Hugging Face's logo

neody88
/
ppo-Huggy

Reinforcement Learning
ml-agents
TensorBoard
ONNX
Huggy
deep-reinforcement-learning
ML-Agents-Huggy
Model card Files
xet
 Metrics Community
neody88 commited on
Commit
62c88f8
·
verified ·
1 Parent(s): 0ffaf1a

Huggy

Browse files
Files changed (30) hide show
  1. Huggy.onnx +3 -0
  2. Huggy/Huggy-1199920.onnx +3 -0
  3. Huggy/Huggy-1199920.pt +3 -0
  4. Huggy/Huggy-1399997.onnx +3 -0
  5. Huggy/Huggy-1399997.pt +3 -0
  6. Huggy/Huggy-1599971.onnx +3 -0
  7. Huggy/Huggy-1599971.pt +3 -0
  8. Huggy/Huggy-1799986.onnx +3 -0
  9. Huggy/Huggy-1799986.pt +3 -0
  10. Huggy/Huggy-199978.onnx +3 -0
  11. Huggy/Huggy-199978.pt +3 -0
  12. Huggy/Huggy-1999982.onnx +3 -0
  13. Huggy/Huggy-1999982.pt +3 -0
  14. Huggy/Huggy-2000074.onnx +3 -0
  15. Huggy/Huggy-2000074.pt +3 -0
  16. Huggy/Huggy-399966.onnx +3 -0
  17. Huggy/Huggy-399966.pt +3 -0
  18. Huggy/Huggy-599980.onnx +3 -0
  19. Huggy/Huggy-599980.pt +3 -0
  20. Huggy/Huggy-799906.onnx +3 -0
  21. Huggy/Huggy-799906.pt +3 -0
  22. Huggy/Huggy-999893.onnx +3 -0
  23. Huggy/Huggy-999893.pt +3 -0
  24. Huggy/checkpoint.pt +1 -1
  25. Huggy/events.out.tfevents.1744792364.c42b483351b2.10964.0 +3 -0
  26. config.json +1 -1
  27. configuration.yaml +1 -1
  28. run_logs/Player-0.log +15 -18
  29. run_logs/timers.json +168 -168
  30. run_logs/training_status.json +101 -11
Huggy.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a32cb1ce7a59c82780c8fc50e5ad51274705e887b726e5f0621c4207b7e31394
3
+ size 2274020
Huggy/Huggy-1199920.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc77ffa27956b7f2796c5d039691af9e03879673e3a5a5d6c1c685f56039ca57
3
+ size 2274020
Huggy/Huggy-1199920.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3857a078bae1e9e8fe5e1a5db8b55b635efaa1145efce6253eb857d950a4c8
3
+ size 13509473
Huggy/Huggy-1399997.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8eec103caa93932fe42782434c12db5ea37963707d78901cc6d72fc1ec4ec26
3
+ size 2274020
Huggy/Huggy-1399997.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0743e85de316a09dfae9c0e1c09a899df7d3f1d2edc901119ef5b74116da23b
3
+ size 13509473
Huggy/Huggy-1599971.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c42859e21bac53d650c6627dc45360b96ce2e2f0c3cfda6f44b9fafff873dc
3
+ size 2274020
Huggy/Huggy-1599971.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff5c4f1bff7be651922d4cab62f25494043bbbeae9200541ab62a6429869515
3
+ size 13509473
Huggy/Huggy-1799986.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c50ee4ce63039c636dfef98269860027b76ca28923d59628bfcc30a1f5ff02c3
3
+ size 2274020
Huggy/Huggy-1799986.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:368af9420b6e79f38f60928a708adeface72c955fbb2b33b6f3ec99ca314249b
3
+ size 13509473
Huggy/Huggy-199978.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921aafbb268d147b4ac9575cc8eb69a8527fad4afcae2ff6c3ecd29bb6a1fd8b
3
+ size 2274020
Huggy/Huggy-199978.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab10c2723bdf3b0eadfdfa5fb6b242e5c7deed00e1faa1005fc7e5f5bec2648a
3
+ size 13509388
Huggy/Huggy-1999982.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9a348bc524e0523518fb8ff7e4edc2da03eefbac1017613de5555dff1793da
3
+ size 2274020
Huggy/Huggy-1999982.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:007d1a0d1f561daeb1a55f08a467709a610ece26d2a8f4267237bc327a396592
3
+ size 13509473
Huggy/Huggy-2000074.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a32cb1ce7a59c82780c8fc50e5ad51274705e887b726e5f0621c4207b7e31394
3
+ size 2274020
Huggy/Huggy-2000074.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a51b9de95a8e4a69344f545a90a2ea2129b871397c65391bde95cdf94256474
3
+ size 13509473
Huggy/Huggy-399966.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dadbc9fdd9d3e39ad54c3646b4d9f0638c8300d80f0b84da5580d90a34ba2ce
3
+ size 2274020
Huggy/Huggy-399966.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3992ac08c9bdce42d5add98f4ca0798b513b42dd911f0c8d9c155363d9e2af5f
3
+ size 13509388
Huggy/Huggy-599980.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7beb74a0a84b15fe350fcfe59cd0917a379ebafab960c95edce88828203776e5
3
+ size 2274020
Huggy/Huggy-599980.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152baa632b2c9a536066c5a59901228464ef3203acca1f7f4c42463f0fcd5efa
3
+ size 13509388
Huggy/Huggy-799906.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af54d627171e43bdcd7bac225d1be24074ef18944f72b82c0f4c72114c044ba
3
+ size 2274020
Huggy/Huggy-799906.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f31aa2e5529abc92121ef299f28a1e327bd26a0cc115cc22b91d8dcfdcfaec
3
+ size 13509388
Huggy/Huggy-999893.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4926429a862fcdb21c76a4a33c1bc70970a33cfdc30272be65c652d471967d6e
3
+ size 2274020
Huggy/Huggy-999893.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e85c9dedea69791cb415c55aef63255aa7523697b755e987054d09142161f4
3
+ size 13509388
Huggy/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:239b22349b947e3906b8b22204903948317ccd197627177a93df8d11f5ad43c2
3
  size 13509218
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abdd01d0a4d02927b172ca9a8fccf9b56e82ef6fcfec2ac7f17697259bc114bf
3
  size 13509218
Huggy/events.out.tfevents.1744792364.c42b483351b2.10964.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986a2be6ec774477e5e1a22a1a253a0ca8024f73c629519e3c57c42071b02797
3
+ size 265601
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": 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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -70,7 +70,7 @@ checkpoint_settings:
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
- force: false
74
  train_model: false
75
  inference: false
76
  results_dir: results
 
