,5.0,,,,,,,,,,0.015873015873015872,1.0
0.0,0,64,512,3,1.7812,0,0.8906,4378.4395,4279.6997,4521.5885,31750,1,3800.9451,0.5918,0.0122,0.1617,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1219,0.0,0.0,1.0,0.0,0.0233,0.7344,0.5918,14.3297,51.4598,597.5809,30.3,857.9676,260.3867,0.0842,4.6513,29.0723,176.8748,206.3067,1204.9325,22.4098,177.1498,971.5582,0,38,62,496,441,16,55,0.8709677419354839,54,0.03225806451612903,2.0,0.016129032258064516,1.0,,,0.008,7.9801,,,,,,,
0.0,0,64,512,3,1.7188,0,0.9062,4493.166,4310.5861,4659.3955,31795,1,4271.0567,0.4766,0.0119,0.069,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1184,0.0,0.0,1.0,0.0,0.0179,0.5469,0.4766,14.348,51.4611,594.5972,30.7,857.9676,263.3704,0.066,4.684,33.4072,192.1783,225.9165,1350.158,22.8675,192.4429,1096.6861,0,39,62,496,412,24,83,1.2419354838709677,77,,,0.0967741935483871,6.0,,,,,,,,,,0.016129032258064516,1.0
0.0,0,64,512,4,1.8438,0,0.8594,4353.3359,4784.3178,4043.8389,31733,1,4145.6711,0.418,-0.0101,0.1282,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1206,-0.0,0.0,1.0,0.0,0.0197,0.5625,0.418,14.3591,51.4605,593.515,30.8,857.9676,264.4526,0.0744,4.6433,30.6768,189.7995,220.7957,1518.609,21.7842,190.0441,1271.3814,0,40,63,504,413,26,83,1.3333333333333333,84,,,0.07936507936507936,5.0,0.1111111111111111,7.0,0.0077,7.892,5.8373,,,,,0.015873015873015872,1.0
0.0,0,64,512,4,1.8125,0,0.8594,4279.4121,4658.495,4036.4103,31818,1,4537.4143,0.3906,-0.0052,0.0972,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1165,-0.0,0.0,1.0,0.0,0.0168,0.5156,0.3906,14.3004,51.4662,590.7932,31.1,857.9676,267.1744,0.0921,4.759,31.7989,206.607,238.7776,1695.7901,25.1666,206.8861,1427.0803,0,41,60,480,437,15,42,0.5833333333333334,35,0.016666666666666666,1.0,0.13333333333333333,8.0,,,,,,,,,,0.016666666666666666,1.0
0.0,0,64,512,3,1.7656,0,0.9219,4644.3555,4575.2611,4689.7476,31835,1,4068.353,0.3965,0.0012,0.1321,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1297,0.0,0.0,1.0,0.0,0.0199,0.5469,0.3965,14.7131,51.9086,588.8904,31.4,857.9676,269.0772,0.0651,5.5301,32.9529,196.4083,229.7064,1185.9686,24.4624,196.688,926.2659,0,42,63,504,458,16,43,0.6031746031746031,38,0.015873015873015872,1.0,0.06349206349206349,4.0,0.047619047619047616,3.0,0.0087,8.1946,,,,,,,
0.0,0,64,512,3,1.7656,0,0.9062,4732.2559,4411.7404,5004.1733,31630,1,4031.9761,0.459,0.0033,0.0733,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1225,-0.0015,0.0,1.0,0.0,0.0144,0.5312,0.459,14.5299,51.6583,587.3705,31.5,857.9676,270.5971,0.067,4.679,36.5302,193.1197,229.9798,1288.4443,25.7912,193.3823,1027.9897,0,43,64,512,463,16,41,0.546875,35,0.015625,1.0,0.078125,5.0,0.125,8.0,,,,,,,,,
0.0,0,64,512,4,1.7344,0,0.9062,3914.7676,3964.692,3850.0673,31821,1,3815.7786,0.5645,0.0015,0.0715,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1238,-0.0,0.0,1.0,0.0,0.0195,0.6406,0.5645,14.7441,51.9109,587.1451,31.6,857.9676,270.8224,0.0883,4.6642,27.8516,169.9297,198.1197,1113.2438,22.3695,170.1792,888.0849,0,44,58,464,399,17,57,0.8620689655172413,50,0.06896551724137931,4.0,0.06896551724137931,4.0,0.15517241379310345,9.0,0.0093,8.4633,,,,,,,
