2 Push

SnowballTarget/events.out.tfevents.1725447560.1a1dee110b85.6061.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa99a41821bd7decef694be25ababfd35016ab21b1254f2901c1650f7018e6b8
+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", "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "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", "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, "no_graphics_monitor": false}, "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

@@ -69,7 +69,7 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.111 seconds
+- Completed reload, in  0.165 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ 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: 0.825702 ms
+UnloadTime: 1.256428 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 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5369 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
@@ -81,7 +78,7 @@ Memory Statistics:
     [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 2.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -169,23 +166,23 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 41
+  Peak main deferred allocation count 3
     [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]: 5461 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 7.0 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 20.6 MB
+      Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.3 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 1.7 MB
+      Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -198,7 +195,7 @@ 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)]
@@ -213,13 +210,13 @@ 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]: 4601 frames, [64.0 KB-128.0 KB]: 860 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 66.8 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]: 5461 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
@@ -231,13 +228,13 @@ 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]: 5461 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]: 5460 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
@@ -249,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5461 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]: 5461 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": 1.045837640762329,
-            "min": 1.045837640762329,
-            "max": 2.8653435707092285,
-            "count": 20
-        },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9997.162109375,
-            "min": 9997.162109375,
-            "max": 29375.501953125,
-            "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": 12.72225570678711,
-            "min": 0.3753914535045624,
-            "max": 12.72225570678711,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2480.83984375,
-            "min": 72.82594299316406,
-            "max": 2564.901123046875,
-            "count": 20
-        },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 20
-        },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 20
-        },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06667523928541307,
-            "min": 0.0630998092292073,
-            "max": 0.07480417779062883,
-            "count": 20
-        },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.26670095714165226,
-            "min": 0.26421933305876644,
-            "max": 0.3694506930118865,
-            "count": 20
-        },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.18590383100159028,
-            "min": 0.12113291147968494,
-            "max": 0.2830563764653954,
-            "count": 20
-        },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7436153240063611,
-            "min": 0.48453164591873976,
-            "max": 1.339132680320272,
-            "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": 25.15909090909091,
-            "min": 3.590909090909091,
-            "max": 25.163636363636364,
-            "count": 20
-        },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1107.0,
-            "min": 158.0,
-            "max": 1384.0,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.15909090909091,
-            "min": 3.590909090909091,
-            "max": 25.163636363636364,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1107.0,
-            "min": 158.0,
-            "max": 1384.0,
-            "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": "1725446431",
+        "start_time_seconds": "1725447559",
         "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1725447019"
+        "end_time_seconds": "1725447563"
     },
-    "total": 587.675576239,
+    "total": 3.678352360999952,
     "count": 1,
-    "self": 0.534376805999841,
+    "self": 0.6420187269998223,
     "children": {
         "run_training.setup": {
-            "total": 0.06787866400003395,
+            "total": 0.11124676300005376,
             "count": 1,
-            "self": 0.06787866400003395
+            "self": 0.11124676300005376
         },
         "TrainerController.start_learning": {
-            "total": 587.073320769,
+            "total": 2.925086871000076,
             "count": 1,
-            "self": 0.8556284609962859,
+            "self": 0.00032350099991163006,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.557647225999972,
+                    "total": 2.8003746439999304,
                     "count": 1,
-                    "self": 2.557647225999972
-                },
-                "TrainerController.advance": {
-                    "total": 583.5741436060039,
-                    "count": 18202,
-                    "self": 0.41586176999749114,
-                    "children": {
-                        "env_step": {
-                            "total": 583.1582818360064,
-                            "count": 18202,
-                            "self": 450.28113312699975,
-                            "children": {
-                                "SubprocessEnvManager._take_step": {
-                                    "total": 132.46962751500428,
-                                    "count": 18202,
-                                    "self": 2.2491896280002948,
-                                    "children": {
-                                        "TorchPolicy.evaluate": {
-                                            "total": 130.22043788700398,
-                                            "count": 18202,
-                                            "self": 130.22043788700398
-                                        }
-                                    }
-                                },
-                                "workers": {
-                                    "total": 0.4075211940023564,
-                                    "count": 18202,
-                                    "self": 0.0,
-                                    "children": {
-                                        "worker_root": {
-                                            "total": 585.3596780850047,
-                                            "count": 18202,
-                                            "is_parallel": true,
-                                            "self": 275.55226111301164,
-                                            "children": {
-                                                "run_training.setup": {
-                                                    "total": 0.0,
-                                                    "count": 0,
-                                                    "is_parallel": true,
-                                                    "self": 0.0,
-                                                    "children": {
-                                                        "steps_from_proto": {
-                                                            "total": 0.0023817600000484163,
-                                                            "count": 1,
-                                                            "is_parallel": true,
-                                                            "self": 0.0006903680001641987,
-                                                            "children": {
-                                                                "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0016913919998842175,
-                                                                    "count": 10,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.0016913919998842175
-                                                                }
-                                                            }
-                                                        },
-                                                        "UnityEnvironment.step": {
-                                                            "total": 0.04349682699995583,