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
+ force: true
74
  train_model: false
75
  inference: false
76
  results_dir: results
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: 0.844212 ms
82
  requesting resize 84 x 84
83
  Setting up 1 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]: 5943 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 128 B
97
  Overflow Count 0
98
  [ALLOC_TEMP_Loading.PreloadManager]
99
  Initial Block Size 256.0 KB
@@ -201,22 +198,22 @@ Memory Statistics:
201
  Peak Allocated Bytes 0 B
202
  Overflow Count 0
203
  [ALLOC_DEFAULT] Dual Thread Allocator
204
- Peak main deferred allocation count 190
205
  [ALLOC_BUCKET]
206
  Large Block size 4.0 MB
207
  Used Block count 1
208
  Peak Allocated bytes 1.4 MB
209
  [ALLOC_DEFAULT_MAIN]
210
- Peak usage frame count: [16.0 MB-32.0 MB]: 5944 frames
211
  Requested Block Size 16.0 MB
212
  Peak Block count 1
213
- Peak Allocated memory 22.1 MB
214
  Peak Large allocation bytes 16.0 MB
215
  [ALLOC_DEFAULT_THREAD]
216
- Peak usage frame count: [1.0 MB-2.0 MB]: 1 frames, [2.0 MB-4.0 MB]: 5943 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 2.4 MB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_TEMP_JOB_1_FRAME]
222
  Initial Block Size 2.0 MB
@@ -245,13 +242,13 @@ Memory Statistics:
245
  Used Block count 1
246
  Peak Allocated bytes 1.4 MB
247
  [ALLOC_GFX_MAIN]
248
- Peak usage frame count: [32.0 KB-64.0 KB]: 5943 frames, [64.0 KB-128.0 KB]: 1 frames
249
  Requested Block Size 16.0 MB
250
  Peak Block count 1
251
  Peak Allocated memory 65.6 KB
252
  Peak Large allocation bytes 0 B
253
  [ALLOC_GFX_THREAD]
254
- Peak usage frame count: [64.0 KB-128.0 KB]: 5944 frames
255
  Requested Block Size 16.0 MB
256
  Peak Block count 1
257
  Peak Allocated memory 81.8 KB
@@ -263,13 +260,13 @@ Memory Statistics:
263
  Used Block count 1
264
  Peak Allocated bytes 1.4 MB
265
  [ALLOC_CACHEOBJECTS_MAIN]
266
- Peak usage frame count: [1.0 MB-2.0 MB]: 5943 frames, [16.0 MB-32.0 MB]: 1 frames
267
  Requested Block Size 4.0 MB
268
  Peak Block count 2
269
  Peak Allocated memory 30.6 MB
270
  Peak Large allocation bytes 24.9 MB
271
  [ALLOC_CACHEOBJECTS_THREAD]
272
- Peak usage frame count: [0.5 MB-1.0 MB]: 5943 frames, [2.0 MB-4.0 MB]: 1 frames
273
  Requested Block Size 4.0 MB
274
  Peak Block count 1
275
  Peak Allocated memory 2.6 MB
@@ -281,13 +278,13 @@ Memory Statistics:
281
  Used Block count 1
282
  Peak Allocated bytes 1.4 MB
283
  [ALLOC_TYPETREE_MAIN]
284
- Peak usage frame count: [0-1.0 KB]: 5944 frames
285
  Requested Block Size 2.0 MB
286
  Peak Block count 1
287
  Peak Allocated memory 1.0 KB
288
  Peak Large allocation bytes 0 B
289
  [ALLOC_TYPETREE_THREAD]
290
- Peak usage frame count: [4.0 KB-8.0 KB]: 5944 frames
291
  Requested Block Size 2.0 MB
292
  Peak Block count 1
293
  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 0.097 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: 0.775630 ms
79
  requesting resize 84 x 84
80
  Setting up 1 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]: 26753 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 192 B
94
  Overflow Count 0
95
  [ALLOC_TEMP_Loading.PreloadManager]
96
  Initial Block Size 256.0 KB
 
