diff --git "a/sf_log.txt" "b/sf_log.txt" new file mode 100644--- /dev/null +++ "b/sf_log.txt" @@ -0,0 +1,1162 @@ +[2023-07-08 02:59:10,239][812583] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/config.json... +[2023-07-08 02:59:10,257][812583] Rollout worker 0 uses device cpu +[2023-07-08 02:59:10,257][812583] Rollout worker 1 uses device cpu +[2023-07-08 02:59:10,257][812583] Rollout worker 2 uses device cpu +[2023-07-08 02:59:10,257][812583] Rollout worker 3 uses device cpu +[2023-07-08 02:59:10,257][812583] Rollout worker 4 uses device cpu +[2023-07-08 02:59:10,258][812583] Rollout worker 5 uses device cpu +[2023-07-08 02:59:10,258][812583] Rollout worker 6 uses device cpu +[2023-07-08 02:59:10,258][812583] Rollout worker 7 uses device cpu +[2023-07-08 02:59:10,258][812583] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 +[2023-07-08 02:59:10,269][812583] InferenceWorker_p0-w0: min num requests: 2 +[2023-07-08 02:59:10,288][812583] Starting all processes... +[2023-07-08 02:59:10,288][812583] Starting process learner_proc0 +[2023-07-08 02:59:10,337][812583] Starting all processes... +[2023-07-08 02:59:10,385][812583] Starting process inference_proc0-0 +[2023-07-08 02:59:10,385][812583] Starting process rollout_proc0 +[2023-07-08 02:59:10,385][812583] Starting process rollout_proc1 +[2023-07-08 02:59:10,385][812583] Starting process rollout_proc2 +[2023-07-08 02:59:10,385][812583] Starting process rollout_proc3 +[2023-07-08 02:59:10,385][812583] Starting process rollout_proc4 +[2023-07-08 02:59:10,385][812583] Starting process rollout_proc5 +[2023-07-08 02:59:10,385][812583] Starting process rollout_proc6 +[2023-07-08 02:59:10,385][812583] Starting process rollout_proc7 +[2023-07-08 02:59:12,182][812822] Starting seed is not provided +[2023-07-08 02:59:12,182][812822] Initializing actor-critic model on device cpu +[2023-07-08 02:59:12,183][812822] RunningMeanStd input shape: (39,) +[2023-07-08 02:59:12,183][812822] RunningMeanStd input shape: (1,) +[2023-07-08 02:59:12,254][812822] Created Actor Critic model with architecture: +[2023-07-08 02:59:12,255][812822] ActorCriticSharedWeights( + (obs_normalizer): ObservationNormalizer( + (running_mean_std): RunningMeanStdDictInPlace( + (running_mean_std): ModuleDict( + (obs): RunningMeanStdInPlace() + ) + ) + ) + (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) + (encoder): MultiInputEncoder( + (encoders): ModuleDict( + (obs): MlpEncoder( + (mlp_head): RecursiveScriptModule( + original_name=Sequential + (0): RecursiveScriptModule(original_name=Linear) + (1): RecursiveScriptModule(original_name=Tanh) + (2): RecursiveScriptModule(original_name=Linear) + (3): RecursiveScriptModule(original_name=Tanh) + ) + ) + ) + ) + (core): ModelCoreIdentity() + (decoder): MlpDecoder( + (mlp): Identity() + ) + (critic_linear): Linear(in_features=64, out_features=1, bias=True) + (action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev( + (distribution_linear): Linear(in_features=64, out_features=4, bias=True) + ) +) +[2023-07-08 02:59:12,261][812875] Worker 3 uses CPU cores [12, 13, 14, 15] +[2023-07-08 02:59:12,447][812869] Worker 0 uses CPU cores [0, 1, 2, 3] +[2023-07-08 02:59:12,517][812873] Worker 1 uses CPU cores [4, 5, 6, 7] +[2023-07-08 02:59:12,564][812822] Using optimizer +[2023-07-08 02:59:12,565][812822] No checkpoints found +[2023-07-08 02:59:12,565][812822] Did not load from checkpoint, starting from scratch! +[2023-07-08 02:59:12,565][812822] Initialized policy 0 weights for model version 0 +[2023-07-08 02:59:12,566][812822] LearnerWorker_p0 finished initialization! +[2023-07-08 02:59:12,567][812868] RunningMeanStd input shape: (39,) +[2023-07-08 02:59:12,567][812876] Worker 4 uses CPU cores [16, 17, 18, 19] +[2023-07-08 02:59:12,568][812868] RunningMeanStd input shape: (1,) +[2023-07-08 02:59:12,607][812583] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-07-08 02:59:12,639][812583] Inference worker 0-0 is ready! +[2023-07-08 02:59:12,639][812583] All inference workers are ready! Signal rollout workers to start! +[2023-07-08 02:59:12,654][812940] Worker 6 uses CPU cores [24, 25, 26, 27] +[2023-07-08 02:59:12,773][812874] Worker 2 uses CPU cores [8, 9, 10, 11] +[2023-07-08 02:59:12,901][812877] Worker 5 uses CPU cores [20, 21, 22, 23] +[2023-07-08 02:59:12,998][812972] Worker 7 uses CPU cores [28, 29, 30, 31] +[2023-07-08 02:59:16,507][812873] Decorrelating experience for 0 frames... +[2023-07-08 02:59:16,517][812875] Decorrelating experience for 0 frames... +[2023-07-08 02:59:16,517][812869] Decorrelating experience for 0 frames... +[2023-07-08 02:59:16,519][812876] Decorrelating experience for 0 frames... +[2023-07-08 02:59:16,521][812873] Decorrelating experience for 64 frames... +[2023-07-08 02:59:16,530][812875] Decorrelating experience for 64 frames... +[2023-07-08 02:59:16,531][812869] Decorrelating experience for 64 frames... +[2023-07-08 02:59:16,532][812876] Decorrelating experience for 64 frames... +[2023-07-08 02:59:16,559][812873] Decorrelating experience for 128 frames... +[2023-07-08 02:59:16,568][812875] Decorrelating experience for 128 frames... +[2023-07-08 02:59:16,569][812869] Decorrelating experience for 128 frames... +[2023-07-08 02:59:16,570][812940] Decorrelating experience for 0 frames... +[2023-07-08 02:59:16,570][812876] Decorrelating experience for 128 frames... +[2023-07-08 02:59:16,583][812940] Decorrelating experience for 64 frames... +[2023-07-08 02:59:16,620][812940] Decorrelating experience for 128 frames... +[2023-07-08 02:59:16,633][812873] Decorrelating experience for 192 frames... +[2023-07-08 02:59:16,646][812869] Decorrelating experience for 192 frames... +[2023-07-08 02:59:16,646][812876] Decorrelating experience for 192 frames... +[2023-07-08 02:59:16,646][812875] Decorrelating experience for 192 frames... +[2023-07-08 02:59:16,695][812940] Decorrelating experience for 192 frames... +[2023-07-08 02:59:16,702][812874] Decorrelating experience for 0 frames... +[2023-07-08 02:59:16,715][812874] Decorrelating experience for 64 frames... +[2023-07-08 02:59:16,753][812874] Decorrelating experience for 128 frames... +[2023-07-08 02:59:16,808][812877] Decorrelating experience for 0 frames... +[2023-07-08 02:59:16,821][812877] Decorrelating experience for 64 frames... +[2023-07-08 02:59:16,829][812874] Decorrelating experience for 192 frames... +[2023-07-08 02:59:16,859][812877] Decorrelating experience for 128 frames... +[2023-07-08 02:59:16,932][812877] Decorrelating experience for 192 frames... +[2023-07-08 02:59:16,934][812972] Decorrelating experience for 0 frames... +[2023-07-08 02:59:16,948][812972] Decorrelating experience for 64 frames... +[2023-07-08 02:59:16,986][812972] Decorrelating experience for 128 frames... +[2023-07-08 02:59:17,059][812972] Decorrelating experience for 192 frames... +[2023-07-08 02:59:17,607][812583] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-07-08 02:59:20,478][812873] Decorrelating experience for 256 frames... +[2023-07-08 02:59:20,480][812875] Decorrelating experience for 256 frames... +[2023-07-08 02:59:20,492][812876] Decorrelating experience for 256 frames... +[2023-07-08 02:59:20,495][812869] Decorrelating experience for 256 frames... +[2023-07-08 02:59:20,524][812940] Decorrelating experience for 256 frames... +[2023-07-08 02:59:20,611][812873] Decorrelating experience for 320 frames... +[2023-07-08 02:59:20,615][812875] Decorrelating experience for 320 frames... +[2023-07-08 02:59:20,630][812876] Decorrelating experience for 320 frames... +[2023-07-08 02:59:20,631][812869] Decorrelating experience for 320 frames... +[2023-07-08 02:59:20,661][812940] Decorrelating experience for 320 frames... +[2023-07-08 02:59:20,675][812874] Decorrelating experience for 256 frames... +[2023-07-08 02:59:20,780][812877] Decorrelating experience for 256 frames... +[2023-07-08 02:59:20,784][812873] Decorrelating experience for 384 frames... +[2023-07-08 02:59:20,786][812875] Decorrelating experience for 384 frames... +[2023-07-08 02:59:20,804][812876] Decorrelating experience for 384 frames... +[2023-07-08 02:59:20,807][812869] Decorrelating experience for 384 frames... +[2023-07-08 02:59:20,812][812874] Decorrelating experience for 320 frames... +[2023-07-08 02:59:20,833][812940] Decorrelating experience for 384 frames... +[2023-07-08 02:59:20,894][812972] Decorrelating experience for 256 frames... +[2023-07-08 02:59:20,916][812877] Decorrelating experience for 320 frames... +[2023-07-08 02:59:20,983][812873] Decorrelating experience for 448 frames... +[2023-07-08 02:59:20,986][812874] Decorrelating experience for 384 frames... +[2023-07-08 02:59:20,988][812875] Decorrelating experience for 448 frames... +[2023-07-08 02:59:20,999][812876] Decorrelating experience for 448 frames... +[2023-07-08 02:59:21,003][812869] Decorrelating experience for 448 frames... +[2023-07-08 02:59:21,034][812972] Decorrelating experience for 320 frames... +[2023-07-08 02:59:21,035][812940] Decorrelating experience for 448 frames... +[2023-07-08 02:59:21,098][812877] Decorrelating experience for 384 frames... +[2023-07-08 02:59:21,180][812874] Decorrelating experience for 448 frames... +[2023-07-08 02:59:21,204][812972] Decorrelating experience for 384 frames... +[2023-07-08 02:59:21,297][812877] Decorrelating experience for 448 frames... +[2023-07-08 02:59:21,401][812972] Decorrelating experience for 448 frames... +[2023-07-08 02:59:22,607][812583] Fps is (10 sec: 409.6, 60 sec: 409.6, 300 sec: 409.6). Total num frames: 4096. Throughput: 0: 107.6. Samples: 1076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 02:59:22,607][812583] Avg episode reward: [(0, '1.525')] +[2023-07-08 02:59:22,632][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000016_8192.pth... +[2023-07-08 02:59:25,871][812868] Updated weights for policy 0, policy_version 80 (0.0004) +[2023-07-08 02:59:27,607][812583] Fps is (10 sec: 5324.8, 60 sec: 3549.9, 300 sec: 3549.9). Total num frames: 53248. Throughput: 0: 1948.8. Samples: 29232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 02:59:27,607][812583] Avg episode reward: [(0, '9.956')] +[2023-07-08 02:59:30,265][812583] Heartbeat connected on Batcher_0 +[2023-07-08 02:59:30,267][812583] Heartbeat connected on LearnerWorker_p0 +[2023-07-08 02:59:30,270][812583] Heartbeat connected on InferenceWorker_p0-w0 +[2023-07-08 02:59:30,276][812583] Heartbeat connected on RolloutWorker_w0 +[2023-07-08 02:59:30,279][812583] Heartbeat connected on RolloutWorker_w2 +[2023-07-08 02:59:30,282][812583] Heartbeat connected on RolloutWorker_w3 +[2023-07-08 02:59:30,283][812583] Heartbeat connected on RolloutWorker_w4 +[2023-07-08 02:59:30,286][812583] Heartbeat connected on RolloutWorker_w5 +[2023-07-08 02:59:30,286][812583] Heartbeat connected on RolloutWorker_w7 +[2023-07-08 02:59:30,287][812583] Heartbeat connected on RolloutWorker_w1 +[2023-07-08 02:59:30,287][812583] Heartbeat connected on RolloutWorker_w6 +[2023-07-08 02:59:30,341][812868] Updated weights for policy 0, policy_version 160 (0.0005) +[2023-07-08 02:59:32,607][812583] Fps is (10 sec: 9830.5, 60 sec: 5120.0, 300 sec: 5120.0). Total num frames: 102400. Throughput: 0: 4286.2. Samples: 85724. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 02:59:32,607][812583] Avg episode reward: [(0, '61.679')] +[2023-07-08 02:59:32,614][812822] Saving new best policy, reward=61.679! +[2023-07-08 02:59:34,321][812868] Updated weights for policy 0, policy_version 240 (0.0004) +[2023-07-08 02:59:37,607][812583] Fps is (10 sec: 9830.4, 60 sec: 6062.1, 300 sec: 6062.1). Total num frames: 151552. Throughput: 0: 5850.7. Samples: 146268. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 02:59:37,607][812583] Avg episode reward: [(0, '117.263')] +[2023-07-08 02:59:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000296_151552.pth... +[2023-07-08 02:59:37,612][812822] Saving new best policy, reward=117.263! +[2023-07-08 02:59:38,528][812868] Updated weights for policy 0, policy_version 320 (0.0004) +[2023-07-08 02:59:42,569][812868] Updated weights for policy 0, policy_version 400 (0.0004) +[2023-07-08 02:59:42,607][812583] Fps is (10 sec: 10240.1, 60 sec: 6826.7, 300 sec: 6826.7). Total num frames: 204800. Throughput: 0: 5856.5. Samples: 175696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 02:59:42,607][812583] Avg episode reward: [(0, '92.984')] +[2023-07-08 02:59:46,866][812868] Updated weights for policy 0, policy_version 480 (0.0005) +[2023-07-08 02:59:47,607][812583] Fps is (10 sec: 9830.4, 60 sec: 7138.7, 300 sec: 7138.7). Total num frames: 249856. Throughput: 0: 6707.3. Samples: 234756. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 02:59:47,607][812583] Avg episode reward: [(0, '103.264')] +[2023-07-08 02:59:51,183][812868] Updated weights for policy 0, policy_version 560 (0.0005) +[2023-07-08 02:59:52,607][812583] Fps is (10 sec: 9420.8, 60 sec: 7475.2, 300 sec: 7475.2). Total num frames: 299008. Throughput: 0: 7281.6. Samples: 291264. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 02:59:52,607][812583] Avg episode reward: [(0, '118.763')] +[2023-07-08 02:59:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000584_299008.pth... +[2023-07-08 02:59:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000016_8192.pth +[2023-07-08 02:59:52,613][812822] Saving new best policy, reward=118.763! +[2023-07-08 02:59:55,341][812868] Updated weights for policy 0, policy_version 640 (0.0004) +[2023-07-08 02:59:57,607][812583] Fps is (10 sec: 9830.4, 60 sec: 7736.9, 300 sec: 7736.9). Total num frames: 348160. Throughput: 0: 7129.3. Samples: 320820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 02:59:57,607][812583] Avg episode reward: [(0, '137.461')] +[2023-07-08 02:59:57,608][812822] Saving new best policy, reward=137.461! +[2023-07-08 02:59:59,429][812868] Updated weights for policy 0, policy_version 720 (0.0005) +[2023-07-08 03:00:02,607][812583] Fps is (10 sec: 9830.5, 60 sec: 7946.3, 300 sec: 7946.3). Total num frames: 397312. Throughput: 0: 8466.7. Samples: 381000. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:00:02,607][812583] Avg episode reward: [(0, '151.721')] +[2023-07-08 03:00:02,636][812822] Saving new best policy, reward=151.721! +[2023-07-08 03:00:03,434][812868] Updated weights for policy 0, policy_version 800 (0.0005) +[2023-07-08 03:00:07,558][812868] Updated weights for policy 0, policy_version 880 (0.0005) +[2023-07-08 03:00:07,607][812583] Fps is (10 sec: 10239.9, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 450560. Throughput: 0: 9799.2. Samples: 442040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:00:07,607][812583] Avg episode reward: [(0, '213.252')] +[2023-07-08 03:00:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000880_450560.pth... +[2023-07-08 03:00:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000296_151552.pth +[2023-07-08 03:00:07,613][812822] Saving new best policy, reward=213.252! +[2023-07-08 03:00:11,686][812868] Updated weights for policy 0, policy_version 960 (0.0005) +[2023-07-08 03:00:12,607][812583] Fps is (10 sec: 10239.9, 60 sec: 8328.5, 300 sec: 8328.5). Total num frames: 499712. Throughput: 0: 9821.7. Samples: 471208. