Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1688878853.snowflake

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440f3682432896f32d41a122192825803e3ee49b39e95ec081ddda42a7105474
+size 4526

.summary/0/events.out.tfevents.1688879192.snowflake

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e11fa2e82dffd054eaec8e49fef1ca9028159b42f5eb78b05f554c8e50e21c
+size 16844

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 3.97 +/- 0.26
+      value: 3.94 +/- 0.61
       name: mean_reward
       verified: false
 ---

checkpoint_p0/checkpoint_000000000_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd947d392e08465a103e5c4243c9f5c9277099b2304fc1ba5c09a1ad1867e86d
-size 14040084
+oid sha256:f546634a38180cb4a57aec199213e3b845b90a5ebb8206ddaa081c2c9d4ba854
+size 41231900

checkpoint_p0/checkpoint_000466273_3819708416.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad911b64da964df63b10a6c450dbf67193cd2e4eb0163db5a9e46fa8946e6efb
+size 41232964

config.json

@@ -63,7 +63,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 10,
   "heartbeat_reporting_interval": 300,
-  "train_for_env_steps": 20000,
+  "train_for_env_steps": 20,
   "train_for_seconds": 1000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,
@@ -130,8 +130,8 @@
   "cli_args": {},
   "git_hash": "0401714b01ee832562a0930e3744117f1ba51e10",
   "git_repo_name": "https://github.com/tenkara/HF-DeepRL.git",
-  "command_line": "--env=doom_health_gathering_supreme --train_for_env_steps=2000000",
-  "env_gpu_observations": true,
+  "command_line": "--env=doom_health_gathering_supreme --train_for_env_steps=20",
   "lr_adaptive_min": 1e-06,
-  "lr_adaptive_max": 0.01
+  "lr_adaptive_max": 0.01,
+  "env_gpu_observations": true
 }

git.diff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72fd3c87dce5ac3afe8766d7caea74393f7369ee1e0f7a4adff360d24911b999
-size 211383812
+oid sha256:a8b97eeeb6021f14696de0a65f48c22164dbc358a9a63500114e3970e8a301d7
+size 211342672

