ppo-Huggy / run_logs /timers.json
niftymark's picture
Huggy model commited
ae2f082
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3998477458953857,
"min": 1.3998477458953857,
"max": 1.4278501272201538,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71213.0546875,
"min": 68585.21875,
"max": 78004.890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 114.20091324200914,
"min": 109.46756152125279,
"max": 401.72,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50020.0,
"min": 48932.0,
"max": 50215.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999919.0,
"min": 49900.0,
"max": 1999919.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999919.0,
"min": 49900.0,
"max": 1999919.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2742435932159424,
"min": 0.1248428151011467,
"max": 2.2942047119140625,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 996.11865234375,
"min": 15.480508804321289,
"max": 1010.589111328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.484942441525525,
"min": 1.6626933584770849,
"max": 3.650224849046805,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1526.4047893881798,
"min": 206.17397645115852,
"max": 1548.890519976616,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.484942441525525,
"min": 1.6626933584770849,
"max": 3.650224849046805,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1526.4047893881798,
"min": 206.17397645115852,
"max": 1548.890519976616,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016873225931582664,
"min": 0.012569394512684086,
"max": 0.020723888622148932,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03374645186316533,
"min": 0.028959366005922978,
"max": 0.05714223333731449,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.046959296924372514,
"min": 0.02183272872741024,
"max": 0.0645944656804204,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09391859384874503,
"min": 0.04366545745482048,
"max": 0.19143519923090935,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6346737884749906e-06,
"min": 3.6346737884749906e-06,
"max": 0.00029525655158115,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 7.269347576949981e-06,
"min": 7.269347576949981e-06,
"max": 0.00084385666871445,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121152500000001,
"min": 0.10121152500000001,
"max": 0.19841885,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20242305000000002,
"min": 0.20242305000000002,
"max": 0.5812855500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.045509749999983e-05,
"min": 7.045509749999983e-05,
"max": 0.004921100614999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00014091019499999966,
"min": 0.00014091019499999966,
"max": 0.014066148944999999,
"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": "1686227396",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1686229724"
},
"total": 2327.829462888,
"count": 1,
"self": 0.44250296299969705,
"children": {
"run_training.setup": {
"total": 0.0419571160000487,
"count": 1,
"self": 0.0419571160000487
},
"TrainerController.start_learning": {
"total": 2327.345002809,
"count": 1,
"self": 4.282676437966529,
"children": {
"TrainerController._reset_env": {
"total": 4.323059628999999,
"count": 1,
"self": 4.323059628999999
},
"TrainerController.advance": {
"total": 2318.6184166590333,
"count": 230155,
"self": 4.2896200939953815,
"children": {
"env_step": {
"total": 1819.7626894800655,
"count": 230155,
"self": 1530.5253205769739,
"children": {
"SubprocessEnvManager._take_step": {
"total": 286.5436149320443,
"count": 230155,
"self": 16.911878301069123,
"children": {
"TorchPolicy.evaluate": {
"total": 269.6317366309752,
"count": 222986,
"self": 269.6317366309752
}
}
},
"workers": {
"total": 2.6937539710473857,
"count": 230155,
"self": 0.0,
"children": {
"worker_root": {
"total": 2320.084026384146,
"count": 230155,
"is_parallel": true,
"self": 1069.1865364071782,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009559270000636388,
"count": 1,
"is_parallel": true,
"self": 0.00026960700006384286,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000686319999999796,
"count": 2,
"is_parallel": true,
"self": 0.000686319999999796
}
}
},
"UnityEnvironment.step": {
"total": 0.051599507000105405,
"count": 1,
"is_parallel": true,
"self": 0.0003272060001791033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023995100002593972,
"count": 1,
"is_parallel": true,
"self": 0.00023995100002593972
},
"communicator.exchange": {
"total": 0.05031682199989973,
"count": 1,
"is_parallel": true,
"self": 0.05031682199989973
},
"steps_from_proto": {
"total": 0.0007155280000006314,
"count": 1,
"is_parallel": true,
"self": 0.0001860529998793936,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005294750001212378,
"count": 2,
"is_parallel": true,
"self": 0.0005294750001212378
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1250.8974899769678,
"count": 230154,
"is_parallel": true,
"self": 38.545851936974486,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.49083922198452,
"count": 230154,
"is_parallel": true,
"self": 77.49083922198452
},
"communicator.exchange": {
"total": 1041.8165832538984,
"count": 230154,
"is_parallel": true,
"self": 1041.8165832538984
},
"steps_from_proto": {
"total": 93.04421556411023,
"count": 230154,
"is_parallel": true,
"self": 33.2065626620672,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.83765290204303,
"count": 460308,
"is_parallel": true,
"self": 59.83765290204303
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 494.5661070849726,
"count": 230155,
"self": 6.488043036937256,
"children": {
"process_trajectory": {
"total": 121.38369173303306,
"count": 230155,
"self": 120.07783479203272,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3058569410003429,
"count": 10,
"self": 1.3058569410003429
}
}
},
"_update_policy": {
"total": 366.6943723150023,
"count": 96,
"self": 307.65136530799396,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.04300700700833,
"count": 2880,
"self": 59.04300700700833
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0160001693293452e-06,
"count": 1,
"self": 1.0160001693293452e-06
},
"TrainerController._save_models": {
"total": 0.12084906700010833,
"count": 1,
"self": 0.0019692160003614845,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11887985099974685,
"count": 1,
"self": 0.11887985099974685
}
}
}
}
}
}
}