hand-insert-v2 / sf_log.txt
qgallouedec's picture
qgallouedec HF Staff
Upload folder using huggingface_hub
cce9670
[2023-07-17 00:03:43,834][271166] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/config.json...
[2023-07-17 00:03:43,850][271166] Rollout worker 0 uses device cpu
[2023-07-17 00:03:43,850][271166] Rollout worker 1 uses device cpu
[2023-07-17 00:03:43,850][271166] Rollout worker 2 uses device cpu
[2023-07-17 00:03:43,850][271166] Rollout worker 3 uses device cpu
[2023-07-17 00:03:43,851][271166] Rollout worker 4 uses device cpu
[2023-07-17 00:03:43,851][271166] Rollout worker 5 uses device cpu
[2023-07-17 00:03:43,851][271166] Rollout worker 6 uses device cpu
[2023-07-17 00:03:43,851][271166] Rollout worker 7 uses device cpu
[2023-07-17 00:03:43,851][271166] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1
[2023-07-17 00:03:43,862][271166] InferenceWorker_p0-w0: min num requests: 2
[2023-07-17 00:03:43,879][271166] Starting all processes...
[2023-07-17 00:03:43,879][271166] Starting process learner_proc0
[2023-07-17 00:03:43,928][271166] Starting all processes...
[2023-07-17 00:03:43,964][271166] Starting process inference_proc0-0
[2023-07-17 00:03:43,964][271166] Starting process rollout_proc0
[2023-07-17 00:03:43,964][271166] Starting process rollout_proc1
[2023-07-17 00:03:43,964][271166] Starting process rollout_proc2
[2023-07-17 00:03:43,964][271166] Starting process rollout_proc3
[2023-07-17 00:03:43,964][271166] Starting process rollout_proc4
[2023-07-17 00:03:43,964][271166] Starting process rollout_proc5
[2023-07-17 00:03:43,965][271166] Starting process rollout_proc6
[2023-07-17 00:03:43,966][271166] Starting process rollout_proc7
[2023-07-17 00:03:45,793][271404] Starting seed is not provided
[2023-07-17 00:03:45,794][271404] Initializing actor-critic model on device cpu
[2023-07-17 00:03:45,794][271404] RunningMeanStd input shape: (39,)
[2023-07-17 00:03:45,794][271404] RunningMeanStd input shape: (1,)
[2023-07-17 00:03:45,850][271404] Created Actor Critic model with architecture:
[2023-07-17 00:03:45,850][271404] 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)
)
)
[2023-07-17 00:03:45,916][271455] Worker 6 uses CPU cores [24, 25, 26, 27]
[2023-07-17 00:03:46,013][271450] Worker 1 uses CPU cores [4, 5, 6, 7]
[2023-07-17 00:03:46,056][271449] Worker 0 uses CPU cores [0, 1, 2, 3]
[2023-07-17 00:03:46,135][271452] Worker 3 uses CPU cores [12, 13, 14, 15]
[2023-07-17 00:03:46,151][271404] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-07-17 00:03:46,152][271404] No checkpoints found
[2023-07-17 00:03:46,152][271404] Did not load from checkpoint, starting from scratch!
[2023-07-17 00:03:46,152][271404] Initialized policy 0 weights for model version 0
[2023-07-17 00:03:46,153][271404] LearnerWorker_p0 finished initialization!
[2023-07-17 00:03:46,154][271448] RunningMeanStd input shape: (39,)
[2023-07-17 00:03:46,154][271448] RunningMeanStd input shape: (1,)
[2023-07-17 00:03:46,210][271453] Worker 4 uses CPU cores [16, 17, 18, 19]
[2023-07-17 00:03:46,236][271166] Inference worker 0-0 is ready!
[2023-07-17 00:03:46,236][271166] All inference workers are ready! Signal rollout workers to start!
[2023-07-17 00:03:46,365][271518] Worker 7 uses CPU cores [28, 29, 30, 31]
[2023-07-17 00:03:46,476][271451] Worker 2 uses CPU cores [8, 9, 10, 11]
[2023-07-17 00:03:46,568][271454] Worker 5 uses CPU cores [20, 21, 22, 23]
[2023-07-17 00:03:46,863][271166] 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)
[2023-07-17 00:03:47,539][271449] Decorrelating experience for 0 frames...
[2023-07-17 00:03:47,542][271450] Decorrelating experience for 0 frames...
[2023-07-17 00:03:47,545][271455] Decorrelating experience for 0 frames...
[2023-07-17 00:03:47,546][271449] Decorrelating experience for 64 frames...
[2023-07-17 00:03:47,549][271450] Decorrelating experience for 64 frames...
[2023-07-17 00:03:47,552][271455] Decorrelating experience for 64 frames...
[2023-07-17 00:03:47,554][271452] Decorrelating experience for 0 frames...
[2023-07-17 00:03:47,561][271452] Decorrelating experience for 64 frames...
[2023-07-17 00:03:47,570][271453] Decorrelating experience for 0 frames...
[2023-07-17 00:03:47,577][271453] Decorrelating experience for 64 frames...
[2023-07-17 00:03:47,578][271449] Decorrelating experience for 128 frames...
[2023-07-17 00:03:47,580][271450] Decorrelating experience for 128 frames...
[2023-07-17 00:03:47,586][271455] Decorrelating experience for 128 frames...
[2023-07-17 00:03:47,592][271452] Decorrelating experience for 128 frames...
[2023-07-17 00:03:47,610][271453] Decorrelating experience for 128 frames...
[2023-07-17 00:03:47,640][271449] Decorrelating experience for 192 frames...
[2023-07-17 00:03:47,642][271450] Decorrelating experience for 192 frames...
[2023-07-17 00:03:47,656][271452] Decorrelating experience for 192 frames...
[2023-07-17 00:03:47,668][271455] Decorrelating experience for 192 frames...
[2023-07-17 00:03:47,671][271453] Decorrelating experience for 192 frames...
[2023-07-17 00:03:47,783][271518] Decorrelating experience for 0 frames...
[2023-07-17 00:03:47,790][271518] Decorrelating experience for 64 frames...
[2023-07-17 00:03:47,802][271451] Decorrelating experience for 0 frames...
[2023-07-17 00:03:47,809][271451] Decorrelating experience for 64 frames...
[2023-07-17 00:03:47,823][271518] Decorrelating experience for 128 frames...
[2023-07-17 00:03:47,843][271451] Decorrelating experience for 128 frames...
[2023-07-17 00:03:47,886][271518] Decorrelating experience for 192 frames...
[2023-07-17 00:03:47,906][271451] Decorrelating experience for 192 frames...
[2023-07-17 00:03:47,941][271454] Decorrelating experience for 0 frames...
[2023-07-17 00:03:47,948][271454] Decorrelating experience for 64 frames...
[2023-07-17 00:03:47,980][271454] Decorrelating experience for 128 frames...
[2023-07-17 00:03:48,042][271454] Decorrelating experience for 192 frames...
[2023-07-17 00:03:48,916][271449] Decorrelating experience for 256 frames...
[2023-07-17 00:03:48,935][271452] Decorrelating experience for 256 frames...
[2023-07-17 00:03:48,939][271450] Decorrelating experience for 256 frames...
[2023-07-17 00:03:48,948][271455] Decorrelating experience for 256 frames...
[2023-07-17 00:03:48,949][271453] Decorrelating experience for 256 frames...
[2023-07-17 00:03:49,034][271449] Decorrelating experience for 320 frames...
[2023-07-17 00:03:49,050][271452] Decorrelating experience for 320 frames...
[2023-07-17 00:03:49,063][271453] Decorrelating experience for 320 frames...
[2023-07-17 00:03:49,065][271450] Decorrelating experience for 320 frames...
[2023-07-17 00:03:49,066][271455] Decorrelating experience for 320 frames...
[2023-07-17 00:03:49,177][271518] Decorrelating experience for 256 frames...
[2023-07-17 00:03:49,181][271449] Decorrelating experience for 384 frames...
[2023-07-17 00:03:49,194][271451] Decorrelating experience for 256 frames...
[2023-07-17 00:03:49,199][271452] Decorrelating experience for 384 frames...
[2023-07-17 00:03:49,210][271453] Decorrelating experience for 384 frames...
[2023-07-17 00:03:49,211][271450] Decorrelating experience for 384 frames...
[2023-07-17 00:03:49,218][271455] Decorrelating experience for 384 frames...
[2023-07-17 00:03:49,297][271518] Decorrelating experience for 320 frames...
[2023-07-17 00:03:49,311][271451] Decorrelating experience for 320 frames...
[2023-07-17 00:03:49,337][271454] Decorrelating experience for 256 frames...
[2023-07-17 00:03:49,349][271449] Decorrelating experience for 448 frames...
[2023-07-17 00:03:49,374][271452] Decorrelating experience for 448 frames...
[2023-07-17 00:03:49,383][271450] Decorrelating experience for 448 frames...
[2023-07-17 00:03:49,390][271453] Decorrelating experience for 448 frames...
[2023-07-17 00:03:49,390][271455] Decorrelating experience for 448 frames...
[2023-07-17 00:03:49,445][271518] Decorrelating experience for 384 frames...
[2023-07-17 00:03:49,457][271454] Decorrelating experience for 320 frames...
[2023-07-17 00:03:49,457][271451] Decorrelating experience for 384 frames...
[2023-07-17 00:03:49,609][271454] Decorrelating experience for 384 frames...
[2023-07-17 00:03:49,615][271518] Decorrelating experience for 448 frames...
[2023-07-17 00:03:49,627][271451] Decorrelating experience for 448 frames...
[2023-07-17 00:03:49,781][271454] Decorrelating experience for 448 frames...
[2023-07-17 00:03:51,863][271166] Fps is (10 sec: 3276.9, 60 sec: 3276.9, 300 sec: 3276.9). Total num frames: 16384. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:03:51,863][271166] Avg episode reward: [(0, '3.459')]
[2023-07-17 00:03:53,958][271448] Updated weights for policy 0, policy_version 80 (0.0005)
[2023-07-17 00:03:56,863][271166] Fps is (10 sec: 6963.2, 60 sec: 6963.2, 300 sec: 6963.2). Total num frames: 69632. Throughput: 0: 5384.0. Samples: 53840. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:03:56,863][271166] Avg episode reward: [(0, '25.402')]
[2023-07-17 00:03:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000136_69632.pth...
[2023-07-17 00:03:57,999][271448] Updated weights for policy 0, policy_version 160 (0.0005)
[2023-07-17 00:04:01,862][271166] Fps is (10 sec: 10240.0, 60 sec: 7919.0, 300 sec: 7919.0). Total num frames: 118784. Throughput: 0: 7741.9. Samples: 116128. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:04:01,863][271166] Avg episode reward: [(0, '58.993')]
[2023-07-17 00:04:01,863][271404] Saving new best policy, reward=58.993!
[2023-07-17 00:04:01,929][271448] Updated weights for policy 0, policy_version 240 (0.0005)
[2023-07-17 00:04:03,857][271166] Heartbeat connected on Batcher_0
[2023-07-17 00:04:03,859][271166] Heartbeat connected on LearnerWorker_p0
[2023-07-17 00:04:03,863][271166] Heartbeat connected on InferenceWorker_p0-w0
[2023-07-17 00:04:03,864][271166] Heartbeat connected on RolloutWorker_w0
[2023-07-17 00:04:03,866][271166] Heartbeat connected on RolloutWorker_w1
[2023-07-17 00:04:03,870][271166] Heartbeat connected on RolloutWorker_w3
[2023-07-17 00:04:03,872][271166] Heartbeat connected on RolloutWorker_w2
[2023-07-17 00:04:03,874][271166] Heartbeat connected on RolloutWorker_w5
[2023-07-17 00:04:03,876][271166] Heartbeat connected on RolloutWorker_w4
[2023-07-17 00:04:03,878][271166] Heartbeat connected on RolloutWorker_w6
[2023-07-17 00:04:03,882][271166] Heartbeat connected on RolloutWorker_w7
[2023-07-17 00:04:05,951][271448] Updated weights for policy 0, policy_version 320 (0.0005)
[2023-07-17 00:04:06,863][271166] Fps is (10 sec: 10240.0, 60 sec: 8601.6, 300 sec: 8601.6). Total num frames: 172032. Throughput: 0: 7357.6. Samples: 147152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:04:06,863][271166] Avg episode reward: [(0, '165.397')]
[2023-07-17 00:04:06,863][271404] Saving new best policy, reward=165.397!
[2023-07-17 00:04:09,923][271448] Updated weights for policy 0, policy_version 400 (0.0005)
[2023-07-17 00:04:11,863][271166] Fps is (10 sec: 10239.8, 60 sec: 8847.4, 300 sec: 8847.4). Total num frames: 221184. Throughput: 0: 8354.7. Samples: 208868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:04:11,863][271166] Avg episode reward: [(0, '160.321')]
[2023-07-17 00:04:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000432_221184.pth...