-                                                            "count": 1,
-                                                            "is_parallel": true,
-                                                            "self": 0.0008347739999408077,
-                                                            "children": {
-                                                                "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00044193400003678107,
-                                                                    "count": 1,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.00044193400003678107
-                                                                },
-                                                                "communicator.exchange": {
-                                                                    "total": 0.03984495299999935,
-                                                                    "count": 1,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.03984495299999935
-                                                                },
-                                                                "steps_from_proto": {
-                                                                    "total": 0.00237516599997889,
-                                                                    "count": 1,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.0004573869999831004,
-                                                                    "children": {
-                                                                        "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0019177789999957895,
-                                                                            "count": 10,
-                                                                            "is_parallel": true,
-                                                                            "self": 0.0019177789999957895
-                                                                        }
-                                                                    }
-                                                                }
-                                                            }
-                                                        }
-                                                    }
-                                                },
-                                                "UnityEnvironment.step": {
-                                                    "total": 309.80741697199306,
-                                                    "count": 18201,
-                                                    "is_parallel": true,
-                                                    "self": 14.67362322899794,
-                                                    "children": {
-                                                        "UnityEnvironment._generate_step_input": {
-                                                            "total": 7.378407473996219,
-                                                            "count": 18201,
-                                                            "is_parallel": true,
-                                                            "self": 7.378407473996219
-                                                        },
-                                                        "communicator.exchange": {
-                                                            "total": 243.95200306099974,
-                                                            "count": 18201,
-                                                            "is_parallel": true,
-                                                            "self": 243.95200306099974
-                                                        },
-                                                        "steps_from_proto": {
-                                                            "total": 43.80338320799916,
-                                                            "count": 18201,
-                                                            "is_parallel": true,
-                                                            "self": 8.451055533977751,
-                                                            "children": {
-                                                                "_process_rank_one_or_two_observation": {
-                                                                    "total": 35.35232767402141,
-                                                                    "count": 182010,
-                                                                    "is_parallel": true,
-                                                                    "self": 35.35232767402141
-                                                                }
-                                                            }
-                                                        }
-                                                    }
-                                                }
-                                            }
-                                        }
-                                    }
-                                }
-                            }
-                        }
-                    }
+                    "self": 2.8003746439999304
                 },
                 "trainer_threads": {
-                    "total": 0.00022250399990753067,
+                    "total": 3.537400016284664e-05,
                     "count": 1,
-                    "self": 0.00022250399990753067,
+                    "self": 3.537400016284664e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,38 +43,16 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 577.0433314389519,
-                                    "count": 763406,
+                                    "total": 0.0002446969999709836,
+                                    "count": 1,
                                     "is_parallel": true,
-                                    "self": 16.77063533093451,
+                                    "self": 2.55510001352377e-05,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 309.4938472800175,
-                                            "count": 763406,
-                                            "is_parallel": true,
-                                            "self": 308.52480487101764,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 0.9690424089998828,
-                                                    "count": 4,
-                                                    "is_parallel": true,
-                                                    "self": 0.9690424089998828
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 250.77884882799987,
-                                            "count": 90,
+                                            "total": 0.0002191459998357459,
+                                            "count": 1,
                                             "is_parallel": true,
-                                            "self": 70.9260778250017,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 179.85277100299817,
-                                                    "count": 4587,
-                                                    "is_parallel": true,
-                                                    "self": 179.85277100299817
-                                                }
-                                            }
+                                            "self": 0.0002191459998357459
                                         }
                                     }
                                 }
@@ -360,14 +61,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08567897199998242,
+                    "total": 0.12435335200007103,
                     "count": 1,
-                    "self": 0.0012652169999682883,
+                    "self": 0.001577724000071612,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08441375500001413,
+                            "total": 0.12277562799999941,
                             "count": 1,
-                            "self": 0.08441375500001413
+                            "self": 0.12277562799999941
                         }
                     }
                 }

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": 1725447562.5325375,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
             }
         ],
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.454545454545453,
-            "creation_time": 1725447018.9591513,
+            "reward": null,
+            "creation_time": 1725447562.5325375,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]