First training for SnowballTarget

SnowballTarget/events.out.tfevents.1721473267.Montana.27072.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c3475beff39aea916c9ac6e5e319dcde1f712dd9f2f4c624dc02f06a6aa32f
+size 1114

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -68,8 +68,8 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: false
-  force: true
+  resume: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -22,7 +22,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.378228 ms
+UnloadTime: 0.474486 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 4 worker threads for Enlighten.
@@ -30,7 +30,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5371 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -53,12 +53,12 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 6]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 2.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -73,7 +73,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 5]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
@@ -88,12 +88,12 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 4]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 2.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 3]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -143,12 +143,12 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 1]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 2.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 2]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 2.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
@@ -176,22 +176,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 40
+  Peak main deferred allocation count 2
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.8 MB
+      Peak Allocated memory 4.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.7 MB
+      Peak Allocated memory 17.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -205,7 +205,7 @@ Memory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 2
+  Used Block Count 1
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -220,13 +220,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4951 frames, [64.0 KB-128.0 KB]: 512 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.4 KB
+      Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -238,13 +238,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5463 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.6 MB
+      Peak Allocated memory 0.5 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -256,13 +256,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5463 frames
+      Peak usage frame count: [0-1.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 5463 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,317 +1,40 @@
 {
     "name": "root",
-    "gauges": {
-        "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.9319132566452026,
-            "min": 0.9319132566452026,
-            "max": 2.870424747467041,
-            "count": 20
-        },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8938.912109375,
-            "min": 8938.912109375,
-            "max": 29522.318359375,
-            "count": 20
-        },
-        "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
-        },
-        "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.874151229858398,
-            "min": 0.39834508299827576,
-            "max": 12.874151229858398,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2510.45947265625,
-            "min": 77.27894592285156,
-            "max": 2602.755126953125,
-            "count": 20
-        },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 20
-        },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 10945.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 20
-        },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06857709564963657,
-            "min": 0.057933525650250714,
-            "max": 0.07610024299595833,
-            "count": 20
-        },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2743083825985463,
-            "min": 0.23173410260100286,
-            "max": 0.38050121497979167,
-            "count": 20
-        },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.17977972606233525,
-            "min": 0.10100476959761343,
-            "max": 0.28556475897922234,
-            "count": 20
-        },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.719118904249341,
-            "min": 0.4040190783904537,
-            "max": 1.408571179006614,
-            "count": 20
-        },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
-        },
-        "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
-        },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
-        },
-        "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
-        },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
-        },
-        "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
-        },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.363636363636363,
-            "min": 3.1136363636363638,
-            "max": 25.418181818181818,
-            "count": 20
-        },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1116.0,
-            "min": 137.0,
-            "max": 1398.0,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.363636363636363,
-            "min": 3.1136363636363638,
-            "max": 25.418181818181818,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1116.0,
-            "min": 137.0,
-            "max": 1398.0,
-            "count": 20
-        },
-        "SnowballTarget.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 20
-        },
-        "SnowballTarget.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 20
-        }
-    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1721472628",
+        "start_time_seconds": "1721473267",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/home/montana/miniconda3/envs/huggy/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force",
+        "command_line_arguments": "/home/montana/miniconda3/envs/huggy/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --resume",
         "mlagents_version": "1.0.0",
         "mlagents_envs_version": "1.0.0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1721473081"
+        "end_time_seconds": "1721473271"
     },
-    "total": 453.7232466909918,
+    "total": 4.123133318993496,
     "count": 1,
-    "self": 0.2725397319882177,
+    "self": 0.27164047601399943,
     "children": {
         "run_training.setup": {
-            "total": 0.013106368016451597,
+            "total": 0.016180282982531935,
             "count": 1,
-            "self": 0.013106368016451597
+            "self": 0.016180282982531935
         },
         "TrainerController.start_learning": {
-            "total": 453.43760059098713,
+            "total": 3.8353125599969644,
             "count": 1,
-            "self": 0.4767339399259072,
+            "self": 0.0002827090211212635,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.856478811998386,
+                    "total": 2.398862707981607,
                     "count": 1,
-                    "self": 2.856478811998386
-                },
-                "TrainerController.advance": {
-                    "total": 450.0170217230916,
-                    "count": 18207,
-                    "self": 0.2265568540606182,
-                    "children": {
-                        "env_step": {
-                            "total": 449.790464869031,
-                            "count": 18207,
-                            "self": 262.4828545647615,
-                            "children": {
-                                "SubprocessEnvManager._take_step": {
-                                    "total": 187.07232962345006,
-                                    "count": 18207,
-                                    "self": 1.2606316194287501,
-                                    "children": {
-                                        "TorchPolicy.evaluate": {
-                                            "total": 185.8116980040213,
-                                            "count": 18207,
-                                            "self": 185.8116980040213
-                                        }
-                                    }
-                                },
-                                "workers": {
-                                    "total": 0.23528068081941456,
-                                    "count": 18207,
-                                    "self": 0.0,
-                                    "children": {
-                                        "worker_root": {
-                                            "total": 452.63578140575555,
-                                            "count": 18207,
-                                            "is_parallel": true,
-                                            "self": 268.31014963949565,
-                                            "children": {
-                                                "run_training.setup": {
-                                                    "total": 0.0,
-                                                    "count": 0,
-                                                    "is_parallel": true,
-                                                    "self": 0.0,
-                                                    "children": {
-                                                        "steps_from_proto": {
-                                                            "total": 0.0011406879930291325,
-                                                            "count": 1,
-                                                            "is_parallel": true,