[2023-07-17 00:04:14,137][271448] Updated weights for policy 0, policy_version 480 (0.0005)
[2023-07-17 00:04:16,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9011.2, 300 sec: 9011.2). Total num frames: 270336. Throughput: 0: 8875.1. Samples: 266252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:04:16,863][271166] Avg episode reward: [(0, '185.316')]
[2023-07-17 00:04:16,863][271404] Saving new best policy, reward=185.316!
[2023-07-17 00:04:18,467][271448] Updated weights for policy 0, policy_version 560 (0.0005)
[2023-07-17 00:04:21,863][271166] Fps is (10 sec: 9830.5, 60 sec: 9128.3, 300 sec: 9128.3). Total num frames: 319488. Throughput: 0: 8426.1. Samples: 294912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:04:21,863][271166] Avg episode reward: [(0, '320.420')]
[2023-07-17 00:04:21,863][271404] Saving new best policy, reward=320.420!
[2023-07-17 00:04:22,715][271448] Updated weights for policy 0, policy_version 640 (0.0005)
[2023-07-17 00:04:26,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9113.6, 300 sec: 9113.6). Total num frames: 364544. Throughput: 0: 8808.0. Samples: 352320. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:04:26,863][271166] Avg episode reward: [(0, '323.152')]
[2023-07-17 00:04:26,865][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000712_364544.pth...
[2023-07-17 00:04:26,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000136_69632.pth
[2023-07-17 00:04:26,868][271404] Saving new best policy, reward=323.152!
[2023-07-17 00:04:26,947][271448] Updated weights for policy 0, policy_version 720 (0.0005)
[2023-07-17 00:04:31,221][271448] Updated weights for policy 0, policy_version 800 (0.0005)
[2023-07-17 00:04:31,863][271166] Fps is (10 sec: 9420.7, 60 sec: 9193.3, 300 sec: 9193.3). Total num frames: 413696. Throughput: 0: 9107.6. Samples: 409840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:04:31,863][271166] Avg episode reward: [(0, '379.438')]
[2023-07-17 00:04:31,864][271404] Saving new best policy, reward=379.438!
[2023-07-17 00:04:35,487][271448] Updated weights for policy 0, policy_version 880 (0.0005)
[2023-07-17 00:04:36,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9257.0, 300 sec: 9257.0). Total num frames: 462848. Throughput: 0: 9764.2. Samples: 439388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:04:36,863][271166] Avg episode reward: [(0, '402.195')]
[2023-07-17 00:04:36,863][271404] Saving new best policy, reward=402.195!
[2023-07-17 00:04:39,771][271448] Updated weights for policy 0, policy_version 960 (0.0005)
[2023-07-17 00:04:41,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9234.6, 300 sec: 9234.6). Total num frames: 507904. Throughput: 0: 9828.3. Samples: 496112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:04:41,863][271166] Avg episode reward: [(0, '386.311')]
[2023-07-17 00:04:41,914][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001000_512000.pth...
[2023-07-17 00:04:41,917][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000432_221184.pth
[2023-07-17 00:04:44,144][271448] Updated weights for policy 0, policy_version 1040 (0.0005)
[2023-07-17 00:04:46,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9284.3). Total num frames: 557056. Throughput: 0: 9701.0. Samples: 552676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:04:46,864][271166] Avg episode reward: [(0, '422.656')]
[2023-07-17 00:04:46,864][271404] Saving new best policy, reward=422.656!
[2023-07-17 00:04:48,556][271448] Updated weights for policy 0, policy_version 1120 (0.0005)
[2023-07-17 00:04:51,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9263.3). Total num frames: 602112. Throughput: 0: 9631.6. Samples: 580572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:04:51,863][271166] Avg episode reward: [(0, '440.043')]
[2023-07-17 00:04:51,864][271404] Saving new best policy, reward=440.043!
[2023-07-17 00:04:52,886][271448] Updated weights for policy 0, policy_version 1200 (0.0005)
[2023-07-17 00:04:56,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9303.8). Total num frames: 651264. Throughput: 0: 9535.8. Samples: 637980. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-17 00:04:56,864][271166] Avg episode reward: [(0, '522.662')]
[2023-07-17 00:04:56,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001272_651264.pth...
[2023-07-17 00:04:56,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000000712_364544.pth
[2023-07-17 00:04:56,870][271404] Saving new best policy, reward=522.662!
[2023-07-17 00:04:57,075][271448] Updated weights for policy 0, policy_version 1280 (0.0005)
[2023-07-17 00:05:01,305][271448] Updated weights for policy 0, policy_version 1360 (0.0005)
[2023-07-17 00:05:01,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9338.9). Total num frames: 700416. Throughput: 0: 9557.1. Samples: 696320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:05:01,864][271166] Avg episode reward: [(0, '472.562')]
[2023-07-17 00:05:05,494][271448] Updated weights for policy 0, policy_version 1440 (0.0005)
[2023-07-17 00:05:06,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9369.6). Total num frames: 749568. Throughput: 0: 9558.9. Samples: 725064. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:05:06,864][271166] Avg episode reward: [(0, '508.235')]
[2023-07-17 00:05:09,714][271448] Updated weights for policy 0, policy_version 1520 (0.0005)
[2023-07-17 00:05:11,863][271166] Fps is (10 sec: 9420.7, 60 sec: 9557.3, 300 sec: 9348.5). Total num frames: 794624. Throughput: 0: 9578.8. Samples: 783368. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-17 00:05:11,863][271166] Avg episode reward: [(0, '521.913')]
[2023-07-17 00:05:11,896][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001560_798720.pth...
[2023-07-17 00:05:11,899][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001000_512000.pth
[2023-07-17 00:05:13,991][271448] Updated weights for policy 0, policy_version 1600 (0.0005)
[2023-07-17 00:05:16,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9375.3). Total num frames: 843776. Throughput: 0: 9575.3. Samples: 840728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:05:16,863][271166] Avg episode reward: [(0, '568.386')]
[2023-07-17 00:05:16,864][271404] Saving new best policy, reward=568.386!
[2023-07-17 00:05:18,287][271448] Updated weights for policy 0, policy_version 1680 (0.0005)
[2023-07-17 00:05:21,863][271166] Fps is (10 sec: 9830.5, 60 sec: 9557.3, 300 sec: 9399.3). Total num frames: 892928. Throughput: 0: 9562.1. Samples: 869680. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-17 00:05:21,863][271166] Avg episode reward: [(0, '569.451')]
[2023-07-17 00:05:21,864][271404] Saving new best policy, reward=569.451!
[2023-07-17 00:05:22,547][271448] Updated weights for policy 0, policy_version 1760 (0.0005)
[2023-07-17 00:05:26,848][271448] Updated weights for policy 0, policy_version 1840 (0.0005)
[2023-07-17 00:05:26,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9420.8). Total num frames: 942080. Throughput: 0: 9577.3. Samples: 927092. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-17 00:05:26,863][271166] Avg episode reward: [(0, '601.341')]
[2023-07-17 00:05:26,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001840_942080.pth...
[2023-07-17 00:05:26,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001272_651264.pth
[2023-07-17 00:05:26,868][271404] Saving new best policy, reward=601.341!
[2023-07-17 00:05:31,160][271448] Updated weights for policy 0, policy_version 1920 (0.0005)
[2023-07-17 00:05:31,862][271166] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9401.3). Total num frames: 987136. Throughput: 0: 9584.7. Samples: 983988. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-17 00:05:31,863][271166] Avg episode reward: [(0, '614.822')]
[2023-07-17 00:05:31,863][271404] Saving new best policy, reward=614.822!
[2023-07-17 00:05:35,358][271448] Updated weights for policy 0, policy_version 2000 (0.0005)
[2023-07-17 00:05:36,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9420.8). Total num frames: 1036288. Throughput: 0: 9625.7. Samples: 1013728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:05:36,863][271166] Avg episode reward: [(0, '604.394')]
[2023-07-17 00:05:39,500][271448] Updated weights for policy 0, policy_version 2080 (0.0005)
[2023-07-17 00:05:41,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9438.6). Total num frames: 1085440. Throughput: 0: 9669.8. Samples: 1073120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:05:41,863][271166] Avg episode reward: [(0, '605.848')]
[2023-07-17 00:05:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002120_1085440.pth...
[2023-07-17 00:05:41,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001560_798720.pth
[2023-07-17 00:05:43,703][271448] Updated weights for policy 0, policy_version 2160 (0.0005)
[2023-07-17 00:05:46,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9454.9). Total num frames: 1134592. Throughput: 0: 9653.5. Samples: 1130728. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:05:46,863][271166] Avg episode reward: [(0, '614.841')]
[2023-07-17 00:05:46,863][271404] Saving new best policy, reward=614.841!
[2023-07-17 00:05:47,888][271448] Updated weights for policy 0, policy_version 2240 (0.0005)
[2023-07-17 00:05:51,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9470.0). Total num frames: 1183744. Throughput: 0: 9672.4. Samples: 1160324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:05:51,863][271166] Avg episode reward: [(0, '626.187')]
[2023-07-17 00:05:51,864][271404] Saving new best policy, reward=626.187!
[2023-07-17 00:05:52,150][271448] Updated weights for policy 0, policy_version 2320 (0.0005)
[2023-07-17 00:05:56,418][271448] Updated weights for policy 0, policy_version 2400 (0.0005)
[2023-07-17 00:05:56,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9483.8). Total num frames: 1232896. Throughput: 0: 9652.9. Samples: 1217748. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:05:56,863][271166] Avg episode reward: [(0, '632.109')]
[2023-07-17 00:05:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002408_1232896.pth...
[2023-07-17 00:05:56,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000001840_942080.pth
[2023-07-17 00:05:56,868][271404] Saving new best policy, reward=632.109!
[2023-07-17 00:06:00,688][271448] Updated weights for policy 0, policy_version 2480 (0.0005)
[2023-07-17 00:06:01,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9466.3). Total num frames: 1277952. Throughput: 0: 9663.6. Samples: 1275588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:06:01,863][271166] Avg episode reward: [(0, '630.362')]
[2023-07-17 00:06:04,793][271448] Updated weights for policy 0, policy_version 2560 (0.0005)
[2023-07-17 00:06:06,863][271166] Fps is (10 sec: 9420.9, 60 sec: 9625.6, 300 sec: 9479.3). Total num frames: 1327104. Throughput: 0: 9687.3. Samples: 1305608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:06:06,863][271166] Avg episode reward: [(0, '631.061')]
[2023-07-17 00:06:08,929][271448] Updated weights for policy 0, policy_version 2640 (0.0005)
[2023-07-17 00:06:11,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9762.1, 300 sec: 9519.7). Total num frames: 1380352. Throughput: 0: 9742.7. Samples: 1365512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:06:11,863][271166] Avg episode reward: [(0, '615.124')]
[2023-07-17 00:06:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002696_1380352.pth...
[2023-07-17 00:06:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002120_1085440.pth
[2023-07-17 00:06:13,033][271448] Updated weights for policy 0, policy_version 2720 (0.0005)
[2023-07-17 00:06:16,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9502.7). Total num frames: 1425408. Throughput: 0: 9776.9. Samples: 1423948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:06:16,870][271166] Avg episode reward: [(0, '647.338')]
[2023-07-17 00:06:16,871][271404] Saving new best policy, reward=647.338!
[2023-07-17 00:06:17,281][271448] Updated weights for policy 0, policy_version 2800 (0.0005)
[2023-07-17 00:06:21,603][271448] Updated weights for policy 0, policy_version 2880 (0.0005)
[2023-07-17 00:06:21,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9513.3). Total num frames: 1474560. Throughput: 0: 9751.0. Samples: 1452524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:06:21,863][271166] Avg episode reward: [(0, '660.969')]
[2023-07-17 00:06:21,863][271404] Saving new best policy, reward=660.969!
[2023-07-17 00:06:25,839][271448] Updated weights for policy 0, policy_version 2960 (0.0005)
[2023-07-17 00:06:26,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9523.2). Total num frames: 1523712. Throughput: 0: 9720.0. Samples: 1510520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:06:26,863][271166] Avg episode reward: [(0, '660.249')]
[2023-07-17 00:06:26,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002976_1523712.pth...
[2023-07-17 00:06:26,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002408_1232896.pth
[2023-07-17 00:06:30,212][271448] Updated weights for policy 0, policy_version 3040 (0.0005)
[2023-07-17 00:06:31,862][271166] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 9507.7). Total num frames: 1568768. Throughput: 0: 9706.9. Samples: 1567536. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:06:31,863][271166] Avg episode reward: [(0, '646.598')]
[2023-07-17 00:06:34,375][271448] Updated weights for policy 0, policy_version 3120 (0.0005)
[2023-07-17 00:06:36,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9517.2). Total num frames: 1617920. Throughput: 0: 9696.9. Samples: 1596684. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:06:36,864][271166] Avg episode reward: [(0, '671.683')]
[2023-07-17 00:06:36,864][271404] Saving new best policy, reward=671.683!