198
  Peak Allocated Bytes 0 B
199
  Overflow Count 0
200
  [ALLOC_DEFAULT] Dual Thread Allocator
201
+ Peak main deferred allocation count 153
202
  [ALLOC_BUCKET]
203
  Large Block size 4.0 MB
204
  Used Block count 1
205
  Peak Allocated bytes 1.4 MB
206
  [ALLOC_DEFAULT_MAIN]
207
+ Peak usage frame count: [16.0 MB-32.0 MB]: 26754 frames
208
  Requested Block Size 16.0 MB
209
  Peak Block count 1
210
+ Peak Allocated memory 24.1 MB
211
  Peak Large allocation bytes 16.0 MB
212
  [ALLOC_DEFAULT_THREAD]
213
+ Peak usage frame count: [1.0 MB-2.0 MB]: 26753 frames, [2.0 MB-4.0 MB]: 1 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 2.2 MB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_TEMP_JOB_1_FRAME]
219
  Initial Block Size 2.0 MB
 
242
  Used Block count 1
243
  Peak Allocated bytes 1.4 MB
244
  [ALLOC_GFX_MAIN]
245
+ Peak usage frame count: [32.0 KB-64.0 KB]: 26753 frames, [64.0 KB-128.0 KB]: 1 frames
246
  Requested Block Size 16.0 MB
247
  Peak Block count 1
248
  Peak Allocated memory 65.6 KB
249
  Peak Large allocation bytes 0 B
250
  [ALLOC_GFX_THREAD]
251
+ Peak usage frame count: [64.0 KB-128.0 KB]: 26754 frames
252
  Requested Block Size 16.0 MB
253
  Peak Block count 1
254
  Peak Allocated memory 81.8 KB
 
260
  Used Block count 1
261
  Peak Allocated bytes 1.4 MB
262
  [ALLOC_CACHEOBJECTS_MAIN]
263
+ Peak usage frame count: [1.0 MB-2.0 MB]: 26753 frames, [16.0 MB-32.0 MB]: 1 frames
264
  Requested Block Size 4.0 MB
265
  Peak Block count 2
266
  Peak Allocated memory 30.6 MB
267
  Peak Large allocation bytes 24.9 MB
268
  [ALLOC_CACHEOBJECTS_THREAD]
269
+ Peak usage frame count: [0.5 MB-1.0 MB]: 26753 frames, [2.0 MB-4.0 MB]: 1 frames
270
  Requested Block Size 4.0 MB
271
  Peak Block count 1
272
  Peak Allocated memory 2.6 MB
 