sf_log.txt

@@ -701,3 +701,278 @@ Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
 [2023-07-08 22:48:57,115][18621] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth...
 [2023-07-08 22:48:57,152][18621] Stopping LearnerWorker_p0...
 [2023-07-08 22:48:57,152][18621] Loop learner_proc0_evt_loop terminating...
+[2023-07-08 23:01:01,233][19220] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 23:01:01,234][19220] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-07-08 23:01:01,277][19220] Num visible devices: 1
+[2023-07-08 23:01:01,412][19220] Setting fixed seed 42
+[2023-07-08 23:01:01,412][19220] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 23:01:01,412][19220] Initializing actor-critic model on device cuda:0
+[2023-07-08 23:01:01,413][19220] RunningMeanStd input shape: (3, 72, 128)
+[2023-07-08 23:01:01,413][19220] RunningMeanStd input shape: (1,)
+[2023-07-08 23:01:01,420][19220] ConvEncoder: input_channels=3
+[2023-07-08 23:01:01,502][19241] Worker 0 uses CPU cores [0]
+[2023-07-08 23:01:01,550][19242] Worker 2 uses CPU cores [2]
+[2023-07-08 23:01:01,609][19243] Worker 1 uses CPU cores [1]
+[2023-07-08 23:01:01,648][19244] Worker 3 uses CPU cores [3]
+[2023-07-08 23:01:01,649][19240] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 23:01:01,649][19240] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-07-08 23:01:01,737][19240] Num visible devices: 1
+[2023-07-08 23:01:01,782][19246] Worker 4 uses CPU cores [0]
+[2023-07-08 23:01:01,741][19220] Conv encoder output size: 512
+[2023-07-08 23:01:01,787][19220] Policy head output size: 512
+[2023-07-08 23:01:01,794][19252] Worker 11 uses CPU cores [3]
+[2023-07-08 23:01:01,800][19250] Worker 9 uses CPU cores [1]
+[2023-07-08 23:01:01,807][19220] Created Actor Critic model with architecture:
+[2023-07-08 23:01:01,831][19248] Worker 7 uses CPU cores [3]
+[2023-07-08 23:01:01,849][19249] Worker 8 uses CPU cores [0]
+[2023-07-08 23:01:01,862][19251] Worker 10 uses CPU cores [2]
+[2023-07-08 23:01:01,891][19220] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ReLU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ReLU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ReLU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ReLU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): LSTM(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2023-07-08 23:01:01,903][19253] Worker 12 uses CPU cores [0]
+[2023-07-08 23:01:01,925][19247] Worker 6 uses CPU cores [2]
+[2023-07-08 23:01:01,943][19254] Worker 13 uses CPU cores [1]
+[2023-07-08 23:01:01,967][19256] Worker 15 uses CPU cores [3]
+[2023-07-08 23:01:01,975][19259] Worker 18 uses CPU cores [2]
+[2023-07-08 23:01:01,991][19255] Worker 14 uses CPU cores [2]
+[2023-07-08 23:01:02,001][19257] Worker 16 uses CPU cores [0]
+[2023-07-08 23:01:02,021][19260] Worker 19 uses CPU cores [3]
+[2023-07-08 23:01:02,041][19245] Worker 5 uses CPU cores [1]
+[2023-07-08 23:01:02,052][19258] Worker 17 uses CPU cores [1]
+[2023-07-08 23:01:02,219][19220] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-07-08 23:01:02,220][19220] No checkpoints found
+[2023-07-08 23:01:02,220][19220] Did not load from checkpoint, starting from scratch!
+[2023-07-08 23:01:02,220][19220] Initialized policy 0 weights for model version 0
+[2023-07-08 23:01:02,223][19220] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 23:01:02,236][19220] LearnerWorker_p0 finished initialization!
+[2023-07-08 23:01:02,356][19240] Unhandled exception CUDA error: OS call failed or operation not supported on this OS
+CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
+For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
+Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
+ in evt loop inference_proc0-0_evt_loop
+[2023-07-08 23:02:53,735][19220] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth...
+[2023-07-08 23:04:53,736][19220] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth...
+[2023-07-08 23:05:29,863][19259] Stopping RolloutWorker_w18...
+[2023-07-08 23:05:29,864][19259] Loop rollout_proc18_evt_loop terminating...
+[2023-07-08 23:05:29,864][19260] Stopping RolloutWorker_w19...
+[2023-07-08 23:05:29,864][19260] Loop rollout_proc19_evt_loop terminating...
+[2023-07-08 23:05:29,872][19252] Stopping RolloutWorker_w11...
+[2023-07-08 23:05:29,872][19249] Stopping RolloutWorker_w8...
+[2023-07-08 23:05:29,872][19251] Stopping RolloutWorker_w10...
+[2023-07-08 23:05:29,872][19252] Loop rollout_proc11_evt_loop terminating...
+[2023-07-08 23:05:29,872][19249] Loop rollout_proc8_evt_loop terminating...
+[2023-07-08 23:05:29,872][19251] Loop rollout_proc10_evt_loop terminating...
+[2023-07-08 23:05:29,882][19255] Stopping RolloutWorker_w14...
+[2023-07-08 23:05:29,882][19248] Stopping RolloutWorker_w7...
+[2023-07-08 23:05:29,882][19257] Stopping RolloutWorker_w16...
+[2023-07-08 23:05:29,882][19255] Loop rollout_proc14_evt_loop terminating...
