First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694f1f1cb6c6c737a6a193432a7e7785f87b58dc5fa12cb1c8c4478d6b4b594f
+oid sha256:37e199153c8ed62c31534fe3ffada038cb8e47c287a2332b5b7bda914b7279e4
 size 94197

SnowballTarget/events.out.tfevents.1688056138.0c7b145c0c19.70881.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2745f273faffed1a46d4d5c1940083d0e5f284aab4e097bc6017c2ecc95347
+size 1108

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 32, "buffer_size": 2048, "learning_rate": 3e-05, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 10, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 32, "num_layers": 10, "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": 2000000, "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, "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": 32, "buffer_size": 2048, "learning_rate": 3e-05, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 10, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 32, "num_layers": 10, "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": 1, "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, "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

@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 2000000
+    max_steps: 1
     time_horizon: 64
     summary_freq: 10000
     threaded: true
@@ -67,8 +67,8 @@ 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

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2642:(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  0.077 seconds
+- Completed reload, in  0.126 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)
@@ -42,7 +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: 0.695991 ms
+UnloadTime: 0.899359 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.
@@ -50,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 23279 frames, [16.0 KB-32.0 KB]: 394 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
@@ -78,7 +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
@@ -166,19 +166,19 @@ 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]: 13060 frames, [8.0 MB-16.0 MB]: 10614 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 16.0 MB
-      Peak Block count 2
-      Peak Allocated memory 13.7 MB
+      Peak Block count 1
+      Peak Allocated memory 4.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 23674 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
@@ -195,7 +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)]
@@ -210,13 +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]: 21880 frames, [64.0 KB-128.0 KB]: 1794 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]: 23674 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
@@ -228,13 +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]: 23674 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]: 23673 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
@@ -246,13 +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]: 23674 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]: 23674 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": 0.8005643486976624,
-            "min": 0.8005643486976624,
-            "max": 2.8897595405578613,
-            "count": 86
-        },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 7679.01318359375,
-            "min": 7679.01318359375,
-            "max": 29689.390625,
-            "count": 86
-        },
-        "SnowballTarget.Step.mean": {
-            "value": 859984.0,
-            "min": 9952.0,
-            "max": 859984.0,
-            "count": 86
-        },
-        "SnowballTarget.Step.sum": {
-            "value": 859984.0,
-            "min": 9952.0,
-            "max": 859984.0,
-            "count": 86
-        },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.663809776306152,
-            "min": 0.3006419539451599,
-            "max": 13.663809776306152,
-            "count": 86
-        },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2664.44287109375,
-            "min": 58.32453918457031,
-            "max": 2758.469970703125,
-            "count": 86
-        },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 86
-        },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 10945.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 86
-        },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.14014193106472436,
-            "min": 0.13611076401899697,
-            "max": 0.14403688367747985,
-            "count": 86
-        },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.5605677242588974,
-            "min": 0.550232109960983,
-            "max": 0.7201844183873992,
-            "count": 86
-        },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.18197881391765,
-            "min": 0.1057476676526457,
-            "max": 0.30833898726028997,
-            "count": 86
-        },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7279152556706,
-            "min": 0.4229906706105828,
-            "max": 1.496446692647741,
-            "count": 86
-        },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 1.7180862730599998e-05,
-            "min": 1.7180862730599998e-05,
-            "max": 2.99188202706e-05,
-            "count": 86
-        },
-        "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 6.872345092239999e-05,
-            "min": 6.872345092239999e-05,
-            "max": 0.000148851603828,
-            "count": 86
-        },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.1572694,
-            "min": 0.1572694,
-            "max": 0.1997294,
-            "count": 86
-        },
-        "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.6290776,
-            "min": 0.6290776,
-            "max": 0.9961720000000001,
-            "count": 86
-        },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0028677430599999996,
-            "min": 0.0028677430599999996,
-            "max": 0.00498649706,
-            "count": 86
-        },
-        "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.011470972239999998,
-            "min": 0.011470972239999998,
-            "max": 0.024808982800000004,
-            "count": 86
-        },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 27.15909090909091,
-            "min": 2.9545454545454546,
-            "max": 27.15909090909091,
-            "count": 86
-        },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1195.0,
-            "min": 130.0,
-            "max": 1455.0,
-            "count": 86
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 27.15909090909091,
-            "min": 2.9545454545454546,
-            "max": 27.15909090909091,
-            "count": 86
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1195.0,
-            "min": 130.0,
-            "max": 1455.0,
-            "count": 86
-        },
-        "SnowballTarget.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 86
-        },
-        "SnowballTarget.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 86
-        }
-    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1688049644",