[2023-07-17 00:06:38,655][271448] Updated weights for policy 0, policy_version 3200 (0.0005)
[2023-07-17 00:06:41,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9526.1). Total num frames: 1667072. Throughput: 0: 9697.2. Samples: 1654120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:06:41,864][271166] Avg episode reward: [(0, '688.650')]
[2023-07-17 00:06:41,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003256_1667072.pth...
[2023-07-17 00:06:41,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002696_1380352.pth
[2023-07-17 00:06:41,870][271404] Saving new best policy, reward=688.650!
[2023-07-17 00:06:42,896][271448] Updated weights for policy 0, policy_version 3280 (0.0005)
[2023-07-17 00:06:46,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9534.6). Total num frames: 1716224. Throughput: 0: 9706.5. Samples: 1712380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:06:46,864][271166] Avg episode reward: [(0, '679.834')]
[2023-07-17 00:06:47,014][271448] Updated weights for policy 0, policy_version 3360 (0.0005)
[2023-07-17 00:06:51,035][271448] Updated weights for policy 0, policy_version 3440 (0.0005)
[2023-07-17 00:06:51,862][271166] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9542.6). Total num frames: 1765376. Throughput: 0: 9739.3. Samples: 1743876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:06:51,863][271166] Avg episode reward: [(0, '685.850')]
[2023-07-17 00:06:55,300][271448] Updated weights for policy 0, policy_version 3520 (0.0005)
[2023-07-17 00:06:56,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9550.2). Total num frames: 1814528. Throughput: 0: 9705.1. Samples: 1802240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:06:56,864][271166] Avg episode reward: [(0, '682.141')]
[2023-07-17 00:06:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003544_1814528.pth...
[2023-07-17 00:06:56,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000002976_1523712.pth
[2023-07-17 00:06:59,524][271448] Updated weights for policy 0, policy_version 3600 (0.0005)
[2023-07-17 00:07:01,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9557.3). Total num frames: 1863680. Throughput: 0: 9686.1. Samples: 1859820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:07:01,863][271166] Avg episode reward: [(0, '676.528')]
[2023-07-17 00:07:03,618][271448] Updated weights for policy 0, policy_version 3680 (0.0005)
[2023-07-17 00:07:06,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 9584.6). Total num frames: 1916928. Throughput: 0: 9741.0. Samples: 1890868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:07:06,863][271166] Avg episode reward: [(0, '648.975')]
[2023-07-17 00:07:07,503][271448] Updated weights for policy 0, policy_version 3760 (0.0004)
[2023-07-17 00:07:11,402][271448] Updated weights for policy 0, policy_version 3840 (0.0004)
[2023-07-17 00:07:11,863][271166] Fps is (10 sec: 10649.6, 60 sec: 9830.4, 300 sec: 9610.6). Total num frames: 1970176. Throughput: 0: 9852.1. Samples: 1953864. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-17 00:07:11,863][271166] Avg episode reward: [(0, '694.739')]
[2023-07-17 00:07:11,865][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003848_1970176.pth...
[2023-07-17 00:07:11,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003256_1667072.pth
[2023-07-17 00:07:11,868][271404] Saving new best policy, reward=694.739!
[2023-07-17 00:07:15,385][271448] Updated weights for policy 0, policy_version 3920 (0.0005)
[2023-07-17 00:07:16,863][271166] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9615.8). Total num frames: 2019328. Throughput: 0: 9953.7. Samples: 2015456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:07:16,863][271166] Avg episode reward: [(0, '691.697')]
[2023-07-17 00:07:19,428][271448] Updated weights for policy 0, policy_version 4000 (0.0005)
[2023-07-17 00:07:21,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9639.9). Total num frames: 2072576. Throughput: 0: 9991.1. Samples: 2046284. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:07:21,863][271166] Avg episode reward: [(0, '703.933')]
[2023-07-17 00:07:21,864][271404] Saving new best policy, reward=703.933!
[2023-07-17 00:07:23,452][271448] Updated weights for policy 0, policy_version 4080 (0.0004)
[2023-07-17 00:07:26,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9644.2). Total num frames: 2121728. Throughput: 0: 10069.8. Samples: 2107260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:07:26,863][271166] Avg episode reward: [(0, '679.415')]
[2023-07-17 00:07:26,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004144_2121728.pth...
[2023-07-17 00:07:26,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003544_1814528.pth
[2023-07-17 00:07:27,456][271448] Updated weights for policy 0, policy_version 4160 (0.0005)
[2023-07-17 00:07:31,425][271448] Updated weights for policy 0, policy_version 4240 (0.0005)
[2023-07-17 00:07:31,863][271166] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 9666.6). Total num frames: 2174976. Throughput: 0: 10156.1. Samples: 2169404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:07:31,863][271166] Avg episode reward: [(0, '686.992')]
[2023-07-17 00:07:35,492][271448] Updated weights for policy 0, policy_version 4320 (0.0005)
[2023-07-17 00:07:36,863][271166] Fps is (10 sec: 10239.9, 60 sec: 10103.4, 300 sec: 9670.1). Total num frames: 2224128. Throughput: 0: 10127.5. Samples: 2199616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:07:36,863][271166] Avg episode reward: [(0, '667.422')]
[2023-07-17 00:07:39,505][271448] Updated weights for policy 0, policy_version 4400 (0.0005)
[2023-07-17 00:07:41,863][271166] Fps is (10 sec: 9830.3, 60 sec: 10103.5, 300 sec: 9673.5). Total num frames: 2273280. Throughput: 0: 10194.1. Samples: 2260976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:07:41,863][271166] Avg episode reward: [(0, '660.764')]
[2023-07-17 00:07:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004440_2273280.pth...
[2023-07-17 00:07:41,867][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000003848_1970176.pth
[2023-07-17 00:07:43,530][271448] Updated weights for policy 0, policy_version 4480 (0.0004)
[2023-07-17 00:07:46,863][271166] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 9693.9). Total num frames: 2326528. Throughput: 0: 10260.2. Samples: 2321532. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:07:46,863][271166] Avg episode reward: [(0, '684.696')]
[2023-07-17 00:07:47,565][271448] Updated weights for policy 0, policy_version 4560 (0.0005)
[2023-07-17 00:07:51,615][271448] Updated weights for policy 0, policy_version 4640 (0.0004)
[2023-07-17 00:07:51,863][271166] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9696.7). Total num frames: 2375680. Throughput: 0: 10246.8. Samples: 2351976. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:07:51,863][271166] Avg episode reward: [(0, '674.509')]
[2023-07-17 00:07:55,780][271448] Updated weights for policy 0, policy_version 4720 (0.0005)
[2023-07-17 00:07:56,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 9699.3). Total num frames: 2424832. Throughput: 0: 10185.7. Samples: 2412220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:07:56,863][271166] Avg episode reward: [(0, '687.885')]
[2023-07-17 00:07:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004736_2424832.pth...
[2023-07-17 00:07:56,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004144_2121728.pth
[2023-07-17 00:08:00,089][271448] Updated weights for policy 0, policy_version 4800 (0.0005)
[2023-07-17 00:08:01,863][271166] Fps is (10 sec: 9830.3, 60 sec: 10171.7, 300 sec: 9701.9). Total num frames: 2473984. Throughput: 0: 10080.4. Samples: 2469076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:08:01,863][271166] Avg episode reward: [(0, '688.096')]
[2023-07-17 00:08:04,402][271448] Updated weights for policy 0, policy_version 4880 (0.0005)
[2023-07-17 00:08:06,863][271166] Fps is (10 sec: 9420.9, 60 sec: 10035.2, 300 sec: 9688.6). Total num frames: 2519040. Throughput: 0: 10029.3. Samples: 2497604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:08:06,863][271166] Avg episode reward: [(0, '663.307')]
[2023-07-17 00:08:08,819][271448] Updated weights for policy 0, policy_version 4960 (0.0005)
[2023-07-17 00:08:11,863][271166] Fps is (10 sec: 9420.9, 60 sec: 9966.9, 300 sec: 9691.3). Total num frames: 2568192. Throughput: 0: 9916.8. Samples: 2553516. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:08:11,863][271166] Avg episode reward: [(0, '678.622')]
[2023-07-17 00:08:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005016_2568192.pth...
[2023-07-17 00:08:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004440_2273280.pth
[2023-07-17 00:08:13,153][271448] Updated weights for policy 0, policy_version 5040 (0.0005)
[2023-07-17 00:08:16,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9898.7, 300 sec: 9678.7). Total num frames: 2613248. Throughput: 0: 9789.9. Samples: 2609948. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:08:16,863][271166] Avg episode reward: [(0, '655.431')]
[2023-07-17 00:08:17,491][271448] Updated weights for policy 0, policy_version 5120 (0.0005)
[2023-07-17 00:08:21,858][271448] Updated weights for policy 0, policy_version 5200 (0.0005)
[2023-07-17 00:08:21,863][271166] Fps is (10 sec: 9420.9, 60 sec: 9830.4, 300 sec: 9681.5). Total num frames: 2662400. Throughput: 0: 9739.6. Samples: 2637896. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:08:21,863][271166] Avg episode reward: [(0, '686.820')]
[2023-07-17 00:08:26,208][271448] Updated weights for policy 0, policy_version 5280 (0.0005)
[2023-07-17 00:08:26,863][271166] Fps is (10 sec: 9420.7, 60 sec: 9762.1, 300 sec: 9669.5). Total num frames: 2707456. Throughput: 0: 9641.6. Samples: 2694848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:08:26,863][271166] Avg episode reward: [(0, '668.624')]
[2023-07-17 00:08:26,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005288_2707456.pth...
[2023-07-17 00:08:26,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000004736_2424832.pth
[2023-07-17 00:08:30,492][271448] Updated weights for policy 0, policy_version 5360 (0.0005)
[2023-07-17 00:08:31,863][271166] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 9672.3). Total num frames: 2756608. Throughput: 0: 9572.2. Samples: 2752280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:08:31,864][271166] Avg episode reward: [(0, '657.053')]
[2023-07-17 00:08:34,858][271448] Updated weights for policy 0, policy_version 5440 (0.0005)
[2023-07-17 00:08:36,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9660.9). Total num frames: 2801664. Throughput: 0: 9512.1. Samples: 2780020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:08:36,864][271166] Avg episode reward: [(0, '692.033')]
[2023-07-17 00:08:39,277][271448] Updated weights for policy 0, policy_version 5520 (0.0005)
[2023-07-17 00:08:41,863][271166] Fps is (10 sec: 9011.2, 60 sec: 9557.3, 300 sec: 9649.9). Total num frames: 2846720. Throughput: 0: 9396.5. Samples: 2835064. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:08:41,863][271166] Avg episode reward: [(0, '671.372')]
[2023-07-17 00:08:41,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005560_2846720.pth...
[2023-07-17 00:08:41,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005016_2568192.pth
[2023-07-17 00:08:43,731][271448] Updated weights for policy 0, policy_version 5600 (0.0005)
[2023-07-17 00:08:46,863][271166] Fps is (10 sec: 9011.2, 60 sec: 9420.8, 300 sec: 9747.1). Total num frames: 2891776. Throughput: 0: 9359.0. Samples: 2890228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:08:46,864][271166] Avg episode reward: [(0, '671.212')]
[2023-07-17 00:08:48,262][271448] Updated weights for policy 0, policy_version 5680 (0.0005)
[2023-07-17 00:08:51,863][271166] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 9719.3). Total num frames: 2936832. Throughput: 0: 9315.1. Samples: 2916784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:08:51,864][271166] Avg episode reward: [(0, '691.569')]
[2023-07-17 00:08:52,834][271448] Updated weights for policy 0, policy_version 5760 (0.0005)
[2023-07-17 00:08:56,863][271166] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9705.4). Total num frames: 2981888. Throughput: 0: 9281.4. Samples: 2971180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:08:56,863][271166] Avg episode reward: [(0, '697.410')]
[2023-07-17 00:08:56,901][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005832_2985984.pth...
[2023-07-17 00:08:56,903][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005288_2707456.pth
[2023-07-17 00:08:57,352][271448] Updated weights for policy 0, policy_version 5840 (0.0005)
[2023-07-17 00:09:01,734][271448] Updated weights for policy 0, policy_version 5920 (0.0005)
[2023-07-17 00:09:01,863][271166] Fps is (10 sec: 9420.9, 60 sec: 9284.3, 300 sec: 9691.6). Total num frames: 3031040. Throughput: 0: 9263.6. Samples: 3026808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:09:01,864][271166] Avg episode reward: [(0, '701.333')]
[2023-07-17 00:09:06,124][271448] Updated weights for policy 0, policy_version 6000 (0.0005)
[2023-07-17 00:09:06,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9677.7). Total num frames: 3076096. Throughput: 0: 9274.5. Samples: 3055248. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:09:06,863][271166] Avg episode reward: [(0, '694.434')]
[2023-07-17 00:09:10,491][271448] Updated weights for policy 0, policy_version 6080 (0.0005)
[2023-07-17 00:09:11,863][271166] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9677.7). Total num frames: 3125248. Throughput: 0: 9250.1. Samples: 3111104. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:09:11,863][271166] Avg episode reward: [(0, '674.621')]
[2023-07-17 00:09:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006104_3125248.pth...
