ppo-Huggy / run_logs /timers.json
Vladislav-HuggingFace's picture
Huggy
85a5f19
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408516526222229,
"min": 1.408516526222229,
"max": 1.426863193511963,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72125.90625,
"min": 67924.984375,
"max": 75197.828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 69.56558533145275,
"min": 69.56558533145275,
"max": 428.5811965811966,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49322.0,
"min": 49158.0,
"max": 50144.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999926.0,
"min": 49512.0,
"max": 1999926.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999926.0,
"min": 49512.0,
"max": 1999926.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4461746215820312,
"min": 0.020248960703611374,
"max": 2.5333826541900635,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1731.8916015625,
"min": 2.348879337310791,
"max": 1731.8916015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7409985513336914,
"min": 1.7373264753099145,
"max": 3.9752586852351763,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2648.6269743442535,
"min": 201.5298711359501,
"max": 2648.6269743442535,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7409985513336914,
"min": 1.7373264753099145,
"max": 3.9752586852351763,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2648.6269743442535,
"min": 201.5298711359501,
"max": 2648.6269743442535,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01472512853344799,
"min": 0.014452693193258408,
"max": 0.018919367465787217,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04417538560034397,
"min": 0.028905386386516817,
"max": 0.05455885601477349,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0679780329681105,
"min": 0.023454637701312703,
"max": 0.06809518660108249,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.2039340989043315,
"min": 0.046909275402625406,
"max": 0.2039340989043315,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.86554871151666e-06,
"min": 3.86554871151666e-06,
"max": 0.000295356676547775,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.159664613454998e-05,
"min": 1.159664613454998e-05,
"max": 0.0008443017185661001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128848333333335,
"min": 0.10128848333333335,
"max": 0.198452225,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30386545000000004,
"min": 0.20770905000000003,
"max": 0.5814339000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.429531833333322e-05,
"min": 7.429531833333322e-05,
"max": 0.0049227660275,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022288595499999966,
"min": 0.00022288595499999966,
"max": 0.014073551610000002,
"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": "1688580031",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688582452"
},
"total": 2420.460022186,
"count": 1,
"self": 0.7949829330000284,
"children": {
"run_training.setup": {
"total": 0.042815832000002274,
"count": 1,
"self": 0.042815832000002274
},
"TrainerController.start_learning": {
"total": 2419.622223421,
"count": 1,
"self": 4.338602159955826,
"children": {
"TrainerController._reset_env": {
"total": 4.0717372299999965,
"count": 1,
"self": 4.0717372299999965
},
"TrainerController.advance": {
"total": 2411.025663201044,
"count": 232737,
"self": 4.584860719125572,
"children": {
"env_step": {
"total": 1873.310644911961,
"count": 232737,
"self": 1580.4812760368718,
"children": {
"SubprocessEnvManager._take_step": {
"total": 290.0228563261101,
"count": 232737,
"self": 16.95031230110743,
"children": {
"TorchPolicy.evaluate": {
"total": 273.0725440250027,
"count": 222948,
"self": 273.0725440250027
}
}
},
"workers": {
"total": 2.806512548978958,
"count": 232737,
"self": 0.0,
"children": {
"worker_root": {
"total": 2411.5324142728937,
"count": 232737,
"is_parallel": true,
"self": 1123.4014068299464,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009354550000182371,
"count": 1,
"is_parallel": true,
"self": 0.0002733549999902607,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006621000000279764,
"count": 2,
"is_parallel": true,
"self": 0.0006621000000279764
}
}
},
"UnityEnvironment.step": {
"total": 0.028298068999987436,
"count": 1,
"is_parallel": true,
"self": 0.0003538150000110818,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020763999998507643,
"count": 1,
"is_parallel": true,
"self": 0.00020763999998507643
},
"communicator.exchange": {
"total": 0.027035859999983813,
"count": 1,
"is_parallel": true,
"self": 0.027035859999983813
},
"steps_from_proto": {
"total": 0.0007007540000074641,
"count": 1,
"is_parallel": true,
"self": 0.00020271300002150383,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004980409999859603,
"count": 2,
"is_parallel": true,
"self": 0.0004980409999859603
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1288.1310074429473,
"count": 232736,
"is_parallel": true,
"self": 40.122615129135056,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.97536687990535,
"count": 232736,
"is_parallel": true,
"self": 77.97536687990535
},
"communicator.exchange": {
"total": 1073.6144192909737,
"count": 232736,
"is_parallel": true,
"self": 1073.6144192909737
},
"steps_from_proto": {
"total": 96.4186061429331,
"count": 232736,
"is_parallel": true,
"self": 34.288238234957504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.1303679079756,
"count": 465472,
"is_parallel": true,
"self": 62.1303679079756
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 533.1301575699574,
"count": 232737,
"self": 6.669432061994939,
"children": {
"process_trajectory": {
"total": 138.86686792296302,
"count": 232737,
"self": 137.42186459796199,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4450033250010392,
"count": 10,
"self": 1.4450033250010392
}
}
},
"_update_policy": {
"total": 387.5938575849995,
"count": 97,
"self": 326.74883164200725,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.845025942992265,
"count": 2910,
"self": 60.845025942992265
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2770001376338769e-06,
"count": 1,
"self": 1.2770001376338769e-06
},
"TrainerController._save_models": {
"total": 0.18621955299977344,
"count": 1,
"self": 0.007330454999646463,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17888909800012698,
"count": 1,
"self": 0.17888909800012698
}
}
}
}
}
}
}