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:00:12,607][812583] Avg episode reward: [(0, '221.996')] +[2023-07-08 03:00:12,608][812822] Saving new best policy, reward=221.996! +[2023-07-08 03:00:15,925][812868] Updated weights for policy 0, policy_version 1040 (0.0006) +[2023-07-08 03:00:17,607][812583] Fps is (10 sec: 9421.0, 60 sec: 9079.5, 300 sec: 8381.1). Total num frames: 544768. Throughput: 0: 9867.1. Samples: 529744. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:00:17,607][812583] Avg episode reward: [(0, '281.212')] +[2023-07-08 03:00:17,607][812822] Saving new best policy, reward=281.212! +[2023-07-08 03:00:20,307][812868] Updated weights for policy 0, policy_version 1120 (0.0006) +[2023-07-08 03:00:22,607][812583] Fps is (10 sec: 9420.8, 60 sec: 9830.4, 300 sec: 8484.6). Total num frames: 593920. Throughput: 0: 9766.0. Samples: 585736. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:00:22,607][812583] Avg episode reward: [(0, '346.252')] +[2023-07-08 03:00:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001160_593920.pth... +[2023-07-08 03:00:22,611][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000584_299008.pth +[2023-07-08 03:00:22,612][812822] Saving new best policy, reward=346.252! +[2023-07-08 03:00:24,773][812868] Updated weights for policy 0, policy_version 1200 (0.0005) +[2023-07-08 03:00:27,607][812583] Fps is (10 sec: 9420.7, 60 sec: 9762.1, 300 sec: 8519.7). Total num frames: 638976. Throughput: 0: 9736.4. Samples: 613832. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:00:27,607][812583] Avg episode reward: [(0, '349.797')] +[2023-07-08 03:00:27,608][812822] Saving new best policy, reward=349.797! +[2023-07-08 03:00:29,383][812868] Updated weights for policy 0, policy_version 1280 (0.0005) +[2023-07-08 03:00:32,607][812583] Fps is (10 sec: 8601.6, 60 sec: 9625.6, 300 sec: 8499.2). Total num frames: 679936. Throughput: 0: 9607.4. Samples: 667088. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:00:32,607][812583] Avg episode reward: [(0, '355.523')] +[2023-07-08 03:00:32,615][812822] Saving new best policy, reward=355.523! +[2023-07-08 03:00:33,982][812868] Updated weights for policy 0, policy_version 1360 (0.0005) +[2023-07-08 03:00:37,607][812583] Fps is (10 sec: 8601.6, 60 sec: 9557.3, 300 sec: 8529.3). Total num frames: 724992. Throughput: 0: 9535.3. Samples: 720352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:00:37,607][812583] Avg episode reward: [(0, '342.091')] +[2023-07-08 03:00:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001416_724992.pth... +[2023-07-08 03:00:37,611][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000880_450560.pth +[2023-07-08 03:00:38,622][812868] Updated weights for policy 0, policy_version 1440 (0.0005) +[2023-07-08 03:00:42,607][812583] Fps is (10 sec: 9011.3, 60 sec: 9420.8, 300 sec: 8556.1). Total num frames: 770048. Throughput: 0: 9464.0. Samples: 746700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:00:42,607][812583] Avg episode reward: [(0, '325.724')] +[2023-07-08 03:00:43,199][812868] Updated weights for policy 0, policy_version 1520 (0.0005) +[2023-07-08 03:00:47,607][812583] Fps is (10 sec: 9011.2, 60 sec: 9420.8, 300 sec: 8580.0). Total num frames: 815104. Throughput: 0: 9311.4. Samples: 800016. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:00:47,607][812583] Avg episode reward: [(0, '378.064')] +[2023-07-08 03:00:47,608][812822] Saving new best policy, reward=378.064! +[2023-07-08 03:00:47,796][812868] Updated weights for policy 0, policy_version 1600 (0.0005) +[2023-07-08 03:00:52,352][812868] Updated weights for policy 0, policy_version 1680 (0.0005) +[2023-07-08 03:00:52,607][812583] Fps is (10 sec: 9011.1, 60 sec: 9352.5, 300 sec: 8601.6). Total num frames: 860160. Throughput: 0: 9162.9. Samples: 854368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:00:52,607][812583] Avg episode reward: [(0, '366.167')] +[2023-07-08 03:00:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001680_860160.pth... +[2023-07-08 03:00:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001160_593920.pth +[2023-07-08 03:00:57,054][812868] Updated weights for policy 0, policy_version 1760 (0.0005) +[2023-07-08 03:00:57,607][812583] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 8621.1). Total num frames: 905216. Throughput: 0: 9095.9. Samples: 880524. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:00:57,607][812583] Avg episode reward: [(0, '301.250')] +[2023-07-08 03:01:01,914][812868] Updated weights for policy 0, policy_version 1840 (0.0005) +[2023-07-08 03:01:02,607][812583] Fps is (10 sec: 8601.7, 60 sec: 9147.7, 300 sec: 8601.6). Total num frames: 946176. Throughput: 0: 8939.2. Samples: 932008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:01:02,607][812583] Avg episode reward: [(0, '337.909')] +[2023-07-08 03:01:06,750][812868] Updated weights for policy 0, policy_version 1920 (0.0005) +[2023-07-08 03:01:07,607][812583] Fps is (10 sec: 8191.9, 60 sec: 8942.9, 300 sec: 8583.8). Total num frames: 987136. Throughput: 0: 8824.6. Samples: 982844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:01:07,607][812583] Avg episode reward: [(0, '385.899')] +[2023-07-08 03:01:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001928_987136.pth... +[2023-07-08 03:01:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001416_724992.pth +[2023-07-08 03:01:07,614][812822] Saving new best policy, reward=385.899! +[2023-07-08 03:01:11,699][812868] Updated weights for policy 0, policy_version 2000 (0.0005) +[2023-07-08 03:01:12,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8806.4, 300 sec: 8567.5). Total num frames: 1028096. Throughput: 0: 8750.7. Samples: 1007612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:01:12,607][812583] Avg episode reward: [(0, '326.106')] +[2023-07-08 03:01:16,689][812868] Updated weights for policy 0, policy_version 2080 (0.0005) +[2023-07-08 03:01:17,607][812583] Fps is (10 sec: 8192.1, 60 sec: 8738.1, 300 sec: 8552.5). Total num frames: 1069056. Throughput: 0: 8661.2. Samples: 1056840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:01:17,607][812583] Avg episode reward: [(0, '293.843')] +[2023-07-08 03:01:21,427][812868] Updated weights for policy 0, policy_version 2160 (0.0005) +[2023-07-08 03:01:22,607][812583] Fps is (10 sec: 8601.5, 60 sec: 8669.9, 300 sec: 8570.1). Total num frames: 1114112. Throughput: 0: 8618.0. Samples: 1108160. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:01:22,607][812583] Avg episode reward: [(0, '347.076')] +[2023-07-08 03:01:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002176_1114112.pth... +[2023-07-08 03:01:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001680_860160.pth +[2023-07-08 03:01:26,311][812868] Updated weights for policy 0, policy_version 2240 (0.0005) +[2023-07-08 03:01:27,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8556.1). Total num frames: 1155072. Throughput: 0: 8603.2. Samples: 1133844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:01:27,607][812583] Avg episode reward: [(0, '325.871')] +[2023-07-08 03:01:31,267][812868] Updated weights for policy 0, policy_version 2320 (0.0005) +[2023-07-08 03:01:32,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8543.1). Total num frames: 1196032. Throughput: 0: 8518.3. Samples: 1183340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:01:32,607][812583] Avg episode reward: [(0, '322.223')] +[2023-07-08 03:01:36,169][812868] Updated weights for policy 0, policy_version 2400 (0.0005) +[2023-07-08 03:01:37,607][812583] Fps is (10 sec: 8601.5, 60 sec: 8601.6, 300 sec: 8559.2). Total num frames: 1241088. Throughput: 0: 8414.1. Samples: 1233004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:01:37,607][812583] Avg episode reward: [(0, '298.935')] +[2023-07-08 03:01:37,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002424_1241088.pth... +[2023-07-08 03:01:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001928_987136.pth +[2023-07-08 03:01:40,844][812868] Updated weights for policy 0, policy_version 2480 (0.0005) +[2023-07-08 03:01:42,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8547.0). Total num frames: 1282048. Throughput: 0: 8413.9. Samples: 1259148. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:01:42,607][812583] Avg episode reward: [(0, '300.089')] +[2023-07-08 03:01:45,536][812868] Updated weights for policy 0, policy_version 2560 (0.0005) +[2023-07-08 03:01:47,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8562.0). Total num frames: 1327104. Throughput: 0: 8442.7. Samples: 1311928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:01:47,607][812583] Avg episode reward: [(0, '287.441')] +[2023-07-08 03:01:50,189][812868] Updated weights for policy 0, policy_version 2640 (0.0005) +[2023-07-08 03:01:52,607][812583] Fps is (10 sec: 9011.1, 60 sec: 8533.3, 300 sec: 8576.0). Total num frames: 1372160. Throughput: 0: 8471.0. Samples: 1364040. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:01:52,607][812583] Avg episode reward: [(0, '283.131')] +[2023-07-08 03:01:52,630][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002680_1372160.pth... +[2023-07-08 03:01:52,632][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002176_1114112.pth +[2023-07-08 03:01:54,957][812868] Updated weights for policy 0, policy_version 2720 (0.0005) +[2023-07-08 03:01:57,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8564.4). Total num frames: 1413120. Throughput: 0: 8503.0. Samples: 1390248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:01:57,607][812583] Avg episode reward: [(0, '252.917')] +[2023-07-08 03:01:59,935][812868] Updated weights for policy 0, policy_version 2800 (0.0005) +[2023-07-08 03:02:02,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8553.4). Total num frames: 1454080. Throughput: 0: 8511.4. Samples: 1439852. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:02:02,607][812583] Avg episode reward: [(0, '233.722')] +[2023-07-08 03:02:05,169][812868] Updated weights for policy 0, policy_version 2880 (0.0005) +[2023-07-08 03:02:07,607][812583] Fps is (10 sec: 7782.4, 60 sec: 8396.8, 300 sec: 8519.7). Total num frames: 1490944. Throughput: 0: 8415.6. Samples: 1486860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:02:07,607][812583] Avg episode reward: [(0, '189.576')] +[2023-07-08 03:02:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002912_1490944.pth... +[2023-07-08 03:02:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002424_1241088.pth +[2023-07-08 03:02:10,324][812868] Updated weights for policy 0, policy_version 2960 (0.0005) +[2023-07-08 03:02:12,607][812583] Fps is (10 sec: 7782.4, 60 sec: 8396.8, 300 sec: 8510.6). Total num frames: 1531904. Throughput: 0: 8378.1. Samples: 1510860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:02:12,607][812583] Avg episode reward: [(0, '207.578')] +[2023-07-08 03:02:15,544][812868] Updated weights for policy 0, policy_version 3040 (0.0005) +[2023-07-08 03:02:17,607][812583] Fps is (10 sec: 7782.5, 60 sec: 8328.5, 300 sec: 8479.8). Total num frames: 1568768. Throughput: 0: 8314.4. Samples: 1557488. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:02:17,607][812583] Avg episode reward: [(0, '214.516')] +[2023-07-08 03:02:20,756][812868] Updated weights for policy 0, policy_version 3120 (0.0005) +[2023-07-08 03:02:22,607][812583] Fps is (10 sec: 7782.4, 60 sec: 8260.3, 300 sec: 8472.3). Total num frames: 1609728. Throughput: 0: 8262.1. Samples: 1604800. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:02:22,607][812583] Avg episode reward: [(0, '172.642')] +[2023-07-08 03:02:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003144_1609728.pth... +[2023-07-08 03:02:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002680_1372160.pth +[2023-07-08 03:02:25,964][812868] Updated weights for policy 0, policy_version 3200 (0.0005) +[2023-07-08 03:02:27,607][812583] Fps is (10 sec: 8191.9, 60 sec: 8260.3, 300 sec: 8465.1). Total num frames: 1650688. Throughput: 0: 8206.8. Samples: 1628452. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-08 03:02:27,607][812583] Avg episode reward: [(0, '246.996')] +[2023-07-08 03:02:31,190][812868] Updated weights for policy 0, policy_version 3280 (0.0005) +[2023-07-08 03:02:32,607][812583] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 8437.8). Total num frames: 1687552. Throughput: 0: 8075.6. Samples: 1675328. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-08 03:02:32,607][812583] Avg episode reward: [(0, '222.381')] +[2023-07-08 03:02:36,538][812868] Updated weights for policy 0, policy_version 3360 (0.0005) +[2023-07-08 03:02:37,607][812583] Fps is (10 sec: 7372.8, 60 sec: 8055.5, 300 sec: 8411.8). Total num frames: 1724416. Throughput: 0: 7941.0. Samples: 1721384. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-08 03:02:37,607][812583] Avg episode reward: [(0, '187.423')] +[2023-07-08 03:02:37,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003376_1728512.pth... +[2023-07-08 03:02:37,614][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002912_1490944.pth +[2023-07-08 03:02:41,934][812868] Updated weights for policy 0, policy_version 3440 (0.0004) +[2023-07-08 03:02:42,607][812583] Fps is (10 sec: 7782.5, 60 sec: 8055.5, 300 sec: 8406.6). Total num frames: 1765376. Throughput: 0: 7878.4. Samples: 1744776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:02:42,607][812583] Avg episode reward: [(0, '158.054')] +[2023-07-08 03:02:47,301][812868] Updated weights for policy 0, policy_version 3520 (0.0005) +[2023-07-08 03:02:47,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7918.9, 300 sec: 8382.5). Total num frames: 1802240. Throughput: 0: 7776.3. Samples: 1789784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:02:47,607][812583] Avg episode reward: [(0, '198.426')] +[2023-07-08 03:02:52,502][812868] Updated weights for policy 0, policy_version 3600 (0.0005) +[2023-07-08 03:02:52,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7850.7, 300 sec: 8378.2). Total num frames: 1843200. Throughput: 0: 7777.5. Samples: 1836848. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:02:52,607][812583] Avg episode reward: [(0, '187.839')] +[2023-07-08 03:02:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003600_1843200.pth... +[2023-07-08 03:02:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003144_1609728.pth +[2023-07-08 03:02:57,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8355.8). Total num frames: 1880064. Throughput: 0: 7755.3. Samples: 1859848. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:02:57,607][812583] Avg episode reward: [(0, '202.364')] +[2023-07-08 03:02:57,787][812868] Updated weights for policy 0, policy_version 3680 (0.0005) +[2023-07-08 03:03:02,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8352.3). Total num frames: 1921024. Throughput: 0: 7748.2. Samples: 1906156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:03:02,607][812583] Avg episode reward: [(0, '173.736')] +[2023-07-08 03:03:03,113][812868] Updated weights for policy 0, policy_version 3760 (0.0004) +[2023-07-08 03:03:07,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8331.4). Total num frames: 1957888. Throughput: 0: 7712.4. Samples: 1951856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:03:07,608][812583] Avg episode reward: [(0, '143.653')] +[2023-07-08 03:03:07,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003824_1957888.pth... +[2023-07-08 03:03:07,614][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003376_1728512.pth +[2023-07-08 03:03:08,515][812868] Updated weights for policy 0, policy_version 3840 (0.0005) +[2023-07-08 03:03:12,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7714.1, 300 sec: 8311.5). Total num frames: 1994752. Throughput: 0: 7700.7. Samples: 1974984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:03:12,607][812583] Avg episode reward: [(0, '131.645')] +[2023-07-08 03:03:13,925][812868] Updated weights for policy 0, policy_version 3920 (0.0005) +[2023-07-08 03:03:17,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7714.1, 300 sec: 8292.3). Total num frames: 2031616. Throughput: 0: 7672.1. Samples: 2020572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:03:17,607][812583] Avg episode reward: [(0, '141.715')] +[2023-07-08 03:03:19,235][812868] Updated weights for policy 0, policy_version 4000 (0.0005) +[2023-07-08 03:03:22,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7714.1, 300 sec: 8290.3). Total num frames: 2072576. Throughput: 0: 7667.5. Samples: 2066424. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:03:22,607][812583] Avg episode reward: [(0, '142.179')] +[2023-07-08 03:03:22,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004048_2072576.pth... +[2023-07-08 03:03:22,614][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003600_1843200.pth +[2023-07-08 03:03:24,625][812868] Updated weights for policy 0, policy_version 4080 (0.0005) +[2023-07-08 03:03:27,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 8272.3). Total num frames: 2109440. Throughput: 0: 7651.7. Samples: 2089104. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:03:27,607][812583] Avg episode reward: [(0, '130.114')] +[2023-07-08 03:03:29,959][812868] Updated weights for policy 0, policy_version 4160 (0.0005) +[2023-07-08 03:03:32,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7645.9, 300 sec: 8255.0). Total num frames: 2146304. Throughput: 0: 7679.6. Samples: 2135368. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:03:32,607][812583] Avg episode reward: [(0, '121.630')] +[2023-07-08 03:03:35,402][812868] Updated weights for policy 0, policy_version 4240 (0.0005) +[2023-07-08 03:03:37,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7714.1, 300 sec: 8253.8). Total num frames: 2187264. Throughput: 0: 7642.8. Samples: 2180772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:03:37,607][812583] Avg episode reward: [(0, '145.651')] +[2023-07-08 03:03:37,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004272_2187264.pth... +[2023-07-08 03:03:37,614][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003824_1957888.pth +[2023-07-08 03:03:40,759][812868] Updated weights for policy 0, policy_version 4320 (0.0005) +[2023-07-08 03:03:42,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 8237.5). Total num frames: 2224128. Throughput: 0: 7640.2. Samples: 2203656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:03:42,607][812583] Avg episode reward: [(0, '162.623')] +[2023-07-08 03:03:46,096][812868] Updated weights for policy 0, policy_version 4400 (0.0005) +[2023-07-08 03:03:47,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7645.9, 300 sec: 8221.8). Total num frames: 2260992. Throughput: 0: 7630.0. Samples: 2249508. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:03:47,607][812583] Avg episode reward: [(0, '158.198')] +[2023-07-08 03:03:51,387][812868] Updated weights for policy 0, policy_version 4480 (0.0005) +[2023-07-08 03:03:52,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 8221.3). Total num frames: 2301952. Throughput: 0: 7652.4. Samples: 2296216. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-08 03:03:52,607][812583] Avg episode reward: [(0, '178.073')] +[2023-07-08 03:03:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004496_2301952.pth... +[2023-07-08 03:03:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004048_2072576.pth +[2023-07-08 03:03:56,575][812868] Updated weights for policy 0, policy_version 4560 (0.0005) +[2023-07-08 03:03:57,607][812583] Fps is (10 sec: 8192.1, 60 sec: 7714.1, 300 sec: 8220.7). Total num frames: 2342912. Throughput: 0: 7651.2. Samples: 2319288. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:03:57,607][812583] Avg episode reward: [(0, '203.385')] +[2023-07-08 03:04:01,660][812868] Updated weights for policy 0, policy_version 4640 (0.0005) +[2023-07-08 03:04:02,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 8206.1). Total num frames: 2379776. Throughput: 0: 7710.8. Samples: 2367560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:04:02,607][812583] Avg episode reward: [(0, '340.696')] +[2023-07-08 03:04:06,851][812868] Updated weights for policy 0, policy_version 4720 (0.0005) +[2023-07-08 03:04:07,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7714.1, 300 sec: 8205.9). Total num frames: 2420736. Throughput: 0: 7759.1. Samples: 2415584. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:04:07,607][812583] Avg episode reward: [(0, '228.866')] +[2023-07-08 03:04:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004728_2420736.pth... +[2023-07-08 03:04:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004272_2187264.pth +[2023-07-08 03:04:11,919][812868] Updated weights for policy 0, policy_version 4800 (0.0005) +[2023-07-08 03:04:12,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7782.4, 300 sec: 8344.7). Total num frames: 2461696. Throughput: 0: 7788.9. Samples: 2439604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:04:12,607][812583] Avg episode reward: [(0, '213.689')] +[2023-07-08 03:04:17,248][812868] Updated weights for policy 0, policy_version 4880 (0.0005) +[2023-07-08 03:04:17,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8455.8). Total num frames: 2498560. Throughput: 0: 7800.5. Samples: 2486392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:04:17,607][812583] Avg episode reward: [(0, '179.077')] +[2023-07-08 03:04:22,359][812868] Updated weights for policy 0, policy_version 4960 (0.0005) +[2023-07-08 03:04:22,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8428.0). Total num frames: 2539520. Throughput: 0: 7849.7. Samples: 2534008. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-08 03:04:22,607][812583] Avg episode reward: [(0, '147.280')] +[2023-07-08 03:04:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004960_2539520.pth... +[2023-07-08 03:04:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004496_2301952.pth +[2023-07-08 03:04:27,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7782.4, 300 sec: 8386.4). Total num frames: 2576384. Throughput: 0: 7872.6. Samples: 2557920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:04:27,607][812583] Avg episode reward: [(0, '152.389')] +[2023-07-08 03:04:27,609][812868] Updated weights for policy 0, policy_version 5040 (0.0005) +[2023-07-08 03:04:32,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 8358.6). Total num frames: 2617344. Throughput: 0: 7888.8. Samples: 2604504. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:04:32,607][812583] Avg episode reward: [(0, '143.964')] +[2023-07-08 03:04:32,837][812868] Updated weights for policy 0, policy_version 5120 (0.0005) +[2023-07-08 03:04:37,607][812583] Fps is (10 sec: 8191.9, 60 sec: 7850.7, 300 sec: 8317.0). Total num frames: 2658304. Throughput: 0: 7888.1. Samples: 2651180. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:04:37,607][812583] Avg episode reward: [(0, '143.055')] +[2023-07-08 03:04:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005192_2658304.pth... +[2023-07-08 03:04:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004728_2420736.pth +[2023-07-08 03:04:38,124][812868] Updated weights for policy 0, policy_version 5200 (0.0005) +[2023-07-08 03:04:42,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7850.7, 300 sec: 8289.2). Total num frames: 2695168. Throughput: 0: 7899.2. Samples: 2674752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:04:42,607][812583] Avg episode reward: [(0, '165.957')] +[2023-07-08 03:04:43,152][812868] Updated weights for policy 0, policy_version 5280 (0.0005) +[2023-07-08 03:04:47,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7918.9, 300 sec: 8261.4). Total num frames: 2736128. Throughput: 0: 7897.9. Samples: 2722968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:04:47,607][812583] Avg episode reward: [(0, '129.692')] +[2023-07-08 03:04:48,524][812868] Updated weights for policy 0, policy_version 5360 (0.0005) +[2023-07-08 03:04:52,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7850.7, 300 sec: 8219.8). Total num frames: 2772992. Throughput: 0: 7851.4. Samples: 2768896. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:04:52,607][812583] Avg episode reward: [(0, '130.904')] +[2023-07-08 03:04:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005416_2772992.pth... +[2023-07-08 03:04:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004960_2539520.pth +[2023-07-08 03:04:53,826][812868] Updated weights for policy 0, policy_version 5440 (0.0005) +[2023-07-08 03:04:57,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7782.4, 300 sec: 8178.1). Total num frames: 2809856. Throughput: 0: 7833.9. Samples: 2792128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:04:57,607][812583] Avg episode reward: [(0, '126.397')] +[2023-07-08 03:04:59,199][812868] Updated weights for policy 0, policy_version 5520 (0.0005) +[2023-07-08 03:05:02,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 8136.5). Total num frames: 2850816. Throughput: 0: 7808.9. Samples: 2837792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:05:02,607][812583] Avg episode reward: [(0, '121.591')] +[2023-07-08 03:05:04,520][812868] Updated weights for policy 0, policy_version 5600 (0.0005) +[2023-07-08 03:05:07,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8094.8). Total num frames: 2887680. Throughput: 0: 7769.8. Samples: 2883648. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:05:07,607][812583] Avg episode reward: [(0, '127.347')] +[2023-07-08 03:05:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005640_2887680.pth... +[2023-07-08 03:05:07,612][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005192_2658304.pth +[2023-07-08 03:05:09,707][812868] Updated weights for policy 0, policy_version 5680 (0.0005) +[2023-07-08 03:05:12,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8080.9). Total num frames: 2928640. Throughput: 0: 7780.0. Samples: 2908020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:05:12,607][812583] Avg episode reward: [(0, '124.227')] +[2023-07-08 03:05:15,076][812868] Updated weights for policy 0, policy_version 5760 (0.0005) +[2023-07-08 03:05:17,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7782.4, 300 sec: 8039.3). Total num frames: 2965504. Throughput: 0: 7759.3. Samples: 2953672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:05:17,607][812583] Avg episode reward: [(0, '142.876')] +[2023-07-08 03:05:20,312][812868] Updated weights for policy 0, policy_version 5840 (0.0005) +[2023-07-08 03:05:22,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8025.4). Total num frames: 3006464. Throughput: 0: 7781.8. Samples: 3001360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:05:22,607][812583] Avg episode reward: [(0, '251.672')] +[2023-07-08 03:05:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005872_3006464.pth... +[2023-07-08 03:05:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005416_2772992.pth +[2023-07-08 03:05:25,517][812868] Updated weights for policy 0, policy_version 5920 (0.0005) +[2023-07-08 03:05:27,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7850.7, 300 sec: 8025.4). Total num frames: 3047424. Throughput: 0: 7775.4. Samples: 3024644. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:05:27,607][812583] Avg episode reward: [(0, '153.272')] +[2023-07-08 03:05:30,512][812868] Updated weights for policy 0, policy_version 6000 (0.0005) +[2023-07-08 03:05:32,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7850.7, 300 sec: 8011.5). Total num frames: 3088384. Throughput: 0: 7783.7. Samples: 3073236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:05:32,607][812583] Avg episode reward: [(0, '183.983')] +[2023-07-08 03:05:35,492][812868] Updated weights for policy 0, policy_version 6080 (0.0005) +[2023-07-08 03:05:37,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7782.4, 300 sec: 7983.7). Total num frames: 3125248. Throughput: 0: 7841.6. Samples: 3121768. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:05:37,607][812583] Avg episode reward: [(0, '171.717')] +[2023-07-08 03:05:37,614][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006112_3129344.pth... +[2023-07-08 03:05:37,616][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005640_2887680.pth +[2023-07-08 03:05:40,811][812868] Updated weights for policy 0, policy_version 6160 (0.0005) +[2023-07-08 03:05:42,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 7969.8). Total num frames: 3166208. Throughput: 0: 7857.3. Samples: 3145704. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:05:42,607][812583] Avg episode reward: [(0, '157.849')] +[2023-07-08 03:05:46,199][812868] Updated weights for policy 0, policy_version 6240 (0.0005) +[2023-07-08 03:05:47,607][812583] Fps is (10 sec: 7782.6, 60 sec: 7782.4, 300 sec: 7942.1). Total num frames: 3203072. Throughput: 0: 7845.7. Samples: 3190848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:05:47,607][812583] Avg episode reward: [(0, '159.853')] +[2023-07-08 03:05:51,629][812868] Updated weights for policy 0, policy_version 6320 (0.0005) +[2023-07-08 03:05:52,607][812583] Fps is (10 sec: 7372.7, 60 sec: 7782.4, 300 sec: 7914.3). Total num frames: 3239936. Throughput: 0: 7830.0. Samples: 3235996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:05:52,607][812583] Avg episode reward: [(0, '140.800')] +[2023-07-08 03:05:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006328_3239936.pth... +[2023-07-08 03:05:52,612][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005872_3006464.pth +[2023-07-08 03:05:56,966][812868] Updated weights for policy 0, policy_version 6400 (0.0006) +[2023-07-08 03:05:57,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7850.7, 300 sec: 7914.3). Total num frames: 3280896. Throughput: 0: 7818.4. Samples: 3259848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:05:57,607][812583] Avg episode reward: [(0, '134.483')] +[2023-07-08 03:06:02,432][812868] Updated weights for policy 0, policy_version 6480 (0.0006) +[2023-07-08 03:06:02,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7782.4, 300 sec: 7900.4). Total num frames: 3317760. Throughput: 0: 7813.1. Samples: 3305260. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:06:02,607][812583] Avg episode reward: [(0, '128.116')] +[2023-07-08 03:06:07,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7782.4, 300 sec: 7886.5). Total num frames: 3354624. Throughput: 0: 7744.6. Samples: 3349868. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:06:07,607][812583] Avg episode reward: [(0, '117.912')] +[2023-07-08 03:06:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006552_3354624.pth... +[2023-07-08 03:06:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006112_3129344.pth +[2023-07-08 03:06:07,873][812868] Updated weights for policy 0, policy_version 6560 (0.0005) +[2023-07-08 03:06:12,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7886.5). Total num frames: 3395584. Throughput: 0: 7733.7. Samples: 3372660. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:06:12,607][812583] Avg episode reward: [(0, '131.352')] +[2023-07-08 03:06:13,036][812868] Updated weights for policy 0, policy_version 6640 (0.0006) +[2023-07-08 03:06:17,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7782.4, 300 sec: 7858.8). Total num frames: 3432448. Throughput: 0: 7710.9. Samples: 3420224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:06:17,607][812583] Avg episode reward: [(0, '148.918')] +[2023-07-08 03:06:18,327][812868] Updated weights for policy 0, policy_version 6720 (0.0006) +[2023-07-08 03:06:22,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7858.8). Total num frames: 3473408. Throughput: 0: 7669.3. Samples: 3466888. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:06:22,607][812583] Avg episode reward: [(0, '171.127')] +[2023-07-08 03:06:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006784_3473408.pth... +[2023-07-08 03:06:22,614][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006328_3239936.pth +[2023-07-08 03:06:23,598][812868] Updated weights for policy 0, policy_version 6800 (0.0005) +[2023-07-08 03:06:27,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7844.9). Total num frames: 3510272. Throughput: 0: 7647.8. Samples: 3489856. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:06:27,607][812583] Avg episode reward: [(0, '193.851')] +[2023-07-08 03:06:28,924][812868] Updated weights for policy 0, policy_version 6880 (0.0005) +[2023-07-08 03:06:32,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7645.9, 300 sec: 7817.1). Total num frames: 3547136. Throughput: 0: 7655.2. Samples: 3535332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:06:32,607][812583] Avg episode reward: [(0, '194.110')] +[2023-07-08 03:06:34,347][812868] Updated weights for policy 0, policy_version 6960 (0.0005) +[2023-07-08 03:06:37,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7817.1). Total num frames: 3588096. Throughput: 0: 7681.3. Samples: 3581656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:06:37,607][812583] Avg episode reward: [(0, '147.272')] +[2023-07-08 03:06:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007008_3588096.pth... +[2023-07-08 03:06:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006552_3354624.pth +[2023-07-08 03:06:39,667][812868] Updated weights for policy 0, policy_version 7040 (0.0005) +[2023-07-08 03:06:42,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7789.3). Total num frames: 3624960. Throughput: 0: 7659.9. Samples: 3604544. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:06:42,607][812583] Avg episode reward: [(0, '183.121')] +[2023-07-08 03:06:44,853][812868] Updated weights for policy 0, policy_version 7120 (0.0005) +[2023-07-08 03:06:47,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7775.5). Total num frames: 3665920. Throughput: 0: 7715.2. Samples: 3652444. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:06:47,607][812583] Avg episode reward: [(0, '176.901')] +[2023-07-08 03:06:49,914][812868] Updated weights for policy 0, policy_version 7200 (0.0005) +[2023-07-08 03:06:52,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7782.4, 300 sec: 7775.5). Total num frames: 3706880. Throughput: 0: 7794.2. Samples: 3700608. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:06:52,607][812583] Avg episode reward: [(0, '174.963')] +[2023-07-08 03:06:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007240_3706880.pth... +[2023-07-08 03:06:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006784_3473408.pth +[2023-07-08 03:06:55,076][812868] Updated weights for policy 0, policy_version 7280 (0.0006) +[2023-07-08 03:06:57,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7714.1, 300 sec: 7761.6). Total num frames: 3743744. Throughput: 0: 7806.8. Samples: 3723964. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:06:57,607][812583] Avg episode reward: [(0, '156.674')] +[2023-07-08 03:07:00,438][812868] Updated weights for policy 0, policy_version 7360 (0.0006) +[2023-07-08 03:07:02,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7714.1, 300 sec: 7761.6). Total num frames: 3780608. Throughput: 0: 7776.8. Samples: 3770180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:07:02,607][812583] Avg episode reward: [(0, '156.068')] +[2023-07-08 03:07:05,803][812868] Updated weights for policy 0, policy_version 7440 (0.0006) +[2023-07-08 03:07:07,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7782.4, 300 sec: 7761.6). Total num frames: 3821568. Throughput: 0: 7757.2. Samples: 3815964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:07:07,607][812583] Avg episode reward: [(0, '190.593')] +[2023-07-08 03:07:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007464_3821568.pth... +[2023-07-08 03:07:07,612][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007008_3588096.pth +[2023-07-08 03:07:11,202][812868] Updated weights for policy 0, policy_version 7520 (0.0006) +[2023-07-08 03:07:12,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7714.1, 300 sec: 7761.6). Total num frames: 3858432. Throughput: 0: 7750.1. Samples: 3838612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:07:12,607][812583] Avg episode reward: [(0, '193.371')] +[2023-07-08 03:07:16,440][812868] Updated weights for policy 0, policy_version 7600 (0.0005) +[2023-07-08 03:07:17,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7761.6). Total num frames: 3899392. Throughput: 0: 7784.3. Samples: 3885624. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:07:17,607][812583] Avg episode reward: [(0, '248.789')] +[2023-07-08 03:07:21,559][812868] Updated weights for policy 0, policy_version 7680 (0.0005) +[2023-07-08 03:07:22,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7782.4, 300 sec: 7761.6). Total num frames: 3940352. Throughput: 0: 7807.9. Samples: 3933012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:07:22,607][812583] Avg episode reward: [(0, '290.607')] +[2023-07-08 03:07:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007696_3940352.pth... +[2023-07-08 03:07:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007240_3706880.pth +[2023-07-08 03:07:26,492][812868] Updated weights for policy 0, policy_version 7760 (0.0006) +[2023-07-08 03:07:27,607][812583] Fps is (10 sec: 8192.1, 60 sec: 7850.7, 300 sec: 7775.5). Total num frames: 3981312. Throughput: 0: 7847.7. Samples: 3957692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:07:27,607][812583] Avg episode reward: [(0, '330.948')] +[2023-07-08 03:07:31,305][812868] Updated weights for policy 0, policy_version 7840 (0.0006) +[2023-07-08 03:07:32,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7918.9, 300 sec: 7789.3). Total num frames: 4022272. Throughput: 0: 7918.4. Samples: 4008772. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:07:32,607][812583] Avg episode reward: [(0, '327.668')] +[2023-07-08 03:07:36,084][812868] Updated weights for policy 0, policy_version 7920 (0.0006) +[2023-07-08 03:07:37,607][812583] Fps is (10 sec: 8601.6, 60 sec: 7987.2, 300 sec: 7803.2). Total num frames: 4067328. Throughput: 0: 7983.7. Samples: 4059876. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:07:37,607][812583] Avg episode reward: [(0, '374.687')] +[2023-07-08 03:07:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007944_4067328.pth... +[2023-07-08 03:07:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007464_3821568.pth +[2023-07-08 03:07:40,869][812868] Updated weights for policy 0, policy_version 8000 (0.0005) +[2023-07-08 03:07:42,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8055.5, 300 sec: 7817.1). Total num frames: 4108288. Throughput: 0: 8031.7. Samples: 4085392. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:07:42,607][812583] Avg episode reward: [(0, '290.166')] +[2023-07-08 03:07:45,793][812868] Updated weights for policy 0, policy_version 8080 (0.0006) +[2023-07-08 03:07:47,607][812583] Fps is (10 sec: 8192.1, 60 sec: 8055.5, 300 sec: 7817.1). Total num frames: 4149248. Throughput: 0: 8137.8. Samples: 4136380. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:07:47,607][812583] Avg episode reward: [(0, '437.649')] +[2023-07-08 03:07:47,608][812822] Saving new best policy, reward=437.649! +[2023-07-08 03:07:50,812][812868] Updated weights for policy 0, policy_version 8160 (0.0005) +[2023-07-08 03:07:52,607][812583] Fps is (10 sec: 8191.9, 60 sec: 8055.5, 300 sec: 7831.0). Total num frames: 4190208. Throughput: 0: 8215.6. Samples: 4185664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:07:52,607][812583] Avg episode reward: [(0, '379.224')] +[2023-07-08 03:07:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008184_4190208.pth... +[2023-07-08 03:07:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007696_3940352.pth +[2023-07-08 03:07:55,597][812868] Updated weights for policy 0, policy_version 8240 (0.0006) +[2023-07-08 03:07:57,607][812583] Fps is (10 sec: 8601.5, 60 sec: 8192.0, 300 sec: 7844.9). Total num frames: 4235264. Throughput: 0: 8270.4. Samples: 4210780. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:07:57,607][812583] Avg episode reward: [(0, '445.167')] +[2023-07-08 03:07:57,608][812822] Saving new best policy, reward=445.167! +[2023-07-08 03:08:00,447][812868] Updated weights for policy 0, policy_version 8320 (0.0005) +[2023-07-08 03:08:02,607][812583] Fps is (10 sec: 8601.7, 60 sec: 8260.3, 300 sec: 7858.8). Total num frames: 4276224. Throughput: 0: 8359.7. Samples: 4261812. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:08:02,607][812583] Avg episode reward: [(0, '382.061')] +[2023-07-08 03:08:05,416][812868] Updated weights for policy 0, policy_version 8400 (0.0006) +[2023-07-08 03:08:07,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 7872.6). Total num frames: 4317184. Throughput: 0: 8410.7. Samples: 4311492. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:08:07,607][812583] Avg episode reward: [(0, '453.068')] +[2023-07-08 03:08:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008432_4317184.pth... +[2023-07-08 03:08:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007944_4067328.pth +[2023-07-08 03:08:07,614][812822] Saving new best policy, reward=453.068! +[2023-07-08 03:08:10,272][812868] Updated weights for policy 0, policy_version 8480 (0.0005) +[2023-07-08 03:08:12,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 7886.5). Total num frames: 4358144. Throughput: 0: 8433.2. Samples: 4337188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:08:12,607][812583] Avg episode reward: [(0, '499.222')] +[2023-07-08 03:08:12,608][812822] Saving new best policy, reward=499.222! +[2023-07-08 03:08:15,202][812868] Updated weights for policy 0, policy_version 8560 (0.0005) +[2023-07-08 03:08:17,607][812583] Fps is (10 sec: 8192.1, 60 sec: 8328.5, 300 sec: 7886.5). Total num frames: 4399104. Throughput: 0: 8401.0. Samples: 4386816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:08:17,607][812583] Avg episode reward: [(0, '441.733')] +[2023-07-08 03:08:20,011][812868] Updated weights for policy 0, policy_version 8640 (0.0005) +[2023-07-08 03:08:22,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 7914.3). Total num frames: 4444160. Throughput: 0: 8404.6. Samples: 4438084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:08:22,607][812583] Avg episode reward: [(0, '447.890')] +[2023-07-08 03:08:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008680_4444160.pth... +[2023-07-08 03:08:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008184_4190208.pth +[2023-07-08 03:08:24,702][812868] Updated weights for policy 0, policy_version 8720 (0.0006) +[2023-07-08 03:08:27,607][812583] Fps is (10 sec: 9011.1, 60 sec: 8465.1, 300 sec: 7942.1). Total num frames: 4489216. Throughput: 0: 8427.7. Samples: 4464640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:08:27,607][812583] Avg episode reward: [(0, '480.108')] +[2023-07-08 03:08:29,556][812868] Updated weights for policy 0, policy_version 8800 (0.0005) +[2023-07-08 03:08:32,607][812583] Fps is (10 sec: 8601.7, 60 sec: 8465.1, 300 sec: 7942.1). Total num frames: 4530176. Throughput: 0: 8409.5. Samples: 4514808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:08:32,607][812583] Avg episode reward: [(0, '512.026')] +[2023-07-08 03:08:32,608][812822] Saving new best policy, reward=512.026! +[2023-07-08 03:08:34,318][812868] Updated weights for policy 0, policy_version 8880 (0.0005) +[2023-07-08 03:08:37,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 7969.8). Total num frames: 4575232. Throughput: 0: 8482.4. Samples: 4567372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:08:37,607][812583] Avg episode reward: [(0, '462.521')] +[2023-07-08 03:08:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008936_4575232.pth... +[2023-07-08 03:08:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008432_4317184.pth +[2023-07-08 03:08:39,006][812868] Updated weights for policy 0, policy_version 8960 (0.0006) +[2023-07-08 03:08:42,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 7983.7). Total num frames: 4616192. Throughput: 0: 8500.4. Samples: 4593296. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:08:42,607][812583] Avg episode reward: [(0, '483.030')] +[2023-07-08 03:08:43,719][812868] Updated weights for policy 0, policy_version 9040 (0.0006) +[2023-07-08 03:08:47,607][812583] Fps is (10 sec: 8601.7, 60 sec: 8533.3, 300 sec: 7997.6). Total num frames: 4661248. Throughput: 0: 8516.1. Samples: 4645036. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:08:47,608][812583] Avg episode reward: [(0, '408.333')] +[2023-07-08 03:08:48,510][812868] Updated weights for policy 0, policy_version 9120 (0.0006) +[2023-07-08 03:08:52,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 7997.6). Total num frames: 4702208. Throughput: 0: 8519.4. Samples: 4694864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:08:52,607][812583] Avg episode reward: [(0, '378.055')] +[2023-07-08 03:08:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009184_4702208.pth... +[2023-07-08 03:08:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008680_4444160.pth +[2023-07-08 03:08:53,549][812868] Updated weights for policy 0, policy_version 9200 (0.0006) +[2023-07-08 03:08:57,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8011.5). Total num frames: 4743168. Throughput: 0: 8502.0. Samples: 4719776. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:08:57,607][812583] Avg episode reward: [(0, '448.975')] +[2023-07-08 03:08:58,442][812868] Updated weights for policy 0, policy_version 9280 (0.0006) +[2023-07-08 03:09:02,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8011.5). Total num frames: 4784128. Throughput: 0: 8516.8. Samples: 4770072. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:09:02,607][812583] Avg episode reward: [(0, '407.584')] +[2023-07-08 03:09:03,440][812868] Updated weights for policy 0, policy_version 9360 (0.0005) +[2023-07-08 03:09:07,607][812583] Fps is (10 sec: 8191.9, 60 sec: 8465.1, 300 sec: 8011.5). Total num frames: 4825088. Throughput: 0: 8491.0. Samples: 4820180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:09:07,607][812583] Avg episode reward: [(0, '369.679')] +[2023-07-08 03:09:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009424_4825088.pth... +[2023-07-08 03:09:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008936_4575232.pth +[2023-07-08 03:09:08,185][812868] Updated weights for policy 0, policy_version 9440 (0.0006) +[2023-07-08 03:09:12,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8039.3). Total num frames: 4870144. Throughput: 0: 8473.9. Samples: 4845964. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:09:12,607][812583] Avg episode reward: [(0, '387.414')] +[2023-07-08 03:09:12,909][812868] Updated weights for policy 0, policy_version 9520 (0.0005) +[2023-07-08 03:09:17,607][812583] Fps is (10 sec: 8192.1, 60 sec: 8465.1, 300 sec: 8025.4). Total num frames: 4907008. Throughput: 0: 8475.0. Samples: 4896184. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:09:17,607][812583] Avg episode reward: [(0, '310.604')] +[2023-07-08 03:09:18,112][812868] Updated weights for policy 0, policy_version 9600 (0.0005) +[2023-07-08 03:09:22,607][812583] Fps is (10 sec: 7782.4, 60 sec: 8396.8, 300 sec: 8039.3). Total num frames: 4947968. Throughput: 0: 8371.9. Samples: 4944108. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:09:22,607][812583] Avg episode reward: [(0, '454.029')] +[2023-07-08 03:09:22,650][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009672_4952064.pth... +[2023-07-08 03:09:22,653][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009184_4702208.pth +[2023-07-08 03:09:23,173][812868] Updated weights for policy 0, policy_version 9680 (0.0005) +[2023-07-08 03:09:27,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8053.2). Total num frames: 4993024. Throughput: 0: 8338.2. Samples: 4968512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:09:27,607][812583] Avg episode reward: [(0, '340.675')] +[2023-07-08 03:09:28,082][812868] Updated weights for policy 0, policy_version 9760 (0.0005) +[2023-07-08 03:09:32,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8053.2). Total num frames: 5033984. Throughput: 0: 8310.6. Samples: 5019012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:09:32,607][812583] Avg episode reward: [(0, '400.407')] +[2023-07-08 03:09:32,837][812868] Updated weights for policy 0, policy_version 9840 (0.0005) +[2023-07-08 03:09:37,607][812583] Fps is (10 sec: 8191.9, 60 sec: 8328.5, 300 sec: 8067.0). Total num frames: 5074944. Throughput: 0: 8355.2. Samples: 5070848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:09:37,607][812583] Avg episode reward: [(0, '351.452')] +[2023-07-08 03:09:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009912_5074944.pth... +[2023-07-08 03:09:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009424_4825088.pth +[2023-07-08 03:09:37,688][812868] Updated weights for policy 0, policy_version 9920 (0.0005) +[2023-07-08 03:09:42,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8067.0). Total num frames: 5115904. Throughput: 0: 8347.7. Samples: 5095424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:09:42,607][812583] Avg episode reward: [(0, '356.298')] +[2023-07-08 03:09:42,788][812868] Updated weights for policy 0, policy_version 10000 (0.0005) +[2023-07-08 03:09:47,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8080.9). Total num frames: 5156864. Throughput: 0: 8312.4. Samples: 5144128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:09:47,607][812583] Avg episode reward: [(0, '389.404')] +[2023-07-08 03:09:47,831][812868] Updated weights for policy 0, policy_version 10080 (0.0005) +[2023-07-08 03:09:52,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8094.8). Total num frames: 5197824. Throughput: 0: 8268.9. Samples: 5192280. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:09:52,607][812583] Avg episode reward: [(0, '347.826')] +[2023-07-08 03:09:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010152_5197824.pth... +[2023-07-08 03:09:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009672_4952064.pth +[2023-07-08 03:09:52,840][812868] Updated weights for policy 0, policy_version 10160 (0.0005) +[2023-07-08 03:09:57,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8094.8). Total num frames: 5238784. Throughput: 0: 8271.5. Samples: 5218180. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:09:57,607][812583] Avg episode reward: [(0, '316.724')] +[2023-07-08 03:09:57,684][812868] Updated weights for policy 0, policy_version 10240 (0.0005) +[2023-07-08 03:10:02,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8108.7). Total num frames: 5279744. Throughput: 0: 8254.0. Samples: 5267616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:10:02,607][812583] Avg episode reward: [(0, '254.715')] +[2023-07-08 03:10:02,661][812868] Updated weights for policy 0, policy_version 10320 (0.0005) +[2023-07-08 03:10:07,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8108.7). Total num frames: 5320704. Throughput: 0: 8262.6. Samples: 5315924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:10:07,607][812583] Avg episode reward: [(0, '265.888')] +[2023-07-08 03:10:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010392_5320704.pth... +[2023-07-08 03:10:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009912_5074944.pth +[2023-07-08 03:10:07,851][812868] Updated weights for policy 0, policy_version 10400 (0.0006) +[2023-07-08 03:10:12,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8122.6). Total num frames: 5361664. Throughput: 0: 8249.9. Samples: 5339760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:10:12,607][812583] Avg episode reward: [(0, '268.471')] +[2023-07-08 03:10:12,811][812868] Updated weights for policy 0, policy_version 10480 (0.0005) +[2023-07-08 03:10:17,607][812583] Fps is (10 sec: 8192.1, 60 sec: 8260.3, 300 sec: 8122.6). Total num frames: 5402624. Throughput: 0: 8232.7. Samples: 5389484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:10:17,607][812583] Avg episode reward: [(0, '313.686')] +[2023-07-08 03:10:17,840][812868] Updated weights for policy 0, policy_version 10560 (0.0005) +[2023-07-08 03:10:22,607][812583] Fps is (10 sec: 8191.9, 60 sec: 8260.3, 300 sec: 8122.6). Total num frames: 5443584. Throughput: 0: 8152.2. Samples: 5437700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:10:22,607][812583] Avg episode reward: [(0, '291.868')] +[2023-07-08 03:10:22,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010632_5443584.pth... +[2023-07-08 03:10:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010152_5197824.pth +[2023-07-08 03:10:22,946][812868] Updated weights for policy 0, policy_version 10640 (0.0005) +[2023-07-08 03:10:27,607][812583] Fps is (10 sec: 8191.9, 60 sec: 8192.0, 300 sec: 8122.6). Total num frames: 5484544. Throughput: 0: 8135.9. Samples: 5461540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:10:27,607][812583] Avg episode reward: [(0, '339.716')] +[2023-07-08 03:10:27,916][812868] Updated weights for policy 0, policy_version 10720 (0.0005) +[2023-07-08 03:10:32,607][812583] Fps is (10 sec: 8192.1, 60 sec: 8192.0, 300 sec: 8136.5). Total num frames: 5525504. Throughput: 0: 8186.1. Samples: 5512504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:10:32,607][812583] Avg episode reward: [(0, '275.299')] +[2023-07-08 03:10:32,766][812868] Updated weights for policy 0, policy_version 10800 (0.0005) +[2023-07-08 03:10:37,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8136.5). Total num frames: 5566464. Throughput: 0: 8225.8. Samples: 5562440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:10:37,607][812583] Avg episode reward: [(0, '225.467')] +[2023-07-08 03:10:37,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010880_5570560.pth... +[2023-07-08 03:10:37,612][812868] Updated weights for policy 0, policy_version 10880 (0.0005) +[2023-07-08 03:10:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010392_5320704.pth +[2023-07-08 03:10:42,607][812868] Updated weights for policy 0, policy_version 10960 (0.0005) +[2023-07-08 03:10:42,610][812583] Fps is (10 sec: 8598.6, 60 sec: 8259.8, 300 sec: 8164.1). Total num frames: 5611520. Throughput: 0: 8195.5. Samples: 5587008. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:10:42,611][812583] Avg episode reward: [(0, '285.244')] +[2023-07-08 03:10:47,474][812868] Updated weights for policy 0, policy_version 11040 (0.0006) +[2023-07-08 03:10:47,607][812583] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 8178.1). Total num frames: 5652480. Throughput: 0: 8208.8. Samples: 5637012. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:10:47,607][812583] Avg episode reward: [(0, '248.028')] +[2023-07-08 03:10:52,432][812868] Updated weights for policy 0, policy_version 11120 (0.0006) +[2023-07-08 03:10:52,607][812583] Fps is (10 sec: 8194.8, 60 sec: 8260.3, 300 sec: 8178.1). Total num frames: 5693440. Throughput: 0: 8245.7. Samples: 5686980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:10:52,607][812583] Avg episode reward: [(0, '283.344')] +[2023-07-08 03:10:52,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011120_5693440.pth... +[2023-07-08 03:10:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010632_5443584.pth +[2023-07-08 03:10:57,268][812868] Updated weights for policy 0, policy_version 11200 (0.0005) +[2023-07-08 03:10:57,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8192.0). Total num frames: 5734400. Throughput: 0: 8292.0. Samples: 5712900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:10:57,607][812583] Avg episode reward: [(0, '390.643')] +[2023-07-08 03:11:01,981][812868] Updated weights for policy 0, policy_version 11280 (0.0005) +[2023-07-08 03:11:02,607][812583] Fps is (10 sec: 8601.7, 60 sec: 8328.5, 300 sec: 8219.8). Total num frames: 5779456. Throughput: 0: 8331.0. Samples: 5764380. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:11:02,607][812583] Avg episode reward: [(0, '297.492')] +[2023-07-08 03:11:06,890][812868] Updated weights for policy 0, policy_version 11360 (0.0005) +[2023-07-08 03:11:07,607][812583] Fps is (10 sec: 8601.5, 60 sec: 8328.5, 300 sec: 8219.8). Total num frames: 5820416. Throughput: 0: 8379.2. Samples: 5814764. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:11:07,607][812583] Avg episode reward: [(0, '224.658')] +[2023-07-08 03:11:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011368_5820416.pth... +[2023-07-08 03:11:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010880_5570560.pth +[2023-07-08 03:11:11,812][812868] Updated weights for policy 0, policy_version 11440 (0.0005) +[2023-07-08 03:11:12,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8233.7). Total num frames: 5861376. Throughput: 0: 8400.3. Samples: 5839552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:11:12,607][812583] Avg episode reward: [(0, '273.921')] +[2023-07-08 03:11:16,713][812868] Updated weights for policy 0, policy_version 11520 (0.0005) +[2023-07-08 03:11:17,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8233.7). Total num frames: 5902336. Throughput: 0: 8389.6. Samples: 5890036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:11:17,607][812583] Avg episode reward: [(0, '346.702')] +[2023-07-08 03:11:21,762][812868] Updated weights for policy 0, policy_version 11600 (0.0006) +[2023-07-08 03:11:22,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8247.5). Total num frames: 5943296. Throughput: 0: 8369.3. Samples: 5939060. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:11:22,607][812583] Avg episode reward: [(0, '252.814')] +[2023-07-08 03:11:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011608_5943296.pth... +[2023-07-08 03:11:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011120_5693440.pth +[2023-07-08 03:11:26,771][812868] Updated weights for policy 0, policy_version 11680 (0.0005) +[2023-07-08 03:11:27,607][812583] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8261.4). Total num frames: 5984256. Throughput: 0: 8353.1. Samples: 5962868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:11:27,607][812583] Avg episode reward: [(0, '254.848')] +[2023-07-08 03:11:32,136][812868] Updated weights for policy 0, policy_version 11760 (0.0005) +[2023-07-08 03:11:32,607][812583] Fps is (10 sec: 7782.5, 60 sec: 8260.3, 300 sec: 8247.5). Total num frames: 6021120. Throughput: 0: 8287.2. Samples: 6009936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:11:32,607][812583] Avg episode reward: [(0, '271.255')] +[2023-07-08 03:11:37,273][812868] Updated weights for policy 0, policy_version 11840 (0.0005) +[2023-07-08 03:11:37,607][812583] Fps is (10 sec: 7782.4, 60 sec: 8260.3, 300 sec: 8261.4). Total num frames: 6062080. Throughput: 0: 8242.9. Samples: 6057908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:11:37,607][812583] Avg episode reward: [(0, '191.303')] +[2023-07-08 03:11:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011840_6062080.pth... +[2023-07-08 03:11:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011368_5820416.pth +[2023-07-08 03:11:42,435][812868] Updated weights for policy 0, policy_version 11920 (0.0005) +[2023-07-08 03:11:42,607][812583] Fps is (10 sec: 8191.9, 60 sec: 8192.5, 300 sec: 8261.4). Total num frames: 6103040. Throughput: 0: 8183.8. Samples: 6081172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:11:42,607][812583] Avg episode reward: [(0, '151.274')] +[2023-07-08 03:11:47,607][812583] Fps is (10 sec: 7782.4, 60 sec: 8123.7, 300 sec: 8247.5). Total num frames: 6139904. Throughput: 0: 8083.0. Samples: 6128116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:11:47,607][812583] Avg episode reward: [(0, '168.107')] +[2023-07-08 03:11:47,677][812868] Updated weights for policy 0, policy_version 12000 (0.0005) +[2023-07-08 03:11:52,607][812583] Fps is (10 sec: 7782.3, 60 sec: 8123.7, 300 sec: 8261.4). Total num frames: 6180864. Throughput: 0: 7995.8. Samples: 6174576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:11:52,607][812583] Avg episode reward: [(0, '134.998')] +[2023-07-08 03:11:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012072_6180864.pth... +[2023-07-08 03:11:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011608_5943296.pth +[2023-07-08 03:11:52,941][812868] Updated weights for policy 0, policy_version 12080 (0.0005) +[2023-07-08 03:11:57,607][812583] Fps is (10 sec: 7782.4, 60 sec: 8055.5, 300 sec: 8261.4). Total num frames: 6217728. Throughput: 0: 7960.0. Samples: 6197752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:11:57,607][812583] Avg episode reward: [(0, '137.237')] +[2023-07-08 03:11:58,393][812868] Updated weights for policy 0, policy_version 12160 (0.0005) +[2023-07-08 03:12:02,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7987.2, 300 sec: 8261.4). Total num frames: 6258688. Throughput: 0: 7850.5. Samples: 6243308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:12:02,607][812583] Avg episode reward: [(0, '124.341')] +[2023-07-08 03:12:03,583][812868] Updated weights for policy 0, policy_version 12240 (0.0005) +[2023-07-08 03:12:07,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7919.0, 300 sec: 8261.4). Total num frames: 6295552. Throughput: 0: 7832.5. Samples: 6291520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:12:07,607][812583] Avg episode reward: [(0, '173.393')] +[2023-07-08 03:12:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012296_6295552.pth... +[2023-07-08 