hard007ik/shopmanager-grpo-smoke-l4-v2
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: hard007ik/shopmanager-grpo-smoke-l4-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-02 12:37:45 +08:00
commit b8ef3bde9b
19 changed files with 152349 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
metrics.csv Normal file
View File

@@ -0,0 +1,10 @@
step,loss,grad_norm,learning_rate,num_tokens,completions/mean_length,completions/min_length,completions/max_length,completions/clipped_ratio,completions/mean_terminated_length,completions/min_terminated_length,completions/max_terminated_length,rewards/reward_total/mean,rewards/reward_total/std,rewards/reward_market/mean,rewards/reward_market/std,rewards/reward_warehouse/mean,rewards/reward_warehouse/std,rewards/reward_showroom/mean,rewards/reward_showroom/std,reward,reward_std,frac_reward_zero_std,sampling/sampling_logp_difference/mean,sampling/sampling_logp_difference/max,sampling/importance_sampling_ratio/min,sampling/importance_sampling_ratio/mean,sampling/importance_sampling_ratio/max,entropy,clip_ratio/low_mean,clip_ratio/low_min,clip_ratio/high_mean,clip_ratio/high_max,clip_ratio/region_mean,step_time,epoch,train_runtime,train_samples_per_second,train_steps_per_second,total_flos,train_loss
1,-0.0,0.0,0.0,6155.0,18.5,13.0,24.0,0.0,18.5,13.0,24.0,0.8737499713897705,0.014071441255509853,0.6000000238418579,0.0,0.20000000298023224,0.0,0.07375000417232513,0.01407142635434866,0.8737499713897705,0.014071442186832428,0.0,4.520341396331787,27.174238204956055,4.035991810979052e-40,3.371377950408304e-34,6.742751768219281e-34,0.1811772882938385,0.0,0.0,0.0,0.0,0.0,4.618328085001849,0.0033333333333333335,,,,,
2,0.0,0.0,5.000000000000001e-07,13990.0,20.5,13.0,28.0,0.0,20.5,13.0,28.0,0.9020000100135803,0.04058792069554329,0.20000000298023224,0.0,0.6000000238418579,0.0,0.10199999809265137,0.04058793559670448,0.9020000100135803,0.04058792069554329,0.0,4.2938385009765625,26.646509170532227,2.0038568039844884e-43,9.08055335179305e-34,1.81611067035861e-33,0.11802829056978226,0.0,0.0,0.0,0.0,0.0,6.2618235270019795,0.006666666666666667,,,,,
3,0.0,0.0,1.0000000000000002e-06,27189.0,47.5,40.0,55.0,0.0,47.5,40.0,55.0,0.800000011920929,0.0,0.20000000298023224,0.0,0.6000000238418579,0.0,0.0,0.0,0.800000011920929,0.0,1.0,2.252011299133301,28.722728729248047,0.0,5.605193857299268e-45,1.2611686178923354e-44,0.12017613649368286,0.0,0.0,0.0,0.0,0.0,10.559301583001798,0.01,,,,,
4,0.0,0.0,1.5e-06,32537.0,16.0,16.0,16.0,0.0,16.0,16.0,16.0,0.8726999759674072,0.008343853987753391,0.20000000298023224,0.0,0.6000000238418579,0.0,0.07269999384880066,0.008343859575688839,0.8726999759674072,0.008343853987753391,0.0,6.424993515014648,30.274734497070312,1.401298464324817e-45,2.802596928649634e-45,2.802596928649634e-45,0.17401638627052307,0.0,0.0,0.0,0.0,0.0,1.9552808339976764,0.013333333333333334,,,,,
5,-0.0,0.0,2.0000000000000003e-06,41360.0,32.0,12.0,52.0,0.0,32.0,12.0,52.0,0.8379999995231628,0.05374009534716606,0.6000000238418579,0.0,0.20000000298023224,0.0,0.03799999877810478,0.053740113973617554,0.8379999995231628,0.05374009534716606,0.0,3.4955575466156006,31.43513298034668,0.0,2.3879863577791495e-32,4.775972715558299e-32,0.10594719648361206,0.0,0.0,0.0,0.0,0.0,8.467385248000937,0.016666666666666666,,,,,
6,0.0,0.0,2.5e-06,53669.0,47.0,34.0,60.0,0.0,47.0,34.0,60.0,0.800000011920929,0.0,0.20000000298023224,0.0,0.6000000238418579,0.0,0.0,0.0,0.800000011920929,0.0,1.0,2.4156625270843506,28.952373504638672,0.0,1.090479293292958e-33,2.180958586585916e-33,0.1315789371728897,0.0,0.0,0.0,0.0,0.0,8.83436526999867,0.02,,,,,
7,-0.0,0.0,3e-06,62446.0,26.0,13.0,39.0,0.0,26.0,13.0,39.0,0.8481500148773193,0.024678032845258713,0.20000000298023224,0.0,0.6000000238418579,0.0,0.04814999923110008,0.024678027257323265,0.8481500148773193,0.024678032845258713,0.0,3.9407880306243896,28.3719482421875,0.0,6.8739474988531065e-34,1.3747894997706213e-33,0.10619711875915527,0.0,0.0,0.0,0.0,0.0,8.326133659000334,0.023333333333333334,,,,,
8,0.0,0.0,3.5e-06,72064.0,29.5,19.0,40.0,0.0,29.5,19.0,40.0,0.8438500165939331,0.06201327219605446,0.20000000298023224,0.0,0.6000000238418579,0.0,0.04385000094771385,0.06201326474547386,0.8438500165939331,0.06201327219605446,0.0,3.4995782375335693,30.46342658996582,7.006492321624085e-45,8.407790785948902e-45,9.80908925027372e-45,0.11579056829214096,0.0,0.0,0.0,0.0,0.0,8.365506213998742,0.02666666666666667,,,,,
