legalaspro commited on
Commit
ea07f0f
·
verified ·
1 Parent(s): 15b410d
Huggy.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b35058396e15828c047817feb347d20baab31832092bcc65b06fd62edbae8364
3
  size 2274020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda98a519f9b7186530d21afa03e0ad25d4a0eb58d5fc0cbb343b2085a0ec2c4
3
  size 2274020
Huggy/Huggy-2199943.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abaa6c68c6cebbd8cfd9b036f8e7d45bb57c49bea3251c83b4acbed5a6fc055b
3
+ size 2274020
Huggy/Huggy-2199943.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5ea4bce1b5c573af49ec867a3d7bb85c9d7eaee9e79e2995d052808b0201f1
3
+ size 13509473
Huggy/Huggy-2299931.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde8e338cb1a84bc908b31ba5837a1dcd347e5d723ac4d417b81572f31d5afe5
3
+ size 2274020
Huggy/Huggy-2299931.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b05da8a7d60083e50747dfe2682afb38ca11c42f771dce467275157aa8aa464
3
+ size 13509473
Huggy/Huggy-2399961.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa995c76b23f5258239b641946587b9ed79a1a73e2bbdc017dc075dfbc81bb5b
3
+ size 2274020
Huggy/Huggy-2399961.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eefd178f0c40fa959174454c9e0c29d74adbfb9b0071f8a768b5328539abc888
3
+ size 13509473
Huggy/Huggy-2499799.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e5889e9cb791f8ad1b9face3bdf70822fca9c1b7b2755997f0a9dcccfe19d3
3
+ size 2274020
Huggy/Huggy-2499799.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb574d7ba89dd19a8d587a9e5741d854e3279569efc237a8b0c68bd406231bf
3
+ size 13509473
Huggy/Huggy-2599962.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1153c8d2ee59b7d61c20fadfbc932955f1788b19a6afc9014f0ec83684f95480
3
+ size 2274020
Huggy/Huggy-2599962.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c325615771d873e710525798f1e01a053b1d70222d823cfeef3a9718a6a1019
3
+ size 13509473
Huggy/Huggy-2699735.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f10b985d321e008eed3cf1144d0251ae0f73e44f6074eaee2ba38fd65827cb0
3
+ size 2274020
Huggy/Huggy-2699735.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f1840edb5899b1c9c93493ba25990856c0501d3a53fd6f101b602ab15e0e0c
3
+ size 13509473
Huggy/Huggy-2799586.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a22b444cababfe1dda3a9e67bce76abc1f30dd2bbc6d2a56a006581d377bff5
3
+ size 2274020
Huggy/Huggy-2799586.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:502a795e2ada8b63de4d349251a220d3768d5d134e74191cba30fca9cccf1916
3
+ size 13509473
Huggy/Huggy-2899484.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf29ba76557b2e59b5880aac4ccf1d90956a0f8013315f0f0d7b7bb7158066a2
3
+ size 2274020
Huggy/Huggy-2899484.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e80385951637d0a7baa6e3d3230155929029a886f5b42b72b4ac0e986e77fd
3
+ size 13509473
Huggy/Huggy-2999479.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f530423a77635c885e97e01cb8dafe1a35ffd95a7504f3810fe14e8e9923f401
3
+ size 2274020
Huggy/Huggy-2999479.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7fede4dbe76b30c81f05e674ed89cc33ae5c8ddb5189afe88333f1cc3890726
3
+ size 13509473
Huggy/Huggy-3000229.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda98a519f9b7186530d21afa03e0ad25d4a0eb58d5fc0cbb343b2085a0ec2c4
3
+ size 2274020
Huggy/Huggy-3000229.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66e35020ca38775b37ff69639faa9e497ba54705561e0db70c8893a81495924
3
+ size 13509473
Huggy/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6bb3274f7d4d8fd0cfd7fe2218290d149c0289a5599d146e01542d86e28ea4c
3
  size 13509218
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a26455a706293b9bd7c0abeba9c25ef87150fb1d60f9ee701c16390ab506301
3
  size 13509218
Huggy/events.out.tfevents.1730735926.ca47c506af0d.26697.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:facfb230cb22b7ba23c4d9c728ea120534d24336575d50bc78a1b965109cd576
3
+ size 551021
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "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": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "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": "Huggy2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 4096, "buffer_size": 61440, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 100000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 3000000, "time_horizon": 750, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "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": "Huggy3", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -3,18 +3,18 @@ behaviors:
3
  Huggy:
4
  trainer_type: ppo
5
  hyperparameters:
6
- batch_size: 2048
7
- buffer_size: 20480
8
  learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
- num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
- checkpoint_interval: 200000
18
  network_settings:
19
  normalize: true
20
  hidden_units: 512
@@ -36,10 +36,10 @@ behaviors:
36
  goal_conditioning_type: hyper
37
  deterministic: false
38
  init_path: null
39
- keep_checkpoints: 15
40
  even_checkpoints: false
41
- max_steps: 2000000
42
- time_horizon: 1000
43
  summary_freq: 50000
44
  threaded: false
45
  self_play: null
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: Huggy2
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
3
  Huggy:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 4096
7
+ buffer_size: 61440
8
  learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
+ num_epoch: 5
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
+ checkpoint_interval: 100000
18
  network_settings:
19
  normalize: true
20
  hidden_units: 512
 