+[2023-07-08 23:05:29,882][19248] Loop rollout_proc7_evt_loop terminating...
+[2023-07-08 23:05:29,882][19257] Loop rollout_proc16_evt_loop terminating...
+[2023-07-08 23:05:29,882][19220] Stopping Batcher_0...
+[2023-07-08 23:05:29,883][19220] Loop batcher_evt_loop terminating...
+[2023-07-08 23:05:29,892][19244] Stopping RolloutWorker_w3...
+[2023-07-08 23:05:29,892][19241] Stopping RolloutWorker_w0...
+[2023-07-08 23:05:29,892][19244] Loop rollout_proc3_evt_loop terminating...
+[2023-07-08 23:05:29,892][19241] Loop rollout_proc0_evt_loop terminating...
+[2023-07-08 23:05:29,892][19220] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth...
+[2023-07-08 23:05:29,895][19256] Stopping RolloutWorker_w15...
+[2023-07-08 23:05:29,895][19247] Stopping RolloutWorker_w6...
+[2023-07-08 23:05:29,895][19256] Loop rollout_proc15_evt_loop terminating...
+[2023-07-08 23:05:29,896][19253] Stopping RolloutWorker_w12...
+[2023-07-08 23:05:29,896][19247] Loop rollout_proc6_evt_loop terminating...
+[2023-07-08 23:05:29,896][19253] Loop rollout_proc12_evt_loop terminating...
+[2023-07-08 23:05:29,901][19246] Stopping RolloutWorker_w4...
+[2023-07-08 23:05:29,902][19246] Loop rollout_proc4_evt_loop terminating...
+[2023-07-08 23:05:29,903][19242] Stopping RolloutWorker_w2...
+[2023-07-08 23:05:29,905][19242] Loop rollout_proc2_evt_loop terminating...
+[2023-07-08 23:05:29,956][19220] Stopping LearnerWorker_p0...
+[2023-07-08 23:05:29,956][19220] Loop learner_proc0_evt_loop terminating...
+[2023-07-08 23:05:30,040][19250] Stopping RolloutWorker_w9...
+[2023-07-08 23:05:30,041][19250] Loop rollout_proc9_evt_loop terminating...
+[2023-07-08 23:05:30,042][19254] Stopping RolloutWorker_w13...
+[2023-07-08 23:05:30,042][19254] Loop rollout_proc13_evt_loop terminating...
+[2023-07-08 23:05:30,052][19245] Stopping RolloutWorker_w5...
+[2023-07-08 23:05:30,052][19245] Loop rollout_proc5_evt_loop terminating...
+[2023-07-08 23:05:30,062][19258] Stopping RolloutWorker_w17...
+[2023-07-08 23:05:30,062][19258] Loop rollout_proc17_evt_loop terminating...
+[2023-07-08 23:05:30,072][19243] Stopping RolloutWorker_w1...
+[2023-07-08 23:05:30,072][19243] Loop rollout_proc1_evt_loop terminating...
+[2023-07-08 23:06:39,079][19475] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 23:06:39,079][19475] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-07-08 23:06:39,116][19475] Num visible devices: 1
+[2023-07-08 23:06:39,240][19475] Setting fixed seed 42
+[2023-07-08 23:06:39,241][19475] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 23:06:39,241][19475] Initializing actor-critic model on device cuda:0
+[2023-07-08 23:06:39,241][19475] RunningMeanStd input shape: (3, 72, 128)
+[2023-07-08 23:06:39,242][19475] RunningMeanStd input shape: (1,)
+[2023-07-08 23:06:39,248][19475] ConvEncoder: input_channels=3
+[2023-07-08 23:06:39,280][19499] Worker 3 uses CPU cores [3]
+[2023-07-08 23:06:39,412][19496] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 23:06:39,412][19496] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-07-08 23:06:39,470][19496] Num visible devices: 1
+[2023-07-08 23:06:39,462][19500] Worker 4 uses CPU cores [0]
+[2023-07-08 23:06:39,527][19495] Worker 0 uses CPU cores [0]
+[2023-07-08 23:06:39,541][19497] Worker 1 uses CPU cores [1]
+[2023-07-08 23:06:39,541][19502] Worker 6 uses CPU cores [2]
+[2023-07-08 23:06:39,604][19475] Conv encoder output size: 512
+[2023-07-08 23:06:39,605][19475] Policy head output size: 512
+[2023-07-08 23:06:39,608][19507] Worker 12 uses CPU cores [0]
+[2023-07-08 23:06:39,646][19475] Created Actor Critic model with architecture:
+[2023-07-08 23:06:39,646][19475] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ReLU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ReLU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ReLU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ReLU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): LSTM(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2023-07-08 23:06:39,648][19498] Worker 2 uses CPU cores [2]
+[2023-07-08 23:06:39,753][19513] Worker 15 uses CPU cores [3]
+[2023-07-08 23:06:39,774][19503] Worker 7 uses CPU cores [3]
+[2023-07-08 23:06:39,781][19510] Worker 14 uses CPU cores [2]
+[2023-07-08 23:06:39,800][19511] Worker 16 uses CPU cores [0]
+[2023-07-08 23:06:39,801][19506] Worker 10 uses CPU cores [2]
+[2023-07-08 23:06:39,804][19508] Worker 13 uses CPU cores [1]
+[2023-07-08 23:06:39,805][19505] Worker 9 uses CPU cores [1]
+[2023-07-08 23:06:39,811][19501] Worker 5 uses CPU cores [1]
+[2023-07-08 23:06:39,821][19509] Worker 11 uses CPU cores [3]
+[2023-07-08 23:06:39,888][19514] Worker 17 uses CPU cores [1]
+[2023-07-08 23:06:39,899][19515] Worker 19 uses CPU cores [3]
+[2023-07-08 23:06:39,901][19512] Worker 18 uses CPU cores [2]
+[2023-07-08 23:06:39,968][19504] Worker 8 uses CPU cores [0]
+[2023-07-08 23:06:40,230][19475] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-07-08 23:06:40,230][19475] Loading state from checkpoint /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth...