[2023-07-17 00:09:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005560_2846720.pth
[2023-07-17 00:09:14,862][271448] Updated weights for policy 0, policy_version 6160 (0.0005)
[2023-07-17 00:09:16,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9663.8). Total num frames: 3170304. Throughput: 0: 9222.4. Samples: 3167288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:09:16,863][271166] Avg episode reward: [(0, '692.520')]
[2023-07-17 00:09:19,180][271448] Updated weights for policy 0, policy_version 6240 (0.0005)
[2023-07-17 00:09:21,863][271166] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 9663.8). Total num frames: 3215360. Throughput: 0: 9235.5. Samples: 3195616. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-17 00:09:21,863][271166] Avg episode reward: [(0, '691.371')]
[2023-07-17 00:09:23,652][271448] Updated weights for policy 0, policy_version 6320 (0.0005)
[2023-07-17 00:09:26,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9663.8). Total num frames: 3264512. Throughput: 0: 9258.6. Samples: 3251700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:09:26,863][271166] Avg episode reward: [(0, '682.823')]
[2023-07-17 00:09:26,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006376_3264512.pth...
[2023-07-17 00:09:26,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000005832_2985984.pth
[2023-07-17 00:09:27,896][271448] Updated weights for policy 0, policy_version 6400 (0.0005)
[2023-07-17 00:09:31,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9284.3, 300 sec: 9663.8). Total num frames: 3313664. Throughput: 0: 9320.1. Samples: 3309632. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:09:31,863][271166] Avg episode reward: [(0, '704.052')]
[2023-07-17 00:09:31,864][271404] Saving new best policy, reward=704.052!
[2023-07-17 00:09:32,118][271448] Updated weights for policy 0, policy_version 6480 (0.0005)
[2023-07-17 00:09:36,377][271448] Updated weights for policy 0, policy_version 6560 (0.0005)
[2023-07-17 00:09:36,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9352.5, 300 sec: 9677.7). Total num frames: 3362816. Throughput: 0: 9373.0. Samples: 3338568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:09:36,863][271166] Avg episode reward: [(0, '693.331')]
[2023-07-17 00:09:40,555][271448] Updated weights for policy 0, policy_version 6640 (0.0005)
[2023-07-17 00:09:41,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9420.8, 300 sec: 9677.7). Total num frames: 3411968. Throughput: 0: 9458.4. Samples: 3396808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:09:41,863][271166] Avg episode reward: [(0, '692.102')]
[2023-07-17 00:09:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006664_3411968.pth...
[2023-07-17 00:09:41,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006104_3125248.pth
[2023-07-17 00:09:44,809][271448] Updated weights for policy 0, policy_version 6720 (0.0005)
[2023-07-17 00:09:46,862][271166] Fps is (10 sec: 9420.9, 60 sec: 9420.8, 300 sec: 9677.7). Total num frames: 3457024. Throughput: 0: 9515.7. Samples: 3455016. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:09:46,863][271166] Avg episode reward: [(0, '700.040')]
[2023-07-17 00:09:49,011][271448] Updated weights for policy 0, policy_version 6800 (0.0005)
[2023-07-17 00:09:51,863][271166] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9677.7). Total num frames: 3506176. Throughput: 0: 9535.3. Samples: 3484336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:09:51,863][271166] Avg episode reward: [(0, '696.344')]
[2023-07-17 00:09:53,228][271448] Updated weights for policy 0, policy_version 6880 (0.0005)
[2023-07-17 00:09:56,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9557.3, 300 sec: 9677.7). Total num frames: 3555328. Throughput: 0: 9575.2. Samples: 3541988. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:09:56,863][271166] Avg episode reward: [(0, '696.733')]
[2023-07-17 00:09:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006944_3555328.pth...
[2023-07-17 00:09:56,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006376_3264512.pth
[2023-07-17 00:09:57,595][271448] Updated weights for policy 0, policy_version 6960 (0.0005)
[2023-07-17 00:10:01,787][271448] Updated weights for policy 0, policy_version 7040 (0.0005)
[2023-07-17 00:10:01,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9677.7). Total num frames: 3604480. Throughput: 0: 9612.5. Samples: 3599852. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-17 00:10:01,863][271166] Avg episode reward: [(0, '690.644')]
[2023-07-17 00:10:06,014][271448] Updated weights for policy 0, policy_version 7120 (0.0005)
[2023-07-17 00:10:06,863][271166] Fps is (10 sec: 9420.9, 60 sec: 9557.3, 300 sec: 9677.7). Total num frames: 3649536. Throughput: 0: 9622.8. Samples: 3628640. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-17 00:10:06,863][271166] Avg episode reward: [(0, '705.270')]
[2023-07-17 00:10:06,876][271404] Saving new best policy, reward=705.270!
[2023-07-17 00:10:10,235][271448] Updated weights for policy 0, policy_version 7200 (0.0005)
[2023-07-17 00:10:11,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9677.7). Total num frames: 3698688. Throughput: 0: 9661.6. Samples: 3686472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:10:11,863][271166] Avg episode reward: [(0, '703.404')]
[2023-07-17 00:10:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007224_3698688.pth...
[2023-07-17 00:10:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006664_3411968.pth
[2023-07-17 00:10:14,488][271448] Updated weights for policy 0, policy_version 7280 (0.0005)
[2023-07-17 00:10:16,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9677.7). Total num frames: 3747840. Throughput: 0: 9674.2. Samples: 3744972. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:10:16,863][271166] Avg episode reward: [(0, '691.697')]
[2023-07-17 00:10:18,701][271448] Updated weights for policy 0, policy_version 7360 (0.0005)
[2023-07-17 00:10:21,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9677.7). Total num frames: 3796992. Throughput: 0: 9681.3. Samples: 3774228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:10:21,863][271166] Avg episode reward: [(0, '642.191')]
[2023-07-17 00:10:22,790][271448] Updated weights for policy 0, policy_version 7440 (0.0005)
[2023-07-17 00:10:26,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9691.5). Total num frames: 3846144. Throughput: 0: 9712.2. Samples: 3833856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:10:26,863][271166] Avg episode reward: [(0, '702.559')]
[2023-07-17 00:10:26,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007512_3846144.pth...
[2023-07-17 00:10:26,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000006944_3555328.pth
[2023-07-17 00:10:26,948][271448] Updated weights for policy 0, policy_version 7520 (0.0005)
[2023-07-17 00:10:31,117][271448] Updated weights for policy 0, policy_version 7600 (0.0005)
[2023-07-17 00:10:31,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9691.5). Total num frames: 3895296. Throughput: 0: 9725.7. Samples: 3892672. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:10:31,863][271166] Avg episode reward: [(0, '716.116')]
[2023-07-17 00:10:31,864][271404] Saving new best policy, reward=716.116!
[2023-07-17 00:10:35,272][271448] Updated weights for policy 0, policy_version 7680 (0.0005)
[2023-07-17 00:10:36,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9691.6). Total num frames: 3944448. Throughput: 0: 9741.5. Samples: 3922704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:10:36,863][271166] Avg episode reward: [(0, '709.953')]
[2023-07-17 00:10:39,432][271448] Updated weights for policy 0, policy_version 7760 (0.0005)
[2023-07-17 00:10:41,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9691.6). Total num frames: 3993600. Throughput: 0: 9765.2. Samples: 3981420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:10:41,863][271166] Avg episode reward: [(0, '707.085')]
[2023-07-17 00:10:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007800_3993600.pth...
[2023-07-17 00:10:41,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007224_3698688.pth
[2023-07-17 00:10:43,603][271448] Updated weights for policy 0, policy_version 7840 (0.0005)
[2023-07-17 00:10:46,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9691.6). Total num frames: 4042752. Throughput: 0: 9783.6. Samples: 4040116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:10:46,863][271166] Avg episode reward: [(0, '700.769')]
[2023-07-17 00:10:47,758][271448] Updated weights for policy 0, policy_version 7920 (0.0005)
[2023-07-17 00:10:51,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9691.6). Total num frames: 4091904. Throughput: 0: 9817.5. Samples: 4070428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:10:51,863][271166] Avg episode reward: [(0, '718.924')]
[2023-07-17 00:10:51,883][271404] Saving new best policy, reward=718.924!
[2023-07-17 00:10:51,885][271448] Updated weights for policy 0, policy_version 8000 (0.0005)
[2023-07-17 00:10:55,992][271448] Updated weights for policy 0, policy_version 8080 (0.0005)
[2023-07-17 00:10:56,863][271166] Fps is (10 sec: 10239.9, 60 sec: 9830.4, 300 sec: 9719.3). Total num frames: 4145152. Throughput: 0: 9849.8. Samples: 4129712. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:10:56,863][271166] Avg episode reward: [(0, '709.066')]
[2023-07-17 00:10:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008096_4145152.pth...
[2023-07-17 00:10:56,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007512_3846144.pth
[2023-07-17 00:11:00,171][271448] Updated weights for policy 0, policy_version 8160 (0.0005)
[2023-07-17 00:11:01,863][271166] Fps is (10 sec: 10240.1, 60 sec: 9830.4, 300 sec: 9719.3). Total num frames: 4194304. Throughput: 0: 9875.2. Samples: 4189356. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:11:01,863][271166] Avg episode reward: [(0, '663.046')]
[2023-07-17 00:11:04,234][271448] Updated weights for policy 0, policy_version 8240 (0.0005)
[2023-07-17 00:11:06,863][271166] Fps is (10 sec: 9830.5, 60 sec: 9898.7, 300 sec: 9705.4). Total num frames: 4243456. Throughput: 0: 9882.9. Samples: 4218960. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:11:06,863][271166] Avg episode reward: [(0, '695.046')]
[2023-07-17 00:11:08,350][271448] Updated weights for policy 0, policy_version 8320 (0.0005)
[2023-07-17 00:11:11,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9898.7, 300 sec: 9719.3). Total num frames: 4292608. Throughput: 0: 9881.0. Samples: 4278500. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:11:11,863][271166] Avg episode reward: [(0, '690.624')]
[2023-07-17 00:11:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008384_4292608.pth...
[2023-07-17 00:11:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000007800_3993600.pth
[2023-07-17 00:11:12,583][271448] Updated weights for policy 0, policy_version 8400 (0.0005)
[2023-07-17 00:11:16,679][271448] Updated weights for policy 0, policy_version 8480 (0.0005)
[2023-07-17 00:11:16,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9719.3). Total num frames: 4341760. Throughput: 0: 9890.1. Samples: 4337728. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:11:16,863][271166] Avg episode reward: [(0, '709.836')]
[2023-07-17 00:11:20,850][271448] Updated weights for policy 0, policy_version 8560 (0.0005)
[2023-07-17 00:11:21,863][271166] Fps is (10 sec: 9830.5, 60 sec: 9898.7, 300 sec: 9719.3). Total num frames: 4390912. Throughput: 0: 9880.9. Samples: 4367344. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:11:21,863][271166] Avg episode reward: [(0, '707.387')]
[2023-07-17 00:11:25,021][271448] Updated weights for policy 0, policy_version 8640 (0.0005)
[2023-07-17 00:11:26,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9733.2). Total num frames: 4440064. Throughput: 0: 9887.8. Samples: 4426372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:11:26,863][271166] Avg episode reward: [(0, '708.445')]
[2023-07-17 00:11:26,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008672_4440064.pth...
[2023-07-17 00:11:26,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008096_4145152.pth
[2023-07-17 00:11:29,169][271448] Updated weights for policy 0, policy_version 8720 (0.0005)
[2023-07-17 00:11:31,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9733.2). Total num frames: 4489216. Throughput: 0: 9896.2. Samples: 4485444. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-17 00:11:31,863][271166] Avg episode reward: [(0, '712.926')]
[2023-07-17 00:11:33,262][271448] Updated weights for policy 0, policy_version 8800 (0.0005)
[2023-07-17 00:11:36,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9733.2). Total num frames: 4538368. Throughput: 0: 9902.4. Samples: 4516036. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-17 00:11:36,863][271166] Avg episode reward: [(0, '703.993')]
[2023-07-17 00:11:37,442][271448] Updated weights for policy 0, policy_version 8880 (0.0005)
[2023-07-17 00:11:41,521][271448] Updated weights for policy 0, policy_version 8960 (0.0005)
[2023-07-17 00:11:41,862][271166] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9733.2). Total num frames: 4587520. Throughput: 0: 9900.7. Samples: 4575244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:11:41,863][271166] Avg episode reward: [(0, '717.271')]
[2023-07-17 00:11:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008960_4587520.pth...