36
  goal_conditioning_type: hyper
37
  deterministic: false
38
  init_path: null
39
+ keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 3000000
42
+ time_horizon: 750
43
  summary_freq: 50000
44
  threaded: false
45
  self_play: null
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: Huggy3
70
  initialize_from: null
71
  load_model: false
72
  resume: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Da
2
  Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/Huggy
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.092 seconds
38
  ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -78,14 +75,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
78
  WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
79
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
80
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
81
- UnloadTime: 0.743740 ms
82
  requesting resize 84 x 84
83
  Setting up 6 worker threads for Enlighten.
84
  Memory Statistics:
85
  [ALLOC_TEMP_TLS] TLS Allocator
86
  StackAllocators :
87
  [ALLOC_TEMP_MAIN]
88
- Peak usage frame count: [4.0 KB-8.0 KB]: 26751 frames, [2.0 MB-4.0 MB]: 1 frames
89
  Initial Block Size 4.0 MB
90
  Current Block Size 4.0 MB
91
  Peak Allocated Bytes 3.6 MB
@@ -93,7 +90,7 @@ Memory Statistics:
93
  [ALLOC_TEMP_Loading.AsyncRead]
94
  Initial Block Size 64.0 KB
95
  Current Block Size 64.0 KB
96
- Peak Allocated Bytes 136 B
97
  Overflow Count 0
98
  [ALLOC_TEMP_Loading.PreloadManager]
99
  Initial Block Size 256.0 KB
@@ -257,16 +254,16 @@ Memory Statistics:
257
  Used Block count 1
258
  Peak Allocated bytes 1.4 MB
259
  [ALLOC_DEFAULT_MAIN]
260
- Peak usage frame count: [16.0 MB-32.0 MB]: 26752 frames
261
  Requested Block Size 16.0 MB
262
  Peak Block count 1
263
- Peak Allocated memory 24.3 MB
264
  Peak Large allocation bytes 16.0 MB
265
  [ALLOC_DEFAULT_THREAD]
266
- Peak usage frame count: [2.0 MB-4.0 MB]: 26752 frames
267
  Requested Block Size 16.0 MB
268
  Peak Block count 1
269
- Peak Allocated memory 2.5 MB
270
  Peak Large allocation bytes 0 B
271
  [ALLOC_TEMP_JOB_1_FRAME]
272
  Initial Block Size 2.0 MB
@@ -295,13 +292,13 @@ Memory Statistics:
295
  Used Block count 1
296
  Peak Allocated bytes 1.4 MB
297
  [ALLOC_GFX_MAIN]
298
- Peak usage frame count: [32.0 KB-64.0 KB]: 26751 frames, [64.0 KB-128.0 KB]: 1 frames
299
  Requested Block Size 16.0 MB
300
  Peak Block count 1
301
  Peak Allocated memory 65.6 KB
302
  Peak Large allocation bytes 0 B
303
  [ALLOC_GFX_THREAD]
304
- Peak usage frame count: [64.0 KB-128.0 KB]: 26752 frames
305
  Requested Block Size 16.0 MB
306
  Peak Block count 1
307
  Peak Allocated memory 81.8 KB
@@ -313,13 +310,13 @@ Memory Statistics:
313
  Used Block count 1
314
  Peak Allocated bytes 1.4 MB
315
  [ALLOC_CACHEOBJECTS_MAIN]
316
- Peak usage frame count: [1.0 MB-2.0 MB]: 26751 frames, [16.0 MB-32.0 MB]: 1 frames
317
  Requested Block Size 4.0 MB
318
  Peak Block count 2
319
  Peak Allocated memory 30.6 MB
320
  Peak Large allocation bytes 24.9 MB
321
  [ALLOC_CACHEOBJECTS_THREAD]
322
- Peak usage frame count: [0.5 MB-1.0 MB]: 26751 frames, [2.0 MB-4.0 MB]: 1 frames
323
  Requested Block Size 4.0 MB
324
  Peak Block count 1
325
  Peak Allocated memory 2.6 MB
@@ -331,13 +328,13 @@ Memory Statistics:
331
  Used Block count 1
332
  Peak Allocated bytes 1.4 MB
333
  [ALLOC_TYPETREE_MAIN]
334
- Peak usage frame count: [0-1.0 KB]: 26752 frames
335
  Requested Block Size 2.0 MB
336
  Peak Block count 1
337
  Peak Allocated memory 1.0 KB
338
  Peak Large allocation bytes 0 B
339
  [ALLOC_TYPETREE_THREAD]
340
- Peak usage frame count: [4.0 KB-8.0 KB]: 26752 frames
341
  Requested Block Size 2.0 MB
342
  Peak Block count 1
343
  Peak Allocated memory 7.3 KB
 