+[2023-07-08 23:06:40,254][19475] Loading model from checkpoint
+[2023-07-08 23:06:40,257][19475] Loaded experiment state at self.train_step=466273, self.env_steps=3819708416
+[2023-07-08 23:06:40,257][19475] Initialized policy 0 weights for model version 466273
+[2023-07-08 23:06:40,260][19475] LearnerWorker_p0 finished initialization!
+[2023-07-08 23:06:40,260][19475] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 23:06:40,402][19496] Unhandled exception CUDA error: OS call failed or operation not supported on this OS
+CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
+For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
+Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
+ in evt loop inference_proc0-0_evt_loop
+[2023-07-08 23:08:32,108][19475] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000466273_3819708416.pth...
+[2023-07-08 23:10:32,106][19475] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000466273_3819708416.pth...
+[2023-07-08 23:12:32,106][19475] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000466273_3819708416.pth...
+[2023-07-08 23:14:32,106][19475] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000466273_3819708416.pth...
+[2023-07-08 23:16:32,106][19475] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000466273_3819708416.pth...
+[2023-07-08 23:18:32,106][19475] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000466273_3819708416.pth...
+[2023-07-08 23:20:32,106][19475] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000466273_3819708416.pth...
+[2023-07-08 23:21:32,107][19507] Stopping RolloutWorker_w12...
+[2023-07-08 23:21:32,107][19475] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000466273_3819708416.pth...
+[2023-07-08 23:21:32,107][19513] Stopping RolloutWorker_w15...
+[2023-07-08 23:21:32,107][19507] Loop rollout_proc12_evt_loop terminating...
+[2023-07-08 23:21:32,108][19513] Loop rollout_proc15_evt_loop terminating...
+[2023-07-08 23:21:32,108][19505] Stopping RolloutWorker_w9...
+[2023-07-08 23:21:32,108][19508] Stopping RolloutWorker_w13...
+[2023-07-08 23:21:32,109][19514] Stopping RolloutWorker_w17...
+[2023-07-08 23:21:32,109][19501] Stopping RolloutWorker_w5...
+[2023-07-08 23:21:32,109][19501] Loop rollout_proc5_evt_loop terminating...
+[2023-07-08 23:21:32,109][19502] Stopping RolloutWorker_w6...
+[2023-07-08 23:21:32,109][19502] Loop rollout_proc6_evt_loop terminating...
+[2023-07-08 23:21:32,107][19497] Stopping RolloutWorker_w1...
+[2023-07-08 23:21:32,112][19497] Loop rollout_proc1_evt_loop terminating...
+[2023-07-08 23:21:32,112][19509] Stopping RolloutWorker_w11...
+[2023-07-08 23:21:32,112][19495] Stopping RolloutWorker_w0...
+[2023-07-08 23:21:32,112][19512] Stopping RolloutWorker_w18...
+[2023-07-08 23:21:32,112][19495] Loop rollout_proc0_evt_loop terminating...
+[2023-07-08 23:21:32,112][19509] Loop rollout_proc11_evt_loop terminating...
+[2023-07-08 23:21:32,112][19512] Loop rollout_proc18_evt_loop terminating...
+[2023-07-08 23:21:32,117][19499] Stopping RolloutWorker_w3...
+[2023-07-08 23:21:32,117][19506] Stopping RolloutWorker_w10...
+[2023-07-08 23:21:32,107][19515] Stopping RolloutWorker_w19...
+[2023-07-08 23:21:32,116][19503] Stopping RolloutWorker_w7...
+[2023-07-08 23:21:32,117][19506] Loop rollout_proc10_evt_loop terminating...
+[2023-07-08 23:21:32,117][19499] Loop rollout_proc3_evt_loop terminating...
+[2023-07-08 23:21:32,117][19503] Loop rollout_proc7_evt_loop terminating...
+[2023-07-08 23:21:32,122][19505] Loop rollout_proc9_evt_loop terminating...
+[2023-07-08 23:21:32,122][19498] Stopping RolloutWorker_w2...
+[2023-07-08 23:21:32,122][19511] Stopping RolloutWorker_w16...
+[2023-07-08 23:21:32,118][19515] Loop rollout_proc19_evt_loop terminating...
+[2023-07-08 23:21:32,122][19511] Loop rollout_proc16_evt_loop terminating...
+[2023-07-08 23:21:32,122][19498] Loop rollout_proc2_evt_loop terminating...
+[2023-07-08 23:21:32,129][19510] Stopping RolloutWorker_w14...
+[2023-07-08 23:21:32,129][19510] Loop rollout_proc14_evt_loop terminating...
+[2023-07-08 23:21:32,132][19514] Loop rollout_proc17_evt_loop terminating...
+[2023-07-08 23:21:32,132][19504] Stopping RolloutWorker_w8...
+[2023-07-08 23:21:32,132][19504] Loop rollout_proc8_evt_loop terminating...
+[2023-07-08 23:21:32,132][19475] Stopping Batcher_0...
+[2023-07-08 23:21:32,132][19475] Loop batcher_evt_loop terminating...
+[2023-07-08 23:21:32,136][19508] Loop rollout_proc13_evt_loop terminating...
+[2023-07-08 23:21:32,142][19500] Stopping RolloutWorker_w4...
+[2023-07-08 23:21:32,142][19500] Loop rollout_proc4_evt_loop terminating...
+[2023-07-08 23:21:32,239][19475] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000466273_3819708416.pth...
+[2023-07-08 23:21:32,373][19475] Stopping LearnerWorker_p0...
+[2023-07-08 23:21:32,373][19475] Loop learner_proc0_evt_loop terminating...