Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1688875833.snowflake

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd527d5dbe9948b3cf172942eb93e28853a71d7bdd8acbe7fb8f234fc78af4ba
+size 16844

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 3.88 +/- 0.22
+      value: 3.86 +/- 1.25
       name: mean_reward
       verified: false
 ---

checkpoint_p0/checkpoint_000539850_4422451200.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1be9248848cf708023922e66ee9ba4efbea47de9ceb068c402f6fb25ff47dba
+size 41232964

git.diff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a61a193f0cc481d66bfc2627e32f7543022b6969516b6c1e19e74af543e7c41
-size 212435236
+oid sha256:671503816d17efebd2950b3a8da881615b5bda60f712ce94d1cc40365a4b13fa
+size 211382168

sf_log.txt

@@ -420,3 +420,144 @@ Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
 [2023-07-08 21:54:27,855][17857] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth...
 [2023-07-08 21:54:27,905][17857] Stopping LearnerWorker_p0...
 [2023-07-08 21:54:27,905][17857] Loop learner_proc0_evt_loop terminating...
+[2023-07-08 22:10:38,828][18235] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 22:10:38,832][18235] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-07-08 22:10:38,894][18235] Num visible devices: 1
+[2023-07-08 22:10:39,062][18235] Setting fixed seed 42
+[2023-07-08 22:10:39,063][18235] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 22:10:39,063][18235] Initializing actor-critic model on device cuda:0
+[2023-07-08 22:10:39,063][18235] RunningMeanStd input shape: (3, 72, 128)
+[2023-07-08 22:10:39,063][18235] RunningMeanStd input shape: (1,)
+[2023-07-08 22:10:39,070][18235] ConvEncoder: input_channels=3
+[2023-07-08 22:10:39,386][18235] Conv encoder output size: 512
+[2023-07-08 22:10:39,428][18235] Policy head output size: 512
+[2023-07-08 22:10:39,448][18235] Created Actor Critic model with architecture:
+[2023-07-08 22:10:39,481][18235] 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 22:10:40,063][18235] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-07-08 22:10:40,063][18235] Loading state from checkpoint /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2023-07-08 22:10:40,149][18255] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 22:10:40,150][18255] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-07-08 22:10:40,226][18255] Num visible devices: 1
+[2023-07-08 22:10:40,229][18235] Loading model from checkpoint
+[2023-07-08 22:10:40,231][18235] Loaded experiment state at self.train_step=539850, self.env_steps=4422451200
+[2023-07-08 22:10:40,232][18235] Initialized policy 0 weights for model version 539850
+[2023-07-08 22:10:40,252][18235] LearnerWorker_p0 finished initialization!
+[2023-07-08 22:10:40,253][18235] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-08 22:10:40,461][18260] Worker 3 uses CPU cores [3]
+[2023-07-08 22:10:40,672][18256] Worker 0 uses CPU cores [0]
+[2023-07-08 22:10:40,741][18261] Worker 5 uses CPU cores [1]
+[2023-07-08 22:10:40,772][18257] Worker 1 uses CPU cores [1]
+[2023-07-08 22:10:40,774][18258] Worker 2 uses CPU cores [2]
+[2023-07-08 22:10:40,917][18263] Worker 7 uses CPU cores [3]
+[2023-07-08 22:10:40,931][18264] Worker 8 uses CPU cores [0]
+[2023-07-08 22:10:40,941][18269] Worker 13 uses CPU cores [1]
+[2023-07-08 22:10:40,977][18259] Worker 4 uses CPU cores [0]
+[2023-07-08 22:10:41,112][18274] Worker 18 uses CPU cores [2]
+[2023-07-08 22:10:41,119][18272] Worker 16 uses CPU cores [0]
+[2023-07-08 22:10:41,137][18262] Worker 6 uses CPU cores [2]
+[2023-07-08 22:10:41,156][18270] Worker 14 uses CPU cores [2]
+[2023-07-08 22:10:41,172][18266] Worker 11 uses CPU cores [3]
+[2023-07-08 22:10:41,191][18275] Worker 19 uses CPU cores [3]
+[2023-07-08 22:10:41,201][18268] Worker 9 uses CPU cores [1]
+[2023-07-08 22:10:41,214][18273] Worker 17 uses CPU cores [1]
+[2023-07-08 22:10:41,218][18267] Worker 12 uses CPU cores [0]
+[2023-07-08 22:10:41,218][18271] Worker 15 uses CPU cores [3]
+[2023-07-08 22:10:41,227][18265] Worker 10 uses CPU cores [2]