2
  Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.087 seconds
35
  ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
75
  WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
76
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
77
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
78
+ UnloadTime: 0.761684 ms
79
  requesting resize 84 x 84
80
  Setting up 6 worker threads for Enlighten.
81
  Memory Statistics:
82
  [ALLOC_TEMP_TLS] TLS Allocator
83
  StackAllocators :
84
  [ALLOC_TEMP_MAIN]
85
+ Peak usage frame count: [4.0 KB-8.0 KB]: 40115 frames, [2.0 MB-4.0 MB]: 1 frames
86
  Initial Block Size 4.0 MB
87
  Current Block Size 4.0 MB
88
  Peak Allocated Bytes 3.6 MB
 
90
  [ALLOC_TEMP_Loading.AsyncRead]
91
  Initial Block Size 64.0 KB
92
  Current Block Size 64.0 KB
93
+ Peak Allocated Bytes 160 B
94
  Overflow Count 0
95
  [ALLOC_TEMP_Loading.PreloadManager]
96
  Initial Block Size 256.0 KB
 
254
  Used Block count 1
255
  Peak Allocated bytes 1.4 MB
256
  [ALLOC_DEFAULT_MAIN]
257
+ Peak usage frame count: [16.0 MB-32.0 MB]: 40116 frames
258
  Requested Block Size 16.0 MB
259
  Peak Block count 1
260
+ Peak Allocated memory 24.2 MB
261
  Peak Large allocation bytes 16.0 MB
262
  [ALLOC_DEFAULT_THREAD]
263
+ Peak usage frame count: [2.0 MB-4.0 MB]: 40116 frames
264
  Requested Block Size 16.0 MB
265
  Peak Block count 1
266
+ Peak Allocated memory 2.3 MB
267
  Peak Large allocation bytes 0 B
268
  [ALLOC_TEMP_JOB_1_FRAME]
269
  Initial Block Size 2.0 MB
 
292
  Used Block count 1
293
  Peak Allocated bytes 1.4 MB
294
  [ALLOC_GFX_MAIN]
295
+ Peak usage frame count: [32.0 KB-64.0 KB]: 40115 frames, [64.0 KB-128.0 KB]: 1 frames
296
  Requested Block Size 16.0 MB
297
  Peak Block count 1
298
  Peak Allocated memory 65.6 KB
299
  Peak Large allocation bytes 0 B
300
  [ALLOC_GFX_THREAD]
301
+ Peak usage frame count: [64.0 KB-128.0 KB]: 40116 frames
302
  Requested Block Size 16.0 MB
303
  Peak Block count 1
304
  Peak Allocated memory 81.8 KB
 
310
  Used Block count 1
311
  Peak Allocated bytes 1.4 MB
312
  [ALLOC_CACHEOBJECTS_MAIN]
313
+ Peak usage frame count: [1.0 MB-2.0 MB]: 40115 frames, [16.0 MB-32.0 MB]: 1 frames
314
  Requested Block Size 4.0 MB
315
  Peak Block count 2
316
  Peak Allocated memory 30.6 MB
317
  Peak Large allocation bytes 24.9 MB
318
  [ALLOC_CACHEOBJECTS_THREAD]
319
+ Peak usage frame count: [0.5 MB-1.0 MB]: 40115 frames, [2.0 MB-4.0 MB]: 1 frames
320
  Requested Block Size 4.0 MB
321
  Peak Block count 1
322
  Peak Allocated memory 2.6 MB
 