278
  Used Block count 1
279
  Peak Allocated bytes 1.4 MB
280
  [ALLOC_TYPETREE_MAIN]
281
+ Peak usage frame count: [0-1.0 KB]: 26754 frames
282
  Requested Block Size 2.0 MB
283
  Peak Block count 1
284
  Peak Allocated memory 1.0 KB
285
  Peak Large allocation bytes 0 B
286
  [ALLOC_TYPETREE_THREAD]
287
+ Peak usage frame count: [4.0 KB-8.0 KB]: 26754 frames
288
  Requested Block Size 2.0 MB
289
  Peak Block count 1
290
  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": 1.4237254858016968,
6
- "min": 1.4187397956848145,
7
- "max": 1.4257341623306274,
8
- "count": 8
9
  },
10
  "Huggy.Policy.Entropy.sum": {
11
- "value": 70717.8671875,
12
- "min": 69900.3671875,
13
- "max": 77034.734375,
14
- "count": 8
15
  },
16
  "Huggy.Environment.EpisodeLength.mean": {
17
- "value": 130.48812664907652,
18
- "min": 130.48812664907652,
19
- "max": 389.13953488372096,
20
- "count": 8
21
  },
22
  "Huggy.Environment.EpisodeLength.sum": {
23
- "value": 49455.0,
24
- "min": 49455.0,
25
- "max": 50199.0,
26
- "count": 8
27
  },
28
  "Huggy.Step.mean": {
29
- "value": 399901.0,
30
- "min": 49593.0,
31
- "max": 399901.0,
32
- "count": 8
33
  },
34
  "Huggy.Step.sum": {
35
- "value": 399901.0,
36
- "min": 49593.0,
37
- "max": 399901.0,
38
- "count": 8
39
  },
40
  "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
- "value": 1.951921820640564,
42
- "min": 0.011517061851918697,
43
- "max": 1.951921820640564,
44
- "count": 8
45
  },
46
  "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
- "value": 739.7783813476562,
48
- "min": 1.4741839170455933,
49
- "max": 739.7783813476562,
50
- "count": 8
51
  },
52
  "Huggy.Environment.CumulativeReward.mean": {
53
- "value": 3.6024209275094687,
54
- "min": 1.617667007027194,
55
- "max": 3.6398176294894307,
56
- "count": 8
57
  },
58
  "Huggy.Environment.CumulativeReward.sum": {
59
- "value": 1365.3175315260887,
60
- "min": 207.06137689948082,
61
- "max": 1365.3175315260887,
62
- "count": 8
63
  },
64
  "Huggy.Policy.ExtrinsicReward.mean": {
65
- "value": 3.6024209275094687,
66
- "min": 1.617667007027194,
67
- "max": 3.6398176294894307,
68
- "count": 8
69
  },
70
  "Huggy.Policy.ExtrinsicReward.sum": {
71
- "value": 1365.3175315260887,
72
- "min": 207.06137689948082,
73
- "max": 1365.3175315260887,
74
- "count": 8
75
  },
76
  "Huggy.Losses.PolicyLoss.mean": {
77
- "value": 0.016865756332279287,
78
- "min": 0.012512484227651537,
79
- "max": 0.017876650334801524,
80
- "count": 8
81
  },
82
  "Huggy.Losses.PolicyLoss.sum": {
83
- "value": 0.05059726899683786,
84
- "min": 0.025024968455303075,
85
- "max": 0.05362995100440457,
86
- "count": 8
87
  },
88
  "Huggy.Losses.ValueLoss.mean": {
89
- "value": 0.049976338942845665,
90
- "min": 0.024112095156063634,
91
- "max": 0.049976338942845665,
92
- "count": 8
93
  },
94
  "Huggy.Losses.ValueLoss.sum": {
95
- "value": 0.149929016828537,
96
- "min": 0.04822419031212727,
97
- "max": 0.149929016828537,
98
- "count": 8
99
  },
100
  "Huggy.Policy.LearningRate.mean": {
101
- "value": 0.0002443153685615499,
102
- "min": 0.0002443153685615499,
103
- "max": 0.00029529247656917497,
104
- "count": 8
105
  },
106
  "Huggy.Policy.LearningRate.sum": {
107
- "value": 0.0007329461056846498,
108
- "min": 0.0005040522319826001,
109
- "max": 0.0008439364686878498,
110
- "count": 8
111
  },
112
  "Huggy.Policy.Epsilon.mean": {
113
- "value": 0.18143845,
114
- "min": 0.18143845,
115
- "max": 0.1984308250000001,
116
- "count": 8
117
  },
118
  "Huggy.Policy.Epsilon.sum": {
119
- "value": 0.54431535,
120
- "min": 0.36801740000000005,
121
- "max": 0.5813121500000001,
122
- "count": 8
123
  },
124
  "Huggy.Policy.Beta.mean": {
125
- "value": 0.004073778654999999,
126
- "min": 0.004073778654999999,
127
- "max": 0.0049216981675,
128
- "count": 8
129
  },
130
  "Huggy.Policy.Beta.sum": {
131
- "value": 0.012221335964999996,
132
- "min": 0.008404068259999998,
133
- "max": 0.014067476285000002,
134
- "count": 8
135
  },
136
  "Huggy.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 8
141
  },
142
  "Huggy.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 8
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1744790835",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1744791375"
160
  },
