ppo-Huggy / run_logs /timers.json
CSLM's picture
Huggy training
fabd37c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3999977111816406,
"min": 1.3999977111816406,
"max": 1.42556893825531,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70018.0859375,
"min": 67992.9375,
"max": 79625.5390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.62724014336918,
"min": 78.76874003189792,
"max": 419.675,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49454.0,
"min": 48891.0,
"max": 50361.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999924.0,
"min": 49287.0,
"max": 1999924.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999924.0,
"min": 49287.0,
"max": 1999924.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.462941884994507,
"min": -0.014782018028199673,
"max": 2.5032002925872803,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1374.321533203125,
"min": -1.744278073310852,
"max": 1513.771240234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.876616789235009,
"min": 1.9353583124229463,
"max": 4.074012624293509,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2163.152168393135,
"min": 228.37228086590767,
"max": 2385.926415979862,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.876616789235009,
"min": 1.9353583124229463,
"max": 4.074012624293509,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2163.152168393135,
"min": 228.37228086590767,
"max": 2385.926415979862,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018327037885157754,
"min": 0.014221402998373378,
"max": 0.021555027601304268,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05498111365547326,
"min": 0.028442805996746756,
"max": 0.05579494662032024,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05353124286565516,
"min": 0.023019380991657575,
"max": 0.06069511268287897,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16059372859696547,
"min": 0.04603876198331515,
"max": 0.17890398216744263,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5164988278666653e-06,
"min": 3.5164988278666653e-06,
"max": 0.00029524897658367495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0549496483599995e-05,
"min": 1.0549496483599995e-05,
"max": 0.0008437477687507498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117213333333332,
"min": 0.10117213333333332,
"max": 0.19841632500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30351639999999996,
"min": 0.20747084999999998,
"max": 0.58124925,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.848945333333329e-05,
"min": 6.848945333333329e-05,
"max": 0.004920974617499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020546835999999985,
"min": 0.00020546835999999985,
"max": 0.014064337575000002,
"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": "1729232316",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729234840"
},
"total": 2524.6010089700003,
"count": 1,
"self": 0.7348731840002074,
"children": {
"run_training.setup": {
"total": 0.055570317000047,
"count": 1,
"self": 0.055570317000047
},
"TrainerController.start_learning": {
"total": 2523.810565469,
"count": 1,
"self": 4.53890336798986,
"children": {
"TrainerController._reset_env": {
"total": 4.778660068999898,
"count": 1,
"self": 4.778660068999898
},
"TrainerController.advance": {
"total": 2514.3114703060096,
"count": 232874,
"self": 4.8336463208834175,
"children": {
"env_step": {
"total": 1991.3814368980893,
"count": 232874,
"self": 1569.9219266449625,
"children": {
"SubprocessEnvManager._take_step": {
"total": 418.5541919120377,
"count": 232874,
"self": 16.135903128081736,
"children": {
"TorchPolicy.evaluate": {
"total": 402.418288783956,
"count": 223005,
"self": 402.418288783956
}
}
},
"workers": {
"total": 2.905318341089128,
"count": 232874,
"self": 0.0,
"children": {
"worker_root": {
"total": 2516.437699806994,
"count": 232874,
"is_parallel": true,
"self": 1246.8526817649572,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000784655000074963,
"count": 1,
"is_parallel": true,
"self": 0.00021779900009732955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005668559999776335,
"count": 2,
"is_parallel": true,
"self": 0.0005668559999776335
}
}
},
"UnityEnvironment.step": {
"total": 0.03329062000000249,
"count": 1,
"is_parallel": true,
"self": 0.00036688599993794924,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017900500006362563,
"count": 1,
"is_parallel": true,
"self": 0.00017900500006362563
},
"communicator.exchange": {
"total": 0.03200824800001101,
"count": 1,
"is_parallel": true,
"self": 0.03200824800001101
},
"steps_from_proto": {
"total": 0.000736480999989908,
"count": 1,
"is_parallel": true,
"self": 0.00018689000000904343,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005495909999808646,
"count": 2,
"is_parallel": true,
"self": 0.0005495909999808646
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1269.5850180420366,
"count": 232873,
"is_parallel": true,
"self": 38.47964747532865,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.47900635299789,
"count": 232873,
"is_parallel": true,
"self": 84.47900635299789
},
"communicator.exchange": {
"total": 1055.67404022693,
"count": 232873,
"is_parallel": true,
"self": 1055.67404022693
},
"steps_from_proto": {
"total": 90.95232398678013,
"count": 232873,
"is_parallel": true,
"self": 34.28338944863992,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.668934538140206,
"count": 465746,
"is_parallel": true,
"self": 56.668934538140206
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.0963870870368,
"count": 232874,
"self": 6.7438127971510085,
"children": {
"process_trajectory": {
"total": 167.7082072648867,
"count": 232874,
"self": 166.33480428188716,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3734029829995507,
"count": 10,
"self": 1.3734029829995507
}
}
},
"_update_policy": {
"total": 343.64436702499904,
"count": 97,
"self": 277.22796235500266,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.41640466999638,
"count": 2910,
"self": 66.41640466999638
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5740001799713355e-06,
"count": 1,
"self": 1.5740001799713355e-06
},
"TrainerController._save_models": {
"total": 0.1815301520000503,
"count": 1,
"self": 0.0027246480003668694,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17880550399968342,
"count": 1,
"self": 0.17880550399968342
}
}
}
}
}
}
}