+        "start_time_seconds": "1688056136",
         "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn --force ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn --resume ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1688055896"
+        "end_time_seconds": "1688056142"
     },
-    "total": 6252.132397349,
+    "total": 5.395517639999525,
     "count": 1,
-    "self": 0.5343544099996507,
+    "self": 0.475445623998894,
     "children": {
         "run_training.setup": {
-            "total": 0.0397060049999709,
+            "total": 0.06738246100030665,
             "count": 1,
-            "self": 0.0397060049999709
+            "self": 0.06738246100030665
         },
         "TrainerController.start_learning": {
-            "total": 6251.558336934,
+            "total": 4.852689555000325,
             "count": 1,
-            "self": 2.8322411269409713,
+            "self": 0.0003010580021509668,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.987936718000128,
+                    "total": 4.64344661999894,
                     "count": 1,
-                    "self": 3.987936718000128
-                },
-                "TrainerController.advance": {
-                    "total": 6244.736176606059,
-                    "count": 78913,
-                    "self": 1.371338105194809,
-                    "children": {
-                        "env_step": {
-                            "total": 6243.364838500865,
-                            "count": 78913,
-                            "self": 5632.559633587176,
-                            "children": {
-                                "SubprocessEnvManager._take_step": {
-                                    "total": 609.501925863759,
-                                    "count": 78913,
-                                    "self": 8.872054845755883,
-                                    "children": {
-                                        "TorchPolicy.evaluate": {
-                                            "total": 600.6298710180031,
-                                            "count": 78913,
-                                            "self": 600.6298710180031
-                                        }
-                                    }
-                                },
-                                "workers": {
-                                    "total": 1.3032790499300972,
-                                    "count": 78912,
-                                    "self": 0.0,
-                                    "children": {
-                                        "worker_root": {
-                                            "total": 6242.012165772212,
-                                            "count": 78912,
-                                            "is_parallel": true,
-                                            "self": 5023.656429102948,
-                                            "children": {
-                                                "run_training.setup": {
-                                                    "total": 0.0,
-                                                    "count": 0,
-                                                    "is_parallel": true,
-                                                    "self": 0.0,
-                                                    "children": {
-                                                        "steps_from_proto": {
-                                                            "total": 0.0019513950001055491,
-                                                            "count": 1,
-                                                            "is_parallel": true,
-                                                            "self": 0.0005977889995847363,
-                                                            "children": {
-                                                                "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013536060005208128,
-                                                                    "count": 10,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.0013536060005208128
-                                                                }
-                                                            }
-                                                        },
-                                                        "UnityEnvironment.step": {
-                                                            "total": 0.06701464399975521,
-                                                            "count": 1,
-                                                            "is_parallel": true,
-                                                            "self": 0.0006015869998918788,
-                                                            "children": {
-                                                                "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00046059799979047966,
-                                                                    "count": 1,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.00046059799979047966
-                                                                },
-                                                                "communicator.exchange": {
-                                                                    "total": 0.06392959599997994,
-                                                                    "count": 1,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.06392959599997994
-                                                                },
-                                                                "steps_from_proto": {
-                                                                    "total": 0.0020228630000929115,
-                                                                    "count": 1,
-                                                                    "is_parallel": true,
-                                                                    "self": 0.0003697500005728216,
-                                                                    "children": {
-                                                                        "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.00165311299952009,
-                                                                            "count": 10,
-                                                                            "is_parallel": true,
-                                                                            "self": 0.00165311299952009
-                                                                        }
-                                                                    }
-                                                                }
-                                                            }
-                                                        }
-                                                    }
-                                                },