0.0,0,64,512,4,2.1094,0,0.875,4301.2285,3804.0427,4719.723,31776,1,4255.9316,0.457,-0.0,0.0722,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1162,0.0,0.0,1.0,0.0,0.0154,0.5625,0.457,14.9178,52.0336,584.7567,31.8,857.9676,273.2109,0.0679,4.6617,30.6844,188.2174,219.2604,1357.3257,22.0089,188.5077,1111.3908,0,45,62,496,447,13,47,0.7419354838709677,46,0.016129032258064516,1.0,,,0.016129032258064516,1.0,,,6.2322,,,,,0.016129032258064516,1.0
0.0,0,64,512,4,1.8281,0,0.875,4070.9902,4041.1,4099.5115,31688,1,3373.0068,0.4883,0.0004,0.1013,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1194,0.0,0.0,1.0,0.0,0.0536,0.5625,0.4883,15.1863,52.3452,585.3444,31.8,857.9676,272.6232,0.0926,4.6418,28.428,166.7965,195.5772,1268.2115,23.6294,167.0562,1044.3556,0,46,62,496,436,18,52,0.7903225806451613,49,,,0.04838709677419355,3.0,0.12903225806451613,8.0,0.0087,8.1314,,,,,,,
0.0,0,64,512,4,2.3438,0,0.9531,4738.4648,5245.1542,4334.8912,31750,1,4459.8261,0.4434,0.002,0.1073,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1235,0.0,0.0,1.0,0.0,0.0205,0.5781,0.4434,14.8623,51.9712,585.1224,31.8,857.9676,272.8452,0.0679,4.772,36.545,205.0078,241.8901,1544.9845,25.2698,205.2769,1273.0488,0,47,62,496,436,22,60,0.8709677419354839,54,0.04838709677419355,3.0,0.04838709677419355,3.0,,,,,,,,,,,
0.0,0,64,512,4,1.8438,0,0.8906,4116.1836,3927.0762,4262.1038,31786,1,3948.7686,0.4355,0.0076,0.1357,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1231,-0.0,0.0,1.0,0.0,0.021,0.5938,0.4355,14.7819,51.9097,583.8033,32.0,857.9676,274.1643,0.0638,4.5769,29.1074,177.2445,206.6741,1623.8625,23.6393,177.5024,1388.9681,0,48,62,496,434,21,62,0.9354838709677419,58,0.03225806451612903,2.0,0.03225806451612903,2.0,,,0.0097,8.1153,,,,,,,
0.0,0,64,512,3,1.6719,0,0.9219,4220.3594,3816.7342,4529.3414,31767,1,4322.0974,0.4336,-0.011,0.06,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1171,0.0,0.0,1.0,0.0,0.0148,0.5156,0.4336,14.782,51.9094,582.043,32.2,857.9676,275.9246,0.0953,4.8001,29.5038,190.42,220.266,1295.397,22.6579,190.6665,1047.6658,0,49,63,504,443,18,61,0.9365079365079365,59,0.015873015873015872,1.0,0.015873015873015872,1.0,,,,,,,,,,,
0.0,0,64,512,3,1.7656,0,0.9219,4165.8223,3780.6132,4438.0367,31807,1,3811.0311,0.4141,-0.0123,0.079,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1203,-0.0,0.0,1.0,0.0,0.015,0.5,0.4141,14.7839,51.9753,581.3082,32.2,857.9676,276.6594,0.0972,4.6738,27.3101,174.4772,202.1804,1512.647,23.5038,174.7725,1282.2827,0,50,62,496,438,18,50,0.7096774193548387,44,0.03225806451612903,2.0,0.06451612903225806,4.0,0.12903225806451613,8.0,0.0088,8.4124,6.613,,,,,,
0.0,0,64,512,3,1.5312,0,0.8125,3720.3535,3495.7536,3877.7973,20957,1,3256.5953,0.4121,0.0004,0.0987,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1222,-0.0023,0.0,1.0,0.0,0.0173,0.5312,0.4121,14.6185,51.8736,580.6026,32.3,857.9676,277.365,0.0439,3.2715,24.9104,154.876,180.0568,1530.0051,23.5918,155.1023,1323.0806,0,51,63,504,402,26,100,1.492063492063492,94,0.031746031746031744,2.0,0.06349206349206349,4.0,0.031746031746031744,2.0,,,,,,,,,