161
- "total": 539.7686826920001,
162
  "count": 1,
163
- "self": 0.49820525200016164,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.025035699000000022,
167
  "count": 1,
168
- "self": 0.025035699000000022
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 539.2454417409999,
172
  "count": 1,
173
- "self": 0.9150932890020158,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.1461101390000294,
177
  "count": 1,
178
- "self": 3.1461101390000294
179
  },
180
  "TrainerController.advance": {
181
- "total": 535.1834073909979,
182
- "count": 50661,
183
- "self": 0.964010304000567,
184
  "children": {
185
  "env_step": {
186
- "total": 428.22337060799623,
187
- "count": 50661,
188
- "self": 332.99161521696305,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 94.66671449703176,
192
- "count": 50661,
193
- "self": 3.494855064047897,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 91.17185943298387,
197
- "count": 49526,
198
- "self": 91.17185943298387
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.5650408940014131,
204
- "count": 50660,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 537.664546980026,
209
- "count": 50660,
210
  "is_parallel": true,
211
- "self": 265.180672031981,
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": 0.001118116000043301,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.00040940900021269044,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0007087069998306106,
227
  "count": 2,
228
  "is_parallel": true,
229
- "self": 0.0007087069998306106
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.02912323199984712,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0003346659998442192,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00023127100007513945,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00023127100007513945
244
  },
245
  "communicator.exchange": {
246
- "total": 0.027862407999919014,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.027862407999919014
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0006948870000087481,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00020072799998160917,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.000494159000027139,
259
  "count": 2,
260
  "is_parallel": true,
261
- "self": 0.000494159000027139
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 272.483874948045,
271
- "count": 50659,
272
  "is_parallel": true,
273
- "self": 8.22380441201858,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 18.51504337200322,
277
- "count": 50659,
278
  "is_parallel": true,
279
- "self": 18.51504337200322
280
  },
281
  "communicator.exchange": {
282
- "total": 226.2741081289953,
283
- "count": 50659,
284
  "is_parallel": true,
285
- "self": 226.2741081289953
286
  },
287
  "steps_from_proto": {
288
- "total": 19.47091903502792,
289
- "count": 50659,
290
  "is_parallel": true,
291
- "self": 7.264775501045506,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 12.206143533982413,
295
- "count": 101318,
296
  "is_parallel": true,
297
- "self": 12.206143533982413
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 105.9960264790011,
311
- "count": 50660,
312
- "self": 1.3890160760363415,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 29.481606141964903,
316
- "count": 50660,
317
- "self": 29.180282277964807,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.30132386400009636,
321
- "count": 2,
322
- "self": 0.30132386400009636
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 75.12540426099986,
328
- "count": 21,
329
- "self": 60.10328774899699,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 15.022116512002867,
333
- "count": 630,
334
- "self": 15.022116512002867
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.3199999102653237e-06,
344
  "count": 1,
345
- "self": 1.3199999102653237e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.0008296020000670978,
349
  "count": 1,
350
- "self": 3.520799987200007e-05,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.0007943940001950978,
354
  "count": 1,
355
- "self": 0.0007943940001950978
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "Huggy.Policy.Entropy.mean": {
5
+ "value": 1.408053994178772,
6
+ "min": 1.408053994178772,
7