[2023-07-17 00:11:41,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008384_4292608.pth
[2023-07-17 00:11:45,582][271448] Updated weights for policy 0, policy_version 9040 (0.0005)
[2023-07-17 00:11:46,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9747.1). Total num frames: 4640768. Throughput: 0: 9914.0. Samples: 4635488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:11:46,864][271166] Avg episode reward: [(0, '707.781')]
[2023-07-17 00:11:49,715][271448] Updated weights for policy 0, policy_version 9120 (0.0005)
[2023-07-17 00:11:51,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9967.0, 300 sec: 9747.1). Total num frames: 4689920. Throughput: 0: 9917.7. Samples: 4665256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:11:51,864][271166] Avg episode reward: [(0, '708.967')]
[2023-07-17 00:11:53,895][271448] Updated weights for policy 0, policy_version 9200 (0.0005)
[2023-07-17 00:11:56,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9898.7, 300 sec: 9747.1). Total num frames: 4739072. Throughput: 0: 9905.3. Samples: 4724240. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-17 00:11:56,864][271166] Avg episode reward: [(0, '718.159')]
[2023-07-17 00:11:56,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009256_4739072.pth...
[2023-07-17 00:11:56,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008672_4440064.pth
[2023-07-17 00:11:57,980][271448] Updated weights for policy 0, policy_version 9280 (0.0005)
[2023-07-17 00:12:01,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9733.2). Total num frames: 4788224. Throughput: 0: 9920.3. Samples: 4784140. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:12:01,864][271166] Avg episode reward: [(0, '712.132')]
[2023-07-17 00:12:02,131][271448] Updated weights for policy 0, policy_version 9360 (0.0005)
[2023-07-17 00:12:06,333][271448] Updated weights for policy 0, policy_version 9440 (0.0005)
[2023-07-17 00:12:06,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9719.3). Total num frames: 4837376. Throughput: 0: 9912.5. Samples: 4813408. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:12:06,864][271166] Avg episode reward: [(0, '702.771')]
[2023-07-17 00:12:10,551][271448] Updated weights for policy 0, policy_version 9520 (0.0005)
[2023-07-17 00:12:11,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9898.7, 300 sec: 9719.3). Total num frames: 4886528. Throughput: 0: 9891.7. Samples: 4871500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:12:11,864][271166] Avg episode reward: [(0, '717.578')]
[2023-07-17 00:12:11,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009544_4886528.pth...
[2023-07-17 00:12:11,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000008960_4587520.pth
[2023-07-17 00:12:14,698][271448] Updated weights for policy 0, policy_version 9600 (0.0005)
[2023-07-17 00:12:16,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9705.4). Total num frames: 4935680. Throughput: 0: 9905.9. Samples: 4931208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:12:16,863][271166] Avg episode reward: [(0, '721.334')]
[2023-07-17 00:12:16,864][271404] Saving new best policy, reward=721.334!
[2023-07-17 00:12:18,813][271448] Updated weights for policy 0, policy_version 9680 (0.0005)
[2023-07-17 00:12:21,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9705.4). Total num frames: 4984832. Throughput: 0: 9877.3. Samples: 4960516. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:12:21,863][271166] Avg episode reward: [(0, '710.325')]
[2023-07-17 00:12:23,039][271448] Updated weights for policy 0, policy_version 9760 (0.0005)
[2023-07-17 00:12:26,863][271166] Fps is (10 sec: 9830.2, 60 sec: 9898.6, 300 sec: 9691.5). Total num frames: 5033984. Throughput: 0: 9854.2. Samples: 5018684. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-17 00:12:26,863][271166] Avg episode reward: [(0, '718.657')]
[2023-07-17 00:12:26,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009832_5033984.pth...
[2023-07-17 00:12:26,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009256_4739072.pth
[2023-07-17 00:12:27,230][271448] Updated weights for policy 0, policy_version 9840 (0.0005)
[2023-07-17 00:12:31,438][271448] Updated weights for policy 0, policy_version 9920 (0.0005)
[2023-07-17 00:12:31,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9830.4, 300 sec: 9677.7). Total num frames: 5079040. Throughput: 0: 9828.1. Samples: 5077752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:12:31,863][271166] Avg episode reward: [(0, '728.133')]
[2023-07-17 00:12:31,867][271404] Saving new best policy, reward=728.133!
[2023-07-17 00:12:35,667][271448] Updated weights for policy 0, policy_version 10000 (0.0005)
[2023-07-17 00:12:36,863][271166] Fps is (10 sec: 9421.0, 60 sec: 9830.4, 300 sec: 9677.7). Total num frames: 5128192. Throughput: 0: 9801.5. Samples: 5106324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:12:36,863][271166] Avg episode reward: [(0, '715.694')]
[2023-07-17 00:12:39,812][271448] Updated weights for policy 0, policy_version 10080 (0.0005)
[2023-07-17 00:12:41,863][271166] Fps is (10 sec: 10239.8, 60 sec: 9898.6, 300 sec: 9677.7). Total num frames: 5181440. Throughput: 0: 9802.5. Samples: 5165356. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:12:41,863][271166] Avg episode reward: [(0, '718.400')]
[2023-07-17 00:12:41,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010120_5181440.pth...
[2023-07-17 00:12:41,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009544_4886528.pth
[2023-07-17 00:12:43,905][271448] Updated weights for policy 0, policy_version 10160 (0.0005)
[2023-07-17 00:12:46,863][271166] Fps is (10 sec: 10239.9, 60 sec: 9830.4, 300 sec: 9677.7). Total num frames: 5230592. Throughput: 0: 9818.6. Samples: 5225980. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:12:46,863][271166] Avg episode reward: [(0, '721.510')]
[2023-07-17 00:12:48,080][271448] Updated weights for policy 0, policy_version 10240 (0.0005)
[2023-07-17 00:12:51,863][271166] Fps is (10 sec: 9830.6, 60 sec: 9830.4, 300 sec: 9677.7). Total num frames: 5279744. Throughput: 0: 9817.2. Samples: 5255180. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:12:51,863][271166] Avg episode reward: [(0, '724.590')]
[2023-07-17 00:12:52,237][271448] Updated weights for policy 0, policy_version 10320 (0.0005)
[2023-07-17 00:12:56,390][271448] Updated weights for policy 0, policy_version 10400 (0.0005)
[2023-07-17 00:12:56,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9677.7). Total num frames: 5328896. Throughput: 0: 9816.4. Samples: 5313236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:12:56,863][271166] Avg episode reward: [(0, '730.039')]
[2023-07-17 00:12:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010408_5328896.pth...
[2023-07-17 00:12:56,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000009832_5033984.pth
[2023-07-17 00:12:56,869][271404] Saving new best policy, reward=730.039!
[2023-07-17 00:13:00,357][271448] Updated weights for policy 0, policy_version 10480 (0.0005)
[2023-07-17 00:13:01,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9691.6). Total num frames: 5378048. Throughput: 0: 9873.9. Samples: 5375532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:13:01,863][271166] Avg episode reward: [(0, '717.776')]
[2023-07-17 00:13:04,234][271448] Updated weights for policy 0, policy_version 10560 (0.0004)
[2023-07-17 00:13:06,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 9705.4). Total num frames: 5431296. Throughput: 0: 9917.5. Samples: 5406804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:13:06,863][271166] Avg episode reward: [(0, '714.121')]
[2023-07-17 00:13:08,132][271448] Updated weights for policy 0, policy_version 10640 (0.0005)
[2023-07-17 00:13:11,863][271166] Fps is (10 sec: 10649.5, 60 sec: 9966.9, 300 sec: 9733.2). Total num frames: 5484544. Throughput: 0: 10043.2. Samples: 5470628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:13:11,863][271166] Avg episode reward: [(0, '702.516')]
[2023-07-17 00:13:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010712_5484544.pth...
[2023-07-17 00:13:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010120_5181440.pth
[2023-07-17 00:13:12,105][271448] Updated weights for policy 0, policy_version 10720 (0.0005)
[2023-07-17 00:13:16,129][271448] Updated weights for policy 0, policy_version 10800 (0.0006)
[2023-07-17 00:13:16,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9733.2). Total num frames: 5533696. Throughput: 0: 10070.8. Samples: 5530936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:13:16,863][271166] Avg episode reward: [(0, '710.768')]
[2023-07-17 00:13:20,260][271448] Updated weights for policy 0, policy_version 10880 (0.0006)
[2023-07-17 00:13:21,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9747.1). Total num frames: 5582848. Throughput: 0: 10094.1. Samples: 5560560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:13:21,863][271166] Avg episode reward: [(0, '707.906')]
[2023-07-17 00:13:24,287][271448] Updated weights for policy 0, policy_version 10960 (0.0005)
[2023-07-17 00:13:26,863][271166] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 9761.0). Total num frames: 5636096. Throughput: 0: 10148.1. Samples: 5622020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:13:26,864][271166] Avg episode reward: [(0, '717.069')]
[2023-07-17 00:13:26,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011008_5636096.pth...
[2023-07-17 00:13:26,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010408_5328896.pth
[2023-07-17 00:13:28,266][271448] Updated weights for policy 0, policy_version 11040 (0.0005)
[2023-07-17 00:13:31,863][271166] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 9774.9). Total num frames: 5685248. Throughput: 0: 10152.0. Samples: 5682820. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:13:31,863][271166] Avg episode reward: [(0, '722.696')]
[2023-07-17 00:13:32,331][271448] Updated weights for policy 0, policy_version 11120 (0.0005)
[2023-07-17 00:13:36,406][271448] Updated weights for policy 0, policy_version 11200 (0.0005)
[2023-07-17 00:13:36,863][271166] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9802.6). Total num frames: 5738496. Throughput: 0: 10183.1. Samples: 5713420. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:13:36,863][271166] Avg episode reward: [(0, '725.507')]
[2023-07-17 00:13:40,536][271448] Updated weights for policy 0, policy_version 11280 (0.0005)
[2023-07-17 00:13:41,863][271166] Fps is (10 sec: 10239.9, 60 sec: 10103.5, 300 sec: 9816.5). Total num frames: 5787648. Throughput: 0: 10213.2. Samples: 5772828. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:13:41,864][271166] Avg episode reward: [(0, '721.938')]
[2023-07-17 00:13:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011304_5787648.pth...
[2023-07-17 00:13:41,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000010712_5484544.pth
[2023-07-17 00:13:44,641][271448] Updated weights for policy 0, policy_version 11360 (0.0005)
[2023-07-17 00:13:46,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 9830.4). Total num frames: 5836800. Throughput: 0: 10159.6. Samples: 5832716. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:13:46,864][271166] Avg episode reward: [(0, '716.690')]
[2023-07-17 00:13:48,738][271448] Updated weights for policy 0, policy_version 11440 (0.0005)
[2023-07-17 00:13:51,863][271166] Fps is (10 sec: 9830.5, 60 sec: 10103.5, 300 sec: 9844.3). Total num frames: 5885952. Throughput: 0: 10129.6. Samples: 5862636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:13:51,863][271166] Avg episode reward: [(0, '732.971')]
[2023-07-17 00:13:51,864][271404] Saving new best policy, reward=732.971!
[2023-07-17 00:13:52,860][271448] Updated weights for policy 0, policy_version 11520 (0.0005)
[2023-07-17 00:13:56,863][271166] Fps is (10 sec: 9830.3, 60 sec: 10103.5, 300 sec: 9844.3). Total num frames: 5935104. Throughput: 0: 10045.2. Samples: 5922664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:13:56,864][271166] Avg episode reward: [(0, '716.996')]
[2023-07-17 00:13:56,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011592_5935104.pth...
[2023-07-17 00:13:56,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011008_5636096.pth
[2023-07-17 00:13:56,933][271448] Updated weights for policy 0, policy_version 11600 (0.0005)
[2023-07-17 00:14:00,953][271448] Updated weights for policy 0, policy_version 11680 (0.0005)
[2023-07-17 00:14:01,863][271166] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9872.1). Total num frames: 5988352. Throughput: 0: 10061.3. Samples: 5983696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:14:01,863][271166] Avg episode reward: [(0, '721.955')]
[2023-07-17 00:14:05,138][271448] Updated weights for policy 0, policy_version 11760 (0.0005)
[2023-07-17 00:14:06,863][271166] Fps is (10 sec: 10240.1, 60 sec: 10103.5, 300 sec: 9872.1). Total num frames: 6037504. Throughput: 0: 10052.6. Samples: 6012928. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:14:06,863][271166] Avg episode reward: [(0, '715.824')]
[2023-07-17 00:14:09,193][271448] Updated weights for policy 0, policy_version 11840 (0.0005)
[2023-07-17 00:14:11,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 9885.9). Total num frames: 6086656. Throughput: 0: 10022.6. Samples: 6073036. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:14:11,863][271166] Avg episode reward: [(0, '725.163')]
[2023-07-17 00:14:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011888_6086656.pth...