-                                                "UnityEnvironment.step": {
-                                                    "total": 1218.3557366692635,
-                                                    "count": 78911,
-                                                    "is_parallel": true,
-                                                    "self": 47.01313297297838,
-                                                    "children": {
-                                                        "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.05665892715524,
-                                                            "count": 78911,
-                                                            "is_parallel": true,
-                                                            "self": 23.05665892715524
-                                                        },
-                                                        "communicator.exchange": {
-                                                            "total": 985.968607595295,
-                                                            "count": 78911,
-                                                            "is_parallel": true,
-                                                            "self": 985.968607595295
-                                                        },
-                                                        "steps_from_proto": {
-                                                            "total": 162.31733717383486,
-                                                            "count": 78911,
-                                                            "is_parallel": true,
-                                                            "self": 30.564958347634274,
-                                                            "children": {
-                                                                "_process_rank_one_or_two_observation": {
-                                                                    "total": 131.75237882620058,
-                                                                    "count": 789110,
-                                                                    "is_parallel": true,
-                                                                    "self": 131.75237882620058
-                                                                }
-                                                            }
-                                                        }
-                                                    }
-                                                }
-                                            }
-                                        }
-                                    }
-                                }
-                            }
-                        }
-                    }
+                    "self": 4.64344661999894
                 },
                 "trainer_threads": {
-                    "total": 4.9361000492353924e-05,
+                    "total": 1.731200063659344e-05,
                     "count": 1,
-                    "self": 4.9361000492353924e-05,
+                    "self": 1.731200063659344e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,38 +43,16 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 6225.817099724835,
-                                    "count": 2504578,
+                                    "total": 0.00021390300025814213,
+                                    "count": 1,
                                     "is_parallel": true,
-                                    "self": 51.866628838743054,
+                                    "self": 1.9797000277321786e-05,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 1278.9955774550644,
-                                            "count": 2504578,
-                                            "is_parallel": true,
-                                            "self": 1268.4845690100638,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 10.511008445000698,
-                                                    "count": 17,
-                                                    "is_parallel": true,
-                                                    "self": 10.511008445000698
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 4894.954893431028,
-                                            "count": 394,
+                                            "total": 0.00019410599998082034,
+                                            "count": 1,
                                             "is_parallel": true,
-                                            "self": 862.4403812670084,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 4032.5145121640194,
-                                                    "count": 267910,
-                                                    "is_parallel": true,
-                                                    "self": 4032.5145121640194
-                                                }
-                                            }
+                                            "self": 0.00019410599998082034
                                         }
                                     }
                                 }
@@ -360,14 +61,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0019331219991727266,
+                    "total": 0.2089245649985969,
                     "count": 1,
-                    "self": 2.5392999305040576e-05,
+                    "self": 0.0006888179977977416,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.001907728999867686,
+                            "total": 0.20823574700079917,
                             "count": 1,
-                            "self": 0.001907728999867686
+                            "self": 0.20823574700079917
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "SnowballTarget": {
         "checkpoints": [
-            {
-                "steps": 399992,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
-                "reward": 23.0,
-                "creation_time": 1688052517.365193,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
-                ]
-            },
             {
                 "steps": 449952,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
@@ -90,8 +81,26 @@
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.pt"
                 ]
+            },
+            {
+                "steps": 849968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.onnx",
+                "reward": null,
+                "creation_time": 1688056141.8490736,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.pt"
+                ]
             }
-        ]
+        ],
+        "final_checkpoint": {
+            "steps": 849968,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": null,
+            "creation_time": 1688056141.8490736,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.pt"
+            ]
+        }
     },
     "metadata": {
         "stats_format_version": "0.3.0",