+ "max": 1.4261473417282104,
8
+ "count": 40
9
  },
10
  "Huggy.Policy.Entropy.sum": {
11
+ "value": 71102.5,
12
+ "min": 68120.15625,
13
+ "max": 78536.3203125,
14
+ "count": 40
15
  },
16
  "Huggy.Environment.EpisodeLength.mean": {
17
+ "value": 73.15851851851852,
18
+ "min": 73.15851851851852,
19
+ "max": 385.9307692307692,
20
+ "count": 40
21
  },
22
  "Huggy.Environment.EpisodeLength.sum": {
23
+ "value": 49382.0,
24
+ "min": 49263.0,
25
+ "max": 50171.0,
26
+ "count": 40
27
  },
28
  "Huggy.Step.mean": {
29
+ "value": 1999982.0,
30
+ "min": 49985.0,
31
+ "max": 1999982.0,
32
+ "count": 40
33
  },
34
  "Huggy.Step.sum": {
35
+ "value": 1999982.0,
36
+ "min": 49985.0,
37
+ "max": 1999982.0,
38
+ "count": 40
39
  },
40
  "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 2.4577407836914062,
42
+ "min": 0.09748142212629318,
43
+ "max": 2.4878804683685303,
44
+ "count": 40
45
  },
46
  "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 1658.9749755859375,
48
+ "min": 12.575103759765625,
49
+ "max": 1658.9749755859375,
50
+ "count": 40
51
  },
52
  "Huggy.Environment.CumulativeReward.mean": {
53
+ "value": 3.828570303475415,
54
+ "min": 1.7983498527098072,
55
+ "max": 3.994807656498643,
56
+ "count": 40
57
  },
58
  "Huggy.Environment.CumulativeReward.sum": {
59
+ "value": 2584.2849548459053,
60
+ "min": 231.98713099956512,
61
+ "max": 2615.4127359986305,
62
+ "count": 40
63
  },
64
  "Huggy.Policy.ExtrinsicReward.mean": {
65
+ "value": 3.828570303475415,
66
+ "min": 1.7983498527098072,
67
+ "max": 3.994807656498643,
68
+ "count": 40
69
  },
70
  "Huggy.Policy.ExtrinsicReward.sum": {
71
+ "value": 2584.2849548459053,
72
+ "min": 231.98713099956512,
73
+ "max": 2615.4127359986305,
74
+ "count": 40
75
  },
76
  "Huggy.Losses.PolicyLoss.mean": {
77
+ "value": 0.015204337436792533,
78
+ "min": 0.013891695984784746,
79
+ "max": 0.020601315647743628,
80
+ "count": 40
81
  },
82
  "Huggy.Losses.PolicyLoss.sum": {
83
+ "value": 0.0456130123103776,
84
+ "min": 0.02778339196956949,
85
+ "max": 0.06180394694323088,
86
+ "count": 40
87
  },
88
  "Huggy.Losses.ValueLoss.mean": {
89
+ "value": 0.05927399475541379,
90
+ "min": 0.02234348977605502,
91
+ "max": 0.061774766569336254,
92
+ "count": 40
93
  },
94
  "Huggy.Losses.ValueLoss.sum": {
95
+ "value": 0.17782198426624138,
96
+ "min": 0.04468697955211004,
97
+ "max": 0.18532429970800876,
98
+ "count": 40
99
  },
100
  "Huggy.Policy.LearningRate.mean": {
101
+ "value": 3.859748713449993e-06,
102
+ "min": 3.859748713449993e-06,
103
+ "max": 0.00029531535156155004,
104
+ "count": 40
105
  },
106
  "Huggy.Policy.LearningRate.sum": {
107
+ "value": 1.1579246140349978e-05,
108
+ "min": 1.1579246140349978e-05,
109
+ "max": 0.0008439259686913499,
110
+ "count": 40
111
  },
112
  "Huggy.Policy.Epsilon.mean": {
113
+ "value": 0.10128655000000002,
114
+ "min": 0.10128655000000002,
115
+ "max": 0.19843845000000004,
116
+ "count": 40
117
  },
118
  "Huggy.Policy.Epsilon.sum": {
119
+ "value": 0.30385965000000004,
120
+ "min": 0.20771255000000005,
121
+ "max": 0.5813086500000001,
122
+ "count": 40
123
  },
124
  "Huggy.Policy.Beta.mean": {
125
+ "value": 7.419884499999989e-05,
126
+ "min": 7.419884499999989e-05,
127
+ "max": 0.0049220786549999986,
128
+ "count": 40
129
  },
130
  "Huggy.Policy.Beta.sum": {
131
+ "value": 0.00022259653499999966,
132
+ "min": 0.00022259653499999966,
133
+ "max": 0.014067301635000001,
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": "1744792364",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
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 --force",
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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1744794840"
160
  },
161
+ "total": 2476.7697507420003,
162
  "count": 1,
163
+ "self": 0.43412296800079275,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.02036751599962372,
167
  "count": 1,
168
+ "self": 0.02036751599962372
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 2476.315260258,
172
  "count": 1,
173
+ "self": 4.47991132601328,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.9490104039996368,
177
  "count": 1,
178
+ "self": 1.9490104039996368
179
  },
180
  "TrainerController.advance": {
181