+[2023-07-08 22:10:41,377][18255] 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 22:12:33,306][18235] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2023-07-08 22:14:33,308][18235] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2023-07-08 22:16:33,307][18235] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2023-07-08 22:18:33,307][18235] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2023-07-08 22:20:33,307][18235] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2023-07-08 22:22:33,307][18235] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2023-07-08 22:24:33,306][18235] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2023-07-08 22:25:33,309][18274] Stopping RolloutWorker_w18...
+[2023-07-08 22:25:33,308][18264] Stopping RolloutWorker_w8...
+[2023-07-08 22:25:33,309][18264] Loop rollout_proc8_evt_loop terminating...
+[2023-07-08 22:25:33,309][18235] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2023-07-08 22:25:33,309][18267] Stopping RolloutWorker_w12...
+[2023-07-08 22:25:33,309][18267] Loop rollout_proc12_evt_loop terminating...
+[2023-07-08 22:25:33,308][18270] Stopping RolloutWorker_w14...
+[2023-07-08 22:25:33,310][18258] Stopping RolloutWorker_w2...
+[2023-07-08 22:25:33,309][18262] Stopping RolloutWorker_w6...
+[2023-07-08 22:25:33,311][18266] Stopping RolloutWorker_w11...
+[2023-07-08 22:25:33,309][18265] Stopping RolloutWorker_w10...
+[2023-07-08 22:25:33,311][18266] Loop rollout_proc11_evt_loop terminating...
+[2023-07-08 22:25:33,310][18270] Loop rollout_proc14_evt_loop terminating...
+[2023-07-08 22:25:33,312][18260] Stopping RolloutWorker_w3...
+[2023-07-08 22:25:33,312][18257] Stopping RolloutWorker_w1...
+[2023-07-08 22:25:33,312][18260] Loop rollout_proc3_evt_loop terminating...
+[2023-07-08 22:25:33,312][18257] Loop rollout_proc1_evt_loop terminating...
+[2023-07-08 22:25:33,310][18258] Loop rollout_proc2_evt_loop terminating...
+[2023-07-08 22:25:33,316][18275] Stopping RolloutWorker_w19...
+[2023-07-08 22:25:33,316][18275] Loop rollout_proc19_evt_loop terminating...
+[2023-07-08 22:25:33,311][18262] Loop rollout_proc6_evt_loop terminating...
+[2023-07-08 22:25:33,311][18274] Loop rollout_proc18_evt_loop terminating...
+[2023-07-08 22:25:33,321][18271] Stopping RolloutWorker_w15...
+[2023-07-08 22:25:33,311][18265] Loop rollout_proc10_evt_loop terminating...
+[2023-07-08 22:25:33,321][18271] Loop rollout_proc15_evt_loop terminating...
+[2023-07-08 22:25:33,322][18268] Stopping RolloutWorker_w9...
+[2023-07-08 22:25:33,322][18263] Stopping RolloutWorker_w7...
+[2023-07-08 22:25:33,322][18256] Stopping RolloutWorker_w0...
+[2023-07-08 22:25:33,322][18263] Loop rollout_proc7_evt_loop terminating...
+[2023-07-08 22:25:33,322][18268] Loop rollout_proc9_evt_loop terminating...
+[2023-07-08 22:25:33,322][18256] Loop rollout_proc0_evt_loop terminating...
+[2023-07-08 22:25:33,326][18272] Stopping RolloutWorker_w16...
+[2023-07-08 22:25:33,326][18272] Loop rollout_proc16_evt_loop terminating...
+[2023-07-08 22:25:33,332][18273] Stopping RolloutWorker_w17...
+[2023-07-08 22:25:33,332][18273] Loop rollout_proc17_evt_loop terminating...
+[2023-07-08 22:25:33,332][18259] Stopping RolloutWorker_w4...
+[2023-07-08 22:25:33,332][18259] Loop rollout_proc4_evt_loop terminating...
+[2023-07-08 22:25:33,342][18261] Stopping RolloutWorker_w5...
+[2023-07-08 22:25:33,342][18261] Loop rollout_proc5_evt_loop terminating...
+[2023-07-08 22:25:33,347][18235] Stopping Batcher_0...
+[2023-07-08 22:25:33,348][18235] Loop batcher_evt_loop terminating...
+[2023-07-08 22:25:33,352][18269] Stopping RolloutWorker_w13...
+[2023-07-08 22:25:33,352][18269] Loop rollout_proc13_evt_loop terminating...
+[2023-07-08 22:25:33,428][18235] Saving /home/raj/repos/HF-DeepRL/8-Proximal-Policy-Optimization/train_dir/default_experiment/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2023-07-08 22:25:33,539][18235] Stopping LearnerWorker_p0...
+[2023-07-08 22:25:33,539][18235] Loop learner_proc0_evt_loop terminating...