0.0,0,64,512,5,1.7188,0,0.9531,3783.1348,4544.0099,3287.3387,31784,1,3783.8372,0.3945,-0.0001,0.1475,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1173,-0.0014,0.0,1.0,0.0,0.0226,0.5312,0.3945,15.0491,52.4155,580.1515,32.4,857.9676,277.8161,0.0633,4.6164,25.5189,170.3928,196.2659,1451.3636,23.7931,170.6833,1226.6852,0,52,64,512,458,17,54,0.78125,50,,,0.0625,4.0,,,0.0092,7.8929,,,,,,,
0.0,0,64,512,3,1.6719,0,0.8438,4142.5859,4016.5782,4230.9169,31731,1,4001.5179,0.4121,0.0013,0.0487,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1236,0.0,0.0,1.0,0.0,0.0124,0.4844,0.4121,15.0288,52.348,578.971,32.5,857.9676,278.9966,0.0891,4.6754,31.7101,181.196,213.3246,1666.3496,25.0736,181.5249,1423.2691,0,53,60,480,406,19,70,1.0333333333333334,62,0.06666666666666667,4.0,0.08333333333333333,5.0,0.06666666666666667,4.0,,,,,,,,,
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 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_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 timing/save_hf_model batch_errors/avg_DaytonaAuthenticationError batch_errors/total_DaytonaAuthenticationError batch_errors/avg_DaytonaNotFoundError batch_errors/total_DaytonaNotFoundError batch_errors/avg_AgentSetupTimeoutError batch_errors/total_AgentSetupTimeoutError
2 0.0 0 64 512 4 0.875 0 0.3438 4767.7715 4795.1262 4728.7488 25222 1 3182.1526 0.5879 0.0092 0.1088 -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 0.1199 -0.0056 0.0 1.0 0.0 0.013 0.625 0.5879 10.536 50.3104 626.3275 27.0 857.9676 231.6401 0.2023 3.92 34.2457 174.2058 208.9411 4078.6541 22.8866 174.4925 3842.9061 0 27 53 424 388 18 33 0.6226415094339622 33 0.03773584905660377 2.0 0.16981132075471697 9.0 0.05660377358490566 3.0
3 0.0 0 64 512 1 0.9219 0 0.9219 4983.4746 5436.399 4709.4483 31754 1 4133.7783 0.377 0.0227 0.1274 -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 0.1345 -0.0042 0.0 1.0 0.0 0.0185 0.5 0.377 13.5033 50.54 618.0227 28.0 857.9676 239.9449 0.0639 4.7884 32.7876 194.5012 227.5803 1263.0117 21.7204 194.7281 1008.9141 0 28 56 448 407 14 36 0.6964285714285714 39 0.03571428571428571 2.0 0.125 7.0 0.08928571428571429 5.0 12.171 20.1752
4 0.0 0 64 512 2 1.625 0 0.9375 4671.3027 5053.6712 4385.5051 31822 1 4728.8661 0.4277 0.0211 0.0979 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1248 0.0 0.0 1.0 0.0 0.0199 0.5469 0.4277 13.6422 50.7001 613.7819 28.5 857.9676 244.1857 0.0632 4.7469 34.1954 213.2039 247.7078 1068.7568 23.7909 213.4484 792.5078 0 29 60 480 418 17 56 0.8 48 0.03333333333333333 2.0 0.1 6.0 0.1 6.0
5 0.0 0 64 512 3 1.7969 0 0.8594 4280.7344 4076.9107 4439.2639 31798 1 3580.8473 0.4375 0.0025 0.0887 -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 0.1155 -0.0042 0.0 1.0 0.0 0.0155 0.5156 0.4375 13.777 50.8871 612.502 28.6 857.9676 245.4656 0.0913 4.6547 28.7012 169.1447 198.1744 1539.4904 20.8891 169.3814 1315.7664 0 30 61 488 437 18 51 0.7704918032786885 47 0.08196721311475409 5.0 0.009 8.6111 6.395
6 0.0 0 64 512 4 2.1406 0 0.9375 5000.9766 5222.5862 4817.3571 31737 1 4371.6949 0.4531 0.016 0.088 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1205 0.0 0.0 1.0 0.0 0.0168 0.5312 0.4531 14.216 51.3028 608.8709 29.0 857.9676 249.0967 0.0647 4.7976 32.6722 201.0971 234.1363 1535.0765 21.6286 201.399 1274.5101 0 31 62 496 382 30 106 1.5806451612903225 98 0.04838709677419355 3.0 0.0967741935483871 6.0 0.0967741935483871 6.0 0.016129032258064516 1.0 0.016129032258064516 1.0
