ppo-Huggy / run_logs /timers.json
GillesEverling's picture
Push Huggy to the Hub
93ad0df verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4022072553634644,
"min": 1.4022072553634644,
"max": 1.4261634349822998,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69836.9296875,
"min": 69134.546875,
"max": 76595.7421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.25318761384335,
"min": 78.25356576862124,
"max": 430.22222222222223,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49000.0,
"min": 48856.0,
"max": 50336.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999958.0,
"min": 49739.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999958.0,
"min": 49739.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.425412654876709,
"min": 0.01204171683639288,
"max": 2.493408441543579,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1331.551513671875,
"min": 1.3968391418457031,
"max": 1527.6243896484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6939150238297676,
"min": 1.9505444118945763,
"max": 4.058129034561219,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2027.9593480825424,
"min": 226.26315177977085,
"max": 2410.4650573134422,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6939150238297676,
"min": 1.9505444118945763,
"max": 4.058129034561219,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2027.9593480825424,
"min": 226.26315177977085,
"max": 2410.4650573134422,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01809984855612533,
"min": 0.013328933242398004,
"max": 0.019910352633774487,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05429954566837599,
"min": 0.028243457803910132,
"max": 0.05973105790132346,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05599840407570204,
"min": 0.02393402624875307,
"max": 0.059407338417238664,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16799521222710612,
"min": 0.04786805249750614,
"max": 0.178222015251716,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7006987664666656e-06,
"min": 3.7006987664666656e-06,
"max": 0.000295358926547025,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1102096299399996e-05,
"min": 1.1102096299399996e-05,
"max": 0.00084426286857905,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123353333333336,
"min": 0.10123353333333336,
"max": 0.198452975,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037006000000001,
"min": 0.20762175,
"max": 0.5814209500000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.15533133333333e-05,
"min": 7.15533133333333e-05,
"max": 0.0049228034525,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021465993999999992,
"min": 0.00021465993999999992,
"max": 0.014072905404999999,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1712636849",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/home/ml/miniforge3/envs/mlagents/bin/mlagents-learn results/ppo/Huggy.yaml --env=trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.0.0",
"mlagents_envs_version": "1.0.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.2+cu121",
"numpy_version": "1.21.2",
"end_time_seconds": "1712638367"
},
"total": 1518.4730888290069,
"count": 1,
"self": 0.16631875099847093,
"children": {
"run_training.setup": {
"total": 0.006443063000915572,
"count": 1,
"self": 0.006443063000915572
},
"TrainerController.start_learning": {
"total": 1518.3003270150075,
"count": 1,
"self": 3.9357719262188766,
"children": {
"TrainerController._reset_env": {
"total": 1.1701630129973637,
"count": 1,
"self": 1.1701630129973637
},
"TrainerController.advance": {
"total": 1513.1432395667798,
"count": 232840,
"self": 3.72213457088219,
"children": {
"env_step": {
"total": 1267.3294759379205,
"count": 232840,
"self": 1034.1169278264133,
"children": {
"SubprocessEnvManager._take_step": {
"total": 230.5955084934103,
"count": 232840,
"self": 15.000276385690086,
"children": {
"TorchPolicy.evaluate": {
"total": 215.59523210772022,
"count": 223008,
"self": 215.59523210772022
}
}
},
"workers": {
"total": 2.6170396180968964,
"count": 232840,
"self": 0.0,
"children": {
"worker_root": {
"total": 1513.2506227253616,
"count": 232840,
"is_parallel": true,
"self": 692.5803882344189,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0002703060017665848,
"count": 1,
"is_parallel": true,
"self": 7.375401037279516e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00019655199139378965,
"count": 2,
"is_parallel": true,
"self": 0.00019655199139378965
}
}
},
"UnityEnvironment.step": {
"total": 0.009142100010649301,
"count": 1,
"is_parallel": true,
"self": 7.645001460332423e-05,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.674499647691846e-05,
"count": 1,
"is_parallel": true,
"self": 7.674499647691846e-05
},
"communicator.exchange": {
"total": 0.008185753002180718,
"count": 1,
"is_parallel": true,
"self": 0.008185753002180718
},
"steps_from_proto": {
"total": 0.0008031519973883405,
"count": 1,
"is_parallel": true,
"self": 0.0006687369896098971,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0001344150077784434,
"count": 2,
"is_parallel": true,
"self": 0.0001344150077784434
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 820.6702344909427,
"count": 232839,
"is_parallel": true,
"self": 24.79280639157514,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 47.37283598830982,
"count": 232839,
"is_parallel": true,
"self": 47.37283598830982
},
"communicator.exchange": {
"total": 690.1029986612994,
"count": 232839,
"is_parallel": true,
"self": 690.1029986612994
},
"steps_from_proto": {
"total": 58.401593449758366,
"count": 232839,
"is_parallel": true,
"self": 20.29724729146983,
"children": {
"_process_rank_one_or_two_observation": {
"total": 38.104346158288536,
"count": 465678,
"is_parallel": true,
"self": 38.104346158288536
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 242.09162905797712,
"count": 232840,
"self": 5.203942200008896,
"children": {
"process_trajectory": {
"total": 106.41067790686793,
"count": 232840,
"self": 105.73657044184802,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6741074650199153,
"count": 10,
"self": 0.6741074650199153
}
}
},
"_update_policy": {
"total": 130.4770089511003,
"count": 97,
"self": 114.98695048346417,
"children": {
"TorchPPOOptimizer.update": {
"total": 15.490058467636118,
"count": 2910,
"self": 15.490058467636118
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2420059647411108e-06,
"count": 1,
"self": 1.2420059647411108e-06
},
"TrainerController._save_models": {
"total": 0.051151267005479895,
"count": 1,
"self": 0.0008100300037767738,
"children": {
"RLTrainer._checkpoint": {
"total": 0.05034123700170312,
"count": 1,
"self": 0.05034123700170312
}
}
}
}
}
}
}