328
  Used Block count 1
329
  Peak Allocated bytes 1.4 MB
330
  [ALLOC_TYPETREE_MAIN]
331
+ Peak usage frame count: [0-1.0 KB]: 40116 frames
332
  Requested Block Size 2.0 MB
333
  Peak Block count 1
334
  Peak Allocated memory 1.0 KB
335
  Peak Large allocation bytes 0 B
336
  [ALLOC_TYPETREE_THREAD]
337
+ Peak usage frame count: [4.0 KB-8.0 KB]: 40116 frames
338
  Requested Block Size 2.0 MB
339
  Peak Block count 1
340
  Peak Allocated memory 7.3 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "Huggy.Policy.Entropy.mean": {
5
- "value": 1.4086451530456543,
6
- "min": 1.4086451530456543,
7
- "max": 1.4282143115997314,
8
- "count": 40
9
  },
10
  "Huggy.Policy.Entropy.sum": {
11
- "value": 71250.6796875,
12
- "min": 69846.4609375,
13
- "max": 76052.203125,
14
- "count": 40
15
  },
16
  "Huggy.Environment.EpisodeLength.mean": {
17
- "value": 77.1234375,
18
- "min": 69.96595744680852,
19
- "max": 370.56296296296296,
20
- "count": 40
21
  },
22
  "Huggy.Environment.EpisodeLength.sum": {
23
- "value": 49359.0,
24
- "min": 49215.0,
25
- "max": 50049.0,
26
- "count": 40
27
  },
28
  "Huggy.Step.mean": {
29
- "value": 1999962.0,
30
- "min": 49908.0,
31
- "max": 1999962.0,
32
- "count": 40
33
  },
34
  "Huggy.Step.sum": {
35
- "value": 1999962.0,
36
- "min": 49908.0,
37
- "max": 1999962.0,
38
- "count": 40
39
  },
40
  "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
- "value": 2.451430559158325,
42
- "min": 0.20409581065177917,
43
- "max": 2.511143445968628,
44
- "count": 40
45
  },
46
  "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
- "value": 1568.91552734375,
48
- "min": 27.348838806152344,
49
- "max": 1731.51025390625,
50
- "count": 40
51
  },
52
  "Huggy.Environment.CumulativeReward.mean": {
53
- "value": 3.781427578255534,
54
- "min": 1.8144129203326667,
55
- "max": 3.9730969858239575,
56
- "count": 40
57
  },
58
  "Huggy.Environment.CumulativeReward.sum": {
59
- "value": 2420.113650083542,
60
- "min": 243.13133132457733,
61
- "max": 2735.5089861750603,
62
- "count": 40
63
  },
64
  "Huggy.Policy.ExtrinsicReward.mean": {
65
- "value": 3.781427578255534,
66
- "min": 1.8144129203326667,
67
- "max": 3.9730969858239575,
68
- "count": 40
69
  },
70
  "Huggy.Policy.ExtrinsicReward.sum": {
71
- "value": 2420.113650083542,
72
- "min": 243.13133132457733,
73
- "max": 2735.5089861750603,
74
- "count": 40
 
 
 
 
 
 
 
 
 
 
 