03:12:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011840_6062080.pth +[2023-07-08 03:12:08,771][812868] Updated weights for policy 0, policy_version 12320 (0.0005) +[2023-07-08 03:12:12,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7918.9, 300 sec: 8261.4). Total num frames: 6336512. Throughput: 0: 7826.2. Samples: 6315048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:12:12,607][812583] Avg episode reward: [(0, '136.129')] +[2023-07-08 03:12:14,023][812868] Updated weights for policy 0, policy_version 12400 (0.0006) +[2023-07-08 03:12:17,607][812583] Fps is (10 sec: 8191.9, 60 sec: 7918.9, 300 sec: 8261.4). Total num frames: 6377472. Throughput: 0: 7825.5. Samples: 6362084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:12:17,607][812583] Avg episode reward: [(0, '179.706')] +[2023-07-08 03:12:19,077][812868] Updated weights for policy 0, policy_version 12480 (0.0006) +[2023-07-08 03:12:22,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 8247.5). Total num frames: 6414336. Throughput: 0: 7841.7. Samples: 6410784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:12:22,607][812583] Avg episode reward: [(0, '164.452')] +[2023-07-08 03:12:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012536_6418432.pth... +[2023-07-08 03:12:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012072_6180864.pth +[2023-07-08 03:12:24,108][812868] Updated weights for policy 0, policy_version 12560 (0.0005) +[2023-07-08 03:12:27,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 8247.5). Total num frames: 6455296. Throughput: 0: 7867.4. Samples: 6435204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:12:27,607][812583] Avg episode reward: [(0, '158.297')] +[2023-07-08 03:12:29,229][812868] Updated weights for policy 0, policy_version 12640 (0.0006) +[2023-07-08 03:12:32,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7918.9, 300 sec: 8233.7). Total num frames: 6496256. Throughput: 0: 7895.1. Samples: 6483396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:12:32,607][812583] Avg episode reward: [(0, '129.296')] +[2023-07-08 03:12:34,489][812868] Updated weights for policy 0, policy_version 12720 (0.0006) +[2023-07-08 03:12:37,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 8219.8). Total num frames: 6533120. Throughput: 0: 7876.8. Samples: 6529032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:12:37,607][812583] Avg episode reward: [(0, '151.768')] +[2023-07-08 03:12:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012760_6533120.pth... +[2023-07-08 03:12:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012296_6295552.pth +[2023-07-08 03:12:39,874][812868] Updated weights for policy 0, policy_version 12800 (0.0005) +[2023-07-08 03:12:42,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 8219.8). Total num frames: 6574080. Throughput: 0: 7879.5. Samples: 6552328. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:12:42,607][812583] Avg episode reward: [(0, '135.496')] +[2023-07-08 03:12:45,175][812868] Updated weights for policy 0, policy_version 12880 (0.0005) +[2023-07-08 03:12:47,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7850.7, 300 sec: 8205.9). Total num frames: 6610944. Throughput: 0: 7896.6. Samples: 6598656. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-08 03:12:47,607][812583] Avg episode reward: [(0, '133.706')] +[2023-07-08 03:12:50,371][812868] Updated weights for policy 0, policy_version 12960 (0.0006) +[2023-07-08 03:12:52,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 8192.0). Total num frames: 6651904. Throughput: 0: 7876.8. Samples: 6645976. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:12:52,607][812583] Avg episode reward: [(0, '141.736')] +[2023-07-08 03:12:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012992_6651904.pth... +[2023-07-08 03:12:52,612][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012536_6418432.pth +[2023-07-08 03:12:55,494][812868] Updated weights for policy 0, policy_version 13040 (0.0005) +[2023-07-08 03:12:57,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7918.9, 300 sec: 8192.0). Total num frames: 6692864. Throughput: 0: 7881.7. Samples: 6669724. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:12:57,607][812583] Avg episode reward: [(0, '126.794')] +[2023-07-08 03:13:00,573][812868] Updated weights for policy 0, policy_version 13120 (0.0005) +[2023-07-08 03:13:02,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7918.9, 300 sec: 8192.0). Total num frames: 6733824. Throughput: 0: 7911.8. Samples: 6718116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:13:02,607][812583] Avg episode reward: [(0, '122.721')] +[2023-07-08 03:13:05,800][812868] Updated weights for policy 0, policy_version 13200 (0.0005) +[2023-07-08 03:13:07,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7918.9, 300 sec: 8178.1). Total num frames: 6770688. Throughput: 0: 7878.6. Samples: 6765320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:13:07,607][812583] Avg episode reward: [(0, '125.515')] +[2023-07-08 03:13:07,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013224_6770688.pth... +[2023-07-08 03:13:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012760_6533120.pth +[2023-07-08 03:13:11,149][812868] Updated weights for policy 0, policy_version 13280 (0.0005) +[2023-07-08 03:13:12,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7850.7, 300 sec: 8164.2). Total num frames: 6807552. Throughput: 0: 7836.8. Samples: 6787860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:13:12,607][812583] Avg episode reward: [(0, '135.268')] +[2023-07-08 03:13:16,520][812868] Updated weights for policy 0, policy_version 13360 (0.0006) +[2023-07-08 03:13:17,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7850.7, 300 sec: 8150.3). Total num frames: 6848512. Throughput: 0: 7786.8. Samples: 6833800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:13:17,607][812583] Avg episode reward: [(0, '125.843')] +[2023-07-08 03:13:21,721][812868] Updated weights for policy 0, policy_version 13440 (0.0005) +[2023-07-08 03:13:22,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 8122.6). Total num frames: 6885376. Throughput: 0: 7827.7. Samples: 6881280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:13:22,607][812583] Avg episode reward: [(0, '128.295')] +[2023-07-08 03:13:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013448_6885376.pth... +[2023-07-08 03:13:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012992_6651904.pth +[2023-07-08 03:13:26,852][812868] Updated weights for policy 0, policy_version 13520 (0.0005) +[2023-07-08 03:13:27,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 8122.6). Total num frames: 6926336. Throughput: 0: 7834.0. Samples: 6904856. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:13:27,607][812583] Avg episode reward: [(0, '127.148')] +[2023-07-08 03:13:32,182][812868] Updated weights for policy 0, policy_version 13600 (0.0006) +[2023-07-08 03:13:32,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8094.8). Total num frames: 6963200. Throughput: 0: 7837.9. Samples: 6951360. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-08 03:13:32,607][812583] Avg episode reward: [(0, '133.602')] +[2023-07-08 03:13:37,599][812868] Updated weights for policy 0, policy_version 13680 (0.0006) +[2023-07-08 03:13:37,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7850.7, 300 sec: 8094.8). Total num frames: 7004160. Throughput: 0: 7800.8. Samples: 6997012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:13:37,607][812583] Avg episode reward: [(0, '128.318')] +[2023-07-08 03:13:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013680_7004160.pth... +[2023-07-08 03:13:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013224_6770688.pth +[2023-07-08 03:13:42,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8067.0). Total num frames: 7041024. Throughput: 0: 7796.0. Samples: 7020544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:13:42,607][812583] Avg episode reward: [(0, '125.530')] +[2023-07-08 03:13:42,978][812868] Updated weights for policy 0, policy_version 13760 (0.0005) +[2023-07-08 03:13:47,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7782.4, 300 sec: 8053.2). Total num frames: 7077888. Throughput: 0: 7744.8. Samples: 7066632. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:13:47,607][812583] Avg episode reward: [(0, '126.481')] +[2023-07-08 03:13:48,187][812868] Updated weights for policy 0, policy_version 13840 (0.0005) +[2023-07-08 03:13:52,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 8053.2). Total num frames: 7118848. Throughput: 0: 7718.1. Samples: 7112632. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:13:52,607][812583] Avg episode reward: [(0, '146.998')] +[2023-07-08 03:13:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013904_7118848.pth... +[2023-07-08 03:13:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013448_6885376.pth +[2023-07-08 03:13:53,554][812868] Updated weights for policy 0, policy_version 13920 (0.0006) +[2023-07-08 03:13:57,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7714.1, 300 sec: 8039.3). Total num frames: 7155712. Throughput: 0: 7721.0. Samples: 7135304. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:13:57,607][812583] Avg episode reward: [(0, '136.158')] +[2023-07-08 03:13:58,858][812868] Updated weights for policy 0, policy_version 14000 (0.0006) +[2023-07-08 03:14:02,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7645.9, 300 sec: 8025.4). Total num frames: 7192576. Throughput: 0: 7731.6. Samples: 7181720. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:14:02,607][812583] Avg episode reward: [(0, '134.103')] +[2023-07-08 03:14:04,243][812868] Updated weights for policy 0, policy_version 14080 (0.0006) +[2023-07-08 03:14:07,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7714.1, 300 sec: 8011.5). Total num frames: 7233536. Throughput: 0: 7681.2. Samples: 7226932. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:14:07,607][812583] Avg episode reward: [(0, '134.349')] +[2023-07-08 03:14:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014128_7233536.pth... +[2023-07-08 03:14:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013680_7004160.pth +[2023-07-08 03:14:09,692][812868] Updated weights for policy 0, policy_version 14160 (0.0005) +[2023-07-08 03:14:12,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7714.1, 300 sec: 8011.5). Total num frames: 7270400. Throughput: 0: 7668.3. Samples: 7249928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:14:12,607][812583] Avg episode reward: [(0, '145.229')] +[2023-07-08 03:14:15,035][812868] Updated weights for policy 0, policy_version 14240 (0.0005) +[2023-07-08 03:14:17,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7645.9, 300 sec: 7997.6). Total num frames: 7307264. Throughput: 0: 7649.5. Samples: 7295588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:14:17,607][812583] Avg episode reward: [(0, '153.395')] +[2023-07-08 03:14:20,423][812868] Updated weights for policy 0, policy_version 14320 (0.0005) +[2023-07-08 03:14:22,607][812583] Fps is (10 sec: 7372.6, 60 sec: 7645.8, 300 sec: 7969.8). Total num frames: 7344128. Throughput: 0: 7648.7. Samples: 7341204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:14:22,608][812583] Avg episode reward: [(0, '143.033')] +[2023-07-08 03:14:22,643][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014352_7348224.pth... +[2023-07-08 03:14:22,645][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013904_7118848.pth +[2023-07-08 03:14:25,939][812868] Updated weights for policy 0, policy_version 14400 (0.0005) +[2023-07-08 03:14:27,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7969.8). Total num frames: 7385088. Throughput: 0: 7618.5. Samples: 7363376. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-08 03:14:27,607][812583] Avg episode reward: [(0, '148.496')] +[2023-07-08 03:14:31,438][812868] Updated weights for policy 0, policy_version 14480 (0.0005) +[2023-07-08 03:14:32,607][812583] Fps is (10 sec: 7782.6, 60 sec: 7645.9, 300 sec: 7956.0). Total num frames: 7421952. Throughput: 0: 7593.8. Samples: 7408352. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-08 03:14:32,607][812583] Avg episode reward: [(0, '138.960')] +[2023-07-08 03:14:36,941][812868] Updated weights for policy 0, policy_version 14560 (0.0005) +[2023-07-08 03:14:37,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7577.6, 300 sec: 7942.1). Total num frames: 7458816. Throughput: 0: 7567.5. Samples: 7453172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:14:37,607][812583] Avg episode reward: [(0, '121.966')] +[2023-07-08 03:14:37,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014568_7458816.pth... +[2023-07-08 03:14:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014128_7233536.pth +[2023-07-08 03:14:42,524][812868] Updated weights for policy 0, policy_version 14640 (0.0005) +[2023-07-08 03:14:42,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7577.6, 300 sec: 7928.2). Total num frames: 7495680. Throughput: 0: 7554.7. Samples: 7475264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:14:42,607][812583] Avg episode reward: [(0, '125.349')] +[2023-07-08 03:14:47,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7577.6, 300 sec: 7914.3). Total num frames: 7532544. Throughput: 0: 7508.6. Samples: 7519608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:14:47,607][812583] Avg episode reward: [(0, '121.767')] +[2023-07-08 03:14:47,981][812868] Updated weights for policy 0, policy_version 14720 (0.0005) +[2023-07-08 03:14:52,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 7900.4). Total num frames: 7569408. Throughput: 0: 7490.9. Samples: 7564024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:14:52,607][812583] Avg episode reward: [(0, '127.264')] +[2023-07-08 03:14:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014784_7569408.pth... +[2023-07-08 03:14:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014352_7348224.pth +[2023-07-08 03:14:53,559][812868] Updated weights for policy 0, policy_version 14800 (0.0005) +[2023-07-08 03:14:57,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 7886.5). Total num frames: 7606272. Throughput: 0: 7465.1. Samples: 7585856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:14:57,607][812583] Avg episode reward: [(0, '137.052')] +[2023-07-08 03:14:58,861][812868] Updated weights for policy 0, policy_version 14880 (0.0005) +[2023-07-08 03:15:02,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7577.6, 300 sec: 7886.5). Total num frames: 7647232. Throughput: 0: 7501.5. Samples: 7633156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:15:02,607][812583] Avg episode reward: [(0, '140.184')] +[2023-07-08 03:15:04,031][812868] Updated weights for policy 0, policy_version 14960 (0.0005) +[2023-07-08 03:15:07,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7509.3, 300 sec: 7872.6). Total num frames: 7684096. Throughput: 0: 7534.3. Samples: 7680244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:15:07,607][812583] Avg episode reward: [(0, '138.012')] +[2023-07-08 03:15:07,624][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015016_7688192.pth... +[2023-07-08 03:15:07,626][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014568_7458816.pth +[2023-07-08 03:15:09,219][812868] Updated weights for policy 0, policy_version 15040 (0.0005) +[2023-07-08 03:15:12,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7577.6, 300 sec: 7872.7). Total num frames: 7725056. Throughput: 0: 7576.3. Samples: 7704308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:15:12,607][812583] Avg episode reward: [(0, '127.450')] +[2023-07-08 03:15:14,407][812868] Updated weights for policy 0, policy_version 15120 (0.0005) +[2023-07-08 03:15:17,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7645.9, 300 sec: 7872.7). Total num frames: 7766016. Throughput: 0: 7618.9. Samples: 7751204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:15:17,607][812583] Avg episode reward: [(0, '123.294')] +[2023-07-08 03:15:19,622][812868] Updated weights for policy 0, policy_version 15200 (0.0005) +[2023-07-08 03:15:22,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7858.8). Total num frames: 7802880. Throughput: 0: 7680.4. Samples: 7798792. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:15:22,607][812583] Avg episode reward: [(0, '135.689')] +[2023-07-08 03:15:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015240_7802880.pth... +[2023-07-08 03:15:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014784_7569408.pth +[2023-07-08 03:15:24,946][812868] Updated weights for policy 0, policy_version 15280 (0.0005) +[2023-07-08 03:15:27,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7577.6, 300 sec: 7844.9). Total num frames: 7839744. Throughput: 0: 7688.9. Samples: 7821264. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:15:27,607][812583] Avg episode reward: [(0, '130.691')] +[2023-07-08 03:15:30,398][812868] Updated weights for policy 0, policy_version 15360 (0.0005) +[2023-07-08 03:15:32,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7844.9). Total num frames: 7880704. Throughput: 0: 7709.8. Samples: 7866548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:15:32,607][812583] Avg episode reward: [(0, '131.034')] +[2023-07-08 03:15:35,789][812868] Updated weights for policy 0, policy_version 15440 (0.0005) +[2023-07-08 03:15:37,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7645.9, 300 sec: 7817.2). Total num frames: 7917568. Throughput: 0: 7738.3. Samples: 7912248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:15:37,607][812583] Avg episode reward: [(0, '123.296')] +[2023-07-08 03:15:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015464_7917568.pth... +[2023-07-08 03:15:37,612][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015016_7688192.pth +[2023-07-08 03:15:41,108][812868] Updated weights for policy 0, policy_version 15520 (0.0005) +[2023-07-08 03:15:42,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7645.9, 300 sec: 7803.2). Total num frames: 7954432. Throughput: 0: 7767.9. Samples: 7935412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:15:42,607][812583] Avg episode reward: [(0, '141.841')] +[2023-07-08 03:15:46,227][812868] Updated weights for policy 0, policy_version 15600 (0.0005) +[2023-07-08 03:15:47,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7803.2). Total num frames: 7995392. Throughput: 0: 7773.4. Samples: 7982960. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:15:47,607][812583] Avg episode reward: [(0, '131.935')] +[2023-07-08 03:15:51,575][812868] Updated weights for policy 0, policy_version 15680 (0.0005) +[2023-07-08 03:15:52,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7714.1, 300 sec: 7789.3). Total num frames: 8032256. Throughput: 0: 7743.6. Samples: 8028708. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:15:52,607][812583] Avg episode reward: [(0, '153.225')] +[2023-07-08 03:15:52,661][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015696_8036352.pth... +[2023-07-08 03:15:52,664][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015240_7802880.pth +[2023-07-08 03:15:56,910][812868] Updated weights for policy 0, policy_version 15760 (0.0005) +[2023-07-08 03:15:57,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7775.5). Total num frames: 8073216. Throughput: 0: 7728.4. Samples: 8052084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:15:57,607][812583] Avg episode reward: [(0, '148.611')] +[2023-07-08 03:16:02,248][812868] Updated weights for policy 0, policy_version 15840 (0.0005) +[2023-07-08 03:16:02,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7761.6). Total num frames: 8110080. Throughput: 0: 7702.3. Samples: 8097808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:16:02,607][812583] Avg episode reward: [(0, '136.190')] +[2023-07-08 03:16:07,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7714.1, 300 sec: 7747.7). Total num frames: 8146944. Throughput: 0: 7659.8. Samples: 8143484. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:16:07,607][812583] Avg episode reward: [(0, '133.976')] +[2023-07-08 03:16:07,641][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015920_8151040.pth... +[2023-07-08 03:16:07,641][812868] Updated weights for policy 0, policy_version 15920 (0.0006) +[2023-07-08 03:16:07,643][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015464_7917568.pth +[2023-07-08 03:16:12,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7747.7). Total num frames: 8187904. Throughput: 0: 7686.7. Samples: 8167168. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:16:12,607][812583] Avg episode reward: [(0, '124.429')] +[2023-07-08 03:16:12,978][812868] Updated weights for policy 0, policy_version 16000 (0.0006) +[2023-07-08 03:16:17,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7733.8). Total num frames: 8224768. Throughput: 0: 7687.6. Samples: 8212488. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:16:17,607][812583] Avg episode reward: [(0, '133.281')] +[2023-07-08 03:16:18,447][812868] Updated weights for policy 0, policy_version 16080 (0.0006) +[2023-07-08 03:16:22,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7645.9, 300 sec: 7719.9). Total num frames: 8261632. Throughput: 0: 7674.5. Samples: 8257600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:16:22,607][812583] Avg episode reward: [(0, '130.041')] +[2023-07-08 03:16:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016136_8261632.pth... +[2023-07-08 03:16:22,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015696_8036352.pth +[2023-07-08 03:16:23,821][812868] Updated weights for policy 0, policy_version 16160 (0.0006) +[2023-07-08 03:16:27,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7733.8). Total num frames: 8302592. Throughput: 0: 7665.8. Samples: 8280372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:16:27,607][812583] Avg episode reward: [(0, '129.993')] +[2023-07-08 03:16:29,153][812868] Updated weights for policy 0, policy_version 16240 (0.0005) +[2023-07-08 03:16:32,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7719.9). Total num frames: 8339456. Throughput: 0: 7639.4. Samples: 8326732. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:16:32,607][812583] Avg episode reward: [(0, '134.904')] +[2023-07-08 03:16:34,310][812868] Updated weights for policy 0, policy_version 16320 (0.0005) +[2023-07-08 03:16:37,607][812583] Fps is (10 sec: 7782.2, 60 sec: 7714.1, 300 sec: 7719.9). Total num frames: 8380416. Throughput: 0: 7685.8. Samples: 8374568. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:16:37,607][812583] Avg episode reward: [(0, '138.037')] +[2023-07-08 03:16:37,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016368_8380416.pth... +[2023-07-08 03:16:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015920_8151040.pth +[2023-07-08 03:16:39,423][812868] Updated weights for policy 0, policy_version 16400 (0.0006) +[2023-07-08 03:16:42,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7782.4, 300 sec: 7733.8). Total num frames: 8421376. Throughput: 0: 7705.0. Samples: 8398808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:16:42,607][812583] Avg episode reward: [(0, '130.122')] +[2023-07-08 03:16:44,591][812868] Updated weights for policy 0, policy_version 16480 (0.0006) +[2023-07-08 03:16:47,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7714.1, 300 sec: 7719.9). Total num frames: 8458240. Throughput: 0: 7740.6. Samples: 8446136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:16:47,607][812583] Avg episode reward: [(0, '146.407')] +[2023-07-08 03:16:49,906][812868] Updated weights for policy 0, policy_version 16560 (0.0006) +[2023-07-08 03:16:52,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7714.1, 300 sec: 7719.9). Total num frames: 8495104. Throughput: 0: 7738.0. Samples: 8491696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:16:52,607][812583] Avg episode reward: [(0, '118.512')] +[2023-07-08 03:16:52,626][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016600_8499200.pth... +[2023-07-08 03:16:52,629][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016136_8261632.pth +[2023-07-08 03:16:55,396][812868] Updated weights for policy 0, policy_version 16640 (0.0006) +[2023-07-08 03:16:57,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7719.9). Total num frames: 8536064. Throughput: 0: 7724.8. Samples: 8514784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:16:57,607][812583] Avg episode reward: [(0, '131.424')] +[2023-07-08 03:17:00,695][812868] Updated weights for policy 0, policy_version 16720 (0.0005) +[2023-07-08 03:17:02,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7719.9). Total num frames: 8572928. Throughput: 0: 7736.9. Samples: 8560648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:17:02,607][812583] Avg episode reward: [(0, '130.378')] +[2023-07-08 03:17:06,139][812868] Updated weights for policy 0, policy_version 16800 (0.0005) +[2023-07-08 03:17:07,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7714.1, 300 sec: 7706.0). Total num frames: 8609792. Throughput: 0: 7736.9. Samples: 8605760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:17:07,607][812583] Avg episode reward: [(0, '133.433')] +[2023-07-08 03:17:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016816_8609792.pth... +[2023-07-08 03:17:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016368_8380416.pth +[2023-07-08 03:17:11,587][812868] Updated weights for policy 0, policy_version 16880 (0.0005) +[2023-07-08 03:17:12,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7645.9, 300 sec: 7692.1). Total num frames: 8646656. Throughput: 0: 7729.1. Samples: 8628180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:17:12,607][812583] Avg episode reward: [(0, '131.485')] +[2023-07-08 03:17:17,019][812868] Updated weights for policy 0, policy_version 16960 (0.0005) +[2023-07-08 03:17:17,607][812583] Fps is (10 sec: 7782.5, 60 sec: 7714.1, 300 sec: 7706.0). Total num frames: 8687616. Throughput: 0: 7714.8. Samples: 8673896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:17:17,607][812583] Avg episode reward: [(0, '126.725')] +[2023-07-08 03:17:22,430][812868] Updated weights for policy 0, policy_version 17040 (0.0005) +[2023-07-08 03:17:22,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7692.1). Total num frames: 8724480. Throughput: 0: 7649.6. Samples: 8718800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:17:22,607][812583] Avg episode reward: [(0, '125.693')] +[2023-07-08 03:17:22,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017040_8724480.pth... +[2023-07-08 03:17:22,612][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016600_8499200.pth +[2023-07-08 03:17:27,607][812583] Fps is (10 sec: 7372.7, 60 sec: 7645.9, 300 sec: 7678.3). Total num frames: 8761344. Throughput: 0: 7608.9. Samples: 8741208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:17:27,607][812583] Avg episode reward: [(0, '120.579')] +[2023-07-08 03:17:27,906][812868] Updated weights for policy 0, policy_version 17120 (0.0005) +[2023-07-08 03:17:32,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7645.9, 300 sec: 7678.3). Total num frames: 8798208. Throughput: 0: 7552.2. Samples: 8785984. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-08 03:17:32,607][812583] Avg episode reward: [(0, '123.979')] +[2023-07-08 03:17:33,398][812868] Updated weights for policy 0, policy_version 17200 (0.0005) +[2023-07-08 03:17:37,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7678.3). Total num frames: 8839168. Throughput: 0: 7564.6. Samples: 8832104. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-08 03:17:37,607][812583] Avg episode reward: [(0, '121.756')] +[2023-07-08 03:17:37,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017264_8839168.pth... +[2023-07-08 03:17:37,612][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016816_8609792.pth +[2023-07-08 03:17:38,598][812868] Updated weights for policy 0, policy_version 17280 (0.0005) +[2023-07-08 03:17:42,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7577.6, 300 sec: 7678.3). Total num frames: 8876032. Throughput: 0: 7575.5. Samples: 8855680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:17:42,607][812583] Avg episode reward: [(0, '140.055')] +[2023-07-08 03:17:43,788][812868] Updated weights for policy 0, policy_version 17360 (0.0005) +[2023-07-08 03:17:47,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7678.3). Total num frames: 8916992. Throughput: 0: 7607.7. Samples: 8902996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:17:47,607][812583] Avg episode reward: [(0, '124.659')] +[2023-07-08 03:17:49,100][812868] Updated weights for policy 0, policy_version 17440 (0.0005) +[2023-07-08 03:17:52,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7664.4). Total num frames: 8953856. Throughput: 0: 7643.1. Samples: 8949700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:17:52,607][812583] Avg episode reward: [(0, '118.539')] +[2023-07-08 03:17:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017488_8953856.pth... +[2023-07-08 03:17:52,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017040_8724480.pth +[2023-07-08 03:17:54,382][812868] Updated weights for policy 0, policy_version 17520 (0.0005) +[2023-07-08 03:17:57,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7664.4). Total num frames: 8994816. Throughput: 0: 7654.0. Samples: 8972612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:17:57,607][812583] Avg episode reward: [(0, '129.855')] +[2023-07-08 03:17:59,602][812868] Updated weights for policy 0, policy_version 17600 (0.0005) +[2023-07-08 03:18:02,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7664.4). Total num frames: 9031680. Throughput: 0: 7679.1. Samples: 9019456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:18:02,607][812583] Avg episode reward: [(0, '131.156')] +[2023-07-08 03:18:04,908][812868] Updated weights for policy 0, policy_version 17680 (0.0005) +[2023-07-08 03:18:07,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7678.3). Total num frames: 9072640. Throughput: 0: 7708.1. Samples: 9065664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:18:07,607][812583] Avg episode reward: [(0, '135.050')] +[2023-07-08 03:18:07,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017720_9072640.pth... +[2023-07-08 03:18:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017264_8839168.pth +[2023-07-08 03:18:10,208][812868] Updated weights for policy 0, policy_version 17760 (0.0005) +[2023-07-08 03:18:12,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7664.4). Total