7 0.0 0 64 512 5 1.9688 0 0.9219 3795.5312 4476.6118 3456.9825 31804 1 4323.2735 0.332 0.0128 0.1017 -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 0.1108 -0.0064 0.0 1.0 0.0 0.0172 0.4844 0.332 14.2689 51.3345 607.3277 29.2 857.9676 250.6399 0.0644 4.6435 28.605 177.2897 206.2082 1701.0639 23.5775 177.5384 1466.6314 0 32 62 496 430 20 62 0.9354838709677419 58 0.08064516129032258 5.0 0.06451612903225806 4.0 0.0098 7.957
8 0.0 0 64 512 5 1.8281 0 0.9062 4426.4102 4337.7767 4486.0784 31776 1 4189.8754 0.4023 0.02 0.084 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1229 0.0 0.0 1.0 0.0 0.0162 0.4844 0.4023 14.2714 51.3339 605.3755 29.4 857.9676 252.5921 0.0989 4.7055 30.6605 192.3827 223.4015 1469.9716 21.125 192.6417 1220.734 0 33 62 496 445 19 46 0.6129032258064516 38 0.016129032258064516 1.0 0.11290322580645161 7.0 0.06451612903225806 4.0 0.016129032258064516 1.0
9 0.0 0 64 512 4 1.8594 0 0.8906 4549.4668 4319.729 4714.4463 31620 1 3895.5488 0.418 -0.0026 0.1007 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1269 -0.002 0.0 1.0 0.0 0.0154 0.4844 0.418 14.2645 51.3268 603.5889 29.6 857.9676 254.3787 0.0836 4.6898 28.9795 187.0802 216.4045 1363.6601 23.3237 187.3409 1119.2363 0 34 62 496 423 24 73 1.032258064516129 64 0.016129032258064516 1.0 0.12903225806451613 8.0 0.0095 8.3515
10 0.0 0 64 512 6 1.9219 0 0.9219 3946.0859 4376.362 3619.3127 31808 1 3948.408 0.4316 0.0053 0.1214 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1186 0.0 0.0 1.0 0.0 0.0191 0.5781 0.4316 14.2697 51.332 602.1526 29.8 857.9676 255.815 0.0941 4.6209 31.141 176.3125 207.7997 1421.4447 22.28 176.5642 1186.7383 0 35 64 512 454 20 49 0.75 48 0.015625 1.0 0.125 8.0 5.9666 0.015625 1.0
11 0.0 0 64 512 4 1.9844 0 0.8438 4738.3516 4627.5896 4816.6233 31838 1 4336.9944 0.4141 0.0016 0.1087 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1313 -0.002 0.0 1.0 0.0 0.0214 0.5469 0.4141 14.2961 51.3983 600.9323 30.0 857.9676 257.0353 0.077 4.82 30.3179 188.5618 219.2099 1686.9542 23.188 188.8147 1439.7332 0 36 62 496 429 23 66 0.9838709677419355 61 0.016129032258064516 1.0 0.06451612903225806 4.0 0.016129032258064516 1.0 0.0087 8.22
12 0.0 0 64 512 3 1.75 0 0.875 4288.6914 4517.4416 4100.6441 31765 1 3993.4464 0.4512 0.0038 0.1186 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1252 -0.0 0.0 1.0 0.0 0.0137 0.5469 0.4512 14.4357 51.5209 598.8259 30.2 857.9676 259.1417 0.0654 5.1265 29.5529 183.3451 213.2355 1634.9331 22.0702 183.617 1394.4971 0 37 63 504 462 16 41 0.49206349206349204 31 0.07936507936507936 5.0 0.07936507936507936 5.0 0.015873015873015872 1.0
13 0.0 0 64 512 3 1.7812 0 0.8906 4378.4395 4279.6997 4521.5885 31750 1 3800.9451 0.5918 0.0122 0.1617 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1219 0.0 0.0 1.0 0.0 0.0233 0.7344 0.5918 14.3297 51.4598 597.5809 30.3 857.9676 260.3867 0.0842 4.6513 29.0723 176.8748 206.3067 1204.9325 22.4098 177.1498 971.5582 0 38 62 496 441 16 55 0.8709677419354839 54 0.03225806451612903 2.0 0.016129032258064516 1.0 0.008 7.9801