[2023-07-17 00:14:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011304_5787648.pth
[2023-07-17 00:14:13,318][271448] Updated weights for policy 0, policy_version 11920 (0.0005)
[2023-07-17 00:14:16,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 9899.8). Total num frames: 6135808. Throughput: 0: 9976.8. Samples: 6131776. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:14:16,863][271166] Avg episode reward: [(0, '725.603')]
[2023-07-17 00:14:17,468][271448] Updated weights for policy 0, policy_version 12000 (0.0005)
[2023-07-17 00:14:21,629][271448] Updated weights for policy 0, policy_version 12080 (0.0005)
[2023-07-17 00:14:21,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 9899.8). Total num frames: 6184960. Throughput: 0: 9965.6. Samples: 6161872. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:14:21,863][271166] Avg episode reward: [(0, '707.462')]
[2023-07-17 00:14:25,800][271448] Updated weights for policy 0, policy_version 12160 (0.0005)
[2023-07-17 00:14:26,863][271166] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 9899.8). Total num frames: 6234112. Throughput: 0: 9959.8. Samples: 6221020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:14:26,863][271166] Avg episode reward: [(0, '705.338')]
[2023-07-17 00:14:26,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012176_6234112.pth...
[2023-07-17 00:14:26,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011592_5935104.pth
[2023-07-17 00:14:29,852][271448] Updated weights for policy 0, policy_version 12240 (0.0005)
[2023-07-17 00:14:31,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9899.8). Total num frames: 6283264. Throughput: 0: 9968.4. Samples: 6281296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:14:31,863][271166] Avg episode reward: [(0, '724.018')]
[2023-07-17 00:14:33,945][271448] Updated weights for policy 0, policy_version 12320 (0.0005)
[2023-07-17 00:14:36,863][271166] Fps is (10 sec: 10240.1, 60 sec: 9966.9, 300 sec: 9913.7). Total num frames: 6336512. Throughput: 0: 9974.1. Samples: 6311472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:14:36,863][271166] Avg episode reward: [(0, '718.988')]
[2023-07-17 00:14:38,080][271448] Updated weights for policy 0, policy_version 12400 (0.0005)
[2023-07-17 00:14:41,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9927.6). Total num frames: 6385664. Throughput: 0: 9960.9. Samples: 6370904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:14:41,863][271166] Avg episode reward: [(0, '711.938')]
[2023-07-17 00:14:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012472_6385664.pth...
[2023-07-17 00:14:41,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000011888_6086656.pth
[2023-07-17 00:14:42,128][271448] Updated weights for policy 0, policy_version 12480 (0.0005)
[2023-07-17 00:14:46,231][271448] Updated weights for policy 0, policy_version 12560 (0.0005)
[2023-07-17 00:14:46,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9927.6). Total num frames: 6434816. Throughput: 0: 9936.1. Samples: 6430820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:14:46,863][271166] Avg episode reward: [(0, '709.665')]
[2023-07-17 00:14:50,187][271448] Updated weights for policy 0, policy_version 12640 (0.0005)
[2023-07-17 00:14:51,863][271166] Fps is (10 sec: 10240.1, 60 sec: 10035.2, 300 sec: 9941.5). Total num frames: 6488064. Throughput: 0: 9984.4. Samples: 6462224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:14:51,863][271166] Avg episode reward: [(0, '715.463')]
[2023-07-17 00:14:54,002][271448] Updated weights for policy 0, policy_version 12720 (0.0004)
[2023-07-17 00:14:56,863][271166] Fps is (10 sec: 10649.6, 60 sec: 10103.5, 300 sec: 9955.4). Total num frames: 6541312. Throughput: 0: 10068.8. Samples: 6526132. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:14:56,863][271166] Avg episode reward: [(0, '718.614')]
[2023-07-17 00:14:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012776_6541312.pth...
[2023-07-17 00:14:56,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012176_6234112.pth
[2023-07-17 00:14:57,820][271448] Updated weights for policy 0, policy_version 12800 (0.0004)
[2023-07-17 00:15:01,645][271448] Updated weights for policy 0, policy_version 12880 (0.0004)
[2023-07-17 00:15:01,863][271166] Fps is (10 sec: 10649.6, 60 sec: 10103.5, 300 sec: 9983.1). Total num frames: 6594560. Throughput: 0: 10193.1. Samples: 6590464. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:15:01,863][271166] Avg episode reward: [(0, '714.814')]
[2023-07-17 00:15:05,520][271448] Updated weights for policy 0, policy_version 12960 (0.0004)
[2023-07-17 00:15:06,863][271166] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 9997.0). Total num frames: 6647808. Throughput: 0: 10250.0. Samples: 6623124. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:15:06,863][271166] Avg episode reward: [(0, '731.042')]
[2023-07-17 00:15:09,519][271448] Updated weights for policy 0, policy_version 13040 (0.0005)
[2023-07-17 00:15:11,863][271166] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 9997.0). Total num frames: 6696960. Throughput: 0: 10295.3. Samples: 6684308. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:15:11,863][271166] Avg episode reward: [(0, '719.653')]
[2023-07-17 00:15:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013080_6696960.pth...
[2023-07-17 00:15:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012472_6385664.pth
[2023-07-17 00:15:13,645][271448] Updated weights for policy 0, policy_version 13120 (0.0005)
[2023-07-17 00:15:16,862][271166] Fps is (10 sec: 9830.5, 60 sec: 10171.7, 300 sec: 9997.0). Total num frames: 6746112. Throughput: 0: 10279.8. Samples: 6743888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:15:16,863][271166] Avg episode reward: [(0, '717.134')]
[2023-07-17 00:15:17,729][271448] Updated weights for policy 0, policy_version 13200 (0.0005)
[2023-07-17 00:15:21,831][271448] Updated weights for policy 0, policy_version 13280 (0.0005)
[2023-07-17 00:15:21,863][271166] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10010.9). Total num frames: 6799360. Throughput: 0: 10284.4. Samples: 6774272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:15:21,863][271166] Avg episode reward: [(0, '732.580')]
[2023-07-17 00:15:26,004][271448] Updated weights for policy 0, policy_version 13360 (0.0005)
[2023-07-17 00:15:26,863][271166] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10010.9). Total num frames: 6848512. Throughput: 0: 10266.1. Samples: 6832880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:15:26,863][271166] Avg episode reward: [(0, '724.108')]
[2023-07-17 00:15:26,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013376_6848512.pth...
[2023-07-17 00:15:26,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000012776_6541312.pth
[2023-07-17 00:15:29,964][271448] Updated weights for policy 0, policy_version 13440 (0.0005)
[2023-07-17 00:15:31,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10010.9). Total num frames: 6897664. Throughput: 0: 10297.1. Samples: 6894188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:15:31,863][271166] Avg episode reward: [(0, '727.430')]
[2023-07-17 00:15:34,073][271448] Updated weights for policy 0, policy_version 13520 (0.0005)
[2023-07-17 00:15:36,862][271166] Fps is (10 sec: 9830.5, 60 sec: 10171.7, 300 sec: 10010.9). Total num frames: 6946816. Throughput: 0: 10268.5. Samples: 6924308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:15:36,863][271166] Avg episode reward: [(0, '725.546')]
[2023-07-17 00:15:38,010][271448] Updated weights for policy 0, policy_version 13600 (0.0005)
[2023-07-17 00:15:41,863][271166] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10024.8). Total num frames: 7000064. Throughput: 0: 10223.3. Samples: 6986180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:15:41,863][271166] Avg episode reward: [(0, '728.248')]
[2023-07-17 00:15:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013672_7000064.pth...
[2023-07-17 00:15:41,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013080_6696960.pth
[2023-07-17 00:15:42,104][271448] Updated weights for policy 0, policy_version 13680 (0.0005)
[2023-07-17 00:15:46,131][271448] Updated weights for policy 0, policy_version 13760 (0.0005)
[2023-07-17 00:15:46,863][271166] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10024.8). Total num frames: 7049216. Throughput: 0: 10134.1. Samples: 7046500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:15:46,863][271166] Avg episode reward: [(0, '724.525')]
[2023-07-17 00:15:49,979][271448] Updated weights for policy 0, policy_version 13840 (0.0004)
[2023-07-17 00:15:51,863][271166] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10024.8). Total num frames: 7102464. Throughput: 0: 10109.7. Samples: 7078060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:15:51,863][271166] Avg episode reward: [(0, '727.414')]
[2023-07-17 00:15:53,836][271448] Updated weights for policy 0, policy_version 13920 (0.0004)
[2023-07-17 00:15:56,863][271166] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10038.7). Total num frames: 7155712. Throughput: 0: 10167.2. Samples: 7141832. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:15:56,863][271166] Avg episode reward: [(0, '716.754')]
[2023-07-17 00:15:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013976_7155712.pth...
[2023-07-17 00:15:56,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013376_6848512.pth
[2023-07-17 00:15:57,691][271448] Updated weights for policy 0, policy_version 14000 (0.0005)
[2023-07-17 00:16:01,536][271448] Updated weights for policy 0, policy_version 14080 (0.0004)
[2023-07-17 00:16:01,863][271166] Fps is (10 sec: 10649.5, 60 sec: 10240.0, 300 sec: 10052.6). Total num frames: 7208960. Throughput: 0: 10272.2. Samples: 7206140. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:16:01,863][271166] Avg episode reward: [(0, '719.660')]
[2023-07-17 00:16:05,345][271448] Updated weights for policy 0, policy_version 14160 (0.0004)
[2023-07-17 00:16:06,863][271166] Fps is (10 sec: 11059.2, 60 sec: 10308.3, 300 sec: 10080.3). Total num frames: 7266304. Throughput: 0: 10310.8. Samples: 7238260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:16:06,864][271166] Avg episode reward: [(0, '718.578')]
[2023-07-17 00:16:09,128][271448] Updated weights for policy 0, policy_version 14240 (0.0004)
[2023-07-17 00:16:11,863][271166] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10080.3). Total num frames: 7315456. Throughput: 0: 10445.9. Samples: 7302944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:16:11,864][271166] Avg episode reward: [(0, '723.376')]
[2023-07-17 00:16:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014288_7315456.pth...
[2023-07-17 00:16:11,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013672_7000064.pth
[2023-07-17 00:16:13,095][271448] Updated weights for policy 0, policy_version 14320 (0.0005)
[2023-07-17 00:16:16,863][271166] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10094.2). Total num frames: 7368704. Throughput: 0: 10459.0. Samples: 7364844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:16:16,864][271166] Avg episode reward: [(0, '726.688')]
[2023-07-17 00:16:16,993][271448] Updated weights for policy 0, policy_version 14400 (0.0004)
[2023-07-17 00:16:20,843][271448] Updated weights for policy 0, policy_version 14480 (0.0004)
[2023-07-17 00:16:21,863][271166] Fps is (10 sec: 10649.7, 60 sec: 10376.5, 300 sec: 10108.1). Total num frames: 7421952. Throughput: 0: 10512.8. Samples: 7397384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:16:21,864][271166] Avg episode reward: [(0, '727.991')]
[2023-07-17 00:16:24,724][271448] Updated weights for policy 0, policy_version 14560 (0.0004)
[2023-07-17 00:16:26,863][271166] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10122.0). Total num frames: 7475200. Throughput: 0: 10543.3. Samples: 7460628. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-17 00:16:26,864][271166] Avg episode reward: [(0, '718.678')]
[2023-07-17 00:16:26,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014600_7475200.pth...
[2023-07-17 00:16:26,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000013976_7155712.pth
[2023-07-17 00:16:28,508][271448] Updated weights for policy 0, policy_version 14640 (0.0004)
[2023-07-17 00:16:31,863][271166] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10135.9). Total num frames: 7528448. Throughput: 0: 10619.2. Samples: 7524364. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-17 00:16:31,863][271166] Avg episode reward: [(0, '732.573')]
[2023-07-17 00:16:32,483][271448] Updated weights for policy 0, policy_version 14720 (0.0005)
[2023-07-17 00:16:36,328][271448] Updated weights for policy 0, policy_version 14800 (0.0004)
[2023-07-17 00:16:36,863][271166] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10149.7). Total num frames: 7581696. Throughput: 0: 10608.6. Samples: 7555448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:16:36,863][271166] Avg episode reward: [(0, '727.641')]
[2023-07-17 00:16:40,179][271448] Updated weights for policy 0, policy_version 14880 (0.0004)
[2023-07-17 00:16:41,863][271166] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10149.7). Total num frames: 7634944. Throughput: 0: 10609.9. Samples: 7619276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:16:41,863][271166] Avg episode reward: [(0, '722.105')]
[2023-07-17 00:16:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014912_7634944.pth...
[2023-07-17 00:16:41,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014288_7315456.pth
[2023-07-17 00:16:44,021][271448] Updated weights for policy 0, policy_version 14960 (0.0004)
[2023-07-17 00:16:46,862][271166] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10163.6). Total num frames: 7688192. Throughput: 0: 10613.1. Samples: 7683728. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:16:46,863][271166] Avg episode reward: [(0, '736.443')]
[2023-07-17 00:16:46,863][271404] Saving new best policy, reward=736.443!
