ppo-Worm / run_logs /timers.json
saikiranp's picture
First training of Worm
c5c70f7
{
"name": "root",
"gauges": {
"Worm.Policy.Entropy.mean": {
"value": 1.2473835945129395,
"min": 1.2473835945129395,
"max": 1.3855050802230835,
"count": 67
},
"Worm.Policy.Entropy.sum": {
"value": 37421.5078125,
"min": 13855.05078125,
"max": 41526.13671875,
"count": 67
},
"Worm.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 67
},
"Worm.Environment.EpisodeLength.sum": {
"value": 29970.0,
"min": 9990.0,
"max": 29970.0,
"count": 67
},
"Worm.Step.mean": {
"value": 2999000.0,
"min": 1019000.0,
"max": 2999000.0,
"count": 67
},
"Worm.Step.sum": {
"value": 2999000.0,
"min": 1019000.0,
"max": 2999000.0,
"count": 67
},
"Worm.Policy.ExtrinsicValueEstimate.mean": {
"value": 88.42459106445312,
"min": 7.076003074645996,
"max": 88.42459106445312,
"count": 67
},
"Worm.Policy.ExtrinsicValueEstimate.sum": {
"value": 2652.73779296875,
"min": 63.68402862548828,
"max": 2652.73779296875,
"count": 67
},
"Worm.Environment.CumulativeReward.mean": {
"value": 485.6922536214193,
"min": 65.49288283454047,
"max": 485.6922536214193,
"count": 67
},
"Worm.Environment.CumulativeReward.sum": {
"value": 14570.767608642578,
"min": 589.4359455108643,
"max": 14570.767608642578,
"count": 67
},
"Worm.Policy.ExtrinsicReward.mean": {
"value": 485.6922536214193,
"min": 65.49288283454047,
"max": 485.6922536214193,
"count": 67
},
"Worm.Policy.ExtrinsicReward.sum": {
"value": 14570.767608642578,
"min": 589.4359455108643,
"max": 14570.767608642578,
"count": 67
},
"Worm.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 67
},
"Worm.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 67
},
"Worm.Losses.PolicyLoss.mean": {
"value": 0.01923009639479763,
"min": 0.012588625807655348,
"max": 0.022810967846973135,
"count": 66
},
"Worm.Losses.PolicyLoss.sum": {
"value": 0.01923009639479763,
"min": 0.012588625807655348,
"max": 0.022810967846973135,
"count": 66
},
"Worm.Losses.ValueLoss.mean": {
"value": 8.96524442945208,
"min": 0.7316992041610536,
"max": 8.96524442945208,
"count": 66
},
"Worm.Losses.ValueLoss.sum": {
"value": 8.96524442945208,
"min": 0.7316992041610536,
"max": 8.96524442945208,
"count": 66
},
"Worm.Policy.LearningRate.mean": {
"value": 1.0000996666666565e-06,
"min": 1.0000996666666565e-06,
"max": 0.0001960000346666667,
"count": 66
},
"Worm.Policy.LearningRate.sum": {
"value": 1.0000996666666565e-06,
"min": 1.0000996666666565e-06,
"max": 0.0001960000346666667,
"count": 66
},
"Worm.Policy.Epsilon.mean": {
"value": 0.10033333333333334,
"min": 0.10033333333333334,
"max": 0.1653333333333333,
"count": 66
},
"Worm.Policy.Epsilon.sum": {
"value": 0.10033333333333334,
"min": 0.10033333333333334,
"max": 0.1653333333333333,
"count": 66
},
"Worm.Policy.Beta.mean": {
"value": 2.663333333333317e-05,
"min": 2.663333333333317e-05,
"max": 0.003270133333333334,
"count": 66
},
"Worm.Policy.Beta.sum": {
"value": 2.663333333333317e-05,
"min": 2.663333333333317e-05,
"max": 0.003270133333333334,
"count": 66
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1673596721",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./training-envs-executables/linux/Worm/Worm --run-id=Worm Training --no-graphics --resume",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673599255"
},
"total": 2533.895560222,
"count": 1,
"self": 0.3826803120000477,
"children": {
"run_training.setup": {
"total": 0.11366827200026819,
"count": 1,
"self": 0.11366827200026819
},
"TrainerController.start_learning": {
"total": 2533.3992116379995,
"count": 1,
"self": 3.6822132199090447,
"children": {
"TrainerController._reset_env": {
"total": 6.363252045000081,
"count": 1,
"self": 6.363252045000081
},
"TrainerController.advance": {
"total": 2523.2309502990906,
"count": 200000,
"self": 3.704318265191432,
"children": {
"env_step": {
"total": 2090.9527501580924,
"count": 200000,
"self": 1825.465447973144,
"children": {
"SubprocessEnvManager._take_step": {
"total": 262.99436340811735,
"count": 200000,
"self": 16.696327589024804,
"children": {
"TorchPolicy.evaluate": {
"total": 246.29803581909255,
"count": 200000,
"self": 61.51209154401113,
"children": {
"TorchPolicy.sample_actions": {
"total": 184.78594427508142,
"count": 200000,
"self": 184.78594427508142
}
}
}
}
},
"workers": {
"total": 2.4929387768311244,
"count": 200000,
"self": 0.0,
"children": {
"worker_root": {
"total": 2525.981292178923,
"count": 200000,
"is_parallel": true,
"self": 941.2388896158895,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009491400001024886,
"count": 1,
"is_parallel": true,
"self": 0.0003122079997410765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006369320003614121,
"count": 2,
"is_parallel": true,
"self": 0.0006369320003614121
}
}
},
"UnityEnvironment.step": {
"total": 0.032511349999822414,
"count": 1,
"is_parallel": true,
"self": 0.0002228489997833094,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004554140000436746,
"count": 1,
"is_parallel": true,
"self": 0.0004554140000436746
},
"communicator.exchange": {
"total": 0.03119927000034295,
"count": 1,
"is_parallel": true,
"self": 0.03119927000034295
},
"steps_from_proto": {
"total": 0.0006338169996524812,
"count": 1,
"is_parallel": true,
"self": 0.00027419100024417276,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003596259994083084,
"count": 2,
"is_parallel": true,
"self": 0.0003596259994083084
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1584.7424025630335,
"count": 199999,
"is_parallel": true,
"self": 33.701285600835945,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 67.27756689308626,
"count": 199999,
"is_parallel": true,
"self": 67.27756689308626
},
"communicator.exchange": {
"total": 1384.9838197258905,
"count": 199999,
"is_parallel": true,
"self": 1384.9838197258905
},
"steps_from_proto": {
"total": 98.77973034322076,
"count": 199999,
"is_parallel": true,
"self": 37.63187597298793,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.147854370232835,
"count": 399998,
"is_parallel": true,
"self": 61.147854370232835
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 428.5738818758068,
"count": 200000,
"self": 4.225397488769886,
"children": {
"process_trajectory": {
"total": 112.8562919180381,
"count": 200000,
"self": 112.34849405003797,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5077978680001252,
"count": 4,
"self": 0.5077978680001252
}
}
},
"_update_policy": {
"total": 311.49219246899884,
"count": 66,
"self": 262.42764281600284,
"children": {
"TorchPPOOptimizer.update": {
"total": 49.06454965299599,
"count": 2772,
"self": 49.06454965299599
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.129998943535611e-07,
"count": 1,
"self": 9.129998943535611e-07
},
"TrainerController._save_models": {
"total": 0.12279516099988541,
"count": 1,
"self": 0.0027404689999457332,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12005469199993968,
"count": 1,
"self": 0.12005469199993968
}
}
}
}
}
}
}