14 0.0 0 64 512 3 1.7188 0 0.9062 4493.166 4310.5861 4659.3955 31795 1 4271.0567 0.4766 0.0119 0.069 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1184 0.0 0.0 1.0 0.0 0.0179 0.5469 0.4766 14.348 51.4611 594.5972 30.7 857.9676 263.3704 0.066 4.684 33.4072 192.1783 225.9165 1350.158 22.8675 192.4429 1096.6861 0 39 62 496 412 24 83 1.2419354838709677 77 0.0967741935483871 6.0 0.016129032258064516 1.0
15 0.0 0 64 512 4 1.8438 0 0.8594 4353.3359 4784.3178 4043.8389 31733 1 4145.6711 0.418 -0.0101 0.1282 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1206 -0.0 0.0 1.0 0.0 0.0197 0.5625 0.418 14.3591 51.4605 593.515 30.8 857.9676 264.4526 0.0744 4.6433 30.6768 189.7995 220.7957 1518.609 21.7842 190.0441 1271.3814 0 40 63 504 413 26 83 1.3333333333333333 84 0.07936507936507936 5.0 0.1111111111111111 7.0 0.0077 7.892 5.8373 0.015873015873015872 1.0
16 0.0 0 64 512 4 1.8125 0 0.8594 4279.4121 4658.495 4036.4103 31818 1 4537.4143 0.3906 -0.0052 0.0972 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1165 -0.0 0.0 1.0 0.0 0.0168 0.5156 0.3906 14.3004 51.4662 590.7932 31.1 857.9676 267.1744 0.0921 4.759 31.7989 206.607 238.7776 1695.7901 25.1666 206.8861 1427.0803 0 41 60 480 437 15 42 0.5833333333333334 35 0.016666666666666666 1.0 0.13333333333333333 8.0 0.016666666666666666 1.0
17 0.0 0 64 512 3 1.7656 0 0.9219 4644.3555 4575.2611 4689.7476 31835 1 4068.353 0.3965 0.0012 0.1321 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1297 0.0 0.0 1.0 0.0 0.0199 0.5469 0.3965 14.7131 51.9086 588.8904 31.4 857.9676 269.0772 0.0651 5.5301 32.9529 196.4083 229.7064 1185.9686 24.4624 196.688 926.2659 0 42 63 504 458 16 43 0.6031746031746031 38 0.015873015873015872 1.0 0.06349206349206349 4.0 0.047619047619047616 3.0 0.0087 8.1946
18 0.0 0 64 512 3 1.7656 0 0.9062 4732.2559 4411.7404 5004.1733 31630 1 4031.9761 0.459 0.0033 0.0733 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1225 -0.0015 0.0 1.0 0.0 0.0144 0.5312 0.459 14.5299 51.6583 587.3705 31.5 857.9676 270.5971 0.067 4.679 36.5302 193.1197 229.9798 1288.4443 25.7912 193.3823 1027.9897 0 43 64 512 463 16 41 0.546875 35 0.015625 1.0 0.078125 5.0 0.125 8.0
19 0.0 0 64 512 4 1.7344 0 0.9062 3914.7676 3964.692 3850.0673 31821 1 3815.7786 0.5645 0.0015 0.0715 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1238 -0.0 0.0 1.0 0.0 0.0195 0.6406 0.5645 14.7441 51.9109 587.1451 31.6 857.9676 270.8224 0.0883 4.6642 27.8516 169.9297 198.1197 1113.2438 22.3695 170.1792 888.0849 0 44 58 464 399 17 57 0.8620689655172413 50 0.06896551724137931 4.0 0.06896551724137931 4.0 0.15517241379310345 9.0 0.0093 8.4633
20 0.0 0 64 512 4 2.1094 0 0.875 4301.2285 3804.0427 4719.723 31776 1 4255.9316 0.457 -0.0 0.0722 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1162 0.0 0.0 1.0 0.0 0.0154 0.5625 0.457 14.9178 52.0336 584.7567 31.8 857.9676 273.2109 0.0679 4.6617 30.6844 188.2174 219.2604 1357.3257 22.0089 188.5077 1111.3908 0 45 62 496 447 13 47 0.7419354838709677 46 0.016129032258064516 1.0 0.016129032258064516 1.0 6.2322 0.016129032258064516 1.0
21 0.0 0 64 512 4 1.8281 0 0.875 4070.9902 4041.1 4099.5115 31688 1 3373.0068 0.4883 0.0004 0.1013 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1194 0.0 0.0 1.0 0.0 0.0536 0.5625 0.4883 15.1863 52.3452 585.3444 31.8 857.9676 272.6232 0.0926 4.6418 28.428 166.7965 195.5772 1268.2115 23.6294 167.0562 1044.3556 0 46 62 496 436 18 52 0.7903225806451613 49 0.04838709677419355 3.0 0.12903225806451613 8.0 0.0087 8.1314