[2023-07-17 00:16:47,901][271448] Updated weights for policy 0, policy_version 15040 (0.0005)
[2023-07-17 00:16:51,812][271448] Updated weights for policy 0, policy_version 15120 (0.0005)
[2023-07-17 00:16:51,863][271166] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10177.5). Total num frames: 7741440. Throughput: 0: 10590.7. Samples: 7714840. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-17 00:16:51,863][271166] Avg episode reward: [(0, '726.769')]
[2023-07-17 00:16:55,601][271448] Updated weights for policy 0, policy_version 15200 (0.0004)
[2023-07-17 00:16:56,863][271166] Fps is (10 sec: 10649.4, 60 sec: 10649.6, 300 sec: 10191.4). Total num frames: 7794688. Throughput: 0: 10567.2. Samples: 7778468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:16:56,863][271166] Avg episode reward: [(0, '733.046')]
[2023-07-17 00:16:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015224_7794688.pth...
[2023-07-17 00:16:56,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014600_7475200.pth
[2023-07-17 00:16:59,471][271448] Updated weights for policy 0, policy_version 15280 (0.0004)
[2023-07-17 00:17:01,863][271166] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10205.3). Total num frames: 7847936. Throughput: 0: 10610.7. Samples: 7842324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:17:01,863][271166] Avg episode reward: [(0, '723.561')]
[2023-07-17 00:17:03,369][271448] Updated weights for policy 0, policy_version 15360 (0.0004)
[2023-07-17 00:17:06,863][271166] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10205.3). Total num frames: 7897088. Throughput: 0: 10572.7. Samples: 7873156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:17:06,863][271166] Avg episode reward: [(0, '721.075')]
[2023-07-17 00:17:07,265][271448] Updated weights for policy 0, policy_version 15440 (0.0004)
[2023-07-17 00:17:11,241][271448] Updated weights for policy 0, policy_version 15520 (0.0004)
[2023-07-17 00:17:11,863][271166] Fps is (10 sec: 10239.9, 60 sec: 10581.3, 300 sec: 10219.2). Total num frames: 7950336. Throughput: 0: 10559.0. Samples: 7935784. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:17:11,863][271166] Avg episode reward: [(0, '727.339')]
[2023-07-17 00:17:11,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015528_7950336.pth...
[2023-07-17 00:17:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000014912_7634944.pth
[2023-07-17 00:17:15,182][271448] Updated weights for policy 0, policy_version 15600 (0.0004)
[2023-07-17 00:17:16,863][271166] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10233.1). Total num frames: 8003584. Throughput: 0: 10529.5. Samples: 7998192. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-17 00:17:16,863][271166] Avg episode reward: [(0, '724.541')]
[2023-07-17 00:17:19,311][271448] Updated weights for policy 0, policy_version 15680 (0.0005)
[2023-07-17 00:17:21,863][271166] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10233.1). Total num frames: 8052736. Throughput: 0: 10504.7. Samples: 8028160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:17:21,863][271166] Avg episode reward: [(0, '720.713')]
[2023-07-17 00:17:23,411][271448] Updated weights for policy 0, policy_version 15760 (0.0005)
[2023-07-17 00:17:26,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10444.8, 300 sec: 10246.9). Total num frames: 8101888. Throughput: 0: 10412.2. Samples: 8087824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:17:26,863][271166] Avg episode reward: [(0, '728.258')]
[2023-07-17 00:17:26,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015824_8101888.pth...
[2023-07-17 00:17:26,867][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015224_7794688.pth
[2023-07-17 00:17:27,536][271448] Updated weights for policy 0, policy_version 15840 (0.0005)
[2023-07-17 00:17:31,603][271448] Updated weights for policy 0, policy_version 15920 (0.0005)
[2023-07-17 00:17:31,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10246.9). Total num frames: 8151040. Throughput: 0: 10304.5. Samples: 8147432. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:17:31,863][271166] Avg episode reward: [(0, '719.874')]
[2023-07-17 00:17:35,683][271448] Updated weights for policy 0, policy_version 16000 (0.0005)
[2023-07-17 00:17:36,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10233.1). Total num frames: 8200192. Throughput: 0: 10284.4. Samples: 8177640. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:17:36,863][271166] Avg episode reward: [(0, '718.888')]
[2023-07-17 00:17:39,860][271448] Updated weights for policy 0, policy_version 16080 (0.0005)
[2023-07-17 00:17:41,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10233.1). Total num frames: 8249344. Throughput: 0: 10192.3. Samples: 8237120. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:17:41,863][271166] Avg episode reward: [(0, '724.252')]
[2023-07-17 00:17:41,865][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016112_8249344.pth...
[2023-07-17 00:17:41,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015528_7950336.pth
[2023-07-17 00:17:43,925][271448] Updated weights for policy 0, policy_version 16160 (0.0005)
[2023-07-17 00:17:46,863][271166] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10246.9). Total num frames: 8302592. Throughput: 0: 10137.4. Samples: 8298508. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:17:46,863][271166] Avg episode reward: [(0, '728.808')]
[2023-07-17 00:17:47,885][271448] Updated weights for policy 0, policy_version 16240 (0.0005)
[2023-07-17 00:17:51,863][271166] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10246.9). Total num frames: 8351744. Throughput: 0: 10147.5. Samples: 8329796. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-17 00:17:51,863][271166] Avg episode reward: [(0, '728.225')]
[2023-07-17 00:17:51,938][271448] Updated weights for policy 0, policy_version 16320 (0.0005)
[2023-07-17 00:17:56,140][271448] Updated weights for policy 0, policy_version 16400 (0.0005)
[2023-07-17 00:17:56,862][271166] Fps is (10 sec: 9830.5, 60 sec: 10103.5, 300 sec: 10246.9). Total num frames: 8400896. Throughput: 0: 10062.8. Samples: 8388608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:17:56,863][271166] Avg episode reward: [(0, '726.958')]
[2023-07-17 00:17:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016408_8400896.pth...
[2023-07-17 00:17:56,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000015824_8101888.pth
[2023-07-17 00:18:00,383][271448] Updated weights for policy 0, policy_version 16480 (0.0005)
[2023-07-17 00:18:01,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10233.1). Total num frames: 8450048. Throughput: 0: 9956.6. Samples: 8446240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:01,863][271166] Avg episode reward: [(0, '730.278')]
[2023-07-17 00:18:04,565][271448] Updated weights for policy 0, policy_version 16560 (0.0005)
[2023-07-17 00:18:06,863][271166] Fps is (10 sec: 9830.3, 60 sec: 10035.2, 300 sec: 10219.2). Total num frames: 8499200. Throughput: 0: 9950.7. Samples: 8475940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:06,863][271166] Avg episode reward: [(0, '729.596')]
[2023-07-17 00:18:08,567][271448] Updated weights for policy 0, policy_version 16640 (0.0005)
[2023-07-17 00:18:11,863][271166] Fps is (10 sec: 10239.9, 60 sec: 10035.2, 300 sec: 10233.1). Total num frames: 8552448. Throughput: 0: 9992.0. Samples: 8537464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:11,863][271166] Avg episode reward: [(0, '730.019')]
[2023-07-17 00:18:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016704_8552448.pth...
[2023-07-17 00:18:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016112_8249344.pth
[2023-07-17 00:18:12,506][271448] Updated weights for policy 0, policy_version 16720 (0.0004)
[2023-07-17 00:18:16,525][271448] Updated weights for policy 0, policy_version 16800 (0.0005)
[2023-07-17 00:18:16,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 10233.1). Total num frames: 8601600. Throughput: 0: 10031.8. Samples: 8598864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:16,863][271166] Avg episode reward: [(0, '726.656')]
[2023-07-17 00:18:20,606][271448] Updated weights for policy 0, policy_version 16880 (0.0005)
[2023-07-17 00:18:21,863][271166] Fps is (10 sec: 10240.1, 60 sec: 10035.2, 300 sec: 10233.1). Total num frames: 8654848. Throughput: 0: 10015.2. Samples: 8628324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:21,863][271166] Avg episode reward: [(0, '732.308')]
[2023-07-17 00:18:24,574][271448] Updated weights for policy 0, policy_version 16960 (0.0004)
[2023-07-17 00:18:26,863][271166] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10233.1). Total num frames: 8704000. Throughput: 0: 10086.1. Samples: 8690996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:26,863][271166] Avg episode reward: [(0, '729.736')]
[2023-07-17 00:18:26,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017000_8704000.pth...
[2023-07-17 00:18:26,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016408_8400896.pth
[2023-07-17 00:18:28,620][271448] Updated weights for policy 0, policy_version 17040 (0.0005)
[2023-07-17 00:18:31,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10219.2). Total num frames: 8753152. Throughput: 0: 10027.5. Samples: 8749744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:31,863][271166] Avg episode reward: [(0, '732.003')]
[2023-07-17 00:18:32,910][271448] Updated weights for policy 0, policy_version 17120 (0.0005)
[2023-07-17 00:18:36,863][271166] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10219.2). Total num frames: 8802304. Throughput: 0: 9973.2. Samples: 8778588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:36,863][271166] Avg episode reward: [(0, '734.419')]
[2023-07-17 00:18:36,973][271448] Updated weights for policy 0, policy_version 17200 (0.0005)
[2023-07-17 00:18:40,954][271448] Updated weights for policy 0, policy_version 17280 (0.0004)
[2023-07-17 00:18:41,863][271166] Fps is (10 sec: 10239.9, 60 sec: 10103.4, 300 sec: 10233.1). Total num frames: 8855552. Throughput: 0: 10035.1. Samples: 8840188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:41,863][271166] Avg episode reward: [(0, '730.859')]
[2023-07-17 00:18:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017296_8855552.pth...
[2023-07-17 00:18:41,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000016704_8552448.pth
[2023-07-17 00:18:44,989][271448] Updated weights for policy 0, policy_version 17360 (0.0004)
[2023-07-17 00:18:46,863][271166] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10233.1). Total num frames: 8904704. Throughput: 0: 10103.3. Samples: 8900888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:46,863][271166] Avg episode reward: [(0, '728.014')]
[2023-07-17 00:18:49,183][271448] Updated weights for policy 0, policy_version 17440 (0.0005)
[2023-07-17 00:18:51,863][271166] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10233.1). Total num frames: 8953856. Throughput: 0: 10090.6. Samples: 8930016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:51,863][271166] Avg episode reward: [(0, '729.318')]
[2023-07-17 00:18:53,496][271448] Updated weights for policy 0, policy_version 17520 (0.0005)
[2023-07-17 00:18:56,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10219.2). Total num frames: 9003008. Throughput: 0: 9994.6. Samples: 8987220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:18:56,863][271166] Avg episode reward: [(0, '740.371')]
[2023-07-17 00:18:56,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017584_9003008.pth...
[2023-07-17 00:18:56,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017000_8704000.pth
[2023-07-17 00:18:56,869][271404] Saving new best policy, reward=740.371!
[2023-07-17 00:18:57,625][271448] Updated weights for policy 0, policy_version 17600 (0.0005)
[2023-07-17 00:19:01,803][271448] Updated weights for policy 0, policy_version 17680 (0.0005)
[2023-07-17 00:19:01,863][271166] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10219.2). Total num frames: 9052160. Throughput: 0: 9965.3. Samples: 9047300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:01,863][271166] Avg episode reward: [(0, '732.392')]
[2023-07-17 00:19:06,008][271448] Updated weights for policy 0, policy_version 17760 (0.0005)
[2023-07-17 00:19:06,863][271166] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10219.2). Total num frames: 9101312. Throughput: 0: 9964.7. Samples: 9076736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:06,863][271166] Avg episode reward: [(0, '735.936')]
[2023-07-17 00:19:10,104][271448] Updated weights for policy 0, policy_version 17840 (0.0005)
[2023-07-17 00:19:11,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10219.2). Total num frames: 9150464. Throughput: 0: 9881.8. Samples: 9135676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:11,863][271166] Avg episode reward: [(0, '728.815')]
[2023-07-17 00:19:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017872_9150464.pth...
[2023-07-17 00:19:11,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017296_8855552.pth
[2023-07-17 00:19:14,371][271448] Updated weights for policy 0, policy_version 17920 (0.0005)
[2023-07-17 00:19:16,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9898.7, 300 sec: 10205.3). Total num frames: 9195520. Throughput: 0: 9854.4. Samples: 9193192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:16,863][271166] Avg episode reward: [(0, '730.324')]
[2023-07-17 00:19:18,463][271448] Updated weights for policy 0, policy_version 18000 (0.0005)
[2023-07-17 00:19:21,863][271166] Fps is (10 sec: 9830.5, 60 sec: 9898.7, 300 sec: 10219.2). Total num frames: 9248768. Throughput: 0: 9902.6. Samples: 9224204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:21,863][271166] Avg episode reward: [(0, '729.198')]
[2023-07-17 00:19:22,724][271448] Updated weights for policy 0, policy_version 18080 (0.0005)
[2023-07-17 00:19:26,863][271166] Fps is (10 sec: 9830.2, 60 sec: 9830.4, 300 sec: 10205.3). Total num frames: 9293824. Throughput: 0: 9809.1. Samples: 9281600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:26,863][271166] Avg episode reward: [(0, '729.965')]
[2023-07-17 00:19:26,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018152_9293824.pth...