 
75
  },
76
  "Huggy.Losses.PolicyLoss.mean": {
77
- "value": 0.01733207583246339,
78
- "min": 0.013427162553489325,
79
- "max": 0.01936902105872933,
80
- "count": 40
81
  },
82
  "Huggy.Losses.PolicyLoss.sum": {
83
- "value": 0.05199622749739016,
84
- "min": 0.02685432510697865,
85
- "max": 0.058107063176187995,
86
- "count": 40
87
  },
88
  "Huggy.Losses.ValueLoss.mean": {
89
- "value": 0.06360530406236649,
90
- "min": 0.02129305132354299,
91
- "max": 0.06467222049832344,
92
- "count": 40
93
  },
94
  "Huggy.Losses.ValueLoss.sum": {
95
- "value": 0.19081591218709945,
96
- "min": 0.04258610264708598,
97
- "max": 0.19401666149497032,
98
- "count": 40
99
  },
100
  "Huggy.Policy.LearningRate.mean": {
101
- "value": 3.876398707900001e-06,
102
- "min": 3.876398707900001e-06,
103
- "max": 0.00029530477656507497,
104
- "count": 40
105
  },
106
  "Huggy.Policy.LearningRate.sum": {
107
- "value": 1.1629196123700002e-05,
108
- "min": 1.1629196123700002e-05,
109
- "max": 0.00084427036857655,
110
- "count": 40
111
  },
112
  "Huggy.Policy.Epsilon.mean": {
113
- "value": 0.10129209999999998,
114
- "min": 0.10129209999999998,
115
- "max": 0.1984349250000001,
116
- "count": 40
117
  },
118
  "Huggy.Policy.Epsilon.sum": {
119
- "value": 0.30387629999999993,
120
- "min": 0.20771675000000006,
121
- "max": 0.5814234500000001,
122
- "count": 40
123
  },
124
  "Huggy.Policy.Beta.mean": {
125
- "value": 7.447579000000001e-05,
126
- "min": 7.447579000000001e-05,
127
- "max": 0.004921902757500001,
128
- "count": 40
129
  },
130
  "Huggy.Policy.Beta.sum": {
131
- "value": 0.00022342737,
132
- "min": 0.00022342737,
133
- "max": 0.014073030155000001,
134
- "count": 40
135
- },
136
- "Huggy.IsTraining.mean": {
137
- "value": 1.0,
138
- "min": 1.0,
139
- "max": 1.0,
140
- "count": 40
141
- },
142
- "Huggy.IsTraining.sum": {
143
- "value": 1.0,
144
- "min": 1.0,
145
- "max": 1.0,
146
- "count": 40
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1730730857",
152
  "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.5.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1730732922"
160
  },
161
- "total": 2065.628300517,
162
  "count": 1,
163
- "self": 0.32152190399938263,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.061153282000077525,
167
  "count": 1,
168
- "self": 0.061153282000077525
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 2065.245625331,
172
  "count": 1,
173
- "self": 4.1912719980377915,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.899576870999908,
177
  "count": 1,
178
- "self": 4.899576870999908
179
  },
180
  "TrainerController.advance": {
181
- "total": 2056.0464354439623,
182
- "count": 233267,
183
- "self": 4.079347843870437,
184
  "children": {
185
  "env_step": {
186
- "total": 1594.6005854680732,
187
- "count": 233267,
188
- "self": 1209.4219125279446,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 382.4492671999558,
192
- "count": 233267,
193
- "self": 14.443311594882744,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 368.00595560507304,
197
- "count": 222930,
198
- "self": 368.00595560507304
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 2.7294057401727514,
204
- "count": 233267,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 2058.2862308040167,
209
- "count": 233267,
210
  "is_parallel": true,
211
- "self": 1085.2336838789113,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
@@ -217,48 +217,48 @@
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.0008778320000146778,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.00029092999989188684,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0005869020001227909,
227
  "count": 2,
228
  "is_parallel": true,
229
- "self": 0.0005869020001227909
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.021873027999845363,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00028533599970614887,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00014947099998607882,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00014947099998607882
244
  },
245
  "communicator.exchange": {
246
- "total": 0.020887933000039993,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.020887933000039993
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0005502880001131416,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00016294100032610004,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.00038734699978704157,
259
  "count": 2,
260
  "is_parallel": true,
261
- "self": 0.00038734699978704157
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 973.0525469251054,
271
- "count": 233266,
272
  "is_parallel": true,
273
- "self": 26.368971752106518,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 49.65014063208855,
277
- "count": 233266,
278
  "is_parallel": true,
279
- "self": 49.65014063208855
280
  },
281
  "communicator.exchange": {
282
- "total": 836.1185904249767,
283
- "count": 233266,
284
  "is_parallel": true,
285
- "self": 836.1185904249767
286
  },
287
  "steps_from_proto": {
288
- "total": 60.91484411593365,
289
- "count": 233266,
290
  "is_parallel": true,
291
- "self": 23.906007893971264,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 37.00883622196238,
295
- "count": 466532,
296
  "is_parallel": true,
297
- "self": 37.00883622196238
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 457.36650213201847,
311
- "count": 233267,
312
- "self": 6.016239951967691,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 159.57708967305234,
316
- "count": 233267,
317
- "self": 158.39782267205305,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 1.179267000999289,
321
- "count": 10,
322
- "self": 1.179267000999289
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 291.77317250699843,
328
- "count": 97,
329
- "self": 239.44788752500017,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 52.325284981998266,
333
- "count": 2910,
334