num frames: 9109504. Throughput: 0: 7730.7. Samples: 9089088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:18:12,607][812583] Avg episode reward: [(0, '146.772')] +[2023-07-08 03:18:15,622][812868] Updated weights for policy 0, policy_version 17840 (0.0005) +[2023-07-08 03:18:17,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7645.9, 300 sec: 7664.4). Total num frames: 9146368. Throughput: 0: 7740.0. Samples: 9134284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:18:17,607][812583] Avg episode reward: [(0, '133.403')] +[2023-07-08 03:18:21,042][812868] Updated weights for policy 0, policy_version 17920 (0.0005) +[2023-07-08 03:18:22,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7645.9, 300 sec: 7650.5). Total num frames: 9183232. Throughput: 0: 7721.3. Samples: 9179560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:18:22,607][812583] Avg episode reward: [(0, '127.335')] +[2023-07-08 03:18:22,662][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017944_9187328.pth... +[2023-07-08 03:18:22,665][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017488_8953856.pth +[2023-07-08 03:18:26,433][812868] Updated weights for policy 0, policy_version 18000 (0.0005) +[2023-07-08 03:18:27,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7664.4). Total num frames: 9224192. Throughput: 0: 7719.0. Samples: 9203036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:18:27,607][812583] Avg episode reward: [(0, '158.617')] +[2023-07-08 03:18:31,701][812868] Updated weights for policy 0, policy_version 18080 (0.0005) +[2023-07-08 03:18:32,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7650.5). Total num frames: 9261056. Throughput: 0: 7685.4. Samples: 9248840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:18:32,607][812583] Avg episode reward: [(0, '137.688')] +[2023-07-08 03:18:36,938][812868] Updated weights for policy 0, policy_version 18160 (0.0005) +[2023-07-08 03:18:37,607][812583] Fps is (10 sec: 7782.3, 60 sec: 7714.1, 300 sec: 7664.4). Total num frames: 9302016. Throughput: 0: 7694.0. Samples: 9295928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:18:37,607][812583] Avg episode reward: [(0, '128.066')] +[2023-07-08 03:18:37,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018168_9302016.pth... +[2023-07-08 03:18:37,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017720_9072640.pth +[2023-07-08 03:18:42,045][812868] Updated weights for policy 0, policy_version 18240 (0.0005) +[2023-07-08 03:18:42,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7782.4, 300 sec: 7678.3). Total num frames: 9342976. Throughput: 0: 7716.4. Samples: 9319848. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:18:42,607][812583] Avg episode reward: [(0, '117.339')] +[2023-07-08 03:18:47,214][812868] Updated weights for policy 0, policy_version 18320 (0.0005) +[2023-07-08 03:18:47,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7714.1, 300 sec: 7664.4). Total num frames: 9379840. Throughput: 0: 7735.7. Samples: 9367560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:18:47,607][812583] Avg episode reward: [(0, '122.590')] +[2023-07-08 03:18:52,309][812868] Updated weights for policy 0, policy_version 18400 (0.0005) +[2023-07-08 03:18:52,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7678.3). Total num frames: 9420800. Throughput: 0: 7778.7. Samples: 9415704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:18:52,607][812583] Avg episode reward: [(0, '135.278')] +[2023-07-08 03:18:52,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018400_9420800.pth... +[2023-07-08 03:18:52,612][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017944_9187328.pth +[2023-07-08 03:18:57,513][812868] Updated weights for policy 0, policy_version 18480 (0.0005) +[2023-07-08 03:18:57,607][812583] Fps is (10 sec: 8192.0, 60 sec: 7782.4, 300 sec: 7692.1). Total num frames: 9461760. Throughput: 0: 7789.8. Samples: 9439628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:18:57,607][812583] Avg episode reward: [(0, '122.162')] +[2023-07-08 03:19:02,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7678.3). Total num frames: 9498624. Throughput: 0: 7838.0. Samples: 9486996. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:19:02,607][812583] Avg episode reward: [(0, '151.324')] +[2023-07-08 03:19:02,646][812868] Updated weights for policy 0, policy_version 18560 (0.0005) +[2023-07-08 03:19:07,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7692.1). Total num frames: 9539584. Throughput: 0: 7865.2. Samples: 9533496. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-08 03:19:07,607][812583] Avg episode reward: [(0, '123.628')] +[2023-07-08 03:19:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018632_9539584.pth... +[2023-07-08 03:19:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018168_9302016.pth +[2023-07-08 03:19:07,965][812868] Updated weights for policy 0, policy_version 18640 (0.0005) +[2023-07-08 03:19:12,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7692.1). Total num frames: 9576448. Throughput: 0: 7855.6. Samples: 9556540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:19:12,607][812583] Avg episode reward: [(0, '146.270')] +[2023-07-08 03:19:13,362][812868] Updated weights for policy 0, policy_version 18720 (0.0005) +[2023-07-08 03:19:17,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7782.4, 300 sec: 7692.2). Total num frames: 9613312. Throughput: 0: 7856.5. Samples: 9602384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:19:17,607][812583] Avg episode reward: [(0, '135.859')] +[2023-07-08 03:19:18,731][812868] Updated weights for policy 0, policy_version 18800 (0.0005) +[2023-07-08 03:19:22,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 7692.1). Total num frames: 9654272. Throughput: 0: 7828.7. Samples: 9648220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:19:22,607][812583] Avg episode reward: [(0, '138.449')] +[2023-07-08 03:19:22,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018856_9654272.pth... +[2023-07-08 03:19:22,614][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018400_9420800.pth +[2023-07-08 03:19:24,137][812868] Updated weights for policy 0, policy_version 18880 (0.0005) +[2023-07-08 03:19:27,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7692.1). Total num frames: 9691136. Throughput: 0: 7797.2. Samples: 9670720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:19:27,607][812583] Avg episode reward: [(0, '148.744')] +[2023-07-08 03:19:29,421][812868] Updated weights for policy 0, policy_version 18960 (0.0005) +[2023-07-08 03:19:32,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 7706.0). Total num frames: 9732096. Throughput: 0: 7782.4. Samples: 9717768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:19:32,607][812583] Avg episode reward: [(0, '143.222')] +[2023-07-08 03:19:34,662][812868] Updated weights for policy 0, policy_version 19040 (0.0005) +[2023-07-08 03:19:37,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7706.0). Total num frames: 9768960. Throughput: 0: 7738.9. Samples: 9763956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-08 03:19:37,607][812583] Avg episode reward: [(0, '132.816')] +[2023-07-08 03:19:37,611][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019080_9768960.pth... +[2023-07-08 03:19:37,614][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018632_9539584.pth +[2023-07-08 03:19:40,142][812868] Updated weights for policy 0, policy_version 19120 (0.0005) +[2023-07-08 03:19:42,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7714.1, 300 sec: 7706.0). Total num frames: 9805824. Throughput: 0: 7692.2. Samples: 9785776. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:19:42,607][812583] Avg episode reward: [(0, '149.340')] +[2023-07-08 03:19:45,618][812868] Updated weights for policy 0, policy_version 19200 (0.0005) +[2023-07-08 03:19:47,607][812583] Fps is (10 sec: 7372.9, 60 sec: 7714.1, 300 sec: 7706.0). Total num frames: 9842688. Throughput: 0: 7636.1. Samples: 9830620. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-08 03:19:47,607][812583] Avg episode reward: [(0, '148.833')] +[2023-07-08 03:19:51,025][812868] Updated weights for policy 0, policy_version 19280 (0.0005) +[2023-07-08 03:19:52,607][812583] Fps is (10 sec: 7372.8, 60 sec: 7645.9, 300 sec: 7706.0). Total num frames: 9879552. Throughput: 0: 7615.6. Samples: 9876196. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:19:52,607][812583] Avg episode reward: [(0, '160.308')] +[2023-07-08 03:19:52,652][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019304_9883648.pth... +[2023-07-08 03:19:52,654][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018856_9654272.pth +[2023-07-08 03:19:56,403][812868] Updated weights for policy 0, policy_version 19360 (0.0005) +[2023-07-08 03:19:57,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7706.0). Total num frames: 9920512. Throughput: 0: 7618.2. Samples: 9899360. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:19:57,607][812583] Avg episode reward: [(0, '175.872')] +[2023-07-08 03:20:01,853][812868] Updated weights for policy 0, policy_version 19440 (0.0005) +[2023-07-08 03:20:02,607][812583] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7706.0). Total num frames: 9957376. Throughput: 0: 7606.3. Samples: 9944668. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-08 03:20:02,607][812583] Avg episode reward: [(0, '141.710')] +[2023-07-08 03:20:07,311][812868] Updated weights for policy 0, policy_version 19520 (0.0005) +[2023-07-08 03:20:07,607][812583] Fps is (10 sec: 7372.7, 60 sec: 7577.6, 300 sec: 7692.1). Total num frames: 9994240. Throughput: 0: 7594.7. Samples: 9989984. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-08 03:20:07,607][812583] Avg episode reward: [(0, '164.306')] +[2023-07-08 03:20:07,610][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019520_9994240.pth... +[2023-07-08 03:20:07,613][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019080_9768960.pth +[2023-07-08 03:20:08,400][812822] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000001 +[2023-07-08 03:20:08,921][812822] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 +[2023-07-08 03:20:08,922][812877] Stopping RolloutWorker_w5... +[2023-07-08 03:20:08,922][812875] Stopping RolloutWorker_w3... +[2023-07-08 03:20:08,922][812874] Stopping RolloutWorker_w2... +[2023-07-08 03:20:08,922][812873] Stopping RolloutWorker_w1... +[2023-07-08 03:20:08,922][812877] Loop rollout_proc5_evt_loop terminating... +[2023-07-08 03:20:08,922][812940] Stopping RolloutWorker_w6... +[2023-07-08 03:20:08,922][812869] Stopping RolloutWorker_w0... +[2023-07-08 03:20:08,922][812876] Stopping RolloutWorker_w4... +[2023-07-08 03:20:08,922][812875] Loop rollout_proc3_evt_loop terminating... +[2023-07-08 03:20:08,922][812972] Stopping RolloutWorker_w7... +[2023-07-08 03:20:08,922][812874] Loop rollout_proc2_evt_loop terminating... +[2023-07-08 03:20:08,922][812873] Loop rollout_proc1_evt_loop terminating... +[2023-07-08 03:20:08,922][812869] Loop rollout_proc0_evt_loop terminating... +[2023-07-08 03:20:08,922][812940] Loop rollout_proc6_evt_loop terminating... +[2023-07-08 03:20:08,922][812972] Loop rollout_proc7_evt_loop terminating... +[2023-07-08 03:20:08,922][812876] Loop rollout_proc4_evt_loop terminating... +[2023-07-08 03:20:08,922][812583] Component RolloutWorker_w5 stopped! +[2023-07-08 03:20:08,922][812822] Stopping Batcher_0... +[2023-07-08 03:20:08,922][812583] Component RolloutWorker_w3 stopped! +[2023-07-08 03:20:08,923][812822] Loop batcher_evt_loop terminating... +[2023-07-08 03:20:08,923][812583] Component RolloutWorker_w2 stopped! +[2023-07-08 03:20:08,923][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... +[2023-07-08 03:20:08,923][812583] Component RolloutWorker_w1 stopped! +[2023-07-08 03:20:08,923][812583] Component RolloutWorker_w6 stopped! +[2023-07-08 03:20:08,924][812583] Component RolloutWorker_w4 stopped! +[2023-07-08 03:20:08,924][812583] Component RolloutWorker_w0 stopped! +[2023-07-08 03:20:08,924][812583] Component RolloutWorker_w7 stopped! +[2023-07-08 03:20:08,924][812583] Component Batcher_0 stopped! +[2023-07-08 03:20:08,926][812822] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019304_9883648.pth +[2023-07-08 03:20:08,926][812822] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... +[2023-07-08 03:20:08,929][812822] Stopping LearnerWorker_p0... +[2023-07-08 03:20:08,929][812822] Loop learner_proc0_evt_loop terminating... +[2023-07-08 03:20:08,929][812583] Component LearnerWorker_p0 stopped! +[2023-07-08 03:20:08,990][812868] Weights refcount: 2 0 +[2023-07-08 03:20:08,991][812868] Stopping InferenceWorker_p0-w0... +[2023-07-08 03:20:08,991][812868] Loop inference_proc0-0_evt_loop terminating... +[2023-07-08 03:20:08,991][812583] Component InferenceWorker_p0-w0 stopped! +[2023-07-08 03:20:08,992][812583] Waiting for process learner_proc0 to stop... +[2023-07-08 03:20:09,520][812583] Waiting for process inference_proc0-0 to join... +[2023-07-08 03:20:09,548][812583] Waiting for process rollout_proc0 to join... +[2023-07-08 03:20:09,548][812583] Waiting for process rollout_proc1 to join... +[2023-07-08 03:20:09,548][812583] Waiting for process rollout_proc2 to join... +[2023-07-08 03:20:09,549][812583] Waiting for process rollout_proc3 to join... +[2023-07-08 03:20:09,549][812583] Waiting for process rollout_proc4 to join... +[2023-07-08 03:20:09,549][812583] Waiting for process rollout_proc5 to join... +[2023-07-08 03:20:09,549][812583] Waiting for process rollout_proc6 to join... +[2023-07-08 03:20:09,549][812583] Waiting for process rollout_proc7 to join... +[2023-07-08 03:20:09,550][812583] Batcher 0 profile tree view: +batching: 1.7977, releasing_batches: 1.5525 +[2023-07-08 03:20:09,550][812583] InferenceWorker_p0-w0 profile tree view: +wait_policy: 0.0051 + wait_policy_total: 548.2661 +update_model: 13.6947 + weight_update: 0.0005 +one_step: 0.0006 + handle_policy_step: 618.1793 + deserialize: 25.7365, stack: 6.7418, obs_to_device_normalize: 113.6410, forward: 306.8181, send_messages: 41.2083 + prepare_outputs: 70.5919 + to_cpu: 11.0178 +[2023-07-08 03:20:09,550][812583] Learner 0 profile tree view: +misc: 0.0099, prepare_batch: 9.6020 +train: 99.5479 + epoch_init: 0.0382, minibatch_init: 1.3641, losses_postprocess: 1.3193, kl_divergence: 0.4607, after_optimizer: 0.6633 + calculate_losses: 42.4232 + losses_init: 0.0324, forward_head: 16.6529, bptt_initial: 0.1439, bptt: 0.1316, tail: 11.9616, advantages_returns: 0.9074, losses: 11.1104 + update: 51.6290 + clip: 6.0967 +[2023-07-08 03:20:09,550][812583] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.2986, enqueue_policy_requests: 12.9010, env_step: 931.4892, overhead: 20.2720, complete_rollouts: 0.3212 +save_policy_outputs: 37.9032 + split_output_tensors: 13.1261 +[2023-07-08 03:20:09,550][812583] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.2892, enqueue_policy_requests: 12.7221, env_step: 931.4016, overhead: 19.6078, complete_rollouts: 0.3164 +save_policy_outputs: 37.3067 + split_output_tensors: 13.0456 +[2023-07-08 03:20:09,551][812583] Loop Runner_EvtLoop terminating... +[2023-07-08 03:20:09,551][812583] Runner profile tree view: +main_loop: 1259.2643 +[2023-07-08 03:20:09,551][812583] Collected {0: 10006528}, FPS: 7946.3