8,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.02666666666666667,91.2182,0.175,0.088,0.0,-7.903189287664419e-34
1 step loss grad_norm learning_rate num_tokens completions/mean_length completions/min_length completions/max_length completions/clipped_ratio completions/mean_terminated_length completions/min_terminated_length completions/max_terminated_length rewards/reward_total/mean rewards/reward_total/std rewards/reward_market/mean rewards/reward_market/std rewards/reward_warehouse/mean rewards/reward_warehouse/std rewards/reward_showroom/mean rewards/reward_showroom/std reward reward_std frac_reward_zero_std sampling/sampling_logp_difference/mean sampling/sampling_logp_difference/max sampling/importance_sampling_ratio/min sampling/importance_sampling_ratio/mean sampling/importance_sampling_ratio/max entropy clip_ratio/low_mean clip_ratio/low_min clip_ratio/high_mean clip_ratio/high_max clip_ratio/region_mean step_time epoch train_runtime train_samples_per_second train_steps_per_second total_flos train_loss
2 1 -0.0 0.0 0.0 6155.0 18.5 13.0 24.0 0.0 18.5 13.0 24.0 0.8737499713897705 0.014071441255509853 0.6000000238418579 0.0 0.20000000298023224 0.0 0.07375000417232513 0.01407142635434866 0.8737499713897705 0.014071442186832428 0.0 4.520341396331787 27.174238204956055 4.035991810979052e-40 3.371377950408304e-34 6.742751768219281e-34 0.1811772882938385 0.0 0.0 0.0 0.0 0.0 4.618328085001849 0.0033333333333333335
3 2 0.0 0.0 5.000000000000001e-07 13990.0 20.5 13.0 28.0 0.0 20.5 13.0 28.0 0.9020000100135803 0.04058792069554329 0.20000000298023224 0.0 0.6000000238418579 0.0 0.10199999809265137 0.04058793559670448 0.9020000100135803 0.04058792069554329 0.0 4.2938385009765625 26.646509170532227 2.0038568039844884e-43 9.08055335179305e-34 1.81611067035861e-33 0.11802829056978226 0.0 0.0 0.0 0.0 0.0 6.2618235270019795 0.006666666666666667
4 3 0.0 0.0 1.0000000000000002e-06 27189.0 47.5 40.0 55.0 0.0 47.5 40.0 55.0 0.800000011920929 0.0 0.20000000298023224 0.0 0.6000000238418579 0.0 0.0 0.0 0.800000011920929 0.0 1.0 2.252011299133301 28.722728729248047 0.0 5.605193857299268e-45 1.2611686178923354e-44 0.12017613649368286 0.0 0.0 0.0 0.0 0.0 10.559301583001798 0.01
5 4 0.0 0.0 1.5e-06 32537.0 16.0 16.0 16.0 0.0 16.0 16.0 16.0 0.8726999759674072 0.008343853987753391 0.20000000298023224 0.0 0.6000000238418579 0.0 0.07269999384880066 0.008343859575688839 0.8726999759674072 0.008343853987753391 0.0 6.424993515014648 30.274734497070312 1.401298464324817e-45 2.802596928649634e-45 2.802596928649634e-45 0.17401638627052307 0.0 0.0 0.0 0.0 0.0 1.9552808339976764 0.013333333333333334
6 5 -0.0 0.0 2.0000000000000003e-06 41360.0 32.0 12.0 52.0 0.0 32.0 12.0 52.0 0.8379999995231628 0.05374009534716606 0.6000000238418579 0.0 0.20000000298023224 0.0 0.03799999877810478 0.053740113973617554 0.8379999995231628 0.05374009534716606 0.0 3.4955575466156006 31.43513298034668 0.0 2.3879863577791495e-32 4.775972715558299e-32 0.10594719648361206 0.0 0.0 0.0 0.0 0.0 8.467385248000937 0.016666666666666666
7 6 0.0 0.0 2.5e-06 53669.0 47.0 34.0 60.0 0.0 47.0 34.0 60.0 0.800000011920929 0.0 0.20000000298023224 0.0 0.6000000238418579 0.0 0.0 0.0 0.800000011920929 0.0 1.0 2.4156625270843506 28.952373504638672 0.0 1.090479293292958e-33 2.180958586585916e-33 0.1315789371728897 0.0 0.0 0.0 0.0 0.0 8.83436526999867 0.02
8 7 -0.0 0.0 3e-06 62446.0 26.0 13.0 39.0 0.0 26.0 13.0 39.0 0.8481500148773193 0.024678032845258713 0.20000000298023224 0.0 0.6000000238418579 0.0 0.04814999923110008 0.024678027257323265 0.8481500148773193 0.024678032845258713 0.0 3.9407880306243896 28.3719482421875 0.0 6.8739474988531065e-34 1.3747894997706213e-33 0.10619711875915527 0.0 0.0 0.0 0.0 0.0 8.326133659000334 0.023333333333333334
9 8 0.0 0.0 3.5e-06 72064.0 29.5 19.0 40.0 0.0 29.5 19.0 40.0 0.8438500165939331 0.06201327219605446 0.20000000298023224 0.0 0.6000000238418579 0.0 0.04385000094771385 0.06201326474547386 0.8438500165939331 0.06201327219605446 0.0 3.4995782375335693 30.46342658996582 7.006492321624085e-45 8.407790785948902e-45 9.80908925027372e-45 0.11579056829214096 0.0 0.0 0.0 0.0 0.0 8.365506213998742 0.02666666666666667
10 8 0.02666666666666667 91.2182 0.175 0.088 0.0 -7.903189287664419e-34