-                                                            "self": 0.0003602970391511917,
-                                                            "children": {
-                                                                "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0007803909538779408,
-                                                                    "count": 10,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.0007803909538779408
-                                                                }
-                                                            }
-                                                        },
-                                                        "UnityEnvironment.step": {
-                                                            "total": 0.035801211022771895,
-                                                            "count": 1,
-                                                            "is_parallel": true,
-                                                            "self": 0.00043541903141885996,
-                                                            "children": {
-                                                                "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0012463539896998554,
-                                                                    "count": 1,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.0012463539896998554
-                                                                },
-                                                                "communicator.exchange": {
-                                                                    "total": 0.032584517990471795,
-                                                                    "count": 1,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.032584517990471795
-                                                                },
-                                                                "steps_from_proto": {
-                                                                    "total": 0.0015349200111813843,
-                                                                    "count": 1,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.00049385498277843,
-                                                                    "children": {
-                                                                        "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0010410650284029543,
-                                                                            "count": 10,
-                                                                            "is_parallel": true,
-                                                                            "self": 0.0010410650284029543
-                                                                        }
-                                                                    }
-                                                                }
-                                                            }
-                                                        }
-                                                    }
-                                                },
-                                                "UnityEnvironment.step": {
-                                                    "total": 184.3256317662599,
-                                                    "count": 18206,
-                                                    "is_parallel": true,
-                                                    "self": 4.547100880125072,
-                                                    "children": {
-                                                        "UnityEnvironment._generate_step_input": {
-                                                            "total": 2.7601509311934933,
-                                                            "count": 18206,
-                                                            "is_parallel": true,
-                                                            "self": 2.7601509311934933
-                                                        },
-                                                        "communicator.exchange": {
-                                                            "total": 162.79889808109147,
-                                                            "count": 18206,
-                                                            "is_parallel": true,
-                                                            "self": 162.79889808109147
-                                                        },
-                                                        "steps_from_proto": {
-                                                            "total": 14.219481873849872,
-                                                            "count": 18206,
-                                                            "is_parallel": true,
-                                                            "self": 3.3427517008967698,
-                                                            "children": {
-                                                                "_process_rank_one_or_two_observation": {
-                                                                    "total": 10.876730172953103,
-                                                                    "count": 182060,
-                                                                    "is_parallel": true,
-                                                                    "self": 10.876730172953103
-                                                                }
-                                                            }
-                                                        }
-                                                    }
-                                                }
-                                            }
-                                        }
-                                    }
-                                }
-                            }
-                        }
-                    }
+                    "self": 2.398862707981607
                 },
                 "trainer_threads": {
-                    "total": 0.0001153459888882935,
+                    "total": 1.2222997611388564e-05,
                     "count": 1,
-                    "self": 0.0001153459888882935,
+                    "self": 1.2222997611388564e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,38 +43,16 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 448.1581348279433,
-                                    "count": 372741,
+                                    "total": 0.0002568429918028414,
+                                    "count": 1,
                                     "is_parallel": true,
-                                    "self": 5.601814194989856,
+                                    "self": 1.4424003893509507e-05,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 245.7939493758895,
-                                            "count": 372741,
-                                            "is_parallel": true,
-                                            "self": 245.11395980493398,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 0.679989570955513,
-                                                    "count": 4,
-                                                    "is_parallel": true,
-                                                    "self": 0.679989570955513
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 196.76237125706393,
-                                            "count": 90,
+                                            "total": 0.00024241898790933192,
+                                            "count": 1,
                                             "is_parallel": true,
-                                            "self": 30.571620423404966,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 166.19075083365897,
-                                                    "count": 4587,
-                                                    "is_parallel": true,
-                                                    "self": 166.19075083365897
-                                                }
-                                            }
+                                            "self": 0.00024241898790933192
                                         }
                                     }
                                 }
@@ -360,14 +61,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08725076998234726,
+                    "total": 1.4361549199966248,
                     "count": 1,
-                    "self": 0.0015113929694052786,
+                    "self": 0.0006549700046889484,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08573937701294199,
+                            "total": 1.4354999499919359,
                             "count": 1,
-                            "self": 0.08573937701294199
+                            "self": 1.4354999499919359
                         }
                     }
                 }

run_logs/training_status.json

@@ -45,13 +45,22 @@
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": null,
+                "creation_time": 1721473271.0107923,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
             }
         ],
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.454545454545453,
-            "creation_time": 1721473081.5591972,
+            "reward": null,
+            "creation_time": 1721473271.0107923,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]