- "self": 52.325284981998266
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.0930002645181958e-06,
344
  "count": 1,
345
- "self": 1.0930002645181958e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.10833992500010936,
349
  "count": 1,
350
- "self": 0.0021823110000696033,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.10615761400003976,
354
  "count": 1,
355
- "self": 0.10615761400003976
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "Huggy.Policy.Entropy.mean": {
5
+ "value": 1.3804458379745483,
6
+ "min": 1.3804458379745483,
7
+ "max": 1.4215736389160156,
8
+ "count": 60
9
  },
10
  "Huggy.Policy.Entropy.sum": {
11
+ "value": 70239.84375,
12
+ "min": 67526.2890625,
13
+ "max": 77451.3359375,
14
+ "count": 60
15
  },
16
  "Huggy.Environment.EpisodeLength.mean": {
17
+ "value": 98.31485148514851,
18
+ "min": 88.34821428571429,
19
+ "max": 447.1517857142857,
20
+ "count": 60
21
  },
22
  "Huggy.Environment.EpisodeLength.sum": {
23
+ "value": 49649.0,
24
+ "min": 48812.0,
25
+ "max": 50133.0,
26
+ "count": 60
27
  },
28
  "Huggy.Step.mean": {
29
+ "value": 2999479.0,
30
+ "min": 49749.0,
31
+ "max": 2999479.0,
32
+ "count": 60
33
  },
34
  "Huggy.Step.sum": {
35
+ "value": 2999479.0,
36
+ "min": 49749.0,
37
+ "max": 2999479.0,
38
+ "count": 60
39
  },
40
  "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 2.3580973148345947,
42
+ "min": 0.036438342183828354,
43
+ "max": 2.4295308589935303,
44
+ "count": 60
45
  },
46
  "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 1190.839111328125,
48
+ "min": 4.044655799865723,
49
+ "max": 1299.747802734375,
50
+ "count": 60
51
  },
52
  "Huggy.Environment.CumulativeReward.mean": {
53
+ "value": 3.5494548730330893,
54
+ "min": 1.6166541140090238,
55
+ "max": 3.972915584342325,
56
+ "count": 60
57
  },
58
  "Huggy.Environment.CumulativeReward.sum": {
59
+ "value": 1792.47471088171,
60
+ "min": 179.44860665500164,
61
+ "max": 2169.8267478346825,
62
+ "count": 60
63
  },
64
  "Huggy.Policy.ExtrinsicReward.mean": {
65
+ "value": 3.5494548730330893,
66
+ "min": 1.6166541140090238,
67
+ "max": 3.972915584342325,
68
+ "count": 60
69
  },
70
  "Huggy.Policy.ExtrinsicReward.sum": {
71
+ "value": 1792.47471088171,
72
+ "min": 179.44860665500164,
73
+ "max": 2169.8267478346825,
74
+ "count": 60
75
+ },
76
+ "Huggy.IsTraining.mean": {
77
+ "value": 1.0,
78
+ "min": 1.0,
79
+ "max": 1.0,
80
+ "count": 60
81
+ },
82
+ "Huggy.IsTraining.sum": {
83
+ "value": 1.0,
84
+ "min": 1.0,
85
+ "max": 1.0,
86
+ "count": 60
87
  },
88
  "Huggy.Losses.PolicyLoss.mean": {
89
+ "value": 0.011700202270779603,
90
+ "min": 0.00900723785996282,
91
+ "max": 0.015729527000221424,
92
+ "count": 48
93
  },
94
  "Huggy.Losses.PolicyLoss.sum": {
95
+ "value": 0.011700202270779603,
96
+ "min": 0.00900723785996282,
97
+ "max": 0.015729527000221424,
98
+ "count": 48
99
  },
100
  "Huggy.Losses.ValueLoss.mean": {
101
+ "value": 0.05095967883865039,
102
+ "min": 0.020325829510887464,
103
+ "max": 0.05095967883865039,
104
+ "count": 48
105
  },
106
  "Huggy.Losses.ValueLoss.sum": {
107
+ "value": 0.05095967883865039,
108
+ "min": 0.020325829510887464,
109
+ "max": 0.05095967883865039,
110
+ "count": 48
111
  },
112
  "Huggy.Policy.LearningRate.mean": {
113
+ "value": 4.583998472033342e-06,
114
+ "min": 4.583998472033342e-06,
115
+ "max": 0.00029383200205599985,
116
+ "count": 48
117
  },
118
  "Huggy.Policy.LearningRate.sum": {
119
+ "value": 4.583998472033342e-06,
120
+ "min": 4.583998472033342e-06,
121
+ "max": 0.00029383200205599985,
122
+ "count": 48
123
  },
124
  "Huggy.Policy.Epsilon.mean": {
125
+ "value": 0.10152796666666666,
126
+ "min": 0.10152796666666666,
127
+ "max": 0.197944,
128
+ "count": 48
129
  },
130
  "Huggy.Policy.Epsilon.sum": {
131
+ "value": 0.10152796666666666,
132
+ "min": 0.10152796666666666,
133
+ "max": 0.197944,
134
+ "count": 48
135
  },
136
  "Huggy.Policy.Beta.mean": {
137
+ "value": 8.624553666666679e-05,
138
+ "min": 8.624553666666679e-05,
139
+ "max": 0.004897405600000002,
140
+ "count": 48
141
  },
142
  "Huggy.Policy.Beta.sum": {
143
+ "value": 8.624553666666679e-05,
144
+ "min": 8.624553666666679e-05,
145
+ "max": 0.004897405600000002,
146
+ "count": 48
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1730735926",
152
  "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy3 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.5.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1730739278"
160
  },
161
+ "total": 3352.0195238860006,
162
  "count": 1,
163
+ "self": 0.32168215600086114,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05849840199971368,
167
  "count": 1,
168
+ "self": 0.05849840199971368
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 3351.639343328,
172
  "count": 1,
173
+ "self": 6.42968809166814,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.9763992649995998,
177
  "count": 1,
178
+ "self": 1.9763992649995998
179
  },
180
  "TrainerController.advance": {
181
+ "total": 3343.1023010693334,
182
+ "count": 346244,
183
+ "self": 5.913388387607483,
184
  "children": {
185
  "env_step": {
186
+ "total": 2378.616213645988,
187
+ "count": 346244,
188
+ "self": 1802.2615034367436,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 572.3139085806733,
192
+ "count": 346244,
193
+ "self": 21.671261441225397,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 550.642647139448,
197
+ "count": 334292,
198
+ "self": 550.642647139448
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 4.040801628570989,
204
+ "count": 346244,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 3340.9970179501197,
209
+ "count": 346244,
210
  "is_parallel": true,
211
+ "self": 1890.5932259452075,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0008735420005905326,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0002642150011524791,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0006093269994380535,