[2023-07-17 00:19:26,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017584_9003008.pth
[2023-07-17 00:19:27,001][271448] Updated weights for policy 0, policy_version 18160 (0.0005)
[2023-07-17 00:19:31,201][271448] Updated weights for policy 0, policy_version 18240 (0.0005)
[2023-07-17 00:19:31,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9830.4, 300 sec: 10191.4). Total num frames: 9342976. Throughput: 0: 9744.3. Samples: 9339380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:31,863][271166] Avg episode reward: [(0, '732.708')]
[2023-07-17 00:19:35,475][271448] Updated weights for policy 0, policy_version 18320 (0.0005)
[2023-07-17 00:19:36,863][271166] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 10191.4). Total num frames: 9392128. Throughput: 0: 9735.6. Samples: 9368116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:36,863][271166] Avg episode reward: [(0, '734.083')]
[2023-07-17 00:19:39,702][271448] Updated weights for policy 0, policy_version 18400 (0.0005)
[2023-07-17 00:19:41,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 10191.4). Total num frames: 9441280. Throughput: 0: 9752.1. Samples: 9426064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:41,863][271166] Avg episode reward: [(0, '735.448')]
[2023-07-17 00:19:41,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018440_9441280.pth...
[2023-07-17 00:19:41,868][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000017872_9150464.pth
[2023-07-17 00:19:44,036][271448] Updated weights for policy 0, policy_version 18480 (0.0005)
[2023-07-17 00:19:46,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 10163.6). Total num frames: 9486336. Throughput: 0: 9681.3. Samples: 9482960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:46,864][271166] Avg episode reward: [(0, '738.966')]
[2023-07-17 00:19:48,327][271448] Updated weights for policy 0, policy_version 18560 (0.0005)
[2023-07-17 00:19:51,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 10149.8). Total num frames: 9535488. Throughput: 0: 9662.2. Samples: 9511536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:51,863][271166] Avg episode reward: [(0, '736.547')]
[2023-07-17 00:19:52,514][271448] Updated weights for policy 0, policy_version 18640 (0.0005)
[2023-07-17 00:19:56,720][271448] Updated weights for policy 0, policy_version 18720 (0.0005)
[2023-07-17 00:19:56,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 10135.9). Total num frames: 9584640. Throughput: 0: 9664.9. Samples: 9570596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:19:56,864][271166] Avg episode reward: [(0, '740.304')]
[2023-07-17 00:19:56,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018720_9584640.pth...
[2023-07-17 00:19:56,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018152_9293824.pth
[2023-07-17 00:20:01,047][271448] Updated weights for policy 0, policy_version 18800 (0.0005)
[2023-07-17 00:20:01,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 10108.1). Total num frames: 9629696. Throughput: 0: 9660.2. Samples: 9627900. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-17 00:20:01,877][271166] Avg episode reward: [(0, '741.115')]
[2023-07-17 00:20:01,901][271404] Saving new best policy, reward=741.115!
[2023-07-17 00:20:05,152][271448] Updated weights for policy 0, policy_version 18880 (0.0004)
[2023-07-17 00:20:06,863][271166] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 10122.0). Total num frames: 9682944. Throughput: 0: 9631.6. Samples: 9657624. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-17 00:20:06,863][271166] Avg episode reward: [(0, '733.855')]
[2023-07-17 00:20:09,174][271448] Updated weights for policy 0, policy_version 18960 (0.0004)
[2023-07-17 00:20:11,863][271166] Fps is (10 sec: 10240.0, 60 sec: 9693.9, 300 sec: 10122.0). Total num frames: 9732096. Throughput: 0: 9714.5. Samples: 9718752. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-17 00:20:11,863][271166] Avg episode reward: [(0, '726.833')]
[2023-07-17 00:20:11,866][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019008_9732096.pth...
[2023-07-17 00:20:11,869][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018440_9441280.pth
[2023-07-17 00:20:13,251][271448] Updated weights for policy 0, policy_version 19040 (0.0005)
[2023-07-17 00:20:16,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 10108.1). Total num frames: 9781248. Throughput: 0: 9728.3. Samples: 9777152. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-17 00:20:16,864][271166] Avg episode reward: [(0, '731.322')]
[2023-07-17 00:20:17,580][271448] Updated weights for policy 0, policy_version 19120 (0.0005)
[2023-07-17 00:20:21,863][271166] Fps is (10 sec: 9420.9, 60 sec: 9625.6, 300 sec: 10094.2). Total num frames: 9826304. Throughput: 0: 9726.1. Samples: 9805788. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-17 00:20:21,883][271448] Updated weights for policy 0, policy_version 19200 (0.0005)
[2023-07-17 00:20:21,917][271166] Avg episode reward: [(0, '736.827')]
[2023-07-17 00:20:26,241][271448] Updated weights for policy 0, policy_version 19280 (0.0005)
[2023-07-17 00:20:26,863][271166] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 10094.2). Total num frames: 9875456. Throughput: 0: 9700.1. Samples: 9862568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:20:26,863][271166] Avg episode reward: [(0, '741.765')]
[2023-07-17 00:20:26,867][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019288_9875456.pth...
[2023-07-17 00:20:26,870][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000018720_9584640.pth
[2023-07-17 00:20:26,870][271404] Saving new best policy, reward=741.765!
[2023-07-17 00:20:30,574][271448] Updated weights for policy 0, policy_version 19360 (0.0005)
[2023-07-17 00:20:31,863][271166] Fps is (10 sec: 9420.7, 60 sec: 9625.6, 300 sec: 10080.3). Total num frames: 9920512. Throughput: 0: 9689.6. Samples: 9918992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:20:31,863][271166] Avg episode reward: [(0, '745.144')]
[2023-07-17 00:20:31,872][271404] Saving new best policy, reward=745.144!
[2023-07-17 00:20:34,725][271448] Updated weights for policy 0, policy_version 19440 (0.0005)
[2023-07-17 00:20:36,863][271166] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 10080.3). Total num frames: 9973760. Throughput: 0: 9712.5. Samples: 9948600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-17 00:20:36,863][271166] Avg episode reward: [(0, '745.284')]
[2023-07-17 00:20:36,863][271404] Saving new best policy, reward=745.284!
[2023-07-17 00:20:38,779][271448] Updated weights for policy 0, policy_version 19520 (0.0004)
[2023-07-17 00:20:39,984][271404] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000
[2023-07-17 00:20:39,984][271454] Stopping RolloutWorker_w5...
[2023-07-17 00:20:39,984][271450] Stopping RolloutWorker_w1...
[2023-07-17 00:20:39,984][271453] Stopping RolloutWorker_w4...
[2023-07-17 00:20:39,984][271452] Stopping RolloutWorker_w3...
[2023-07-17 00:20:39,984][271451] Stopping RolloutWorker_w2...
[2023-07-17 00:20:39,985][271455] Stopping RolloutWorker_w6...
[2023-07-17 00:20:39,985][271518] Stopping RolloutWorker_w7...
[2023-07-17 00:20:39,985][271454] Loop rollout_proc5_evt_loop terminating...
[2023-07-17 00:20:39,985][271450] Loop rollout_proc1_evt_loop terminating...
[2023-07-17 00:20:39,985][271453] Loop rollout_proc4_evt_loop terminating...
[2023-07-17 00:20:39,985][271452] Loop rollout_proc3_evt_loop terminating...
[2023-07-17 00:20:39,985][271449] Stopping RolloutWorker_w0...
[2023-07-17 00:20:39,985][271451] Loop rollout_proc2_evt_loop terminating...
[2023-07-17 00:20:39,985][271455] Loop rollout_proc6_evt_loop terminating...
[2023-07-17 00:20:39,985][271518] Loop rollout_proc7_evt_loop terminating...
[2023-07-17 00:20:39,985][271166] Component RolloutWorker_w4 stopped!
[2023-07-17 00:20:39,985][271449] Loop rollout_proc0_evt_loop terminating...
[2023-07-17 00:20:39,985][271166] Component RolloutWorker_w1 stopped!
[2023-07-17 00:20:39,985][271404] Stopping Batcher_0...
[2023-07-17 00:20:39,985][271166] Component RolloutWorker_w5 stopped!
[2023-07-17 00:20:39,985][271404] Loop batcher_evt_loop terminating...
[2023-07-17 00:20:39,986][271166] Component RolloutWorker_w3 stopped!
[2023-07-17 00:20:39,986][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019544_10006528.pth...
[2023-07-17 00:20:39,986][271166] Component RolloutWorker_w2 stopped!
[2023-07-17 00:20:39,986][271166] Component RolloutWorker_w7 stopped!
[2023-07-17 00:20:39,986][271166] Component RolloutWorker_w6 stopped!
[2023-07-17 00:20:39,986][271166] Component RolloutWorker_w0 stopped!
[2023-07-17 00:20:39,986][271166] Component Batcher_0 stopped!
[2023-07-17 00:20:39,988][271404] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019008_9732096.pth
[2023-07-17 00:20:39,989][271404] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/hand-insert-v2/checkpoint_p0/checkpoint_000019544_10006528.pth...
[2023-07-17 00:20:39,991][271404] Stopping LearnerWorker_p0...
[2023-07-17 00:20:39,991][271404] Loop learner_proc0_evt_loop terminating...
[2023-07-17 00:20:39,991][271166] Component LearnerWorker_p0 stopped!
[2023-07-17 00:20:40,049][271448] Weights refcount: 2 0
[2023-07-17 00:20:40,050][271448] Stopping InferenceWorker_p0-w0...
[2023-07-17 00:20:40,050][271448] Loop inference_proc0-0_evt_loop terminating...
[2023-07-17 00:20:40,050][271166] Component InferenceWorker_p0-w0 stopped!
[2023-07-17 00:20:40,051][271166] Waiting for process learner_proc0 to stop...
[2023-07-17 00:20:40,577][271166] Waiting for process inference_proc0-0 to join...
[2023-07-17 00:20:40,601][271166] Waiting for process rollout_proc0 to join...
[2023-07-17 00:20:40,601][271166] Waiting for process rollout_proc1 to join...
[2023-07-17 00:20:40,601][271166] Waiting for process rollout_proc2 to join...
[2023-07-17 00:20:40,601][271166] Waiting for process rollout_proc3 to join...
[2023-07-17 00:20:40,602][271166] Waiting for process rollout_proc4 to join...
[2023-07-17 00:20:40,602][271166] Waiting for process rollout_proc5 to join...
[2023-07-17 00:20:40,602][271166] Waiting for process rollout_proc6 to join...
[2023-07-17 00:20:40,602][271166] Waiting for process rollout_proc7 to join...
[2023-07-17 00:20:40,602][271166] Batcher 0 profile tree view:
batching: 1.8725, releasing_batches: 1.6566
[2023-07-17 00:20:40,602][271166] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0051
wait_policy_total: 376.4697
update_model: 12.5152
weight_update: 0.0005
one_step: 0.0005
handle_policy_step: 558.1795
deserialize: 23.3477, stack: 6.1745, obs_to_device_normalize: 101.0868, forward: 277.4123, send_messages: 38.3580
prepare_outputs: 63.5173
to_cpu: 9.6384
[2023-07-17 00:20:40,603][271166] Learner 0 profile tree view:
misc: 0.0118, prepare_batch: 10.5958
train: 109.4913
epoch_init: 0.0398, minibatch_init: 1.4902, losses_postprocess: 1.4396, kl_divergence: 0.4996, after_optimizer: 0.7124
calculate_losses: 46.8726
losses_init: 0.0404, forward_head: 18.5056, bptt_initial: 0.1608, bptt: 0.1493, tail: 13.1222, advantages_returns: 0.9980, losses: 12.2335
update: 56.5773
clip: 6.7124
[2023-07-17 00:20:40,603][271166] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.2717, enqueue_policy_requests: 12.9039, env_step: 728.9594, overhead: 19.6438, complete_rollouts: 0.3345
save_policy_outputs: 38.6970
split_output_tensors: 13.3877
[2023-07-17 00:20:40,603][271166] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.3083, enqueue_policy_requests: 12.7270, env_step: 729.4476, overhead: 19.9300, complete_rollouts: 0.3217
save_policy_outputs: 37.7004
split_output_tensors: 13.0048
[2023-07-17 00:20:40,603][271166] Loop Runner_EvtLoop terminating...
[2023-07-17 00:20:40,603][271166] Runner profile tree view:
main_loop: 1016.7253
[2023-07-17 00:20:40,603][271166] Collected {0: 10006528}, FPS: 9841.9