+ "total": 2469.7662575189865,
182
+ "count": 233252,
183
+ "self": 4.503267734934525,
184
  "children": {
185
  "env_step": {
186
+ "total": 1979.9687515009205,
187
+ "count": 233252,
188
+ "self": 1550.6323515788004,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 426.60236642703103,
192
+ "count": 233252,
193
+ "self": 15.803257024163486,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 410.79910940286754,
197
+ "count": 222948,
198
+ "self": 410.79910940286754
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 2.7340334950890792,
204
+ "count": 233252,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 2468.7206049879187,
209
+ "count": 233252,
210
  "is_parallel": true,
211
+ "self": 1202.0010912610142,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0009543520000079297,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0003086520000579185,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0006456999999500113,
227
  "count": 2,
228
  "is_parallel": true,
229
+ "self": 0.0006456999999500113
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.02970595900023909,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0002678399996511871,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0002947520001725934,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0002947520001725934
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.02832397400015907,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.02832397400015907
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0008193930002562411,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00019345100054124487,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0006259419997149962,
259
  "count": 2,
260
  "is_parallel": true,
261
+ "self": 0.0006259419997149962
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 1266.7195137269046,
271
+ "count": 233251,
272
  "is_parallel": true,
273
+ "self": 36.92599578915997,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 82.89408573577794,
277
+ "count": 233251,
278
  "is_parallel": true,
279
+ "self": 82.89408573577794
280
  },
281
  "communicator.exchange": {
282
+ "total": 1058.9048166521202,
283
+ "count": 233251,
284
  "is_parallel": true,
285
+ "self": 1058.9048166521202
286
  },
287
  "steps_from_proto": {
288
+ "total": 87.99461554984646,
289
+ "count": 233251,
290
  "is_parallel": true,
291
+ "self": 32.931983125924944,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 55.062632423921514,
295
+ "count": 466502,
296
  "is_parallel": true,
297
+ "self": 55.062632423921514
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 485.29423828313156,
311
+ "count": 233252,
312
+ "self": 6.212426161245276,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 174.0844045908848,
316
+ "count": 233252,
317
+ "self": 172.84049520888402,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 1.2439093820007656,
321
+ "count": 10,
322
+ "self": 1.2439093820007656
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 304.9974075310015,
328
+ "count": 97,
329
+ "self": 241.74839912600646,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 63.24900840499504,
333
+ "count": 2910,
334
+ "self": 63.24900840499504
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 8.429997251369059e-07,
344
  "count": 1,
345
+ "self": 8.429997251369059e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.12008016600066185,
349
  "count": 1,
350
+ "self": 0.0019248830012656981,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.11815528299939615,
354
  "count": 1,
355
+ "self": 0.11815528299939615
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,24 +2,114 @@
2
  "Huggy": {
3
  "checkpoints": [
4
  {
5
- "steps": 199647,
6
- "file_path": "results/Huggy2/Huggy/Huggy-199647.onnx",
7
- "reward": 3.374940789514972,
8
- "creation_time": 1744791075.6793284,
9
  "auxillary_file_paths": [
10
- "results/Huggy2/Huggy/Huggy-199647.pt"
11
  ]
12
  },
13
  {
14
- "steps": 399901,
15
- "file_path": "results/Huggy2/Huggy/Huggy-399901.onnx",
16
- "reward": 3.374084941486814,
17
- "creation_time": 1744791320.9772274,
18
  "auxillary_file_paths": [
19
- "results/Huggy2/Huggy/Huggy-399901.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  ]
21
  }
22
- ]
 