227
  "count": 2,
228
  "is_parallel": true,
229
+ "self": 0.0006093269994380535
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.021068762999675528,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0003229260000807699,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00016661999961797846,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00016661999961797846
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.020067968999683217,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.020067968999683217
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0005112480002935627,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00016482499995618127,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0003464230003373814,
259
  "count": 2,
260
  "is_parallel": true,
261
+ "self": 0.0003464230003373814
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 1450.4037920049122,
271
+ "count": 346243,
272
  "is_parallel": true,
273
+ "self": 39.693915219837436,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 75.67559444013114,
277
+ "count": 346243,
278
  "is_parallel": true,
279
+ "self": 75.67559444013114
280
  },
281
  "communicator.exchange": {
282
+ "total": 1243.948104283062,
283
+ "count": 346243,
284
  "is_parallel": true,
285
+ "self": 1243.948104283062
286
  },
287
  "steps_from_proto": {
288
+ "total": 91.08617806188158,
289
+ "count": 346243,
290
  "is_parallel": true,
291
+ "self": 34.960538926589834,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 56.12563913529175,
295
+ "count": 692486,
296
  "is_parallel": true,
297
+ "self": 56.12563913529175
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 958.572699035738,
311
+ "count": 346244,
312
+ "self": 9.520970072259843,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 218.84396512347212,
316
+ "count": 346244,
317
+ "self": 215.3858673074683,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 3.4580978160038285,
321
+ "count": 30,
322
+ "self": 3.4580978160038285
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 730.207763840006,
328
+ "count": 48,
329
+ "self": 625.0683427559998,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 105.13942108400624,
333
+ "count": 3600,
334
+ "self": 105.13942108400624
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 9.849991329247132e-07,
344
  "count": 1,
345
+ "self": 9.849991329247132e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.13095391699971515,
349
  "count": 1,
350
+ "self": 0.0025618249983381247,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.12839209200137702,
354
  "count": 1,
355
+ "self": 0.12839209200137702
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,112 +2,103 @@
2
  "Huggy": {
3
  "checkpoints": [
4
  {
5
- "steps": 199770,
6
- "file_path": "results/Huggy2/Huggy/Huggy-199770.onnx",
7
- "reward": 3.39975471060041,
8
- "creation_time": 1730731060.1453917,
9
  "auxillary_file_paths": [
10
- "results/Huggy2/Huggy/Huggy-199770.pt"
11
  ]
12
  },
13
  {
14
- "steps": 399945,
15
- "file_path": "results/Huggy2/Huggy/Huggy-399945.onnx",
16
- "reward": 4.066762394196278,
17
- "creation_time": 1730731261.578533,
18
  "auxillary_file_paths": [
19
- "results/Huggy2/Huggy/Huggy-399945.pt"
20
  ]
21
  },
22
  {
23
- "steps": 599989,
24
- "file_path": "results/Huggy2/Huggy/Huggy-599989.onnx",
25
- "reward": 3.99101983678752,
26
- "creation_time": 1730731467.9383197,
27
  "auxillary_file_paths": [
28
- "results/Huggy2/Huggy/Huggy-599989.pt"
29
  ]
30
  },
31
  {
32
- "steps": 799941,
33
- "file_path": "results/Huggy2/Huggy/Huggy-799941.onnx",
34
- "reward": 3.8657672925648954,
35
- "creation_time": 1730731671.378436,
36
  "auxillary_file_paths": [
37
- "results/Huggy2/Huggy/Huggy-799941.pt"
38
  ]
39
  },
40
  {
41
- "steps": 999942,
42
- "file_path": "results/Huggy2/Huggy/Huggy-999942.onnx",
43
- "reward": 3.7003243387573295,
44
- "creation_time": 1730731878.9401162,
45
  "auxillary_file_paths": [
46
- "results/Huggy2/Huggy/Huggy-999942.pt"
47
  ]
48
  },
49
  {
50
- "steps": 1199940,
51
- "file_path": "results/Huggy2/Huggy/Huggy-1199940.onnx",
52
- "reward": 3.719017545878887,
53
- "creation_time": 1730732087.9131427,
54
  "auxillary_file_paths": [
55
- "results/Huggy2/Huggy/Huggy-1199940.pt"
56
  ]
57
  },
58
  {
59
- "steps": 1399993,
60
- "file_path": "results/Huggy2/Huggy/Huggy-1399993.onnx",
61
- "reward": 3.2324970279421126,
62
- "creation_time": 1730732296.4197328,
63
  "auxillary_file_paths": [
64
- "results/Huggy2/Huggy/Huggy-1399993.pt"
65
  ]
66
  },
67
  {
68
- "steps": 1599948,
69
- "file_path": "results/Huggy2/Huggy/Huggy-1599948.onnx",
70
- "reward": 3.6305906583087237,
71
- "creation_time": 1730732502.534829,
72
  "auxillary_file_paths": [
73
- "results/Huggy2/Huggy/Huggy-1599948.pt"
74
  ]
75
  },
76
  {
77
- "steps": 1799990,
78
- "file_path": "results/Huggy2/Huggy/Huggy-1799990.onnx",
79
- "reward": 4.043395517282928,
80
- "creation_time": 1730732713.235032,
81
  "auxillary_file_paths": [
82
- "results/Huggy2/Huggy/Huggy-1799990.pt"
83
  ]
84
  },
85
  {
86
- "steps": 1999962,
87
- "file_path": "results/Huggy2/Huggy/Huggy-1999962.onnx",
88
- "reward": 4.06773927526654,
89
- "creation_time": 1730732922.5516403,
90
  "auxillary_file_paths": [
91
- "results/Huggy2/Huggy/Huggy-1999962.pt"
92
- ]
93
- },
94
- {
95
- "steps": 2000072,
96
- "file_path": "results/Huggy2/Huggy/Huggy-2000072.onnx",
97
- "reward": 4.080555761301959,
98
- "creation_time": 1730732922.6655488,
99
- "auxillary_file_paths": [
100
- "results/Huggy2/Huggy/Huggy-2000072.pt"
101
  ]
102
  }
103
  ],
104
  "final_checkpoint": {
105
- "steps": 2000072,
106
- "file_path": "results/Huggy2/Huggy.onnx",
107
- "reward": 4.080555761301959,
108
- "creation_time": 1730732922.6655488,
109
  "auxillary_file_paths": [
110
- "results/Huggy2/Huggy/Huggy-2000072.pt"
111
  ]
112
  }
113
  },
 
