ppo-Huggy / run_logs /timers.json
samuelabc's picture
Upload folder using huggingface_hub
de5a453
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4072827100753784,
"min": 1.4072827100753784,
"max": 1.4294835329055786,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71665.875,
"min": 68827.9921875,
"max": 76348.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.8256880733945,
"min": 76.64696734059098,
"max": 397.3095238095238,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49500.0,
"min": 48868.0,
"max": 50061.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999991.0,
"min": 49716.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999991.0,
"min": 49716.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.437350273132324,
"min": 0.12172623723745346,
"max": 2.4991397857666016,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1328.35595703125,
"min": 15.215779304504395,
"max": 1570.7802734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7052158993318542,
"min": 1.8753699214458466,
"max": 4.0405095714341455,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2019.3426651358604,
"min": 234.42124018073082,
"max": 2452.7952835559845,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7052158993318542,
"min": 1.8753699214458466,
"max": 4.0405095714341455,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2019.3426651358604,
"min": 234.42124018073082,
"max": 2452.7952835559845,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01784490371723627,
"min": 0.013844083091074329,
"max": 0.021561324177158288,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05353471115170881,
"min": 0.027688166182148657,
"max": 0.05685952332569286,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05641236243148645,
"min": 0.021790739676604668,
"max": 0.05858757284780343,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16923708729445935,
"min": 0.043581479353209336,
"max": 0.17213051033516724,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.085398638233337e-06,
"min": 4.085398638233337e-06,
"max": 0.00029536102654632493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.225619591470001e-05,
"min": 1.225619591470001e-05,
"max": 0.0008444007185330998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10136176666666667,
"min": 0.10136176666666667,
"max": 0.19845367499999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3040853,
"min": 0.2078658,
"max": 0.5814669000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.795215666666672e-05,
"min": 7.795215666666672e-05,
"max": 0.004922838382499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023385647000000016,
"min": 0.00023385647000000016,
"max": 0.014075198309999998,
"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": "1682575882",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1682578310"
},
"total": 2427.243592148,
"count": 1,
"self": 0.44190012199987905,
"children": {
"run_training.setup": {
"total": 0.1254425939999919,
"count": 1,
"self": 0.1254425939999919
},
"TrainerController.start_learning": {
"total": 2426.676249432,
"count": 1,
"self": 4.548230733023502,
"children": {
"TrainerController._reset_env": {
"total": 4.7998782939999955,
"count": 1,
"self": 4.7998782939999955
},
"TrainerController.advance": {
"total": 2417.2143813149764,
"count": 232991,
"self": 4.846205188116983,
"children": {
"env_step": {
"total": 1891.8225552859774,
"count": 232991,
"self": 1605.5046753068061,
"children": {
"SubprocessEnvManager._take_step": {
"total": 283.3535706600338,
"count": 232991,
"self": 17.05685105298636,
"children": {
"TorchPolicy.evaluate": {
"total": 266.29671960704746,
"count": 223086,
"self": 266.29671960704746
}
}
},
"workers": {
"total": 2.964309319137442,
"count": 232991,
"self": 0.0,
"children": {
"worker_root": {
"total": 2418.358840724019,
"count": 232991,
"is_parallel": true,
"self": 1104.3743622388984,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009486749999609856,
"count": 1,
"is_parallel": true,
"self": 0.0002847770000471428,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006638979999138428,
"count": 2,
"is_parallel": true,
"self": 0.0006638979999138428
}
}
},
"UnityEnvironment.step": {
"total": 0.049217229000021234,
"count": 1,
"is_parallel": true,
"self": 0.0003231460000279185,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025555599995641387,
"count": 1,
"is_parallel": true,
"self": 0.00025555599995641387
},
"communicator.exchange": {
"total": 0.04785806000001003,
"count": 1,
"is_parallel": true,
"self": 0.04785806000001003
},
"steps_from_proto": {
"total": 0.0007804670000268743,
"count": 1,
"is_parallel": true,
"self": 0.00022275700001728183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005577100000095925,
"count": 2,
"is_parallel": true,
"self": 0.0005577100000095925
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1313.9844784851207,
"count": 232990,
"is_parallel": true,
"self": 39.64681896032812,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.58183516804309,
"count": 232990,
"is_parallel": true,
"self": 82.58183516804309
},
"communicator.exchange": {
"total": 1100.3995902739157,
"count": 232990,
"is_parallel": true,
"self": 1100.3995902739157
},
"steps_from_proto": {
"total": 91.35623408283362,
"count": 232990,
"is_parallel": true,
"self": 34.55160451195883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.804629570874795,
"count": 465980,
"is_parallel": true,
"self": 56.804629570874795
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 520.545620840882,
"count": 232991,
"self": 6.9363198498673455,
"children": {
"process_trajectory": {
"total": 137.7143241180155,
"count": 232991,
"self": 136.42011655601607,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2942075619994284,
"count": 10,
"self": 1.2942075619994284
}
}
},
"_update_policy": {
"total": 375.8949768729991,
"count": 97,
"self": 315.5257589870075,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.36921788599159,
"count": 2910,
"self": 60.36921788599159
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0680000741558615e-06,
"count": 1,
"self": 1.0680000741558615e-06
},
"TrainerController._save_models": {
"total": 0.1137580220001837,
"count": 1,
"self": 0.0020496320003076107,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11170838999987609,
"count": 1,
"self": 0.11170838999987609
}
}
}
}
}
}
}