 
 
 
 
 
 
 
 
23
  },
24
  "metadata": {
25
  "stats_format_version": "0.3.0",
 
2
  "Huggy": {
3
  "checkpoints": [
4
  {
5
+ "steps": 199978,
6
+ "file_path": "results/Huggy2/Huggy/Huggy-199978.onnx",
7
+ "reward": 3.423110367888111,
8
+ "creation_time": 1744792608.026579,
9
  "auxillary_file_paths": [
10
+ "results/Huggy2/Huggy/Huggy-199978.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 399966,
15
+ "file_path": "results/Huggy2/Huggy/Huggy-399966.onnx",
16
+ "reward": 3.6031065613031386,
17
+ "creation_time": 1744792849.9829512,
18
  "auxillary_file_paths": [
19
+ "results/Huggy2/Huggy/Huggy-399966.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 599980,
24
+ "file_path": "results/Huggy2/Huggy/Huggy-599980.onnx",
25
+ "reward": 3.618810792764028,
26
+ "creation_time": 1744793096.6683683,
27
+ "auxillary_file_paths": [
28
+ "results/Huggy2/Huggy/Huggy-599980.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 799906,
33
+ "file_path": "results/Huggy2/Huggy/Huggy-799906.onnx",
34
+ "reward": 4.030083014648788,
35
+ "creation_time": 1744793342.2883441,
36
+ "auxillary_file_paths": [
37
+ "results/Huggy2/Huggy/Huggy-799906.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 999893,
42
+ "file_path": "results/Huggy2/Huggy/Huggy-999893.onnx",
43
+ "reward": 3.816746229178285,
44
+ "creation_time": 1744793594.7907786,
45
+ "auxillary_file_paths": [
46
+ "results/Huggy2/Huggy/Huggy-999893.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 1199920,
51
+ "file_path": "results/Huggy2/Huggy/Huggy-1199920.onnx",
52
+ "reward": 4.086365943085657,
53
+ "creation_time": 1744793846.8600254,
54
+ "auxillary_file_paths": [
55
+ "results/Huggy2/Huggy/Huggy-1199920.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 1399997,
60
+ "file_path": "results/Huggy2/Huggy/Huggy-1399997.onnx",
61
+ "reward": 3.4520819266637166,
62
+ "creation_time": 1744794096.2904313,
63
+ "auxillary_file_paths": [
64
+ "results/Huggy2/Huggy/Huggy-1399997.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 1599971,
69
+ "file_path": "results/Huggy2/Huggy/Huggy-1599971.onnx",
70
+ "reward": 3.947774065348009,
71
+ "creation_time": 1744794341.42919,
72
+ "auxillary_file_paths": [
73
+ "results/Huggy2/Huggy/Huggy-1599971.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 1799986,
78
+ "file_path": "results/Huggy2/Huggy/Huggy-1799986.onnx",
79
+ "reward": 3.87702033149785,
80
+ "creation_time": 1744794591.1639597,
81
+ "auxillary_file_paths": [
82
+ "results/Huggy2/Huggy/Huggy-1799986.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 1999982,
87
+ "file_path": "results/Huggy2/Huggy/Huggy-1999982.onnx",
88
+ "reward": 3.84935052211468,
89
+ "creation_time": 1744794840.2323465,
90
+ "auxillary_file_paths": [
91
+ "results/Huggy2/Huggy/Huggy-1999982.pt"
92
+ ]
93
+ },
94
+ {
95
+ "steps": 2000074,
96
+ "file_path": "results/Huggy2/Huggy/Huggy-2000074.onnx",
97
+ "reward": 3.863086964144851,
98
+ "creation_time": 1744794840.3609204,
99
+ "auxillary_file_paths": [
100
+ "results/Huggy2/Huggy/Huggy-2000074.pt"
101
  ]
102
  }
103
+ ],
104
+ "final_checkpoint": {
105
+ "steps": 2000074,
106
+ "file_path": "results/Huggy2/Huggy.onnx",
107
+ "reward": 3.863086964144851,
108
+ "creation_time": 1744794840.3609204,
109
+ "auxillary_file_paths": [
110
+ "results/Huggy2/Huggy/Huggy-2000074.pt"
111
+ ]
112
+ }
113
  },
114
  "metadata": {
115
  "stats_format_version": "0.3.0",