2
  "Huggy": {
3
  "checkpoints": [
4
  {
5
+ "steps": 2199943,
6
+ "file_path": "results/Huggy3/Huggy/Huggy-2199943.onnx",
7
+ "reward": 3.725997256151286,
8
+ "creation_time": 1730738367.0056586,
9
  "auxillary_file_paths": [
10
+ "results/Huggy3/Huggy/Huggy-2199943.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 2299931,
15
+ "file_path": "results/Huggy3/Huggy/Huggy-2299931.onnx",
16
+ "reward": 3.895195650735072,
17
+ "creation_time": 1730738485.737616,
18
  "auxillary_file_paths": [
19
+ "results/Huggy3/Huggy/Huggy-2299931.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 2399961,
24
+ "file_path": "results/Huggy3/Huggy/Huggy-2399961.onnx",
25
+ "reward": 3.6073987014750215,
26
+ "creation_time": 1730738591.4069104,
27
  "auxillary_file_paths": [
28
+ "results/Huggy3/Huggy/Huggy-2399961.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 2499799,
33
+ "file_path": "results/Huggy3/Huggy/Huggy-2499799.onnx",
34
+ "reward": 3.7827326296032338,
35
+ "creation_time": 1730738711.8428204,
36
  "auxillary_file_paths": [
37
+ "results/Huggy3/Huggy/Huggy-2499799.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 2599962,
42
+ "file_path": "results/Huggy3/Huggy/Huggy-2599962.onnx",
43
+ "reward": 3.667599461640522,
44
+ "creation_time": 1730738831.025522,
45
  "auxillary_file_paths": [
46
+ "results/Huggy3/Huggy/Huggy-2599962.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 2699735,
51
+ "file_path": "results/Huggy3/Huggy/Huggy-2699735.onnx",
52
+ "reward": 3.709622797753551,
53
+ "creation_time": 1730738934.156856,
54
  "auxillary_file_paths": [
55
+ "results/Huggy3/Huggy/Huggy-2699735.pt"
56
  ]
57
  },
58
  {
59
+ "steps": 2799586,
60
+ "file_path": "results/Huggy3/Huggy/Huggy-2799586.onnx",
61
+ "reward": 3.5667643091744847,
62
+ "creation_time": 1730739052.8364458,
63
  "auxillary_file_paths": [
64
+ "results/Huggy3/Huggy/Huggy-2799586.pt"
65
  ]
66
  },
67
  {
68
+ "steps": 2899484,
69
+ "file_path": "results/Huggy3/Huggy/Huggy-2899484.onnx",
70
+ "reward": 3.9963971534196068,
71
+ "creation_time": 1730739172.7037284,
72
  "auxillary_file_paths": [
73
+ "results/Huggy3/Huggy/Huggy-2899484.pt"
74
  ]
75
  },
76
  {
77
+ "steps": 2999479,
78
+ "file_path": "results/Huggy3/Huggy/Huggy-2999479.onnx",
79
+ "reward": 3.547086771758117,
80
+ "creation_time": 1730739277.846835,
81
  "auxillary_file_paths": [
82
+ "results/Huggy3/Huggy/Huggy-2999479.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 3000229,
87
+ "file_path": "results/Huggy3/Huggy/Huggy-3000229.onnx",
88
+ "reward": 3.5312195593184166,
89
+ "creation_time": 1730739278.0061228,
90
  "auxillary_file_paths": [
91
+ "results/Huggy3/Huggy/Huggy-3000229.pt"
 
 
 
 
 
 
 
 
 
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 3000229,
97
+ "file_path": "results/Huggy3/Huggy.onnx",
98
+ "reward": 3.5312195593184166,
99
+ "creation_time": 1730739278.0061228,
100
  "auxillary_file_paths": [
101
+ "results/Huggy3/Huggy/Huggy-3000229.pt"
102
  ]
103
  }
104
  },