22 0.0 0 64 512 4 2.3438 0 0.9531 4738.4648 5245.1542 4334.8912 31750 1 4459.8261 0.4434 0.002 0.1073 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1235 0.0 0.0 1.0 0.0 0.0205 0.5781 0.4434 14.8623 51.9712 585.1224 31.8 857.9676 272.8452 0.0679 4.772 36.545 205.0078 241.8901 1544.9845 25.2698 205.2769 1273.0488 0 47 62 496 436 22 60 0.8709677419354839 54 0.04838709677419355 3.0 0.04838709677419355 3.0
23 0.0 0 64 512 4 1.8438 0 0.8906 4116.1836 3927.0762 4262.1038 31786 1 3948.7686 0.4355 0.0076 0.1357 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1231 -0.0 0.0 1.0 0.0 0.021 0.5938 0.4355 14.7819 51.9097 583.8033 32.0 857.9676 274.1643 0.0638 4.5769 29.1074 177.2445 206.6741 1623.8625 23.6393 177.5024 1388.9681 0 48 62 496 434 21 62 0.9354838709677419 58 0.03225806451612903 2.0 0.03225806451612903 2.0 0.0097 8.1153
24 0.0 0 64 512 3 1.6719 0 0.9219 4220.3594 3816.7342 4529.3414 31767 1 4322.0974 0.4336 -0.011 0.06 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1171 0.0 0.0 1.0 0.0 0.0148 0.5156 0.4336 14.782 51.9094 582.043 32.2 857.9676 275.9246 0.0953 4.8001 29.5038 190.42 220.266 1295.397 22.6579 190.6665 1047.6658 0 49 63 504 443 18 61 0.9365079365079365 59 0.015873015873015872 1.0 0.015873015873015872 1.0
25 0.0 0 64 512 3 1.7656 0 0.9219 4165.8223 3780.6132 4438.0367 31807 1 3811.0311 0.4141 -0.0123 0.079 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1203 -0.0 0.0 1.0 0.0 0.015 0.5 0.4141 14.7839 51.9753 581.3082 32.2 857.9676 276.6594 0.0972 4.6738 27.3101 174.4772 202.1804 1512.647 23.5038 174.7725 1282.2827 0 50 62 496 438 18 50 0.7096774193548387 44 0.03225806451612903 2.0 0.06451612903225806 4.0 0.12903225806451613 8.0 0.0088 8.4124 6.613
26 0.0 0 64 512 3 1.5312 0 0.8125 3720.3535 3495.7536 3877.7973 20957 1 3256.5953 0.4121 0.0004 0.0987 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1222 -0.0023 0.0 1.0 0.0 0.0173 0.5312 0.4121 14.6185 51.8736 580.6026 32.3 857.9676 277.365 0.0439 3.2715 24.9104 154.876 180.0568 1530.0051 23.5918 155.1023 1323.0806 0 51 63 504 402 26 100 1.492063492063492 94 0.031746031746031744 2.0 0.06349206349206349 4.0 0.031746031746031744 2.0
27 0.0 0 64 512 5 1.7188 0 0.9531 3783.1348 4544.0099 3287.3387 31784 1 3783.8372 0.3945 -0.0001 0.1475 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1173 -0.0014 0.0 1.0 0.0 0.0226 0.5312 0.3945 15.0491 52.4155 580.1515 32.4 857.9676 277.8161 0.0633 4.6164 25.5189 170.3928 196.2659 1451.3636 23.7931 170.6833 1226.6852 0 52 64 512 458 17 54 0.78125 50 0.0625 4.0 0.0092 7.8929
28 0.0 0 64 512 3 1.6719 0 0.8438 4142.5859 4016.5782 4230.9169 31731 1 4001.5179 0.4121 0.0013 0.0487 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1236 0.0 0.0 1.0 0.0 0.0124 0.4844 0.4121 15.0288 52.348 578.971 32.5 857.9676 278.9966 0.0891 4.6754 31.7101 181.196 213.3246 1666.3496 25.0736 181.5249 1423.2691 0 53 60 480 406 19 70 1.0333333333333334 62 0.06666666666666667 4.0 0.08333333333333333 5.0 0.06666666666666667 4.0